system

Abstract

We provide the system. [Solution] Means of collecting sales representative data, A means for analyzing the data to generate parameters that characterize the work environment, A means of matching sales representatives in similar work environments, Means of providing online training, Methods for evaluating performance after training, A method of rewarding sales representatives who provide success stories, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current sales business, there is a problem that it is difficult to improve the performance of individual salespersons because the sharing of know-how among salespersons is limited. In addition, the lack of opportunities to quickly and effectively learn successful cases in similar business environments hinders skill improvement. Furthermore, since there is no appropriate incentive for salespersons who have achieved results, the motivation to promote knowledge sharing is insufficient.

Means for Solving the Problems

[0005] This invention provides a means for collecting data on sales representatives, analyzing this data, and parameterizing the characteristics of their work environment. Next, it constructs a means for matching sales representatives in similar work environments based on this data, and aims to improve each representative's skills by providing continuous online training. Furthermore, it strengthens the motivation for knowledge sharing by providing a means for evaluating post-training performance and rewarding representatives who provide successful case studies.

[0006] A "sales representative" refers to an individual responsible for selling products or services to customers.

[0007] "Data" refers to information related to sales operations, including sales volume, customer feedback, and sales figures by product category.

[0008] "Analysis" is the act of systematically examining collected data and using that data to understand the store environment and operational patterns.

[0009] A "parameter" is a numerical or indicator-based quantification of a specific work environment or work pattern.

[0010] "Matching" refers to the process of finding sales representatives in similar work environments and enabling them to interact and share information with each other.

[0011] "Online training" refers to educational programs conducted via the internet, either in real time or on demand.

[0012] "Performance evaluation" is the process of measuring and evaluating the performance of sales representatives after training.

[0013] "Compensation" refers to points or other forms of payment provided as an incentive to sales representatives who provide success stories. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and its embodiment is shown below. This system mainly consists of three elements: a server, a terminal, and a user.

[0036] Data collection and analysis

[0037] The server receives sales representative data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server analyzes this data and generates parameters to quantify the work environment for each store.

[0038] Matching similar crews

[0039] The server uses the generated parameters to identify sales representatives with similar work environments. In doing so, it considers past performance and success stories to match representatives with the most effective expertise.

[0040] Online training

[0041] Once matching is complete, the device displays an invitation to online training from the successful sales representative. This training can be conducted in real-time or on-demand, for example, through web conferencing or video materials. Users can deepen their learning through case studies similar to their own work environment.

[0042] Performance evaluation and compensation after training

[0043] Once the training is complete, the server monitors the users' performance data and evaluates improvements in sales performance and customer satisfaction. If performance improves, the server rewards the sales representatives who shared their success stories. This reward is provided in the form of crew points and functions as an incentive.

[0044] Specific example

[0045] First, suppose a terminal at a certain store sends recent daily sales reports and customer reviews to a server. Based on this information, the server identifies store-specific challenges and searches for other stores that are solving similar problems. Finally, it matches the user with a representative from a successful store and shares problem-solving know-how in a webinar format. After the training, it is found that the user's sales efficiency has improved by 30%, so the server awards points to the successful representative.

[0046] This system is expected to practically improve the individual work capabilities of sales representatives and enhance overall business performance.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server receives data about sales representatives from terminals in each store. This data includes sales volume, customer feedback, and sales by product category.

[0050] Step 2:

[0051] The server analyzes the received data. Here, it quantifies the unique operational environment of each store and generates parameters. These parameters reflect factors such as the store's location, customer base, and the characteristics of the products it handles.

[0052] Step 3:

[0053] The server identifies sales representatives with similar characteristics based on the generated parameters. During this process, past performance data is also considered, and representatives with a proven track record of success are given priority.

[0054] Step 4:

[0055] Based on instructions from the server, the terminal displays an invitation to an online training session with a successful case study representative for the user (sales representative). The user can then review the training details and decide whether to participate.

[0056] Step 5:

[0057] Users participate in online training using their devices. This training allows them to learn about successful case studies and actual work processes.

[0058] Step 6:

[0059] After the training is completed, the server continuously monitors the user's sales performance. It analyzes whether there has been an increase in sales volume or an improvement in customer satisfaction.

[0060] Step 7:

[0061] If improved performance is confirmed, the server will reward the sales representative who provided the success story with crew points. This strengthens the incentive for information sharing.

[0062] (Example 1)

[0063] 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."

[0064] In modern sales, improving the individual skills of salespeople and optimizing operational efficiency are crucial challenges. However, there is a lack of effective support systems that enable individual salespeople to independently learn from successful practices and apply them to their work environment. As a result, there is a problem of inconsistency in sales performance and stagnation in overall organizational performance.

[0065] 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.

[0066] In this invention, the server includes means for collecting information on salespeople, means for processing said information to generate indicators that characterize their work situation, and means for associating salespeople in similar work situations. This enables effective sharing of know-how, leading to improved salespeople skills and increased work efficiency.

[0067] A "salesperson" refers to an employee whose job is to introduce and sell products and services to customers.

[0068] "Means of gathering information" refers to the processes and methods used to collect specific data or information from various sources and devices.

[0069] "Means of processing information to generate indicators that characterize business conditions" refers to methods for analyzing collected data and creating evaluation criteria and parameters that quantify and represent the business environment and conditions.

[0070] "Means of linking salespeople in similar work situations" refers to the process of identifying and connecting salespeople who have similar work environments and conditions.

[0071] "Means of providing online education" refers to the technologies and methods used to deliver learning content and educational programs to students via the internet.

[0072] "Means for determining results" refers to indicators and methods used to evaluate the results obtained after training or activities and to measure their effectiveness.

[0073] "Means of awarding rewards" refers to systems and methods for providing rewards or incentives to salespeople based on their performance and contributions.

[0074] This invention provides a system in which a server, terminal, and user work in cooperation with each other, in order to improve the efficiency of sales operations and enhance the capabilities of the person in charge.

[0075] The server collects sales staff data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server uses data analysis software such as Python's Pandas and NumPy to analyze this data. This generates parameters that characterize the operational status of each store.

[0076] Based on the generated parameters, the server uses an SQL database to identify salespeople in similar work situations. An algorithm is then executed to extract highly similar salespeople, referencing past success stories, and to correlate those with the most effective expertise.

[0077] The device provides users with online training from successful salespeople. The training utilizes an internet-based learning platform and can be both real-time and on-demand. Communication tools such as the Zoom API are used to schedule and conduct actual training sessions.

[0078] After the training is complete, the server re-analyzes the user's performance data to evaluate increases in sales and improvements in customer satisfaction. This allows the effectiveness of the sales staff's work improvements to be determined.

[0079] Furthermore, salespeople who provide success stories are automatically awarded rewards from the server based on a points system. These rewards serve as incentives that can be used for future training or to obtain additional materials.

[0080] As a concrete example, users can learn more advanced sales strategies by entering a prompt for the generative AI model such as, "Please tell me the most effective sales methods used in stores with similar crews." Through this system, it is expected that user efficiency and performance will improve, leading to improved overall organizational performance.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server collects sales staff data from terminals in each store. This input data includes daily sales quantities, customer feedback, and sales information by product category. The server structures the received data and stores it in a database. Storing the data in a format that is easy to use for subsequent analysis enables efficient information access.

[0084] Step 2:

[0085] The server analyzes the collected data and generates parameters that characterize the operational status of each store. Using Python's Pandas and NumPy, it aggregates the data and calculates metrics such as sales and customer satisfaction. The output at this stage is a dataset that quantifies the performance of each store. This enables quantitative operational evaluation.

[0086] Step 3:

[0087] The server uses the generated business parameters to identify salespeople in similar business situations. It references an SQL database and compares it with past success stories to extract salespeople with the closest match. This process employs heuristic algorithms to improve the accuracy of the associations. The output generates a matching list of highly relevant salespeople.

[0088] Step 4:

[0089] The terminal displays a guide to provide users with online training from successful salespeople. Using the Zoom API, it automatically generates and presents links to training sessions. The input here is a matching list from the server, and the output is a schedule of training sessions. Users can then attend online training sessions according to the provided schedule.

[0090] Step 5:

[0091] After a user completes online training, the server re-evaluates their work performance. It analyzes the increase in sales data and improvements in customer feedback to quantify the effectiveness of the training. This generates a report measuring the user's performance improvement. Based on these results, sales staff are rewarded through a points system.

[0092] Through the process described above, users can efficiently improve their skills and effectively enhance their work performance.

[0093] (Application Example 1)

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

[0095] Traditional systems for improving the efficiency and skills of sales representatives primarily focused on data-driven analysis and training, but lacked real-time support during actual work. In particular, in situations requiring immediate responses in the sales field, there were limited means to quickly utilize past success stories and feedback. This limited the ability to improve responsiveness and the quality of work.

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

[0097] In this invention, the server includes means for collecting sales representative data, means for displaying advice information in real time via smart devices, and means for evaluating performance after training. This enables sales representatives to refer to feedback and success stories in real time while on duty, thereby enhancing their ability to respond immediately and improving work efficiency.

[0098] A "sales representative" is a person whose job is to provide products or services to customers.

[0099] "Means of collecting data" refers to technical devices or methods for gathering relevant information from sales representatives.

[0100] "Parameters that characterize the work environment" are quantified indicators that specifically describe the environment in which sales representatives operate.

[0101] "Matching methods" refer to ways of connecting sales representatives who work in similar environments or under similar conditions.

[0102] "Means of providing online training" refers to the technical infrastructure for providing educational and training opportunities via the internet.

[0103] "Methods for evaluating post-training performance" refer to technical processes for analyzing sales representatives' performance and areas for improvement in order to measure the effectiveness of training.

[0104] "Providing success stories" refers to methods of communicating positive results and valuable experiences achieved in the past to other sales representatives.

[0105] "Means of rewarding" refers to technical procedures for providing monetary or non-monetary rewards to sales representatives who achieve results.

[0106] "Means for displaying advisory information in real time via smart devices" refers to devices or software that use the internet or wireless communication to immediately display support information.

[0107] In order to implement this invention, it is necessary to build a system in which servers, terminals, smart devices, and users interact with each other.

[0108] The server collects data from sales representatives and stores it in a database. This includes sales volume, customer feedback, and sales by product category. The collected data is then converted into parameters that quantify the business environment using analytical software. Typical analytical tools used here include data analysis libraries such as Python and R.

[0109] After data analysis, the server identifies and matches sales representatives with similar work environments. This process takes into account past success stories and performance.

[0110] Next, the device provides online training to designated sales representatives. This training is conducted via web conferencing tools and video streaming platforms, allowing users to learn case studies relevant to their actual work. Real-time learning facilitates rapid understanding and practical application.

[0111] Smart devices provide real-time advisory information to sales representatives during their work. For example, smart glasses can instantly display information on solutions to current challenges and relevant success stories. Augmented reality technologies such as ARToolkit are used for this purpose.

[0112] When user performance improvement is confirmed, the server evaluates the results and rewards the sales representative who provided the success story. This reward is provided as a points system and functions as an incentive.

[0113] For example, if a salesperson determines that sales of a new product are below target, the smart glasses will display an advice message such as, "Sales of the new product are below target. Refer to success stories to strengthen your sales strategy." This entire sequence of information is optimized by a generative AI model.

[0114] An example of a prompt for a generative AI model is: "Sales of our new product are below target. Please generate suggestions to improve this situation."

[0115] This allows sales representatives to conduct more effective sales activities in real time, resulting in improved operational efficiency.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server collects data from sales representatives. This input data includes sales volume, customer feedback, and sales by product. The server stores this data in storage and prepares it for subsequent analysis processes. It also performs normalization processes to standardize the data format.

[0119] Step 2:

[0120] The server analyzes the collected data. This analysis process uses Python libraries to generate parameters that characterize the work environment. It outputs numerical indicators based on statistical methods derived from the input data, revealing specific sales trends and customer reaction patterns.

[0121] Step 3:

[0122] The server matches sales representatives with similar work environments based on the parameters generated by the analysis. This step involves comparison calculations using past success stories and sales performance data as references. The output is a list of matched sales representatives.

[0123] Step 4:

[0124] The device provides matching sales representatives with information about online training. The device displays links to web conferencing tools and video streaming platforms, allowing users to participate in training in real-time or on-demand. Users can learn practical case studies by clicking the appropriate links and viewing training materials.

[0125] Step 5:

[0126] Users with smart devices receive real-time advice during their work. Devices such as smart glasses utilize AI models generated from collected data to display advice messages based on prompts. Specifically, they project necessary information onto the screen according to sales status and customer behavior.

[0127] Step 6:

[0128] The server collects and evaluates user performance data after training. Input data includes changes in sales performance and customer satisfaction. This data is analyzed to measure success and generate an evaluation report. Based on this evaluation, a reward system is implemented. The output is a list of how many reward points were awarded.

[0129] 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.

[0130] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and by incorporating an emotion engine, it enables the provision of more personalized training. To that end, it mainly consists of four elements: a server, a terminal, a user, and an emotion engine.

[0131] Data collection and analysis

[0132] The server receives sales representative work data from each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and parameters are generated to quantify the store's work environment based on this information. In addition, the emotion engine analyzes facial expressions, tone of voice, and words used to recognize the emotional state of the sales representative, who is the user.

[0133] Similar crew matching and emotion-based customization

[0134] Based on the generated parameters, the server identifies sales representatives in similar work environments. Once a match is made with a representative who has a successful track record, the server customizes the training content and progression to suit the user's emotional state based on the analysis results of the emotion engine.

[0135] Implementation of online training

[0136] The device displays matching results and personalized online training information to the user. The user reviews the training content and receives support to facilitate participation. During the training, the emotion engine continuously monitors the user's emotions and adjusts the content as needed.

[0137] Performance evaluation and compensation after training

[0138] After the training is complete, the server monitors the user's performance and evaluates, for example, increases in sales volume and improvements in customer satisfaction. If improvements in performance are confirmed, the server rewards the sales representative who provided the success story with crew points.

[0139] Specific example

[0140] For example, by analyzing sales data received through a terminal and the emotional state of employees, the server matches a veteran employee "A" who has achieved success in a similar environment with a new employee "B". If the emotional engine detects an increase in the stress level of new employee "B", the difficulty level of the training is appropriately adjusted, allowing for gradual skill improvement. If it is confirmed that new employee "B"'s performance has improved after the training, veteran employee "A" is awarded points.

[0141] In this way, by utilizing the emotional engine, it is possible to provide appropriate training tailored to each individual sales representative and to continuously and effectively improve business operations.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server receives work data from sales staff at each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and based on this, it generates parameters that quantify the work environment.

[0145] Step 2:

[0146] The emotion engine analyzes the salesperson's facial expressions, tone of voice, and vocabulary. This allows it to recognize the user's emotional state in real time and evaluate their stress level and motivation.

[0147] Step 3:

[0148] The server uses the generated parameters to identify sales representatives who have achieved success in similar work environments. In doing so, it considers past success stories and matches the most suitable representatives.

[0149] Step 4:

[0150] The device displays matching results to the user, along with personalized online training information based on analysis by the emotion engine. The user reviews the training details and prepares to participate.

[0151] Step 5:

[0152] Users participate in online training using their devices. During the training, an emotion engine continuously monitors the user's emotional state, and adjusts the training content and pace as needed.

[0153] Step 6:

[0154] Once the training is complete, the server monitors the user's performance data and evaluates, for example, improvements in sales volume and customer satisfaction.

[0155] Step 7:

[0156] If performance improves, the server will reward the sales representatives who provided success stories. These rewards are provided as crew points and serve as an incentive for knowledge sharing.

[0157] (Example 2)

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

[0159] To improve the skills of sales personnel and increase operational efficiency, training tailored to individual work environments and emotional states is essential. However, traditional methods have faced challenges in providing individualized support and effectively evaluating and reflecting the results after implementation.

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

[0161] In this invention, the server includes means for collecting business data of individuals related to sales, means for evaluating the emotional state of users using emotion analysis technology, means for identifying individuals with similar work environments based on the data and evaluation results, and means for personalizing training content based on the evaluation results. This enables the provision of training optimized for individual work environments and emotional states, resulting in efficient and effective skill development.

[0162] "Business data" refers to information obtained from sales activities and interactions with customers, including sales volume, revenue information, and customer feedback.

[0163] "Emotional analysis technology" is a technology that recognizes and quantifies a user's emotional state by evaluating their facial expressions, tone of voice, and spoken language.

[0164] "Similar work environments" refer to the characteristics of work conditions that are common to different sellers, and are expressed using generated numerical indicators.

[0165] "Personalized training" refers to an educational program tailored to each user's work data and emotional state.

[0166] "Evaluation results" refer to user performance indicators derived from the analysis of emotional data obtained through emotion analysis technology and business data.

[0167] "Online training" refers to educational programs delivered via the internet, a form of training that is accessible without relying on physical classrooms.

[0168] "Rewards" refer to incentives given to individuals who provide success stories, and are offered in the form of points, bonuses, or other similar benefits.

[0169] This invention is a system primarily composed of a server, terminals, users, and sentiment analysis technology. First, the server periodically collects sales-related business data from each terminal in the store. During this process, it accesses a database via the network to obtain sales volume, sales information by product category, customer feedback, and other data. The terminals have the function of automatically transmitting this data to the server.

[0170] The server uses data analysis software to analyze the collected business data. This software automatically generates metrics to quantify the business environment of each store and saves them to storage. Next, by introducing sentiment analysis technology, the terminals collect user facial expression data and voice data and send them to the server. Sentiment analysis is performed using a machine learning model to determine the user's current emotional state.

[0171] Identifying individuals with similar work environments is performed by a dedicated algorithm within the server. This algorithm is based on numerical data of the work environment and emotional states. Based on this data, the server generates training programs tailored to each user. For example, users with high stress levels will be offered training programs that include a lot of relaxing content.

[0172] Online training is accessible from the user's device and is conducted in real time. Users' emotional states are monitored throughout the training, and the server adjusts the training content as needed. In this way, a more personalized and effective learning experience is provided.

[0173] At the end of the training, the server monitors the users' work performance, and if improvement is confirmed, the person who provided the success story will be rewarded. The reward will mainly be in the form of points.

[0174] A concrete example is matching experienced employees who have achieved success in similar environments with new employees based on sales data and emotional states received by the server from terminals. In this case, a generative AI model can be used with the prompt, "Analyze the sales data received from terminals and the emotional states of employees, and match experienced senior employees who have achieved success in similar environments with new employees." The AI ​​will then appropriately analyze the data and perform the optimal matching.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server collects sales-related business data from terminals. Inputs include sales volume, sales information by product category, and customer feedback. Terminals send this data to the server after business hours or at a specified time. The server stores the received data in a database, preparing it for subsequent processing.

[0178] Step 2:

[0179] The server analyzes collected business data and generates metrics that quantify the work environment. Inputs include data such as sales volume and customer feedback. Analysis software processes this data to generate numerical metrics for evaluating sales fluctuation patterns and customer satisfaction. The output consists of numerical data representing the work environment for each individual employee.

[0180] Step 3:

[0181] The device collects the user's facial expression and voice data and sends it to the server. The input for this step is the user's video and audio information. The device captures this in real time and uploads it to the server for emotion analysis.

[0182] Step 4:

[0183] The server uses emotion analysis technology to evaluate the user's emotional state. Inputs include facial expression data and voice data received from the terminal. The server uses a generative AI model to recognize the user's stress level and motivation and generate evaluation results. The output is emotional state data for each user.

[0184] Step 5:

[0185] The server identifies individuals with similar environments based on quantified work environment data and emotional state data. Using an algorithm, it analyzes the input numerical and emotional data and matches different users with similar characteristics. The output is a list of user pairs resulting from the matching.

[0186] Step 6:

[0187] The server personalizes the training program based on the matching results. Input information includes the matched user pairs and their sentiment analysis results. The server uses this information to create a program optimized for stress reduction and skill development. The output is a personalized online training program.

[0188] Step 7:

[0189] The terminal notifies users of personalized training programs and assists in their implementation. Users review and participate in the training content through the terminal. The terminal reassesss the user's emotional state in real time and sends data to the server to adjust the training content as needed.

[0190] Step 8:

[0191] The server monitors the work performance of users after training. Inputs include sales data and customer feedback after training. The server analyzes the data to evaluate the impact of matching and training on work performance. If improved performance is confirmed, points are awarded to the relevant users as a reward. Outputs include work performance evaluation data and reward point information.

[0192] (Application Example 2)

[0193] 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".

[0194] The challenge lies in improving the work efficiency of users engaged in sales roles and effectively enhancing their skills through individualized training. In particular, it is necessary to dynamically adjust training content according to the emotional state of the users, but achieving this requires advanced analytical techniques and flexible responses.

[0195] 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.

[0196] In this invention, the server includes means for analyzing the personal attributes and commercial transaction information of users engaged in sales duties to generate components that characterize the work environment, means for comparing users in similar work environments, and means for analyzing emotional states and dynamically adjusting training programs. This enables the provision of training adapted to the individual emotional states of users, thereby improving the efficiency of sales duties.

[0197] "Users engaged in sales duties" refers to employees or staff involved in the sales of products.

[0198] "Personal attributes" refer to information that describes an individual's characteristics, including, for example, personality, experience, and skill level.

[0199] "Commercial transaction information" refers to data related to transactions, including sales volume, revenue, and customer feedback.

[0200] "Work environment" refers to the entire work environment, including the location and conditions where users perform their work, as well as the systems and processes involved.

[0201] "Components" refer to the basic elements or parameters that make up a system or process.

[0202] "Users in similar work environments" refers to users engaged in other sales positions in work environments with common work conditions and circumstances.

[0203] "Means of comparison" refers to methods or processes for comparing and relating elements that have similarities.

[0204] "Emotional state" refers to the user's emotions and psychological state, including stress levels and motivation.

[0205] "Means of dynamic adjustment" refers to functions or processes that automatically change their content or methods in response to changing conditions.

[0206] A "training program" refers to educational activities or courses designed to improve users' skills and knowledge.

[0207] The system for implementing this invention includes a server, a terminal, a user, and an emotion engine. The server receives personal attributes and commercial transaction information from users engaged in sales duties, and uses this to generate components that characterize the work environment. Specifically, the server stores various types of information using a database and performs analysis using machine learning algorithms.

[0208] The terminal provides an interface for user access and displays online training programs. The terminal, for example, is a smartphone or tablet and uses software capable of streaming various digital content. At this time, an emotion engine is installed on the terminal, which uses the camera and microphone to analyze the user's emotional state in real time.

[0209] The emotion engine uses analytical software like the Affectiva SDK to recognize the user's facial expressions and tone of voice. This allows the server to understand the user's stress level and motivation, and dynamically adjust the training program content based on that information.

[0210] Users participate in training programs through their devices to improve their skills. After the training is complete, the server analyzes the transaction information again to evaluate the improvement in performance. A concrete example is the process by which new sales staff improve their customer service skills through the training program. During the training, an emotion engine monitors the user's emotional state and adaptively adjusts the program to reduce stress.

[0211] An example of a prompt message might be: "Generate a training program to effectively improve the customer service skills of new sales staff. Propose customized learning content, taking into account the staff's current stress levels and motivation."

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

[0213] Step 1:

[0214] The server receives user attributes and transaction information from terminals for users engaged in sales roles. Input data includes user personality, experience, sales volume, revenue, and customer feedback. The server stores this information in a database and performs data cleansing and preprocessing. The output is data formatted in a parseable format.

[0215] Step 2:

[0216] The server generates components that characterize the work environment based on the received data. Specifically, it applies machine learning algorithms to extract parameters that represent the work environment. The input is the data formatted in the previous step, and the output is the quantified work environment parameters.

[0217] Step 3:

[0218] The server compares other users in similar work environments based on the generated parameters. Clustering techniques are used to identify groups of users with common work conditions. The input is quantified work environment parameters, and the output is a list of the compared users.

[0219] Step 4:

[0220] The terminal displays the training program provided by the server, making it accessible to the user. This program is customized to the user's emotional state. The input is the training program information received from the server, and the output is the training content displayed to the user.

[0221] Step 5:

[0222] The device uses a camera and microphone to capture the user's facial expressions and voice tone, and inputs this data into an emotion engine. The emotion engine analyzes this data to understand the user's emotional state. The input is real-time data obtained from sensors, and the output is numerical data on stress levels and motivation.

[0223] Step 6:

[0224] The server dynamically adjusts the content of the training program based on user emotional state data obtained from the emotion engine. The input is numerical data of the emotional state, and the output is the adjusted training content.

[0225] Step 7:

[0226] Users participate in training programs provided through their devices to improve their skills and knowledge. Specific actions include viewing displayed content and completing assignments.

[0227] Step 8:

[0228] After the training is completed, the server collects commercial transaction information again and performs analysis to evaluate performance improvement. The input is sales data after the training, and the output is the performance evaluation result. This allows us to understand the degree of user growth.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and its embodiment is shown below. This system mainly consists of three elements: a server, a terminal, and a user.

[0246] Data collection and analysis

[0247] The server receives sales representative data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server analyzes this data and generates parameters to quantify the work environment for each store.

[0248] Matching similar crews

[0249] The server uses the generated parameters to identify sales representatives with similar work environments. In doing so, it considers past performance and success stories to match representatives with the most effective expertise.

[0250] Online training

[0251] Once matching is complete, the device displays an invitation to online training from the successful sales representative. This training can be conducted in real-time or on-demand, for example, through web conferencing or video materials. Users can deepen their learning through case studies similar to their own work environment.

[0252] Performance evaluation and compensation after training

[0253] Once the training is complete, the server monitors the users' performance data and evaluates improvements in sales performance and customer satisfaction. If performance improves, the server rewards the sales representatives who shared their success stories. This reward is provided in the form of crew points and functions as an incentive.

[0254] Specific example

[0255] First, suppose a terminal at a certain store sends recent daily sales reports and customer reviews to a server. Based on this information, the server identifies store-specific challenges and searches for other stores that are solving similar problems. Finally, it matches the user with a representative from a successful store and shares problem-solving know-how in a webinar format. After the training, it is found that the user's sales efficiency has improved by 30%, so the server awards points to the successful representative.

[0256] This system is expected to practically improve the individual work capabilities of sales representatives and enhance overall business performance.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] The server receives data about sales representatives from terminals in each store. This data includes sales volume, customer feedback, and sales by product category.

[0260] Step 2:

[0261] The server analyzes the received data. Here, it quantifies the unique operational environment of each store and generates parameters. These parameters reflect factors such as the store's location, customer base, and the characteristics of the products it handles.

[0262] Step 3:

[0263] The server identifies sales representatives with similar characteristics based on the generated parameters. During this process, past performance data is also considered, and representatives with a proven track record of success are given priority.

[0264] Step 4:

[0265] Based on instructions from the server, the terminal displays an invitation to an online training session with a successful case study representative for the user (sales representative). The user can then review the training details and decide whether to participate.

[0266] Step 5:

[0267] Users participate in online training using their devices. This training allows them to learn about successful case studies and actual work processes.

[0268] Step 6:

[0269] After the training is completed, the server continuously monitors the user's sales performance. It analyzes whether there has been an increase in sales volume or an improvement in customer satisfaction.

[0270] Step 7:

[0271] If improved performance is confirmed, the server will reward the sales representative who provided the success story with crew points. This strengthens the incentive for information sharing.

[0272] (Example 1)

[0273] 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."

[0274] In modern sales, improving the individual skills of salespeople and optimizing operational efficiency are crucial challenges. However, there is a lack of effective support systems that enable individual salespeople to independently learn from successful practices and apply them to their work environment. As a result, there is a problem of inconsistency in sales performance and stagnation in overall organizational performance.

[0275] 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.

[0276] In this invention, the server includes means for collecting information on salespeople, means for processing said information to generate indicators that characterize their work situation, and means for associating salespeople in similar work situations. This enables effective sharing of know-how, leading to improved salespeople skills and increased work efficiency.

[0277] A "salesperson" refers to an employee whose job is to introduce and sell products and services to customers.

[0278] "Means of gathering information" refers to the processes and methods used to collect specific data or information from various sources and devices.

[0279] The means for "processing information to generate indicators characterizing the business situation" is a method for analyzing the collected data and creating evaluation criteria and parameters that numerically represent the business environment and conditions.

[0280] The means for "associating salespersons in similar business situations" refers to the process of identifying salespersons with similar business environments and conditions and linking them together.

[0281] The means for "providing online education" is a technology or method for providing learning content and educational programs to learners using the Internet.

[0282] The means for "judging results" refers to indicators and methods for evaluating the results obtained after training or activities and measuring the effects.

[0283] The means for "awarding rewards" refers to a mechanism or method for awarding rewards and incentives according to the performance and contribution of salespersons.

[0284] In this invention, in order to improve the efficiency of the sales business and the capabilities of the persons in charge, a system is provided in which a server, a terminal, and a user operate in cooperation.

[0285] The server collects data of salespersons from the terminals of each store. The data to be collected includes the quantity of sales, customer feedback, and sales by product category. The server uses Pandas and NumPy of Python, which are data analysis software, to analyze these data. As a result, parameters characterizing the business situation are generated for each store.

[0286] Based on the generated parameters, the server uses an SQL database to identify salespersons in similar business situations. Referring to past successful cases, an algorithm is executed to extract persons in charge with a high degree of similarity and associate salespersons with the most effective know-how with each other.

[0287] The device provides users with online training from successful salespeople. The training utilizes an internet-based learning platform and can be both real-time and on-demand. Communication tools such as the Zoom API are used to schedule and conduct actual training sessions.

[0288] After the training is complete, the server re-analyzes the user's performance data to evaluate increases in sales and improvements in customer satisfaction. This allows the effectiveness of the sales staff's work improvements to be determined.

[0289] Furthermore, salespeople who provide success stories are automatically awarded rewards from the server based on a points system. These rewards serve as incentives that can be used for future training or to obtain additional materials.

[0290] As a concrete example, users can learn more advanced sales strategies by entering a prompt for the generative AI model such as, "Please tell me the most effective sales methods used in stores with similar crews." Through this system, it is expected that user efficiency and performance will improve, leading to improved overall organizational performance.

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] The server collects sales staff data from terminals in each store. This input data includes daily sales quantities, customer feedback, and sales information by product category. The server structures the received data and stores it in a database. Storing the data in a format that is easy to use for subsequent analysis enables efficient information access.

[0294] Step 2:

[0295] The server analyzes the collected data and generates parameters that characterize the operational status of each store. Using Python's Pandas and NumPy, it aggregates the data and calculates metrics such as sales and customer satisfaction. The output at this stage is a dataset that quantifies the performance of each store. This enables quantitative operational evaluation.

[0296] Step 3:

[0297] The server uses the generated business parameters to identify salespeople in similar business situations. It references an SQL database and compares it with past success stories to extract salespeople with the closest match. This process employs heuristic algorithms to improve the accuracy of the associations. The output generates a matching list of highly relevant salespeople.

[0298] Step 4:

[0299] The terminal displays a guide to provide users with online training from successful salespeople. Using the Zoom API, it automatically generates and presents links to training sessions. The input here is a matching list from the server, and the output is a schedule of training sessions. Users can then attend online training sessions according to the provided schedule.

[0300] Step 5:

[0301] After a user completes online training, the server re-evaluates their work performance. It analyzes the increase in sales data and improvements in customer feedback to quantify the effectiveness of the training. This generates a report measuring the user's performance improvement. Based on these results, sales staff are rewarded through a points system.

[0302] Through the process described above, users can efficiently improve their skills and effectively enhance their work performance.

[0303] (Application Example 1)

[0304] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0305] The conventional system for improving the work efficiency and skills of sales representatives mainly focuses on data-based analysis and providing training, and there is a problem that real-time support during actual work is insufficient. In particular, in situations where immediate response at the sales site is required, the means for quickly utilizing past success cases and feedback are limited. As a result, there were limitations in immediate responsiveness and improving the quality of work.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0307] In this invention, the server includes means for collecting data of sales representatives, means for displaying support information in real time via smart devices, and means for evaluating the performance after training. As a result, sales representatives can refer to real-time feedback and success cases even during work, and strengthening immediate response ability and improving work efficiency are realized.

[0308] A "sales representative" is a person who has a position responsible for the business of providing goods and services to customers.

[0309] The "means for collecting data" is a technical device or method for collecting relevant information from sales representatives.

[0310] The "parameters characterizing the business environment" are numerical indicators for specifically representing the environment in which sales representatives operate.

[0311] The "means for matching" is a method for linking sales representatives working under similar environments and conditions.

[0312] "Means of providing online training" refers to the technical infrastructure for providing educational and training opportunities via the internet.

[0313] "Methods for evaluating post-training performance" refer to technical processes for analyzing sales representatives' performance and areas for improvement in order to measure the effectiveness of training.

[0314] "Providing success stories" refers to methods of communicating positive results and valuable experiences achieved in the past to other sales representatives.

[0315] "Means of rewarding" refers to technical procedures for providing monetary or non-monetary rewards to sales representatives who achieve results.

[0316] "Means for displaying advisory information in real time via smart devices" refers to devices or software that use the internet or wireless communication to immediately display support information.

[0317] In order to implement this invention, it is necessary to build a system in which servers, terminals, smart devices, and users interact with each other.

[0318] The server collects data from sales representatives and stores it in a database. This includes sales volume, customer feedback, and sales by product category. The collected data is then converted into parameters that quantify the business environment using analytical software. Typical analytical tools used here include data analysis libraries such as Python and R.

[0319] After data analysis, the server identifies and matches sales representatives with similar work environments. This process takes into account past success stories and performance.

[0320] Next, the device provides online training to designated sales representatives. This training is conducted via web conferencing tools and video streaming platforms, allowing users to learn case studies relevant to their actual work. Real-time learning facilitates rapid understanding and practical application.

[0321] Smart devices provide real-time advisory information to sales representatives during their work. For example, smart glasses can instantly display information on solutions to current challenges and relevant success stories. Augmented reality technologies such as ARToolkit are used for this purpose.

[0322] When user performance improvement is confirmed, the server evaluates the results and rewards the sales representative who provided the success story. This reward is provided as a points system and functions as an incentive.

[0323] For example, if a salesperson determines that sales of a new product are below target, the smart glasses will display an advice message such as, "Sales of the new product are below target. Refer to success stories to strengthen your sales strategy." This entire sequence of information is optimized by a generative AI model.

[0324] An example of a prompt for a generative AI model is: "Sales of our new product are below target. Please generate suggestions to improve this situation."

[0325] This allows sales representatives to conduct more effective sales activities in real time, resulting in improved operational efficiency.

[0326] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0327] Step 1:

[0328] The server collects data from sales representatives. This input data includes sales volume, customer feedback, and sales by product. The server stores this data in storage and prepares it for subsequent analysis processes. It also performs normalization processes to standardize the data format.

[0329] Step 2:

[0330] The server analyzes the collected data. This analysis process uses Python libraries to generate parameters that characterize the work environment. It outputs numerical indicators based on statistical methods derived from the input data, revealing specific sales trends and customer reaction patterns.

[0331] Step 3:

[0332] The server matches sales representatives with similar work environments based on the parameters generated by the analysis. This step involves comparison calculations using past success stories and sales performance data as references. The output is a list of matched sales representatives.

[0333] Step 4:

[0334] The device provides matching sales representatives with information about online training. The device displays links to web conferencing tools and video streaming platforms, allowing users to participate in training in real-time or on-demand. Users can learn practical case studies by clicking the appropriate links and viewing training materials.

[0335] Step 5:

[0336] Users with smart devices receive real-time advice during their work. Devices such as smart glasses utilize AI models generated from collected data to display advice messages based on prompts. Specifically, they project necessary information onto the screen according to sales status and customer behavior.

[0337] Step 6:

[0338] The server collects and evaluates user performance data after training. Input data includes changes in sales performance and customer satisfaction. This data is analyzed to measure success and generate an evaluation report. Based on this evaluation, a reward system is implemented. The output is a list of how many reward points were awarded.

[0339] 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.

[0340] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and by incorporating an emotion engine, it enables the provision of more personalized training. To that end, it mainly consists of four elements: a server, a terminal, a user, and an emotion engine.

[0341] Data collection and analysis

[0342] The server receives sales representative work data from each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and parameters are generated to quantify the store's work environment based on this information. In addition, the emotion engine analyzes facial expressions, tone of voice, and words used to recognize the emotional state of the sales representative, who is the user.

[0343] Similar crew matching and emotion-based customization

[0344] Based on the generated parameters, the server identifies sales representatives in similar work environments. Once a match is made with a representative who has a successful track record, the server customizes the training content and progression to suit the user's emotional state based on the analysis results of the emotion engine.

[0345] Implementation of online training

[0346] The device displays matching results and personalized online training information to the user. The user reviews the training content and receives support to facilitate participation. During the training, the emotion engine continuously monitors the user's emotions and adjusts the content as needed.

[0347] Performance evaluation and compensation after training

[0348] After the training is complete, the server monitors the user's performance and evaluates, for example, increases in sales volume and improvements in customer satisfaction. If improvements in performance are confirmed, the server rewards the sales representative who provided the success story with crew points.

[0349] Specific example

[0350] For example, by analyzing sales data received through a terminal and the emotional state of employees, the server matches a veteran employee "A" who has achieved success in a similar environment with a new employee "B". If the emotional engine detects an increase in the stress level of new employee "B", the difficulty level of the training is appropriately adjusted, allowing for gradual skill improvement. If it is confirmed that new employee "B"'s performance has improved after the training, veteran employee "A" is awarded points.

[0351] In this way, by utilizing the emotional engine, it is possible to provide appropriate training tailored to each individual sales representative and to continuously and effectively improve business operations.

[0352] The following describes the processing flow.

[0353] Step 1:

[0354] The server receives work data from sales staff at each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and based on this, it generates parameters that quantify the work environment.

[0355] Step 2:

[0356] The emotion engine analyzes the salesperson's facial expressions, tone of voice, and vocabulary. This allows it to recognize the user's emotional state in real time and evaluate their stress level and motivation.

[0357] Step 3:

[0358] The server uses the generated parameters to identify sales representatives who have achieved success in similar work environments. In doing so, it considers past success stories and matches the most suitable representatives.

[0359] Step 4:

[0360] The device displays matching results to the user, along with personalized online training information based on analysis by the emotion engine. The user reviews the training details and prepares to participate.

[0361] Step 5:

[0362] Users participate in online training using their devices. During the training, an emotion engine continuously monitors the user's emotional state, and adjusts the training content and pace as needed.

[0363] Step 6:

[0364] Once the training is complete, the server monitors the user's performance data and evaluates, for example, improvements in sales volume and customer satisfaction.

[0365] Step 7:

[0366] If performance improves, the server will reward the sales representatives who provided success stories. These rewards are provided as crew points and serve as an incentive for knowledge sharing.

[0367] (Example 2)

[0368] 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".

[0369] To improve the skills of sales personnel and increase operational efficiency, training tailored to individual work environments and emotional states is essential. However, traditional methods have faced challenges in providing individualized support and effectively evaluating and reflecting the results after implementation.

[0370] 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.

[0371] In this invention, the server includes means for collecting business data of individuals related to sales, means for evaluating the emotional state of users using emotion analysis technology, means for identifying individuals with similar work environments based on the data and evaluation results, and means for personalizing training content based on the evaluation results. This enables the provision of training optimized for individual work environments and emotional states, resulting in efficient and effective skill development.

[0372] "Business data" refers to information obtained from sales activities and interactions with customers, including sales volume, revenue information, and customer feedback.

[0373] "Emotional analysis technology" is a technology that recognizes and quantifies a user's emotional state by evaluating their facial expressions, tone of voice, and spoken language.

[0374] "Similar work environments" refer to the characteristics of work conditions that are common to different sellers, and are expressed using generated numerical indicators.

[0375] "Personalized training" refers to an educational program tailored to each user's work data and emotional state.

[0376] "Evaluation results" refer to user performance indicators derived from the analysis of emotional data obtained through emotion analysis technology and business data.

[0377] "Online training" refers to educational programs delivered via the internet, a form of training that is accessible without relying on physical classrooms.

[0378] "Rewards" refer to incentives given to individuals who provide success stories, and are offered in the form of points, bonuses, or other similar benefits.

[0379] This invention is a system primarily composed of a server, terminals, users, and sentiment analysis technology. First, the server periodically collects sales-related business data from each terminal in the store. During this process, it accesses a database via the network to obtain sales volume, sales information by product category, customer feedback, and other data. The terminals have the function of automatically transmitting this data to the server.

[0380] The server uses data analysis software to analyze the collected business data. This software automatically generates metrics to quantify the business environment of each store and saves them to storage. Next, by introducing sentiment analysis technology, the terminals collect user facial expression data and voice data and send them to the server. Sentiment analysis is performed using a machine learning model to determine the user's current emotional state.

[0381] Identifying individuals with similar work environments is performed by a dedicated algorithm within the server. This algorithm is based on numerical data of the work environment and emotional states. Based on this data, the server generates training programs tailored to each user. For example, users with high stress levels will be offered training programs that include a lot of relaxing content.

[0382] Online training is accessible from the user's device and is conducted in real time. Users' emotional states are monitored throughout the training, and the server adjusts the training content as needed. In this way, a more personalized and effective learning experience is provided.

[0383] At the end of the training, the server monitors the users' work performance, and if improvement is confirmed, the person who provided the success story will be rewarded. The reward will mainly be in the form of points.

[0384] A concrete example is matching experienced employees who have achieved success in similar environments with new employees based on sales data and emotional states received by the server from terminals. In this case, a generative AI model can be used with the prompt, "Analyze the sales data received from terminals and the emotional states of employees, and match experienced senior employees who have achieved success in similar environments with new employees." The AI ​​will then appropriately analyze the data and perform the optimal matching.

[0385] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0386] Step 1:

[0387] The server collects sales-related business data from terminals. Inputs include sales volume, sales information by product category, and customer feedback. Terminals send this data to the server after business hours or at a specified time. The server stores the received data in a database, preparing it for subsequent processing.

[0388] Step 2:

[0389] The server analyzes collected business data and generates metrics that quantify the work environment. Inputs include data such as sales volume and customer feedback. Analysis software processes this data to generate numerical metrics for evaluating sales fluctuation patterns and customer satisfaction. The output consists of numerical data representing the work environment for each individual employee.

[0390] Step 3:

[0391] The device collects the user's facial expression and voice data and sends it to the server. The input for this step is the user's video and audio information. The device captures this in real time and uploads it to the server for emotion analysis.

[0392] Step 4:

[0393] The server uses emotion analysis technology to evaluate the user's emotional state. Inputs include facial expression data and voice data received from the terminal. The server uses a generative AI model to recognize the user's stress level and motivation and generate evaluation results. The output is emotional state data for each user.

[0394] Step 5:

[0395] The server identifies individuals with similar environments based on quantified work environment data and emotional state data. Using an algorithm, it analyzes the input numerical and emotional data and matches different users with similar characteristics. The output is a list of user pairs resulting from the matching.

[0396] Step 6:

[0397] The server personalizes the training program based on the matching results. Input information includes the matched user pairs and their sentiment analysis results. The server uses this information to create a program optimized for stress reduction and skill development. The output is a personalized online training program.

[0398] Step 7:

[0399] The terminal notifies users of personalized training programs and assists in their implementation. Users review and participate in the training content through the terminal. The terminal reassesss the user's emotional state in real time and sends data to the server to adjust the training content as needed.

[0400] Step 8:

[0401] The server monitors the work performance of users after training. Inputs include sales data and customer feedback after training. The server analyzes the data to evaluate the impact of matching and training on work performance. If improved performance is confirmed, points are awarded to the relevant users as a reward. Outputs include work performance evaluation data and reward point information.

[0402] (Application Example 2)

[0403] 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."

[0404] The challenge lies in improving the work efficiency of users engaged in sales roles and effectively enhancing their skills through individualized training. In particular, it is necessary to dynamically adjust training content according to the emotional state of the users, but achieving this requires advanced analytical techniques and flexible responses.

[0405] 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.

[0406] In this invention, the server includes means for analyzing the personal attributes and commercial transaction information of users engaged in sales duties to generate components that characterize the work environment, means for comparing users in similar work environments, and means for analyzing emotional states and dynamically adjusting training programs. This enables the provision of training adapted to the individual emotional states of users, thereby improving the efficiency of sales duties.

[0407] "Users engaged in sales duties" refers to employees or staff involved in the sales of products.

[0408] "Personal attributes" refer to information that describes an individual's characteristics, including, for example, personality, experience, and skill level.

[0409] "Commercial transaction information" refers to data related to transactions, including sales volume, revenue, and customer feedback.

[0410] "Work environment" refers to the entire work environment, including the location and conditions where users perform their work, as well as the systems and processes involved.

[0411] "Components" refer to the basic elements or parameters that make up a system or process.

[0412] "Users in similar work environments" refers to users engaged in other sales positions in work environments with common work conditions and circumstances.

[0413] "Means of comparison" refers to methods or processes for comparing and relating elements that have similarities.

[0414] "Emotional state" refers to the user's emotions and psychological state, including stress levels and motivation.

[0415] "Means of dynamic adjustment" refers to functions or processes that automatically change their content or methods in response to changing conditions.

[0416] A "training program" refers to educational activities or courses designed to improve users' skills and knowledge.

[0417] The system for implementing this invention includes a server, a terminal, a user, and an emotion engine. The server receives personal attributes and commercial transaction information from users engaged in sales duties, and uses this to generate components that characterize the work environment. Specifically, the server stores various types of information using a database and performs analysis using machine learning algorithms.

[0418] The terminal provides an interface for user access and displays online training programs. The terminal, for example, is a smartphone or tablet and uses software capable of streaming various digital content. At this time, an emotion engine is installed on the terminal, which uses the camera and microphone to analyze the user's emotional state in real time.

[0419] The emotion engine uses analytical software like the Affectiva SDK to recognize the user's facial expressions and tone of voice. This allows the server to understand the user's stress level and motivation, and dynamically adjust the training program content based on that information.

[0420] Users participate in training programs through their devices to improve their skills. After the training is complete, the server analyzes the transaction information again to evaluate the improvement in performance. A concrete example is the process by which new sales staff improve their customer service skills through the training program. During the training, an emotion engine monitors the user's emotional state and adaptively adjusts the program to reduce stress.

[0421] An example of a prompt message might be: "Generate a training program to effectively improve the customer service skills of new sales staff. Propose customized learning content, taking into account the staff's current stress levels and motivation."

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The server receives user attributes and transaction information from terminals for users engaged in sales roles. Input data includes user personality, experience, sales volume, revenue, and customer feedback. The server stores this information in a database and performs data cleansing and preprocessing. The output is data formatted in a parseable format.

[0425] Step 2:

[0426] The server generates components that characterize the work environment based on the received data. Specifically, it applies machine learning algorithms to extract parameters that represent the work environment. The input is the data formatted in the previous step, and the output is the quantified work environment parameters.

[0427] Step 3:

[0428] The server compares other users in similar work environments based on the generated parameters. Clustering techniques are used to identify groups of users with common work conditions. The input is quantified work environment parameters, and the output is a list of the compared users.

[0429] Step 4:

[0430] The terminal displays the training program provided by the server, making it accessible to the user. This program is customized to the user's emotional state. The input is the training program information received from the server, and the output is the training content displayed to the user.

[0431] Step 5:

[0432] The device uses a camera and microphone to capture the user's facial expressions and voice tone, and inputs this data into an emotion engine. The emotion engine analyzes this data to understand the user's emotional state. The input is real-time data obtained from sensors, and the output is numerical data on stress levels and motivation.

[0433] Step 6:

[0434] The server dynamically adjusts the content of the training program based on user emotional state data obtained from the emotion engine. The input is numerical data of the emotional state, and the output is the adjusted training content.

[0435] Step 7:

[0436] Users participate in training programs provided through their devices to improve their skills and knowledge. Specific actions include viewing displayed content and completing assignments.

[0437] Step 8:

[0438] After the training is completed, the server collects commercial transaction information again and performs analysis to evaluate performance improvement. The input is sales data after the training, and the output is the performance evaluation result. This allows us to understand the degree of user growth.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Third Embodiment]

[0443] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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".

[0455] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and its embodiment is shown below. This system mainly consists of three elements: a server, a terminal, and a user.

[0456] Data collection and analysis

[0457] The server receives sales representative data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server analyzes this data and generates parameters to quantify the work environment for each store.

[0458] Matching similar crews

[0459] The server uses the generated parameters to identify sales representatives with similar work environments. In doing so, it considers past performance and success stories to match representatives with the most effective expertise.

[0460] Online training

[0461] Once matching is complete, the device displays an invitation to online training from the successful sales representative. This training can be conducted in real-time or on-demand, for example, through web conferencing or video materials. Users can deepen their learning through case studies similar to their own work environment.

[0462] Performance evaluation and compensation after training

[0463] Once the training is complete, the server monitors the users' performance data and evaluates improvements in sales performance and customer satisfaction. If performance improves, the server rewards the sales representatives who shared their success stories. This reward is provided in the form of crew points and functions as an incentive.

[0464] Specific example

[0465] First, suppose a terminal at a certain store sends recent daily sales reports and customer reviews to a server. Based on this information, the server identifies store-specific challenges and searches for other stores that are solving similar problems. Finally, it matches the user with a representative from a successful store and shares problem-solving know-how in a webinar format. After the training, it is found that the user's sales efficiency has improved by 30%, so the server awards points to the successful representative.

[0466] This system is expected to practically improve the individual work capabilities of sales representatives and enhance overall business performance.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server receives data about sales representatives from terminals in each store. This data includes sales volume, customer feedback, and sales by product category.

[0470] Step 2:

[0471] The server analyzes the received data. Here, it quantifies the unique operational environment of each store and generates parameters. These parameters reflect factors such as the store's location, customer base, and the characteristics of the products it handles.

[0472] Step 3:

[0473] The server identifies sales representatives with similar characteristics based on the generated parameters. During this process, past performance data is also considered, and representatives with a proven track record of success are given priority.

[0474] Step 4:

[0475] Based on instructions from the server, the terminal displays an invitation to an online training session with a successful case study representative for the user (sales representative). The user can then review the training details and decide whether to participate.

[0476] Step 5:

[0477] Users participate in online training using their devices. This training allows them to learn about successful case studies and actual work processes.

[0478] Step 6:

[0479] After the training is completed, the server continuously monitors the user's sales performance. It analyzes whether there has been an increase in sales volume or an improvement in customer satisfaction.

[0480] Step 7:

[0481] If improved performance is confirmed, the server will reward the sales representative who provided the success story with crew points. This strengthens the incentive for information sharing.

[0482] (Example 1)

[0483] 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."

[0484] In modern sales, improving the individual skills of salespeople and optimizing operational efficiency are crucial challenges. However, there is a lack of effective support systems that enable individual salespeople to independently learn from successful practices and apply them to their work environment. As a result, there is a problem of inconsistency in sales performance and stagnation in overall organizational performance.

[0485] 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.

[0486] In this invention, the server includes means for collecting information on salespeople, means for processing said information to generate indicators that characterize their work situation, and means for associating salespeople in similar work situations. This enables effective sharing of know-how, leading to improved salespeople skills and increased work efficiency.

[0487] A "salesperson" refers to an employee whose job is to introduce and sell products and services to customers.

[0488] "Means of gathering information" refers to the processes and methods used to collect specific data or information from various sources and devices.

[0489] "Means of processing information to generate indicators that characterize business conditions" refers to methods for analyzing collected data and creating evaluation criteria and parameters that quantify and represent the business environment and conditions.

[0490] "Means of linking salespeople in similar work situations" refers to the process of identifying and connecting salespeople who have similar work environments and conditions.

[0491] "Means of providing online education" refers to the technologies and methods used to deliver learning content and educational programs to students via the internet.

[0492] "Means for determining results" refers to indicators and methods used to evaluate the results obtained after training or activities and to measure their effectiveness.

[0493] "Means of awarding rewards" refers to systems and methods for providing rewards or incentives to salespeople based on their performance and contributions.

[0494] This invention provides a system in which a server, terminal, and user work in cooperation with each other, in order to improve the efficiency of sales operations and enhance the capabilities of the person in charge.

[0495] The server collects sales staff data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server uses data analysis software such as Python's Pandas and NumPy to analyze this data. This generates parameters that characterize the operational status of each store.

[0496] Based on the generated parameters, the server uses an SQL database to identify salespeople in similar work situations. An algorithm is then executed to extract highly similar salespeople, referencing past success stories, and to correlate those with the most effective expertise.

[0497] The device provides users with online training from successful salespeople. The training utilizes an internet-based learning platform and can be both real-time and on-demand. Communication tools such as the Zoom API are used to schedule and conduct actual training sessions.

[0498] After the training is complete, the server re-analyzes the user's performance data to evaluate increases in sales and improvements in customer satisfaction. This allows the effectiveness of the sales staff's work improvements to be determined.

[0499] Furthermore, salespeople who provide success stories are automatically awarded rewards from the server based on a points system. These rewards serve as incentives that can be used for future training or to obtain additional materials.

[0500] As a concrete example, users can learn more advanced sales strategies by entering a prompt for the generative AI model such as, "Please tell me the most effective sales methods used in stores with similar crews." Through this system, it is expected that user efficiency and performance will improve, leading to improved overall organizational performance.

[0501] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0502] Step 1:

[0503] The server collects sales staff data from terminals in each store. This input data includes daily sales quantities, customer feedback, and sales information by product category. The server structures the received data and stores it in a database. Storing the data in a format that is easy to use for subsequent analysis enables efficient information access.

[0504] Step 2:

[0505] The server analyzes the collected data and generates parameters that characterize the operational status of each store. Using Python's Pandas and NumPy, it aggregates the data and calculates metrics such as sales and customer satisfaction. The output at this stage is a dataset that quantifies the performance of each store. This enables quantitative operational evaluation.

[0506] Step 3:

[0507] The server uses the generated business parameters to identify salespeople in similar business situations. It references an SQL database and compares it with past success stories to extract salespeople with the closest match. This process employs heuristic algorithms to improve the accuracy of the associations. The output generates a matching list of highly relevant salespeople.

[0508] Step 4:

[0509] The terminal displays a guide to provide users with online training from successful salespeople. Using the Zoom API, it automatically generates and presents links to training sessions. The input here is a matching list from the server, and the output is a schedule of training sessions. Users can then attend online training sessions according to the provided schedule.

[0510] Step 5:

[0511] After a user completes online training, the server re-evaluates their work performance. It analyzes the increase in sales data and improvements in customer feedback to quantify the effectiveness of the training. This generates a report measuring the user's performance improvement. Based on these results, sales staff are rewarded through a points system.

[0512] Through the process described above, users can efficiently improve their skills and effectively enhance their work performance.

[0513] (Application Example 1)

[0514] 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."

[0515] Traditional systems for improving the efficiency and skills of sales representatives primarily focused on data-driven analysis and training, but lacked real-time support during actual work. In particular, in situations requiring immediate responses in the sales field, there were limited means to quickly utilize past success stories and feedback. This limited the ability to improve responsiveness and the quality of work.

[0516] 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.

[0517] In this invention, the server includes means for collecting sales representative data, means for displaying advice information in real time via smart devices, and means for evaluating performance after training. This enables sales representatives to refer to feedback and success stories in real time while on duty, thereby enhancing their ability to respond immediately and improving work efficiency.

[0518] A "sales representative" is a person whose job is to provide products or services to customers.

[0519] "Means of collecting data" refers to technical devices or methods for gathering relevant information from sales representatives.

[0520] "Parameters that characterize the work environment" are quantified indicators that specifically describe the environment in which sales representatives operate.

[0521] "Matching methods" refer to ways of connecting sales representatives who work in similar environments or under similar conditions.

[0522] "Means of providing online training" refers to the technical infrastructure for providing educational and training opportunities via the internet.

[0523] "Methods for evaluating post-training performance" refer to technical processes for analyzing sales representatives' performance and areas for improvement in order to measure the effectiveness of training.

[0524] "Providing success stories" refers to methods of communicating positive results and valuable experiences achieved in the past to other sales representatives.

[0525] "Means of rewarding" refers to technical procedures for providing monetary or non-monetary rewards to sales representatives who achieve results.

[0526] "Means for displaying advisory information in real time via smart devices" refers to devices or software that use the internet or wireless communication to immediately display support information.

[0527] In order to implement this invention, it is necessary to build a system in which servers, terminals, smart devices, and users interact with each other.

[0528] The server collects data from sales representatives and stores it in a database. This includes sales volume, customer feedback, and sales by product category. The collected data is then converted into parameters that quantify the business environment using analytical software. Typical analytical tools used here include data analysis libraries such as Python and R.

[0529] After data analysis, the server identifies and matches sales representatives with similar work environments. This process takes into account past success stories and performance.

[0530] Next, the device provides online training to designated sales representatives. This training is conducted via web conferencing tools and video streaming platforms, allowing users to learn case studies relevant to their actual work. Real-time learning facilitates rapid understanding and practical application.

[0531] Smart devices provide real-time advisory information to sales representatives during their work. For example, smart glasses can instantly display information on solutions to current challenges and relevant success stories. Augmented reality technologies such as ARToolkit are used for this purpose.

[0532] When user performance improvement is confirmed, the server evaluates the results and rewards the sales representative who provided the success story. This reward is provided as a points system and functions as an incentive.

[0533] For example, if a salesperson determines that sales of a new product are below target, the smart glasses will display an advice message such as, "Sales of the new product are below target. Refer to success stories to strengthen your sales strategy." This entire sequence of information is optimized by a generative AI model.

[0534] An example of a prompt for a generative AI model is: "Sales of our new product are below target. Please generate suggestions to improve this situation."

[0535] This allows sales representatives to conduct more effective sales activities in real time, resulting in improved operational efficiency.

[0536] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0537] Step 1:

[0538] The server collects data from sales representatives. This input data includes sales volume, customer feedback, and sales by product. The server stores this data in storage and prepares it for subsequent analysis processes. It also performs normalization processes to standardize the data format.

[0539] Step 2:

[0540] The server analyzes the collected data. This analysis process uses Python libraries to generate parameters that characterize the work environment. It outputs numerical indicators based on statistical methods derived from the input data, revealing specific sales trends and customer reaction patterns.

[0541] Step 3:

[0542] The server matches sales representatives with similar work environments based on the parameters generated by the analysis. This step involves comparison calculations using past success stories and sales performance data as references. The output is a list of matched sales representatives.

[0543] Step 4:

[0544] The device provides matching sales representatives with information about online training. The device displays links to web conferencing tools and video streaming platforms, allowing users to participate in training in real-time or on-demand. Users can learn practical case studies by clicking the appropriate links and viewing training materials.

[0545] Step 5:

[0546] Users with smart devices receive real-time advice during their work. Devices such as smart glasses utilize AI models generated from collected data to display advice messages based on prompts. Specifically, they project necessary information onto the screen according to sales status and customer behavior.

[0547] Step 6:

[0548] The server collects and evaluates user performance data after training. Input data includes changes in sales performance and customer satisfaction. This data is analyzed to measure success and generate an evaluation report. Based on this evaluation, a reward system is implemented. The output is a list of how many reward points were awarded.

[0549] 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.

[0550] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and by incorporating an emotion engine, it enables the provision of more personalized training. To that end, it mainly consists of four elements: a server, a terminal, a user, and an emotion engine.

[0551] Data collection and analysis

[0552] The server receives sales representative work data from each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and parameters are generated to quantify the store's work environment based on this information. In addition, the emotion engine analyzes facial expressions, tone of voice, and words used to recognize the emotional state of the sales representative, who is the user.

[0553] Similar crew matching and emotion-based customization

[0554] Based on the generated parameters, the server identifies sales representatives in similar work environments. Once a match is made with a representative who has a successful track record, the server customizes the training content and progression to suit the user's emotional state based on the analysis results of the emotion engine.

[0555] Implementation of online training

[0556] The device displays matching results and personalized online training information to the user. The user reviews the training content and receives support to facilitate participation. During the training, the emotion engine continuously monitors the user's emotions and adjusts the content as needed.

[0557] Performance evaluation and compensation after training

[0558] After the training is complete, the server monitors the user's performance and evaluates, for example, increases in sales volume and improvements in customer satisfaction. If improvements in performance are confirmed, the server rewards the sales representative who provided the success story with crew points.

[0559] Specific example

[0560] For example, by analyzing sales data received through a terminal and the emotional state of employees, the server matches a veteran employee "A" who has achieved success in a similar environment with a new employee "B". If the emotional engine detects an increase in the stress level of new employee "B", the difficulty level of the training is appropriately adjusted, allowing for gradual skill improvement. If it is confirmed that new employee "B"'s performance has improved after the training, veteran employee "A" is awarded points.

[0561] In this way, by utilizing the emotional engine, it is possible to provide appropriate training tailored to each individual sales representative and to continuously and effectively improve business operations.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The server receives work data from sales staff at each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and based on this, it generates parameters that quantify the work environment.

[0565] Step 2:

[0566] The emotion engine analyzes the salesperson's facial expressions, tone of voice, and vocabulary. This allows it to recognize the user's emotional state in real time and evaluate their stress level and motivation.

[0567] Step 3:

[0568] The server uses the generated parameters to identify sales representatives who have achieved success in similar work environments. In doing so, it considers past success stories and matches the most suitable representatives.

[0569] Step 4:

[0570] The device displays matching results to the user, along with personalized online training information based on analysis by the emotion engine. The user reviews the training details and prepares to participate.

[0571] Step 5:

[0572] Users participate in online training using their devices. During the training, an emotion engine continuously monitors the user's emotional state, and adjusts the training content and pace as needed.

[0573] Step 6:

[0574] Once the training is complete, the server monitors the user's performance data and evaluates, for example, improvements in sales volume and customer satisfaction.

[0575] Step 7:

[0576] If performance improves, the server will reward the sales representatives who provided success stories. These rewards are provided as crew points and serve as an incentive for knowledge sharing.

[0577] (Example 2)

[0578] 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."

[0579] To improve the skills of sales personnel and increase operational efficiency, training tailored to individual work environments and emotional states is essential. However, traditional methods have faced challenges in providing individualized support and effectively evaluating and reflecting the results after implementation.

[0580] 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.

[0581] In this invention, the server includes means for collecting business data of individuals related to sales, means for evaluating the emotional state of users using emotion analysis technology, means for identifying individuals with similar work environments based on the data and evaluation results, and means for personalizing training content based on the evaluation results. This enables the provision of training optimized for individual work environments and emotional states, resulting in efficient and effective skill development.

[0582] "Business data" refers to information obtained from sales activities and interactions with customers, including sales volume, revenue information, and customer feedback.

[0583] "Emotional analysis technology" is a technology that recognizes and quantifies a user's emotional state by evaluating their facial expressions, tone of voice, and spoken language.

[0584] "Similar work environments" refer to the characteristics of work conditions that are common to different sellers, and are expressed using generated numerical indicators.

[0585] "Personalized training" refers to an educational program tailored to each user's work data and emotional state.

[0586] "Evaluation results" refer to user performance indicators derived from the analysis of emotional data obtained through emotion analysis technology and business data.

[0587] "Online training" refers to educational programs delivered via the internet, a form of training that is accessible without relying on physical classrooms.

[0588] "Rewards" refer to incentives given to individuals who provide success stories, and are offered in the form of points, bonuses, or other similar benefits.

[0589] This invention is a system primarily composed of a server, terminals, users, and sentiment analysis technology. First, the server periodically collects sales-related business data from each terminal in the store. During this process, it accesses a database via the network to obtain sales volume, sales information by product category, customer feedback, and other data. The terminals have the function of automatically transmitting this data to the server.

[0590] The server uses data analysis software to analyze the collected business data. This software automatically generates metrics to quantify the business environment of each store and saves them to storage. Next, by introducing sentiment analysis technology, the terminals collect user facial expression data and voice data and send them to the server. Sentiment analysis is performed using a machine learning model to determine the user's current emotional state.

[0591] Identifying individuals with similar work environments is performed by a dedicated algorithm within the server. This algorithm is based on numerical data of the work environment and emotional states. Based on this data, the server generates training programs tailored to each user. For example, users with high stress levels will be offered training programs that include a lot of relaxing content.

[0592] Online training is accessible from the user's device and is conducted in real time. Users' emotional states are monitored throughout the training, and the server adjusts the training content as needed. In this way, a more personalized and effective learning experience is provided.

[0593] At the end of the training, the server monitors the users' work performance, and if improvement is confirmed, the person who provided the success story will be rewarded. The reward will mainly be in the form of points.

[0594] A concrete example is matching experienced employees who have achieved success in similar environments with new employees based on sales data and emotional states received by the server from terminals. In this case, a generative AI model can be used with the prompt, "Analyze the sales data received from terminals and the emotional states of employees, and match experienced senior employees who have achieved success in similar environments with new employees." The AI ​​will then appropriately analyze the data and perform the optimal matching.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The server collects sales-related business data from terminals. Inputs include sales volume, sales information by product category, and customer feedback. Terminals send this data to the server after business hours or at a specified time. The server stores the received data in a database, preparing it for subsequent processing.

[0598] Step 2:

[0599] The server analyzes collected business data and generates metrics that quantify the work environment. Inputs include data such as sales volume and customer feedback. Analysis software processes this data to generate numerical metrics for evaluating sales fluctuation patterns and customer satisfaction. The output consists of numerical data representing the work environment for each individual employee.

[0600] Step 3:

[0601] The device collects the user's facial expression and voice data and sends it to the server. The input for this step is the user's video and audio information. The device captures this in real time and uploads it to the server for emotion analysis.

[0602] Step 4:

[0603] The server uses emotion analysis technology to evaluate the user's emotional state. Inputs include facial expression data and voice data received from the terminal. The server uses a generative AI model to recognize the user's stress level and motivation and generate evaluation results. The output is emotional state data for each user.

[0604] Step 5:

[0605] The server identifies individuals with similar environments based on quantified work environment data and emotional state data. Using an algorithm, it analyzes the input numerical and emotional data and matches different users with similar characteristics. The output is a list of user pairs resulting from the matching.

[0606] Step 6:

[0607] The server personalizes the training program based on the matching results. Input information includes the matched user pairs and their sentiment analysis results. The server uses this information to create a program optimized for stress reduction and skill development. The output is a personalized online training program.

[0608] Step 7:

[0609] The terminal notifies users of personalized training programs and assists in their implementation. Users review and participate in the training content through the terminal. The terminal reassesss the user's emotional state in real time and sends data to the server to adjust the training content as needed.

[0610] Step 8:

[0611] The server monitors the work performance of users after training. Inputs include sales data and customer feedback after training. The server analyzes the data to evaluate the impact of matching and training on work performance. If improved performance is confirmed, points are awarded to the relevant users as a reward. Outputs include work performance evaluation data and reward point information.

[0612] (Application Example 2)

[0613] 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."

[0614] The challenge lies in improving the work efficiency of users engaged in sales roles and effectively enhancing their skills through individualized training. In particular, it is necessary to dynamically adjust training content according to the emotional state of the users, but achieving this requires advanced analytical techniques and flexible responses.

[0615] 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.

[0616] In this invention, the server includes means for analyzing the personal attributes and commercial transaction information of users engaged in sales duties to generate components that characterize the work environment, means for comparing users in similar work environments, and means for analyzing emotional states and dynamically adjusting training programs. This enables the provision of training adapted to the individual emotional states of users, thereby improving the efficiency of sales duties.

[0617] "Users engaged in sales duties" refers to employees or staff involved in the sales of products.

[0618] "Personal attributes" refer to information that describes an individual's characteristics, including, for example, personality, experience, and skill level.

[0619] "Commercial transaction information" refers to data related to transactions, including sales volume, revenue, and customer feedback.

[0620] "Work environment" refers to the entire work environment, including the location and conditions where users perform their work, as well as the systems and processes involved.

[0621] "Components" refer to the basic elements or parameters that make up a system or process.

[0622] "Users in similar work environments" refers to users engaged in other sales positions in work environments with common work conditions and circumstances.

[0623] "Means of comparison" refers to methods or processes for comparing and relating elements that have similarities.

[0624] "Emotional state" refers to the user's emotions and psychological state, including stress levels and motivation.

[0625] "Means of dynamic adjustment" refers to functions or processes that automatically change their content or methods in response to changing conditions.

[0626] A "training program" refers to educational activities or courses designed to improve users' skills and knowledge.

[0627] The system for implementing this invention includes a server, a terminal, a user, and an emotion engine. The server receives personal attributes and commercial transaction information from users engaged in sales duties, and uses this to generate components that characterize the work environment. Specifically, the server stores various types of information using a database and performs analysis using machine learning algorithms.

[0628] The terminal provides an interface for user access and displays online training programs. The terminal, for example, is a smartphone or tablet and uses software capable of streaming various digital content. At this time, an emotion engine is installed on the terminal, which uses the camera and microphone to analyze the user's emotional state in real time.

[0629] The emotion engine uses analytical software like the Affectiva SDK to recognize the user's facial expressions and tone of voice. This allows the server to understand the user's stress level and motivation, and dynamically adjust the training program content based on that information.

[0630] Users participate in training programs through their devices to improve their skills. After the training is complete, the server analyzes the transaction information again to evaluate the improvement in performance. A concrete example is the process by which new sales staff improve their customer service skills through the training program. During the training, an emotion engine monitors the user's emotional state and adaptively adjusts the program to reduce stress.

[0631] An example of a prompt message might be: "Generate a training program to effectively improve the customer service skills of new sales staff. Propose customized learning content, taking into account the staff's current stress levels and motivation."

[0632] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0633] Step 1:

[0634] The server receives user attributes and transaction information from terminals for users engaged in sales roles. Input data includes user personality, experience, sales volume, revenue, and customer feedback. The server stores this information in a database and performs data cleansing and preprocessing. The output is data formatted in a parseable format.

[0635] Step 2:

[0636] The server generates components that characterize the work environment based on the received data. Specifically, it applies machine learning algorithms to extract parameters that represent the work environment. The input is the data formatted in the previous step, and the output is the quantified work environment parameters.

[0637] Step 3:

[0638] The server compares other users in similar work environments based on the generated parameters. Clustering techniques are used to identify groups of users with common work conditions. The input is quantified work environment parameters, and the output is a list of the compared users.

[0639] Step 4:

[0640] The terminal displays the training program provided by the server, making it accessible to the user. This program is customized to the user's emotional state. The input is the training program information received from the server, and the output is the training content displayed to the user.

[0641] Step 5:

[0642] The device uses a camera and microphone to capture the user's facial expressions and voice tone, and inputs this data into an emotion engine. The emotion engine analyzes this data to understand the user's emotional state. The input is real-time data obtained from sensors, and the output is numerical data on stress levels and motivation.

[0643] Step 6:

[0644] The server dynamically adjusts the content of the training program based on user emotional state data obtained from the emotion engine. The input is numerical data of the emotional state, and the output is the adjusted training content.

[0645] Step 7:

[0646] Users participate in training programs provided through their devices to improve their skills and knowledge. Specific actions include viewing displayed content and completing assignments.

[0647] Step 8:

[0648] After the training is completed, the server collects commercial transaction information again and performs analysis to evaluate performance improvement. The input is sales data after the training, and the output is the performance evaluation result. This allows us to understand the degree of user growth.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] [Fourth Embodiment]

[0653] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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).

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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".

[0666] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and its embodiment is shown below. This system mainly consists of three elements: a server, a terminal, and a user.

[0667] Data collection and analysis

[0668] The server receives sales representative data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server analyzes this data and generates parameters to quantify the work environment for each store.

[0669] Matching similar crews

[0670] The server uses the generated parameters to identify sales representatives with similar work environments. In doing so, it considers past performance and success stories to match representatives with the most effective expertise.

[0671] Online training

[0672] Once matching is complete, the device displays an invitation to online training from the successful sales representative. This training can be conducted in real-time or on-demand, for example, through web conferencing or video materials. Users can deepen their learning through case studies similar to their own work environment.

[0673] Performance evaluation and compensation after training

[0674] Once the training is complete, the server monitors the users' performance data and evaluates improvements in sales performance and customer satisfaction. If performance improves, the server rewards the sales representatives who shared their success stories. This reward is provided in the form of crew points and functions as an incentive.

[0675] Specific example

[0676] First, suppose a terminal at a certain store sends recent daily sales reports and customer reviews to a server. Based on this information, the server identifies store-specific challenges and searches for other stores that are solving similar problems. Finally, it matches the user with a representative from a successful store and shares problem-solving know-how in a webinar format. After the training, it is found that the user's sales efficiency has improved by 30%, so the server awards points to the successful representative.

[0677] This system is expected to practically improve the individual work capabilities of sales representatives and enhance overall business performance.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] The server receives data about sales representatives from terminals in each store. This data includes sales volume, customer feedback, and sales by product category.

[0681] Step 2:

[0682] The server analyzes the received data. Here, it quantifies the unique operational environment of each store and generates parameters. These parameters reflect factors such as the store's location, customer base, and the characteristics of the products it handles.

[0683] Step 3:

[0684] The server identifies sales representatives with similar characteristics based on the generated parameters. During this process, past performance data is also considered, and representatives with a proven track record of success are given priority.

[0685] Step 4:

[0686] Based on instructions from the server, the terminal displays an invitation to an online training session with a successful case study representative for the user (sales representative). The user can then review the training details and decide whether to participate.

[0687] Step 5:

[0688] Users participate in online training using their devices. This training allows them to learn about successful case studies and actual work processes.

[0689] Step 6:

[0690] After the training is completed, the server continuously monitors the user's sales performance. It analyzes whether there has been an increase in sales volume or an improvement in customer satisfaction.

[0691] Step 7:

[0692] If improved performance is confirmed, the server will reward the sales representative who provided the success story with crew points. This strengthens the incentive for information sharing.

[0693] (Example 1)

[0694] 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".

[0695] In modern sales, improving the individual skills of salespeople and optimizing operational efficiency are crucial challenges. However, there is a lack of effective support systems that enable individual salespeople to independently learn from successful practices and apply them to their work environment. As a result, there is a problem of inconsistency in sales performance and stagnation in overall organizational performance.

[0696] 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.

[0697] In this invention, the server includes means for collecting information on salespeople, means for processing said information to generate indicators that characterize their work situation, and means for associating salespeople in similar work situations. This enables effective sharing of know-how, leading to improved salespeople skills and increased work efficiency.

[0698] A "salesperson" refers to an employee whose job is to introduce and sell products and services to customers.

[0699] "Means of gathering information" refers to the processes and methods used to collect specific data or information from various sources and devices.

[0700] "Means of processing information to generate indicators that characterize business conditions" refers to methods for analyzing collected data and creating evaluation criteria and parameters that quantify and represent the business environment and conditions.

[0701] "Means of linking salespeople in similar work situations" refers to the process of identifying and connecting salespeople who have similar work environments and conditions.

[0702] "Means of providing online education" refers to the technologies and methods used to deliver learning content and educational programs to students via the internet.

[0703] "Means for determining results" refers to indicators and methods used to evaluate the results obtained after training or activities and to measure their effectiveness.

[0704] "Means of awarding rewards" refers to systems and methods for providing rewards or incentives to salespeople based on their performance and contributions.

[0705] This invention provides a system in which a server, terminal, and user work in cooperation with each other, in order to improve the efficiency of sales operations and enhance the capabilities of the person in charge.

[0706] The server collects sales staff data from terminals in each store. This data includes sales volume, customer feedback, and sales by product category. The server uses data analysis software such as Python's Pandas and NumPy to analyze this data. This generates parameters that characterize the operational status of each store.

[0707] Based on the generated parameters, the server uses an SQL database to identify salespeople in similar work situations. An algorithm is then executed to extract highly similar salespeople, referencing past success stories, and to correlate those with the most effective expertise.

[0708] The device provides users with online training from successful salespeople. The training utilizes an internet-based learning platform and can be both real-time and on-demand. Communication tools such as the Zoom API are used to schedule and conduct actual training sessions.

[0709] After the training is complete, the server re-analyzes the user's performance data to evaluate increases in sales and improvements in customer satisfaction. This allows the effectiveness of the sales staff's work improvements to be determined.

[0710] Furthermore, salespeople who provide success stories are automatically awarded rewards from the server based on a points system. These rewards serve as incentives that can be used for future training or to obtain additional materials.

[0711] As a concrete example, users can learn more advanced sales strategies by entering a prompt for the generative AI model such as, "Please tell me the most effective sales methods used in stores with similar crews." Through this system, it is expected that user efficiency and performance will improve, leading to improved overall organizational performance.

[0712] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0713] Step 1:

[0714] The server collects sales staff data from terminals in each store. This input data includes daily sales quantities, customer feedback, and sales information by product category. The server structures the received data and stores it in a database. Storing the data in a format that is easy to use for subsequent analysis enables efficient information access.

[0715] Step 2:

[0716] The server analyzes the collected data and generates parameters that characterize the operational status of each store. Using Python's Pandas and NumPy, it aggregates the data and calculates metrics such as sales and customer satisfaction. The output at this stage is a dataset that quantifies the performance of each store. This enables quantitative operational evaluation.

[0717] Step 3:

[0718] The server uses the generated business parameters to identify salespeople in similar business situations. It references an SQL database and compares it with past success stories to extract salespeople with the closest match. This process employs heuristic algorithms to improve the accuracy of the associations. The output generates a matching list of highly relevant salespeople.

[0719] Step 4:

[0720] The terminal displays a guide to provide users with online training from successful salespeople. Using the Zoom API, it automatically generates and presents links to training sessions. The input here is a matching list from the server, and the output is a schedule of training sessions. Users can then attend online training sessions according to the provided schedule.

[0721] Step 5:

[0722] After a user completes online training, the server re-evaluates their work performance. It analyzes the increase in sales data and improvements in customer feedback to quantify the effectiveness of the training. This generates a report measuring the user's performance improvement. Based on these results, sales staff are rewarded through a points system.

[0723] Through the process described above, users can efficiently improve their skills and effectively enhance their work performance.

[0724] (Application Example 1)

[0725] 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".

[0726] Traditional systems for improving the efficiency and skills of sales representatives primarily focused on data-driven analysis and training, but lacked real-time support during actual work. In particular, in situations requiring immediate responses in the sales field, there were limited means to quickly utilize past success stories and feedback. This limited the ability to improve responsiveness and the quality of work.

[0727] 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.

[0728] In this invention, the server includes means for collecting sales representative data, means for displaying advice information in real time via smart devices, and means for evaluating performance after training. This enables sales representatives to refer to feedback and success stories in real time while on duty, thereby enhancing their ability to respond immediately and improving work efficiency.

[0729] A "sales representative" is a person whose job is to provide products or services to customers.

[0730] "Means of collecting data" refers to technical devices or methods for gathering relevant information from sales representatives.

[0731] "Parameters that characterize the work environment" are quantified indicators that specifically describe the environment in which sales representatives operate.

[0732] "Matching methods" refer to ways of connecting sales representatives who work in similar environments or under similar conditions.

[0733] "Means of providing online training" refers to the technical infrastructure for providing educational and training opportunities via the internet.

[0734] "Methods for evaluating post-training performance" refer to technical processes for analyzing sales representatives' performance and areas for improvement in order to measure the effectiveness of training.

[0735] "Providing success stories" refers to methods of communicating positive results and valuable experiences achieved in the past to other sales representatives.

[0736] "Means of rewarding" refers to technical procedures for providing monetary or non-monetary rewards to sales representatives who achieve results.

[0737] "Means for displaying advisory information in real time via smart devices" refers to devices or software that use the internet or wireless communication to immediately display support information.

[0738] In order to implement this invention, it is necessary to build a system in which servers, terminals, smart devices, and users interact with each other.

[0739] The server collects data from sales representatives and stores it in a database. This includes sales volume, customer feedback, and sales by product category. The collected data is then converted into parameters that quantify the business environment using analytical software. Typical analytical tools used here include data analysis libraries such as Python and R.

[0740] After data analysis, the server identifies and matches sales representatives with similar work environments. This process takes into account past success stories and performance.

[0741] Next, the device provides online training to designated sales representatives. This training is conducted via web conferencing tools and video streaming platforms, allowing users to learn case studies relevant to their actual work. Real-time learning facilitates rapid understanding and practical application.

[0742] Smart devices provide real-time advisory information to sales representatives during their work. For example, smart glasses can instantly display information on solutions to current challenges and relevant success stories. Augmented reality technologies such as ARToolkit are used for this purpose.

[0743] When user performance improvement is confirmed, the server evaluates the results and rewards the sales representative who provided the success story. This reward is provided as a points system and functions as an incentive.

[0744] For example, if a salesperson determines that sales of a new product are below target, the smart glasses will display an advice message such as, "Sales of the new product are below target. Refer to success stories to strengthen your sales strategy." This entire sequence of information is optimized by a generative AI model.

[0745] An example of a prompt for a generative AI model is: "Sales of our new product are below target. Please generate suggestions to improve this situation."

[0746] This allows sales representatives to conduct more effective sales activities in real time, resulting in improved operational efficiency.

[0747] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0748] Step 1:

[0749] The server collects data from sales representatives. This input data includes sales volume, customer feedback, and sales by product. The server stores this data in storage and prepares it for subsequent analysis processes. It also performs normalization processes to standardize the data format.

[0750] Step 2:

[0751] The server analyzes the collected data. This analysis process uses Python libraries to generate parameters that characterize the work environment. It outputs numerical indicators based on statistical methods derived from the input data, revealing specific sales trends and customer reaction patterns.

[0752] Step 3:

[0753] The server matches sales representatives with similar work environments based on the parameters generated by the analysis. This step involves comparison calculations using past success stories and sales performance data as references. The output is a list of matched sales representatives.

[0754] Step 4:

[0755] The device provides matching sales representatives with information about online training. The device displays links to web conferencing tools and video streaming platforms, allowing users to participate in training in real-time or on-demand. Users can learn practical case studies by clicking the appropriate links and viewing training materials.

[0756] Step 5:

[0757] Users with smart devices receive real-time advice during their work. Devices such as smart glasses utilize AI models generated from collected data to display advice messages based on prompts. Specifically, they project necessary information onto the screen according to sales status and customer behavior.

[0758] Step 6:

[0759] The server collects and evaluates user performance data after training. Input data includes changes in sales performance and customer satisfaction. This data is analyzed to measure success and generate an evaluation report. Based on this evaluation, a reward system is implemented. The output is a list of how many reward points were awarded.

[0760] 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.

[0761] This invention is a system aimed at improving the skills and operational efficiency of sales representatives, and by incorporating an emotion engine, it enables the provision of more personalized training. To that end, it mainly consists of four elements: a server, a terminal, a user, and an emotion engine.

[0762] Data collection and analysis

[0763] The server receives sales representative work data from each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and parameters are generated to quantify the store's work environment based on this information. In addition, the emotion engine analyzes facial expressions, tone of voice, and words used to recognize the emotional state of the sales representative, who is the user.

[0764] Similar crew matching and emotion-based customization

[0765] Based on the generated parameters, the server identifies sales representatives in similar work environments. Once a match is made with a representative who has a successful track record, the server customizes the training content and progression to suit the user's emotional state based on the analysis results of the emotion engine.

[0766] Implementation of online training

[0767] The device displays matching results and personalized online training information to the user. The user reviews the training content and receives support to facilitate participation. During the training, the emotion engine continuously monitors the user's emotions and adjusts the content as needed.

[0768] Performance evaluation and compensation after training

[0769] After the training is complete, the server monitors the user's performance and evaluates, for example, increases in sales volume and improvements in customer satisfaction. If improvements in performance are confirmed, the server rewards the sales representative who provided the success story with crew points.

[0770] Specific example

[0771] For example, by analyzing sales data received through a terminal and the emotional state of employees, the server matches a veteran employee "A" who has achieved success in a similar environment with a new employee "B". If the emotional engine detects an increase in the stress level of new employee "B", the difficulty level of the training is appropriately adjusted, allowing for gradual skill improvement. If it is confirmed that new employee "B"'s performance has improved after the training, veteran employee "A" is awarded points.

[0772] In this way, by utilizing the emotional engine, it is possible to provide appropriate training tailored to each individual sales representative and to continuously and effectively improve business operations.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] The server receives work data from sales staff at each store's terminal. This data includes sales volume, customer feedback, and sales information by product category, and based on this, it generates parameters that quantify the work environment.

[0776] Step 2:

[0777] The emotion engine analyzes the salesperson's facial expressions, tone of voice, and vocabulary. This allows it to recognize the user's emotional state in real time and evaluate their stress level and motivation.

[0778] Step 3:

[0779] The server uses the generated parameters to identify sales representatives who have achieved success in similar work environments. In doing so, it considers past success stories and matches the most suitable representatives.

[0780] Step 4:

[0781] The device displays matching results to the user, along with personalized online training information based on analysis by the emotion engine. The user reviews the training details and prepares to participate.

[0782] Step 5:

[0783] Users participate in online training using their devices. During the training, an emotion engine continuously monitors the user's emotional state, and adjusts the training content and pace as needed.

[0784] Step 6:

[0785] Once the training is complete, the server monitors the user's performance data and evaluates, for example, improvements in sales volume and customer satisfaction.

[0786] Step 7:

[0787] If performance improves, the server will reward the sales representatives who provided success stories. These rewards are provided as crew points and serve as an incentive for knowledge sharing.

[0788] (Example 2)

[0789] 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".

[0790] To improve the skills of sales personnel and increase operational efficiency, training tailored to individual work environments and emotional states is essential. However, traditional methods have faced challenges in providing individualized support and effectively evaluating and reflecting the results after implementation.

[0791] 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.

[0792] In this invention, the server includes means for collecting business data of individuals related to sales, means for evaluating the emotional state of users using emotion analysis technology, means for identifying individuals with similar work environments based on the data and evaluation results, and means for personalizing training content based on the evaluation results. This enables the provision of training optimized for individual work environments and emotional states, resulting in efficient and effective skill development.

[0793] "Business data" refers to information obtained from sales activities and interactions with customers, including sales volume, revenue information, and customer feedback.

[0794] "Emotional analysis technology" is a technology that recognizes and quantifies a user's emotional state by evaluating their facial expressions, tone of voice, and spoken language.

[0795] "Similar work environments" refer to the characteristics of work conditions that are common to different sellers, and are expressed using generated numerical indicators.

[0796] "Personalized training" refers to an educational program tailored to each user's work data and emotional state.

[0797] "Evaluation results" refer to user performance indicators derived from the analysis of emotional data obtained through emotion analysis technology and business data.

[0798] "Online training" refers to educational programs delivered via the internet, a form of training that is accessible without relying on physical classrooms.

[0799] "Rewards" refer to incentives given to individuals who provide success stories, and are offered in the form of points, bonuses, or other similar benefits.

[0800] This invention is a system primarily composed of a server, terminals, users, and sentiment analysis technology. First, the server periodically collects sales-related business data from each terminal in the store. During this process, it accesses a database via the network to obtain sales volume, sales information by product category, customer feedback, and other data. The terminals have the function of automatically transmitting this data to the server.

[0801] The server uses data analysis software to analyze the collected business data. This software automatically generates metrics to quantify the business environment of each store and saves them to storage. Next, by introducing sentiment analysis technology, the terminals collect user facial expression data and voice data and send them to the server. Sentiment analysis is performed using a machine learning model to determine the user's current emotional state.

[0802] Identifying individuals with similar work environments is performed by a dedicated algorithm within the server. This algorithm is based on numerical data of the work environment and emotional states. Based on this data, the server generates training programs tailored to each user. For example, users with high stress levels will be offered training programs that include a lot of relaxing content.

[0803] Online training is accessible from the user's device and is conducted in real time. Users' emotional states are monitored throughout the training, and the server adjusts the training content as needed. In this way, a more personalized and effective learning experience is provided.

[0804] At the end of the training, the server monitors the users' work performance, and if improvement is confirmed, the person who provided the success story will be rewarded. The reward will mainly be in the form of points.

[0805] A concrete example is matching experienced employees who have achieved success in similar environments with new employees based on sales data and emotional states received by the server from terminals. In this case, a generative AI model can be used with the prompt, "Analyze the sales data received from terminals and the emotional states of employees, and match experienced senior employees who have achieved success in similar environments with new employees." The AI ​​will then appropriately analyze the data and perform the optimal matching.

[0806] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0807] Step 1:

[0808] The server collects sales-related business data from terminals. Inputs include sales volume, sales information by product category, and customer feedback. Terminals send this data to the server after business hours or at a specified time. The server stores the received data in a database, preparing it for subsequent processing.

[0809] Step 2:

[0810] The server analyzes collected business data and generates metrics that quantify the work environment. Inputs include data such as sales volume and customer feedback. Analysis software processes this data to generate numerical metrics for evaluating sales fluctuation patterns and customer satisfaction. The output consists of numerical data representing the work environment for each individual employee.

[0811] Step 3:

[0812] The device collects the user's facial expression and voice data and sends it to the server. The input for this step is the user's video and audio information. The device captures this in real time and uploads it to the server for emotion analysis.

[0813] Step 4:

[0814] The server uses emotion analysis technology to evaluate the user's emotional state. Inputs include facial expression data and voice data received from the terminal. The server uses a generative AI model to recognize the user's stress level and motivation and generate evaluation results. The output is emotional state data for each user.

[0815] Step 5:

[0816] The server identifies individuals with similar environments based on quantified work environment data and emotional state data. Using an algorithm, it analyzes the input numerical and emotional data and matches different users with similar characteristics. The output is a list of user pairs resulting from the matching.

[0817] Step 6:

[0818] The server personalizes the training program based on the matching results. Input information includes the matched user pairs and their sentiment analysis results. The server uses this information to create a program optimized for stress reduction and skill development. The output is a personalized online training program.

[0819] Step 7:

[0820] The terminal notifies users of personalized training programs and assists in their implementation. Users review and participate in the training content through the terminal. The terminal reassesss the user's emotional state in real time and sends data to the server to adjust the training content as needed.

[0821] Step 8:

[0822] The server monitors the work performance of users after training. Inputs include sales data and customer feedback after training. The server analyzes the data to evaluate the impact of matching and training on work performance. If improved performance is confirmed, points are awarded to the relevant users as a reward. Outputs include work performance evaluation data and reward point information.

[0823] (Application Example 2)

[0824] 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".

[0825] The challenge lies in improving the work efficiency of users engaged in sales roles and effectively enhancing their skills through individualized training. In particular, it is necessary to dynamically adjust training content according to the emotional state of the users, but achieving this requires advanced analytical techniques and flexible responses.

[0826] 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.

[0827] In this invention, the server includes means for analyzing the personal attributes and commercial transaction information of users engaged in sales duties to generate components that characterize the work environment, means for comparing users in similar work environments, and means for analyzing emotional states and dynamically adjusting training programs. This enables the provision of training adapted to the individual emotional states of users, thereby improving the efficiency of sales duties.

[0828] "Users engaged in sales duties" refers to employees or staff involved in the sales of products.

[0829] "Personal attributes" refer to information that describes an individual's characteristics, including, for example, personality, experience, and skill level.

[0830] "Commercial transaction information" refers to data related to transactions, including sales volume, revenue, and customer feedback.

[0831] "Work environment" refers to the entire work environment, including the location and conditions where users perform their work, as well as the systems and processes involved.

[0832] "Components" refer to the basic elements or parameters that make up a system or process.

[0833] "Users in similar work environments" refers to users engaged in other sales positions in work environments with common work conditions and circumstances.

[0834] "Means of comparison" refers to methods or processes for comparing and relating elements that have similarities.

[0835] "Emotional state" refers to the user's emotions and psychological state, including stress levels and motivation.

[0836] "Means of dynamic adjustment" refers to functions or processes that automatically change their content or methods in response to changing conditions.

[0837] A "training program" refers to educational activities or courses designed to improve users' skills and knowledge.

[0838] The system for implementing this invention includes a server, a terminal, a user, and an emotion engine. The server receives personal attributes and commercial transaction information from users engaged in sales duties, and uses this to generate components that characterize the work environment. Specifically, the server stores various types of information using a database and performs analysis using machine learning algorithms.

[0839] The terminal provides an interface for user access and displays online training programs. The terminal, for example, is a smartphone or tablet and uses software capable of streaming various digital content. At this time, an emotion engine is installed on the terminal, which uses the camera and microphone to analyze the user's emotional state in real time.

[0840] The emotion engine uses analytical software like the Affectiva SDK to recognize the user's facial expressions and tone of voice. This allows the server to understand the user's stress level and motivation, and dynamically adjust the training program content based on that information.

[0841] Users participate in training programs through their devices to improve their skills. After the training is complete, the server analyzes the transaction information again to evaluate the improvement in performance. A concrete example is the process by which new sales staff improve their customer service skills through the training program. During the training, an emotion engine monitors the user's emotional state and adaptively adjusts the program to reduce stress.

[0842] An example of a prompt message might be: "Generate a training program to effectively improve the customer service skills of new sales staff. Propose customized learning content, taking into account the staff's current stress levels and motivation."

[0843] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0844] Step 1:

[0845] The server receives user attributes and transaction information from terminals for users engaged in sales roles. Input data includes user personality, experience, sales volume, revenue, and customer feedback. The server stores this information in a database and performs data cleansing and preprocessing. The output is data formatted in a parseable format.

[0846] Step 2:

[0847] The server generates components that characterize the work environment based on the received data. Specifically, it applies machine learning algorithms to extract parameters that represent the work environment. The input is the data formatted in the previous step, and the output is the quantified work environment parameters.

[0848] Step 3:

[0849] The server compares other users in similar work environments based on the generated parameters. Clustering techniques are used to identify groups of users with common work conditions. The input is quantified work environment parameters, and the output is a list of the compared users.

[0850] Step 4:

[0851] The terminal displays the training program provided by the server, making it accessible to the user. This program is customized to the user's emotional state. The input is the training program information received from the server, and the output is the training content displayed to the user.

[0852] Step 5:

[0853] The device uses a camera and microphone to capture the user's facial expressions and voice tone, and inputs this data into an emotion engine. The emotion engine analyzes this data to understand the user's emotional state. The input is real-time data obtained from sensors, and the output is numerical data on stress levels and motivation.

[0854] Step 6:

[0855] The server dynamically adjusts the content of the training program based on user emotional state data obtained from the emotion engine. The input is numerical data of the emotional state, and the output is the adjusted training content.

[0856] Step 7:

[0857] Users participate in training programs provided through their devices to improve their skills and knowledge. Specific actions include viewing displayed content and completing assignments.

[0858] Step 8:

[0859] After the training is completed, the server collects commercial transaction information again and performs analysis to evaluate performance improvement. The input is sales data after the training, and the output is the performance evaluation result. This allows us to understand the degree of user growth.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] The following is further disclosed regarding the embodiments described above.

[0882] (Claim 1)

[0883] Means of collecting sales representative data,

[0884] A means for analyzing the data to generate parameters that characterize the work environment,

[0885] A means of matching sales representatives in similar work environments,

[0886] Means of providing online training,

[0887] Methods for evaluating performance after training,

[0888] A method of rewarding sales representatives who provide success stories,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, characterized in that the online training enables real-time learning.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising means for collecting feedback from sales representatives and improving matching and training programs based on said feedback.

[0894] "Example 1"

[0895] (Claim 1)

[0896] Means of gathering information on salespeople,

[0897] A means for processing the information to generate indicators that characterize the business situation,

[0898] A means of linking salespeople in similar work situations,

[0899] Means of providing online education,

[0900] Means for determining the outcome after education,

[0901] A method of rewarding salespeople who provide success stories,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, characterized in that the online education enables immediate learning.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising means for collecting feedback from sales staff and improving associations and training programs based on said feedback.

[0907] "Application Example 1"

[0908] (Claim 1)

[0909] Means of collecting sales representative data,

[0910] A means for analyzing the data to generate parameters that characterize the work environment,

[0911] A means of matching sales representatives in similar work environments,

[0912] Means of providing online training,

[0913] Methods for evaluating performance after training,

[0914] A method of rewarding sales representatives who provide success stories,

[0915] A means of displaying advisory information in real time via smart devices,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, characterized in that the online training enables real-time learning.

[0919] (Claim 3)

[0920] The system according to claim 1, further comprising means for collecting feedback from sales representatives and improving matching and training programs based on said feedback.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] Means for collecting business data of persons involved in sales,

[0924] A means for analyzing the data and generating indicators for quantifying the work environment,

[0925] A means of evaluating the emotional state of a user using emotion analysis technology,

[0926] A means of identifying individuals with similar work environments,

[0927] A means of individualizing training content based on evaluation results,

[0928] Means of providing online training,

[0929] Methods for evaluating work performance after training,

[0930] A means of rewarding those who provide success stories,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, characterized in that the online training can monitor the emotional state of the user in real time and adjust the content accordingly.

[0934] (Claim 3)

[0935] The system according to claim 1, further comprising means for continuously improving matching and training programs generated based on business data and sentiment evaluation data.

[0936] "Application example 2 when combining with an emotional engine"

[0937] (Claim 1)

[0938] A means of collecting the personal attributes of users engaged in sales duties,

[0939] Means for analyzing the attributes and commercial transaction information to generate components that characterize the workplace environment,

[0940] A means of comparing users in similar work environments,

[0941] Means of providing online training programs,

[0942] Methods for evaluating performance after the completion of training,

[0943] A means of rewarding users who provide success stories,

[0944] A means of analyzing emotional states and dynamically adjusting training programs,

[0945] A system that includes this.

[0946] (Claim 2)

[0947] The system according to claim 1, characterized in that the online training monitors the user's emotional state in real time and adaptively adjusts the training content based on that state.

[0948] (Claim 3)

[0949] The system according to claim 1, further comprising means for collecting user feedback and optimizing comparison and training programs based on such feedback and emotional state. [Explanation of symbols]

[0950] 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 of collecting sales representative data, A means for analyzing the data to generate parameters that characterize the work environment, A means of matching sales representatives in similar work environments, Means of providing online training, Methods for evaluating performance after training, A method of rewarding sales representatives who provide success stories, A system that includes this.

2. The system according to claim 1, characterized in that the online training enables real-time learning.

3. The system according to claim 1, further comprising means for collecting feedback from sales representatives and improving matching and training programs based on said feedback.

Images