system

Abstract

We provide the system. [Solution] Means for recording business data in sales operations, A means for analyzing recorded business data and generating evaluations corresponding to business activities, A means of presenting a training plan based on the evaluation results, A means of managing schedules based on business data and evaluation results, Methods for collecting customer feedback and performing sentiment analysis, A system that includes a means of evaluating the interpersonal skills of sales staff based on the results of emotional analysis.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There are problems that the skill evaluation and training of sales staff are not appropriately carried out, resulting in a decrease in motivation and turnover in a short period. Furthermore, since there is a lack of an educational program that effectively utilizes the work performance and customer feedback of staff, there is a problem that the operational efficiency of the entire store decreases.

Means for Solving the Problems

[0005] This invention provides a system that records operational data in sales activities, analyzes it, and generates evaluations tailored to individual work activities. Furthermore, it aims to improve the skills of sales staff by suggesting appropriate training plans based on these evaluations. In addition, it collects customer feedback and performs sentiment analysis to evaluate staff interpersonal skills in more detail and solicit feedback. This makes it possible to improve the motivation of individual staff and optimize store operations.

[0006] "Business data" refers to information generated by sales staff in their daily work, such as the number of sales, customer service time, and customer satisfaction.

[0007] "Analysis" refers to the data processing process used to evaluate the performance of each sales staff member, utilizing recorded business data and customer feedback.

[0008] "Evaluation" is the activity of measuring the skills and performance of sales staff based on the results of analysis and assigning them a relative position.

[0009] A "training plan" is a specific educational program or training guide proposed based on evaluations, with the aim of improving staff skills.

[0010] "Schedule management" refers to a system function that organizes and adjusts staff work plans, aiming to improve work efficiency.

[0011] "Sentiment analysis" is a method of measuring customer emotions and satisfaction by analyzing customer feedback data using natural language processing technology.

[0012] "Interpersonal skills" refer to the ability of staff to communicate smoothly with customers, and are a factor that greatly influences customer satisfaction. [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] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0016] In the following embodiments, the numbered 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 numbered 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 numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered 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), and the like.

[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 is a system for streamlining the skill evaluation and training of sales staff. This system utilizes an AI agent to analyze staff work data, generate skill evaluations, and propose training plans.

[0035] The server collects daily work data entered by users (sales staff) using terminals and stores it in a central database. This data entry includes sales performance, customer interaction time, and customer feedback. This information is essential for evaluating the current performance of the staff.

[0036] The server uses the collected data to analyze staff performance through an AI agent. The analysis yields a skill evaluation for each staff member, generating a relative ranking. This ranking differs for each staff member, based on factors such as work efficiency and customer service skills.

[0037] The terminal visually displays the evaluation results received from the server to the user. After understanding the evaluation, the user reviews the training plan proposed by the AI ​​agent. This training plan includes e-learning materials and information on in-house training aimed at improving specific skills.

[0038] Furthermore, customer feedback is processed on a server using sentiment analysis tools. Sentiment analysis extracts customer emotions from text data and uses this information to evaluate the interpersonal skills of sales staff. This allows users to clearly understand their strengths and areas for improvement.

[0039] As a concrete example, suppose a user has short customer service times and receives low ratings from feedback. Based on this data, the server's AI agent analyzes the information and presents the user with a training plan aimed at improving their interpersonal skills. In this way, an appropriate training approach based on individual feedback can improve the user's skills and improve overall store performance.

[0040] This system not only supports the evaluation and training of sales staff, but also serves as a valuable tool for improving the overall operational efficiency of the store.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] After completing their daily tasks, users input business data, including sales figures, customer service time, and customer feedback, using a terminal. The terminal automatically transmits the entered data to the server.

[0044] Step 2:

[0045] The server stores the received business data in a database. Based on the stored data, an AI agent is used to begin evaluating staff performance. The AI ​​agent analyzes each data point and quantifies sales performance and the quality of customer service.

[0046] Step 3:

[0047] The server generates skill evaluation scores for each staff member based on the data analysis results. These scores include indicators such as sales efficiency, customer satisfaction, and communication skills. These indicators determine the relative positioning of each staff member.

[0048] Step 4:

[0049] The server sends the generated skill assessment score to the terminal. The terminal visually displays the detailed assessment results to the user. The user reviews the displayed information and checks their work performance.

[0050] Step 5:

[0051] The AI ​​agent creates an appropriate training plan based on the evaluation results. The server sends this training plan to the terminal. The terminal displays the training plan to the user, including specific improvement actions. For example, it may suggest learning materials aimed at improving specific skills or notify the user of available training dates.

[0052] Step 6:

[0053] The server performs sentiment analysis on collected customer feedback and incorporates the results into the user's interpersonal skills evaluation. It clarifies customer emotions and intentions, and identifies areas for improvement in customer service.

[0054] Step 7:

[0055] Based on all evaluations and feedback, the server identifies each user's growth trend and supports goal setting for the next evaluation period. This allows individual staff members to develop plans for improving their own performance.

[0056] (Example 1)

[0057] 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."

[0058] In modern sales operations, accurately evaluating the individual performance of sales staff and developing effective training plans is challenging. Furthermore, while detailed performance reports are essential for improving employee performance and efficient store operations, this also represents a significant burden. Additionally, properly analyzing customer feedback and utilizing it to improve interpersonal skills is crucial.

[0059] 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.

[0060] In this invention, the server includes means for recording business information in sales operations, means for analyzing the recorded business information and generating evaluations corresponding to business activities, and means for collecting customer feedback and performing sentiment analysis. This enables precise evaluation of sales employee performance, automation of effective training plan development, and improvement of interpersonal skills evaluation based on customer feedback.

[0061] "Sales operations" refers to a series of activities and processes carried out with the aim of providing goods or services.

[0062] "Business information" refers to all data and records related to sales, including sales performance, customer service status, and feedback.

[0063] "Analysis" refers to the process of processing and handling collected information and data to gain useful insights.

[0064] "Evaluation" is the act of measuring the performance of individuals or processes based on specific criteria and determining their value or effectiveness.

[0065] A "development plan" refers to a set of learning and growth steps and policies designed to improve the capabilities of individual employees.

[0066] "Timetable management" refers to the process of adjusting and managing time to ensure that work and activities proceed efficiently and according to plan.

[0067] "Sentiment analysis" is a technique that reads emotions from information such as text data, and is used to understand customer opinions and feedback.

[0068] "Interpersonal skills" refer to the skills and attitudes necessary for communicating efficiently and effectively with others.

[0069] This invention is a system for automating employee skill evaluation and training planning in sales operations. This system utilizes multiple basic hardware and software components to efficiently manage and analyze sales-related business information.

[0070] The server collects business information such as sales performance, customer service time, and feedback entered by users through their terminals, and stores it in a central database. This server uses a cloud-based database management system (DBMS) to perform high-speed and secure data storage.

[0071] Next, the server analyzes the collected business information using a generative AI model. This analysis process utilizes machine learning algorithms to evaluate the skills and performance of individual employees. The analysis results include performance trend analysis and detailed evaluations of specific skills.

[0072] Furthermore, customer feedback is processed through a sentiment analysis tool. This tool uses natural language processing (NLP) techniques to analyze text data and extract customer emotions. The specific software used for this process utilizes open-source NLP libraries.

[0073] The terminal provides visual feedback to the user based on analysis results received from the server. The evaluation results are displayed through a user-friendly interface. Furthermore, the generated training plan includes suggestions for e-learning modules and in-house training.

[0074] For example, if a user is evaluated as having short customer service times, the server uses an AI agent to further analyze the data and present the user with an appropriate training plan. This training plan includes details of online courses and on-the-job training to improve interpersonal skills.

[0075] An example of a prompt is: "To evaluate sales staff, please have the AI ​​agent analyze sales performance, customer interaction time, and feedback data from the past month, and propose a training plan aimed at improving specific skills." This prompt represents a specific analysis request to the AI ​​model.

[0076] In this way, this system can improve overall operational efficiency by analyzing the performance of sales staff in detail and providing individualized training support.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server receives business information such as sales performance, customer service time, and customer feedback entered by users through terminals. The received data is stored in a central database in real time. The specific actions performed here are to validate the entered business information and record it in the database according to the format. The output is a well-organized dataset of business information.

[0080] Step 2:

[0081] The server retrieves business information stored in a central database and performs analysis using a generated AI model. The inputs required for this analysis include sales performance and customer interaction history. Based on this input data, the server performs trend analysis and anomaly detection to generate performance evaluations for each employee. Specifically, it executes machine learning algorithms to calculate evaluation scores and ranks. The output is performance evaluation data for each employee.

[0082] Step 3:

[0083] The server generates a training plan using the analysis results. The inputs for generating this training plan are each employee's performance evaluation and the sentiment analysis results of customer feedback. The server integrates this data to generate a training plan aimed at improving specific skills. Specifically, it assembles a list of e-learning materials and training courses that address the user's weaknesses. The output is an individual training plan.

[0084] Step 4:

[0085] The terminal presents the user with performance evaluations and training plans provided by the server. This process requires incoming data as input to visually display both evaluation results and training plans. Based on this data, the terminal displays the information in a user-friendly graphical interface. Specifically, it displays data on a dashboard and supports the user in viewing detailed information. The output consists of evaluation and training information that the user can visually verify.

[0086] Step 5:

[0087] Based on the evaluation results and training plan displayed on the device, users take action to improve their skills. User input includes providing feedback and deciding whether to participate in training. Users utilize this information to participate in educational or training plans to address their weaknesses. Specific actions include registering for online courses and scheduling training sessions. Outputs include improved skills and adjusted work performance.

[0088] (Application Example 1)

[0089] 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."

[0090] In modern retail, improving the skills of sales staff is a crucial factor directly impacting customer satisfaction and sales. However, individually evaluating each staff member and proposing efficient training plans is time-consuming and costly. In addition, systems that can provide solutions for improving interpersonal skills using customer feedback are not yet widespread. This presents a challenge in maximizing the potential of sales staff.

[0091] 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.

[0092] In this invention, the server includes a device for recording business-related data, a device for analyzing the recorded data and generating an evaluation based on activity efficiency, and a device for presenting a learning plan based on the evaluation results. This makes it possible to efficiently evaluate the skills of sales staff and automatically propose individually optimized training plans. Furthermore, real-time business support provides an environment in which sales staff can immediately implement improvement measures.

[0093] "Business-related data" refers to information related to sales activities, including sales performance, customer service time, and customer feedback.

[0094] A "device" is a combination of hardware or software designed to perform a specific function.

[0095] "Analysis" is the process of examining collected data in detail and extracting patterns and information from that data.

[0096] "Activity efficiency" refers to the ability to achieve maximum results with minimum resources when performing a certain task.

[0097] A "device for generating evaluations" is a device that measures staff performance based on data and calculates quantified evaluation results.

[0098] A "learning plan" is an educational framework designed to improve specific skills or knowledge.

[0099] "Real-time business support" refers to a system that enables immediate support and information provision during work.

[0100] This system aims to improve the skills of sales staff and increase operational efficiency. The server collects operational data and stores it in a central database. This data includes sales performance, customer service time, and customer feedback.

[0101] The server utilizes AI models to analyze the collected data. For example, it uses machine learning frameworks such as TENSORFLOW® and PyTorch to analyze the data and generate evaluations based on the sales staff's work activities.

[0102] Furthermore, the server automatically creates an optimal learning plan for each sales staff member based on the generated evaluation results. The learning plan includes suggestions for e-learning materials and training sessions to improve specific skills.

[0103] The terminal visually displays information so that sales staff, who are the users, can easily check the evaluation results and learning plans. The terminal also provides real-time support for work, offering staff necessary feedback and hints when interacting with customers.

[0104] As a concrete example, suppose a sales staff member enters feedback into a terminal after finishing a conversation with a customer. The server analyzes this feedback and performs sentiment analysis. Based on the results, it updates the evaluation of the staff member's interpersonal skills and immediately suggests improvement measures.

[0105] By utilizing generative AI models, each evaluation and suggestion is always provided in an up-to-date state, allowing sales staff to continuously improve their skills. A specific example of an input prompt for the generative AI model is, "Based on the sales activity data and customer feedback of a new sales staff member, please suggest a training plan to improve their interpersonal skills."

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The user enters sales activity data into the terminal. This data includes sales performance, customer service time, and customer feedback. The terminal formats this data and sends it to the server.

[0109] Step 2:

[0110] The server stores the received data in a central database. During storage, it verifies data integrity and integrates it with existing data.

[0111] Step 3:

[0112] The server performs data analysis based on the stored data. Using machine learning frameworks such as TensorFlow and PyTorch, it extracts data features and generates an evaluation of the sales staff's activity efficiency. The inputs used are sales performance and customer service time, and the output is a skill evaluation.

[0113] Step 4:

[0114] Using the generated evaluations as prompts, a generating AI model is used to create a learning plan for each sales staff member. The AI ​​model takes evaluation data as input and provides an optimized training plan as output.

[0115] Step 5:

[0116] The terminal visually displays the evaluation results and learning plan received from the server to the user. The user reviews this and understands the training content necessary to improve their skills.

[0117] Step 6:

[0118] When users interact with customers, the terminal provides real-time support. The server utilizes historical data to instantly send appropriate feedback and hints to the user. This allows users to improve their interaction skills on the spot.

[0119] 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.

[0120] This invention is a system that incorporates emotion recognition, a crucial element in the skill evaluation and training of sales staff. Using an AI agent and emotion engine, this system not only analyzes staff work data and provides work evaluations and training plans, but also detects and analyzes the emotions of staff and customers in real time.

[0121] The server retrieves business data entered by users through their terminals and stores it in a database. This business data includes sales performance, customer service time, customer feedback, and information about the user's emotional state. The emotion engine recognizes emotions from the user's voice tone and facial expressions and stores this information in the database.

[0122] The server uses business and emotional data for an AI agent to analyze and generate a comprehensive assessment of the user's business and interpersonal skills. This assessment incorporates emotion recognition results, taking into account the impact of the user's emotional aspects on performance. In this way, the assessment becomes more accurate and can clearly identify areas for improvement tailored to each individual staff member.

[0123] The terminal displays evaluation results sent from the server to the user. The display includes a business performance evaluation obtained through analysis, along with feedback based on the user's emotional state. This allows users to improve their skills while being aware of their own emotional tendencies.

[0124] Furthermore, the server analyzes each user's emotional tendencies over the long term, measuring stress levels and emotional patterns during customer interactions. Based on this analysis, it provides users with appropriate training plans and supports them in reducing stress and strengthening interpersonal skills. The server sends these training plans to the terminal, presenting users with appropriate improvement measures and resources.

[0125] For example, if the emotion engine detects that a user frequently experiences negative emotions during customer service, the server will suggest stress management training to that staff member based on the user's work performance. In this way, the entire system evaluates and incorporates the user's emotional characteristics into training, providing more personalized support, improving staff skills, and increasing overall store operational efficiency.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] Users input simple business data using a terminal during sales activities. The terminal provides functions to quickly record sales figures and customer information through voice recognition and touch operation.

[0129] Step 2:

[0130] When users interact with customers, real-time voice and facial expression data is collected through the device's camera and microphone. The emotion engine analyzes this data to recognize the emotions of the user and the customer.

[0131] Step 3:

[0132] The terminal sends the acquired emotional information to the server. The server processes the emotional data so that it is linked to the business database and saves the emotional state at the time of each interaction.

[0133] Step 4:

[0134] The server uses an emotion engine to analyze emotional data in detail and generate metrics that represent the user's emotional state. Based on this information, an AI agent performs a comprehensive performance evaluation. This is integrated with other business metrics to create detailed performance reports for each user.

[0135] Step 5:

[0136] The server develops a training plan based on the generated performance evaluation. Based on emotional data, it suggests specific programs aimed at improving stress management or communication skills, for example.

[0137] Step 6:

[0138] The device presents the user with a training plan and the results of an emotional analysis. The user can then begin training after reviewing specific improvement strategies linked to their own emotional tendencies.

[0139] Step 7:

[0140] The server generates reports based on long-term accumulated sentiment data and performance evaluations to support strategies for overall store operations and staff training, and provides these reports to administrators. This process aims to improve the operational efficiency of the entire organization.

[0141] (Example 2)

[0142] 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".

[0143] In sales operations, there is a challenge in systematically evaluating and developing staff skills. Furthermore, it is difficult to grasp the emotional state of individual staff members in real time and identify areas for performance improvement. Traditional methods are insufficient in providing evaluations and training that consider the emotional aspects of staff. Moreover, there is a need to integrate work data and emotional data to provide more personalized feedback, thereby improving staff capabilities and operational efficiency.

[0144] 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.

[0145] In this invention, the server includes means for recording work data and emotional data, means for analyzing the recorded work data and emotional data to generate evaluations corresponding to work activities and emotional states, and means for presenting personalized training plans based on the evaluation results. This enables skill evaluation that includes the emotional aspects of staff, making it possible to provide more accurate feedback and training plans.

[0146] "Business data" refers to a series of pieces of information related to staff members' work activities, such as sales performance, customer service time, and customer feedback.

[0147] "Emotional data" refers to data that indicates a user's emotional state by analyzing their voice tone and facial expressions.

[0148] "Evaluation" refers to comprehensive evaluation information that takes into account staff members' work performance and emotional aspects, generated by analyzing work data and emotional data.

[0149] A "training plan" is an individualized learning and practice plan based on evaluation results, aimed at improving staff skills and reducing stress.

[0150] A "generative AI model" refers to artificial intelligence technology used for data analysis, specifically a model that has the function of identifying a user's emotional state and proposing the optimal improvement measures.

[0151] A "user terminal" is an information device used by sales staff to input business data and access evaluation results and training plans.

[0152] "Feedback" refers to specific suggestions and advice provided based on the staff member's emotional state, aimed at improving their work performance.

[0153] A "store-wide performance report" is a document that automatically generates based on aggregated operational data and evaluation results, showing the operational efficiency and performance of the store.

[0154] This invention is a system designed to improve the efficiency of sales operations and enhance staff skills. The system collects operational and emotional data and generates evaluation and training plans based on that data.

[0155] The server receives work data entered from terminals in real time and securely stores it in a database. This data includes information about the staff's daily work activities. In addition, the emotion engine analyzes the user's voice tone and facial expression data and records it as emotion data. The emotion engine implements a proprietary algorithm, enabling advanced emotion recognition.

[0156] The server uses a generative AI model to analyze stored business and emotional data. The AI ​​agent analyzes the data characteristics in detail and generates a comprehensive evaluation that takes into account the user's business performance and emotional aspects. This evaluation clearly shows the user's strengths and areas for improvement, directly leading to skill improvement for the user.

[0157] The terminal displays evaluation results and feedback sent from the server. The visually organized evaluation allows users to understand their own work performance and emotional tendencies, enabling them to take concrete actions for improvement. Furthermore, the training plan takes into account the user's past behavioral patterns, providing an optimal learning experience tailored to individual needs.

[0158] For example, if the emotion engine detects that a user is showing some anxiety during a customer interaction, the server will recommend a training plan that includes stress management sessions. This training will include simulations, enabling the user to interact with customers with confidence. An example of a prompt would be, "Generate appropriate feedback based on the user's emotion analysis."

[0159] In this way, the system integrates and evaluates the user's emotional aspects and business data, providing personalized support to achieve effective skill development and improved work efficiency.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] Users input business data into a terminal. This business data includes sales performance, customer service time, and customer feedback. The entered data is sent from the terminal to a server. The server receives the data, encrypts it, and stores it in a database. The stored business data is used as basic information necessary for evaluating user performance.

[0163] Step 2:

[0164] The emotion engine analyzes the user's voice tone and facial expressions in real time. It uses the device's camera and microphone to acquire necessary emotional state information and outputs it as emotional data. The server receives the emotional data transmitted from the emotion engine and stores it in a database. This allows the user's emotional aspects to be used in evaluations along with business data.

[0165] Step 3:

[0166] The server requests data analysis from an AI agent using stored business and sentiment data. The AI ​​agent analyzes the input data using a generative AI model and generates an evaluation that takes into account the user's business performance and emotional impact. This analysis detects outliers and trends in the data and performs calculations to obtain an overall performance evaluation.

[0167] Step 4:

[0168] The server sends the evaluation results generated by the AI ​​agent to the terminal. The terminal visually displays the evaluation results to the user. Specifically, it provides detailed evaluation information and feedback using graphs and dashboards. This allows the user to check their own work performance and emotional state and obtain necessary information for improvement.

[0169] Step 5:

[0170] The server analyzes long-term accumulated emotional data to understand the user's stress level and emotional patterns. Based on this analysis, it generates an individualized training plan. The generated training plan focuses on specific skills and stress management, suggesting an appropriate training program.

[0171] Step 6:

[0172] The server sends the created training plan to the terminal. The terminal displays the training plan to the user, presenting specific learning and practice items. The user can then take actions to improve their skills according to these training plans. Specific examples of training include interactive simulations and situational response training.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0175] Traditionally, evaluating and improving the work and interpersonal skills of sales staff has been difficult because it has been challenging to consider their actual emotional states, making standardized evaluation difficult. Furthermore, the provision of feedback and training plans to staff has been uniform, lacking appropriate approaches based on individual emotional tendencies. This has resulted in insufficient efforts to maintain staff motivation and improve the quality of service provided to customers.

[0176] 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.

[0177] In this invention, the server includes means for recording work activities, means for analyzing the recorded work information and generating evaluations corresponding to job activities, means for recognizing the user's emotional state, means for analyzing the recognized emotions and evaluating the interpersonal skills of sales staff, means for detecting emotions in real time using video and audio from a smart device, and means for providing personalized feedback aligned with emotional tendencies based on the analysis results. This makes it possible to provide more accurate evaluations and training plans that take into account the emotional characteristics of individual sales staff.

[0178] "Duties" refers to all job activities performed by sales staff in stores, and includes sales-related activities such as customer service and inventory management.

[0179] "Evaluation" is a process that involves quantifying and qualitatively analyzing work performance and staff interpersonal skills, and using the results to identify staff skill levels and areas for improvement.

[0180] A "training plan" is a plan that outlines specific learning programs and activities for sales staff to improve their skills based on evaluation results.

[0181] "Schedule management" refers to activities aimed at efficiently managing staff work schedules and understanding the progress of their work.

[0182] "Users" refers to sales staff and managers at stores that use this system.

[0183] "Emotional state" refers to the psychological and physiological state of the user, and is the internal emotional state that can be perceived from facial expressions and tone of voice.

[0184] "Analysis" is the process of analyzing recorded data using machine learning and statistical methods to extract useful information and patterns.

[0185] A "smart device" is an electronic device that connects to the internet and provides multifunctional services using integrated applications; it typically refers to mobile phones and tablets.

[0186] "Real-time" refers to a state where data is processed and analyzed immediately the moment it is generated, a time characteristic that enables immediate responses to users.

[0187] "Feedback" refers to evaluation results and suggestions provided to users, with the aim of improving work processes and enhancing skills.

[0188] This invention provides a system for improving staff skills and performing sentiment analysis in sales operations. This system primarily consists of three elements: a server, a smart device, and a user.

[0189] The server records business data and stores it in a database. This data includes information such as sales performance, customer interaction time, and customer feedback. When analyzing this recorded business data, the server uses AI models such as TensorFlow and PyTorch to evaluate sales skills. Furthermore, the server analyzes the user's voice tone and facial expression data, and uses acoustic and image analysis technologies to recognize emotional states. This process utilizes cloud services such as Google® Cloud Vision API and Amazon Rekognition.

[0190] Smart devices, worn by users during customer service interactions, collect real-time audio and video data. This data is transmitted to a server for detailed analysis through emotion recognition. The analysis results are provided to the user as personalized feedback tailored to their emotional tendencies, allowing them to re-evaluate their work and communication style.

[0191] For example, if a sales staff member frequently exhibits negative emotions while serving customers, the server detects this and displays feedback on the smart device prompting them to implement stress management techniques. In conjunction with this, the smart device is also provided with video links for relaxation exercises and breathing techniques.

[0192] An example of a prompt might be, "Please propose the optimal architecture for building an emotional feedback system for store staff. Emotion recognition will use facial expressions and voice analysis." Through this prompt, the AI ​​model can learn how to provide more appropriate evaluations and feedback to the user.

[0193] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0194] Step 1:

[0195] The user puts on a smart device and begins work. The smart device activates its camera and microphone, collecting the user's voice and video data in real time. This data is transmitted to a server via the network. The input is the user's voice and video data, and the output is the raw data sent to the server.

[0196] Step 2:

[0197] The server analyzes the received audio and video data. It uses the Google Cloud Vision API and Amazon Rekognition to detect changes in facial expressions and Google Cloud Speech-to-Text to analyze speech tone, thereby recognizing the user's emotional state. The input is the user's audio and video data, and the output is parameters indicating the user's emotional state.

[0198] Step 3:

[0199] The server uses an AI model (TensorFlow or PyTorch) to evaluate sales skills based on emotion recognition results and business data stored in a database beforehand. Specifically, it inputs past performance metrics and current emotion data into the model and generates a quantified evaluation result. The input is business data and emotion state data, and the output is the sales skill evaluation result.

[0200] Step 4:

[0201] The server uses the generated sales skills assessment results to create personalized feedback for the user. This feedback includes training plans tailored to emotional tendencies and stress management advice. The input is the sales skills assessment results, and the output is the feedback and training plan information.

[0202] Step 5:

[0203] The server sends feedback and training plans to the user's smart device, which then displays them. This allows the user to review their emotional tendencies and work performance and implement necessary improvements. The input is the feedback and training plan, and the output is the information displayed on the smart device.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] [Second Embodiment]

[0208] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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".

[0220] This invention is a system for streamlining the skill evaluation and training of sales staff. This system utilizes an AI agent to analyze staff work data, generate skill evaluations, and propose training plans.

[0221] The server collects daily work data entered by users (sales staff) using terminals and stores it in a central database. This data entry includes sales performance, customer interaction time, and customer feedback. This information is essential for evaluating the current performance of the staff.

[0222] The server uses the collected data to analyze staff performance through an AI agent. The analysis yields a skill evaluation for each staff member, generating a relative ranking. This ranking differs for each staff member, based on factors such as work efficiency and customer service skills.

[0223] The terminal visually displays the evaluation results received from the server to the user. After understanding the evaluation, the user reviews the training plan proposed by the AI ​​agent. This training plan includes e-learning materials and information on in-house training aimed at improving specific skills.

[0224] Furthermore, customer feedback is processed on a server using sentiment analysis tools. Sentiment analysis extracts customer emotions from text data and uses this information to evaluate the interpersonal skills of sales staff. This allows users to clearly understand their strengths and areas for improvement.

[0225] As a concrete example, suppose a user has short customer service times and receives low ratings from feedback. Based on this data, the server's AI agent analyzes the information and presents the user with a training plan aimed at improving their interpersonal skills. In this way, an appropriate training approach based on individual feedback can improve the user's skills and improve overall store performance.

[0226] This system not only supports the evaluation and training of sales staff, but also serves as a valuable tool for improving the overall operational efficiency of the store.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] After completing their daily tasks, users input business data, including sales figures, customer service time, and customer feedback, using a terminal. The terminal automatically transmits the entered data to the server.

[0230] Step 2:

[0231] The server stores the received business data in a database. Based on the stored data, an AI agent is used to begin evaluating staff performance. The AI ​​agent analyzes each data point and quantifies sales performance and the quality of customer service.

[0232] Step 3:

[0233] The server generates skill evaluation scores for each staff member based on the data analysis results. These scores include indicators such as sales efficiency, customer satisfaction, and communication skills. These indicators determine the relative positioning of each staff member.

[0234] Step 4:

[0235] The server sends the generated skill assessment score to the terminal. The terminal visually displays the detailed assessment results to the user. The user reviews the displayed information and checks their work performance.

[0236] Step 5:

[0237] The AI ​​agent creates an appropriate training plan based on the evaluation results. The server sends this training plan to the terminal. The terminal displays the training plan to the user, including specific improvement actions. For example, it may suggest learning materials aimed at improving specific skills or notify the user of available training dates.

[0238] Step 6:

[0239] The server performs sentiment analysis on collected customer feedback and incorporates the results into the user's interpersonal skills evaluation. It clarifies customer emotions and intentions, and identifies areas for improvement in customer service.

[0240] Step 7:

[0241] Based on all evaluations and feedback, the server identifies each user's growth trend and supports goal setting for the next evaluation period. This allows individual staff members to develop plans for improving their own performance.

[0242] (Example 1)

[0243] 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."

[0244] In modern sales operations, accurately evaluating the individual performance of sales staff and developing effective training plans is challenging. Furthermore, while detailed performance reports are essential for improving employee performance and efficient store operations, this also represents a significant burden. Additionally, properly analyzing customer feedback and utilizing it to improve interpersonal skills is crucial.

[0245] 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.

[0246] In this invention, the server includes means for recording business information in sales operations, means for analyzing the recorded business information and generating evaluations corresponding to business activities, and means for collecting customer feedback and performing sentiment analysis. This enables precise evaluation of sales employee performance, automation of effective training plan development, and improvement of interpersonal skills evaluation based on customer feedback.

[0247] "Sales operations" refers to a series of activities and processes carried out with the aim of providing goods or services.

[0248] "Business information" refers to all data and records related to sales, including sales performance, customer service status, and feedback.

[0249] "Analysis" refers to the process of processing and handling collected information and data to gain useful insights.

[0250] "Evaluation" is the act of measuring the performance of individuals or processes based on specific criteria and determining their value or effectiveness.

[0251] A "development plan" refers to a set of learning and growth steps and policies designed to improve the capabilities of individual employees.

[0252] "Timetable management" refers to the process of adjusting and managing time to ensure that work and activities proceed efficiently and according to plan.

[0253] "Sentiment analysis" is a technique that reads emotions from information such as text data, and is used to understand customer opinions and feedback.

[0254] "Interpersonal skills" refer to the skills and attitudes necessary for communicating efficiently and effectively with others.

[0255] This invention is a system for automating employee skill evaluation and training planning in sales operations. This system utilizes multiple basic hardware and software components to efficiently manage and analyze sales-related business information.

[0256] The server collects business information such as sales performance, customer service time, and feedback entered by users through their terminals, and stores it in a central database. This server uses a cloud-based database management system (DBMS) to perform high-speed and secure data storage.

[0257] Next, the server analyzes the collected business information using a generative AI model. This analysis process utilizes machine learning algorithms to evaluate the skills and performance of individual employees. The analysis results include performance trend analysis and detailed evaluations of specific skills.

[0258] Furthermore, customer feedback is processed through a sentiment analysis tool. This tool uses natural language processing (NLP) techniques to analyze text data and extract customer emotions. The specific software used for this process utilizes open-source NLP libraries.

[0259] The terminal provides visual feedback to the user based on analysis results received from the server. The evaluation results are displayed through a user-friendly interface. Furthermore, the generated training plan includes suggestions for e-learning modules and in-house training.

[0260] For example, if a user is evaluated as having short customer service times, the server uses an AI agent to further analyze the data and present the user with an appropriate training plan. This training plan includes details of online courses and on-the-job training to improve interpersonal skills.

[0261] An example of a prompt is: "To evaluate sales staff, please have the AI ​​agent analyze sales performance, customer interaction time, and feedback data from the past month, and propose a training plan aimed at improving specific skills." This prompt represents a specific analysis request to the AI ​​model.

[0262] In this way, this system can improve overall operational efficiency by analyzing the performance of sales staff in detail and providing individualized training support.

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The server receives business information such as sales performance, customer service time, and customer feedback entered by users through terminals. The received data is stored in a central database in real time. The specific actions performed here are to validate the entered business information and record it in the database according to the format. The output is a well-organized dataset of business information.

[0266] Step 2:

[0267] The server retrieves business information stored in a central database and performs analysis using a generated AI model. The inputs required for this analysis include sales performance and customer interaction history. Based on this input data, the server performs trend analysis and anomaly detection to generate performance evaluations for each employee. Specifically, it executes machine learning algorithms to calculate evaluation scores and ranks. The output is performance evaluation data for each employee.

[0268] Step 3:

[0269] The server generates a training plan using the analysis results. The inputs for generating this training plan are each employee's performance evaluation and the sentiment analysis results of customer feedback. The server integrates this data to generate a training plan aimed at improving specific skills. Specifically, it assembles a list of e-learning materials and training courses that address the user's weaknesses. The output is an individual training plan.

[0270] Step 4:

[0271] The terminal presents the user with performance evaluations and training plans provided by the server. This process requires incoming data as input to visually display both evaluation results and training plans. Based on this data, the terminal displays the information in a user-friendly graphical interface. Specifically, it displays data on a dashboard and supports the user in viewing detailed information. The output consists of evaluation and training information that the user can visually verify.

[0272] Step 5:

[0273] Based on the evaluation results and training plan displayed on the device, users take action to improve their skills. User input includes providing feedback and deciding whether to participate in training. Users utilize this information to participate in educational or training plans to address their weaknesses. Specific actions include registering for online courses and scheduling training sessions. Outputs include improved skills and adjusted work performance.

[0274] (Application Example 1)

[0275] 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."

[0276] In modern retail, improving the skills of sales staff is a crucial factor directly impacting customer satisfaction and sales. However, individually evaluating each staff member and proposing efficient training plans is time-consuming and costly. In addition, systems that can provide solutions for improving interpersonal skills using customer feedback are not yet widespread. This presents a challenge in maximizing the potential of sales staff.

[0277] 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.

[0278] In this invention, the server includes a device for recording data related to operations, a device for analyzing the recorded data and generating an evaluation according to the activity efficiency, and a device for presenting a learning plan based on the evaluation result. Thereby, it becomes possible to efficiently evaluate the skills of sales staff and automatically propose an individually optimized training plan. Furthermore, through real-time operation support, an environment is provided where sales staff can immediately implement improvement measures.

[0279] "Data related to operations" refers to information related to sales activities, including data such as sales performance, customer response time, and customer feedback.

[0280] "Device" refers to a combination of hardware or software designed to perform a specific function.

[0281] "Analysis" refers to the process of investigating the collected data in detail and extracting data patterns and information.

[0282] "Activity efficiency" refers to the ability to achieve maximum results with minimal resources when performing certain operations.

[0283] "Device for generating an evaluation" refers to something having the function of measuring staff performance based on data and calculating a quantified evaluation result.

[0284] "Learning plan" refers to an educational framework organized to improve specific skills and knowledge.

[0285] "Real-time operation support" refers to a mechanism that enables immediate support and information provision during operations.

[0286] This system is aimed at improving the skills of sales staff and enhancing operational efficiency. The server has the function of collecting data related to operations and storing it in a central database. This data includes sales performance, customer response time, and feedback from customers.

[0287] The server utilizes an AI model to analyze the collected data. For example, it uses machine learning frameworks such as TensorFlow or PyTorch to analyze the data and generate an evaluation based on the business activities of the sales staff.

[0288] Furthermore, based on the generated evaluation results, the server automatically creates an optimal learning plan for each sales staff. The learning plan includes e-learning materials and proposals for training sessions to improve specific skills.

[0289] The terminal visually presents information so that the sales staff, who are the users, can easily confirm this evaluation result and learning plan. Also, the terminal provides real-time business support and offers the staff the feedback and hints necessary during customer service.

[0290] As a specific example, assume that a sales staff inputs feedback into the terminal after finishing a conversation with a customer. The server analyzes the feedback and performs sentiment analysis. Based on the results, the evaluation regarding the staff's interpersonal skills is updated, and improvement measures are immediately proposed.

[0291] By leveraging the generative AI model, each evaluation and proposal is always provided in the latest state, and the sales staff can continuously improve their skills. Specific examples of input prompts for the generative AI model include "Please propose a training plan to improve interpersonal skills based on the sales activity data and customer feedback of new sales staff."

[0292] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0293] Step 1:

[0294] The user enters sales activity data into the terminal. This data includes sales performance, customer service time, and customer feedback. The terminal formats this data and sends it to the server.

[0295] Step 2:

[0296] The server stores the received data in a central database. During storage, it verifies data integrity and integrates it with existing data.

[0297] Step 3:

[0298] The server performs data analysis based on the stored data. Using machine learning frameworks such as TensorFlow and PyTorch, it extracts data features and generates an evaluation of the sales staff's activity efficiency. The inputs used are sales performance and customer service time, and the output is a skill evaluation.

[0299] Step 4:

[0300] Using the generated evaluations as prompts, a generating AI model is used to create a learning plan for each sales staff member. The AI ​​model takes evaluation data as input and provides an optimized training plan as output.

[0301] Step 5:

[0302] The terminal visually displays the evaluation results and learning plan received from the server to the user. The user reviews this and understands the training content necessary to improve their skills.

[0303] Step 6:

[0304] When users interact with customers, the terminal provides real-time support. The server utilizes historical data to instantly send appropriate feedback and hints to the user. This allows users to improve their interaction skills on the spot.

[0305] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0306] The present invention is a system incorporating emotion recognition, which is an important element in the skill evaluation and training of sales staff. By using an AI agent and an emotion engine, this system can not only analyze the staff's business data and provide business evaluations and training plans, but also detect and analyze the emotions of staff and customers in real time.

[0307] The server captures the business data input by the user through the terminal and stores it in the database. This business data also includes sales performance, customer response time, customer feedback, and information regarding the user's emotional state. The emotion engine recognizes the emotion from the user's voice tone and expression and stores this in the database.

[0308] The server uses the business data and emotion data for the AI agent to perform analysis and generate a comprehensive evaluation regarding the user's business and interpersonal skills. This evaluation incorporates the emotion recognition results and also takes into account the impact of the user's emotional aspects on performance. Thus, the evaluation can be made more accurate and the areas for improvement suitable for each individual staff can be clarified.

[0309] The terminal displays the evaluation results transmitted from the server to the user. The display content includes, together with the business performance evaluation obtained by the analysis, feedback based on the user's emotional state. Thereby, the user can improve their skills while being aware of their own emotional tendencies.

[0310] Furthermore, the server analyzes each user's emotional tendencies over the long term, measuring stress levels and emotional patterns during customer interactions. Based on this analysis, it provides users with appropriate training plans and supports them in reducing stress and strengthening interpersonal skills. The server sends these training plans to the terminal, presenting users with appropriate improvement measures and resources.

[0311] For example, if the emotion engine detects that a user frequently experiences negative emotions during customer service, the server will suggest stress management training to that staff member based on the user's work performance. In this way, the entire system evaluates and incorporates the user's emotional characteristics into training, providing more personalized support, improving staff skills, and increasing overall store operational efficiency.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] Users input simple business data using a terminal during sales activities. The terminal provides functions to quickly record sales figures and customer information through voice recognition and touch operation.

[0315] Step 2:

[0316] When users interact with customers, real-time voice and facial expression data is collected through the device's camera and microphone. The emotion engine analyzes this data to recognize the emotions of the user and the customer.

[0317] Step 3:

[0318] The terminal sends the acquired emotional information to the server. The server processes the emotional data so that it is linked to the business database and saves the emotional state at the time of each interaction.

[0319] Step 4:

[0320] The server uses an emotion engine to analyze emotional data in detail and generate metrics that represent the user's emotional state. Based on this information, an AI agent performs a comprehensive performance evaluation. This is integrated with other business metrics to create detailed performance reports for each user.

[0321] Step 5:

[0322] The server develops a training plan based on the generated performance evaluation. Based on emotional data, it suggests specific programs aimed at improving stress management or communication skills, for example.

[0323] Step 6:

[0324] The device presents the user with a training plan and the results of an emotional analysis. The user can then begin training after reviewing specific improvement strategies linked to their own emotional tendencies.

[0325] Step 7:

[0326] The server generates reports based on long-term accumulated sentiment data and performance evaluations to support strategies for overall store operations and staff training, and provides these reports to administrators. This process aims to improve the operational efficiency of the entire organization.

[0327] (Example 2)

[0328] 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".

[0329] In sales operations, there is a challenge in systematically evaluating and developing staff skills. Furthermore, it is difficult to grasp the emotional state of individual staff members in real time and identify areas for performance improvement. Traditional methods are insufficient in providing evaluations and training that consider the emotional aspects of staff. Moreover, there is a need to integrate work data and emotional data to provide more personalized feedback, thereby improving staff capabilities and operational efficiency.

[0330] 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.

[0331] In this invention, the server includes means for recording work data and emotional data, means for analyzing the recorded work data and emotional data to generate evaluations corresponding to work activities and emotional states, and means for presenting personalized training plans based on the evaluation results. This enables skill evaluation that includes the emotional aspects of staff, making it possible to provide more accurate feedback and training plans.

[0332] "Business data" refers to a series of pieces of information related to staff members' work activities, such as sales performance, customer service time, and customer feedback.

[0333] "Emotional data" refers to data that indicates a user's emotional state by analyzing their voice tone and facial expressions.

[0334] "Evaluation" refers to comprehensive evaluation information that takes into account staff members' work performance and emotional aspects, generated by analyzing work data and emotional data.

[0335] A "training plan" is an individualized learning and practice plan based on evaluation results, aimed at improving staff skills and reducing stress.

[0336] A "generative AI model" refers to artificial intelligence technology used for data analysis, specifically a model that has the function of identifying a user's emotional state and proposing the optimal improvement measures.

[0337] A "user terminal" is an information device used by sales staff to input business data and access evaluation results and training plans.

[0338] "Feedback" refers to specific suggestions and advice provided based on the staff member's emotional state, aimed at improving their work performance.

[0339] A "store-wide performance report" is a document that automatically generates based on aggregated operational data and evaluation results, showing the operational efficiency and performance of the store.

[0340] This invention is a system designed to improve the efficiency of sales operations and enhance staff skills. The system collects operational and emotional data and generates evaluation and training plans based on that data.

[0341] The server receives work data entered from terminals in real time and securely stores it in a database. This data includes information about the staff's daily work activities. In addition, the emotion engine analyzes the user's voice tone and facial expression data and records it as emotion data. The emotion engine implements a proprietary algorithm, enabling advanced emotion recognition.

[0342] The server uses a generative AI model to analyze stored business and emotional data. The AI ​​agent analyzes the data characteristics in detail and generates a comprehensive evaluation that takes into account the user's business performance and emotional aspects. This evaluation clearly shows the user's strengths and areas for improvement, directly leading to skill improvement for the user.

[0343] The terminal displays evaluation results and feedback sent from the server. The visually organized evaluation allows users to understand their own work performance and emotional tendencies, enabling them to take concrete actions for improvement. Furthermore, the training plan takes into account the user's past behavioral patterns, providing an optimal learning experience tailored to individual needs.

[0344] For example, if the emotion engine detects that a user is showing some anxiety during a customer interaction, the server will recommend a training plan that includes stress management sessions. This training will include simulations, enabling the user to interact with customers with confidence. An example of a prompt would be, "Generate appropriate feedback based on the user's emotion analysis."

[0345] In this way, the system integrates and evaluates the user's emotional aspects and business data, providing personalized support to achieve effective skill development and improved work efficiency.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] Users input business data into a terminal. This business data includes sales performance, customer service time, and customer feedback. The entered data is sent from the terminal to a server. The server receives the data, encrypts it, and stores it in a database. The stored business data is used as basic information necessary for evaluating user performance.

[0349] Step 2:

[0350] The emotion engine analyzes the user's voice tone and facial expressions in real time. It uses the device's camera and microphone to acquire necessary emotional state information and outputs it as emotional data. The server receives the emotional data transmitted from the emotion engine and stores it in a database. This allows the user's emotional aspects to be used in evaluations along with business data.

[0351] Step 3:

[0352] The server requests data analysis from an AI agent using stored business and sentiment data. The AI ​​agent analyzes the input data using a generative AI model and generates an evaluation that takes into account the user's business performance and emotional impact. This analysis detects outliers and trends in the data and performs calculations to obtain an overall performance evaluation.

[0353] Step 4:

[0354] The server sends the evaluation results generated by the AI ​​agent to the terminal. The terminal visually displays the evaluation results to the user. Specifically, it provides detailed evaluation information and feedback using graphs and dashboards. This allows the user to check their own work performance and emotional state and obtain necessary information for improvement.

[0355] Step 5:

[0356] The server analyzes long-term accumulated emotional data to understand the user's stress level and emotional patterns. Based on this analysis, it generates an individualized training plan. The generated training plan focuses on specific skills and stress management, suggesting an appropriate training program.

[0357] Step 6:

[0358] The server sends the created training plan to the terminal. The terminal displays the training plan to the user, presenting specific learning and practice items. The user can then take actions to improve their skills according to these training plans. Specific examples of training include interactive simulations and situational response training.

[0359] (Application Example 2)

[0360] 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."

[0361] Traditionally, evaluating and improving the work and interpersonal skills of sales staff has been difficult because it has been challenging to consider their actual emotional states, making standardized evaluation difficult. Furthermore, the provision of feedback and training plans to staff has been uniform, lacking appropriate approaches based on individual emotional tendencies. This has resulted in insufficient efforts to maintain staff motivation and improve the quality of service provided to customers.

[0362] 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.

[0363] In this invention, the server includes means for recording work activities, means for analyzing the recorded work information and generating evaluations corresponding to job activities, means for recognizing the user's emotional state, means for analyzing the recognized emotions and evaluating the interpersonal skills of sales staff, means for detecting emotions in real time using video and audio from a smart device, and means for providing personalized feedback aligned with emotional tendencies based on the analysis results. This makes it possible to provide more accurate evaluations and training plans that take into account the emotional characteristics of individual sales staff.

[0364] "Duties" refers to all job activities performed by sales staff in stores, and includes sales-related activities such as customer service and inventory management.

[0365] "Evaluation" is a process that involves quantifying and qualitatively analyzing work performance and staff interpersonal skills, and using the results to identify staff skill levels and areas for improvement.

[0366] A "training plan" is a plan that outlines specific learning programs and activities for sales staff to improve their skills based on evaluation results.

[0367] "Schedule management" refers to activities aimed at efficiently managing staff work schedules and understanding the progress of their work.

[0368] "Users" refers to sales staff and managers at stores that use this system.

[0369] "Emotional state" refers to the psychological and physiological state of the user, and is the internal emotional state that can be perceived from facial expressions and tone of voice.

[0370] "Analysis" is the process of analyzing recorded data using machine learning and statistical methods to extract useful information and patterns.

[0371] A "smart device" is an electronic device that connects to the internet and provides multifunctional services using integrated applications; it typically refers to mobile phones and tablets.

[0372] "Real-time" refers to a state where data is processed and analyzed immediately the moment it is generated, a time characteristic that enables immediate responses to users.

[0373] "Feedback" refers to evaluation results and suggestions provided to users, with the aim of improving work processes and enhancing skills.

[0374] This invention provides a system for improving staff skills and performing sentiment analysis in sales operations. This system primarily consists of three elements: a server, a smart device, and a user.

[0375] The server records business data and stores it in a database. This data includes information such as sales performance, customer interaction time, and customer feedback. When analyzing this recorded business data, the server uses AI models such as TensorFlow and PyTorch to evaluate sales skills. Furthermore, the server analyzes the user's voice tone and facial expression data, and uses acoustic and image analysis technologies to recognize emotional states. This process utilizes cloud services such as Google Cloud Vision API and Amazon Rekognition.

[0376] Smart devices, worn by users during customer service interactions, collect real-time audio and video data. This data is transmitted to a server for detailed analysis through emotion recognition. The analysis results are provided to the user as personalized feedback tailored to their emotional tendencies, allowing them to re-evaluate their work and communication style.

[0377] For example, if a sales staff member frequently exhibits negative emotions while serving customers, the server detects this and displays feedback on the smart device prompting them to implement stress management techniques. In conjunction with this, the smart device is also provided with video links for relaxation exercises and breathing techniques.

[0378] An example of a prompt might be, "Please propose the optimal architecture for building an emotional feedback system for store staff. Emotion recognition will use facial expressions and voice analysis." Through this prompt, the AI ​​model can learn how to provide more appropriate evaluations and feedback to the user.

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The user puts on a smart device and begins work. The smart device activates its camera and microphone, collecting the user's voice and video data in real time. This data is transmitted to a server via the network. The input is the user's voice and video data, and the output is the raw data sent to the server.

[0382] Step 2:

[0383] The server analyzes the received audio and video data. It uses the Google Cloud Vision API and Amazon Rekognition to detect changes in facial expressions and Google Cloud Speech-to-Text to analyze speech tone, thereby recognizing the user's emotional state. The input is the user's audio and video data, and the output is parameters indicating the user's emotional state.

[0384] Step 3:

[0385] The server uses an AI model (TensorFlow or PyTorch) to evaluate sales skills based on emotion recognition results and business data stored in a database beforehand. Specifically, it inputs past performance metrics and current emotion data into the model and generates a quantified evaluation result. The input is business data and emotion state data, and the output is the sales skill evaluation result.

[0386] Step 4:

[0387] The server uses the generated sales skills assessment results to create personalized feedback for the user. This feedback includes training plans tailored to emotional tendencies and stress management advice. The input is the sales skills assessment results, and the output is the feedback and training plan information.

[0388] Step 5:

[0389] The server sends feedback and training plans to the user's smart device, which then displays them. This allows the user to review their emotional tendencies and work performance and implement necessary improvements. The input is the feedback and training plan, and the output is the information displayed on the smart device.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] [Third Embodiment]

[0394] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] 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".

[0406] This invention is a system for streamlining the skill evaluation and training of sales staff. This system utilizes an AI agent to analyze staff work data, generate skill evaluations, and propose training plans.

[0407] The server collects daily work data entered by users (sales staff) using terminals and stores it in a central database. This data entry includes sales performance, customer interaction time, and customer feedback. This information is essential for evaluating the current performance of the staff.

[0408] The server uses the collected data to analyze staff performance through an AI agent. The analysis yields a skill evaluation for each staff member, generating a relative ranking. This ranking differs for each staff member, based on factors such as work efficiency and customer service skills.

[0409] The terminal visually displays the evaluation results received from the server to the user. After understanding the evaluation, the user reviews the training plan proposed by the AI ​​agent. This training plan includes e-learning materials and information on in-house training aimed at improving specific skills.

[0410] Furthermore, customer feedback is processed on a server using sentiment analysis tools. Sentiment analysis extracts customer emotions from text data and uses this information to evaluate the interpersonal skills of sales staff. This allows users to clearly understand their strengths and areas for improvement.

[0411] As a concrete example, suppose a user has short customer service times and receives low ratings from feedback. Based on this data, the server's AI agent analyzes the information and presents the user with a training plan aimed at improving their interpersonal skills. In this way, an appropriate training approach based on individual feedback can improve the user's skills and improve overall store performance.

[0412] This system not only supports the evaluation and training of sales staff, but also serves as a valuable tool for improving the overall operational efficiency of the store.

[0413] The following describes the processing flow.

[0414] Step 1:

[0415] After completing their daily tasks, users input business data, including sales figures, customer service time, and customer feedback, using a terminal. The terminal automatically transmits the entered data to the server.

[0416] Step 2:

[0417] The server stores the received business data in a database. Based on the stored data, an AI agent is used to begin evaluating staff performance. The AI ​​agent analyzes each data point and quantifies sales performance and the quality of customer service.

[0418] Step 3:

[0419] The server generates skill evaluation scores for each staff member based on the data analysis results. These scores include indicators such as sales efficiency, customer satisfaction, and communication skills. These indicators determine the relative positioning of each staff member.

[0420] Step 4:

[0421] The server sends the generated skill assessment score to the terminal. The terminal visually displays the detailed assessment results to the user. The user reviews the displayed information and checks their work performance.

[0422] Step 5:

[0423] The AI ​​agent creates an appropriate training plan based on the evaluation results. The server sends this training plan to the terminal. The terminal displays the training plan to the user, including specific improvement actions. For example, it may suggest learning materials aimed at improving specific skills or notify the user of available training dates.

[0424] Step 6:

[0425] The server performs sentiment analysis on collected customer feedback and incorporates the results into the user's interpersonal skills evaluation. It clarifies customer emotions and intentions, and identifies areas for improvement in customer service.

[0426] Step 7:

[0427] Based on all evaluations and feedback, the server identifies each user's growth trend and supports goal setting for the next evaluation period. This allows individual staff members to develop plans for improving their own performance.

[0428] (Example 1)

[0429] 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."

[0430] In modern sales operations, accurately evaluating the individual performance of sales staff and developing effective training plans is challenging. Furthermore, while detailed performance reports are essential for improving employee performance and efficient store operations, this also represents a significant burden. Additionally, properly analyzing customer feedback and utilizing it to improve interpersonal skills is crucial.

[0431] 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.

[0432] In this invention, the server includes means for recording business information in sales operations, means for analyzing the recorded business information and generating evaluations corresponding to business activities, and means for collecting customer feedback and performing sentiment analysis. This enables precise evaluation of sales employee performance, automation of effective training plan development, and improvement of interpersonal skills evaluation based on customer feedback.

[0433] "Sales operations" refers to a series of activities and processes carried out with the aim of providing goods or services.

[0434] "Business information" refers to all data and records related to sales, including sales performance, customer service status, and feedback.

[0435] "Analysis" refers to the process of processing and handling collected information and data to gain useful insights.

[0436] "Evaluation" is the act of measuring the performance of individuals or processes based on specific criteria and determining their value or effectiveness.

[0437] A "development plan" refers to a set of learning and growth steps and policies designed to improve the capabilities of individual employees.

[0438] "Timetable management" refers to the process of adjusting and managing time to ensure that work and activities proceed efficiently and according to plan.

[0439] "Sentiment analysis" is a technique that reads emotions from information such as text data, and is used to understand customer opinions and feedback.

[0440] "Interpersonal skills" refer to the skills and attitudes necessary for communicating efficiently and effectively with others.

[0441] This invention is a system for automating employee skill evaluation and training planning in sales operations. This system utilizes multiple basic hardware and software components to efficiently manage and analyze sales-related business information.

[0442] The server collects business information such as sales performance, customer service time, and feedback entered by users through their terminals, and stores it in a central database. This server uses a cloud-based database management system (DBMS) to perform high-speed and secure data storage.

[0443] Next, the server analyzes the collected business information using a generative AI model. This analysis process utilizes machine learning algorithms to evaluate the skills and performance of individual employees. The analysis results include performance trend analysis and detailed evaluations of specific skills.

[0444] Furthermore, customer feedback is processed through a sentiment analysis tool. This tool uses natural language processing (NLP) techniques to analyze text data and extract customer emotions. The specific software used for this process utilizes open-source NLP libraries.

[0445] The terminal provides visual feedback to the user based on analysis results received from the server. The evaluation results are displayed through a user-friendly interface. Furthermore, the generated training plan includes suggestions for e-learning modules and in-house training.

[0446] For example, if a user is evaluated as having short customer service times, the server uses an AI agent to further analyze the data and present the user with an appropriate training plan. This training plan includes details of online courses and on-the-job training to improve interpersonal skills.

[0447] An example of a prompt is: "To evaluate sales staff, please have the AI ​​agent analyze sales performance, customer interaction time, and feedback data from the past month, and propose a training plan aimed at improving specific skills." This prompt represents a specific analysis request to the AI ​​model.

[0448] In this way, this system can improve overall operational efficiency by analyzing the performance of sales staff in detail and providing individualized training support.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] The server receives business information such as sales performance, customer service time, and customer feedback entered by users through terminals. The received data is stored in a central database in real time. The specific actions performed here are to validate the entered business information and record it in the database according to the format. The output is a well-organized dataset of business information.

[0452] Step 2:

[0453] The server retrieves business information stored in a central database and performs analysis using a generated AI model. The inputs required for this analysis include sales performance and customer interaction history. Based on this input data, the server performs trend analysis and anomaly detection to generate performance evaluations for each employee. Specifically, it executes machine learning algorithms to calculate evaluation scores and ranks. The output is performance evaluation data for each employee.

[0454] Step 3:

[0455] The server generates a training plan using the analysis results. The inputs for generating this training plan are each employee's performance evaluation and the sentiment analysis results of customer feedback. The server integrates this data to generate a training plan aimed at improving specific skills. Specifically, it assembles a list of e-learning materials and training courses that address the user's weaknesses. The output is an individual training plan.

[0456] Step 4:

[0457] The terminal presents the user with performance evaluations and training plans provided by the server. This process requires incoming data as input to visually display both evaluation results and training plans. Based on this data, the terminal displays the information in a user-friendly graphical interface. Specifically, it displays data on a dashboard and supports the user in viewing detailed information. The output consists of evaluation and training information that the user can visually verify.

[0458] Step 5:

[0459] Based on the evaluation results and training plan displayed on the device, users take action to improve their skills. User input includes providing feedback and deciding whether to participate in training. Users utilize this information to participate in educational or training plans to address their weaknesses. Specific actions include registering for online courses and scheduling training sessions. Outputs include improved skills and adjusted work performance.

[0460] (Application Example 1)

[0461] 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."

[0462] In modern retail, improving the skills of sales staff is a crucial factor directly impacting customer satisfaction and sales. However, individually evaluating each staff member and proposing efficient training plans is time-consuming and costly. In addition, systems that can provide solutions for improving interpersonal skills using customer feedback are not yet widespread. This presents a challenge in maximizing the potential of sales staff.

[0463] 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.

[0464] In this invention, the server includes a device for recording business-related data, a device for analyzing the recorded data and generating an evaluation based on activity efficiency, and a device for presenting a learning plan based on the evaluation results. This makes it possible to efficiently evaluate the skills of sales staff and automatically propose individually optimized training plans. Furthermore, real-time business support provides an environment in which sales staff can immediately implement improvement measures.

[0465] "Business-related data" refers to information related to sales activities, including sales performance, customer service time, and customer feedback.

[0466] A "device" is a combination of hardware or software designed to perform a specific function.

[0467] "Analysis" is the process of examining collected data in detail and extracting patterns and information from that data.

[0468] "Activity efficiency" refers to the ability to achieve maximum results with minimum resources when performing a certain task.

[0469] A "device for generating evaluations" is a device that measures staff performance based on data and calculates quantified evaluation results.

[0470] A "learning plan" is an educational framework designed to improve specific skills or knowledge.

[0471] "Real-time business support" refers to a system that enables immediate support and information provision during work.

[0472] This system aims to improve the skills of sales staff and increase operational efficiency. The server collects operational data and stores it in a central database. This data includes sales performance, customer service time, and customer feedback.

[0473] The server utilizes AI models to analyze the collected data. For example, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the data and generate evaluations based on the sales staff's work activities.

[0474] Furthermore, the server automatically creates an optimal learning plan for each sales staff member based on the generated evaluation results. The learning plan includes suggestions for e-learning materials and training sessions to improve specific skills.

[0475] The terminal visually displays information so that sales staff, who are the users, can easily check the evaluation results and learning plans. The terminal also provides real-time support for work, offering staff necessary feedback and hints when interacting with customers.

[0476] As a concrete example, suppose a sales staff member enters feedback into a terminal after finishing a conversation with a customer. The server analyzes this feedback and performs sentiment analysis. Based on the results, it updates the evaluation of the staff member's interpersonal skills and immediately suggests improvement measures.

[0477] By utilizing generative AI models, each evaluation and suggestion is always provided in an up-to-date state, allowing sales staff to continuously improve their skills. A specific example of an input prompt for the generative AI model is, "Based on the sales activity data and customer feedback of a new sales staff member, please suggest a training plan to improve their interpersonal skills."

[0478] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0479] Step 1:

[0480] The user enters sales activity data into the terminal. This data includes sales performance, customer service time, and customer feedback. The terminal formats this data and sends it to the server.

[0481] Step 2:

[0482] The server stores the received data in a central database. During storage, it verifies data integrity and integrates it with existing data.

[0483] Step 3:

[0484] The server performs data analysis based on the stored data. Using machine learning frameworks such as TensorFlow and PyTorch, it extracts data features and generates an evaluation of the sales staff's activity efficiency. The inputs used are sales performance and customer service time, and the output is a skill evaluation.

[0485] Step 4:

[0486] Using the generated evaluations as prompts, a generating AI model is used to create a learning plan for each sales staff member. The AI ​​model takes evaluation data as input and provides an optimized training plan as output.

[0487] Step 5:

[0488] The terminal visually displays the evaluation results and learning plan received from the server to the user. The user reviews this and understands the training content necessary to improve their skills.

[0489] Step 6:

[0490] When users interact with customers, the terminal provides real-time support. The server utilizes historical data to instantly send appropriate feedback and hints to the user. This allows users to improve their interaction skills on the spot.

[0491] 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.

[0492] This invention is a system that incorporates emotion recognition, a crucial element in the skill evaluation and training of sales staff. Using an AI agent and emotion engine, this system not only analyzes staff work data and provides work evaluations and training plans, but also detects and analyzes the emotions of staff and customers in real time.

[0493] The server retrieves business data entered by users through their terminals and stores it in a database. This business data includes sales performance, customer service time, customer feedback, and information about the user's emotional state. The emotion engine recognizes emotions from the user's voice tone and facial expressions and stores this information in the database.

[0494] The server uses business and emotional data for an AI agent to analyze and generate a comprehensive assessment of the user's business and interpersonal skills. This assessment incorporates emotion recognition results, taking into account the impact of the user's emotional aspects on performance. In this way, the assessment becomes more accurate and can clearly identify areas for improvement tailored to each individual staff member.

[0495] The terminal displays evaluation results sent from the server to the user. The display includes a business performance evaluation obtained through analysis, along with feedback based on the user's emotional state. This allows users to improve their skills while being aware of their own emotional tendencies.

[0496] Furthermore, the server analyzes each user's emotional tendencies over the long term, measuring stress levels and emotional patterns during customer interactions. Based on this analysis, it provides users with appropriate training plans and supports them in reducing stress and strengthening interpersonal skills. The server sends these training plans to the terminal, presenting users with appropriate improvement measures and resources.

[0497] For example, if the emotion engine detects that a user frequently experiences negative emotions during customer service, the server will suggest stress management training to that staff member based on the user's work performance. In this way, the entire system evaluates and incorporates the user's emotional characteristics into training, providing more personalized support, improving staff skills, and increasing overall store operational efficiency.

[0498] The following describes the processing flow.

[0499] Step 1:

[0500] Users input simple business data using a terminal during sales activities. The terminal provides functions to quickly record sales figures and customer information through voice recognition and touch operation.

[0501] Step 2:

[0502] When users interact with customers, real-time voice and facial expression data is collected through the device's camera and microphone. The emotion engine analyzes this data to recognize the emotions of the user and the customer.

[0503] Step 3:

[0504] The terminal sends the acquired emotional information to the server. The server processes the emotional data so that it is linked to the business database and saves the emotional state at the time of each interaction.

[0505] Step 4:

[0506] The server uses an emotion engine to analyze emotional data in detail and generate metrics that represent the user's emotional state. Based on this information, an AI agent performs a comprehensive performance evaluation. This is integrated with other business metrics to create detailed performance reports for each user.

[0507] Step 5:

[0508] The server develops a training plan based on the generated performance evaluation. Based on emotional data, it suggests specific programs aimed at improving stress management or communication skills, for example.

[0509] Step 6:

[0510] The device presents the user with a training plan and the results of an emotional analysis. The user can then begin training after reviewing specific improvement strategies linked to their own emotional tendencies.

[0511] Step 7:

[0512] The server generates reports based on long-term accumulated sentiment data and performance evaluations to support strategies for overall store operations and staff training, and provides these reports to administrators. This process aims to improve the operational efficiency of the entire organization.

[0513] (Example 2)

[0514] 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."

[0515] In sales operations, there is a challenge in systematically evaluating and developing staff skills. Furthermore, it is difficult to grasp the emotional state of individual staff members in real time and identify areas for performance improvement. Traditional methods are insufficient in providing evaluations and training that consider the emotional aspects of staff. Moreover, there is a need to integrate work data and emotional data to provide more personalized feedback, thereby improving staff capabilities and operational efficiency.

[0516] 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.

[0517] In this invention, the server includes means for recording work data and emotional data, means for analyzing the recorded work data and emotional data to generate evaluations corresponding to work activities and emotional states, and means for presenting personalized training plans based on the evaluation results. This enables skill evaluation that includes the emotional aspects of staff, making it possible to provide more accurate feedback and training plans.

[0518] "Business data" refers to a series of pieces of information related to staff members' work activities, such as sales performance, customer service time, and customer feedback.

[0519] "Emotional data" refers to data that indicates a user's emotional state by analyzing their voice tone and facial expressions.

[0520] "Evaluation" refers to comprehensive evaluation information that takes into account staff members' work performance and emotional aspects, generated by analyzing work data and emotional data.

[0521] A "training plan" is an individualized learning and practice plan based on evaluation results, aimed at improving staff skills and reducing stress.

[0522] A "generative AI model" refers to artificial intelligence technology used for data analysis, specifically a model that has the function of identifying a user's emotional state and proposing the optimal improvement measures.

[0523] A "user terminal" is an information device used by sales staff to input business data and access evaluation results and training plans.

[0524] "Feedback" refers to specific suggestions and advice provided based on the staff member's emotional state, aimed at improving their work performance.

[0525] A "store-wide performance report" is a document that automatically generates based on aggregated operational data and evaluation results, showing the operational efficiency and performance of the store.

[0526] This invention is a system designed to improve the efficiency of sales operations and enhance staff skills. The system collects operational and emotional data and generates evaluation and training plans based on that data.

[0527] The server receives work data entered from terminals in real time and securely stores it in a database. This data includes information about the staff's daily work activities. In addition, the emotion engine analyzes the user's voice tone and facial expression data and records it as emotion data. The emotion engine implements a proprietary algorithm, enabling advanced emotion recognition.

[0528] The server uses a generative AI model to analyze stored business and emotional data. The AI ​​agent analyzes the data characteristics in detail and generates a comprehensive evaluation that takes into account the user's business performance and emotional aspects. This evaluation clearly shows the user's strengths and areas for improvement, directly leading to skill improvement for the user.

[0529] The terminal displays evaluation results and feedback sent from the server. The visually organized evaluation allows users to understand their own work performance and emotional tendencies, enabling them to take concrete actions for improvement. Furthermore, the training plan takes into account the user's past behavioral patterns, providing an optimal learning experience tailored to individual needs.

[0530] For example, if the emotion engine detects that a user is showing some anxiety during a customer interaction, the server will recommend a training plan that includes stress management sessions. This training will include simulations, enabling the user to interact with customers with confidence. An example of a prompt would be, "Generate appropriate feedback based on the user's emotion analysis."

[0531] In this way, the system integrates and evaluates the user's emotional aspects and business data, providing personalized support to achieve effective skill development and improved work efficiency.

[0532] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0533] Step 1:

[0534] Users input business data into a terminal. This business data includes sales performance, customer service time, and customer feedback. The entered data is sent from the terminal to a server. The server receives the data, encrypts it, and stores it in a database. The stored business data is used as basic information necessary for evaluating user performance.

[0535] Step 2:

[0536] The emotion engine analyzes the user's voice tone and facial expressions in real time. It uses the device's camera and microphone to acquire necessary emotional state information and outputs it as emotional data. The server receives the emotional data transmitted from the emotion engine and stores it in a database. This allows the user's emotional aspects to be used in evaluations along with business data.

[0537] Step 3:

[0538] The server requests data analysis from an AI agent using stored business and sentiment data. The AI ​​agent analyzes the input data using a generative AI model and generates an evaluation that takes into account the user's business performance and emotional impact. This analysis detects outliers and trends in the data and performs calculations to obtain an overall performance evaluation.

[0539] Step 4:

[0540] The server sends the evaluation results generated by the AI ​​agent to the terminal. The terminal visually displays the evaluation results to the user. Specifically, it provides detailed evaluation information and feedback using graphs and dashboards. This allows the user to check their own work performance and emotional state and obtain necessary information for improvement.

[0541] Step 5:

[0542] The server analyzes long-term accumulated emotional data to understand the user's stress level and emotional patterns. Based on this analysis, it generates an individualized training plan. The generated training plan focuses on specific skills and stress management, suggesting an appropriate training program.

[0543] Step 6:

[0544] The server sends the created training plan to the terminal. The terminal displays the training plan to the user, presenting specific learning and practice items. The user can then take actions to improve their skills according to these training plans. Specific examples of training include interactive simulations and situational response training.

[0545] (Application Example 2)

[0546] 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."

[0547] Traditionally, evaluating and improving the work and interpersonal skills of sales staff has been difficult because it has been challenging to consider their actual emotional states, making standardized evaluation difficult. Furthermore, the provision of feedback and training plans to staff has been uniform, lacking appropriate approaches based on individual emotional tendencies. This has resulted in insufficient efforts to maintain staff motivation and improve the quality of service provided to customers.

[0548] 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.

[0549] In this invention, the server includes means for recording work activities, means for analyzing the recorded work information and generating evaluations corresponding to job activities, means for recognizing the user's emotional state, means for analyzing the recognized emotions and evaluating the interpersonal skills of sales staff, means for detecting emotions in real time using video and audio from a smart device, and means for providing personalized feedback aligned with emotional tendencies based on the analysis results. This makes it possible to provide more accurate evaluations and training plans that take into account the emotional characteristics of individual sales staff.

[0550] "Duties" refers to all job activities performed by sales staff in stores, and includes sales-related activities such as customer service and inventory management.

[0551] "Evaluation" is a process that involves quantifying and qualitatively analyzing work performance and staff interpersonal skills, and using the results to identify staff skill levels and areas for improvement.

[0552] A "training plan" is a plan that outlines specific learning programs and activities for sales staff to improve their skills based on evaluation results.

[0553] "Schedule management" refers to activities aimed at efficiently managing staff work schedules and understanding the progress of their work.

[0554] "Users" refers to sales staff and managers at stores that use this system.

[0555] "Emotional state" refers to the psychological and physiological state of the user, and is the internal emotional state that can be perceived from facial expressions and tone of voice.

[0556] "Analysis" is the process of analyzing recorded data using machine learning and statistical methods to extract useful information and patterns.

[0557] A "smart device" is an electronic device that connects to the internet and provides multifunctional services using integrated applications; it typically refers to mobile phones and tablets.

[0558] "Real-time" refers to a state where data is processed and analyzed immediately the moment it is generated, a time characteristic that enables immediate responses to users.

[0559] "Feedback" refers to evaluation results and suggestions provided to users, with the aim of improving work processes and enhancing skills.

[0560] This invention provides a system for improving staff skills and performing sentiment analysis in sales operations. This system primarily consists of three elements: a server, a smart device, and a user.

[0561] The server records business data and stores it in a database. This data includes information such as sales performance, customer interaction time, and customer feedback. When analyzing this recorded business data, the server uses AI models such as TensorFlow and PyTorch to evaluate sales skills. Furthermore, the server analyzes the user's voice tone and facial expression data, and uses acoustic and image analysis technologies to recognize emotional states. This process utilizes cloud services such as Google Cloud Vision API and Amazon Rekognition.

[0562] Smart devices, worn by users during customer service interactions, collect real-time audio and video data. This data is transmitted to a server for detailed analysis through emotion recognition. The analysis results are provided to the user as personalized feedback tailored to their emotional tendencies, allowing them to re-evaluate their work and communication style.

[0563] For example, if a sales staff member frequently exhibits negative emotions while serving customers, the server detects this and displays feedback on the smart device prompting them to implement stress management techniques. In conjunction with this, the smart device is also provided with video links for relaxation exercises and breathing techniques.

[0564] An example of a prompt might be, "Please propose the optimal architecture for building an emotional feedback system for store staff. Emotion recognition will use facial expressions and voice analysis." Through this prompt, the AI ​​model can learn how to provide more appropriate evaluations and feedback to the user.

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] The user puts on a smart device and begins work. The smart device activates its camera and microphone, collecting the user's voice and video data in real time. This data is transmitted to a server via the network. The input is the user's voice and video data, and the output is the raw data sent to the server.

[0568] Step 2:

[0569] The server analyzes the received audio and video data. It uses the Google Cloud Vision API and Amazon Rekognition to detect changes in facial expressions and Google Cloud Speech-to-Text to analyze speech tone, thereby recognizing the user's emotional state. The input is the user's audio and video data, and the output is parameters indicating the user's emotional state.

[0570] Step 3:

[0571] The server uses an AI model (TensorFlow or PyTorch) to evaluate sales skills based on emotion recognition results and business data stored in a database beforehand. Specifically, it inputs past performance metrics and current emotion data into the model and generates a quantified evaluation result. The input is business data and emotion state data, and the output is the sales skill evaluation result.

[0572] Step 4:

[0573] The server uses the generated sales skills assessment results to create personalized feedback for the user. This feedback includes training plans tailored to emotional tendencies and stress management advice. The input is the sales skills assessment results, and the output is the feedback and training plan information.

[0574] Step 5:

[0575] The server sends feedback and training plans to the user's smart device, which then displays them. This allows the user to review their emotional tendencies and work performance and implement necessary improvements. The input is the feedback and training plan, and the output is the information displayed on the smart device.

[0576] 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.

[0577] 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.

[0578] 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.

[0579] [Fourth Embodiment]

[0580] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0581] 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.

[0582] 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).

[0583] 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.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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".

[0593] This invention is a system for streamlining the skill evaluation and training of sales staff. This system utilizes an AI agent to analyze staff work data, generate skill evaluations, and propose training plans.

[0594] The server collects daily work data entered by users (sales staff) using terminals and stores it in a central database. This data entry includes sales performance, customer interaction time, and customer feedback. This information is essential for evaluating the current performance of the staff.

[0595] The server uses the collected data to analyze staff performance through an AI agent. The analysis yields a skill evaluation for each staff member, generating a relative ranking. This ranking differs for each staff member, based on factors such as work efficiency and customer service skills.

[0596] The terminal visually displays the evaluation results received from the server to the user. After understanding the evaluation, the user reviews the training plan proposed by the AI ​​agent. This training plan includes e-learning materials and information on in-house training aimed at improving specific skills.

[0597] Furthermore, customer feedback is processed on a server using sentiment analysis tools. Sentiment analysis extracts customer emotions from text data and uses this information to evaluate the interpersonal skills of sales staff. This allows users to clearly understand their strengths and areas for improvement.

[0598] As a concrete example, suppose a user has short customer service times and receives low ratings from feedback. Based on this data, the server's AI agent analyzes the information and presents the user with a training plan aimed at improving their interpersonal skills. In this way, an appropriate training approach based on individual feedback can improve the user's skills and improve overall store performance.

[0599] This system not only supports the evaluation and training of sales staff, but also serves as a valuable tool for improving the overall operational efficiency of the store.

[0600] The following describes the processing flow.

[0601] Step 1:

[0602] After completing their daily tasks, users input business data, including sales figures, customer service time, and customer feedback, using a terminal. The terminal automatically transmits the entered data to the server.

[0603] Step 2:

[0604] The server stores the received business data in a database. Based on the stored data, an AI agent is used to begin evaluating staff performance. The AI ​​agent analyzes each data point and quantifies sales performance and the quality of customer service.

[0605] Step 3:

[0606] The server generates skill evaluation scores for each staff member based on the data analysis results. These scores include indicators such as sales efficiency, customer satisfaction, and communication skills. These indicators determine the relative positioning of each staff member.

[0607] Step 4:

[0608] The server sends the generated skill assessment score to the terminal. The terminal visually displays the detailed assessment results to the user. The user reviews the displayed information and checks their work performance.

[0609] Step 5:

[0610] The AI ​​agent creates an appropriate training plan based on the evaluation results. The server sends this training plan to the terminal. The terminal displays the training plan to the user, including specific improvement actions. For example, it may suggest learning materials aimed at improving specific skills or notify the user of available training dates.

[0611] Step 6:

[0612] The server performs sentiment analysis on collected customer feedback and incorporates the results into the user's interpersonal skills evaluation. It clarifies customer emotions and intentions, and identifies areas for improvement in customer service.

[0613] Step 7:

[0614] Based on all evaluations and feedback, the server identifies each user's growth trend and supports goal setting for the next evaluation period. This allows individual staff members to develop plans for improving their own performance.

[0615] (Example 1)

[0616] 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".

[0617] In modern sales operations, accurately evaluating the individual performance of sales staff and developing effective training plans is challenging. Furthermore, while detailed performance reports are essential for improving employee performance and efficient store operations, this also represents a significant burden. Additionally, properly analyzing customer feedback and utilizing it to improve interpersonal skills is crucial.

[0618] 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.

[0619] In this invention, the server includes means for recording business information in sales operations, means for analyzing the recorded business information and generating evaluations corresponding to business activities, and means for collecting customer feedback and performing sentiment analysis. This enables precise evaluation of sales employee performance, automation of effective training plan development, and improvement of interpersonal skills evaluation based on customer feedback.

[0620] "Sales operations" refers to a series of activities and processes carried out with the aim of providing goods or services.

[0621] "Business information" refers to all data and records related to sales, including sales performance, customer service status, and feedback.

[0622] "Analysis" refers to the process of processing and handling collected information and data to gain useful insights.

[0623] "Evaluation" is the act of measuring the performance of individuals or processes based on specific criteria and determining their value or effectiveness.

[0624] A "development plan" refers to a set of learning and growth steps and policies designed to improve the capabilities of individual employees.

[0625] "Timetable management" refers to the process of adjusting and managing time to ensure that work and activities proceed efficiently and according to plan.

[0626] "Sentiment analysis" is a technique that reads emotions from information such as text data, and is used to understand customer opinions and feedback.

[0627] "Interpersonal skills" refer to the skills and attitudes necessary for communicating efficiently and effectively with others.

[0628] This invention is a system for automating employee skill evaluation and training planning in sales operations. This system utilizes multiple basic hardware and software components to efficiently manage and analyze sales-related business information.

[0629] The server collects business information such as sales performance, customer service time, and feedback entered by users through their terminals, and stores it in a central database. This server uses a cloud-based database management system (DBMS) to perform high-speed and secure data storage.

[0630] Next, the server analyzes the collected business information using a generative AI model. This analysis process utilizes machine learning algorithms to evaluate the skills and performance of individual employees. The analysis results include performance trend analysis and detailed evaluations of specific skills.

[0631] Furthermore, customer feedback is processed through a sentiment analysis tool. This tool uses natural language processing (NLP) techniques to analyze text data and extract customer emotions. The specific software used for this process utilizes open-source NLP libraries.

[0632] The terminal provides visual feedback to the user based on analysis results received from the server. The evaluation results are displayed through a user-friendly interface. Furthermore, the generated training plan includes suggestions for e-learning modules and in-house training.

[0633] For example, if a user is evaluated as having short customer service times, the server uses an AI agent to further analyze the data and present the user with an appropriate training plan. This training plan includes details of online courses and on-the-job training to improve interpersonal skills.

[0634] An example of a prompt is: "To evaluate sales staff, please have the AI ​​agent analyze sales performance, customer interaction time, and feedback data from the past month, and propose a training plan aimed at improving specific skills." This prompt represents a specific analysis request to the AI ​​model.

[0635] In this way, this system can improve overall operational efficiency by analyzing the performance of sales staff in detail and providing individualized training support.

[0636] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0637] Step 1:

[0638] The server receives business information such as sales performance, customer service time, and customer feedback entered by users through terminals. The received data is stored in a central database in real time. The specific actions performed here are to validate the entered business information and record it in the database according to the format. The output is a well-organized dataset of business information.

[0639] Step 2:

[0640] The server retrieves business information stored in a central database and performs analysis using a generated AI model. The inputs required for this analysis include sales performance and customer interaction history. Based on this input data, the server performs trend analysis and anomaly detection to generate performance evaluations for each employee. Specifically, it executes machine learning algorithms to calculate evaluation scores and ranks. The output is performance evaluation data for each employee.

[0641] Step 3:

[0642] The server generates a training plan using the analysis results. The inputs for generating this training plan are each employee's performance evaluation and the sentiment analysis results of customer feedback. The server integrates this data to generate a training plan aimed at improving specific skills. Specifically, it assembles a list of e-learning materials and training courses that address the user's weaknesses. The output is an individual training plan.

[0643] Step 4:

[0644] The terminal presents the user with performance evaluations and training plans provided by the server. This process requires incoming data as input to visually display both evaluation results and training plans. Based on this data, the terminal displays the information in a user-friendly graphical interface. Specifically, it displays data on a dashboard and supports the user in viewing detailed information. The output consists of evaluation and training information that the user can visually verify.

[0645] Step 5:

[0646] Based on the evaluation results and training plan displayed on the device, users take action to improve their skills. User input includes providing feedback and deciding whether to participate in training. Users utilize this information to participate in educational or training plans to address their weaknesses. Specific actions include registering for online courses and scheduling training sessions. Outputs include improved skills and adjusted work performance.

[0647] (Application Example 1)

[0648] 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".

[0649] In modern retail, improving the skills of sales staff is a crucial factor directly impacting customer satisfaction and sales. However, individually evaluating each staff member and proposing efficient training plans is time-consuming and costly. In addition, systems that can provide solutions for improving interpersonal skills using customer feedback are not yet widespread. This presents a challenge in maximizing the potential of sales staff.

[0650] 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.

[0651] In this invention, the server includes a device for recording business-related data, a device for analyzing the recorded data and generating an evaluation based on activity efficiency, and a device for presenting a learning plan based on the evaluation results. This makes it possible to efficiently evaluate the skills of sales staff and automatically propose individually optimized training plans. Furthermore, real-time business support provides an environment in which sales staff can immediately implement improvement measures.

[0652] "Business-related data" refers to information related to sales activities, including sales performance, customer service time, and customer feedback.

[0653] A "device" is a combination of hardware or software designed to perform a specific function.

[0654] "Analysis" is the process of examining collected data in detail and extracting patterns and information from that data.

[0655] "Activity efficiency" refers to the ability to achieve maximum results with minimum resources when performing a certain task.

[0656] A "device for generating evaluations" is a device that measures staff performance based on data and calculates quantified evaluation results.

[0657] A "learning plan" is an educational framework designed to improve specific skills or knowledge.

[0658] "Real-time business support" refers to a system that enables immediate support and information provision during work.

[0659] This system aims to improve the skills of sales staff and increase operational efficiency. The server collects operational data and stores it in a central database. This data includes sales performance, customer service time, and customer feedback.

[0660] The server utilizes AI models to analyze the collected data. For example, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the data and generate evaluations based on the sales staff's work activities.

[0661] Furthermore, the server automatically creates an optimal learning plan for each sales staff member based on the generated evaluation results. The learning plan includes suggestions for e-learning materials and training sessions to improve specific skills.

[0662] The terminal visually displays information so that sales staff, who are the users, can easily check the evaluation results and learning plans. The terminal also provides real-time support for work, offering staff necessary feedback and hints when interacting with customers.

[0663] As a concrete example, suppose a sales staff member enters feedback into a terminal after finishing a conversation with a customer. The server analyzes this feedback and performs sentiment analysis. Based on the results, it updates the evaluation of the staff member's interpersonal skills and immediately suggests improvement measures.

[0664] By utilizing generative AI models, each evaluation and suggestion is always provided in an up-to-date state, allowing sales staff to continuously improve their skills. A specific example of an input prompt for the generative AI model is, "Based on the sales activity data and customer feedback of a new sales staff member, please suggest a training plan to improve their interpersonal skills."

[0665] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0666] Step 1:

[0667] The user enters sales activity data into the terminal. This data includes sales performance, customer service time, and customer feedback. The terminal formats this data and sends it to the server.

[0668] Step 2:

[0669] The server stores the received data in a central database. During storage, it verifies data integrity and integrates it with existing data.

[0670] Step 3:

[0671] The server performs data analysis based on the stored data. Using machine learning frameworks such as TensorFlow and PyTorch, it extracts data features and generates an evaluation of the sales staff's activity efficiency. The inputs used are sales performance and customer service time, and the output is a skill evaluation.

[0672] Step 4:

[0673] Using the generated evaluations as prompts, a generating AI model is used to create a learning plan for each sales staff member. The AI ​​model takes evaluation data as input and provides an optimized training plan as output.

[0674] Step 5:

[0675] The terminal visually displays the evaluation results and learning plan received from the server to the user. The user reviews this and understands the training content necessary to improve their skills.

[0676] Step 6:

[0677] When users interact with customers, the terminal provides real-time support. The server utilizes historical data to instantly send appropriate feedback and hints to the user. This allows users to improve their interaction skills on the spot.

[0678] 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.

[0679] This invention is a system that incorporates emotion recognition, a crucial element in the skill evaluation and training of sales staff. Using an AI agent and emotion engine, this system not only analyzes staff work data and provides work evaluations and training plans, but also detects and analyzes the emotions of staff and customers in real time.

[0680] The server retrieves business data entered by users through their terminals and stores it in a database. This business data includes sales performance, customer service time, customer feedback, and information about the user's emotional state. The emotion engine recognizes emotions from the user's voice tone and facial expressions and stores this information in the database.

[0681] The server uses business and emotional data for an AI agent to analyze and generate a comprehensive assessment of the user's business and interpersonal skills. This assessment incorporates emotion recognition results, taking into account the impact of the user's emotional aspects on performance. In this way, the assessment becomes more accurate and can clearly identify areas for improvement tailored to each individual staff member.

[0682] The terminal displays evaluation results sent from the server to the user. The display includes a business performance evaluation obtained through analysis, along with feedback based on the user's emotional state. This allows users to improve their skills while being aware of their own emotional tendencies.

[0683] Furthermore, the server analyzes each user's emotional tendencies over the long term, measuring stress levels and emotional patterns during customer interactions. Based on this analysis, it provides users with appropriate training plans and supports them in reducing stress and strengthening interpersonal skills. The server sends these training plans to the terminal, presenting users with appropriate improvement measures and resources.

[0684] For example, if the emotion engine detects that a user frequently experiences negative emotions during customer service, the server will suggest stress management training to that staff member based on the user's work performance. In this way, the entire system evaluates and incorporates the user's emotional characteristics into training, providing more personalized support, improving staff skills, and increasing overall store operational efficiency.

[0685] The following describes the processing flow.

[0686] Step 1:

[0687] Users input simple business data using a terminal during sales activities. The terminal provides functions to quickly record sales figures and customer information through voice recognition and touch operation.

[0688] Step 2:

[0689] When users interact with customers, real-time voice and facial expression data is collected through the device's camera and microphone. The emotion engine analyzes this data to recognize the emotions of the user and the customer.

[0690] Step 3:

[0691] The terminal sends the acquired emotional information to the server. The server processes the emotional data so that it is linked to the business database and saves the emotional state at the time of each interaction.

[0692] Step 4:

[0693] The server uses an emotion engine to analyze emotional data in detail and generate metrics that represent the user's emotional state. Based on this information, an AI agent performs a comprehensive performance evaluation. This is integrated with other business metrics to create detailed performance reports for each user.

[0694] Step 5:

[0695] The server develops a training plan based on the generated performance evaluation. Based on emotional data, it suggests specific programs aimed at improving stress management or communication skills, for example.

[0696] Step 6:

[0697] The device presents the user with a training plan and the results of an emotional analysis. The user can then begin training after reviewing specific improvement strategies linked to their own emotional tendencies.

[0698] Step 7:

[0699] The server generates reports based on long-term accumulated sentiment data and performance evaluations to support strategies for overall store operations and staff training, and provides these reports to administrators. This process aims to improve the operational efficiency of the entire organization.

[0700] (Example 2)

[0701] 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".

[0702] In sales operations, there is a challenge in systematically evaluating and developing staff skills. Furthermore, it is difficult to grasp the emotional state of individual staff members in real time and identify areas for performance improvement. Traditional methods are insufficient in providing evaluations and training that consider the emotional aspects of staff. Moreover, there is a need to integrate work data and emotional data to provide more personalized feedback, thereby improving staff capabilities and operational efficiency.

[0703] 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.

[0704] In this invention, the server includes means for recording work data and emotional data, means for analyzing the recorded work data and emotional data to generate evaluations corresponding to work activities and emotional states, and means for presenting personalized training plans based on the evaluation results. This enables skill evaluation that includes the emotional aspects of staff, making it possible to provide more accurate feedback and training plans.

[0705] "Business data" refers to a series of pieces of information related to staff members' work activities, such as sales performance, customer service time, and customer feedback.

[0706] "Emotional data" refers to data that indicates a user's emotional state by analyzing their voice tone and facial expressions.

[0707] "Evaluation" refers to comprehensive evaluation information that takes into account staff members' work performance and emotional aspects, generated by analyzing work data and emotional data.

[0708] A "training plan" is an individualized learning and practice plan based on evaluation results, aimed at improving staff skills and reducing stress.

[0709] A "generative AI model" refers to artificial intelligence technology used for data analysis, specifically a model that has the function of identifying a user's emotional state and proposing the optimal improvement measures.

[0710] A "user terminal" is an information device used by sales staff to input business data and access evaluation results and training plans.

[0711] "Feedback" refers to specific suggestions and advice provided based on the staff member's emotional state, aimed at improving their work performance.

[0712] A "store-wide performance report" is a document that automatically generates based on aggregated operational data and evaluation results, showing the operational efficiency and performance of the store.

[0713] This invention is a system designed to improve the efficiency of sales operations and enhance staff skills. The system collects operational and emotional data and generates evaluation and training plans based on that data.

[0714] The server receives work data entered from terminals in real time and securely stores it in a database. This data includes information about the staff's daily work activities. In addition, the emotion engine analyzes the user's voice tone and facial expression data and records it as emotion data. The emotion engine implements a proprietary algorithm, enabling advanced emotion recognition.

[0715] The server uses a generative AI model to analyze stored business and emotional data. The AI ​​agent analyzes the data characteristics in detail and generates a comprehensive evaluation that takes into account the user's business performance and emotional aspects. This evaluation clearly shows the user's strengths and areas for improvement, directly leading to skill improvement for the user.

[0716] The terminal displays evaluation results and feedback sent from the server. The visually organized evaluation allows users to understand their own work performance and emotional tendencies, enabling them to take concrete actions for improvement. Furthermore, the training plan takes into account the user's past behavioral patterns, providing an optimal learning experience tailored to individual needs.

[0717] For example, if the emotion engine detects that a user is showing some anxiety during a customer interaction, the server will recommend a training plan that includes stress management sessions. This training will include simulations, enabling the user to interact with customers with confidence. An example of a prompt would be, "Generate appropriate feedback based on the user's emotion analysis."

[0718] In this way, the system integrates and evaluates the user's emotional aspects and business data, providing personalized support to achieve effective skill development and improved work efficiency.

[0719] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0720] Step 1:

[0721] Users input business data into a terminal. This business data includes sales performance, customer service time, and customer feedback. The entered data is sent from the terminal to a server. The server receives the data, encrypts it, and stores it in a database. The stored business data is used as basic information necessary for evaluating user performance.

[0722] Step 2:

[0723] The emotion engine analyzes the user's voice tone and facial expressions in real time. It uses the device's camera and microphone to acquire necessary emotional state information and outputs it as emotional data. The server receives the emotional data transmitted from the emotion engine and stores it in a database. This allows the user's emotional aspects to be used in evaluations along with business data.

[0724] Step 3:

[0725] The server requests data analysis from an AI agent using stored business and sentiment data. The AI ​​agent analyzes the input data using a generative AI model and generates an evaluation that takes into account the user's business performance and emotional impact. This analysis detects outliers and trends in the data and performs calculations to obtain an overall performance evaluation.

[0726] Step 4:

[0727] The server sends the evaluation results generated by the AI ​​agent to the terminal. The terminal visually displays the evaluation results to the user. Specifically, it provides detailed evaluation information and feedback using graphs and dashboards. This allows the user to check their own work performance and emotional state and obtain necessary information for improvement.

[0728] Step 5:

[0729] The server analyzes long-term accumulated emotional data to understand the user's stress level and emotional patterns. Based on this analysis, it generates an individualized training plan. The generated training plan focuses on specific skills and stress management, suggesting an appropriate training program.

[0730] Step 6:

[0731] The server sends the created training plan to the terminal. The terminal displays the training plan to the user, presenting specific learning and practice items. The user can then take actions to improve their skills according to these training plans. Specific examples of training include interactive simulations and situational response training.

[0732] (Application Example 2)

[0733] 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".

[0734] Traditionally, evaluating and improving the work and interpersonal skills of sales staff has been difficult because it has been challenging to consider their actual emotional states, making standardized evaluation difficult. Furthermore, the provision of feedback and training plans to staff has been uniform, lacking appropriate approaches based on individual emotional tendencies. This has resulted in insufficient efforts to maintain staff motivation and improve the quality of service provided to customers.

[0735] 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.

[0736] In this invention, the server includes means for recording work activities, means for analyzing the recorded work information and generating evaluations corresponding to job activities, means for recognizing the user's emotional state, means for analyzing the recognized emotions and evaluating the interpersonal skills of sales staff, means for detecting emotions in real time using video and audio from a smart device, and means for providing personalized feedback aligned with emotional tendencies based on the analysis results. This makes it possible to provide more accurate evaluations and training plans that take into account the emotional characteristics of individual sales staff.

[0737] "Duties" refers to all job activities performed by sales staff in stores, and includes sales-related activities such as customer service and inventory management.

[0738] "Evaluation" is a process that involves quantifying and qualitatively analyzing work performance and staff interpersonal skills, and using the results to identify staff skill levels and areas for improvement.

[0739] A "training plan" is a plan that outlines specific learning programs and activities for sales staff to improve their skills based on evaluation results.

[0740] "Schedule management" refers to activities aimed at efficiently managing staff work schedules and understanding the progress of their work.

[0741] "Users" refers to sales staff and managers at stores that use this system.

[0742] "Emotional state" refers to the psychological and physiological state of the user, and is the internal emotional state that can be perceived from facial expressions and tone of voice.

[0743] "Analysis" is the process of analyzing recorded data using machine learning and statistical methods to extract useful information and patterns.

[0744] A "smart device" is an electronic device that connects to the internet and provides multifunctional services using integrated applications; it typically refers to mobile phones and tablets.

[0745] "Real-time" refers to a state where data is processed and analyzed immediately the moment it is generated, a time characteristic that enables immediate responses to users.

[0746] "Feedback" refers to evaluation results and suggestions provided to users, with the aim of improving work processes and enhancing skills.

[0747] This invention provides a system for improving staff skills and performing sentiment analysis in sales operations. This system primarily consists of three elements: a server, a smart device, and a user.

[0748] The server records business data and stores it in a database. This data includes information such as sales performance, customer interaction time, and customer feedback. When analyzing this recorded business data, the server uses AI models such as TensorFlow and PyTorch to evaluate sales skills. Furthermore, the server analyzes the user's voice tone and facial expression data, and uses acoustic and image analysis technologies to recognize emotional states. This process utilizes cloud services such as Google Cloud Vision API and Amazon Rekognition.

[0749] Smart devices, worn by users during customer service interactions, collect real-time audio and video data. This data is transmitted to a server for detailed analysis through emotion recognition. The analysis results are provided to the user as personalized feedback tailored to their emotional tendencies, allowing them to re-evaluate their work and communication style.

[0750] For example, if a sales staff member frequently exhibits negative emotions while serving customers, the server detects this and displays feedback on the smart device prompting them to implement stress management techniques. In conjunction with this, the smart device is also provided with video links for relaxation exercises and breathing techniques.

[0751] An example of a prompt might be, "Please propose the optimal architecture for building an emotional feedback system for store staff. Emotion recognition will use facial expressions and voice analysis." Through this prompt, the AI ​​model can learn how to provide more appropriate evaluations and feedback to the user.

[0752] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0753] Step 1:

[0754] The user puts on a smart device and begins work. The smart device activates its camera and microphone, collecting the user's voice and video data in real time. This data is transmitted to a server via the network. The input is the user's voice and video data, and the output is the raw data sent to the server.

[0755] Step 2:

[0756] The server analyzes the received audio and video data. It uses the Google Cloud Vision API and Amazon Rekognition to detect changes in facial expressions and Google Cloud Speech-to-Text to analyze speech tone, thereby recognizing the user's emotional state. The input is the user's audio and video data, and the output is parameters indicating the user's emotional state.

[0757] Step 3:

[0758] The server uses an AI model (TensorFlow or PyTorch) to evaluate sales skills based on emotion recognition results and business data stored in a database beforehand. Specifically, it inputs past performance metrics and current emotion data into the model and generates a quantified evaluation result. The input is business data and emotion state data, and the output is the sales skill evaluation result.

[0759] Step 4:

[0760] The server uses the generated sales skills assessment results to create personalized feedback for the user. This feedback includes training plans tailored to emotional tendencies and stress management advice. The input is the sales skills assessment results, and the output is the feedback and training plan information.

[0761] Step 5:

[0762] The server sends feedback and training plans to the user's smart device, which then displays them. This allows the user to review their emotional tendencies and work performance and implement necessary improvements. The input is the feedback and training plan, and the output is the information displayed on the smart device.

[0763] 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.

[0764] 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.

[0765] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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."

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] The following is further disclosed regarding the embodiments described above.

[0785] (Claim 1)

[0786] Means for recording business data in sales operations,

[0787] A means for analyzing recorded business data and generating evaluations corresponding to business activities,

[0788] A means of presenting a training plan based on the evaluation results,

[0789] A means of managing schedules based on business data and evaluation results,

[0790] Methods for collecting customer feedback and performing sentiment analysis,

[0791] A system that includes a means of evaluating the interpersonal skills of sales staff based on the results of emotional analysis.

[0792] (Claim 2)

[0793] The system according to claim 1, which displays evaluation results and a training plan on a user terminal.

[0794] (Claim 3)

[0795] The system according to claim 1, which automatically generates a store-wide performance report using business data and evaluation results.

[0796] "Example 1"

[0797] (Claim 1)

[0798] Means for recording business information in sales operations,

[0799] A means for analyzing recorded business information and generating evaluations corresponding to business activities,

[0800] A means of presenting a training plan based on the evaluation results,

[0801] A means of managing timetables based on business information and evaluation results,

[0802] A means of collecting customer opinions and performing sentiment analysis,

[0803] A system that includes a means of evaluating the interpersonal skills of sales employees based on the results of emotional analysis.

[0804] (Claim 2)

[0805] The system according to claim 1, which displays evaluation results and training plans on a user terminal.

[0806] (Claim 3)

[0807] The system according to claim 1, which automatically generates a performance report for the entire facility using business information and evaluation results.

[0808] "Application Example 1"

[0809] (Claim 1)

[0810] A device for recording business-related data,

[0811] A device that analyzes recorded data and generates an evaluation based on activity efficiency,

[0812] A device that presents a learning plan based on evaluation results,

[0813] A device that performs planning and management based on data and evaluation results,

[0814] A device that collects user opinions and performs sentiment analysis,

[0815] A device that evaluates interpersonal skills in sales work based on the results of emotional analysis,

[0816] A system that includes a device that provides real-time business support based on input data.

[0817] (Claim 2)

[0818] The system according to claim 1, which displays evaluation results and a learning plan on a device for the user.

[0819] (Claim 3)

[0820] The system according to claim 1, which automatically generates a performance report for the entire facility using business data and evaluation results.

[0821] "Example 2 of combining an emotion engine"

[0822] (Claim 1)

[0823] Means for recording business data and emotional data,

[0824] A means for analyzing recorded work data and emotional data to generate evaluations corresponding to work activities and emotional states,

[0825] A means of presenting a personalized training plan based on the evaluation results,

[0826] A method for analyzing users' emotional tendencies over the long term and adjusting training plans while considering stress levels and emotional patterns,

[0827] A method for proposing optimal improvement measures based on the user's emotional state using a generative AI model,

[0828] A system that includes means for visually displaying evaluation results and training plans on a user terminal.

[0829] (Claim 2)

[0830] The system according to claim 1, which displays evaluation results generated from business data and emotional data on a user terminal and provides feedback based on the emotional state.

[0831] (Claim 3)

[0832] The system according to claim 1, which automatically generates a store-wide performance report based on business data and evaluation results, thereby supporting the improvement of operational efficiency.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] Means for recording work,

[0836] A means for analyzing recorded work information and generating evaluations corresponding to job activities,

[0837] A means of presenting a training plan based on the evaluation results,

[0838] A means of managing schedules based on work information and evaluation results,

[0839] Means for recognizing the emotional state of the user,

[0840] A means of analyzing perceived emotions and evaluating the interpersonal skills of sales staff,

[0841] A means of detecting emotions in real time using video and audio from smart devices,

[0842] A system that includes means for providing personalized feedback tailored to emotional tendencies based on analysis results.

[0843] (Claim 2)

[0844] The system according to claim 1, which displays evaluation results and training plans on the user's information processing device and provides feedback based on emotional tendencies.

[0845] (Claim 3)

[0846] The system according to claim 1, which automatically generates an overall performance report for the organization using business information and evaluation results, and provides a guidance plan that takes emotional tendencies into consideration. [Explanation of symbols]

[0847] 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. Means for recording business data in sales operations, A means for analyzing recorded business data and generating evaluations corresponding to business activities, A means of presenting a training plan based on the evaluation results, A means of managing schedules based on business data and evaluation results, Methods for collecting customer feedback and performing sentiment analysis, A system that includes a means of evaluating the interpersonal skills of sales staff based on the results of emotional analysis.

2. The system according to claim 1, which displays evaluation results and a training plan on a user terminal.

3. The system according to claim 1, which automatically generates a store-wide performance report using business data and evaluation results.

Images