system

Abstract

Provide a system. A means for acquiring salesperson performance data and activity data; means for preprocessing the acquired data; means for clustering the preprocessed data; means for analyzing the characteristics of each cluster based on the results of the clustering; a means for suggesting learning materials or training contents according to the analyzed characteristics; a means of providing each salesperson with suggested learning materials or training content; A system including:

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, companies have placed a high priority on improving the capabilities of their salespeople. There is a need to efficiently improve the capabilities of individual salespeople by identifying weak areas based on salespeople's performance and activity data and providing appropriate learning materials and training. However, current systems do not perform data preprocessing, analysis, or appropriate clustering, making it difficult to provide appropriate learning materials and training. To address this issue, there is a need for a system that can identify weak areas based on salespeople's performance and activity data and provide optimal learning materials and training for each salesperson. [Means for solving the problem]

[0005] The present invention provides a system including: means for acquiring performance data and activity data of salespeople; means for preprocessing the acquired data; means for clustering the preprocessed data; means for analyzing characteristics of each cluster based on the clustering results; means for proposing learning materials or training content in accordance with the analyzed characteristics; and means for providing the proposed learning materials or training content to each salesperson. The present invention also provides a system further including means for standardizing the data and means for analyzing the characteristics of the clusters based on average values. This makes it possible to provide optimal learning materials and training content to each salesperson, thereby improving the skills of each individual salesperson.

[0006] "Salesperson" refers to an individual or employee whose job is to propose and sell products or services to customers.

[0007] "Performance data" refers to a numerical record of a salesperson's sales activities, including sales amounts, sales quantities, evaluation scores, and the like.

[0008] "Activity data" refers to various data related to the performance of a salesperson's duties, including, for example, the number of contacts with customers, the completion status of training, and the amount of daily work activity.

[0009] "Means for obtaining" refers to a method or device for collecting salesperson performance and activity data.

[0010] "Preprocessing means" refers to a method or device for processing acquired data into a form that is easy to analyze.

[0011] "Clustering means" refers to a method or device for classifying pre-processed data into multiple groups.

[0012] "Means for analyzing" refers to a method or device for analyzing the characteristics of each group obtained as a result of clustering.

[0013] "Learning Materials" refers to educational materials and content provided to salespeople to improve their skills, including textbooks, videos, and online courses.

[0014] "Training content" refers to structured programs or sessions designed to improve salespeople's skills and knowledge.

[0015] "Standardization means" refers to a method or device for converting data values ​​measured on different scales to the same standard.

[0016] "Features" refer to common characteristics, patterns, and trends within a cluster, and are often expressed as statistical indicators such as the mean and standard deviation.

[0017] The "means for suggesting" refers to a method or device for determining and notifying learning materials and training contents suitable for each salesperson based on the analysis results.

[0018] "Means of delivery" refers to the method or device by which the proposed learning materials or training content is actually distributed, displayed, or made available to the sales force. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a 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.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0033] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention relates to a system for analyzing weak areas based on salesperson performance data and activity data, and proposing appropriate learning materials and training for each salesperson. This system performs the following processes.

[0041] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0042] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0043] The server then uses a clustering technique on the pre-processed data to classify the salespeople into clusters, such as using the KMeans algorithm, so that salespeople with similar characteristics are grouped together in the same cluster.

[0044] The server then analyzes the characteristics of each cluster based on the clustering results. For example, it calculates the average value and standard deviation of each cluster and identifies the areas in which the salesperson is strong or weak. This analysis clarifies the weak areas of each cluster.

[0045] The server then proposes learning materials or training content based on the analyzed characteristics. Specifically, it provides customer service textbooks and videos to clusters with low customer service ratings, and proposes closing skills training to clusters with low sales skills.

[0046] Finally, the server provides the suggested learning materials or training content to each salesperson. This information is displayed to each salesperson via their terminal. The salesperson can improve their skills by taking the suggested learning materials or training.

[0047] Examples:

[0048] For example, a salesperson with ID 1 has the following data:

[0049] Sales amount: 200

[0050] Customer Service Rating: 4.5

[0051] Training Completed: True

[0052] Activity Level: 50

[0053] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0054] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0055] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training contents based on the individual data of each salesperson.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] A server retrieves salesperson performance and activity data, including each salesperson's sales volume, customer service ratings, training completion status, activity level, etc.

[0059] Step 2:

[0060] The server preprocesses the acquired data. First, it removes unnecessary columns from the dataset. Next, it uses StandardScaler to standardize the data, converting the values ​​of each column to the same scale. This unifies data with different scales into a consistent scale.

[0061] Step 3:

[0062] The server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into the specified number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0063] Step 4:

[0064] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0065] Step 5:

[0066] The server then proposes learning materials and training content for each cluster based on the analysis results. For example, if a particular cluster has a low customer service rating, it will provide customer service textbooks and videos to the salespeople in that cluster. On the other hand, it will propose training on closing techniques to clusters with low sales performance.

[0067] Step 6:

[0068] The server provides each salesperson with suggested learning materials and training content. The method of delivery is displayed to each salesperson via their terminal. The salesperson can then access the suggested learning materials and training content and receive the necessary training.

[0069] Step 7:

[0070] Salespeople (users) receive training according to the proposed learning materials and training content, which is expected to improve the skills and knowledge of salespeople and improve their individual sales performance.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] Conventional salesperson training systems have the problem of being unable to effectively utilize the performance and activity data of individual salespeople and propose optimal learning materials and training programs that address their weaknesses. As a result, the effectiveness of the training is limited, making it difficult to achieve overall improvement in the salesperson's abilities. In addition, the lack of individual guidance for each salesperson makes it difficult to take an effective approach.

[0074] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0075] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training contents according to the analyzed characteristics, means for providing the proposed learning materials or training contents to each salesperson, and means for displaying the proposed learning materials or training contents to the salesperson via a terminal. This makes it possible to propose optimal learning materials and training contents for each salesperson, thereby improving the overall ability of the salesperson.

[0076] "Salesperson performance data" refers to data on the results of sales activities, such as sales volume and sales amount achieved by the salesperson in the past, and evaluation scores from customers.

[0077] "Activity data" is information about the salesperson's daily activities, including the number of contacts with customers, training progress, activity level, and the like.

[0078] "Capture means" refers to the processes and techniques by which the system collects salesperson performance and activity data.

[0079] "Preprocessing means" refers to the processes and techniques used to remove unnecessary data and standardize data in order to format collected data in a way that makes it easier to analyze.

[0080] A "clustering method" is a process or technique for grouping data with similar characteristics based on preprocessed data, and specifically, the KMeans algorithm is used.

[0081] "Means of analysis" refers to the processes and techniques for analyzing the characteristics of each cluster classified by clustering and identifying weaknesses and strengths.

[0082] The "means for proposing learning materials or training content" refers to the process or technique for selecting and proposing optimal learning materials or training programs for each cluster or individual salesperson based on the analysis results.

[0083] The "means of delivery" refers to the process and technology used to deliver the proposed learning materials and training content to each salesperson.

[0084] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, used by a salesperson to display suggested learning materials or training content.

[0085] The present invention is a system that analyzes salesperson performance data and activity data and proposes appropriate learning materials and training for each salesperson. This system is implemented using the following hardware and software.

[0086] First, the server acquires salesperson performance data and activity data. To do this, the server collects the data using an application programming interface (API) from a CRM system, sales management tool, etc. For example, Salesforce is often used as a common CRM system.

[0087] Next, the data acquired by the server is preprocessed. In this process, unnecessary data is deleted and the Python pandas library and scikit-learn library are used to standardize the data. Standardization unifies the scale of the data and improves the accuracy of clustering.

[0088] The server then applies the KMeans algorithm to cluster the preprocessed data using Python's scikit-learn library, with the goal of classifying salespeople with similar characteristics into the same cluster.

[0089] Based on the clustering results, the server analyzes the characteristics of each cluster, calculating the mean and standard deviation of each cluster and identifying areas in which each cluster excels or fails. This analysis is also performed using Python's numpy and pandas libraries.

[0090] The server then uses the analysis results to recommend the most appropriate learning materials and training content for each cluster and salesperson. These can include various formats, such as text-based and video materials. For example, a cluster with poor customer service ratings might be provided with text or videos about customer service, while a cluster with poor sales skills might be offered training on closing skills.

[0091] Finally, the server provides each salesperson with suggested learning materials and training content, which is displayed to them via their device (e.g., computer, smartphone, tablet, etc.).

[0092] Specific examples

[0093] For example, a salesperson with ID 1 has the following data:

[0094] Sales amount: 200

[0095] Customer Service Rating: 4.5

[0096] Training Completed: True

[0097] Activity Level: 50

[0098] The server preprocesses this data, standardizes the data of other salespeople, and performs clustering. As a result, the salesperson with ID 1 is classified into cluster 0. The analysis shows that the characteristics of cluster 0 are that their customer service is highly rated, but their sales amount is average. In this case, the server makes a suggestion to cluster 0 saying, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0099] On the other hand, salesperson ID4 has the following data:

[0100] Sales amount: 400

[0101] Customer Service Rating: 5

[0102] Training Complete: False

[0103] Activity Level: 80

[0104] This salesperson is classified into cluster 1, and based on the characteristics of the cluster, the server suggests, "Customer service needs improvement. Provide customer service text and video."

[0105] Prompt Sentence Examples

[0106] "Please explain the specific processing steps and operation of a system that identifies weak areas of salespeople based on sales performance data and activity data, and suggests optimal learning materials and training content for each salesperson."

[0107] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by analyzing the data of individual salespeople and proposing optimal learning materials and training contents.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] A server retrieves salesperson performance and activity data.

[0111] Inputs: Performance data (sales amount, evaluation score, etc.) and activity data (number of contacts, activity level, etc.) for each salesperson.

[0112] Specific operation: The server collects salesperson data from the sales system or CRM tool using APIs. For example, it reads data from the API endpoint of the CRM tool.

[0113] Output: A set of captured salesperson performance and activity data.

[0114] Step 2:

[0115] Preprocess the data retrieved by the server.

[0116] Input: A captured set of salesperson performance and activity data.

[0117] What it does: The server cleanses the dataset using Python's pandas library to remove unnecessary rows and columns, and standardizes the data using the StandardScaler library from scikit-learn.

[0118] Output: A cleansed and standardized dataset.

[0119] Step 3:

[0120] The server clusters the preprocessed data.

[0121] Input: Preprocessed salesperson dataset.

[0122] What it does: The server clusters the data using the KMeans algorithm from Python's scikit-learn library. After setting the K value, it applies a clustering method to group data points with similar characteristics.

[0123] Output: Cluster labels and cluster centers for each salesperson resulting from the clustering.

[0124] Step 4:

[0125] The server analyzes the clustering results.

[0126] Input: Cluster labels and cluster centers obtained as a result of clustering.

[0127] Specific operation: The server uses Python's numpy and pandas libraries to calculate the mean and standard deviation of each cluster to analyze the characteristics of each cluster, thereby clarifying the weaknesses and strengths of each cluster.

[0128] Output: Statistical data about the characteristics of each cluster (mean, standard deviation, etc.).

[0129] Step 5:

[0130] The server suggests learning materials and training content based on the analysis results.

[0131] Input: Statistical data about the characteristics of each cluster.

[0132] How it works: The server uses the generative AI model to select the optimal learning materials and training content for each cluster based on its weaknesses, for example, suggesting training on closing techniques or customer service texts and videos.

[0133] Output: Recommendations (list of training and educational materials) for each cluster or individual salesperson.

[0134] Step 6:

[0135] The server provides each salesperson with suggested learning materials and training content.

[0136] Input: A list of suggested learning materials and training content.

[0137] Specific Operation: The server distributes the proposed learning materials and training content to the salesperson via email or a learning management system (LMS).

[0138] Output: Delivered learning materials and training content.

[0139] Step 7:

[0140] The device displays the provided learning materials and training content to the user.

[0141] Input: Learning materials and training content delivered from the server.

[0142] Specific operation: The device (computer, smartphone, tablet) notifies and displays the learning materials and training content to the user. The user checks the learning materials and training information on the device and begins learning.

[0143] Output: The learning material or training content displayed to the user.

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] In conventional training proposal systems based on salesperson performance data and activity data, the proposed learning materials and training contents are not properly notified to salespersons, and progress management is insufficient, making it difficult to expect effective skill improvement. The present invention aims to solve this problem by notifying each salesperson and managing their progress, thereby improving the overall skills of salespersons.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, means for notifying each salesperson of the proposed learning materials or training content, and means for managing the progress of the notified learning materials or training content. This enables salespeople to receive the proposed learning materials or training content in a timely manner and effectively manage their progress.

[0149] "Salesperson" refers to an individual who sells products or services to customers in a brick-and-mortar store.

[0150] "Performance data" refers to data including sales figures and customer evaluation scores achieved by salespeople in the past.

[0151] "Activity data" refers to data including salesperson training completion status, number of customer contacts, and daily activity levels.

[0152] "Preprocessing" refers to processes such as removing unnecessary information from acquired data and standardizing the data.

[0153] "Clustering" refers to the process of grouping data with similar characteristics using algorithms such as the KMeans algorithm.

[0154] "Characteristic analysis" refers to analyzing the characteristics of each group formed as a result of clustering and identifying areas of strength and weakness.

[0155] "Learning materials" refers to educational resources such as textbooks and videos aimed at improving the skills of salespeople.

[0156] "Training content" refers to the specific content of the training program to improve sales staff skills.

[0157] "Means of notification" refers to the method by which each salesperson is informed of the proposed learning materials and training content.

[0158] "Progress management" refers to tracking how much of the suggested learning material or training content a salesperson has completed.

[0159] The present invention relates to a system for proposing learning materials and training contents based on performance data and activity data of salespeople, and further for notifying them and managing their progress. Specific embodiments of the system are described below.

[0160] Hardware and Software

[0161] The system's main hardware includes a smartphone and a server, and the software uses Python, Scikit-learn, and Firebase. The server plays a central role in data collection, preprocessing, clustering, and notification / progress management. Meanwhile, the smartphone acts as a terminal where salespeople input their data and receive notifications from the server.

[0162] Data collection and preprocessing

[0163] The server receives salesperson performance data (e.g., sales amount and customer evaluation score) and activity data (e.g., training completion status and number of contacts) sent from the smartphone. The server preprocesses this data using Python's Pandas library. This preprocessing includes removing unnecessary data and standardizing data items.

[0164] Clustering and feature analysis

[0165] The preprocessed data is clustered using Scikit-learn's KMeans algorithm, which classifies salespeople with similar characteristics into the same cluster. The server analyzes the characteristics of each cluster and calculates statistics such as the mean and standard deviation. This clarifies the strengths and weaknesses of each cluster.

[0166] Proposal of learning materials and training contents

[0167] Based on the analysis results, the server will suggest optimal learning materials and training content for each cluster. For example, it will provide customer service textbooks and videos to a cluster with low customer service ratings, and suggest closing skills training to a cluster with low sales ability.

[0168] Notifications and progress tracking

[0169] Salespeople are notified of suggested learning materials and training content through an application installed on their smartphones. This notification is made using Firebase's push notification function. Furthermore, the system also includes a progress management function to track how much of the learning material and training content a salesperson has completed. This allows salespeople to check their progress in real time and study more efficiently.

[0170] Examples and prompts

[0171] Salespeople use a smartphone app to input, for example, sales figures for the past month and customer ratings. The data is preprocessed on the server side, and based on the clustering results, a link to a video tutorial to improve "closing skills" is provided and a push notification is sent to the salesperson.

[0172] (Example of a prompt to input to a generative AI model):

[0173] Given a dataset of sales performance and activity data for salespeople, apply data preprocessing steps to clean and standardize the data. Use KMeans clustering to group the salespeople into clusters based on their performance metrics. Analyze the characteristics of each cluster and identify the areas where they need improvement. Suggest appropriate training materials and send push notifications to the salespeople via a mobile application.

[0174] In this way, salespeople can receive suggested educational materials and training content in a timely manner and their progress can be effectively managed.

[0175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0176] Step 1:

[0177] The server acquires the salesperson's performance data and activity data from the smartphone. Performance data includes sales amount and customer evaluation score, and activity data includes training completion status and number of contacts. This data is entered and sent to the server.

[0178] Step 2:

[0179] The server preprocesses the acquired data. Specifically, it uses Python's Pandas library to clean the data, impute missing values, and remove unnecessary columns. It also standardizes the data and converts each data item to the same scale. This process improves the accuracy of clustering and analysis. The input is unprocessed raw data, and the output is clean, standardized data.

[0180] Step 3:

[0181] The server clusters the preprocessed data, using the KMeans algorithm from the Scikit-learn library to group salespeople with similar characteristics. The input is the preprocessed data, and the output is the cluster label assigned to each data point.

[0182] Step 4:

[0183] The server analyzes the characteristics of each cluster from the clustering results. For example, it calculates the mean and standard deviation for each cluster and identifies areas of strength and weakness. The input is data with cluster labels, and the output is statistical information for each cluster.

[0184] Step 5:

[0185] The server proposes learning materials and training content suitable for each cluster based on the analysis results. The proposed content is automatically generated based on the characteristics of each cluster. The input is statistical information for each cluster, and the output is a list of learning materials and training content for each cluster.

[0186] Step 6:

[0187] Suggested learning materials and training content are notified to each salesperson via a smartphone app. This notification is sent using Firebase's push notification function. The input is the suggestion content from the server, and the output is a notification displayed on the salesperson's device.

[0188] Step 7:

[0189] Salespeople use a smartphone app to work through learning materials and training content, and input their progress in real time. The server receives this progress data and manages it. The input is the user's progress data, and the output is updated progress information.

[0190] In this way, each salesperson can receive the suggested educational materials and training content in a timely manner and effectively manage their progress.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. This system performs the following processes.

[0193] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0194] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0195] Next, the server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0196] The server then analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0197] The server then proposes learning materials or training content according to the analyzed characteristics. Specifically, if a particular cluster has a low customer service rating, it provides customer service textbooks and videos to the salespeople in that cluster, and proposes closing skills training to the cluster with low sales ability.

[0198] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson during learning and training. Based on this, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling stressed, the server will provide them with content that is less difficult, and conversely, if they are in a state of high excitement, it will add more challenging tasks.

[0199] The server also evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data, making it possible to understand how effective the provided content was in improving the salesperson's skills.

[0200] Examples:

[0201] For example, a salesperson with ID 1 has the following data:

[0202] Sales amount: 200

[0203] Customer Service Rating: 4.5

[0204] Training Completed: True

[0205] Activity Level: 50

[0206] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0207] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0208] Furthermore, the emotion engine recognizes the emotions of the salesperson (user), and if it detects that the salesperson is feeling nervous or stressed during the training, the server adjusts the difficulty level to allow the user to study in a relaxed state. For example, if salesperson ID1 feels high stress during training on closing techniques, the emotion engine will detect this and the server will change the training content to a relatively easy one. This provides an environment in which the salesperson can study effectively.

[0209] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training content based on each salesperson's individual data and further adjusting the content in real time using an emotion engine.

[0210] The processing flow will be explained below.

[0211] Step 1:

[0212] The server acquires salesperson performance data and activity data, including sales amounts, customer service ratings, training completion status, activity levels, etc. This data is collected from a database or the like.

[0213] Step 2:

[0214] The server preprocesses the acquired data. Specifically, it removes unnecessary columns and standardizes the values ​​of each column using StandardScaler. This standardization unifies data with different scales into a consistent scale.

[0215] Step 3:

[0216] The server performs clustering using the preprocessed data, dividing the data into multiple clusters using the KMeans algorithm, and adding information to the original data about which cluster each salesperson belongs to.

[0217] Step 4:

[0218] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales, customer service evaluation, and activity level within each cluster to clarify the characteristics of each cluster. This analysis identifies the areas in which each cluster has strengths and weaknesses.

[0219] Step 5:

[0220] The server then proposes learning materials and training content for each cluster based on the analysis results. For clusters with low customer service ratings, it provides customer service textbooks and videos, and for clusters with low sales ability, it proposes training on closing techniques.

[0221] Step 6:

[0222] The server provides the salespeople with the learning materials and training content proposed for each cluster. The appropriate learning materials and training content are displayed to each salesperson via their terminal. The salesperson accesses these and receives the training.

[0223] Step 7:

[0224] The emotion engine recognizes the emotions of the salesperson user in real time during training. Emotion data is collected using facial recognition and biometric sensors, for example.

[0225] Step 8:

[0226] Based on the emotional data collected by the emotion engine, the server adjusts the learning materials and training content in real time. For example, if a salesperson is feeling stressed, it will provide them with less difficult content, and conversely, if they are highly excited, it will provide them with more challenging tasks.

[0227] Step 9:

[0228] The server evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data. By comparing the emotional data with the learning outcomes, the server analyzes the extent to which the provided content contributed to improving the salesperson's skills.

[0229] Step 10:

[0230] Salespeople (users) receive training according to the suggested learning materials and training content. By providing adjusted learning materials and training in real time via their devices, they can efficiently learn and improve their skills. This process continues, and data is updated regularly to ensure that optimal training is always provided.

[0231] Example 2

[0232] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0233] There is a need to effectively utilize salesperson performance and activity data, accurately analyze each salesperson's strengths and weaknesses, and then propose appropriate learning materials and training content.However, conventional systems have not been able to fully provide learning materials and training content optimized for each salesperson, and they do not make adjustments based on real-time emotional data, so there are limitations to improving the overall capabilities of salespersons.

[0234] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0235] In this invention, the server includes means for acquiring salesperson performance data and activity data, means for preprocessing the acquired data, and means for clustering the preprocessed data. This enables accurate clustering based on the data of individual salespersons. It also includes means for analyzing the characteristics of each cluster based on the clustering results and means for proposing learning materials or training content based on the analyzed characteristics, and means for providing the proposed learning materials or training content to each salesperson. It also includes means for recognizing the emotions of the salesperson during the learning or training, means for adjusting the learning materials or training content in real time based on the recognized emotions, and means for evaluating the effectiveness of the proposed learning materials or training content. This enables accurate analysis and individualized learning based on the salesperson's performance data and activity data, and further enables the salesperson's overall ability to be improved by adjusting the learning content in real time using emotional data.

[0236] "Salesperson performance data" refers to data that indicates the results of sales activities that a salesperson has conducted in the past, and specifically includes the quantity of products sold, the sales amount, and evaluation scores from customers.

[0237] "Activity data" refers to data relating to the salesperson's daily work activities, including, for example, the number of customer contacts, training completion status, and daily activity level.

[0238] "Means of acquisition" refers to the means for collecting the target data, and includes methods such as API calls and database queries.

[0239] "Preprocessing means" refers to means for converting collected raw data into an analyzable format, and specifically includes removing unnecessary columns and standardizing data.

[0240] The "clustering means" refers to a means for dividing collected and preprocessed data into groups based on specific criteria, and specifically includes the KMeans algorithm.

[0241] "Means for analyzing the characteristics of clusters" refers to means for clarifying the characteristics of each cluster based on the results of clustering, and specifically includes methods for calculating the mean value and standard deviation.

[0242] The "means for proposing learning materials or training contents" refers to a means for selecting and proposing the most suitable learning materials or training contents for each cluster based on the characteristics of the analyzed cluster.

[0243] The "means of provision" refers to the means for delivering or notifying each salesperson of the proposed learning materials and training content.

[0244] "Emotion recognition means" refers to means for detecting the emotions felt by salespeople in real time during learning and training, and specifically includes biofeedback devices and emotion recognition software.

[0245] "Means for real-time adjustment" refers to means for changing the difficulty level and content of learning materials and training content on the fly based on recognized emotional data.

[0246] "Means for evaluating effectiveness" are means for measuring the extent to which the proposed learning materials and training content have contributed to improving the skills of sales staff.

[0247] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. The program of this system will be described in detail below.

[0248] First, the server acquires the salesperson's performance data and activity data. This performance data includes the number of products sold, sales amount, and customer evaluation scores, while the activity data includes the number of customer contacts, training completion status, daily activity level, etc. A database management system (e.g., MySQL (registered trademark) or PostgreSQL) and an API communication tool (e.g., REST API) are used to collect the data.

[0249] Next, the server preprocesses the acquired data by removing unnecessary columns and standardizing each data item to the same scale. Data processing frameworks such as Pandas and NumPy are used for data processing.

[0250] The server then performs clustering on the preprocessed data. Specifically, it uses Scikit-learn's KMeans algorithm to divide the data into a specific number of clusters. During this process, information about which cluster each salesperson belongs to is added to the original data.

[0251] Next, the server analyzes the characteristics of each cluster based on the clustering results. Specifically, it calculates the mean and standard deviation of each cluster and clarifies characteristics such as sales performance and customer service evaluation for each cluster. This process uses statistical analysis tools (e.g., Pandas).

[0252] The server then suggests optimal learning materials and training content for each cluster based on the cluster's characteristics. For example, it provides customer service textbooks and videos to a cluster with low customer service ratings, and suggests training on closing skills to a cluster with low sales ability. Notifications of the suggestions are sent via email or notification systems (e.g., SMTP or SNS).

[0253] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson users in real time during learning and training. Based on this data, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling high stress, the difficulty level can be lowered, and conversely, if the salesperson is in a high state of excitement, more challenging tasks can be added. Emotion recognition is achieved using biofeedback devices and emotion recognition software (e.g., Affectiva).

[0254] Finally, the server evaluates the effectiveness of the proposed learning materials and training content, which involves comparing performance data and emotion data after training to evaluate the learning effect.

[0255] As a concrete example, suppose the performance data for a salesperson with ID 1 is as follows:

[0256] Sales amount: 200

[0257] Customer Service Rating: 4.5

[0258] Training Completed: True

[0259] Activity Level: 50

[0260] The server preprocesses this data and clusters it with other salespeople who belong to the same cluster. As a result, salesperson ID1 is classified into cluster 0. Cluster 0 has a high reputation for customer service but average sales. In this case, the server suggests to the salesperson in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques." If salesperson ID1 feels high stress during the training, the emotion engine detects this and the server adjusts the training content to be easier.

[0261] In this way, the system of the present invention provides optimal learning materials and training content based on salesperson performance data and activity data, and further makes adjustments based on real-time emotion recognition, thereby comprehensively supporting the improvement of salesperson skills.

[0262] Example prompt sentence:

[0263] "What are the data entries for Salesperson ID 1, with sales of 200 and a customer service rating of 4.5?"

[0264] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0265] Step 1: Collect data

[0266] A server retrieves salesperson performance and activity data.

[0267] Input: Salesperson performance and activity data from a database or API

[0268] Specific operation: The server executes an API call to retrieve salesperson information from the database, including sales volume, sales amount, customer evaluation score, number of customer contacts, training completion status, and daily activity level.

[0269] Output: raw data collected

[0270] Step 2: Preprocessing the data

[0271] The server preprocesses the collected data.

[0272] Input: Raw data

[0273] Specific operation: The server uses the Pandas library to remove unnecessary columns from the raw data, standardize each data item to the same scale, and impute missing values ​​appropriately.

[0274] Output: Preprocessed data

[0275] Step 3: Clustering

[0276] The server performs clustering using the preprocessed data.

[0277] Input: Preprocessed data

[0278] Specific operation: The server uses Scikit-learn's KMeans algorithm to divide the data into the number of clusters. The number of clusters is based on the parameters set in advance. Information about which cluster each salesperson belongs to is added to the original data.

[0279] Output: Clustering results (data with cluster information for each salesperson added)

[0280] Step 4: Feature Analysis

[0281] The server analyzes the characteristics of each cluster based on the clustering results.

[0282] Input: Clustering results

[0283] Specific operation: The server uses Pandas to calculate the mean and standard deviation of each cluster, clarifying the characteristics of each cluster. This identifies the areas in which each cluster has strengths and weaknesses.

[0284] Output: Feature data for each cluster

[0285] Step 5: Proposing learning materials and training content

[0286] The server proposes the most suitable learning materials and training content for each cluster based on the characteristics of the cluster.

[0287] Input: Cluster feature data

[0288] Specific operation: The server considers the characteristics of each cluster, for example, providing customer service texts and videos for a cluster with low customer service ratings, and suggesting closing skills training for a cluster with low sales ability. This information is added to the suggestion list.

[0289] Output: A list of suggested learning materials and training content

[0290] Step 6: Real-time adjustments with the emotion engine

[0291] The emotion engine collects emotional data from salespeople, and the server uses this data to adjust learning materials and training content in real time.

[0292] Input: Emotion data during learning or training

[0293] How it works: The emotion engine recognizes the salesperson's emotions, such as stress and concentration, in real time, and the server analyzes the data. For example, if the salesperson is highly stressed, the difficulty level is reduced, and if the salesperson is highly excited, more challenging tasks are added.

[0294] Output: Tailored learning materials and training content

[0295] Step 7: Evaluate the effect

[0296] The server evaluates the effectiveness of the proposed learning materials and training contents.

[0297] Input: Performance data and emotional data after implementing learning materials and training content

[0298] Specific operation: The server compares performance data before and after learning or training, and evaluates the learning effectiveness by taking into account emotional data. This allows the server to understand how effective the proposed training content was in improving the salesperson's skills. Feedback is reflected in the next proposal.

[0299] Output: Evaluation results of learning effect

[0300] The above is a series of specific processing steps for the program of this system.

[0301] (Application example 2)

[0302] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0303] Conventional salesperson skill improvement systems have difficulty reflecting individual salesperson weaknesses and learning progress in real time. Furthermore, they have had problems with ineffective learning and training, resulting in lower sales work efficiency and lower customer satisfaction. The present invention aims to effectively improve salesperson skills by providing appropriate learning materials and training based on the performance and activity data of individual salespersons, and further adjusting the learning materials and training content in real time based on emotion recognition.

[0304] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for pre-processing the acquired data, means for clustering the pre-processed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, and means for adjusting the learning materials or training content in real time based on emotion recognition. This makes it possible to provide an optimized learning experience for each salesperson, thereby improving sales efficiency and customer satisfaction.

[0305] - "Salesperson performance data" is a general term for data recorded as performance, such as sales amounts, sales quantities, and customer evaluation scores achieved by salespersons in the past.

[0306] "Activity data" refers to data about the salesperson's daily work activities, including the number of customer contacts, training completion status, patrol frequency, and number of security camera checks.

[0307] "Preprocessing" refers to the process of removing unnecessary columns from raw data, standardizing the data, and preparing the data for analysis and clustering.

[0308] "Clustering" is an analytical technique for classifying data into multiple groups (clusters), and is used in the present invention to identify the strengths and weaknesses of salespeople.

[0309] "Cluster characteristics" refer to common characteristics of the data belonging to each cluster, including, for example, the average value and standard deviation of sales performance and customer service evaluation within each cluster.

[0310] "Learning Materials" refers to educational content, such as textbooks, videos, and online courses, provided to salespeople to improve their skills.

[0311] "Training Content" refers to the content of the training program in which salespeople learn specific skills, including on-the-job training and simulations.

[0312] "Emotion recognition" refers to technology that analyzes a user's facial expressions, voice, and physical movements to identify their emotional state at any given time (stress, tension, excitement, etc.).

[0313] "Real-time adjustment" refers to the process of instantly changing learning materials and training content based on the user's current state and performance.

[0314] MODE FOR CARRYING OUT THE INVENTION

[0315] The present invention combines an emotion recognition function with a system that proposes appropriate learning materials and training for each salesperson based on the salesperson's performance data and activity data. Specific embodiments for carrying out the present invention will be described below.

[0316] System Program

[0317] 1. Data Collection:

[0318] The server acquires salesperson performance and activity data, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, daily activity levels, etc.

[0319] 2. Data Preprocessing:

[0320] The server preprocesses the acquired data. During the preprocessing stage, unnecessary columns are removed and the data is scaled for standardization purposes, so that data of different scales can be treated on the same basis.

[0321] 3. Clustering:

[0322] Clustering is performed using the preprocessed data. Specifically, the KMeans algorithm is used to classify the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0323] 4. Feature analysis:

[0324] The server analyzes the characteristics of each cluster based on the clustering results, calculating the mean and standard deviation within each cluster and identifying which clusters have strengths and weaknesses in which areas.

[0325] 5. Learning Materials and Training Suggestions:

[0326] Depending on the analyzed characteristics, learning materials or training content suitable for a specific cluster are suggested. For example, customer service textbooks and videos are provided to a cluster with low customer service ratings, and closing skills training is provided to a cluster with low sales ability.

[0327] 6. Emotion recognition and real-time adjustment:

[0328] Using an emotion recognition engine, the server recognizes the emotions of salespeople during learning and training. For example, if a user is feeling stressed, the server will lower the difficulty of the content provided, and conversely, if the user is in a state of high excitement, it will add more challenging tasks.

[0329] Hardware / Software used

[0330] Hardware: Smart glasses (generic name), head-mounted display (generic name), cloud-based server (generic name).

[0331] Software: Python, Pandas, Scikit-Learn, Affectiva (emotion recognition system).

[0332] Specific examples

[0333] For example, say you have a salesperson ID1 with the following data:

[0334] Sales amount: 200

[0335] Customer Service Rating: 4.5

[0336] Training Completion Status: Completed

[0337] Activity Level: 50

[0338] The server preprocesses this data, standardizes the data of salespeople with similar data, and performs clustering. As a result, salesperson ID 1 is classified into cluster 0. The analysis shows that salespeople in cluster 0 have high customer service ratings, but average sales. In this case, the server suggests to the salespeople in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0339] Furthermore, if the emotion recognition engine detects the emotions of the salesperson (user), for example, if it detects that the salesperson is feeling high stress during training, the server will change the training content to a relatively easy one, thereby providing an environment in which the salesperson can learn effectively.

[0340] As an example of a specific prompt, you can enter the following:

[0341] "Adjust the next training content based on Security Guard A's latest emotional data. If his stress level is high, lower the difficulty."

[0342] "If high stress is detected during closing skills training for salesperson ID1, change the content to something simpler in real time."

[0343] In this way, the system effectively improves salespeople's skills by providing them with optimal learning materials and training content based on their individual data, and further adjusting the content in real time using emotion recognition.

[0344] Summary of the Invention

[0345] This system provides an optimal learning experience for each salesperson by proposing learning materials and training content based on the salesperson's performance and activity data and adjusting the content in real time based on emotion recognition, thereby improving sales efficiency and customer satisfaction.

[0346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0347] Step 1:

[0348] The server retrieves salesperson performance and activity data from a database, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, and daily activity levels. The input is the raw data extracted from the database, and the output is a dataset for preprocessing.

[0349] Step 2:

[0350] The server preprocesses the acquired data. This preprocessing includes removing unnecessary columns, imputing missing values, and standardizing the data. For example, standardization converts each data item to the same scale. The input is the raw dataset, and the output is the preprocessed dataset.

[0351] Step 3:

[0352] The server performs clustering using the preprocessed dataset. Specifically, it applies the KMeans algorithm to classify the data into the set number of clusters. The input is the preprocessed dataset, and the output is a data label indicating which cluster each salesperson belongs to.

[0353] Step 4:

[0354] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales performance, customer service ratings, and activity levels within each cluster to identify cluster characteristics. The input is the clustered dataset, and the output is the average feature value of each cluster.

[0355] Step 5:

[0356] The server then proposes appropriate learning materials or training content for each salesperson based on the analyzed cluster characteristics. For example, if a particular cluster has a low customer service rating, it provides customer service texts or videos to the salespersons in that cluster. The input is the cluster characteristics and individual salesperson information, and the output is a list of suggested learning materials or training content for each salesperson.

[0357] Step 6:

[0358] The server uses an emotion recognition engine to receive real-time emotional data from users (salespeople) who are learning or undergoing training. For example, it analyzes emotional data collected while the user is undergoing training through smart glasses or a head-mounted display. The input is real-time emotional data, and the output is the user's emotional state (stress level, elation, etc.).

[0359] Step 7:

[0360] The server adjusts the learning materials or training content in real time based on the received emotional data. For example, if the user is feeling highly stressed, it will issue instructions to reduce the difficulty of the training content, and conversely, if the user is feeling excited, it will add more challenging tasks. The input is the user's emotional state, and the output is the adjusted learning materials or training content.

[0361] As a specific example, if salesperson ID1 feels high stress during closing skills training, the server adjusts the training to lower its difficulty based on data from the emotion recognition engine. An example of the prompt sentence in this case could be, "If high stress is detected during closing skills training for salesperson ID1, please change the content to something easier in real time."

[0362] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0363] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0364] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0368] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0369] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0370] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0371] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0372] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0373] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0374] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0375] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0376] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0377] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0378] The present invention relates to a system for analyzing weak areas based on salesperson performance data and activity data, and proposing appropriate learning materials and training for each salesperson. This system performs the following processes.

[0379] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0380] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0381] The server then uses a clustering technique on the pre-processed data to classify the salespeople into clusters, such as using the KMeans algorithm, so that salespeople with similar characteristics are grouped together in the same cluster.

[0382] The server then analyzes the characteristics of each cluster based on the clustering results. For example, it calculates the average value and standard deviation of each cluster and identifies the areas in which the salesperson is strong or weak. This analysis clarifies the weak areas of each cluster.

[0383] The server then proposes learning materials or training content based on the analyzed characteristics. Specifically, it provides customer service textbooks and videos to clusters with low customer service ratings, and proposes closing skills training to clusters with low sales skills.

[0384] Finally, the server provides the suggested learning materials or training content to each salesperson. This information is displayed to each salesperson via their terminal. The salesperson can improve their skills by taking the suggested learning materials or training.

[0385] Examples:

[0386] For example, a salesperson with ID 1 has the following data:

[0387] Sales amount: 200

[0388] Customer Service Rating: 4.5

[0389] Training Completed: True

[0390] Activity Level: 50

[0391] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0392] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0393] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training contents based on the individual data of each salesperson.

[0394] The processing flow will be explained below.

[0395] Step 1:

[0396] A server retrieves salesperson performance and activity data, including each salesperson's sales volume, customer service ratings, training completion status, activity level, etc.

[0397] Step 2:

[0398] The server preprocesses the acquired data. First, it removes unnecessary columns from the dataset. Next, it uses StandardScaler to standardize the data, converting the values ​​of each column to the same scale. This unifies data with different scales into a consistent scale.

[0399] Step 3:

[0400] The server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into the specified number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0401] Step 4:

[0402] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0403] Step 5:

[0404] The server then proposes learning materials and training content for each cluster based on the analysis results. For example, if a particular cluster has a low customer service rating, it will provide customer service textbooks and videos to the salespeople in that cluster. On the other hand, it will propose training on closing techniques to clusters with low sales performance.

[0405] Step 6:

[0406] The server provides each salesperson with suggested learning materials and training content. The method of delivery is displayed to each salesperson via their terminal. The salesperson can then access the suggested learning materials and training content and receive the necessary training.

[0407] Step 7:

[0408] Salespeople (users) receive training according to the proposed learning materials and training content, which is expected to improve the skills and knowledge of salespeople and improve their individual sales performance.

[0409] Example 1

[0410] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0411] Conventional salesperson training systems have the problem of being unable to effectively utilize the performance and activity data of individual salespeople and propose optimal learning materials and training programs that address their weaknesses. As a result, the effectiveness of the training is limited, making it difficult to achieve overall improvement in the salesperson's abilities. In addition, the lack of individual guidance for each salesperson makes it difficult to take an effective approach.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0413] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training contents according to the analyzed characteristics, means for providing the proposed learning materials or training contents to each salesperson, and means for displaying the proposed learning materials or training contents to the salesperson via a terminal. This makes it possible to propose optimal learning materials and training contents for each salesperson, thereby improving the overall ability of the salesperson.

[0414] "Salesperson performance data" refers to data on the results of sales activities, such as sales volume and sales amount achieved by the salesperson in the past, and evaluation scores from customers.

[0415] "Activity data" is information about the salesperson's daily activities, including the number of contacts with customers, training progress, activity level, and the like.

[0416] "Capture means" refers to the processes and techniques by which the system collects salesperson performance and activity data.

[0417] "Preprocessing means" refers to the processes and techniques used to remove unnecessary data and standardize data in order to format collected data in a way that makes it easier to analyze.

[0418] A "clustering method" is a process or technique for grouping data with similar characteristics based on preprocessed data, and specifically, the KMeans algorithm is used.

[0419] "Means of analysis" refers to the processes and techniques for analyzing the characteristics of each cluster classified by clustering and identifying weaknesses and strengths.

[0420] The "means for proposing learning materials or training content" refers to the process or technique for selecting and proposing optimal learning materials or training programs for each cluster or individual salesperson based on the analysis results.

[0421] The "means of delivery" refers to the process and technology used to deliver the proposed learning materials and training content to each salesperson.

[0422] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, used by a salesperson to display suggested learning materials or training content.

[0423] The present invention is a system that analyzes salesperson performance data and activity data and proposes appropriate learning materials and training for each salesperson. This system is implemented using the following hardware and software.

[0424] First, the server acquires salesperson performance data and activity data. To do this, the server collects the data using an application programming interface (API) from a CRM system, sales management tool, etc. For example, Salesforce is often used as a common CRM system.

[0425] Next, the data acquired by the server is preprocessed. In this process, unnecessary data is deleted and the Python pandas library and scikit-learn library are used to standardize the data. Standardization unifies the scale of the data and improves the accuracy of clustering.

[0426] The server then applies the KMeans algorithm to cluster the preprocessed data using Python's scikit-learn library, with the goal of classifying salespeople with similar characteristics into the same cluster.

[0427] Based on the clustering results, the server analyzes the characteristics of each cluster, calculating the mean and standard deviation of each cluster and identifying areas in which each cluster excels or fails. This analysis is also performed using Python's numpy and pandas libraries.

[0428] The server then uses the analysis results to recommend the most appropriate learning materials and training content for each cluster and salesperson. These can include various formats, such as text-based and video materials. For example, a cluster with poor customer service ratings might be provided with text or videos about customer service, while a cluster with poor sales skills might be offered training on closing skills.

[0429] Finally, the server provides each salesperson with suggested learning materials and training content, which is displayed to them via their device (e.g., computer, smartphone, tablet, etc.).

[0430] Specific examples

[0431] For example, a salesperson with ID 1 has the following data:

[0432] Sales amount: 200

[0433] Customer Service Rating: 4.5

[0434] Training Completed: True

[0435] Activity Level: 50

[0436] The server preprocesses this data, standardizes the data of other salespeople, and performs clustering. As a result, the salesperson with ID 1 is classified into cluster 0. The analysis shows that the characteristics of cluster 0 are that their customer service is highly rated, but their sales amount is average. In this case, the server makes a suggestion to cluster 0 saying, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0437] On the other hand, salesperson ID4 has the following data:

[0438] Sales amount: 400

[0439] Customer Service Rating: 5

[0440] Training Complete: False

[0441] Activity Level: 80

[0442] This salesperson is classified into cluster 1, and based on the characteristics of the cluster, the server suggests, "Customer service needs improvement. Provide customer service text and video."

[0443] Prompt Sentence Examples

[0444] "Please explain the specific processing steps and operation of a system that identifies weak areas of salespeople based on sales performance data and activity data, and suggests optimal learning materials and training content for each salesperson."

[0445] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by analyzing the data of individual salespeople and proposing optimal learning materials and training contents.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] A server retrieves salesperson performance and activity data.

[0449] Inputs: Performance data (sales amount, evaluation score, etc.) and activity data (number of contacts, activity level, etc.) for each salesperson.

[0450] Specific operation: The server collects salesperson data from the sales system or CRM tool using APIs. For example, it reads data from the API endpoint of the CRM tool.

[0451] Output: A set of captured salesperson performance and activity data.

[0452] Step 2:

[0453] Preprocess the data retrieved by the server.

[0454] Input: A captured set of salesperson performance and activity data.

[0455] What it does: The server cleanses the dataset using Python's pandas library to remove unnecessary rows and columns, and standardizes the data using the StandardScaler library from scikit-learn.

[0456] Output: A cleansed and standardized dataset.

[0457] Step 3:

[0458] The server clusters the preprocessed data.

[0459] Input: Preprocessed salesperson dataset.

[0460] What it does: The server clusters the data using the KMeans algorithm from Python's scikit-learn library. After setting the K value, it applies a clustering method to group data points with similar characteristics.

[0461] Output: Cluster labels and cluster centers for each salesperson resulting from the clustering.

[0462] Step 4:

[0463] The server analyzes the clustering results.

[0464] Input: Cluster labels and cluster centers obtained as a result of clustering.

[0465] Specific operation: The server uses Python's numpy and pandas libraries to calculate the mean and standard deviation of each cluster to analyze the characteristics of each cluster, thereby clarifying the weaknesses and strengths of each cluster.

[0466] Output: Statistical data about the characteristics of each cluster (mean, standard deviation, etc.).

[0467] Step 5:

[0468] The server suggests learning materials and training content based on the analysis results.

[0469] Input: Statistical data about the characteristics of each cluster.

[0470] How it works: The server uses the generative AI model to select the optimal learning materials and training content for each cluster based on its weaknesses, for example, suggesting training on closing techniques or customer service texts and videos.

[0471] Output: Recommendations (list of training and educational materials) for each cluster or individual salesperson.

[0472] Step 6:

[0473] The server provides each salesperson with suggested learning materials and training content.

[0474] Input: A list of suggested learning materials and training content.

[0475] Specific Operation: The server distributes the proposed learning materials and training content to the salesperson via email or a learning management system (LMS).

[0476] Output: Delivered learning materials and training content.

[0477] Step 7:

[0478] The device displays the provided learning materials and training content to the user.

[0479] Input: Learning materials and training content delivered from the server.

[0480] Specific operation: The device (computer, smartphone, tablet) notifies and displays the learning materials and training content to the user. The user checks the learning materials and training information on the device and begins learning.

[0481] Output: The learning material or training content displayed to the user.

[0482] (Application example 1)

[0483] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0484] In conventional training proposal systems based on salesperson performance data and activity data, the proposed learning materials and training contents are not properly notified to salespersons, and progress management is insufficient, making it difficult to expect effective skill improvement. The present invention aims to solve this problem by notifying each salesperson and managing their progress, thereby improving the overall skills of salespersons.

[0485] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0486] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, means for notifying each salesperson of the proposed learning materials or training content, and means for managing the progress of the notified learning materials or training content. This enables salespeople to receive the proposed learning materials or training content in a timely manner and effectively manage their progress.

[0487] "Salesperson" refers to an individual who sells products or services to customers in a brick-and-mortar store.

[0488] "Performance data" refers to data including sales figures and customer evaluation scores achieved by salespeople in the past.

[0489] "Activity data" refers to data including salesperson training completion status, number of customer contacts, and daily activity levels.

[0490] "Preprocessing" refers to processes such as removing unnecessary information from acquired data and standardizing the data.

[0491] "Clustering" refers to the process of grouping data with similar characteristics using algorithms such as the KMeans algorithm.

[0492] "Characteristic analysis" refers to analyzing the characteristics of each group formed as a result of clustering and identifying areas of strength and weakness.

[0493] "Learning materials" refers to educational resources such as textbooks and videos aimed at improving the skills of salespeople.

[0494] "Training content" refers to the specific content of the training program to improve sales staff skills.

[0495] "Means of notification" refers to the method by which each salesperson is informed of the proposed learning materials and training content.

[0496] "Progress management" refers to tracking how much of the suggested learning material or training content a salesperson has completed.

[0497] The present invention relates to a system for proposing learning materials and training contents based on performance data and activity data of salespeople, and further for notifying them and managing their progress. Specific embodiments of the system are described below.

[0498] Hardware and Software

[0499] The system's main hardware includes a smartphone and a server, and the software uses Python, Scikit-learn, and Firebase. The server plays a central role in data collection, preprocessing, clustering, and notification / progress management. Meanwhile, the smartphone acts as a terminal where salespeople input their data and receive notifications from the server.

[0500] Data collection and preprocessing

[0501] The server receives salesperson performance data (e.g., sales amount and customer evaluation score) and activity data (e.g., training completion status and number of contacts) sent from the smartphone. The server preprocesses this data using Python's Pandas library. This preprocessing includes removing unnecessary data and standardizing data items.

[0502] Clustering and feature analysis

[0503] The preprocessed data is clustered using Scikit-learn's KMeans algorithm, which classifies salespeople with similar characteristics into the same cluster. The server analyzes the characteristics of each cluster and calculates statistics such as the mean and standard deviation. This clarifies the strengths and weaknesses of each cluster.

[0504] Proposal of learning materials and training contents

[0505] Based on the analysis results, the server will suggest optimal learning materials and training content for each cluster. For example, it will provide customer service textbooks and videos to a cluster with low customer service ratings, and suggest closing skills training to a cluster with low sales ability.

[0506] Notifications and progress tracking

[0507] Salespeople are notified of suggested learning materials and training content through an application installed on their smartphones. This notification is made using Firebase's push notification function. Furthermore, the system also includes a progress management function to track how much of the learning material and training content a salesperson has completed. This allows salespeople to check their progress in real time and study more efficiently.

[0508] Examples and prompts

[0509] Salespeople use a smartphone app to input, for example, sales figures for the past month and customer ratings. The data is preprocessed on the server side, and based on the clustering results, a link to a video tutorial to improve "closing skills" is provided and a push notification is sent to the salesperson.

[0510] (Example of a prompt to input to a generative AI model):

[0511] Given a dataset of sales performance and activity data for salespeople, apply data preprocessing steps to clean and standardize the data. Use KMeans clustering to group the salespeople into clusters based on their performance metrics. Analyze the characteristics of each cluster and identify the areas where they need improvement. Suggest appropriate training materials and send push notifications to the salespeople via a mobile application.

[0512] In this way, salespeople can receive suggested educational materials and training content in a timely manner and their progress can be effectively managed.

[0513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0514] Step 1:

[0515] The server acquires the salesperson's performance data and activity data from the smartphone. Performance data includes sales amount and customer evaluation score, and activity data includes training completion status and number of contacts. This data is entered and sent to the server.

[0516] Step 2:

[0517] The server preprocesses the acquired data. Specifically, it uses Python's Pandas library to clean the data, impute missing values, and remove unnecessary columns. It also standardizes the data and converts each data item to the same scale. This process improves the accuracy of clustering and analysis. The input is unprocessed raw data, and the output is clean, standardized data.

[0518] Step 3:

[0519] The server clusters the preprocessed data, using the KMeans algorithm from the Scikit-learn library to group salespeople with similar characteristics. The input is the preprocessed data, and the output is the cluster label assigned to each data point.

[0520] Step 4:

[0521] The server analyzes the characteristics of each cluster from the clustering results. For example, it calculates the mean and standard deviation for each cluster and identifies areas of strength and weakness. The input is data with cluster labels, and the output is statistical information for each cluster.

[0522] Step 5:

[0523] The server proposes learning materials and training content suitable for each cluster based on the analysis results. The proposed content is automatically generated based on the characteristics of each cluster. The input is statistical information for each cluster, and the output is a list of learning materials and training content for each cluster.

[0524] Step 6:

[0525] Suggested learning materials and training content are notified to each salesperson via a smartphone app. This notification is sent using Firebase's push notification function. The input is the suggestion content from the server, and the output is a notification displayed on the salesperson's device.

[0526] Step 7:

[0527] Salespeople use a smartphone app to work through learning materials and training content, and input their progress in real time. The server receives this progress data and manages it. The input is the user's progress data, and the output is updated progress information.

[0528] In this way, each salesperson can receive the suggested educational materials and training content in a timely manner and effectively manage their progress.

[0529] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0530] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. This system performs the following processes.

[0531] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0532] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0533] Next, the server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0534] The server then analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0535] The server then proposes learning materials or training content according to the analyzed characteristics. Specifically, if a particular cluster has a low customer service rating, it provides customer service textbooks and videos to the salespeople in that cluster, and proposes closing skills training to the cluster with low sales ability.

[0536] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson during learning and training. Based on this, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling stressed, the server will provide them with content that is less difficult, and conversely, if they are in a state of high excitement, it will add more challenging tasks.

[0537] The server also evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data, making it possible to understand how effective the provided content was in improving the salesperson's skills.

[0538] Examples:

[0539] For example, a salesperson with ID 1 has the following data:

[0540] Sales amount: 200

[0541] Customer Service Rating: 4.5

[0542] Training Completed: True

[0543] Activity Level: 50

[0544] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0545] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0546] Furthermore, the emotion engine recognizes the emotions of the salesperson (user), and if it detects that the salesperson is feeling nervous or stressed during the training, the server adjusts the difficulty level to allow the user to study in a relaxed state. For example, if salesperson ID1 feels high stress during training on closing techniques, the emotion engine will detect this and the server will change the training content to a relatively easy one. This provides an environment in which the salesperson can study effectively.

[0547] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training content based on each salesperson's individual data and further adjusting the content in real time using an emotion engine.

[0548] The processing flow will be explained below.

[0549] Step 1:

[0550] The server acquires salesperson performance data and activity data, including sales amounts, customer service ratings, training completion status, activity levels, etc. This data is collected from a database or the like.

[0551] Step 2:

[0552] The server preprocesses the acquired data. Specifically, it removes unnecessary columns and standardizes the values ​​of each column using StandardScaler. This standardization unifies data with different scales into a consistent scale.

[0553] Step 3:

[0554] The server performs clustering using the preprocessed data, dividing the data into multiple clusters using the KMeans algorithm, and adding information to the original data about which cluster each salesperson belongs to.

[0555] Step 4:

[0556] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales, customer service evaluation, and activity level within each cluster to clarify the characteristics of each cluster. This analysis identifies the areas in which each cluster has strengths and weaknesses.

[0557] Step 5:

[0558] The server then proposes learning materials and training content for each cluster based on the analysis results. For clusters with low customer service ratings, it provides customer service textbooks and videos, and for clusters with low sales ability, it proposes training on closing techniques.

[0559] Step 6:

[0560] The server provides the salespeople with the learning materials and training content proposed for each cluster. The appropriate learning materials and training content are displayed to each salesperson via their terminal. The salesperson accesses these and receives the training.

[0561] Step 7:

[0562] The emotion engine recognizes the emotions of the salesperson user in real time during training. Emotion data is collected using facial recognition and biometric sensors, for example.

[0563] Step 8:

[0564] Based on the emotional data collected by the emotion engine, the server adjusts the learning materials and training content in real time. For example, if a salesperson is feeling stressed, it will provide them with less difficult content, and conversely, if they are highly excited, it will provide them with more challenging tasks.

[0565] Step 9:

[0566] The server evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data. By comparing the emotional data with the learning outcomes, the server analyzes the extent to which the provided content contributed to improving the salesperson's skills.

[0567] Step 10:

[0568] Salespeople (users) receive training according to the suggested learning materials and training content. By providing adjusted learning materials and training in real time via their devices, they can efficiently learn and improve their skills. This process continues, and data is updated regularly to ensure that optimal training is always provided.

[0569] Example 2

[0570] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0571] There is a need to effectively utilize salesperson performance and activity data, accurately analyze each salesperson's strengths and weaknesses, and then propose appropriate learning materials and training content.However, conventional systems have not been able to fully provide learning materials and training content optimized for each salesperson, and they do not make adjustments based on real-time emotional data, so there are limitations to improving the overall capabilities of salespersons.

[0572] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0573] In this invention, the server includes means for acquiring salesperson performance data and activity data, means for preprocessing the acquired data, and means for clustering the preprocessed data. This enables accurate clustering based on the data of individual salespersons. It also includes means for analyzing the characteristics of each cluster based on the clustering results and means for proposing learning materials or training content based on the analyzed characteristics, and means for providing the proposed learning materials or training content to each salesperson. It also includes means for recognizing the emotions of the salesperson during the learning or training, means for adjusting the learning materials or training content in real time based on the recognized emotions, and means for evaluating the effectiveness of the proposed learning materials or training content. This enables accurate analysis and individualized learning based on the salesperson's performance data and activity data, and further enables the salesperson's overall ability to be improved by adjusting the learning content in real time using emotional data.

[0574] "Salesperson performance data" refers to data that indicates the results of sales activities that a salesperson has conducted in the past, and specifically includes the quantity of products sold, the sales amount, and evaluation scores from customers.

[0575] "Activity data" refers to data relating to the salesperson's daily work activities, including, for example, the number of customer contacts, training completion status, and daily activity level.

[0576] "Means of acquisition" refers to the means for collecting the target data, and includes methods such as API calls and database queries.

[0577] "Preprocessing means" refers to means for converting collected raw data into an analyzable format, and specifically includes removing unnecessary columns and standardizing data.

[0578] The "clustering means" refers to a means for dividing collected and preprocessed data into groups based on specific criteria, and specifically includes the KMeans algorithm.

[0579] "Means for analyzing the characteristics of clusters" refers to means for clarifying the characteristics of each cluster based on the results of clustering, and specifically includes methods for calculating the mean value and standard deviation.

[0580] The "means for proposing learning materials or training contents" refers to a means for selecting and proposing the most suitable learning materials or training contents for each cluster based on the characteristics of the analyzed cluster.

[0581] The "means of provision" refers to the means for delivering or notifying each salesperson of the proposed learning materials and training content.

[0582] "Emotion recognition means" refers to means for detecting the emotions felt by salespeople in real time during learning and training, and specifically includes biofeedback devices and emotion recognition software.

[0583] "Means for real-time adjustment" refers to means for changing the difficulty level and content of learning materials and training content on the fly based on recognized emotional data.

[0584] "Means for evaluating effectiveness" are means for measuring the extent to which the proposed learning materials and training content have contributed to improving the skills of sales staff.

[0585] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. The program of this system will be described in detail below.

[0586] First, the server acquires the salesperson's performance data and activity data. This performance data includes the number of products sold, sales amount, and customer evaluation scores, while activity data includes the number of customer contacts, training completion status, daily activity level, etc. Data collection is performed using a database management system (e.g., MySQL or PostgreSQL) and an API communication tool (e.g., REST API).

[0587] Next, the server preprocesses the acquired data by removing unnecessary columns and standardizing each data item to the same scale. Data processing frameworks such as Pandas and NumPy are used for data processing.

[0588] The server then performs clustering on the preprocessed data. Specifically, it uses Scikit-learn's KMeans algorithm to divide the data into a specific number of clusters. During this process, information about which cluster each salesperson belongs to is added to the original data.

[0589] Next, the server analyzes the characteristics of each cluster based on the clustering results. Specifically, it calculates the mean and standard deviation of each cluster and clarifies characteristics such as sales performance and customer service evaluation for each cluster. This process uses statistical analysis tools (e.g., Pandas).

[0590] The server then suggests optimal learning materials and training content for each cluster based on the cluster's characteristics. For example, it provides customer service textbooks and videos to a cluster with low customer service ratings, and suggests training on closing skills to a cluster with low sales ability. Notifications of the suggestions are sent via email or notification systems (e.g., SMTP or SNS).

[0591] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson users in real time during learning and training. Based on this data, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling high stress, the difficulty level can be lowered, and conversely, if the salesperson is in a high state of excitement, more challenging tasks can be added. Emotion recognition is achieved using biofeedback devices and emotion recognition software (e.g., Affectiva).

[0592] Finally, the server evaluates the effectiveness of the proposed learning materials and training content, which involves comparing performance data and emotion data after training to evaluate the learning effect.

[0593] As a concrete example, suppose the performance data for a salesperson with ID 1 is as follows:

[0594] Sales amount: 200

[0595] Customer Service Rating: 4.5

[0596] Training Completed: True

[0597] Activity Level: 50

[0598] The server preprocesses this data and clusters it with other salespeople who belong to the same cluster. As a result, salesperson ID1 is classified into cluster 0. Cluster 0 has a high reputation for customer service but average sales. In this case, the server suggests to the salesperson in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques." If salesperson ID1 feels high stress during the training, the emotion engine detects this and the server adjusts the training content to be easier.

[0599] In this way, the system of the present invention provides optimal learning materials and training content based on salesperson performance data and activity data, and further makes adjustments based on real-time emotion recognition, thereby comprehensively supporting the improvement of salesperson skills.

[0600] Example prompt sentence:

[0601] "What are the data entries for Salesperson ID 1, with sales of 200 and a customer service rating of 4.5?"

[0602] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0603] Step 1: Collect data

[0604] A server retrieves salesperson performance and activity data.

[0605] Input: Salesperson performance and activity data from a database or API

[0606] Specific operation: The server executes an API call to retrieve salesperson information from the database, including sales volume, sales amount, customer evaluation score, number of customer contacts, training completion status, and daily activity level.

[0607] Output: raw data collected

[0608] Step 2: Preprocessing the data

[0609] The server preprocesses the collected data.

[0610] Input: Raw data

[0611] Specific operation: The server uses the Pandas library to remove unnecessary columns from the raw data, standardize each data item to the same scale, and impute missing values ​​appropriately.

[0612] Output: Preprocessed data

[0613] Step 3: Clustering

[0614] The server performs clustering using the preprocessed data.

[0615] Input: Preprocessed data

[0616] Specific operation: The server uses Scikit-learn's KMeans algorithm to divide the data into the number of clusters. The number of clusters is based on the parameters set in advance. Information about which cluster each salesperson belongs to is added to the original data.

[0617] Output: Clustering results (data with cluster information for each salesperson added)

[0618] Step 4: Feature Analysis

[0619] The server analyzes the characteristics of each cluster based on the clustering results.

[0620] Input: Clustering results

[0621] Specific operation: The server uses Pandas to calculate the mean and standard deviation of each cluster, clarifying the characteristics of each cluster. This identifies the areas in which each cluster has strengths and weaknesses.

[0622] Output: Feature data for each cluster

[0623] Step 5: Proposing learning materials and training content

[0624] The server proposes the most suitable learning materials and training content for each cluster based on the characteristics of the cluster.

[0625] Input: Cluster feature data

[0626] Specific operation: The server considers the characteristics of each cluster, for example, providing customer service texts and videos for a cluster with low customer service ratings, and suggesting closing skills training for a cluster with low sales ability. This information is added to the suggestion list.

[0627] Output: A list of suggested learning materials and training content

[0628] Step 6: Real-time adjustments with the emotion engine

[0629] The emotion engine collects emotional data from salespeople, and the server uses this data to adjust learning materials and training content in real time.

[0630] Input: Emotion data during learning or training

[0631] How it works: The emotion engine recognizes the salesperson's emotions, such as stress and concentration, in real time, and the server analyzes the data. For example, if the salesperson is highly stressed, the difficulty level is reduced, and if the salesperson is highly excited, more challenging tasks are added.

[0632] Output: Tailored learning materials and training content

[0633] Step 7: Evaluate the effect

[0634] The server evaluates the effectiveness of the proposed learning materials and training contents.

[0635] Input: Performance data and emotional data after implementing learning materials and training content

[0636] Specific operation: The server compares performance data before and after learning or training, and evaluates the learning effectiveness by taking into account emotional data. This allows the server to understand how effective the proposed training content was in improving the salesperson's skills. Feedback is reflected in the next proposal.

[0637] Output: Evaluation results of learning effect

[0638] The above is a series of specific processing steps for the program of this system.

[0639] (Application example 2)

[0640] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0641] Conventional salesperson skill improvement systems have difficulty reflecting individual salesperson weaknesses and learning progress in real time. Furthermore, they have had problems with ineffective learning and training, resulting in lower sales work efficiency and lower customer satisfaction. The present invention aims to effectively improve salesperson skills by providing appropriate learning materials and training based on the performance and activity data of individual salespersons, and further adjusting the learning materials and training content in real time based on emotion recognition.

[0642] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for pre-processing the acquired data, means for clustering the pre-processed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, and means for adjusting the learning materials or training content in real time based on emotion recognition. This makes it possible to provide an optimized learning experience for each salesperson, thereby improving sales efficiency and customer satisfaction.

[0643] - "Salesperson performance data" is a general term for data recorded as performance, such as sales amounts, sales quantities, and customer evaluation scores achieved by salespersons in the past.

[0644] "Activity data" refers to data about the salesperson's daily work activities, including the number of customer contacts, training completion status, patrol frequency, and number of security camera checks.

[0645] "Preprocessing" refers to the process of removing unnecessary columns from raw data, standardizing the data, and preparing the data for analysis and clustering.

[0646] "Clustering" is an analytical technique for classifying data into multiple groups (clusters), and is used in the present invention to identify the strengths and weaknesses of salespeople.

[0647] "Cluster characteristics" refer to common characteristics of the data belonging to each cluster, including, for example, the average value and standard deviation of sales performance and customer service evaluation within each cluster.

[0648] "Learning Materials" refers to educational content, such as textbooks, videos, and online courses, provided to salespeople to improve their skills.

[0649] "Training Content" refers to the content of the training program in which salespeople learn specific skills, including on-the-job training and simulations.

[0650] "Emotion recognition" refers to technology that analyzes a user's facial expressions, voice, and physical movements to identify their emotional state at any given time (stress, tension, excitement, etc.).

[0651] "Real-time adjustment" refers to the process of instantly changing learning materials and training content based on the user's current state and performance.

[0652] MODE FOR CARRYING OUT THE INVENTION

[0653] The present invention combines an emotion recognition function with a system that proposes appropriate learning materials and training for each salesperson based on the salesperson's performance data and activity data. Specific embodiments for carrying out the present invention will be described below.

[0654] System Program

[0655] 1. Data Collection:

[0656] The server acquires salesperson performance and activity data, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, daily activity levels, etc.

[0657] 2. Data Preprocessing:

[0658] The server preprocesses the acquired data. During the preprocessing stage, unnecessary columns are removed and the data is scaled for standardization purposes, so that data of different scales can be treated on the same basis.

[0659] 3. Clustering:

[0660] Clustering is performed using the preprocessed data. Specifically, the KMeans algorithm is used to classify the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0661] 4. Feature analysis:

[0662] The server analyzes the characteristics of each cluster based on the clustering results, calculating the mean and standard deviation within each cluster and identifying which clusters have strengths and weaknesses in which areas.

[0663] 5. Learning Materials and Training Suggestions:

[0664] Depending on the analyzed characteristics, learning materials or training content suitable for a specific cluster are suggested. For example, customer service textbooks and videos are provided to a cluster with low customer service ratings, and closing skills training is provided to a cluster with low sales ability.

[0665] 6. Emotion recognition and real-time adjustment:

[0666] Using an emotion recognition engine, the server recognizes the emotions of salespeople during learning and training. For example, if a user is feeling stressed, the server will lower the difficulty of the content provided, and conversely, if the user is in a state of high excitement, it will add more challenging tasks.

[0667] Hardware / Software used

[0668] Hardware: Smart glasses (generic name), head-mounted display (generic name), cloud-based server (generic name).

[0669] Software: Python, Pandas, Scikit-Learn, Affectiva (emotion recognition system).

[0670] Specific examples

[0671] For example, say you have a salesperson ID1 with the following data:

[0672] Sales amount: 200

[0673] Customer Service Rating: 4.5

[0674] Training Completion Status: Completed

[0675] Activity Level: 50

[0676] The server preprocesses this data, standardizes the data of salespeople with similar data, and performs clustering. As a result, salesperson ID 1 is classified into cluster 0. The analysis shows that salespeople in cluster 0 have high customer service ratings, but average sales. In this case, the server suggests to the salespeople in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0677] Furthermore, if the emotion recognition engine detects the emotions of the salesperson (user), for example, if it detects that the salesperson is feeling high stress during training, the server will change the training content to a relatively easy one, thereby providing an environment in which the salesperson can learn effectively.

[0678] As an example of a specific prompt, you can enter the following:

[0679] "Adjust the next training content based on Security Guard A's latest emotional data. If his stress level is high, lower the difficulty."

[0680] "If high stress is detected during closing skills training for salesperson ID1, change the content to something simpler in real time."

[0681] In this way, the system effectively improves salespeople's skills by providing them with optimal learning materials and training content based on their individual data, and further adjusting the content in real time using emotion recognition.

[0682] Summary of the Invention

[0683] This system provides an optimal learning experience for each salesperson by proposing learning materials and training content based on the salesperson's performance and activity data and adjusting the content in real time based on emotion recognition, thereby improving sales efficiency and customer satisfaction.

[0684] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0685] Step 1:

[0686] The server retrieves salesperson performance and activity data from a database, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, and daily activity levels. The input is the raw data extracted from the database, and the output is a dataset for preprocessing.

[0687] Step 2:

[0688] The server preprocesses the acquired data. This preprocessing includes removing unnecessary columns, imputing missing values, and standardizing the data. For example, standardization converts each data item to the same scale. The input is the raw dataset, and the output is the preprocessed dataset.

[0689] Step 3:

[0690] The server performs clustering using the preprocessed dataset. Specifically, it applies the KMeans algorithm to classify the data into the set number of clusters. The input is the preprocessed dataset, and the output is a data label indicating which cluster each salesperson belongs to.

[0691] Step 4:

[0692] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales performance, customer service ratings, and activity levels within each cluster to identify cluster characteristics. The input is the clustered dataset, and the output is the average feature value of each cluster.

[0693] Step 5:

[0694] The server then proposes appropriate learning materials or training content for each salesperson based on the analyzed cluster characteristics. For example, if a particular cluster has a low customer service rating, it provides customer service texts or videos to the salespersons in that cluster. The input is the cluster characteristics and individual salesperson information, and the output is a list of suggested learning materials or training content for each salesperson.

[0695] Step 6:

[0696] The server uses an emotion recognition engine to receive real-time emotional data from users (salespeople) who are learning or undergoing training. For example, it analyzes emotional data collected while the user is undergoing training through smart glasses or a head-mounted display. The input is real-time emotional data, and the output is the user's emotional state (stress level, elation, etc.).

[0697] Step 7:

[0698] The server adjusts the learning materials or training content in real time based on the received emotional data. For example, if the user is feeling highly stressed, it will issue instructions to reduce the difficulty of the training content, and conversely, if the user is feeling excited, it will add more challenging tasks. The input is the user's emotional state, and the output is the adjusted learning materials or training content.

[0699] As a specific example, if salesperson ID1 feels high stress during closing skills training, the server adjusts the training to lower its difficulty based on data from the emotion recognition engine. An example of the prompt sentence in this case could be, "If high stress is detected during closing skills training for salesperson ID1, please change the content to something easier in real time."

[0700] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0701] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0702] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0703] [Third embodiment]

[0704] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0705] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0706] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0707] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0708] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0709] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0710] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0711] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0712] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0713] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0714] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0715] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0716] The present invention relates to a system for analyzing weak areas based on salesperson performance data and activity data, and proposing appropriate learning materials and training for each salesperson. This system performs the following processes.

[0717] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0718] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0719] The server then uses a clustering technique on the pre-processed data to classify the salespeople into clusters, such as using the KMeans algorithm, so that salespeople with similar characteristics are grouped together in the same cluster.

[0720] The server then analyzes the characteristics of each cluster based on the clustering results. For example, it calculates the average value and standard deviation of each cluster and identifies the areas in which the salesperson is strong or weak. This analysis clarifies the weak areas of each cluster.

[0721] The server then proposes learning materials or training content based on the analyzed characteristics. Specifically, it provides customer service textbooks and videos to clusters with low customer service ratings, and proposes closing skills training to clusters with low sales skills.

[0722] Finally, the server provides the suggested learning materials or training content to each salesperson. This information is displayed to each salesperson via their terminal. The salesperson can improve their skills by taking the suggested learning materials or training.

[0723] Examples:

[0724] For example, a salesperson with ID 1 has the following data:

[0725] Sales amount: 200

[0726] Customer Service Rating: 4.5

[0727] Training Completed: True

[0728] Activity Level: 50

[0729] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0730] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0731] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training contents based on the individual data of each salesperson.

[0732] The processing flow will be explained below.

[0733] Step 1:

[0734] A server retrieves salesperson performance and activity data, including each salesperson's sales volume, customer service ratings, training completion status, activity level, etc.

[0735] Step 2:

[0736] The server preprocesses the acquired data. First, it removes unnecessary columns from the dataset. Next, it uses StandardScaler to standardize the data, converting the values ​​of each column to the same scale. This unifies data with different scales into a consistent scale.

[0737] Step 3:

[0738] The server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into the specified number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0739] Step 4:

[0740] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0741] Step 5:

[0742] The server then proposes learning materials and training content for each cluster based on the analysis results. For example, if a particular cluster has a low customer service rating, it will provide customer service textbooks and videos to the salespeople in that cluster. On the other hand, it will propose training on closing techniques to clusters with low sales performance.

[0743] Step 6:

[0744] The server provides each salesperson with suggested learning materials and training content. The method of delivery is displayed to each salesperson via their terminal. The salesperson can then access the suggested learning materials and training content and receive the necessary training.

[0745] Step 7:

[0746] Salespeople (users) receive training according to the proposed learning materials and training content, which is expected to improve the skills and knowledge of salespeople and improve their individual sales performance.

[0747] Example 1

[0748] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0749] Conventional salesperson training systems have the problem of being unable to effectively utilize the performance and activity data of individual salespeople and propose optimal learning materials and training programs that address their weaknesses. As a result, the effectiveness of the training is limited, making it difficult to achieve overall improvement in the salesperson's abilities. In addition, the lack of individual guidance for each salesperson makes it difficult to take an effective approach.

[0750] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0751] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training contents according to the analyzed characteristics, means for providing the proposed learning materials or training contents to each salesperson, and means for displaying the proposed learning materials or training contents to the salesperson via a terminal. This makes it possible to propose optimal learning materials and training contents for each salesperson, thereby improving the overall ability of the salesperson.

[0752] "Salesperson performance data" refers to data on the results of sales activities, such as sales volume and sales amount achieved by the salesperson in the past, and evaluation scores from customers.

[0753] "Activity data" is information about the salesperson's daily activities, including the number of contacts with customers, training progress, activity level, and the like.

[0754] "Capture means" refers to the processes and techniques by which the system collects salesperson performance and activity data.

[0755] "Preprocessing means" refers to the processes and techniques used to remove unnecessary data and standardize data in order to format collected data in a way that makes it easier to analyze.

[0756] A "clustering method" is a process or technique for grouping data with similar characteristics based on preprocessed data, and specifically, the KMeans algorithm is used.

[0757] "Means of analysis" refers to the processes and techniques for analyzing the characteristics of each cluster classified by clustering and identifying weaknesses and strengths.

[0758] The "means for proposing learning materials or training content" refers to the process or technique for selecting and proposing optimal learning materials or training programs for each cluster or individual salesperson based on the analysis results.

[0759] The "means of delivery" refers to the process and technology used to deliver the proposed learning materials and training content to each salesperson.

[0760] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, used by a salesperson to display suggested learning materials or training content.

[0761] The present invention is a system that analyzes salesperson performance data and activity data and proposes appropriate learning materials and training for each salesperson. This system is implemented using the following hardware and software.

[0762] First, the server acquires salesperson performance data and activity data. To do this, the server collects the data using an application programming interface (API) from a CRM system, sales management tool, etc. For example, Salesforce is often used as a common CRM system.

[0763] Next, the data acquired by the server is preprocessed. In this process, unnecessary data is deleted and the Python pandas library and scikit-learn library are used to standardize the data. Standardization unifies the scale of the data and improves the accuracy of clustering.

[0764] The server then applies the KMeans algorithm to cluster the preprocessed data using Python's scikit-learn library, with the goal of classifying salespeople with similar characteristics into the same cluster.

[0765] Based on the clustering results, the server analyzes the characteristics of each cluster, calculating the mean and standard deviation of each cluster and identifying areas in which each cluster excels or fails. This analysis is also performed using Python's numpy and pandas libraries.

[0766] The server then uses the analysis results to recommend the most appropriate learning materials and training content for each cluster and salesperson. These can include various formats, such as text-based and video materials. For example, a cluster with poor customer service ratings might be provided with text or videos about customer service, while a cluster with poor sales skills might be offered training on closing skills.

[0767] Finally, the server provides each salesperson with suggested learning materials and training content, which is displayed to them via their device (e.g., computer, smartphone, tablet, etc.).

[0768] Specific examples

[0769] For example, a salesperson with ID 1 has the following data:

[0770] Sales amount: 200

[0771] Customer Service Rating: 4.5

[0772] Training Completed: True

[0773] Activity Level: 50

[0774] The server preprocesses this data, standardizes the data of other salespeople, and performs clustering. As a result, the salesperson with ID 1 is classified into cluster 0. The analysis shows that the characteristics of cluster 0 are that their customer service is highly rated, but their sales amount is average. In this case, the server makes a suggestion to cluster 0 saying, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0775] On the other hand, salesperson ID4 has the following data:

[0776] Sales amount: 400

[0777] Customer Service Rating: 5

[0778] Training Complete: False

[0779] Activity Level: 80

[0780] This salesperson is classified into cluster 1, and based on the characteristics of the cluster, the server suggests, "Customer service needs improvement. Provide customer service text and video."

[0781] Prompt Sentence Examples

[0782] "Please explain the specific processing steps and operation of a system that identifies weak areas of salespeople based on sales performance data and activity data, and suggests optimal learning materials and training content for each salesperson."

[0783] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by analyzing the data of individual salespeople and proposing optimal learning materials and training contents.

[0784] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0785] Step 1:

[0786] A server retrieves salesperson performance and activity data.

[0787] Inputs: Performance data (sales amount, evaluation score, etc.) and activity data (number of contacts, activity level, etc.) for each salesperson.

[0788] Specific operation: The server collects salesperson data from the sales system or CRM tool using APIs. For example, it reads data from the API endpoint of the CRM tool.

[0789] Output: A set of captured salesperson performance and activity data.

[0790] Step 2:

[0791] Preprocess the data retrieved by the server.

[0792] Input: A captured set of salesperson performance and activity data.

[0793] What it does: The server cleanses the dataset using Python's pandas library to remove unnecessary rows and columns, and standardizes the data using the StandardScaler library from scikit-learn.

[0794] Output: A cleansed and standardized dataset.

[0795] Step 3:

[0796] The server clusters the preprocessed data.

[0797] Input: Preprocessed salesperson dataset.

[0798] What it does: The server clusters the data using the KMeans algorithm from Python's scikit-learn library. After setting the K value, it applies a clustering method to group data points with similar characteristics.

[0799] Output: Cluster labels and cluster centers for each salesperson resulting from the clustering.

[0800] Step 4:

[0801] The server analyzes the clustering results.

[0802] Input: Cluster labels and cluster centers obtained as a result of clustering.

[0803] Specific operation: The server uses Python's numpy and pandas libraries to calculate the mean and standard deviation of each cluster to analyze the characteristics of each cluster, thereby clarifying the weaknesses and strengths of each cluster.

[0804] Output: Statistical data about the characteristics of each cluster (mean, standard deviation, etc.).

[0805] Step 5:

[0806] The server suggests learning materials and training content based on the analysis results.

[0807] Input: Statistical data about the characteristics of each cluster.

[0808] How it works: The server uses the generative AI model to select the optimal learning materials and training content for each cluster based on its weaknesses, for example, suggesting training on closing techniques or customer service texts and videos.

[0809] Output: Recommendations (list of training and educational materials) for each cluster or individual salesperson.

[0810] Step 6:

[0811] The server provides each salesperson with suggested learning materials and training content.

[0812] Input: A list of suggested learning materials and training content.

[0813] Specific Operation: The server distributes the proposed learning materials and training content to the salesperson via email or a learning management system (LMS).

[0814] Output: Delivered learning materials and training content.

[0815] Step 7:

[0816] The device displays the provided learning materials and training content to the user.

[0817] Input: Learning materials and training content delivered from the server.

[0818] Specific operation: The device (computer, smartphone, tablet) notifies and displays the learning materials and training content to the user. The user checks the learning materials and training information on the device and begins learning.

[0819] Output: The learning material or training content displayed to the user.

[0820] (Application example 1)

[0821] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0822] In conventional training proposal systems based on salesperson performance data and activity data, the proposed learning materials and training contents are not properly notified to salespersons, and progress management is insufficient, making it difficult to expect effective skill improvement. The present invention aims to solve this problem by notifying each salesperson and managing their progress, thereby improving the overall skills of salespersons.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0824] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, means for notifying each salesperson of the proposed learning materials or training content, and means for managing the progress of the notified learning materials or training content. This enables salespeople to receive the proposed learning materials or training content in a timely manner and effectively manage their progress.

[0825] "Salesperson" refers to an individual who sells products or services to customers in a brick-and-mortar store.

[0826] "Performance data" refers to data including sales figures and customer evaluation scores achieved by salespeople in the past.

[0827] "Activity data" refers to data including salesperson training completion status, number of customer contacts, and daily activity levels.

[0828] "Preprocessing" refers to processes such as removing unnecessary information from acquired data and standardizing the data.

[0829] "Clustering" refers to the process of grouping data with similar characteristics using algorithms such as the KMeans algorithm.

[0830] "Characteristic analysis" refers to analyzing the characteristics of each group formed as a result of clustering and identifying areas of strength and weakness.

[0831] "Learning materials" refers to educational resources such as textbooks and videos aimed at improving the skills of salespeople.

[0832] "Training content" refers to the specific content of the training program to improve sales staff skills.

[0833] "Means of notification" refers to the method by which each salesperson is informed of the proposed learning materials and training content.

[0834] "Progress management" refers to tracking how much of the suggested learning material or training content a salesperson has completed.

[0835] The present invention relates to a system for proposing learning materials and training contents based on performance data and activity data of salespeople, and further for notifying them and managing their progress. Specific embodiments of the system are described below.

[0836] Hardware and Software

[0837] The system's main hardware includes a smartphone and a server, and the software uses Python, Scikit-learn, and Firebase. The server plays a central role in data collection, preprocessing, clustering, and notification / progress management. Meanwhile, the smartphone acts as a terminal where salespeople input their data and receive notifications from the server.

[0838] Data collection and preprocessing

[0839] The server receives salesperson performance data (e.g., sales amount and customer evaluation score) and activity data (e.g., training completion status and number of contacts) sent from the smartphone. The server preprocesses this data using Python's Pandas library. This preprocessing includes removing unnecessary data and standardizing data items.

[0840] Clustering and feature analysis

[0841] The preprocessed data is clustered using Scikit-learn's KMeans algorithm, which classifies salespeople with similar characteristics into the same cluster. The server analyzes the characteristics of each cluster and calculates statistics such as the mean and standard deviation. This clarifies the strengths and weaknesses of each cluster.

[0842] Proposal of learning materials and training contents

[0843] Based on the analysis results, the server will suggest optimal learning materials and training content for each cluster. For example, it will provide customer service textbooks and videos to a cluster with low customer service ratings, and suggest closing skills training to a cluster with low sales ability.

[0844] Notifications and progress tracking

[0845] Salespeople are notified of suggested learning materials and training content through an application installed on their smartphones. This notification is made using Firebase's push notification function. Furthermore, the system also includes a progress management function to track how much of the learning material and training content a salesperson has completed. This allows salespeople to check their progress in real time and study more efficiently.

[0846] Examples and prompts

[0847] Salespeople use a smartphone app to input, for example, sales figures for the past month and customer ratings. The data is preprocessed on the server side, and based on the clustering results, a link to a video tutorial to improve "closing skills" is provided and a push notification is sent to the salesperson.

[0848] (Example of a prompt to input to a generative AI model):

[0849] Given a dataset of sales performance and activity data for salespeople, apply data preprocessing steps to clean and standardize the data. Use KMeans clustering to group the salespeople into clusters based on their performance metrics. Analyze the characteristics of each cluster and identify the areas where they need improvement. Suggest appropriate training materials and send push notifications to the salespeople via a mobile application.

[0850] In this way, salespeople can receive suggested educational materials and training content in a timely manner and their progress can be effectively managed.

[0851] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0852] Step 1:

[0853] The server acquires the salesperson's performance data and activity data from the smartphone. Performance data includes sales amount and customer evaluation score, and activity data includes training completion status and number of contacts. This data is entered and sent to the server.

[0854] Step 2:

[0855] The server preprocesses the acquired data. Specifically, it uses Python's Pandas library to clean the data, impute missing values, and remove unnecessary columns. It also standardizes the data and converts each data item to the same scale. This process improves the accuracy of clustering and analysis. The input is unprocessed raw data, and the output is clean, standardized data.

[0856] Step 3:

[0857] The server clusters the preprocessed data, using the KMeans algorithm from the Scikit-learn library to group salespeople with similar characteristics. The input is the preprocessed data, and the output is the cluster label assigned to each data point.

[0858] Step 4:

[0859] The server analyzes the characteristics of each cluster from the clustering results. For example, it calculates the mean and standard deviation for each cluster and identifies areas of strength and weakness. The input is data with cluster labels, and the output is statistical information for each cluster.

[0860] Step 5:

[0861] The server proposes learning materials and training content suitable for each cluster based on the analysis results. The proposed content is automatically generated based on the characteristics of each cluster. The input is statistical information for each cluster, and the output is a list of learning materials and training content for each cluster.

[0862] Step 6:

[0863] Suggested learning materials and training content are notified to each salesperson via a smartphone app. This notification is sent using Firebase's push notification function. The input is the suggestion content from the server, and the output is a notification displayed on the salesperson's device.

[0864] Step 7:

[0865] Salespeople use a smartphone app to work through learning materials and training content, and input their progress in real time. The server receives this progress data and manages it. The input is the user's progress data, and the output is updated progress information.

[0866] In this way, each salesperson can receive the suggested educational materials and training content in a timely manner and effectively manage their progress.

[0867] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0868] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. This system performs the following processes.

[0869] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[0870] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[0871] Next, the server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0872] The server then analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[0873] The server then proposes learning materials or training content according to the analyzed characteristics. Specifically, if a particular cluster has a low customer service rating, it provides customer service textbooks and videos to the salespeople in that cluster, and proposes closing skills training to the cluster with low sales ability.

[0874] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson during learning and training. Based on this, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling stressed, the server will provide them with content that is less difficult, and conversely, if they are in a state of high excitement, it will add more challenging tasks.

[0875] The server also evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data, making it possible to understand how effective the provided content was in improving the salesperson's skills.

[0876] Examples:

[0877] For example, a salesperson with ID 1 has the following data:

[0878] Sales amount: 200

[0879] Customer Service Rating: 4.5

[0880] Training Completed: True

[0881] Activity Level: 50

[0882] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[0883] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[0884] Furthermore, the emotion engine recognizes the emotions of the salesperson (user), and if it detects that the salesperson is feeling nervous or stressed during the training, the server adjusts the difficulty level to allow the user to study in a relaxed state. For example, if salesperson ID1 feels high stress during training on closing techniques, the emotion engine will detect this and the server will change the training content to a relatively easy one. This provides an environment in which the salesperson can study effectively.

[0885] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training content based on each salesperson's individual data and further adjusting the content in real time using an emotion engine.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The server acquires salesperson performance data and activity data, including sales amounts, customer service ratings, training completion status, activity levels, etc. This data is collected from a database or the like.

[0889] Step 2:

[0890] The server preprocesses the acquired data. Specifically, it removes unnecessary columns and standardizes the values ​​of each column using StandardScaler. This standardization unifies data with different scales into a consistent scale.

[0891] Step 3:

[0892] The server performs clustering using the preprocessed data, dividing the data into multiple clusters using the KMeans algorithm, and adding information to the original data about which cluster each salesperson belongs to.

[0893] Step 4:

[0894] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales, customer service evaluation, and activity level within each cluster to clarify the characteristics of each cluster. This analysis identifies the areas in which each cluster has strengths and weaknesses.

[0895] Step 5:

[0896] The server then proposes learning materials and training content for each cluster based on the analysis results. For clusters with low customer service ratings, it provides customer service textbooks and videos, and for clusters with low sales ability, it proposes training on closing techniques.

[0897] Step 6:

[0898] The server provides the salespeople with the learning materials and training content proposed for each cluster. The appropriate learning materials and training content are displayed to each salesperson via their terminal. The salesperson accesses these and receives the training.

[0899] Step 7:

[0900] The emotion engine recognizes the emotions of the salesperson user in real time during training. Emotion data is collected using facial recognition and biometric sensors, for example.

[0901] Step 8:

[0902] Based on the emotional data collected by the emotion engine, the server adjusts the learning materials and training content in real time. For example, if a salesperson is feeling stressed, it will provide them with less difficult content, and conversely, if they are highly excited, it will provide them with more challenging tasks.

[0903] Step 9:

[0904] The server evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data. By comparing the emotional data with the learning outcomes, the server analyzes the extent to which the provided content contributed to improving the salesperson's skills.

[0905] Step 10:

[0906] Salespeople (users) receive training according to the suggested learning materials and training content. By providing adjusted learning materials and training in real time via their devices, they can efficiently learn and improve their skills. This process continues, and data is updated regularly to ensure that optimal training is always provided.

[0907] Example 2

[0908] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0909] There is a need to effectively utilize salesperson performance and activity data, accurately analyze each salesperson's strengths and weaknesses, and then propose appropriate learning materials and training content.However, conventional systems have not been able to fully provide learning materials and training content optimized for each salesperson, and they do not make adjustments based on real-time emotional data, so there are limitations to improving the overall capabilities of salespersons.

[0910] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0911] In this invention, the server includes means for acquiring salesperson performance data and activity data, means for preprocessing the acquired data, and means for clustering the preprocessed data. This enables accurate clustering based on the data of individual salespersons. It also includes means for analyzing the characteristics of each cluster based on the clustering results and means for proposing learning materials or training content based on the analyzed characteristics, and means for providing the proposed learning materials or training content to each salesperson. It also includes means for recognizing the emotions of the salesperson during the learning or training, means for adjusting the learning materials or training content in real time based on the recognized emotions, and means for evaluating the effectiveness of the proposed learning materials or training content. This enables accurate analysis and individualized learning based on the salesperson's performance data and activity data, and further enables the salesperson's overall ability to be improved by adjusting the learning content in real time using emotional data.

[0912] "Salesperson performance data" refers to data that indicates the results of sales activities that a salesperson has conducted in the past, and specifically includes the quantity of products sold, the sales amount, and evaluation scores from customers.

[0913] "Activity data" refers to data relating to the salesperson's daily work activities, including, for example, the number of customer contacts, training completion status, and daily activity level.

[0914] "Means of acquisition" refers to the means for collecting the target data, and includes methods such as API calls and database queries.

[0915] "Preprocessing means" refers to means for converting collected raw data into an analyzable format, and specifically includes removing unnecessary columns and standardizing data.

[0916] The "clustering means" refers to a means for dividing collected and preprocessed data into groups based on specific criteria, and specifically includes the KMeans algorithm.

[0917] "Means for analyzing the characteristics of clusters" refers to means for clarifying the characteristics of each cluster based on the results of clustering, and specifically includes methods for calculating the mean value and standard deviation.

[0918] The "means for proposing learning materials or training contents" refers to a means for selecting and proposing the most suitable learning materials or training contents for each cluster based on the characteristics of the analyzed cluster.

[0919] The "means of provision" refers to the means for delivering or notifying each salesperson of the proposed learning materials and training content.

[0920] "Emotion recognition means" refers to means for detecting the emotions felt by salespeople in real time during learning and training, and specifically includes biofeedback devices and emotion recognition software.

[0921] "Means for real-time adjustment" refers to means for changing the difficulty level and content of learning materials and training content on the fly based on recognized emotional data.

[0922] "Means for evaluating effectiveness" are means for measuring the extent to which the proposed learning materials and training content have contributed to improving the skills of sales staff.

[0923] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. The program of this system will be described in detail below.

[0924] First, the server acquires the salesperson's performance data and activity data. This performance data includes the number of products sold, sales amount, and customer evaluation scores, while activity data includes the number of customer contacts, training completion status, daily activity level, etc. Data collection is performed using a database management system (e.g., MySQL or PostgreSQL) and an API communication tool (e.g., REST API).

[0925] Next, the server preprocesses the acquired data by removing unnecessary columns and standardizing each data item to the same scale. Data processing frameworks such as Pandas and NumPy are used for data processing.

[0926] The server then performs clustering on the preprocessed data. Specifically, it uses Scikit-learn's KMeans algorithm to divide the data into a specific number of clusters. During this process, information about which cluster each salesperson belongs to is added to the original data.

[0927] Next, the server analyzes the characteristics of each cluster based on the clustering results. Specifically, it calculates the mean and standard deviation of each cluster and clarifies characteristics such as sales performance and customer service evaluation for each cluster. This process uses statistical analysis tools (e.g., Pandas).

[0928] The server then suggests optimal learning materials and training content for each cluster based on the cluster's characteristics. For example, it provides customer service textbooks and videos to a cluster with low customer service ratings, and suggests training on closing skills to a cluster with low sales ability. Notifications of the suggestions are sent via email or notification systems (e.g., SMTP or SNS).

[0929] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson users in real time during learning and training. Based on this data, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling high stress, the difficulty level can be lowered, and conversely, if the salesperson is in a high state of excitement, more challenging tasks can be added. Emotion recognition is achieved using biofeedback devices and emotion recognition software (e.g., Affectiva).

[0930] Finally, the server evaluates the effectiveness of the proposed learning materials and training content, which involves comparing performance data and emotion data after training to evaluate the learning effect.

[0931] As a concrete example, suppose the performance data for a salesperson with ID 1 is as follows:

[0932] Sales amount: 200

[0933] Customer Service Rating: 4.5

[0934] Training Completed: True

[0935] Activity Level: 50

[0936] The server preprocesses this data and clusters it with other salespeople who belong to the same cluster. As a result, salesperson ID1 is classified into cluster 0. Cluster 0 has a high reputation for customer service but average sales. In this case, the server suggests to the salesperson in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques." If salesperson ID1 feels high stress during the training, the emotion engine detects this and the server adjusts the training content to be easier.

[0937] In this way, the system of the present invention provides optimal learning materials and training content based on salesperson performance data and activity data, and further makes adjustments based on real-time emotion recognition, thereby comprehensively supporting the improvement of salesperson skills.

[0938] Example prompt sentence:

[0939] "What are the data entries for Salesperson ID 1, with sales of 200 and a customer service rating of 4.5?"

[0940] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0941] Step 1: Collect data

[0942] A server retrieves salesperson performance and activity data.

[0943] Input: Salesperson performance and activity data from a database or API

[0944] Specific operation: The server executes an API call to retrieve salesperson information from the database, including sales volume, sales amount, customer evaluation score, number of customer contacts, training completion status, and daily activity level.

[0945] Output: raw data collected

[0946] Step 2: Preprocessing the data

[0947] The server preprocesses the collected data.

[0948] Input: Raw data

[0949] Specific operation: The server uses the Pandas library to remove unnecessary columns from the raw data, standardize each data item to the same scale, and impute missing values ​​appropriately.

[0950] Output: Preprocessed data

[0951] Step 3: Clustering

[0952] The server performs clustering using the preprocessed data.

[0953] Input: Preprocessed data

[0954] Specific operation: The server uses Scikit-learn's KMeans algorithm to divide the data into the number of clusters. The number of clusters is based on the parameters set in advance. Information about which cluster each salesperson belongs to is added to the original data.

[0955] Output: Clustering results (data with cluster information for each salesperson added)

[0956] Step 4: Feature Analysis

[0957] The server analyzes the characteristics of each cluster based on the clustering results.

[0958] Input: Clustering results

[0959] Specific operation: The server uses Pandas to calculate the mean and standard deviation of each cluster, clarifying the characteristics of each cluster. This identifies the areas in which each cluster has strengths and weaknesses.

[0960] Output: Feature data for each cluster

[0961] Step 5: Proposing learning materials and training content

[0962] The server proposes the most suitable learning materials and training content for each cluster based on the characteristics of the cluster.

[0963] Input: Cluster feature data

[0964] Specific operation: The server considers the characteristics of each cluster, for example, providing customer service texts and videos for a cluster with low customer service ratings, and suggesting closing skills training for a cluster with low sales ability. This information is added to the suggestion list.

[0965] Output: A list of suggested learning materials and training content

[0966] Step 6: Real-time adjustments with the emotion engine

[0967] The emotion engine collects emotional data from salespeople, and the server uses this data to adjust learning materials and training content in real time.

[0968] Input: Emotion data during learning or training

[0969] How it works: The emotion engine recognizes the salesperson's emotions, such as stress and concentration, in real time, and the server analyzes the data. For example, if the salesperson is highly stressed, the difficulty level is reduced, and if the salesperson is highly excited, more challenging tasks are added.

[0970] Output: Tailored learning materials and training content

[0971] Step 7: Evaluate the effect

[0972] The server evaluates the effectiveness of the proposed learning materials and training contents.

[0973] Input: Performance data and emotional data after implementing learning materials and training content

[0974] Specific operation: The server compares performance data before and after learning or training, and evaluates the learning effectiveness by taking into account emotional data. This allows the server to understand how effective the proposed training content was in improving the salesperson's skills. Feedback is reflected in the next proposal.

[0975] Output: Evaluation results of learning effect

[0976] The above is a series of specific processing steps for the program of this system.

[0977] (Application example 2)

[0978] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0979] Conventional salesperson skill improvement systems have difficulty reflecting individual salesperson weaknesses and learning progress in real time. Furthermore, they have had problems with ineffective learning and training, resulting in lower sales work efficiency and lower customer satisfaction. The present invention aims to effectively improve salesperson skills by providing appropriate learning materials and training based on the performance and activity data of individual salespersons, and further adjusting the learning materials and training content in real time based on emotion recognition.

[0980] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for pre-processing the acquired data, means for clustering the pre-processed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, and means for adjusting the learning materials or training content in real time based on emotion recognition. This makes it possible to provide an optimized learning experience for each salesperson, thereby improving sales efficiency and customer satisfaction.

[0981] - "Salesperson performance data" is a general term for data recorded as performance, such as sales amounts, sales quantities, and customer evaluation scores achieved by salespersons in the past.

[0982] "Activity data" refers to data about the salesperson's daily work activities, including the number of customer contacts, training completion status, patrol frequency, and number of security camera checks.

[0983] "Preprocessing" refers to the process of removing unnecessary columns from raw data, standardizing the data, and preparing the data for analysis and clustering.

[0984] "Clustering" is an analytical technique for classifying data into multiple groups (clusters), and is used in the present invention to identify the strengths and weaknesses of salespeople.

[0985] "Cluster characteristics" refer to common characteristics of the data belonging to each cluster, including, for example, the average value and standard deviation of sales performance and customer service evaluation within each cluster.

[0986] "Learning Materials" refers to educational content, such as textbooks, videos, and online courses, provided to salespeople to improve their skills.

[0987] "Training Content" refers to the content of the training program in which salespeople learn specific skills, including on-the-job training and simulations.

[0988] "Emotion recognition" refers to technology that analyzes a user's facial expressions, voice, and physical movements to identify their emotional state at any given time (stress, tension, excitement, etc.).

[0989] "Real-time adjustment" refers to the process of instantly changing learning materials and training content based on the user's current state and performance.

[0990] MODE FOR CARRYING OUT THE INVENTION

[0991] The present invention combines an emotion recognition function with a system that proposes appropriate learning materials and training for each salesperson based on the salesperson's performance data and activity data. Specific embodiments for carrying out the present invention will be described below.

[0992] System Program

[0993] 1. Data Collection:

[0994] The server acquires salesperson performance and activity data, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, daily activity levels, etc.

[0995] 2. Data Preprocessing:

[0996] The server preprocesses the acquired data. During the preprocessing stage, unnecessary columns are removed and the data is scaled for standardization purposes, so that data of different scales can be treated on the same basis.

[0997] 3. Clustering:

[0998] Clustering is performed using the preprocessed data. Specifically, the KMeans algorithm is used to classify the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[0999] 4. Feature analysis:

[1000] The server analyzes the characteristics of each cluster based on the clustering results, calculating the mean and standard deviation within each cluster and identifying which clusters have strengths and weaknesses in which areas.

[1001] 5. Learning Materials and Training Suggestions:

[1002] Depending on the analyzed characteristics, learning materials or training content suitable for a specific cluster are suggested. For example, customer service textbooks and videos are provided to a cluster with low customer service ratings, and closing skills training is provided to a cluster with low sales ability.

[1003] 6. Emotion recognition and real-time adjustment:

[1004] Using an emotion recognition engine, the server recognizes the emotions of salespeople during learning and training. For example, if a user is feeling stressed, the server will lower the difficulty of the content provided, and conversely, if the user is in a state of high excitement, it will add more challenging tasks.

[1005] Hardware / Software used

[1006] Hardware: Smart glasses (generic name), head-mounted display (generic name), cloud-based server (generic name).

[1007] Software: Python, Pandas, Scikit-Learn, Affectiva (emotion recognition system).

[1008] Specific examples

[1009] For example, say you have a salesperson ID1 with the following data:

[1010] Sales amount: 200

[1011] Customer Service Rating: 4.5

[1012] Training Completion Status: Completed

[1013] Activity Level: 50

[1014] The server preprocesses this data, standardizes the data of salespeople with similar data, and performs clustering. As a result, salesperson ID 1 is classified into cluster 0. The analysis shows that salespeople in cluster 0 have high customer service ratings, but average sales. In this case, the server suggests to the salespeople in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[1015] Furthermore, if the emotion recognition engine detects the emotions of the salesperson (user), for example, if it detects that the salesperson is feeling high stress during training, the server will change the training content to a relatively easy one, thereby providing an environment in which the salesperson can learn effectively.

[1016] As an example of a specific prompt, you can enter the following:

[1017] "Adjust the next training content based on Security Guard A's latest emotional data. If his stress level is high, lower the difficulty."

[1018] "If high stress is detected during closing skills training for salesperson ID1, change the content to something simpler in real time."

[1019] In this way, the system effectively improves salespeople's skills by providing them with optimal learning materials and training content based on their individual data, and further adjusting the content in real time using emotion recognition.

[1020] Summary of the Invention

[1021] This system provides an optimal learning experience for each salesperson by proposing learning materials and training content based on the salesperson's performance and activity data and adjusting the content in real time based on emotion recognition, thereby improving sales efficiency and customer satisfaction.

[1022] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1023] Step 1:

[1024] The server retrieves salesperson performance and activity data from a database, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, and daily activity levels. The input is the raw data extracted from the database, and the output is a dataset for preprocessing.

[1025] Step 2:

[1026] The server preprocesses the acquired data. This preprocessing includes removing unnecessary columns, imputing missing values, and standardizing the data. For example, standardization converts each data item to the same scale. The input is the raw dataset, and the output is the preprocessed dataset.

[1027] Step 3:

[1028] The server performs clustering using the preprocessed dataset. Specifically, it applies the KMeans algorithm to classify the data into the set number of clusters. The input is the preprocessed dataset, and the output is a data label indicating which cluster each salesperson belongs to.

[1029] Step 4:

[1030] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales performance, customer service ratings, and activity levels within each cluster to identify cluster characteristics. The input is the clustered dataset, and the output is the average feature value of each cluster.

[1031] Step 5:

[1032] The server then proposes appropriate learning materials or training content for each salesperson based on the analyzed cluster characteristics. For example, if a particular cluster has a low customer service rating, it provides customer service texts or videos to the salespersons in that cluster. The input is the cluster characteristics and individual salesperson information, and the output is a list of suggested learning materials or training content for each salesperson.

[1033] Step 6:

[1034] The server uses an emotion recognition engine to receive real-time emotional data from users (salespeople) who are learning or undergoing training. For example, it analyzes emotional data collected while the user is undergoing training through smart glasses or a head-mounted display. The input is real-time emotional data, and the output is the user's emotional state (stress level, elation, etc.).

[1035] Step 7:

[1036] The server adjusts the learning materials or training content in real time based on the received emotional data. For example, if the user is feeling highly stressed, it will issue instructions to reduce the difficulty of the training content, and conversely, if the user is feeling excited, it will add more challenging tasks. The input is the user's emotional state, and the output is the adjusted learning materials or training content.

[1037] As a specific example, if salesperson ID1 feels high stress during closing skills training, the server adjusts the training to lower its difficulty based on data from the emotion recognition engine. An example of the prompt sentence in this case could be, "If high stress is detected during closing skills training for salesperson ID1, please change the content to something easier in real time."

[1038] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1039] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1040] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1041] [Fourth embodiment]

[1042] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1043] 7, a 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.

[1044] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1045] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1046] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1047] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1048] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1049] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1050] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1051] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1052] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1053] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1054] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1055] The present invention relates to a system for analyzing weak areas based on salesperson performance data and activity data, and proposing appropriate learning materials and training for each salesperson. This system performs the following processes.

[1056] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[1057] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[1058] The server then uses a clustering technique on the pre-processed data to classify the salespeople into clusters, such as using the KMeans algorithm, so that salespeople with similar characteristics are grouped together in the same cluster.

[1059] The server then analyzes the characteristics of each cluster based on the clustering results. For example, it calculates the average value and standard deviation of each cluster and identifies the areas in which the salesperson is strong or weak. This analysis clarifies the weak areas of each cluster.

[1060] The server then proposes learning materials or training content based on the analyzed characteristics. Specifically, it provides customer service textbooks and videos to clusters with low customer service ratings, and proposes closing skills training to clusters with low sales skills.

[1061] Finally, the server provides the suggested learning materials or training content to each salesperson. This information is displayed to each salesperson via their terminal. The salesperson can improve their skills by taking the suggested learning materials or training.

[1062] Examples:

[1063] For example, a salesperson with ID 1 has the following data:

[1064] Sales amount: 200

[1065] Customer Service Rating: 4.5

[1066] Training Completed: True

[1067] Activity Level: 50

[1068] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[1069] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[1070] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training contents based on the individual data of each salesperson.

[1071] The processing flow will be explained below.

[1072] Step 1:

[1073] A server retrieves salesperson performance and activity data, including each salesperson's sales volume, customer service ratings, training completion status, activity level, etc.

[1074] Step 2:

[1075] The server preprocesses the acquired data. First, it removes unnecessary columns from the dataset. Next, it uses StandardScaler to standardize the data, converting the values ​​of each column to the same scale. This unifies data with different scales into a consistent scale.

[1076] Step 3:

[1077] The server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into the specified number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[1078] Step 4:

[1079] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[1080] Step 5:

[1081] The server then proposes learning materials and training content for each cluster based on the analysis results. For example, if a particular cluster has a low customer service rating, it will provide customer service textbooks and videos to the salespeople in that cluster. On the other hand, it will propose training on closing techniques to clusters with low sales performance.

[1082] Step 6:

[1083] The server provides each salesperson with suggested learning materials and training content. The method of delivery is displayed to each salesperson via their terminal. The salesperson can then access the suggested learning materials and training content and receive the necessary training.

[1084] Step 7:

[1085] Salespeople (users) receive training according to the proposed learning materials and training content, which is expected to improve the skills and knowledge of salespeople and improve their individual sales performance.

[1086] Example 1

[1087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1088] Conventional salesperson training systems have the problem of being unable to effectively utilize the performance and activity data of individual salespeople and propose optimal learning materials and training programs that address their weaknesses. As a result, the effectiveness of the training is limited, making it difficult to achieve overall improvement in the salesperson's abilities. In addition, the lack of individual guidance for each salesperson makes it difficult to take an effective approach.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1090] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training contents according to the analyzed characteristics, means for providing the proposed learning materials or training contents to each salesperson, and means for displaying the proposed learning materials or training contents to the salesperson via a terminal. This makes it possible to propose optimal learning materials and training contents for each salesperson, thereby improving the overall ability of the salesperson.

[1091] "Salesperson performance data" refers to data on the results of sales activities, such as sales volume and sales amount achieved by the salesperson in the past, and evaluation scores from customers.

[1092] "Activity data" is information about the salesperson's daily activities, including the number of contacts with customers, training progress, activity level, and the like.

[1093] "Capture means" refers to the processes and techniques by which the system collects salesperson performance and activity data.

[1094] "Preprocessing means" refers to the processes and techniques used to remove unnecessary data and standardize data in order to format collected data in a way that makes it easier to analyze.

[1095] A "clustering method" is a process or technique for grouping data with similar characteristics based on preprocessed data, and specifically, the KMeans algorithm is used.

[1096] "Means of analysis" refers to the processes and techniques for analyzing the characteristics of each cluster classified by clustering and identifying weaknesses and strengths.

[1097] The "means for proposing learning materials or training content" refers to the process or technique for selecting and proposing optimal learning materials or training programs for each cluster or individual salesperson based on the analysis results.

[1098] The "means of delivery" refers to the process and technology used to deliver the proposed learning materials and training content to each salesperson.

[1099] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, used by a salesperson to display suggested learning materials or training content.

[1100] The present invention is a system that analyzes salesperson performance data and activity data and proposes appropriate learning materials and training for each salesperson. This system is implemented using the following hardware and software.

[1101] First, the server acquires salesperson performance data and activity data. To do this, the server collects the data using an application programming interface (API) from a CRM system, sales management tool, etc. For example, Salesforce is often used as a common CRM system.

[1102] Next, the data acquired by the server is preprocessed. In this process, unnecessary data is deleted and the Python pandas library and scikit-learn library are used to standardize the data. Standardization unifies the scale of the data and improves the accuracy of clustering.

[1103] The server then applies the KMeans algorithm to cluster the preprocessed data using Python's scikit-learn library, with the goal of classifying salespeople with similar characteristics into the same cluster.

[1104] Based on the clustering results, the server analyzes the characteristics of each cluster, calculating the mean and standard deviation of each cluster and identifying areas in which each cluster excels or fails. This analysis is also performed using Python's numpy and pandas libraries.

[1105] The server then uses the analysis results to recommend the most appropriate learning materials and training content for each cluster and salesperson. These can include various formats, such as text-based and video materials. For example, a cluster with poor customer service ratings might be provided with text or videos about customer service, while a cluster with poor sales skills might be offered training on closing skills.

[1106] Finally, the server provides each salesperson with suggested learning materials and training content, which is displayed to them via their device (e.g., computer, smartphone, tablet, etc.).

[1107] Specific examples

[1108] For example, a salesperson with ID 1 has the following data:

[1109] Sales amount: 200

[1110] Customer Service Rating: 4.5

[1111] Training Completed: True

[1112] Activity Level: 50

[1113] The server preprocesses this data, standardizes the data of other salespeople, and performs clustering. As a result, the salesperson with ID 1 is classified into cluster 0. The analysis shows that the characteristics of cluster 0 are that their customer service is highly rated, but their sales amount is average. In this case, the server makes a suggestion to cluster 0 saying, "You need to improve your sales skills. We will provide you with training on closing techniques."

[1114] On the other hand, salesperson ID4 has the following data:

[1115] Sales amount: 400

[1116] Customer Service Rating: 5

[1117] Training Complete: False

[1118] Activity Level: 80

[1119] This salesperson is classified into cluster 1, and based on the characteristics of the cluster, the server suggests, "Customer service needs improvement. Provide customer service text and video."

[1120] Prompt Sentence Examples

[1121] "Please explain the specific processing steps and operation of a system that identifies weak areas of salespeople based on sales performance data and activity data, and suggests optimal learning materials and training content for each salesperson."

[1122] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by analyzing the data of individual salespeople and proposing optimal learning materials and training contents.

[1123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1124] Step 1:

[1125] A server retrieves salesperson performance and activity data.

[1126] Inputs: Performance data (sales amount, evaluation score, etc.) and activity data (number of contacts, activity level, etc.) for each salesperson.

[1127] Specific operation: The server collects salesperson data from the sales system or CRM tool using APIs. For example, it reads data from the API endpoint of the CRM tool.

[1128] Output: A set of captured salesperson performance and activity data.

[1129] Step 2:

[1130] Preprocess the data retrieved by the server.

[1131] Input: A captured set of salesperson performance and activity data.

[1132] What it does: The server cleanses the dataset using Python's pandas library to remove unnecessary rows and columns, and standardizes the data using the StandardScaler library from scikit-learn.

[1133] Output: A cleansed and standardized dataset.

[1134] Step 3:

[1135] The server clusters the preprocessed data.

[1136] Input: Preprocessed salesperson dataset.

[1137] What it does: The server clusters the data using the KMeans algorithm from Python's scikit-learn library. After setting the K value, it applies a clustering method to group data points with similar characteristics.

[1138] Output: Cluster labels and cluster centers for each salesperson resulting from the clustering.

[1139] Step 4:

[1140] The server analyzes the clustering results.

[1141] Input: Cluster labels and cluster centers obtained as a result of clustering.

[1142] Specific operation: The server uses Python's numpy and pandas libraries to calculate the mean and standard deviation of each cluster to analyze the characteristics of each cluster, thereby clarifying the weaknesses and strengths of each cluster.

[1143] Output: Statistical data about the characteristics of each cluster (mean, standard deviation, etc.).

[1144] Step 5:

[1145] The server suggests learning materials and training content based on the analysis results.

[1146] Input: Statistical data about the characteristics of each cluster.

[1147] How it works: The server uses the generative AI model to select the optimal learning materials and training content for each cluster based on its weaknesses, for example, suggesting training on closing techniques or customer service texts and videos.

[1148] Output: Recommendations (list of training and educational materials) for each cluster or individual salesperson.

[1149] Step 6:

[1150] The server provides each salesperson with suggested learning materials and training content.

[1151] Input: A list of suggested learning materials and training content.

[1152] Specific Operation: The server distributes the proposed learning materials and training content to the salesperson via email or a learning management system (LMS).

[1153] Output: Delivered learning materials and training content.

[1154] Step 7:

[1155] The device displays the provided learning materials and training content to the user.

[1156] Input: Learning materials and training content delivered from the server.

[1157] Specific operation: The device (computer, smartphone, tablet) notifies and displays the learning materials and training content to the user. The user checks the learning materials and training information on the device and begins learning.

[1158] Output: The learning material or training content displayed to the user.

[1159] (Application example 1)

[1160] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1161] In conventional training proposal systems based on salesperson performance data and activity data, the proposed learning materials and training contents are not properly notified to salespersons, and progress management is insufficient, making it difficult to expect effective skill improvement. The present invention aims to solve this problem by notifying each salesperson and managing their progress, thereby improving the overall skills of salespersons.

[1162] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1163] In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for preprocessing the acquired data, means for clustering the preprocessed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, means for notifying each salesperson of the proposed learning materials or training content, and means for managing the progress of the notified learning materials or training content. This enables salespeople to receive the proposed learning materials or training content in a timely manner and effectively manage their progress.

[1164] "Salesperson" refers to an individual who sells products or services to customers in a brick-and-mortar store.

[1165] "Performance data" refers to data including sales figures and customer evaluation scores achieved by salespeople in the past.

[1166] "Activity data" refers to data including salesperson training completion status, number of customer contacts, and daily activity levels.

[1167] "Preprocessing" refers to processes such as removing unnecessary information from acquired data and standardizing the data.

[1168] "Clustering" refers to the process of grouping data with similar characteristics using algorithms such as the KMeans algorithm.

[1169] "Characteristic analysis" refers to analyzing the characteristics of each group formed as a result of clustering and identifying areas of strength and weakness.

[1170] "Learning materials" refers to educational resources such as textbooks and videos aimed at improving the skills of salespeople.

[1171] "Training content" refers to the specific content of the training program to improve sales staff skills.

[1172] "Means of notification" refers to the method by which each salesperson is informed of the proposed learning materials and training content.

[1173] "Progress management" refers to tracking how much of the suggested learning material or training content a salesperson has completed.

[1174] The present invention relates to a system for proposing learning materials and training contents based on performance data and activity data of salespeople, and further for notifying them and managing their progress. Specific embodiments of the system are described below.

[1175] Hardware and Software

[1176] The system's main hardware includes a smartphone and a server, and the software uses Python, Scikit-learn, and Firebase. The server plays a central role in data collection, preprocessing, clustering, and notification / progress management. Meanwhile, the smartphone acts as a terminal where salespeople input their data and receive notifications from the server.

[1177] Data collection and preprocessing

[1178] The server receives salesperson performance data (e.g., sales amount and customer evaluation score) and activity data (e.g., training completion status and number of contacts) sent from the smartphone. The server preprocesses this data using Python's Pandas library. This preprocessing includes removing unnecessary data and standardizing data items.

[1179] Clustering and feature analysis

[1180] The preprocessed data is clustered using Scikit-learn's KMeans algorithm, which classifies salespeople with similar characteristics into the same cluster. The server analyzes the characteristics of each cluster and calculates statistics such as the mean and standard deviation. This clarifies the strengths and weaknesses of each cluster.

[1181] Proposal of learning materials and training contents

[1182] Based on the analysis results, the server will suggest optimal learning materials and training content for each cluster. For example, it will provide customer service textbooks and videos to a cluster with low customer service ratings, and suggest closing skills training to a cluster with low sales ability.

[1183] Notifications and progress tracking

[1184] Salespeople are notified of suggested learning materials and training content through an application installed on their smartphones. This notification is made using Firebase's push notification function. Furthermore, the system also includes a progress management function to track how much of the learning material and training content a salesperson has completed. This allows salespeople to check their progress in real time and study more efficiently.

[1185] Examples and prompts

[1186] Salespeople use a smartphone app to input, for example, sales figures for the past month and customer ratings. The data is preprocessed on the server side, and based on the clustering results, a link to a video tutorial to improve "closing skills" is provided and a push notification is sent to the salesperson.

[1187] (Example of a prompt to input to a generative AI model):

[1188] Given a dataset of sales performance and activity data for salespeople, apply data preprocessing steps to clean and standardize the data. Use KMeans clustering to group the salespeople into clusters based on their performance metrics. Analyze the characteristics of each cluster and identify the areas where they need improvement. Suggest appropriate training materials and send push notifications to the salespeople via a mobile application.

[1189] In this way, salespeople can receive suggested educational materials and training content in a timely manner and their progress can be effectively managed.

[1190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1191] Step 1:

[1192] The server acquires the salesperson's performance data and activity data from the smartphone. Performance data includes sales amount and customer evaluation score, and activity data includes training completion status and number of contacts. This data is entered and sent to the server.

[1193] Step 2:

[1194] The server preprocesses the acquired data. Specifically, it uses Python's Pandas library to clean the data, impute missing values, and remove unnecessary columns. It also standardizes the data and converts each data item to the same scale. This process improves the accuracy of clustering and analysis. The input is unprocessed raw data, and the output is clean, standardized data.

[1195] Step 3:

[1196] The server clusters the preprocessed data, using the KMeans algorithm from the Scikit-learn library to group salespeople with similar characteristics. The input is the preprocessed data, and the output is the cluster label assigned to each data point.

[1197] Step 4:

[1198] The server analyzes the characteristics of each cluster from the clustering results. For example, it calculates the mean and standard deviation for each cluster and identifies areas of strength and weakness. The input is data with cluster labels, and the output is statistical information for each cluster.

[1199] Step 5:

[1200] The server proposes learning materials and training content suitable for each cluster based on the analysis results. The proposed content is automatically generated based on the characteristics of each cluster. The input is statistical information for each cluster, and the output is a list of learning materials and training content for each cluster.

[1201] Step 6:

[1202] Suggested learning materials and training content are notified to each salesperson via a smartphone app. This notification is sent using Firebase's push notification function. The input is the suggestion content from the server, and the output is a notification displayed on the salesperson's device.

[1203] Step 7:

[1204] Salespeople use a smartphone app to work through learning materials and training content, and input their progress in real time. The server receives this progress data and manages it. The input is the user's progress data, and the output is updated progress information.

[1205] In this way, each salesperson can receive the suggested educational materials and training content in a timely manner and effectively manage their progress.

[1206] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1207] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. This system performs the following processes.

[1208] First, the server acquires the salesperson's performance data and activity data. Performance data includes the number of products sold, sales amount, customer evaluation scores, etc. Activity data includes the number of customer contacts, training completion status, daily activity level, etc.

[1209] The server then preprocesses the acquired data, which includes removing unnecessary columns and standardizing the data, converting each data item to the same scale, resulting in more accurate clustering results.

[1210] Next, the server performs clustering using the preprocessed data. Specifically, it uses the KMeans algorithm to divide the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[1211] The server then analyzes the characteristics of each cluster based on the clustering results. It calculates the average value and standard deviation within each cluster and clarifies the characteristics of each cluster, such as sales performance and customer service evaluation. Based on these results, it identifies the areas in which each cluster has strengths and weaknesses.

[1212] The server then proposes learning materials or training content according to the analyzed characteristics. Specifically, if a particular cluster has a low customer service rating, it provides customer service textbooks and videos to the salespeople in that cluster, and proposes closing skills training to the cluster with low sales ability.

[1213] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson during learning and training. Based on this, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling stressed, the server will provide them with content that is less difficult, and conversely, if they are in a state of high excitement, it will add more challenging tasks.

[1214] The server also evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data, making it possible to understand how effective the provided content was in improving the salesperson's skills.

[1215] Examples:

[1216] For example, a salesperson with ID 1 has the following data:

[1217] Sales amount: 200

[1218] Customer Service Rating: 4.5

[1219] Training Completed: True

[1220] Activity Level: 50

[1221] The server preprocesses this data, standardizes the data of other salespeople with similar data, and clusters them. As a result, the salesperson with ID 1 is classified into cluster 0. The salesperson in cluster 0 is analyzed as having high customer service ratings, but average sales. In this case, the server suggests to cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[1222] On the other hand, the salesperson with ID4 has a very high sales amount and a high evaluation of customer service, but also has a high activity level. In this case, ID4 will be classified into cluster 1, and based on the characteristics of the cluster, it is expected that the following will be suggested: "Customer service needs improvement. Provide customer service text and video."

[1223] Furthermore, the emotion engine recognizes the emotions of the salesperson (user), and if it detects that the salesperson is feeling nervous or stressed during the training, the server adjusts the difficulty level to allow the user to study in a relaxed state. For example, if salesperson ID1 feels high stress during training on closing techniques, the emotion engine will detect this and the server will change the training content to a relatively easy one. This provides an environment in which the salesperson can study effectively.

[1224] In this way, the present invention is a system that promotes the overall improvement of salespeople's abilities by providing optimal learning materials and training content based on each salesperson's individual data and further adjusting the content in real time using an emotion engine.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] The server acquires salesperson performance data and activity data, including sales amounts, customer service ratings, training completion status, activity levels, etc. This data is collected from a database or the like.

[1228] Step 2:

[1229] The server preprocesses the acquired data. Specifically, it removes unnecessary columns and standardizes the values ​​of each column using StandardScaler. This standardization unifies data with different scales into a consistent scale.

[1230] Step 3:

[1231] The server performs clustering using the preprocessed data, dividing the data into multiple clusters using the KMeans algorithm, and adding information to the original data about which cluster each salesperson belongs to.

[1232] Step 4:

[1233] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales, customer service evaluation, and activity level within each cluster to clarify the characteristics of each cluster. This analysis identifies the areas in which each cluster has strengths and weaknesses.

[1234] Step 5:

[1235] The server then proposes learning materials and training content for each cluster based on the analysis results. For clusters with low customer service ratings, it provides customer service textbooks and videos, and for clusters with low sales ability, it proposes training on closing techniques.

[1236] Step 6:

[1237] The server provides the salespeople with the learning materials and training content proposed for each cluster. The appropriate learning materials and training content are displayed to each salesperson via their terminal. The salesperson accesses these and receives the training.

[1238] Step 7:

[1239] The emotion engine recognizes the emotions of the salesperson user in real time during training. Emotion data is collected using facial recognition and biometric sensors, for example.

[1240] Step 8:

[1241] Based on the emotional data collected by the emotion engine, the server adjusts the learning materials and training content in real time. For example, if a salesperson is feeling stressed, it will provide them with less difficult content, and conversely, if they are highly excited, it will provide them with more challenging tasks.

[1242] Step 9:

[1243] The server evaluates the effectiveness of the proposed learning materials and training content based on the user's emotional data. By comparing the emotional data with the learning outcomes, the server analyzes the extent to which the provided content contributed to improving the salesperson's skills.

[1244] Step 10:

[1245] Salespeople (users) receive training according to the suggested learning materials and training content. By providing adjusted learning materials and training in real time via their devices, they can efficiently learn and improve their skills. This process continues, and data is updated regularly to ensure that optimal training is always provided.

[1246] Example 2

[1247] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1248] There is a need to effectively utilize salesperson performance and activity data, accurately analyze each salesperson's strengths and weaknesses, and then propose appropriate learning materials and training content.However, conventional systems have not been able to fully provide learning materials and training content optimized for each salesperson, and they do not make adjustments based on real-time emotional data, so there are limitations to improving the overall capabilities of salespersons.

[1249] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1250] In this invention, the server includes means for acquiring salesperson performance data and activity data, means for preprocessing the acquired data, and means for clustering the preprocessed data. This enables accurate clustering based on the data of individual salespersons. It also includes means for analyzing the characteristics of each cluster based on the clustering results and means for proposing learning materials or training content based on the analyzed characteristics, and means for providing the proposed learning materials or training content to each salesperson. It also includes means for recognizing the emotions of the salesperson during the learning or training, means for adjusting the learning materials or training content in real time based on the recognized emotions, and means for evaluating the effectiveness of the proposed learning materials or training content. This enables accurate analysis and individualized learning based on the salesperson's performance data and activity data, and further enables the salesperson's overall ability to be improved by adjusting the learning content in real time using emotional data.

[1251] "Salesperson performance data" refers to data that indicates the results of sales activities that a salesperson has conducted in the past, and specifically includes the quantity of products sold, the sales amount, and evaluation scores from customers.

[1252] "Activity data" refers to data relating to the salesperson's daily work activities, including, for example, the number of customer contacts, training completion status, and daily activity level.

[1253] "Means of acquisition" refers to the means for collecting the target data, and includes methods such as API calls and database queries.

[1254] "Preprocessing means" refers to means for converting collected raw data into an analyzable format, and specifically includes removing unnecessary columns and standardizing data.

[1255] The "clustering means" refers to a means for dividing collected and preprocessed data into groups based on specific criteria, and specifically includes the KMeans algorithm.

[1256] "Means for analyzing the characteristics of clusters" refers to means for clarifying the characteristics of each cluster based on the results of clustering, and specifically includes methods for calculating the mean value and standard deviation.

[1257] The "means for proposing learning materials or training contents" refers to a means for selecting and proposing the most suitable learning materials or training contents for each cluster based on the characteristics of the analyzed cluster.

[1258] The "means of provision" refers to the means for delivering or notifying each salesperson of the proposed learning materials and training content.

[1259] "Emotion recognition means" refers to means for detecting the emotions felt by salespeople in real time during learning and training, and specifically includes biofeedback devices and emotion recognition software.

[1260] "Means for real-time adjustment" refers to means for changing the difficulty level and content of learning materials and training content on the fly based on recognized emotional data.

[1261] "Means for evaluating effectiveness" are means for measuring the extent to which the proposed learning materials and training content have contributed to improving the skills of sales staff.

[1262] The present invention combines an emotion engine with a system that analyzes weak areas based on salesperson performance data and activity data, and proposes appropriate learning materials and training for each salesperson. The program of this system will be described in detail below.

[1263] First, the server acquires the salesperson's performance data and activity data. This performance data includes the number of products sold, sales amount, and customer evaluation scores, while activity data includes the number of customer contacts, training completion status, daily activity level, etc. Data collection is performed using a database management system (e.g., MySQL or PostgreSQL) and an API communication tool (e.g., REST API).

[1264] Next, the server preprocesses the acquired data by removing unnecessary columns and standardizing each data item to the same scale. Data processing frameworks such as Pandas and NumPy are used for data processing.

[1265] The server then performs clustering on the preprocessed data. Specifically, it uses Scikit-learn's KMeans algorithm to divide the data into a specific number of clusters. During this process, information about which cluster each salesperson belongs to is added to the original data.

[1266] Next, the server analyzes the characteristics of each cluster based on the clustering results. Specifically, it calculates the mean and standard deviation of each cluster and clarifies characteristics such as sales performance and customer service evaluation for each cluster. This process uses statistical analysis tools (e.g., Pandas).

[1267] The server then suggests optimal learning materials and training content for each cluster based on the cluster's characteristics. For example, it provides customer service textbooks and videos to a cluster with low customer service ratings, and suggests training on closing skills to a cluster with low sales ability. Notifications of the suggestions are sent via email or notification systems (e.g., SMTP or SNS).

[1268] Furthermore, an emotion engine has been implemented, allowing the server to recognize the emotions of the salesperson users in real time during learning and training. Based on this data, the learning materials and training content can be adjusted in real time. For example, if a salesperson is feeling high stress, the difficulty level can be lowered, and conversely, if the salesperson is in a high state of excitement, more challenging tasks can be added. Emotion recognition is achieved using biofeedback devices and emotion recognition software (e.g., Affectiva).

[1269] Finally, the server evaluates the effectiveness of the proposed learning materials and training content, which involves comparing performance data and emotion data after training to evaluate the learning effect.

[1270] As a concrete example, suppose the performance data for a salesperson with ID 1 is as follows:

[1271] Sales amount: 200

[1272] Customer Service Rating: 4.5

[1273] Training Completed: True

[1274] Activity Level: 50

[1275] The server preprocesses this data and clusters it with other salespeople who belong to the same cluster. As a result, salesperson ID1 is classified into cluster 0. Cluster 0 has a high reputation for customer service but average sales. In this case, the server suggests to the salesperson in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques." If salesperson ID1 feels high stress during the training, the emotion engine detects this and the server adjusts the training content to be easier.

[1276] In this way, the system of the present invention provides optimal learning materials and training content based on salesperson performance data and activity data, and further makes adjustments based on real-time emotion recognition, thereby comprehensively supporting the improvement of salesperson skills.

[1277] Example prompt sentence:

[1278] "What are the data entries for Salesperson ID 1, with sales of 200 and a customer service rating of 4.5?"

[1279] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1280] Step 1: Collect data

[1281] A server retrieves salesperson performance and activity data.

[1282] Input: Salesperson performance and activity data from a database or API

[1283] Specific operation: The server executes an API call to retrieve salesperson information from the database, including sales volume, sales amount, customer evaluation score, number of customer contacts, training completion status, and daily activity level.

[1284] Output: raw data collected

[1285] Step 2: Preprocessing the data

[1286] The server preprocesses the collected data.

[1287] Input: Raw data

[1288] Specific operation: The server uses the Pandas library to remove unnecessary columns from the raw data, standardize each data item to the same scale, and impute missing values ​​appropriately.

[1289] Output: Preprocessed data

[1290] Step 3: Clustering

[1291] The server performs clustering using the preprocessed data.

[1292] Input: Preprocessed data

[1293] Specific operation: The server uses Scikit-learn's KMeans algorithm to divide the data into the number of clusters. The number of clusters is based on the parameters set in advance. Information about which cluster each salesperson belongs to is added to the original data.

[1294] Output: Clustering results (data with cluster information for each salesperson added)

[1295] Step 4: Feature Analysis

[1296] The server analyzes the characteristics of each cluster based on the clustering results.

[1297] Input: Clustering results

[1298] Specific operation: The server uses Pandas to calculate the mean and standard deviation of each cluster, clarifying the characteristics of each cluster. This identifies the areas in which each cluster has strengths and weaknesses.

[1299] Output: Feature data for each cluster

[1300] Step 5: Proposing learning materials and training content

[1301] The server proposes the most suitable learning materials and training content for each cluster based on the characteristics of the cluster.

[1302] Input: Cluster feature data

[1303] Specific operation: The server considers the characteristics of each cluster, for example, providing customer service texts and videos for a cluster with low customer service ratings, and suggesting closing skills training for a cluster with low sales ability. This information is added to the suggestion list.

[1304] Output: A list of suggested learning materials and training content

[1305] Step 6: Real-time adjustments with the emotion engine

[1306] The emotion engine collects emotional data from salespeople, and the server uses this data to adjust learning materials and training content in real time.

[1307] Input: Emotion data during learning or training

[1308] How it works: The emotion engine recognizes the salesperson's emotions, such as stress and concentration, in real time, and the server analyzes the data. For example, if the salesperson is highly stressed, the difficulty level is reduced, and if the salesperson is highly excited, more challenging tasks are added.

[1309] Output: Tailored learning materials and training content

[1310] Step 7: Evaluate the effect

[1311] The server evaluates the effectiveness of the proposed learning materials and training contents.

[1312] Input: Performance data and emotional data after implementing learning materials and training content

[1313] Specific operation: The server compares performance data before and after learning or training, and evaluates the learning effectiveness by taking into account emotional data. This allows the server to understand how effective the proposed training content was in improving the salesperson's skills. Feedback is reflected in the next proposal.

[1314] Output: Evaluation results of learning effect

[1315] The above is a series of specific processing steps for the program of this system.

[1316] (Application example 2)

[1317] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1318] Conventional salesperson skill improvement systems have difficulty reflecting individual salesperson weaknesses and learning progress in real time. Furthermore, they have had problems with ineffective learning and training, resulting in lower sales work efficiency and lower customer satisfaction. The present invention aims to effectively improve salesperson skills by providing appropriate learning materials and training based on the performance and activity data of individual salespersons, and further adjusting the learning materials and training content in real time based on emotion recognition.

[1319] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring performance data and activity data of salespeople, means for pre-processing the acquired data, means for clustering the pre-processed data, means for analyzing characteristics of each cluster based on the clustering results, means for proposing learning materials or training content according to the analyzed characteristics, means for providing the proposed learning materials or training content to each salesperson, and means for adjusting the learning materials or training content in real time based on emotion recognition. This makes it possible to provide an optimized learning experience for each salesperson, thereby improving sales efficiency and customer satisfaction.

[1320] - "Salesperson performance data" is a general term for data recorded as performance, such as sales amounts, sales quantities, and customer evaluation scores achieved by salespersons in the past.

[1321] "Activity data" refers to data about the salesperson's daily work activities, including the number of customer contacts, training completion status, patrol frequency, and number of security camera checks.

[1322] "Preprocessing" refers to the process of removing unnecessary columns from raw data, standardizing the data, and preparing the data for analysis and clustering.

[1323] "Clustering" is an analytical technique for classifying data into multiple groups (clusters), and is used in the present invention to identify the strengths and weaknesses of salespeople.

[1324] "Cluster characteristics" refer to common characteristics of the data belonging to each cluster, including, for example, the average value and standard deviation of sales performance and customer service evaluation within each cluster.

[1325] "Learning Materials" refers to educational content, such as textbooks, videos, and online courses, provided to salespeople to improve their skills.

[1326] "Training Content" refers to the content of the training program in which salespeople learn specific skills, including on-the-job training and simulations.

[1327] "Emotion recognition" refers to technology that analyzes a user's facial expressions, voice, and physical movements to identify their emotional state at any given time (stress, tension, excitement, etc.).

[1328] "Real-time adjustment" refers to the process of instantly changing learning materials and training content based on the user's current state and performance.

[1329] MODE FOR CARRYING OUT THE INVENTION

[1330] The present invention combines an emotion recognition function with a system that proposes appropriate learning materials and training for each salesperson based on the salesperson's performance data and activity data. Specific embodiments for carrying out the present invention will be described below.

[1331] System Program

[1332] 1. Data Collection:

[1333] The server acquires salesperson performance and activity data, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, daily activity levels, etc.

[1334] 2. Data Preprocessing:

[1335] The server preprocesses the acquired data. During the preprocessing stage, unnecessary columns are removed and the data is scaled for standardization purposes, so that data of different scales can be treated on the same basis.

[1336] 3. Clustering:

[1337] Clustering is performed using the preprocessed data. Specifically, the KMeans algorithm is used to classify the data into a set number of clusters. Information about which cluster each salesperson belongs to is added to the original data.

[1338] 4. Feature analysis:

[1339] The server analyzes the characteristics of each cluster based on the clustering results, calculating the mean and standard deviation within each cluster and identifying which clusters have strengths and weaknesses in which areas.

[1340] 5. Learning Materials and Training Suggestions:

[1341] Depending on the analyzed characteristics, learning materials or training content suitable for a specific cluster are suggested. For example, customer service textbooks and videos are provided to a cluster with low customer service ratings, and closing skills training is provided to a cluster with low sales ability.

[1342] 6. Emotion recognition and real-time adjustment:

[1343] Using an emotion recognition engine, the server recognizes the emotions of salespeople during learning and training. For example, if a user is feeling stressed, the server will lower the difficulty of the content provided, and conversely, if the user is in a state of high excitement, it will add more challenging tasks.

[1344] Hardware / Software used

[1345] Hardware: Smart glasses (generic name), head-mounted display (generic name), cloud-based server (generic name).

[1346] Software: Python, Pandas, Scikit-Learn, Affectiva (emotion recognition system).

[1347] Specific examples

[1348] For example, say you have a salesperson ID1 with the following data:

[1349] Sales amount: 200

[1350] Customer Service Rating: 4.5

[1351] Training Completion Status: Completed

[1352] Activity Level: 50

[1353] The server preprocesses this data, standardizes the data of salespeople with similar data, and performs clustering. As a result, salesperson ID 1 is classified into cluster 0. The analysis shows that salespeople in cluster 0 have high customer service ratings, but average sales. In this case, the server suggests to the salespeople in cluster 0, "You need to improve your sales skills. We will provide you with training on closing techniques."

[1354] Furthermore, if the emotion recognition engine detects the emotions of the salesperson (user), for example, if it detects that the salesperson is feeling high stress during training, the server will change the training content to a relatively easy one, thereby providing an environment in which the salesperson can learn effectively.

[1355] As an example of a specific prompt, you can enter the following:

[1356] "Adjust the next training content based on Security Guard A's latest emotional data. If his stress level is high, lower the difficulty."

[1357] "If high stress is detected during closing skills training for salesperson ID1, change the content to something simpler in real time."

[1358] In this way, the system effectively improves salespeople's skills by providing them with optimal learning materials and training content based on their individual data, and further adjusting the content in real time using emotion recognition.

[1359] Summary of the Invention

[1360] This system provides an optimal learning experience for each salesperson by proposing learning materials and training content based on the salesperson's performance and activity data and adjusting the content in real time based on emotion recognition, thereby improving sales efficiency and customer satisfaction.

[1361] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1362] Step 1:

[1363] The server retrieves salesperson performance and activity data from a database, including sales amounts, customer evaluation scores, number of customer contacts, training completion status, and daily activity levels. The input is the raw data extracted from the database, and the output is a dataset for preprocessing.

[1364] Step 2:

[1365] The server preprocesses the acquired data. This preprocessing includes removing unnecessary columns, imputing missing values, and standardizing the data. For example, standardization converts each data item to the same scale. The input is the raw dataset, and the output is the preprocessed dataset.

[1366] Step 3:

[1367] The server performs clustering using the preprocessed dataset. Specifically, it applies the KMeans algorithm to classify the data into the set number of clusters. The input is the preprocessed dataset, and the output is a data label indicating which cluster each salesperson belongs to.

[1368] Step 4:

[1369] The server analyzes the characteristics of each cluster based on the clustering results. It calculates the average and standard deviation of sales performance, customer service ratings, and activity levels within each cluster to identify cluster characteristics. The input is the clustered dataset, and the output is the average feature value of each cluster.

[1370] Step 5:

[1371] The server then proposes appropriate learning materials or training content for each salesperson based on the analyzed cluster characteristics. For example, if a particular cluster has a low customer service rating, it provides customer service texts or videos to the salespersons in that cluster. The input is the cluster characteristics and individual salesperson information, and the output is a list of suggested learning materials or training content for each salesperson.

[1372] Step 6:

[1373] The server uses an emotion recognition engine to receive real-time emotional data from users (salespeople) who are learning or undergoing training. For example, it analyzes emotional data collected while the user is undergoing training through smart glasses or a head-mounted display. The input is real-time emotional data, and the output is the user's emotional state (stress level, elation, etc.).

[1374] Step 7:

[1375] The server adjusts the learning materials or training content in real time based on the received emotional data. For example, if the user is feeling highly stressed, it will issue instructions to reduce the difficulty of the training content, and conversely, if the user is feeling excited, it will add more challenging tasks. The input is the user's emotional state, and the output is the adjusted learning materials or training content.

[1376] As a specific example, if salesperson ID1 feels high stress during closing skills training, the server adjusts the training to lower its difficulty based on data from the emotion recognition engine. An example of the prompt sentence in this case could be, "If high stress is detected during closing skills training for salesperson ID1, please change the content to something easier in real time."

[1377] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1378] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1379] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1380] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1381] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1382] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1383] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1384] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1385] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1386] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1387] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1388] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1389] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1390] 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.

[1391] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1392] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1393] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1394] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1395] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1396] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1397] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1398] The following is further disclosed regarding the above embodiment.

[1399] (Claim 1)

[1400] means for acquiring salesperson performance and activity data;

[1401] means for preprocessing the acquired data;

[1402] means for clustering the preprocessed data;

[1403] means for analyzing the characteristics of each cluster based on the results of the clustering;

[1404] a means for suggesting learning materials or training contents according to the analyzed characteristics;

[1405] a means of providing each salesperson with suggested learning materials or training content;

[1406] A system including:

[1407] (Claim 2)

[1408] 10. The system of claim 1, further comprising means for normalizing the data.

[1409] (Claim 3)

[1410] The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values.

[1411] "Example 1"

[1412] (Claim 1)

[1413] means for acquiring salesperson performance and activity data;

[1414] means for preprocessing the acquired data;

[1415] means for clustering the preprocessed data;

[1416] means for analyzing the characteristics of each cluster based on the results of the clustering;

[1417] a means for suggesting learning materials or training contents according to the analyzed characteristics;

[1418] a means of providing each salesperson with suggested learning materials or training content;

[1419] means for displaying the proposed learning materials or training contents to the salesperson through a terminal;

[1420] A system including:

[1421] (Claim 2)

[1422] 10. The system of claim 1, further comprising means for normalizing the data.

[1423] (Claim 3)

[1424] The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values.

[1425] "Application Example 1"

[1426] (Claim 1)

[1427] means for acquiring salesperson performance and activity data;

[1428] means for preprocessing the acquired data;

[1429] means for clustering the preprocessed data;

[1430] means for analyzing the characteristics of each cluster based on the results of the clustering;

[1431] a means for suggesting learning materials or training contents according to the analyzed characteristics;

[1432] a means of providing each salesperson with suggested learning materials or training content;

[1433] a means of informing each salesperson of the proposed learning materials or training content;

[1434] A means for managing the progress of the notified learning materials or training content;

[1435] A system including:

[1436] (Claim 2)

[1437] 10. The system of claim 1, further comprising means for normalizing the data.

[1438] (Claim 3)

[1439] The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values.

[1440] "Example 2: Combining Emotion Engines"

[1441] (Claim 1)

[1442] means for acquiring salesperson performance and activity data;

[1443] means for preprocessing the acquired data;

[1444] means for clustering the preprocessed data;

[1445] means for analyzing the characteristics of each cluster based on the results of the clustering;

[1446] a means for suggesting learning materials or training contents according to the analyzed characteristics;

[1447] a means of providing each salesperson with suggested learning materials or training content;

[1448] means for recognizing the emotions of the salesperson during said learning or training;

[1449] A means to adjust learning materials and training content in real time based on recognized emotions; and

[1450] A means of evaluating the effectiveness of proposed learning materials and training content;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, further comprising means for normalizing the data.

[1454] (Claim 3)

[1455] The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values.

[1456] "Application example 2 when combining emotion engines"

[1457] (Claim 1)

[1458] means for acquiring salesperson performance and activity data;

[1459] means for preprocessing the acquired data;

[1460] means for clustering the preprocessed data;

[1461] means for analyzing the characteristics of each cluster based on the results of the clustering;

[1462] a means for suggesting learning materials or training contents according to the analyzed characteristics;

[1463] a means of providing each salesperson with suggested learning materials or training content;

[1464] means for adjusting learning materials or training content in real time based on emotion recognition;

[1465] A system including:

[1466] (Claim 2)

[1467] 10. The system of claim 1, further comprising means for normalizing the data.

[1468] (Claim 3)

[1469] The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values. [Explanation of symbols]

[1470] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for acquiring salesperson performance and activity data; means for preprocessing the acquired data; means for clustering the preprocessed data; means for analyzing the characteristics of each cluster based on the results of the clustering; a means for suggesting learning materials or training contents according to the analyzed characteristics; a means of providing each salesperson with suggested learning materials or training content; A system including:

2. The system of claim 1 further comprising means for normalizing the data.

3. The system of claim 1 further comprising means for analyzing the cluster characteristics based on average values.

Images