system

Abstract

We provide the system. [Solution] A means for collecting customer information, sales data, and records of sales activities from a database, A means of analyzing the economic situation and market trends of customers by analyzing the collected data, A means of generating individual advice for each sales member based on the analysis results, A means of distributing the generated individual advice to each sales member's terminal, A system that includes means to collect feedback from each sales member and improve advice and strategies.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern sales activities, it is extremely important for each sales member to accurately grasp individual customer information and sales data and make effective proposals at appropriate times. However, it is very difficult to grasp the economic situation of customers and market trends and provide timely and accurate advice, which causes variations in the performance of sales members. In addition, it is also difficult to accurately formulate the overall strategy of the team and realize a continuous improvement cycle to achieve sales targets. Therefore, there is a need to develop a system to solve these problems and improve the accuracy and effectiveness of sales activities.

Means for Solving the Problems

[0005] This invention provides means for collecting customer information, sales data, and records of sales activities from a database, and means for analyzing the collected data to analyze the customer's economic situation and market trends. Furthermore, it includes means for generating individual advice for each sales member based on the analysis results and means for distributing the generated advice to each sales member's terminal. This system also includes means for collecting feedback provided by each sales member and improving the advice and strategies. This enables each sales member to work efficiently and effectively, supporting the team's overall strategy planning and achievement of sales targets. In addition, a continuous improvement cycle is achieved by updating the analysis algorithm based on feedback and reflecting it in the next strategy planning. Furthermore, by providing means for integrating the team's overall sales data and individual advice to formulate the team's strategy, the strategy for achieving the team's overall sales targets can be effectively executed.

[0006] A "database" is an electronic storage system for systematically collecting and storing data such as customer information, sales data, and records of sales activities.

[0007] "Customer information" refers to detailed data about a customer, such as their name, address, contact information, past purchase history, and contract details.

[0008] "Sales data" refers to information that shows the sales performance of a product or service over a certain period, and includes revenue, sales volume, etc.

[0009] "Sales activity records" refer to data that includes the history of transactions and communications that sales members have had with customers.

[0010] "Analysis" refers to the process of analyzing a customer's economic situation and market trends based on collected data.

[0011] "Analysis results" refer to insights and conclusions obtained through the analysis, including information about the customer's economic situation and market trends.

[0012] "Individualized advice" refers to specific and appropriate recommendations provided to each sales member based on the customer's situation and market trends.

[0013] A "terminal" refers to a device used by each sales member, such as a computer or mobile device, for displaying or inputting information.

[0014] "Feedback" refers to the responses that sales members provide to the system regarding activity results and customer information.

[0015] "Means for improving advice and strategies" refers to functions that use collected feedback to improve the quality of advice and overall strategies for future occasions.

[0016] An "analysis algorithm" is a mathematical and statistical computational method used to extract useful insights from collected data and generate advice.

[0017] A "continuous improvement cycle" is a process of constantly improving the functionality and quality of advice provided by a system based on feedback and new data.

[0018] "Strategic planning" is the process of formulating specific action plans for an organization or team based on collected and analyzed data. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

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

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0040] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[0041] Server Role

[0042] The server is the central hub of the system and performs the following main functions:

[0043] 1. Data collection:

[0044] The server collects customer information, sales data, and records of sales activities from the database. This data forms the basis for analyzing the performance of individual sales members and the entire team.

[0045] 2. Data Analysis:

[0046] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis results form the basis for the individual advice provided to each sales member.

[0047] 3. Generate personalized advice:

[0048] Based on the analysis results, the server generates specific advice for each sales member. This advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[0049] 4. Distribution of advice:

[0050] The generated personalized advice is delivered to each sales member's terminal by the server. This allows sales members to receive the latest information in real time.

[0051] 5. Gathering feedback:

[0052] The server collects feedback from each sales member and stores it in a database. This feedback is used for the continuous improvement of the system.

[0053] 6. Update of the analysis algorithm:

[0054] The server analyzes the collected feedback and updates its analysis algorithm to make the next advice more accurate.

[0055] Terminal role

[0056] The terminal is a device used by each sales member and provides the following functions:

[0057] 1. Displaying data:

[0058] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access the information when needed.

[0059] 2. Feedback Input:

[0060] Each sales member enters feedback using their own device. The entered feedback is sent to the server and stored in the database.

[0061] User roles

[0062] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[0063] 1. Implement the advice:

[0064] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[0065] 2. Providing feedback:

[0066] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[0067] Specific example

[0068] For example, a server analyzes the sales data of a certain company (customer A) over the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice that "a new product enhancement proposal should be made starting in May" and delivers it to sales member B's terminal. When B submits a new product proposal to customer A in May and inputs the result as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy.

[0069] In this way, the system can respond to the individual needs of sales members and effectively plan and execute the team's overall strategy.

[0070] The following describes the processing flow.

[0071] Step 1:

[0072] Database connection

[0073] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[0074] Step 2:

[0075] Data acquisition

[0076] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[0077] Step 3:

[0078] Data organization

[0079] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[0080] Step 4:

[0081] Data Analysis

[0082] Server: Inputs data into the data analysis engine to analyze customer economic conditions, market trends, and sales trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[0083] Step 5:

[0084] Individual advice generation

[0085] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[0086] Step 6:

[0087] Advice distribution

[0088] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[0089] Step 7:

[0090] Data display

[0091] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[0092] Step 8:

[0093] Sales activities

[0094] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[0095] Step 9:

[0096] Feedback Input

[0097] User: Enters sales activity results and new customer information into the terminal. The entered information is sent to the server.

[0098] Step 10:

[0099] Save feedback

[0100] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[0101] Step 11:

[0102] Feedback analysis

[0103] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[0104] Step 12:

[0105] Algorithm update

[0106] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[0107] Step 13:

[0108] Strategic Planning

[0109] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[0110] (Example 1)

[0111] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0112] In sales activities, there is a need to efficiently collect individual advice and feedback from each sales member and improve the accuracy of analysis algorithms. Furthermore, it is necessary to utilize generative AI models to develop more effective sales strategies and enable real-time information sharing.

[0113] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0114] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for inputting prompt sentences to a generating AI model to obtain appropriate advice; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for updating the analysis algorithm based on the collected feedback data; and means for applying the updated analysis algorithm to the next analysis. This improves the quality of individual advice for sales members and enables improved analysis accuracy based on feedback. Furthermore, it enables the formulation of effective sales strategies utilizing the generating AI model and real-time information sharing.

[0115] A "database" is a digital system for systematically organizing and storing information, and it allows for the addition, deletion, searching, and updating of data through queries.

[0116] "Customer information" refers to data about a specific customer, including name, address, purchase history, and contact information.

[0117] "Sales data" refers to information regarding the sale of goods or services during a specific period, including sales amount, transaction date and time, and purchased items.

[0118] "Sales activity records" refer to the history of all business activities performed by sales members, including customer visits, negotiation details, and contract status.

[0119] "Analysis" refers to the process of using collected data to reveal its meaning, trends, and patterns.

[0120] "Individualized advice" refers to behavioral guidelines and strategic proposals provided individually to specific sales members.

[0121] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning techniques to generate new information or suggestions from input data.

[0122] A "prompt" refers to the input text given to a generative AI model in order to generate the requested output.

[0123] "Feedback" refers to the act of sales team members providing the results of their activities and the information they have gathered, as well as the content of that feedback.

[0124] An "analysis algorithm" refers to a computational method used to analyze data and generate output for a specific purpose.

[0125] A "device" refers to a digital device used by a user, and includes personal computers, tablets, smartphones, and other similar devices.

[0126] The system according to the present invention is designed to effectively support individualized advice to sales members and the strategies of departments and teams. Specific embodiments are described below.

[0127] Server Role

[0128] The server plays a central role in the system and performs multiple functions. First, it collects customer information, sales data, and records of sales activities from the database. The databases used include SQL Server and Oracle Database. By collecting this data, a foundation is built for analyzing the performance of individual sales members and the entire team.

[0129] Next, the collected data is analyzed using Python or R. Specifically, the data is processed using libraries such as Pandas and NumPy, and a model is built using the Scikit-learn machine learning library. For example, this data analysis is performed to predict which customers a sales team should act towards during a specific period.

[0130] Based on the generated analysis results, the server uses a generative AI model to generate personalized advice for each sales member. The generative AI model used here is GPT-3®, among others. For example, by entering a prompt such as, "Please suggest a sales pitch to use in the next business meeting," appropriate advice will be generated.

[0131] The generated personalized advice is delivered to each sales member's terminal via a REST API. The terminal receives an HTTP POST request and displays the advice in JSON format. This implementation allows sales members to obtain the latest information in real time.

[0132] The server collects feedback provided by sales members. This feedback includes sales activity results and new customer information. The feedback is then analyzed again and used for continuous system improvement and updating of the analysis algorithms.

[0133] Finally, the analysis algorithm is updated based on the collected feedback data. This update includes retraining the machine learning model, which will be reflected in the next analysis.

[0134] Terminal role

[0135] The terminal is a device used by each sales member and primarily provides the following functions. First, it displays individual advice and analysis results delivered from the server. Sales members can refer to specific advice by looking at the terminal screen. For example, it displays information such as when and what products should be proposed to a particular customer.

[0136] The terminal also provides a means for sales members to input feedback. Feedback is entered through forms and text boxes and sent to the server. The data is sent as an HTTP POST request and parsed on the server.

[0137] User roles

[0138] Users, i.e., sales members, use the system to conduct sales activities. Based on the advice displayed on the terminal, users carry out specific sales actions. For example, they might submit proposals to specific customers or follow up at the appropriate time. They also input the results of their sales activities and newly acquired customer information as feedback into the terminal and provide it to the system. This further improves the accuracy of the system and helps in future analyses.

[0139] Specific example

[0140] For example, a server analyzes the past two years of sales data for a company (customer A) and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should propose enhanced new products starting in May" and delivers it to the sales team members' terminals. When the sales team members submit a proposal for the new products to customer A in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm. Using this updated algorithm in the next analysis allows for more accurate advice.

[0141] Examples of prompts for generative AI models

[0142] For example, the following prompt statement is used:

[0143] "Analyze customer A's sales data for the past two years to identify which season has the highest sales. Based on these results, generate appropriate sales activity advice."

[0144] By using these prompts, the generative AI model can perform appropriate analysis and generate advice. This system functions by internally generating these prompts, which are then executed by the server.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1: Data Collection

[0147] Subject: Server

[0148] Specific actions:

[0149] The server collects data from databases such as SQL Server and Oracle Database. Specifically, it collects customer information, sales data, and records of sales activities. For example, the server issues an SQL query like this: "SELECT FROM sales_data WHERE year = 2022". Based on this input query, the relevant sales data is extracted from the database.

[0150] Input: SQL query

[0151] Output: Results of the SQL query (customer information, sales data, sales activity records)

[0152] Step 2: Data Analysis

[0153] Subject: Server

[0154] Specific actions:

[0155] The server analyzes the collected data using Python or R. It preprocesses the data using libraries such as Pandas and NumPy, and builds machine learning models using libraries such as Scikit-learn. For example, the server uses Pandas to convert the data into a DataFrame and uses a linear regression model to forecast sales.

[0156] Input: Data collected from the database

[0157] Output: Analysis results from the model (e.g., monthly sales forecast)

[0158] Step 3: Generate personalized advice

[0159] Subject: Server

[0160] Specific actions:

[0161] Based on the results of data analysis, the server sends prompt messages to the generating AI model to generate appropriate advice. For example, it might input the prompt message, "Please suggest a sales pitch to use in the next business meeting," into the generating AI model. Based on this input, the generating AI model will generate a sales pitch and proposal to use in the next business meeting.

[0162] Input: Analysis result, prompt message

[0163] Output: Advice from a generative AI model

[0164] Step 4: Delivering advice

[0165] Subject: Server

[0166] Specific actions:

[0167] The server distributes the generated individual advice to each sales member's terminal. Using a REST API, it sends HTTP POST requests to the sales member's terminal, delivering the advice in JSON format. For example, the server sends the advice to the " / advice" endpoint.

[0168] Input: Generated advice

[0169] Output: Notification on the device where the advice was delivered.

[0170] Step 5: Gathering Feedback

[0171] Subject: terminal

[0172] Specific actions:

[0173] Each sales member uses a terminal to input feedback such as the results of their sales activities and new customer information. For example, a sales member might input feedback such as "I proposed a new product to customer A and received a positive response," and send it to the server. The terminal sends this feedback to the server via an HTTP POST request.

[0174] Input: Results of sales activities and new customer information

[0175] Output: Feedback is sent to the server and stored in the database.

[0176] Step 6: Updating the analysis algorithm

[0177] Subject: Server

[0178] Specific actions:

[0179] The server updates its analysis algorithm based on the collected feedback data. Specifically, it retrains the machine learning model using the new feedback data. For example, it retrains the model with the new data using the "fit" method of Scikit-learn. This update ensures that a more accurate algorithm is applied in the next analysis.

[0180] Input: Feedback data

[0181] Output: Updated analysis algorithm

[0182] (Application Example 1)

[0183] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0184] Traditional sales support systems have low accuracy in providing individual customer proposals and advice, and furthermore, manual intervention is required to improve the provided advice. Therefore, there is a need for a more efficient and automated way to improve the accuracy of individual advice. However, these systems have limitations in how they can effectively utilize user purchase data and feedback, making it difficult to maximize sales efficiency. Therefore, a system is needed that analyzes user purchase patterns and automatically generates optimal proposals.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0186] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the collected feedback data and retraining the analysis algorithm; and means for improving the accuracy of subsequent individual advice using the retrained analysis algorithm. This makes it possible to generate individual proposals based on the user's purchasing data and economic situation and deliver those proposals to the user's smart device.

[0187] A "database" is a system for centrally managing and storing various types of data, such as customer information, sales data, and records of sales activities.

[0188] An "analysis algorithm" is a set of procedures and calculation methods used to analyze collected data and find specific patterns or trends.

[0189] "Feedback" refers to information such as results reports, evaluations, and opinions provided by sales members and users, which is useful for improving the system.

[0190] "Individualized advice" refers to customized proposals and strategies provided to specific sales members or users based on analysis results.

[0191] A "smart device" is an electronic device with advanced functions that a user can carry or wear, and includes smartphones, tablets, smartwatches, and other similar devices.

[0192] "Purchase data" refers to a detailed record of products and services that a user has purchased in the past, including information such as the date of purchase, place of purchase, and purchase amount.

[0193] "Data collection methods" refer to processes and technologies for automatically acquiring necessary data from databases or external systems.

[0194] "Delivery methods" refer to the methods and technologies used to efficiently deliver generated personalized advice and suggestions to users or sales members. Specifically, this includes push notifications, email distribution, and dashboard displays.

[0195] "Retraining" is the process of updating existing analysis algorithms based on newly obtained feedback and data to obtain more accurate and effective results.

[0196] "Retraining methods" refer to methods and techniques for retraining analytical algorithms, and this includes updating machine learning models with new data.

[0197] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[0198] Server Role

[0199] The server is the central hub of the system and performs the following main functions:

[0200] 1. Data collection methods

[0201] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it retrieves information from various databases and external systems using SQL and REST APIs.

[0202] 2. Data Analysis Methods

[0203] The server cleanses the collected data using Pandas and Scikit-learn and analyzes the customer's economic situation and market trends. This allows it to understand the user's purchasing patterns and trends, and based on the results, it generates personalized advice.

[0204] 3. Individual advice generation means

[0205] The server generates specific advice for each sales member based on the analysis results. The advice is constructed in natural language using Python and the Natural Language Toolkit (NLTK).

[0206] 4. Methods for delivering advice

[0207] The generated personalized advice is delivered in real time to each sales member's device via the server using Firebase Cloud Messaging (FCM) or the Email API.

[0208] 5. Methods for collecting feedback

[0209] The server collects feedback from each sales member and stores it in a database. The collected feedback data is stored within the system using Firebase Analytics and REST APIs.

[0210] 6. Methods for retraining analysis algorithms

[0211] The server analyzes the collected feedback data and updates its analysis algorithm by retraining it using TENSORFLOW® and Keras. This improves the accuracy of individual advice in subsequent sessions.

[0212] Terminal role

[0213] The terminal is a device used by each sales member and provides the following functions:

[0214] 1. Data display means

[0215] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access information when needed.

[0216] 2. Feedback Input Means

[0217] Sales team members enter feedback using their own devices. The entered feedback is sent to the server and stored in the database.

[0218] User roles

[0219] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[0220] 1. Implement the advice

[0221] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[0222] 2. Providing feedback

[0223] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[0224] Specific example

[0225] For example, a server analyzes a company's sales data for the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should start promoting enhanced new products from May" and delivers it to the sales team members' terminals. When the sales team members actually propose the new products to customers in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. This process further improves the accuracy of future proposals.

[0226] Example of a prompt

[0227] "Based on the user's purchase history and payment data, predict when they will make their next purchase and generate coupon suggestions tailored to their specific needs. Use the following information as a basis:"

[0228] User ID: 12345

[0229] Purchase history over the past 6 months: [Groceries, Electronics, Clothing]

[0230] Payment data: High-value purchases made on the 25th of each month.

[0231] User's financial situation: Stable

[0232] Example of a proposal format: 'We will distribute a special sale coupon around the 25th.'

[0233] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0234] Step 1: Data Collection

[0235] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it uses SQL and REST APIs to query and collect the necessary information from the database. This inputs customer purchase history and financial status information into the server.

[0236] Input: Customer information, sales data, and records of sales activities from the database.

[0237] Output: Collected customer information, sales data, and records of sales activities.

[0238] Specific actions:

[0239] Retrieve customer information from the database using SQL queries.

[0240] Sales data is collected from external systems via API requests.

[0241] Step 2: Data Analysis

[0242] The server uses the collected data to analyze customers' economic situations and market trends. It cleanses the data and extracts features using Python's Pandas and Scikit-learn. Furthermore, it performs data analysis using machine learning algorithms.

[0243] Input: Collected customer information, sales data, and records of sales activities.

[0244] Output: Data analysis results (customer's economic situation, purchasing patterns, trends)

[0245] Specific actions:

[0246] Use Pandas to cleanse data and handle missing values ​​and invalid data.

[0247] We will analyze customer purchasing patterns using Scikit-learn's machine learning algorithms.

[0248] Step 3: Generate personalized advice

[0249] The server generates personalized advice for each sales member based on the results of data analysis. Using Python and the Natural Language Processing (NLTK) library, a generative AI model constructs the advice in natural language.

[0250] Input: Data analysis results

[0251] Output: Individual advice (suggestions expressed in natural language)

[0252] Specific actions:

[0253] Based on the analysis results, an AI model is used to automatically generate advice.

[0254] Using NLTK, the generated advice is expressed in natural language.

[0255] Step 4: Delivering advice

[0256] The server distributes the generated personalized advice to each sales member's terminal. The advice is delivered via push notifications or email using Firebase Cloud Messaging (FCM) or the Email API.

[0257] Input: Individual advice

[0258] Output: Advice delivered to sales team members' terminals.

[0259] Specific actions:

[0260] Use FCM to send push notifications to sales team members' smart devices.

[0261] We will use the Email API to deliver personalized advice via email.

[0262] Step 5: Gathering Feedback

[0263] Each sales member enters feedback using their own device and sends it to the server. The server collects the feedback data via Firebase Analytics and REST APIs and stores it in a database.

[0264] Input: Feedback provided by sales members

[0265] Output: Collected feedback data

[0266] Specific actions:

[0267] Sales team members enter feedback into their terminals.

[0268] Feedback data is sent to the server via Firebase Analytics.

[0269] Step 6: Retrain the analysis algorithm

[0270] The server analyzes the collected feedback data and retrains its analysis algorithms using TensorFlow and Keras. This improves the accuracy of individual advice provided in subsequent sessions.

[0271] Input: Collected feedback data

[0272] Output: Retrained analysis algorithm

[0273] Specific actions:

[0274] The collected feedback data is cleansed and analyzed.

[0275] The analysis algorithm will be retrained using TensorFlow or Keras.

[0276] Through these steps, a system is implemented that involves the coordination of servers, terminals, and users, making it possible to improve the accuracy of individual advice.

[0277] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0278] The system according to the present invention is a system that, in addition to the function of collecting and analyzing customer information, sales data, and records of business activities, recognizes the user's emotion by combining an emotion engine and provides appropriate advice. This system includes a server, a terminal, and an emotion engine, each of which plays a specific role.

[0279] Role of the server

[0280] The server is a central element of the system and is responsible for the following main functions.

[0281] 1. Data collection:

[0282] The server connects to the database and acquires customer information, sales data, and records of business activities. This provides a basis for analyzing the performance of each sales member and the entire team.

[0283] 2. Data analysis:

[0284] The server analyzes the collected data to understand the customer's economic situation, market trends, and sales trends. The analysis results are useful for generating individual advice.

[0285] 3. Generation of individual advice:

[0286] The server generates individual advice for each sales member based on the results of data analysis. The generated advice is tailored to the specific needs of the customer and the timing of the business negotiation.

[0287] 4. Advice delivery:

[0288] The server distributes the generated personalized advice to each sales member's terminal, providing information in real time.

[0289] 5. Gathering and analyzing feedback:

[0290] The server collects feedback entered by each sales member and uses it to continuously improve the system. It also analyzes this feedback and updates the analysis algorithms.

[0291] Terminal role

[0292] The terminal is a device used by sales members and provides the following functions:

[0293] 1. Data display:

[0294] The terminal displays personalized advice and analysis results delivered from the server, providing users with information in real time.

[0295] 2. Feedback Input:

[0296] Users input feedback using their devices and send it to the server.

[0297] The role of the emotional engine

[0298] The emotion engine is responsible for recognizing the user's emotions, which are built into the system.

[0299] 1. Speech analysis:

[0300] The emotion engine analyzes the user's voice input and recognizes their emotions. The recognized emotions are sent to the server and used to generate advice.

[0301] 2. Facial expression analysis:

[0302] The emotion engine collects the user's facial expression data through the camera and analyzes the emotions. By doing so, the user's emotional state can be recognized more accurately.

[0303] 3. Adjustment of advice:

[0304] Based on the emotion data recognized by the emotion engine, the server adjusts the content and expression of the personalized advice provided. Through this process, more personalized and effective advice is provided.

[0305] Specific example

[0306] For example, the server analyzes the sales data of a specific customer (Customer A) over the past two years to identify seasonal fluctuations. Based on this data, the server generates advice such as "It is necessary to propose strengthening new products from May" and distributes it to the terminal of salesperson B. At that time, if the emotion engine analyzes B's emotional state and B is feeling stressed, the advice will be provided with more encouraging words.

[0307] When B submits a proposal for a new product to Customer A in May and inputs the result as feedback, the server analyzes this information and updates the analysis algorithm to reflect it in the next strategy. In this way, the system can respond to the individual needs and emotional states of salespersons and effectively formulate and execute the strategy of the entire team.

[0308] The following explains the processing flow.

[0309] Step 1:

[0310] Database connection

[0311] Server: Connect to the database and prepare to obtain customer information, sales data, and records of sales activities. Specifically, execute an SQL query to establish a connection for obtaining the necessary data.

[0312] Step 2:

[0313] Data acquisition

[0314] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[0315] Step 3:

[0316] Data organization

[0317] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[0318] Step 4:

[0319] Data Analysis

[0320] Server: Inputs data into the data analysis engine to analyze customer economic conditions, sales trends, and market trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[0321] Step 5:

[0322] Individual advice generation

[0323] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[0324] Step 6:

[0325] Preparation for emotional analysis

[0326] Terminal: The sales team member's terminal activates the emotion engine and begins collecting voice and facial expression data. It prepares to acquire user emotion data via the camera and microphone.

[0327] Step 7:

[0328] Emotion analysis

[0329] Emotion Engine: Analyzes the user's (sales member's) voice input and facial expression data to recognize their emotional state. Specific emotions (stress, joy, anger, etc.) are detected.

[0330] Step 8:

[0331] Advice adjustment

[0332] Server: Based on the emotional data recognized by the emotion engine, the server adjusts the content and expression of the personalized advice it provides. This process generates more personalized and effective advice.

[0333] Step 9:

[0334] Advice distribution

[0335] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[0336] Step 10:

[0337] Data display

[0338] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[0339] Step 11:

[0340] Sales activities

[0341] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[0342] Step 12:

[0343] Feedback Input

[0344] User: Inputs sales activity results, new customer information, and changes in emotional state into the terminal. The entered information is sent to the server.

[0345] Step 13:

[0346] Save feedback

[0347] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[0348] Step 14:

[0349] Feedback analysis

[0350] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[0351] Step 15:

[0352] Algorithm update

[0353] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[0354] Step 16:

[0355] Strategic Planning

[0356] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[0357] (Example 2)

[0358] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0359] Traditional sales support systems can collect and analyze customer and sales data, but they lack the functionality to provide effective, personalized advice based on this data. Furthermore, they lack adequate mechanisms for incorporating feedback from sales representatives, making continuous system improvement and sophisticated strategic planning difficult. Additionally, they fail to provide advice that takes into account the emotions of sales representatives, thus failing to contribute to increased motivation and more effective sales activities.

[0360] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0361] In this invention, the server includes means for acquiring customer data, sales information, and sales activity history from a data management system; means for analyzing the acquired data to evaluate the customer's economic status and market trends; means for generating individual advice for each sales representative based on the evaluation results; means for transferring the generated individual advice to each sales representative's device; means for collecting feedback provided by each sales representative and improving the advice and strategy; means for analyzing the user's emotions through voice and facial expressions; and means for dynamically adjusting the expression of the advice based on the analysis results. As a result, individual advice is provided taking into account the emotional state of the sales representative, and the system is constantly improved based on feedback, enabling more effective sales activities and strategic planning.

[0362] A "data management system" is a general term for software or hardware used to centrally collect, store, and manage customer data, sales information, and sales activity history.

[0363] "Customer data" refers to information about a customer, such as their name, contact information, purchase history, and financial status.

[0364] "Sales information" refers to data related to the sale of a product, including information such as sales figures and sales quantities for a specific period.

[0365] "Sales activity history" refers to a record of various sales activities carried out by a sales representative, including information such as visit history, negotiation details, and feedback.

[0366] "Means of acquisition" refers to mechanisms or methods for automatically retrieving necessary data from a database or external system.

[0367] "Means of analysis" refers to methods and systems for analyzing data using statistical and machine learning techniques to evaluate customers' economic status and market trends.

[0368] "Evaluation results" refer to information obtained from the analysis, including the customer's economic situation and market trends.

[0369] "Means for generating personalized advice" refers to systems and methods that automatically generate optimal proposals and action plans for sales representatives based on customer data and evaluation results.

[0370] "Transferring means" refers to the communication methods and protocols used to send the generated personalized advice to the sales representative's device.

[0371] "Provided feedback" refers to information that sales representatives record regarding the results of their actual sales activities and customer reactions, and then input into the system.

[0372] "Means for improving advice and strategies" refers to mechanisms and methods for analyzing the feedback received and formulating and improving new advice and strategies.

[0373] "Means of analyzing emotions through voice and facial expressions" refers to technologies and systems that analyze the voice and facial expressions of sales representatives to identify their emotional state.

[0374] "Means of dynamic adjustment" refers to mechanisms and methods that adjust the content and expression of generated advice in real time based on the results of emotion analysis.

[0375] The system according to the present invention is a system that collects and analyzes customer data, sales information, and sales activity history, and provides appropriate advice through sentiment analysis. This system comprises a server, terminals, and a sentiment analysis engine, each of which plays the following specific roles.

[0376] Server Role

[0377] Server processing:

[0378] The server retrieves customer data, sales information, and sales activity history from the data management system. This process uses relational database management systems (RDBMS) such as MySQL® or PostgreSQL. The server retrieves this data via SQL queries and extracts it from the database as follows:

[0379] Specific example:

[0380] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[0381] SELECT FROM sales WHERE date BETWEEN(registered trademark) '2022-01-01' AND '2022-12-31';

[0382] SELECT FROM activities WHERE type = 'sales_visit';

[0383] Data analysis:

[0384] The server uses the Python Pandas library to analyze the collected data. This analysis includes data cleaning, formatting, and aggregation, which is used to evaluate the customers' economic status and market trends.

[0385] Specific example:

[0386] df_customers = pd.read_sql(query_customers, connection)

[0387] df_sales = pd.read_sql(query_sales, connection)

[0388] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[0389] Generate personalized advice:

[0390] Based on the analysis results, the server generates personalized advice for each sales representative. This generation process uses Python's Pandas and NumPy libraries.

[0391] Specific example:

[0392] The system generates advice such as, "It would be effective to propose a new product to customer A in May."

[0393] Advice delivery:

[0394] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[0395] Specific example:

[0396] api_url = 'https: / / api.company.com / advice'

[0397] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[0398] response = requests.post(api_url, json=payload)

[0399] Gathering and analyzing feedback:

[0400] Each sales representative enters feedback and sends it to the server via their terminal. This feedback is collected and analyzed on the server side and used to improve the system.

[0401] Specific example:

[0402] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[0403] response = requests.post(api_url, json=feedback)

[0404] The server updates its machine learning model based on feedback and incorporates it into future strategy planning. This utilizes tools such as scikit-learn and TensorFlow.

[0405] Terminal role

[0406] Data display:

[0407] The terminal displays personalized advice and analysis results received from the server, providing real-time information to sales representatives (users). This process utilizes React.js and Vue.js.

[0408] Feedback input:

[0409] Users enter feedback via their device and send it to the server. This feedback is sent using HTML forms and JavaScript (registered trademark).

[0410] The role of the emotional engine

[0411] Voice analysis:

[0412] The emotion engine analyzes the user's voice data to recognize emotions. This analysis uses Google® Cloud Speech-to-Text API and IBM Watson®.

[0413] Facial expression analysis:

[0414] The emotion engine analyzes the user's facial expressions through the camera and identifies their emotional state. This process utilizes OpenCV and DeepFace.

[0415] Adjusting advice:

[0416] The server dynamically adjusts the content and wording of the advice provided to each sales representative based on emotional data obtained from the emotion engine.

[0417] Example of a prompt

[0418] "Analyze customer A's sales data for the past two years to identify seasonal sales fluctuations and generate optimal advice for determining the timing of the next proposal. Also, include flexible messaging that takes into account the emotional state of the sales representative making the proposal."

[0419] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0420] Step 1: Data Collection

[0421] Server operation:

[0422] The server connects to the data management system to retrieve customer data, sales information, and sales activity history. Specifically, it extracts data from databases such as MySQL and PostgreSQL using SQL queries.

[0423] Input: Database connection information, query for the required data.

[0424] Output: Extracted customer data, sales information, and sales activity history.

[0425] Specific examples of operation:

[0426] The server sends an SQL query to the database to retrieve data.

[0427] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[0428] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[0429] SELECT FROM activities WHERE type = 'sales_visit';

[0430] Step 2: Data Analysis

[0431] Server operation:

[0432] The server analyzes the acquired data using the Python Pandas library. It performs data cleaning, formatting, and aggregation to evaluate the customer's economic status and market trends.

[0433] Input: Data acquired in the data collection step

[0434] Output: Analysis results (customer's economic status, market trends, etc.)

[0435] Specific examples of operation:

[0436] df_customers = pd.read_sql(query_customers, connection)

[0437] df_sales = pd.read_sql(query_sales, connection)

[0438] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[0439] Step 3: Generate personalized advice

[0440] Server operation:

[0441] The server generates personalized advice for each sales representative based on the analysis results. This generation uses Python's Pandas and NumPy libraries.

[0442] Input: Analysis results

[0443] Output: Individual advice

[0444] Specific examples of operation:

[0445] Based on the analysis results, the system generates advice such as, "It would be effective to propose a new product to customer A in May."

[0446] Step 4: Delivering advice

[0447] Server operation:

[0448] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[0449] Input: Individual advice

[0450] Output: Delivery results (status code, etc.)

[0451] Specific examples of operation:

[0452] api_url = 'https: / / api.company.com / advice'

[0453] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[0454] response = requests.post(api_url, json=payload)

[0455] Step 5: Feedback Input

[0456] User actions:

[0457] Sales representatives (users) input feedback from their terminals. This feedback includes the results of proposals and customer reactions.

[0458] Input: Feedback content

[0459] Output: Feedback data

[0460] Specific examples of operation:

[0461] The user enters their feedback into a form on their device and presses the submit button.

[0462] Step 6: Gathering Feedback

[0463] Device operation:

[0464] The terminal receives user input and sends it to the server. The feedback is sent in JSON format.

[0465] Input: Feedback content

[0466] Output: Feedback submission result (status code, etc.)

[0467] Specific examples of operation:

[0468] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[0469] response = requests.post(api_url, json=feedback)

[0470] Step 7: Emotion Analysis

[0471] How the emotion engine works:

[0472] The emotion engine analyzes the user's voice and facial expressions to recognize their emotions. The analysis results are sent to the server.

[0473] Input: User voice data, facial expression data

[0474] Output: Emotion analysis results

[0475] Specific examples of operation:

[0476] emotion_data = {'stress_level': 'high', 'emotion': 'anxiety'}

[0477] response = requests.post(emotion_api_url, json=emotion_data)

[0478] Step 8: Advice Adjustment

[0479] Server operation:

[0480] The server dynamically adjusts the content and wording of the advice it provides based on the sentiment analysis results.

[0481] Input: Sentiment analysis results

[0482] Output: Adjusted advice

[0483] Specific examples of operation:

[0484] If the emotion analysis reveals that the sales representative is experiencing stress, the message will be adjusted to, "We recommend proposing the new product to customer A in May. Proceed at your own pace."

[0485] Step 9: Feedback Analysis and System Improvement

[0486] Server operation:

[0487] The server analyzes the collected feedback data to improve the system. It updates the analysis algorithm as needed and formulates the next strategy.

[0488] Input: Feedback data

[0489] Output: Updated analysis algorithm, next strategy planning

[0490] Specific examples of operation:

[0491] feedback_df = pd.read_sql(feedback_query, connection)

[0492] model = train_model(feedback_df)

[0493] save_model(model, 'strategy_model.pkl')

[0494] (Application Example 2)

[0495] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0496] In sales activities, it is difficult to grasp customer emotions in real time and provide appropriate advice based on them. Furthermore, there is still a lack of systems for continuously improving advice while collecting feedback. By solving these challenges, it is necessary to improve the performance of sales members and increase customer satisfaction.

[0497] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the user's emotions; means for adjusting the individual advice based on the analyzed emotion data; and means for displaying the adjusted advice to the user. This makes it possible to analyze customer emotions in real time and provide appropriate advice that meets individual needs.

[0498] A "database" is a system for storing, managing, and providing data such as customer information, sales data, and records of sales activities.

[0499] A "collection tool" is a device or program that has the function of obtaining necessary information from a database and sending it to a server for analysis.

[0500] "Analysis tools" refer to devices or programs that process collected data and have the function of analyzing customers' economic conditions and market trends.

[0501] "Generation means" refers to a device or program that has the function of creating individual advice for each sales member based on the analyzed data.

[0502] "Distribution method" refers to a device or program that has the function of sending the generated individual advice to each sales member's terminal.

[0503] A "feedback collection method" refers to a device or program that has the function of collecting feedback provided by sales members on a server.

[0504] An "emotion analysis tool" is a device or program that has the function of analyzing a user's voice and facial expressions to recognize their emotions.

[0505] An "advice adjustment tool" is a device or program that has the function of adjusting the content of individual advice based on analyzed emotional data.

[0506] "Display means" refers to a device or program that has the function of displaying adjusted advice to the user visually or audibly.

[0507] The system for implementing this invention consists of a server, a terminal, and an emotion analysis engine. The server collects customer information, sales data, and records of sales activities from a database, and analyzes this data to understand the customer's economic situation and market trends. Furthermore, it generates individual advice for each sales member based on the analysis results and delivers this advice to the terminal. The terminal displays the advice delivered from the server and collects feedback from the sales member. The emotion analysis engine analyzes the user's voice and facial expressions to recognize their emotions, and the server adjusts the content of the advice based on this.

[0508] Hardware and software to be used

[0509] Server: The server connects to the database and uses Python and SQL to collect, analyze, and generate advice. It also sends the collected feedback to the database in real time using Apache® Kafka or similar tools.

[0510] Device: The device uses smart glasses or a tablet to display advice from the server in real time via a web browser or a dedicated application.

[0511] Emotion Analysis Engine: Uses OpenCV and TensorFlow to recognize emotions from user voice and facial expressions. Data is collected using devices such as cameras and microphones.

[0512] Processing flow

[0513] 1. The server collects customer information, sales data, and records of sales activities from the database.

[0514] 2. The server analyzes the collected data to understand the customer's economic situation and market trends.

[0515] 3. Based on the analysis results, the server generates individual advice for each sales member.

[0516] 4. The generated advice is delivered to the sales team members' devices.

[0517] 5. The emotion analysis engine analyzes the user's voice and facial expressions and sends that data to the server.

[0518] 6. The server adjusts the advice based on sentiment data and displays the content on the terminal.

[0519] 7. Sales members implement the advice and input the results as feedback into their terminals.

[0520] 8. The server collects feedback and incorporates it into the next strategy.

[0521] Specific example

[0522] For example, when sales member A wears smart glasses and interacts with customer B, the emotion analysis engine analyzes customer B's facial expressions in real time. If the analysis indicates that customer B is dissatisfied, the server generates advice appropriate to the situation, providing words of encouragement or suggestions for additional proposals. Sales member A adjusts their response based on this and inputs the outcome of the negotiation as feedback, allowing the server to update the data for future strategic planning.

[0523] Example of a prompt

[0524] "I'm designing a system that analyzes customer emotions in real time and provides appropriate advice to sales team members. This system uses smart glasses to analyze customer emotions from their facial expressions. Based on the collected data, it generates appropriate advice to support sales team members' responses. Please provide a detailed design incorporating specific examples."

[0525] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0526] Step 1:

[0527] The server collects customer information, sales data, and records of sales activities from the database. The collected data is then stored in the server's memory. The input is information from the database, and the output is aggregated data stored within the server.

[0528] Step 2:

[0529] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis is performed using Python and SQL, employing algorithms such as linear regression and time series analysis. The input for this step is the data collected in step 1, and the output is presented in the form of analysis reports and graphs.

[0530] Step 3:

[0531] The server generates personalized advice for each sales member based on the analysis results. This is done using a generative AI model, which extracts specific suggestions from the analysis report that will lead to improved performance for each sales member. The input for this step is the analysis results, and the output is personalized advice.

[0532] Step 4:

[0533] The server delivers the generated individual advice to each sales member's terminal. The advice is transmitted via API and received by the sales members in real time. The input is the generated advice, and the output is the information displayed on the sales member's terminal.

[0534] Step 5:

[0535] The emotion analysis engine analyzes the user's voice and facial expressions and sends the data to the server. The analysis is performed using OpenCV and TensorFlow, and an emotion recognition model is applied. The input for this step is voice and facial expression data collected by the camera and microphone, and the output is recognized emotion data.

[0536] Step 6:

[0537] The server adjusts the advice based on sentiment data. It combines the generated advice with the sentiment data to regenerate the optimal advice. The input is the generated individual advice and sentiment data, and the output is the adjusted advice that takes sentiment into account.

[0538] Step 7:

[0539] The device displays adjusted advice to the user. This is shown in real time on a display such as smart glasses or a tablet. The input is the adjusted advice, and the output is information provided visually or audibly.

[0540] Step 8:

[0541] Sales team members implement the advice and input the results as feedback into their terminals. This feedback is sent to the server and used for generating future advice and developing strategies. The input is feedback from the sales team members, and the output is new data collected by the server.

[0542] Step 9:

[0543] The server updates its analysis algorithm based on the collected feedback and incorporates it into the next strategy formulation. The algorithm improves through continuous learning from the data. The input for this step is the feedback data, and the output is the updated analysis algorithm.

[0544] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0545] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0546] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0547] [Second Embodiment]

[0548] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0549] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0550] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0551] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0552] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0553] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0554] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0555] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0556] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0557] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0558] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0559] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0560] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[0561] Server Role

[0562] The server is the central hub of the system and performs the following main functions:

[0563] 1. Data collection:

[0564] The server collects customer information, sales data, and records of sales activities from the database. This data forms the basis for analyzing the performance of individual sales members and the entire team.

[0565] 2. Data Analysis:

[0566] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis results form the basis for the individual advice provided to each sales member.

[0567] 3. Generate personalized advice:

[0568] Based on the analysis results, the server generates specific advice for each sales member. This advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[0569] 4. Distribution of advice:

[0570] The generated personalized advice is delivered to each sales member's terminal by the server. This allows sales members to receive the latest information in real time.

[0571] 5. Gathering feedback:

[0572] The server collects feedback from each sales member and stores it in a database. This feedback is used for the continuous improvement of the system.

[0573] 6. Update of the analysis algorithm:

[0574] The server analyzes the collected feedback and updates its analysis algorithm to make the next advice more accurate.

[0575] Terminal role

[0576] The terminal is a device used by each sales member and provides the following functions:

[0577] 1. Displaying data:

[0578] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access the information when needed.

[0579] 2. Feedback Input:

[0580] Each sales member enters feedback using their own device. The entered feedback is sent to the server and stored in the database.

[0581] User roles

[0582] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[0583] 1. Implement the advice:

[0584] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[0585] 2. Providing feedback:

[0586] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[0587] Specific example

[0588] For example, a server analyzes the sales data of a certain company (customer A) over the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice that "a new product enhancement proposal should be made starting in May" and delivers it to sales member B's terminal. When B submits a new product proposal to customer A in May and inputs the result as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy.

[0589] In this way, the system can respond to the individual needs of sales members and effectively plan and execute the team's overall strategy.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] Database connection

[0593] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[0594] Step 2:

[0595] Data acquisition

[0596] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[0597] Step 3:

[0598] Data organization

[0599] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[0600] Step 4:

[0601] Data Analysis

[0602] Server: Inputs data into the data analysis engine to analyze customer economic conditions, market trends, and sales trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[0603] Step 5:

[0604] Individual advice generation

[0605] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[0606] Step 6:

[0607] Advice distribution

[0608] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[0609] Step 7:

[0610] Data display

[0611] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[0612] Step 8:

[0613] Sales activities

[0614] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[0615] Step 9:

[0616] Feedback Input

[0617] User: Enters sales activity results and new customer information into the terminal. The entered information is sent to the server.

[0618] Step 10:

[0619] Save feedback

[0620] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[0621] Step 11:

[0622] Feedback analysis

[0623] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[0624] Step 12:

[0625] Algorithm update

[0626] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[0627] Step 13:

[0628] Strategic Planning

[0629] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[0630] (Example 1)

[0631] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0632] In sales activities, there is a need to efficiently collect individual advice and feedback from each sales member and improve the accuracy of analysis algorithms. Furthermore, it is necessary to utilize generative AI models to develop more effective sales strategies and enable real-time information sharing.

[0633] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0634] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for inputting prompt sentences to a generating AI model to obtain appropriate advice; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for updating the analysis algorithm based on the collected feedback data; and means for applying the updated analysis algorithm to the next analysis. This improves the quality of individual advice for sales members and enables improved analysis accuracy based on feedback. Furthermore, it enables the formulation of effective sales strategies utilizing the generating AI model and real-time information sharing.

[0635] A "database" is a digital system for systematically organizing and storing information, and it allows for the addition, deletion, searching, and updating of data through queries.

[0636] "Customer information" refers to data about a specific customer, including name, address, purchase history, and contact information.

[0637] "Sales data" refers to information regarding the sale of goods or services during a specific period, including sales amount, transaction date and time, and purchased items.

[0638] "Sales activity records" refer to the history of all business activities performed by sales members, including customer visits, negotiation details, and contract status.

[0639] "Analysis" refers to the process of using collected data to reveal its meaning, trends, and patterns.

[0640] "Individualized advice" refers to behavioral guidelines and strategic proposals provided individually to specific sales members.

[0641] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning techniques to generate new information or suggestions from input data.

[0642] A "prompt" refers to the input text given to a generative AI model in order to generate the requested output.

[0643] "Feedback" refers to the act of sales team members providing the results of their activities and the information they have gathered, as well as the content of that feedback.

[0644] An "analysis algorithm" refers to a computational method used to analyze data and generate output for a specific purpose.

[0645] A "device" refers to a digital device used by a user, and includes personal computers, tablets, smartphones, and other similar devices.

[0646] The system according to the present invention is designed to effectively support individualized advice to sales members and the strategies of departments and teams. Specific embodiments are described below.

[0647] Server Role

[0648] The server plays a central role in the system and performs multiple functions. First, it collects customer information, sales data, and records of sales activities from the database. The databases used include SQL Server and Oracle Database. By collecting this data, a foundation is built for analyzing the performance of individual sales members and the entire team.

[0649] Next, the collected data is analyzed using Python or R. Specifically, the data is processed using libraries such as Pandas and NumPy, and a model is built using the Scikit-learn machine learning library. For example, this data analysis is performed to predict which customers a sales team should act towards during a specific period.

[0650] Based on the generated analysis results, the server uses a generative AI model to generate personalized advice for each sales member. The generative AI model used here is GPT-3, for example. For instance, by entering a prompt such as, "Please suggest a sales pitch to use in the next business meeting," appropriate advice will be generated.

[0651] The generated personalized advice is delivered to each sales member's terminal via a REST API. The terminal receives an HTTP POST request and displays the advice in JSON format. This implementation allows sales members to obtain the latest information in real time.

[0652] The server collects feedback provided by sales members. This feedback includes sales activity results and new customer information. The feedback is then analyzed again and used for continuous system improvement and updating of the analysis algorithms.

[0653] Finally, the analysis algorithm is updated based on the collected feedback data. This update includes retraining the machine learning model, which will be reflected in the next analysis.

[0654] Terminal role

[0655] The terminal is a device used by each sales member and primarily provides the following functions. First, it displays individual advice and analysis results delivered from the server. Sales members can refer to specific advice by looking at the terminal screen. For example, it displays information such as when and what products should be proposed to a particular customer.

[0656] The terminal also provides a means for sales members to input feedback. Feedback is entered through forms and text boxes and sent to the server. The data is sent as an HTTP POST request and parsed on the server.

[0657] User roles

[0658] Users, i.e., sales members, use the system to conduct sales activities. Based on the advice displayed on the terminal, users carry out specific sales actions. For example, they might submit proposals to specific customers or follow up at the appropriate time. They also input the results of their sales activities and newly acquired customer information as feedback into the terminal and provide it to the system. This further improves the accuracy of the system and helps in future analyses.

[0659] Specific example

[0660] For example, a server analyzes the past two years of sales data for a company (customer A) and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should propose enhanced new products starting in May" and delivers it to the sales team members' terminals. When the sales team members submit a proposal for the new products to customer A in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm. Using this updated algorithm in the next analysis allows for more accurate advice.

[0661] Examples of prompts for generative AI models

[0662] For example, the following prompt statement is used:

[0663] "Analyze customer A's sales data for the past two years to identify which season has the highest sales. Based on these results, generate appropriate sales activity advice."

[0664] By using these prompts, the generative AI model can perform appropriate analysis and generate advice. This system functions by internally generating these prompts, which are then executed by the server.

[0665] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0666] Step 1: Data Collection

[0667] Subject: Server

[0668] Specific actions:

[0669] The server collects data from databases such as SQL Server and Oracle Database. Specifically, it collects customer information, sales data, and records of sales activities. For example, the server issues an SQL query like this: "SELECT FROM sales_data WHERE year = 2022". Based on this input query, the relevant sales data is extracted from the database.

[0670] Input: SQL query

[0671] Output: Results of the SQL query (customer information, sales data, sales activity records)

[0672] Step 2: Data Analysis

[0673] Subject: Server

[0674] Specific actions:

[0675] The server analyzes the collected data using Python or R. It preprocesses the data using libraries such as Pandas and NumPy, and builds machine learning models using libraries such as Scikit-learn. For example, the server uses Pandas to convert the data into a DataFrame and uses a linear regression model to forecast sales.

[0676] Input: Data collected from the database

[0677] Output: Analysis results from the model (e.g., monthly sales forecast)

[0678] Step 3: Generate personalized advice

[0679] Subject: Server

[0680] Specific actions:

[0681] Based on the results of data analysis, the server sends prompt messages to the generating AI model to generate appropriate advice. For example, it might input the prompt message, "Please suggest a sales pitch to use in the next business meeting," into the generating AI model. Based on this input, the generating AI model will generate a sales pitch and proposal to use in the next business meeting.

[0682] Input: Analysis result, prompt message

[0683] Output: Advice from a generative AI model

[0684] Step 4: Delivering advice

[0685] Subject: Server

[0686] Specific actions:

[0687] The server distributes the generated individual advice to each sales member's terminal. Using a REST API, it sends HTTP POST requests to the sales member's terminal, delivering the advice in JSON format. For example, the server sends the advice to the " / advice" endpoint.

[0688] Input: Generated advice

[0689] Output: Notification on the device where the advice was delivered.

[0690] Step 5: Gathering Feedback

[0691] Subject: terminal

[0692] Specific actions:

[0693] Each sales member uses a terminal to input feedback such as the results of their sales activities and new customer information. For example, a sales member might input feedback such as "I proposed a new product to customer A and received a positive response," and send it to the server. The terminal sends this feedback to the server via an HTTP POST request.

[0694] Input: Results of sales activities and new customer information

[0695] Output: Feedback is sent to the server and stored in the database.

[0696] Step 6: Updating the analysis algorithm

[0697] Subject: Server

[0698] Specific actions:

[0699] The server updates its analysis algorithm based on the collected feedback data. Specifically, it retrains the machine learning model using the new feedback data. For example, it retrains the model with the new data using the "fit" method of Scikit-learn. This update ensures that a more accurate algorithm is applied in the next analysis.

[0700] Input: Feedback data

[0701] Output: Updated analysis algorithm

[0702] (Application Example 1)

[0703] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0704] Traditional sales support systems have low accuracy in providing individual customer proposals and advice, and furthermore, manual intervention is required to improve the provided advice. Therefore, there is a need for a more efficient and automated way to improve the accuracy of individual advice. However, these systems have limitations in how they can effectively utilize user purchase data and feedback, making it difficult to maximize sales efficiency. Therefore, a system is needed that analyzes user purchase patterns and automatically generates optimal proposals.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0706] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the collected feedback data and retraining the analysis algorithm; and means for improving the accuracy of subsequent individual advice using the retrained analysis algorithm. This makes it possible to generate individual proposals based on the user's purchasing data and economic situation and deliver those proposals to the user's smart device.

[0707] A "database" is a system for centrally managing and storing various types of data, such as customer information, sales data, and records of sales activities.

[0708] An "analysis algorithm" is a set of procedures and calculation methods used to analyze collected data and find specific patterns or trends.

[0709] "Feedback" refers to information such as results reports, evaluations, and opinions provided by sales members and users, which is useful for improving the system.

[0710] "Individualized advice" refers to customized proposals and strategies provided to specific sales members or users based on analysis results.

[0711] A "smart device" is an electronic device with advanced functions that a user can carry or wear, and includes smartphones, tablets, smartwatches, and other similar devices.

[0712] "Purchase data" refers to a detailed record of products and services that a user has purchased in the past, including information such as the date of purchase, place of purchase, and purchase amount.

[0713] "Data collection methods" refer to processes and technologies for automatically acquiring necessary data from databases or external systems.

[0714] "Delivery methods" refer to the methods and technologies used to efficiently deliver generated personalized advice and suggestions to users or sales members. Specifically, this includes push notifications, email distribution, and dashboard displays.

[0715] "Retraining" is the process of updating existing analysis algorithms based on newly obtained feedback and data to obtain more accurate and effective results.

[0716] "Retraining methods" refer to methods and techniques for retraining analytical algorithms, and this includes updating machine learning models with new data.

[0717] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[0718] Server Role

[0719] The server is the central hub of the system and performs the following main functions:

[0720] 1. Data collection methods

[0721] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it retrieves information from various databases and external systems using SQL and REST APIs.

[0722] 2. Data Analysis Methods

[0723] The server cleanses the collected data using Pandas and Scikit-learn and analyzes the customer's economic situation and market trends. This allows it to understand the user's purchasing patterns and trends, and based on the results, it generates personalized advice.

[0724] 3. Individual advice generation means

[0725] The server generates specific advice for each sales member based on the analysis results. The advice is constructed in natural language using Python and the Natural Language Toolkit (NLTK).

[0726] 4. Methods for delivering advice

[0727] The generated personalized advice is delivered in real time to each sales member's device via the server using Firebase Cloud Messaging (FCM) or the Email API.

[0728] 5. Methods for collecting feedback

[0729] The server collects feedback from each sales member and stores it in a database. The collected feedback data is stored within the system using Firebase Analytics and REST APIs.

[0730] 6. Methods for retraining analysis algorithms

[0731] The server analyzes the collected feedback data and updates its analysis algorithm by retraining it using TensorFlow or Keras. This improves the accuracy of individual advice in subsequent sessions.

[0732] Terminal role

[0733] The terminal is a device used by each sales member and provides the following functions:

[0734] 1. Data display means

[0735] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access information when needed.

[0736] 2. Feedback Input Means

[0737] Sales team members enter feedback using their own devices. The entered feedback is sent to the server and stored in the database.

[0738] User roles

[0739] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[0740] 1. Implement the advice

[0741] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[0742] 2. Providing feedback

[0743] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[0744] Specific example

[0745] For example, a server analyzes a company's sales data for the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should start promoting enhanced new products from May" and delivers it to the sales team members' terminals. When the sales team members actually propose the new products to customers in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. This process further improves the accuracy of future proposals.

[0746] Example of a prompt

[0747] "Based on the user's purchase history and payment data, predict when they will make their next purchase and generate coupon suggestions tailored to their specific needs. Use the following information as a basis:"

[0748] User ID: 12345

[0749] Purchase history over the past 6 months: [Groceries, Electronics, Clothing]

[0750] Payment data: High-value purchases made on the 25th of each month.

[0751] User's financial situation: Stable

[0752] Example of a proposal format: 'We will distribute a special sale coupon around the 25th.'

[0753] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0754] Step 1: Data Collection

[0755] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it uses SQL and REST APIs to query and collect the necessary information from the database. This inputs customer purchase history and financial status information into the server.

[0756] Input: Customer information, sales data, and records of sales activities from the database.

[0757] Output: Collected customer information, sales data, and records of sales activities.

[0758] Specific actions:

[0759] Retrieve customer information from the database using SQL queries.

[0760] Sales data is collected from external systems via API requests.

[0761] Step 2: Data Analysis

[0762] The server uses the collected data to analyze customers' economic situations and market trends. It cleanses the data and extracts features using Python's Pandas and Scikit-learn. Furthermore, it performs data analysis using machine learning algorithms.

[0763] Input: Collected customer information, sales data, and records of sales activities.

[0764] Output: Data analysis results (customer's economic situation, purchasing patterns, trends)

[0765] Specific actions:

[0766] Use Pandas to cleanse data and handle missing values ​​and invalid data.

[0767] We will analyze customer purchasing patterns using Scikit-learn's machine learning algorithms.

[0768] Step 3: Generate personalized advice

[0769] The server generates personalized advice for each sales member based on the results of data analysis. Using Python and the Natural Language Processing (NLTK) library, a generative AI model constructs the advice in natural language.

[0770] Input: Data analysis results

[0771] Output: Individual advice (suggestions expressed in natural language)

[0772] Specific actions:

[0773] Based on the analysis results, an AI model is used to automatically generate advice.

[0774] Using NLTK, the generated advice is expressed in natural language.

[0775] Step 4: Delivering advice

[0776] The server distributes the generated personalized advice to each sales member's terminal. The advice is delivered via push notifications or email using Firebase Cloud Messaging (FCM) or the Email API.

[0777] Input: Individual advice

[0778] Output: Advice delivered to sales team members' terminals.

[0779] Specific actions:

[0780] Use FCM to send push notifications to sales team members' smart devices.

[0781] We will use the Email API to deliver personalized advice via email.

[0782] Step 5: Gathering Feedback

[0783] Each sales member enters feedback using their own device and sends it to the server. The server collects the feedback data via Firebase Analytics and REST APIs and stores it in a database.

[0784] Input: Feedback provided by sales members

[0785] Output: Collected feedback data

[0786] Specific actions:

[0787] Sales team members enter feedback into their terminals.

[0788] Feedback data is sent to the server via Firebase Analytics.

[0789] Step 6: Retrain the analysis algorithm

[0790] The server analyzes the collected feedback data and retrains its analysis algorithms using TensorFlow and Keras. This improves the accuracy of individual advice provided in subsequent sessions.

[0791] Input: Collected feedback data

[0792] Output: Retrained analysis algorithm

[0793] Specific actions:

[0794] The collected feedback data is cleansed and analyzed.

[0795] The analysis algorithm will be retrained using TensorFlow or Keras.

[0796] Through these steps, a system is implemented that involves the coordination of servers, terminals, and users, making it possible to improve the accuracy of individual advice.

[0797] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0798] The system according to the present invention, in addition to functions for collecting and analyzing customer information, sales data, and records of sales activities, recognizes user emotions by combining them with an emotion engine and provides appropriate advice. This system comprises a server, terminals, and an emotion engine, each playing a specific role.

[0799] Server Role

[0800] Servers are the central components of a system and are responsible for the following main functions:

[0801] 1. Data collection:

[0802] The server connects to the database to retrieve customer information, sales data, and records of sales activities. This provides a foundation for analyzing the performance of individual sales members and the entire team.

[0803] 2. Data Analysis:

[0804] The server analyzes the collected data to understand the customer's economic situation, market trends, and sales trends. The analysis results help generate personalized advice.

[0805] 3. Generate personalized advice:

[0806] Based on the data analysis results, the server generates personalized advice for each sales member. The generated advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[0807] 4. Advice distribution:

[0808] The server distributes the generated personalized advice to each sales member's terminal, providing information in real time.

[0809] 5. Gathering and analyzing feedback:

[0810] The server collects feedback entered by each sales member and uses it to continuously improve the system. It also analyzes this feedback and updates the analysis algorithms.

[0811] Terminal role

[0812] The terminal is a device used by sales members and provides the following functions:

[0813] 1. Data display:

[0814] The terminal displays personalized advice and analysis results delivered from the server, providing users with information in real time.

[0815] 2. Feedback Input:

[0816] Users input feedback using their devices and send it to the server.

[0817] The role of the emotional engine

[0818] The emotion engine is responsible for recognizing the user's emotions, which are built into the system.

[0819] 1. Speech analysis:

[0820] The emotion engine analyzes the user's voice input and recognizes their emotions. The recognized emotions are sent to the server and used to generate advice.

[0821] 2. Facial expression analysis:

[0822] The emotion engine collects user facial expression data through the camera and analyzes emotions. This allows for a more accurate recognition of the user's emotional state.

[0823] 3. Adjusting the advice:

[0824] The server adjusts the content and wording of the personalized advice it provides based on the emotional data recognized by the emotion engine. This process ensures that more personalized and effective advice is delivered.

[0825] Specific example

[0826] For example, the server analyzes the past two years of sales data for a specific customer (Customer A) and identifies seasonal fluctuations. Based on this data, the server generates advice such as "We should propose enhanced new products starting in May" and delivers it to sales member B's terminal. At that time, the emotion engine analyzes B's emotional state, and if B is feeling stressed, it provides the advice with more encouraging words.

[0827] When B submits a new product proposal to customer A in May and inputs the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. In this way, the system can respond to the individual needs and emotional states of sales members and effectively plan and execute the team's overall strategy.

[0828] The following describes the processing flow.

[0829] Step 1:

[0830] Database connection

[0831] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[0832] Step 2:

[0833] Data acquisition

[0834] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[0835] Step 3:

[0836] Data organization

[0837] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[0838] Step 4:

[0839] Data Analysis

[0840] Server: Inputs data into the data analysis engine to analyze customer economic conditions, sales trends, and market trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[0841] Step 5:

[0842] Individual advice generation

[0843] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[0844] Step 6:

[0845] Preparation for emotional analysis

[0846] Terminal: The sales team member's terminal activates the emotion engine and begins collecting voice and facial expression data. It prepares to acquire user emotion data via the camera and microphone.

[0847] Step 7:

[0848] Emotion analysis

[0849] Emotion Engine: Analyzes the user's (sales member's) voice input and facial expression data to recognize their emotional state. Specific emotions (stress, joy, anger, etc.) are detected.

[0850] Step 8:

[0851] Advice adjustment

[0852] Server: Based on the emotional data recognized by the emotion engine, the server adjusts the content and expression of the personalized advice it provides. This process generates more personalized and effective advice.

[0853] Step 9:

[0854] Advice distribution

[0855] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[0856] Step 10:

[0857] Data display

[0858] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[0859] Step 11:

[0860] Sales activities

[0861] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[0862] Step 12:

[0863] Feedback Input

[0864] User: Inputs sales activity results, new customer information, and changes in emotional state into the terminal. The entered information is sent to the server.

[0865] Step 13:

[0866] Save feedback

[0867] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[0868] Step 14:

[0869] Feedback analysis

[0870] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[0871] Step 15:

[0872] Algorithm update

[0873] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[0874] Step 16:

[0875] Strategic Planning

[0876] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[0877] (Example 2)

[0878] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0879] Traditional sales support systems can collect and analyze customer and sales data, but they lack the functionality to provide effective, personalized advice based on this data. Furthermore, they lack adequate mechanisms for incorporating feedback from sales representatives, making continuous system improvement and sophisticated strategic planning difficult. Additionally, they fail to provide advice that takes into account the emotions of sales representatives, thus failing to contribute to increased motivation and more effective sales activities.

[0880] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0881] In this invention, the server includes means for acquiring customer data, sales information, and sales activity history from a data management system; means for analyzing the acquired data to evaluate the customer's economic status and market trends; means for generating individual advice for each sales representative based on the evaluation results; means for transferring the generated individual advice to each sales representative's device; means for collecting feedback provided by each sales representative and improving the advice and strategy; means for analyzing the user's emotions through voice and facial expressions; and means for dynamically adjusting the expression of the advice based on the analysis results. As a result, individual advice is provided taking into account the emotional state of the sales representative, and the system is constantly improved based on feedback, enabling more effective sales activities and strategic planning.

[0882] A "data management system" is a general term for software or hardware used to centrally collect, store, and manage customer data, sales information, and sales activity history.

[0883] "Customer data" refers to information about a customer, such as their name, contact information, purchase history, and financial status.

[0884] "Sales information" refers to data related to the sale of a product, including information such as sales figures and sales quantities for a specific period.

[0885] "Sales activity history" refers to a record of various sales activities carried out by a sales representative, including information such as visit history, negotiation details, and feedback.

[0886] "Means of acquisition" refers to mechanisms or methods for automatically retrieving necessary data from a database or external system.

[0887] "Means of analysis" refers to methods and systems for analyzing data using statistical and machine learning techniques to evaluate customers' economic status and market trends.

[0888] "Evaluation results" refer to information obtained from the analysis, including the customer's economic situation and market trends.

[0889] "Means for generating personalized advice" refers to systems and methods that automatically generate optimal proposals and action plans for sales representatives based on customer data and evaluation results.

[0890] "Transferring means" refers to the communication methods and protocols used to send the generated personalized advice to the sales representative's device.

[0891] "Provided feedback" refers to information that sales representatives record regarding the results of their actual sales activities and customer reactions, and then input into the system.

[0892] "Means for improving advice and strategies" refers to mechanisms and methods for analyzing the feedback received and formulating and improving new advice and strategies.

[0893] "Means of analyzing emotions through voice and facial expressions" refers to technologies and systems that analyze the voice and facial expressions of sales representatives to identify their emotional state.

[0894] "Means of dynamic adjustment" refers to mechanisms and methods that adjust the content and expression of generated advice in real time based on the results of emotion analysis.

[0895] The system according to the present invention is a system that collects and analyzes customer data, sales information, and sales activity history, and provides appropriate advice through sentiment analysis. This system comprises a server, terminals, and a sentiment analysis engine, each of which plays the following specific roles.

[0896] Server Role

[0897] Server processing:

[0898] The server retrieves customer data, sales information, and sales activity history from the data management system. This process uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server retrieves this data via SQL queries and extracts it from the database as follows:

[0899] Specific example:

[0900] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[0901] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[0902] SELECT FROM activities WHERE type = 'sales_visit';

[0903] Data analysis:

[0904] The server uses the Python Pandas library to analyze the collected data. This analysis includes data cleaning, formatting, and aggregation, which is used to evaluate the customers' economic status and market trends.

[0905] Specific example:

[0906] df_customers = pd.read_sql(query_customers, connection)

[0907] df_sales = pd.read_sql(query_sales, connection)

[0908] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[0909] Generate personalized advice:

[0910] Based on the analysis results, the server generates personalized advice for each sales representative. This generation process uses Python's Pandas and NumPy libraries.

[0911] Specific example:

[0912] The system generates advice such as, "It would be effective to propose a new product to customer A in May."

[0913] Advice delivery:

[0914] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[0915] Specific example:

[0916] api_url = 'https: / / api.company.com / advice'

[0917] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[0918] response = requests.post(api_url, json=payload)

[0919] Gathering and analyzing feedback:

[0920] Each sales representative enters feedback and sends it to the server via their terminal. This feedback is collected and analyzed on the server side and used to improve the system.

[0921] Specific example:

[0922] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[0923] response = requests.post(api_url, json=feedback)

[0924] The server updates its machine learning model based on feedback and incorporates it into future strategy planning. This utilizes tools such as scikit-learn and TensorFlow.

[0925] Terminal role

[0926] Data display:

[0927] The terminal displays personalized advice and analysis results received from the server, providing real-time information to sales representatives (users). This process utilizes React.js and Vue.js.

[0928] Feedback input:

[0929] Users enter feedback via their device and send it to the server. This feedback is sent using HTML forms and JavaScript.

[0930] The role of the emotional engine

[0931] Voice analysis:

[0932] The emotion engine analyzes the user's voice data to recognize emotions. This analysis uses the Google Cloud Speech-to-Text API and IBM Watson.

[0933] Facial expression analysis:

[0934] The emotion engine analyzes the user's facial expressions through the camera and identifies their emotional state. This process utilizes OpenCV and DeepFace.

[0935] Adjusting advice:

[0936] The server dynamically adjusts the content and wording of the advice provided to each sales representative based on emotional data obtained from the emotion engine.

[0937] Example of a prompt

[0938] "Analyze customer A's sales data for the past two years to identify seasonal sales fluctuations and generate optimal advice for determining the timing of the next proposal. Also, include flexible messaging that takes into account the emotional state of the sales representative making the proposal."

[0939] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0940] Step 1: Data Collection

[0941] Server operation:

[0942] The server connects to the data management system to retrieve customer data, sales information, and sales activity history. Specifically, it extracts data from databases such as MySQL and PostgreSQL using SQL queries.

[0943] Input: Database connection information, query for the required data.

[0944] Output: Extracted customer data, sales information, and sales activity history.

[0945] Specific examples of operation:

[0946] The server sends an SQL query to the database to retrieve data.

[0947] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[0948] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[0949] SELECT FROM activities WHERE type = 'sales_visit';

[0950] Step 2: Data Analysis

[0951] Server operation:

[0952] The server analyzes the acquired data using the Python Pandas library. It performs data cleaning, formatting, and aggregation to evaluate the customer's economic status and market trends.

[0953] Input: Data acquired in the data collection step

[0954] Output: Analysis results (customer's economic status, market trends, etc.)

[0955] Specific examples of operation:

[0956] df_customers = pd.read_sql(query_customers, connection)

[0957] df_sales = pd.read_sql(query_sales, connection)

[0958] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[0959] Step 3: Generate personalized advice

[0960] Server operation:

[0961] The server generates personalized advice for each sales representative based on the analysis results. This generation uses Python's Pandas and NumPy libraries.

[0962] Input: Analysis results

[0963] Output: Individual advice

[0964] Specific examples of operation:

[0965] Based on the analysis results, the system generates advice such as, "It would be effective to propose a new product to customer A in May."

[0966] Step 4: Delivering advice

[0967] Server operation:

[0968] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[0969] Input: Individual advice

[0970] Output: Delivery results (status code, etc.)

[0971] Specific examples of operation:

[0972] api_url = 'https: / / api.company.com / advice'

[0973] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[0974] response = requests.post(api_url, json=payload)

[0975] Step 5: Feedback Input

[0976] User actions:

[0977] Sales representatives (users) input feedback from their terminals. This feedback includes the results of proposals and customer reactions.

[0978] Input: Feedback content

[0979] Output: Feedback data

[0980] Specific examples of operation:

[0981] The user enters their feedback into a form on their device and presses the submit button.

[0982] Step 6: Gathering Feedback

[0983] Device operation:

[0984] The terminal receives user input and sends it to the server. The feedback is sent in JSON format.

[0985] Input: Feedback content

[0986] Output: Feedback submission result (status code, etc.)

[0987] Specific examples of operation:

[0988] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[0989] response = requests.post(api_url, json=feedback)

[0990] Step 7: Emotion Analysis

[0991] How the emotion engine works:

[0992] The emotion engine analyzes the user's voice and facial expressions to recognize their emotions. The analysis results are sent to the server.

[0993] Input: User voice data, facial expression data

[0994] Output: Emotion analysis results

[0995] Specific examples of operation:

[0996] emotion_data = {'stress_level': 'high', 'emotion': 'anxiety'}

[0997] response = requests.post(emotion_api_url, json=emotion_data)

[0998] Step 8: Advice Adjustment

[0999] Server operation:

[1000] The server dynamically adjusts the content and wording of the advice it provides based on the sentiment analysis results.

[1001] Input: Sentiment analysis results

[1002] Output: Adjusted advice

[1003] Specific examples of operation:

[1004] If the emotion analysis reveals that the sales representative is experiencing stress, the message will be adjusted to, "We recommend proposing the new product to customer A in May. Proceed at your own pace."

[1005] Step 9: Feedback Analysis and System Improvement

[1006] Server operation:

[1007] The server analyzes the collected feedback data to improve the system. It updates the analysis algorithm as needed and formulates the next strategy.

[1008] Input: Feedback data

[1009] Output: Updated analysis algorithm, next strategy planning

[1010] Specific examples of operation:

[1011] feedback_df = pd.read_sql(feedback_query, connection)

[1012] model = train_model(feedback_df)

[1013] save_model(model, 'strategy_model.pkl')

[1014] (Application Example 2)

[1015] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1016] In sales activities, it is difficult to grasp customer emotions in real time and provide appropriate advice based on them. Furthermore, there is still a lack of systems for continuously improving advice while collecting feedback. By solving these challenges, it is necessary to improve the performance of sales members and increase customer satisfaction.

[1017] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the user's emotions; means for adjusting the individual advice based on the analyzed emotion data; and means for displaying the adjusted advice to the user. This makes it possible to analyze customer emotions in real time and provide appropriate advice that meets individual needs.

[1018] A "database" is a system for storing, managing, and providing data such as customer information, sales data, and records of sales activities.

[1019] A "collection tool" is a device or program that has the function of obtaining necessary information from a database and sending it to a server for analysis.

[1020] "Analysis tools" refer to devices or programs that process collected data and have the function of analyzing customers' economic conditions and market trends.

[1021] "Generation means" refers to a device or program that has the function of creating individual advice for each sales member based on the analyzed data.

[1022] "Distribution method" refers to a device or program that has the function of sending the generated individual advice to each sales member's terminal.

[1023] A "feedback collection method" refers to a device or program that has the function of collecting feedback provided by sales members on a server.

[1024] An "emotion analysis tool" is a device or program that has the function of analyzing a user's voice and facial expressions to recognize their emotions.

[1025] An "advice adjustment tool" is a device or program that has the function of adjusting the content of individual advice based on analyzed emotional data.

[1026] "Display means" refers to a device or program that has the function of displaying adjusted advice to the user visually or audibly.

[1027] The system for implementing this invention consists of a server, a terminal, and an emotion analysis engine. The server collects customer information, sales data, and records of sales activities from a database, and analyzes this data to understand the customer's economic situation and market trends. Furthermore, it generates individual advice for each sales member based on the analysis results and delivers this advice to the terminal. The terminal displays the advice delivered from the server and collects feedback from the sales member. The emotion analysis engine analyzes the user's voice and facial expressions to recognize their emotions, and the server adjusts the content of the advice based on this.

[1028] Hardware and software to be used

[1029] Server: The server connects to the database and uses Python and SQL to collect, analyze, and generate advice. It also sends the collected feedback to the database in real time using Apache Kafka or similar tools.

[1030] Device: The device uses smart glasses or a tablet to display advice from the server in real time via a web browser or a dedicated application.

[1031] Emotion Analysis Engine: Uses OpenCV and TensorFlow to recognize emotions from user voice and facial expressions. Data is collected using devices such as cameras and microphones.

[1032] Processing flow

[1033] 1. The server collects customer information, sales data, and records of sales activities from the database.

[1034] 2. The server analyzes the collected data to understand the customer's economic situation and market trends.

[1035] 3. Based on the analysis results, the server generates individual advice for each sales member.

[1036] 4. The generated advice is delivered to the sales team members' devices.

[1037] 5. The emotion analysis engine analyzes the user's voice and facial expressions and sends that data to the server.

[1038] 6. The server adjusts the advice based on sentiment data and displays the content on the terminal.

[1039] 7. Sales members implement the advice and input the results as feedback into their terminals.

[1040] 8. The server collects feedback and incorporates it into the next strategy.

[1041] Specific example

[1042] For example, when sales member A wears smart glasses and interacts with customer B, the emotion analysis engine analyzes customer B's facial expressions in real time. If the analysis indicates that customer B is dissatisfied, the server generates advice appropriate to the situation, providing words of encouragement or suggestions for additional proposals. Sales member A adjusts their response based on this and inputs the outcome of the negotiation as feedback, allowing the server to update the data for future strategic planning.

[1043] Example of a prompt

[1044] "I'm designing a system that analyzes customer emotions in real time and provides appropriate advice to sales team members. This system uses smart glasses to analyze customer emotions from their facial expressions. Based on the collected data, it generates appropriate advice to support sales team members' responses. Please provide a detailed design incorporating specific examples."

[1045] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1046] Step 1:

[1047] The server collects customer information, sales data, and records of sales activities from the database. The collected data is then stored in the server's memory. The input is information from the database, and the output is aggregated data stored within the server.

[1048] Step 2:

[1049] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis is performed using Python and SQL, employing algorithms such as linear regression and time series analysis. The input for this step is the data collected in step 1, and the output is presented in the form of analysis reports and graphs.

[1050] Step 3:

[1051] The server generates personalized advice for each sales member based on the analysis results. This is done using a generative AI model, which extracts specific suggestions from the analysis report that will lead to improved performance for each sales member. The input for this step is the analysis results, and the output is personalized advice.

[1052] Step 4:

[1053] The server delivers the generated individual advice to each sales member's terminal. The advice is transmitted via API and received by the sales members in real time. The input is the generated advice, and the output is the information displayed on the sales member's terminal.

[1054] Step 5:

[1055] The emotion analysis engine analyzes the user's voice and facial expressions and sends the data to the server. The analysis is performed using OpenCV and TensorFlow, and an emotion recognition model is applied. The input for this step is voice and facial expression data collected by the camera and microphone, and the output is recognized emotion data.

[1056] Step 6:

[1057] The server adjusts the advice based on sentiment data. It combines the generated advice with the sentiment data to regenerate the optimal advice. The input is the generated individual advice and sentiment data, and the output is the adjusted advice that takes sentiment into account.

[1058] Step 7:

[1059] The device displays adjusted advice to the user. This is shown in real time on a display such as smart glasses or a tablet. The input is the adjusted advice, and the output is information provided visually or audibly.

[1060] Step 8:

[1061] Sales team members implement the advice and input the results as feedback into their terminals. This feedback is sent to the server and used for generating future advice and developing strategies. The input is feedback from the sales team members, and the output is new data collected by the server.

[1062] Step 9:

[1063] The server updates its analysis algorithm based on the collected feedback and incorporates it into the next strategy formulation. The algorithm improves through continuous learning from the data. The input for this step is the feedback data, and the output is the updated analysis algorithm.

[1064] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1065] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1066] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1067] [Third Embodiment]

[1068] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1069] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1070] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1071] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1072] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1073] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1074] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1075] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1076] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1077] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1078] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1079] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1080] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[1081] Server Role

[1082] The server is the central hub of the system and performs the following main functions:

[1083] 1. Data collection:

[1084] The server collects customer information, sales data, and records of sales activities from the database. This data forms the basis for analyzing the performance of individual sales members and the entire team.

[1085] 2. Data Analysis:

[1086] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis results form the basis for the individual advice provided to each sales member.

[1087] 3. Generate personalized advice:

[1088] Based on the analysis results, the server generates specific advice for each sales member. This advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[1089] 4. Distribution of advice:

[1090] The generated personalized advice is delivered to each sales member's terminal by the server. This allows sales members to receive the latest information in real time.

[1091] 5. Gathering feedback:

[1092] The server collects feedback from each sales member and stores it in a database. This feedback is used for the continuous improvement of the system.

[1093] 6. Update of the analysis algorithm:

[1094] The server analyzes the collected feedback and updates its analysis algorithm to make the next advice more accurate.

[1095] Terminal role

[1096] The terminal is a device used by each sales member and provides the following functions:

[1097] 1. Displaying data:

[1098] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access the information when needed.

[1099] 2. Feedback Input:

[1100] Each sales member enters feedback using their own device. The entered feedback is sent to the server and stored in the database.

[1101] User roles

[1102] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[1103] 1. Implement the advice:

[1104] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[1105] 2. Providing feedback:

[1106] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[1107] Specific example

[1108] For example, a server analyzes the sales data of a certain company (customer A) over the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice that "a new product enhancement proposal should be made starting in May" and delivers it to sales member B's terminal. When B submits a new product proposal to customer A in May and inputs the result as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy.

[1109] In this way, the system can respond to the individual needs of sales members and effectively plan and execute the team's overall strategy.

[1110] The following describes the processing flow.

[1111] Step 1:

[1112] Database connection

[1113] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[1114] Step 2:

[1115] Data acquisition

[1116] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[1117] Step 3:

[1118] Data organization

[1119] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[1120] Step 4:

[1121] Data Analysis

[1122] Server: Inputs data into the data analysis engine to analyze customer economic conditions, market trends, and sales trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[1123] Step 5:

[1124] Individual advice generation

[1125] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[1126] Step 6:

[1127] Advice distribution

[1128] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[1129] Step 7:

[1130] Data display

[1131] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[1132] Step 8:

[1133] Sales activities

[1134] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[1135] Step 9:

[1136] Feedback Input

[1137] User: Enters sales activity results and new customer information into the terminal. The entered information is sent to the server.

[1138] Step 10:

[1139] Save feedback

[1140] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[1141] Step 11:

[1142] Feedback analysis

[1143] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[1144] Step 12:

[1145] Algorithm update

[1146] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[1147] Step 13:

[1148] Strategic Planning

[1149] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[1150] (Example 1)

[1151] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1152] In sales activities, there is a need to efficiently collect individual advice and feedback from each sales member and improve the accuracy of analysis algorithms. Furthermore, it is necessary to utilize generative AI models to develop more effective sales strategies and enable real-time information sharing.

[1153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1154] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for inputting prompt sentences to a generating AI model to obtain appropriate advice; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for updating the analysis algorithm based on the collected feedback data; and means for applying the updated analysis algorithm to the next analysis. This improves the quality of individual advice for sales members and enables improved analysis accuracy based on feedback. Furthermore, it enables the formulation of effective sales strategies utilizing the generating AI model and real-time information sharing.

[1155] A "database" is a digital system for systematically organizing and storing information, and it allows for the addition, deletion, searching, and updating of data through queries.

[1156] "Customer information" refers to data about a specific customer, including name, address, purchase history, and contact information.

[1157] "Sales data" refers to information regarding the sale of goods or services during a specific period, including sales amount, transaction date and time, and purchased items.

[1158] "Sales activity records" refer to the history of all business activities performed by sales members, including customer visits, negotiation details, and contract status.

[1159] "Analysis" refers to the process of using collected data to reveal its meaning, trends, and patterns.

[1160] "Individualized advice" refers to behavioral guidelines and strategic proposals provided individually to specific sales members.

[1161] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning techniques to generate new information or suggestions from input data.

[1162] A "prompt" refers to the input text given to a generative AI model in order to generate the requested output.

[1163] "Feedback" refers to the act of sales team members providing the results of their activities and the information they have gathered, as well as the content of that feedback.

[1164] An "analysis algorithm" refers to a computational method used to analyze data and generate output for a specific purpose.

[1165] A "device" refers to a digital device used by a user, and includes personal computers, tablets, smartphones, and other similar devices.

[1166] The system according to the present invention is designed to effectively support individualized advice to sales members and the strategies of departments and teams. Specific embodiments are described below.

[1167] Server Role

[1168] The server plays a central role in the system and performs multiple functions. First, it collects customer information, sales data, and records of sales activities from the database. The databases used include SQL Server and Oracle Database. By collecting this data, a foundation is built for analyzing the performance of individual sales members and the entire team.

[1169] Next, the collected data is analyzed using Python or R. Specifically, the data is processed using libraries such as Pandas and NumPy, and a model is built using the Scikit-learn machine learning library. For example, this data analysis is performed to predict which customers a sales team should act towards during a specific period.

[1170] Based on the generated analysis results, the server uses a generative AI model to generate personalized advice for each sales member. The generative AI model used here is GPT-3, for example. For instance, by entering a prompt such as, "Please suggest a sales pitch to use in the next business meeting," appropriate advice will be generated.

[1171] The generated personalized advice is delivered to each sales member's terminal via a REST API. The terminal receives an HTTP POST request and displays the advice in JSON format. This implementation allows sales members to obtain the latest information in real time.

[1172] The server collects feedback provided by sales members. This feedback includes sales activity results and new customer information. The feedback is then analyzed again and used for continuous system improvement and updating of the analysis algorithms.

[1173] Finally, the analysis algorithm is updated based on the collected feedback data. This update includes retraining the machine learning model, which will be reflected in the next analysis.

[1174] Terminal role

[1175] The terminal is a device used by each sales member and primarily provides the following functions. First, it displays individual advice and analysis results delivered from the server. Sales members can refer to specific advice by looking at the terminal screen. For example, it displays information such as when and what products should be proposed to a particular customer.

[1176] The terminal also provides a means for sales members to input feedback. Feedback is entered through forms and text boxes and sent to the server. The data is sent as an HTTP POST request and parsed on the server.

[1177] User roles

[1178] Users, i.e., sales members, use the system to conduct sales activities. Based on the advice displayed on the terminal, users carry out specific sales actions. For example, they might submit proposals to specific customers or follow up at the appropriate time. They also input the results of their sales activities and newly acquired customer information as feedback into the terminal and provide it to the system. This further improves the accuracy of the system and helps in future analyses.

[1179] Specific example

[1180] For example, a server analyzes the past two years of sales data for a company (customer A) and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should propose enhanced new products starting in May" and delivers it to the sales team members' terminals. When the sales team members submit a proposal for the new products to customer A in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm. Using this updated algorithm in the next analysis allows for more accurate advice.

[1181] Examples of prompts for generative AI models

[1182] For example, the following prompt statement is used:

[1183] "Analyze customer A's sales data for the past two years to identify which season has the highest sales. Based on these results, generate appropriate sales activity advice."

[1184] By using these prompts, the generative AI model can perform appropriate analysis and generate advice. This system functions by internally generating these prompts, which are then executed by the server.

[1185] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1186] Step 1: Data Collection

[1187] Subject: Server

[1188] Specific actions:

[1189] The server collects data from databases such as SQL Server and Oracle Database. Specifically, it collects customer information, sales data, and records of sales activities. For example, the server issues an SQL query like this: "SELECT FROM sales_data WHERE year = 2022". Based on this input query, the relevant sales data is extracted from the database.

[1190] Input: SQL query

[1191] Output: Results of the SQL query (customer information, sales data, sales activity records)

[1192] Step 2: Data Analysis

[1193] Subject: Server

[1194] Specific actions:

[1195] The server analyzes the collected data using Python or R. It preprocesses the data using libraries such as Pandas and NumPy, and builds machine learning models using libraries such as Scikit-learn. For example, the server uses Pandas to convert the data into a DataFrame and uses a linear regression model to forecast sales.

[1196] Input: Data collected from the database

[1197] Output: Analysis results from the model (e.g., monthly sales forecast)

[1198] Step 3: Generate personalized advice

[1199] Subject: Server

[1200] Specific actions:

[1201] Based on the results of data analysis, the server sends prompt messages to the generating AI model to generate appropriate advice. For example, it might input the prompt message, "Please suggest a sales pitch to use in the next business meeting," into the generating AI model. Based on this input, the generating AI model will generate a sales pitch and proposal to use in the next business meeting.

[1202] Input: Analysis result, prompt message

[1203] Output: Advice from a generative AI model

[1204] Step 4: Delivering advice

[1205] Subject: Server

[1206] Specific actions:

[1207] The server distributes the generated individual advice to each sales member's terminal. Using a REST API, it sends HTTP POST requests to the sales member's terminal, delivering the advice in JSON format. For example, the server sends the advice to the " / advice" endpoint.

[1208] Input: Generated advice

[1209] Output: Notification on the device where the advice was delivered.

[1210] Step 5: Gathering Feedback

[1211] Subject: terminal

[1212] Specific actions:

[1213] Each sales member uses a terminal to input feedback such as the results of their sales activities and new customer information. For example, a sales member might input feedback such as "I proposed a new product to customer A and received a positive response," and send it to the server. The terminal sends this feedback to the server via an HTTP POST request.

[1214] Input: Results of sales activities and new customer information

[1215] Output: Feedback is sent to the server and stored in the database.

[1216] Step 6: Updating the analysis algorithm

[1217] Subject: Server

[1218] Specific actions:

[1219] The server updates its analysis algorithm based on the collected feedback data. Specifically, it retrains the machine learning model using the new feedback data. For example, it retrains the model with the new data using the "fit" method of Scikit-learn. This update ensures that a more accurate algorithm is applied in the next analysis.

[1220] Input: Feedback data

[1221] Output: Updated analysis algorithm

[1222] (Application Example 1)

[1223] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1224] Traditional sales support systems have low accuracy in providing individual customer proposals and advice, and furthermore, manual intervention is required to improve the provided advice. Therefore, there is a need for a more efficient and automated way to improve the accuracy of individual advice. However, these systems have limitations in how they can effectively utilize user purchase data and feedback, making it difficult to maximize sales efficiency. Therefore, a system is needed that analyzes user purchase patterns and automatically generates optimal proposals.

[1225] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1226] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the collected feedback data and retraining the analysis algorithm; and means for improving the accuracy of subsequent individual advice using the retrained analysis algorithm. This makes it possible to generate individual proposals based on the user's purchasing data and economic situation and deliver those proposals to the user's smart device.

[1227] A "database" is a system for centrally managing and storing various types of data, such as customer information, sales data, and records of sales activities.

[1228] An "analysis algorithm" is a set of procedures and calculation methods used to analyze collected data and find specific patterns or trends.

[1229] "Feedback" refers to information such as results reports, evaluations, and opinions provided by sales members and users, which is useful for improving the system.

[1230] "Individualized advice" refers to customized proposals and strategies provided to specific sales members or users based on analysis results.

[1231] A "smart device" is an electronic device with advanced functions that a user can carry or wear, and includes smartphones, tablets, smartwatches, and other similar devices.

[1232] "Purchase data" refers to a detailed record of products and services that a user has purchased in the past, including information such as the date of purchase, place of purchase, and purchase amount.

[1233] "Data collection methods" refer to processes and technologies for automatically acquiring necessary data from databases or external systems.

[1234] "Delivery methods" refer to the methods and technologies used to efficiently deliver generated personalized advice and suggestions to users or sales members. Specifically, this includes push notifications, email distribution, and dashboard displays.

[1235] "Retraining" is the process of updating existing analysis algorithms based on newly obtained feedback and data to obtain more accurate and effective results.

[1236] "Retraining methods" refer to methods and techniques for retraining analytical algorithms, and this includes updating machine learning models with new data.

[1237] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[1238] Server Role

[1239] The server is the central hub of the system and performs the following main functions:

[1240] 1. Data collection methods

[1241] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it retrieves information from various databases and external systems using SQL and REST APIs.

[1242] 2. Data Analysis Methods

[1243] The server cleanses the collected data using Pandas and Scikit-learn and analyzes the customer's economic situation and market trends. This allows it to understand the user's purchasing patterns and trends, and based on the results, it generates personalized advice.

[1244] 3. Individual advice generation means

[1245] The server generates specific advice for each sales member based on the analysis results. The advice is constructed in natural language using Python and the Natural Language Toolkit (NLTK).

[1246] 4. Methods for delivering advice

[1247] The generated personalized advice is delivered in real time to each sales member's device via the server using Firebase Cloud Messaging (FCM) or the Email API.

[1248] 5. Methods for collecting feedback

[1249] The server collects feedback from each sales member and stores it in a database. The collected feedback data is stored within the system using Firebase Analytics and REST APIs.

[1250] 6. Methods for retraining analysis algorithms

[1251] The server analyzes the collected feedback data and updates its analysis algorithm by retraining it using TensorFlow or Keras. This improves the accuracy of individual advice in subsequent sessions.

[1252] Terminal role

[1253] The terminal is a device used by each sales member and provides the following functions:

[1254] 1. Data display means

[1255] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access information when needed.

[1256] 2. Feedback Input Means

[1257] Sales team members enter feedback using their own devices. The entered feedback is sent to the server and stored in the database.

[1258] User roles

[1259] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[1260] 1. Implement the advice

[1261] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[1262] 2. Providing feedback

[1263] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[1264] Specific example

[1265] For example, a server analyzes a company's sales data for the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should start promoting enhanced new products from May" and delivers it to the sales team members' terminals. When the sales team members actually propose the new products to customers in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. This process further improves the accuracy of future proposals.

[1266] Example of a prompt

[1267] "Based on the user's purchase history and payment data, predict when they will make their next purchase and generate coupon suggestions tailored to their specific needs. Use the following information as a basis:"

[1268] User ID: 12345

[1269] Purchase history over the past 6 months: [Groceries, Electronics, Clothing]

[1270] Payment data: High-value purchases made on the 25th of each month.

[1271] User's financial situation: Stable

[1272] Example of a proposal format: 'We will distribute a special sale coupon around the 25th.'

[1273] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1274] Step 1: Data Collection

[1275] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it uses SQL and REST APIs to query and collect the necessary information from the database. This inputs customer purchase history and financial status information into the server.

[1276] Input: Customer information, sales data, and records of sales activities from the database.

[1277] Output: Collected customer information, sales data, and records of sales activities.

[1278] Specific actions:

[1279] Retrieve customer information from the database using SQL queries.

[1280] Sales data is collected from external systems via API requests.

[1281] Step 2: Data Analysis

[1282] The server uses the collected data to analyze customers' economic situations and market trends. It cleanses the data and extracts features using Python's Pandas and Scikit-learn. Furthermore, it performs data analysis using machine learning algorithms.

[1283] Input: Collected customer information, sales data, and records of sales activities.

[1284] Output: Data analysis results (customer's economic situation, purchasing patterns, trends)

[1285] Specific actions:

[1286] Use Pandas to cleanse data and handle missing values ​​and invalid data.

[1287] We will analyze customer purchasing patterns using Scikit-learn's machine learning algorithms.

[1288] Step 3: Generate personalized advice

[1289] The server generates personalized advice for each sales member based on the results of data analysis. Using Python and the Natural Language Processing (NLTK) library, a generative AI model constructs the advice in natural language.

[1290] Input: Data analysis results

[1291] Output: Individual advice (suggestions expressed in natural language)

[1292] Specific actions:

[1293] Based on the analysis results, an AI model is used to automatically generate advice.

[1294] Using NLTK, the generated advice is expressed in natural language.

[1295] Step 4: Delivering advice

[1296] The server distributes the generated personalized advice to each sales member's terminal. The advice is delivered via push notifications or email using Firebase Cloud Messaging (FCM) or the Email API.

[1297] Input: Individual advice

[1298] Output: Advice delivered to sales team members' terminals.

[1299] Specific actions:

[1300] Use FCM to send push notifications to sales team members' smart devices.

[1301] We will use the Email API to deliver personalized advice via email.

[1302] Step 5: Gathering Feedback

[1303] Each sales member enters feedback using their own device and sends it to the server. The server collects the feedback data via Firebase Analytics and REST APIs and stores it in a database.

[1304] Input: Feedback provided by sales members

[1305] Output: Collected feedback data

[1306] Specific actions:

[1307] Sales team members enter feedback into their terminals.

[1308] Feedback data is sent to the server via Firebase Analytics.

[1309] Step 6: Retrain the analysis algorithm

[1310] The server analyzes the collected feedback data and retrains its analysis algorithms using TensorFlow and Keras. This improves the accuracy of individual advice provided in subsequent sessions.

[1311] Input: Collected feedback data

[1312] Output: Retrained analysis algorithm

[1313] Specific actions:

[1314] The collected feedback data is cleansed and analyzed.

[1315] The analysis algorithm will be retrained using TensorFlow or Keras.

[1316] Through these steps, a system is implemented that involves the coordination of servers, terminals, and users, making it possible to improve the accuracy of individual advice.

[1317] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1318] The system according to the present invention, in addition to functions for collecting and analyzing customer information, sales data, and records of sales activities, recognizes user emotions by combining them with an emotion engine and provides appropriate advice. This system comprises a server, terminals, and an emotion engine, each playing a specific role.

[1319] Server Role

[1320] Servers are the central components of a system and are responsible for the following main functions:

[1321] 1. Data collection:

[1322] The server connects to the database to retrieve customer information, sales data, and records of sales activities. This provides a foundation for analyzing the performance of individual sales members and the entire team.

[1323] 2. Data Analysis:

[1324] The server analyzes the collected data to understand the customer's economic situation, market trends, and sales trends. The analysis results help generate personalized advice.

[1325] 3. Generate personalized advice:

[1326] Based on the data analysis results, the server generates personalized advice for each sales member. The generated advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[1327] 4. Advice distribution:

[1328] The server distributes the generated personalized advice to each sales member's terminal, providing information in real time.

[1329] 5. Gathering and analyzing feedback:

[1330] The server collects feedback entered by each sales member and uses it to continuously improve the system. It also analyzes this feedback and updates the analysis algorithms.

[1331] Terminal role

[1332] The terminal is a device used by sales members and provides the following functions:

[1333] 1. Data display:

[1334] The terminal displays personalized advice and analysis results delivered from the server, providing users with information in real time.

[1335] 2. Feedback Input:

[1336] Users input feedback using their devices and send it to the server.

[1337] The role of the emotional engine

[1338] The emotion engine is responsible for recognizing the user's emotions, which are built into the system.

[1339] 1. Speech analysis:

[1340] The emotion engine analyzes the user's voice input and recognizes their emotions. The recognized emotions are sent to the server and used to generate advice.

[1341] 2. Facial expression analysis:

[1342] The emotion engine collects user facial expression data through the camera and analyzes emotions. This allows for a more accurate recognition of the user's emotional state.

[1343] 3. Adjusting the advice:

[1344] The server adjusts the content and wording of the personalized advice it provides based on the emotional data recognized by the emotion engine. This process ensures that more personalized and effective advice is delivered.

[1345] Specific example

[1346] For example, the server analyzes the past two years of sales data for a specific customer (Customer A) and identifies seasonal fluctuations. Based on this data, the server generates advice such as "We should propose enhanced new products starting in May" and delivers it to sales member B's terminal. At that time, the emotion engine analyzes B's emotional state, and if B is feeling stressed, it provides the advice with more encouraging words.

[1347] When B submits a new product proposal to customer A in May and inputs the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. In this way, the system can respond to the individual needs and emotional states of sales members and effectively plan and execute the team's overall strategy.

[1348] The following describes the processing flow.

[1349] Step 1:

[1350] Database connection

[1351] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[1352] Step 2:

[1353] Data acquisition

[1354] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[1355] Step 3:

[1356] Data organization

[1357] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[1358] Step 4:

[1359] Data Analysis

[1360] Server: Inputs data into the data analysis engine to analyze customer economic conditions, sales trends, and market trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[1361] Step 5:

[1362] Individual advice generation

[1363] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[1364] Step 6:

[1365] Preparation for emotional analysis

[1366] Terminal: The sales team member's terminal activates the emotion engine and begins collecting voice and facial expression data. It prepares to acquire user emotion data via the camera and microphone.

[1367] Step 7:

[1368] Emotion analysis

[1369] Emotion Engine: Analyzes the user's (sales member's) voice input and facial expression data to recognize their emotional state. Specific emotions (stress, joy, anger, etc.) are detected.

[1370] Step 8:

[1371] Advice adjustment

[1372] Server: Based on the emotional data recognized by the emotion engine, the server adjusts the content and expression of the personalized advice it provides. This process generates more personalized and effective advice.

[1373] Step 9:

[1374] Advice distribution

[1375] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[1376] Step 10:

[1377] Data display

[1378] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[1379] Step 11:

[1380] Sales activities

[1381] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[1382] Step 12:

[1383] Feedback Input

[1384] User: Inputs sales activity results, new customer information, and changes in emotional state into the terminal. The entered information is sent to the server.

[1385] Step 13:

[1386] Save feedback

[1387] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[1388] Step 14:

[1389] Feedback analysis

[1390] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[1391] Step 15:

[1392] Algorithm update

[1393] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[1394] Step 16:

[1395] Strategic Planning

[1396] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[1397] (Example 2)

[1398] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1399] Traditional sales support systems can collect and analyze customer and sales data, but they lack the functionality to provide effective, personalized advice based on this data. Furthermore, they lack adequate mechanisms for incorporating feedback from sales representatives, making continuous system improvement and sophisticated strategic planning difficult. Additionally, they fail to provide advice that takes into account the emotions of sales representatives, thus failing to contribute to increased motivation and more effective sales activities.

[1400] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1401] In this invention, the server includes means for acquiring customer data, sales information, and sales activity history from a data management system; means for analyzing the acquired data to evaluate the customer's economic status and market trends; means for generating individual advice for each sales representative based on the evaluation results; means for transferring the generated individual advice to each sales representative's device; means for collecting feedback provided by each sales representative and improving the advice and strategy; means for analyzing the user's emotions through voice and facial expressions; and means for dynamically adjusting the expression of the advice based on the analysis results. As a result, individual advice is provided taking into account the emotional state of the sales representative, and the system is constantly improved based on feedback, enabling more effective sales activities and strategic planning.

[1402] A "data management system" is a general term for software or hardware used to centrally collect, store, and manage customer data, sales information, and sales activity history.

[1403] "Customer data" refers to information about a customer, such as their name, contact information, purchase history, and financial status.

[1404] "Sales information" refers to data related to the sale of a product, including information such as sales figures and sales quantities for a specific period.

[1405] "Sales activity history" refers to a record of various sales activities carried out by a sales representative, including information such as visit history, negotiation details, and feedback.

[1406] "Means of acquisition" refers to mechanisms or methods for automatically retrieving necessary data from a database or external system.

[1407] "Means of analysis" refers to methods and systems for analyzing data using statistical and machine learning techniques to evaluate customers' economic status and market trends.

[1408] "Evaluation results" refer to information obtained from the analysis, including the customer's economic situation and market trends.

[1409] "Means for generating personalized advice" refers to systems and methods that automatically generate optimal proposals and action plans for sales representatives based on customer data and evaluation results.

[1410] "Transferring means" refers to the communication methods and protocols used to send the generated personalized advice to the sales representative's device.

[1411] "Provided feedback" refers to information that sales representatives record regarding the results of their actual sales activities and customer reactions, and then input into the system.

[1412] "Means for improving advice and strategies" refers to mechanisms and methods for analyzing the feedback received and formulating and improving new advice and strategies.

[1413] "Means of analyzing emotions through voice and facial expressions" refers to technologies and systems that analyze the voice and facial expressions of sales representatives to identify their emotional state.

[1414] "Means of dynamic adjustment" refers to mechanisms and methods that adjust the content and expression of generated advice in real time based on the results of emotion analysis.

[1415] The system according to the present invention is a system that collects and analyzes customer data, sales information, and sales activity history, and provides appropriate advice through sentiment analysis. This system comprises a server, terminals, and a sentiment analysis engine, each of which plays the following specific roles.

[1416] Server Role

[1417] Server processing:

[1418] The server retrieves customer data, sales information, and sales activity history from the data management system. This process uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server retrieves this data via SQL queries and extracts it from the database as follows:

[1419] Specific example:

[1420] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[1421] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[1422] SELECT FROM activities WHERE type = 'sales_visit';

[1423] Data analysis:

[1424] The server uses the Python Pandas library to analyze the collected data. This analysis includes data cleaning, formatting, and aggregation, which is used to evaluate the customers' economic status and market trends.

[1425] Specific example:

[1426] df_customers = pd.read_sql(query_customers, connection)

[1427] df_sales = pd.read_sql(query_sales, connection)

[1428] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[1429] Generate personalized advice:

[1430] Based on the analysis results, the server generates personalized advice for each sales representative. This generation process uses Python's Pandas and NumPy libraries.

[1431] Specific example:

[1432] The system generates advice such as, "It would be effective to propose a new product to customer A in May."

[1433] Advice delivery:

[1434] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[1435] Specific example:

[1436] api_url = 'https: / / api.company.com / advice'

[1437] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[1438] response = requests.post(api_url, json=payload)

[1439] Gathering and analyzing feedback:

[1440] Each sales representative enters feedback and sends it to the server via their terminal. This feedback is collected and analyzed on the server side and used to improve the system.

[1441] Specific example:

[1442] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[1443] response = requests.post(api_url, json=feedback)

[1444] The server updates its machine learning model based on feedback and incorporates it into future strategy planning. This utilizes tools such as scikit-learn and TensorFlow.

[1445] Terminal role

[1446] Data display:

[1447] The terminal displays personalized advice and analysis results received from the server, providing real-time information to sales representatives (users). This process utilizes React.js and Vue.js.

[1448] Feedback input:

[1449] Users enter feedback via their device and send it to the server. This feedback is sent using HTML forms and JavaScript.

[1450] The role of the emotional engine

[1451] Voice analysis:

[1452] The emotion engine analyzes the user's voice data to recognize emotions. This analysis uses the Google Cloud Speech-to-Text API and IBM Watson.

[1453] Facial expression analysis:

[1454] The emotion engine analyzes the user's facial expressions through the camera and identifies their emotional state. This process utilizes OpenCV and DeepFace.

[1455] Adjusting advice:

[1456] The server dynamically adjusts the content and wording of the advice provided to each sales representative based on emotional data obtained from the emotion engine.

[1457] Example of a prompt

[1458] "Analyze customer A's sales data for the past two years to identify seasonal sales fluctuations and generate optimal advice for determining the timing of the next proposal. Also, include flexible messaging that takes into account the emotional state of the sales representative making the proposal."

[1459] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1460] Step 1: Data Collection

[1461] Server operation:

[1462] The server connects to the data management system to retrieve customer data, sales information, and sales activity history. Specifically, it extracts data from databases such as MySQL and PostgreSQL using SQL queries.

[1463] Input: Database connection information, query for the required data.

[1464] Output: Extracted customer data, sales information, and sales activity history.

[1465] Specific examples of operation:

[1466] The server sends an SQL query to the database to retrieve data.

[1467] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[1468] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[1469] SELECT FROM activities WHERE type = 'sales_visit';

[1470] Step 2: Data Analysis

[1471] Server operation:

[1472] The server analyzes the acquired data using the Python Pandas library. It performs data cleaning, formatting, and aggregation to evaluate the customer's economic status and market trends.

[1473] Input: Data acquired in the data collection step

[1474] Output: Analysis results (customer's economic status, market trends, etc.)

[1475] Specific examples of operation:

[1476] df_customers = pd.read_sql(query_customers, connection)

[1477] df_sales = pd.read_sql(query_sales, connection)

[1478] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[1479] Step 3: Generate personalized advice

[1480] Server operation:

[1481] The server generates personalized advice for each sales representative based on the analysis results. This generation uses Python's Pandas and NumPy libraries.

[1482] Input: Analysis results

[1483] Output: Individual advice

[1484] Specific examples of operation:

[1485] Based on the analysis results, the system generates advice such as, "It would be effective to propose a new product to customer A in May."

[1486] Step 4: Delivering advice

[1487] Server operation:

[1488] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[1489] Input: Individual advice

[1490] Output: Delivery results (status code, etc.)

[1491] Specific examples of operation:

[1492] api_url = 'https: / / api.company.com / advice'

[1493] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[1494] response = requests.post(api_url, json=payload)

[1495] Step 5: Feedback Input

[1496] User actions:

[1497] Sales representatives (users) input feedback from their terminals. This feedback includes the results of proposals and customer reactions.

[1498] Input: Feedback content

[1499] Output: Feedback data

[1500] Specific examples of operation:

[1501] The user enters their feedback into a form on their device and presses the submit button.

[1502] Step 6: Gathering Feedback

[1503] Device operation:

[1504] The terminal receives user input and sends it to the server. The feedback is sent in JSON format.

[1505] Input: Feedback content

[1506] Output: Feedback submission result (status code, etc.)

[1507] Specific examples of operation:

[1508] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[1509] response = requests.post(api_url, json=feedback)

[1510] Step 7: Emotion Analysis

[1511] How the emotion engine works:

[1512] The emotion engine analyzes the user's voice and facial expressions to recognize their emotions. The analysis results are sent to the server.

[1513] Input: User voice data, facial expression data

[1514] Output: Emotion analysis results

[1515] Specific examples of operation:

[1516] emotion_data = {'stress_level': 'high', 'emotion': 'anxiety'}

[1517] response = requests.post(emotion_api_url, json=emotion_data)

[1518] Step 8: Advice Adjustment

[1519] Server operation:

[1520] The server dynamically adjusts the content and wording of the advice it provides based on the sentiment analysis results.

[1521] Input: Sentiment analysis results

[1522] Output: Adjusted advice

[1523] Specific examples of operation:

[1524] If the emotion analysis reveals that the sales representative is experiencing stress, the message will be adjusted to, "We recommend proposing the new product to customer A in May. Proceed at your own pace."

[1525] Step 9: Feedback Analysis and System Improvement

[1526] Server operation:

[1527] The server analyzes the collected feedback data to improve the system. It updates the analysis algorithm as needed and formulates the next strategy.

[1528] Input: Feedback data

[1529] Output: Updated analysis algorithm, next strategy planning

[1530] Specific examples of operation:

[1531] feedback_df = pd.read_sql(feedback_query, connection)

[1532] model = train_model(feedback_df)

[1533] save_model(model, 'strategy_model.pkl')

[1534] (Application Example 2)

[1535] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1536] In sales activities, it is difficult to grasp customer emotions in real time and provide appropriate advice based on them. Furthermore, there is still a lack of systems for continuously improving advice while collecting feedback. By solving these challenges, it is necessary to improve the performance of sales members and increase customer satisfaction.

[1537] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the user's emotions; means for adjusting the individual advice based on the analyzed emotion data; and means for displaying the adjusted advice to the user. This makes it possible to analyze customer emotions in real time and provide appropriate advice that meets individual needs.

[1538] A "database" is a system for storing, managing, and providing data such as customer information, sales data, and records of sales activities.

[1539] A "collection tool" is a device or program that has the function of obtaining necessary information from a database and sending it to a server for analysis.

[1540] "Analysis tools" refer to devices or programs that process collected data and have the function of analyzing customers' economic conditions and market trends.

[1541] "Generation means" refers to a device or program that has the function of creating individual advice for each sales member based on the analyzed data.

[1542] "Distribution method" refers to a device or program that has the function of sending the generated individual advice to each sales member's terminal.

[1543] A "feedback collection method" refers to a device or program that has the function of collecting feedback provided by sales members on a server.

[1544] An "emotion analysis tool" is a device or program that has the function of analyzing a user's voice and facial expressions to recognize their emotions.

[1545] An "advice adjustment tool" is a device or program that has the function of adjusting the content of individual advice based on analyzed emotional data.

[1546] "Display means" refers to a device or program that has the function of displaying adjusted advice to the user visually or audibly.

[1547] The system for implementing this invention consists of a server, a terminal, and an emotion analysis engine. The server collects customer information, sales data, and records of sales activities from a database, and analyzes this data to understand the customer's economic situation and market trends. Furthermore, it generates individual advice for each sales member based on the analysis results and delivers this advice to the terminal. The terminal displays the advice delivered from the server and collects feedback from the sales member. The emotion analysis engine analyzes the user's voice and facial expressions to recognize their emotions, and the server adjusts the content of the advice based on this.

[1548] Hardware and software to be used

[1549] Server: The server connects to the database and uses Python and SQL to collect, analyze, and generate advice. It also sends the collected feedback to the database in real time using Apache Kafka or similar tools.

[1550] Device: The device uses smart glasses or a tablet to display advice from the server in real time via a web browser or a dedicated application.

[1551] Emotion Analysis Engine: Uses OpenCV and TensorFlow to recognize emotions from user voice and facial expressions. Data is collected using devices such as cameras and microphones.

[1552] Processing flow

[1553] 1. The server collects customer information, sales data, and records of sales activities from the database.

[1554] 2. The server analyzes the collected data to understand the customer's economic situation and market trends.

[1555] 3. Based on the analysis results, the server generates individual advice for each sales member.

[1556] 4. The generated advice is delivered to the sales team members' devices.

[1557] 5. The emotion analysis engine analyzes the user's voice and facial expressions and sends that data to the server.

[1558] 6. The server adjusts the advice based on sentiment data and displays the content on the terminal.

[1559] 7. Sales members implement the advice and input the results as feedback into their terminals.

[1560] 8. The server collects feedback and incorporates it into the next strategy.

[1561] Specific example

[1562] For example, when sales member A wears smart glasses and interacts with customer B, the emotion analysis engine analyzes customer B's facial expressions in real time. If the analysis indicates that customer B is dissatisfied, the server generates advice appropriate to the situation, providing words of encouragement or suggestions for additional proposals. Sales member A adjusts their response based on this and inputs the outcome of the negotiation as feedback, allowing the server to update the data for future strategic planning.

[1563] Example of a prompt

[1564] "I'm designing a system that analyzes customer emotions in real time and provides appropriate advice to sales team members. This system uses smart glasses to analyze customer emotions from their facial expressions. Based on the collected data, it generates appropriate advice to support sales team members' responses. Please provide a detailed design incorporating specific examples."

[1565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1566] Step 1:

[1567] The server collects customer information, sales data, and records of sales activities from the database. The collected data is then stored in the server's memory. The input is information from the database, and the output is aggregated data stored within the server.

[1568] Step 2:

[1569] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis is performed using Python and SQL, employing algorithms such as linear regression and time series analysis. The input for this step is the data collected in step 1, and the output is presented in the form of analysis reports and graphs.

[1570] Step 3:

[1571] The server generates personalized advice for each sales member based on the analysis results. This is done using a generative AI model, which extracts specific suggestions from the analysis report that will lead to improved performance for each sales member. The input for this step is the analysis results, and the output is personalized advice.

[1572] Step 4:

[1573] The server delivers the generated individual advice to each sales member's terminal. The advice is transmitted via API and received by the sales members in real time. The input is the generated advice, and the output is the information displayed on the sales member's terminal.

[1574] Step 5:

[1575] The emotion analysis engine analyzes the user's voice and facial expressions and sends the data to the server. The analysis is performed using OpenCV and TensorFlow, and an emotion recognition model is applied. The input for this step is voice and facial expression data collected by the camera and microphone, and the output is recognized emotion data.

[1576] Step 6:

[1577] The server adjusts the advice based on sentiment data. It combines the generated advice with the sentiment data to regenerate the optimal advice. The input is the generated individual advice and sentiment data, and the output is the adjusted advice that takes sentiment into account.

[1578] Step 7:

[1579] The device displays adjusted advice to the user. This is shown in real time on a display such as smart glasses or a tablet. The input is the adjusted advice, and the output is information provided visually or audibly.

[1580] Step 8:

[1581] Sales team members implement the advice and input the results as feedback into their terminals. This feedback is sent to the server and used for generating future advice and developing strategies. The input is feedback from the sales team members, and the output is new data collected by the server.

[1582] Step 9:

[1583] The server updates its analysis algorithm based on the collected feedback and incorporates it into the next strategy formulation. The algorithm improves through continuous learning from the data. The input for this step is the feedback data, and the output is the updated analysis algorithm.

[1584] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1585] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1586] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1587] [Fourth Embodiment]

[1588] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1589] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1590] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1591] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1592] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1593] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1594] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1595] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1596] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1597] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1598] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1599] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1600] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1601] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[1602] Server Role

[1603] The server is the central hub of the system and performs the following main functions:

[1604] 1. Data collection:

[1605] The server collects customer information, sales data, and records of sales activities from the database. This data forms the basis for analyzing the performance of individual sales members and the entire team.

[1606] 2. Data Analysis:

[1607] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis results form the basis for the individual advice provided to each sales member.

[1608] 3. Generate personalized advice:

[1609] Based on the analysis results, the server generates specific advice for each sales member. This advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[1610] 4. Distribution of advice:

[1611] The generated personalized advice is delivered to each sales member's terminal by the server. This allows sales members to receive the latest information in real time.

[1612] 5. Gathering feedback:

[1613] The server collects feedback from each sales member and stores it in a database. This feedback is used for the continuous improvement of the system.

[1614] 6. Update of the analysis algorithm:

[1615] The server analyzes the collected feedback and updates its analysis algorithm to make the next advice more accurate.

[1616] Terminal role

[1617] The terminal is a device used by each sales member and provides the following functions:

[1618] 1. Displaying data:

[1619] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access the information when needed.

[1620] 2. Feedback Input:

[1621] Each sales member enters feedback using their own device. The entered feedback is sent to the server and stored in the database.

[1622] User roles

[1623] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[1624] 1. Implement the advice:

[1625] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[1626] 2. Providing feedback:

[1627] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[1628] Specific example

[1629] For example, a server analyzes the sales data of a certain company (customer A) over the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice that "a new product enhancement proposal should be made starting in May" and delivers it to sales member B's terminal. When B submits a new product proposal to customer A in May and inputs the result as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy.

[1630] In this way, the system can respond to the individual needs of sales members and effectively plan and execute the team's overall strategy.

[1631] The following describes the processing flow.

[1632] Step 1:

[1633] Database connection

[1634] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[1635] Step 2:

[1636] Data acquisition

[1637] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[1638] Step 3:

[1639] Data organization

[1640] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[1641] Step 4:

[1642] Data Analysis

[1643] Server: Inputs data into the data analysis engine to analyze customer economic conditions, market trends, and sales trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[1644] Step 5:

[1645] Individual advice generation

[1646] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[1647] Step 6:

[1648] Advice distribution

[1649] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[1650] Step 7:

[1651] Data display

[1652] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[1653] Step 8:

[1654] Sales activities

[1655] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[1656] Step 9:

[1657] Feedback Input

[1658] User: Enters sales activity results and new customer information into the terminal. The entered information is sent to the server.

[1659] Step 10:

[1660] Save feedback

[1661] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[1662] Step 11:

[1663] Feedback analysis

[1664] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[1665] Step 12:

[1666] Algorithm update

[1667] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[1668] Step 13:

[1669] Strategic Planning

[1670] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[1671] (Example 1)

[1672] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1673] In sales activities, there is a need to efficiently collect individual advice and feedback from each sales member and improve the accuracy of analysis algorithms. Furthermore, it is necessary to utilize generative AI models to develop more effective sales strategies and enable real-time information sharing.

[1674] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1675] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for inputting prompt sentences to a generating AI model to obtain appropriate advice; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for updating the analysis algorithm based on the collected feedback data; and means for applying the updated analysis algorithm to the next analysis. This improves the quality of individual advice for sales members and enables improved analysis accuracy based on feedback. Furthermore, it enables the formulation of effective sales strategies utilizing the generating AI model and real-time information sharing.

[1676] A "database" is a digital system for systematically organizing and storing information, and it allows for the addition, deletion, searching, and updating of data through queries.

[1677] "Customer information" refers to data about a specific customer, including name, address, purchase history, and contact information.

[1678] "Sales data" refers to information regarding the sale of goods or services during a specific period, including sales amount, transaction date and time, and purchased items.

[1679] "Sales activity records" refer to the history of all business activities performed by sales members, including customer visits, negotiation details, and contract status.

[1680] "Analysis" refers to the process of using collected data to reveal its meaning, trends, and patterns.

[1681] "Individualized advice" refers to behavioral guidelines and strategic proposals provided individually to specific sales members.

[1682] A "generative AI model" refers to an artificial intelligence model that uses machine learning and deep learning techniques to generate new information or suggestions from input data.

[1683] A "prompt" refers to the input text given to a generative AI model in order to generate the requested output.

[1684] "Feedback" refers to the act of sales team members providing the results of their activities and the information they have gathered, as well as the content of that feedback.

[1685] An "analysis algorithm" refers to a computational method used to analyze data and generate output for a specific purpose.

[1686] A "device" refers to a digital device used by a user, and includes personal computers, tablets, smartphones, and other similar devices.

[1687] The system according to the present invention is designed to effectively support individualized advice to sales members and the strategies of departments and teams. Specific embodiments are described below.

[1688] Server Role

[1689] The server plays a central role in the system and performs multiple functions. First, it collects customer information, sales data, and records of sales activities from the database. The databases used include SQL Server and Oracle Database. By collecting this data, a foundation is built for analyzing the performance of individual sales members and the entire team.

[1690] Next, the collected data is analyzed using Python or R. Specifically, the data is processed using libraries such as Pandas and NumPy, and a model is built using the Scikit-learn machine learning library. For example, this data analysis is performed to predict which customers a sales team should act towards during a specific period.

[1691] Based on the generated analysis results, the server uses a generative AI model to generate personalized advice for each sales member. The generative AI model used here is GPT-3, for example. For instance, by entering a prompt such as, "Please suggest a sales pitch to use in the next business meeting," appropriate advice will be generated.

[1692] The generated personalized advice is delivered to each sales member's terminal via a REST API. The terminal receives an HTTP POST request and displays the advice in JSON format. This implementation allows sales members to obtain the latest information in real time.

[1693] The server collects feedback provided by sales members. This feedback includes sales activity results and new customer information. The feedback is then analyzed again and used for continuous system improvement and updating of the analysis algorithms.

[1694] Finally, the analysis algorithm is updated based on the collected feedback data. This update includes retraining the machine learning model, which will be reflected in the next analysis.

[1695] Terminal role

[1696] The terminal is a device used by each sales member and primarily provides the following functions. First, it displays individual advice and analysis results delivered from the server. Sales members can refer to specific advice by looking at the terminal screen. For example, it displays information such as when and what products should be proposed to a particular customer.

[1697] The terminal also provides a means for sales members to input feedback. Feedback is entered through forms and text boxes and sent to the server. The data is sent as an HTTP POST request and parsed on the server.

[1698] User roles

[1699] Users, i.e., sales members, use the system to conduct sales activities. Based on the advice displayed on the terminal, users carry out specific sales actions. For example, they might submit proposals to specific customers or follow up at the appropriate time. They also input the results of their sales activities and newly acquired customer information as feedback into the terminal and provide it to the system. This further improves the accuracy of the system and helps in future analyses.

[1700] Specific example

[1701] For example, a server analyzes the past two years of sales data for a company (customer A) and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should propose enhanced new products starting in May" and delivers it to the sales team members' terminals. When the sales team members submit a proposal for the new products to customer A in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm. Using this updated algorithm in the next analysis allows for more accurate advice.

[1702] Examples of prompts for generative AI models

[1703] For example, the following prompt statement is used:

[1704] "Analyze customer A's sales data for the past two years to identify which season has the highest sales. Based on these results, generate appropriate sales activity advice."

[1705] By using these prompts, the generative AI model can perform appropriate analysis and generate advice. This system functions by internally generating these prompts, which are then executed by the server.

[1706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1707] Step 1: Data Collection

[1708] Subject: Server

[1709] Specific actions:

[1710] The server collects data from databases such as SQL Server and Oracle Database. Specifically, it collects customer information, sales data, and records of sales activities. For example, the server issues an SQL query like this: "SELECT FROM sales_data WHERE year = 2022". Based on this input query, the relevant sales data is extracted from the database.

[1711] Input: SQL query

[1712] Output: Results of the SQL query (customer information, sales data, sales activity records)

[1713] Step 2: Data Analysis

[1714] Subject: Server

[1715] Specific actions:

[1716] The server analyzes the collected data using Python or R. It preprocesses the data using libraries such as Pandas and NumPy, and builds machine learning models using libraries such as Scikit-learn. For example, the server uses Pandas to convert the data into a DataFrame and uses a linear regression model to forecast sales.

[1717] Input: Data collected from the database

[1718] Output: Analysis results from the model (e.g., monthly sales forecast)

[1719] Step 3: Generate personalized advice

[1720] Subject: Server

[1721] Specific actions:

[1722] Based on the results of data analysis, the server sends prompt messages to the generating AI model to generate appropriate advice. For example, it might input the prompt message, "Please suggest a sales pitch to use in the next business meeting," into the generating AI model. Based on this input, the generating AI model will generate a sales pitch and proposal to use in the next business meeting.

[1723] Input: Analysis result, prompt message

[1724] Output: Advice from a generative AI model

[1725] Step 4: Delivering advice

[1726] Subject: Server

[1727] Specific actions:

[1728] The server distributes the generated individual advice to each sales member's terminal. Using a REST API, it sends HTTP POST requests to the sales member's terminal, delivering the advice in JSON format. For example, the server sends the advice to the " / advice" endpoint.

[1729] Input: Generated advice

[1730] Output: Notification on the device where the advice was delivered.

[1731] Step 5: Gathering Feedback

[1732] Subject: terminal

[1733] Specific actions:

[1734] Each sales member uses a terminal to input feedback such as the results of their sales activities and new customer information. For example, a sales member might input feedback such as "I proposed a new product to customer A and received a positive response," and send it to the server. The terminal sends this feedback to the server via an HTTP POST request.

[1735] Input: Results of sales activities and new customer information

[1736] Output: Feedback is sent to the server and stored in the database.

[1737] Step 6: Updating the analysis algorithm

[1738] Subject: Server

[1739] Specific actions:

[1740] The server updates its analysis algorithm based on the collected feedback data. Specifically, it retrains the machine learning model using the new feedback data. For example, it retrains the model with the new data using the "fit" method of Scikit-learn. This update ensures that a more accurate algorithm is applied in the next analysis.

[1741] Input: Feedback data

[1742] Output: Updated analysis algorithm

[1743] (Application Example 1)

[1744] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1745] Traditional sales support systems have low accuracy in providing individual customer proposals and advice, and furthermore, manual intervention is required to improve the provided advice. Therefore, there is a need for a more efficient and automated way to improve the accuracy of individual advice. However, these systems have limitations in how they can effectively utilize user purchase data and feedback, making it difficult to maximize sales efficiency. Therefore, a system is needed that analyzes user purchase patterns and automatically generates optimal proposals.

[1746] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1747] In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the collected feedback data and retraining the analysis algorithm; and means for improving the accuracy of subsequent individual advice using the retrained analysis algorithm. This makes it possible to generate individual proposals based on the user's purchasing data and economic situation and deliver those proposals to the user's smart device.

[1748] A "database" is a system for centrally managing and storing various types of data, such as customer information, sales data, and records of sales activities.

[1749] An "analysis algorithm" is a set of procedures and calculation methods used to analyze collected data and find specific patterns or trends.

[1750] "Feedback" refers to information such as results reports, evaluations, and opinions provided by sales members and users, which is useful for improving the system.

[1751] "Individualized advice" refers to customized proposals and strategies provided to specific sales members or users based on analysis results.

[1752] A "smart device" is an electronic device with advanced functions that a user can carry or wear, and includes smartphones, tablets, smartwatches, and other similar devices.

[1753] "Purchase data" refers to a detailed record of products and services that a user has purchased in the past, including information such as the date of purchase, place of purchase, and purchase amount.

[1754] "Data collection methods" refer to processes and technologies for automatically acquiring necessary data from databases or external systems.

[1755] "Delivery methods" refer to the methods and technologies used to efficiently deliver generated personalized advice and suggestions to users or sales members. Specifically, this includes push notifications, email distribution, and dashboard displays.

[1756] "Retraining" is the process of updating existing analysis algorithms based on newly obtained feedback and data to obtain more accurate and effective results.

[1757] "Retraining methods" refer to methods and techniques for retraining analytical algorithms, and this includes updating machine learning models with new data.

[1758] The system according to the present invention is designed to provide individualized advice to sales members and support departmental and team strategies. This system consists of server, terminal, and user elements, each playing a specific role.

[1759] Server Role

[1760] The server is the central hub of the system and performs the following main functions:

[1761] 1. Data collection methods

[1762] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it retrieves information from various databases and external systems using SQL and REST APIs.

[1763] 2. Data Analysis Methods

[1764] The server cleanses the collected data using Pandas and Scikit-learn and analyzes the customer's economic situation and market trends. This allows it to understand the user's purchasing patterns and trends, and based on the results, it generates personalized advice.

[1765] 3. Individual advice generation means

[1766] The server generates specific advice for each sales member based on the analysis results. The advice is constructed in natural language using Python and the Natural Language Toolkit (NLTK).

[1767] 4. Methods for delivering advice

[1768] The generated personalized advice is delivered in real time to each sales member's device via the server using Firebase Cloud Messaging (FCM) or the Email API.

[1769] 5. Methods for collecting feedback

[1770] The server collects feedback from each sales member and stores it in a database. The collected feedback data is stored within the system using Firebase Analytics and REST APIs.

[1771] 6. Methods for retraining analysis algorithms

[1772] The server analyzes the collected feedback data and updates its analysis algorithm by retraining it using TensorFlow or Keras. This improves the accuracy of individual advice in subsequent sessions.

[1773] Terminal role

[1774] The terminal is a device used by each sales member and provides the following functions:

[1775] 1. Data display means

[1776] The terminal displays personalized advice and analysis results delivered from the server to sales members. This allows sales members to access information when needed.

[1777] 2. Feedback Input Means

[1778] Sales team members enter feedback using their own devices. The entered feedback is sent to the server and stored in the database.

[1779] User roles

[1780] Users (sales members) use the system to improve the accuracy and efficiency of their sales activities.

[1781] 1. Implement the advice

[1782] Users conduct sales activities based on advice displayed on their devices. For example, they might submit proposals to customers at specific times or follow up with them.

[1783] 2. Providing feedback

[1784] Users input sales activity results and new customer information into their terminals and send it to the server. This feedback contributes to improving the system's accuracy.

[1785] Specific example

[1786] For example, a server analyzes a company's sales data for the past two years and identifies seasonal fluctuations in sales. Based on this, the server generates advice such as "You should start promoting enhanced new products from May" and delivers it to the sales team members' terminals. When the sales team members actually propose the new products to customers in May and input the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. This process further improves the accuracy of future proposals.

[1787] Example of a prompt

[1788] "Based on the user's purchase history and payment data, predict when they will make their next purchase and generate coupon suggestions tailored to their specific needs. Use the following information as a basis:"

[1789] User ID: 12345

[1790] Purchase history over the past 6 months: [Groceries, Electronics, Clothing]

[1791] Payment data: High-value purchases made on the 25th of each month.

[1792] User's financial situation: Stable

[1793] Example of a proposal format: 'We will distribute a special sale coupon around the 25th.'

[1794] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1795] Step 1: Data Collection

[1796] The server collects customer information, sales data, and records of sales activities from the database. Specifically, it uses SQL and REST APIs to query and collect the necessary information from the database. This inputs customer purchase history and financial status information into the server.

[1797] Input: Customer information, sales data, and records of sales activities from the database.

[1798] Output: Collected customer information, sales data, and records of sales activities.

[1799] Specific actions:

[1800] Retrieve customer information from the database using SQL queries.

[1801] Sales data is collected from external systems via API requests.

[1802] Step 2: Data Analysis

[1803] The server uses the collected data to analyze customers' economic situations and market trends. It cleanses the data and extracts features using Python's Pandas and Scikit-learn. Furthermore, it performs data analysis using machine learning algorithms.

[1804] Input: Collected customer information, sales data, and records of sales activities.

[1805] Output: Data analysis results (customer's economic situation, purchasing patterns, trends)

[1806] Specific actions:

[1807] Use Pandas to cleanse data and handle missing values ​​and invalid data.

[1808] We will analyze customer purchasing patterns using Scikit-learn's machine learning algorithms.

[1809] Step 3: Generate personalized advice

[1810] The server generates personalized advice for each sales member based on the results of data analysis. Using Python and the Natural Language Processing (NLTK) library, a generative AI model constructs the advice in natural language.

[1811] Input: Data analysis results

[1812] Output: Individual advice (suggestions expressed in natural language)

[1813] Specific actions:

[1814] Based on the analysis results, an AI model is used to automatically generate advice.

[1815] Using NLTK, the generated advice is expressed in natural language.

[1816] Step 4: Delivering advice

[1817] The server distributes the generated personalized advice to each sales member's terminal. The advice is delivered via push notifications or email using Firebase Cloud Messaging (FCM) or the Email API.

[1818] Input: Individual advice

[1819] Output: Advice delivered to sales team members' terminals.

[1820] Specific actions:

[1821] Use FCM to send push notifications to sales team members' smart devices.

[1822] We will use the Email API to deliver personalized advice via email.

[1823] Step 5: Gathering Feedback

[1824] Each sales member enters feedback using their own device and sends it to the server. The server collects the feedback data via Firebase Analytics and REST APIs and stores it in a database.

[1825] Input: Feedback provided by sales members

[1826] Output: Collected feedback data

[1827] Specific actions:

[1828] Sales team members enter feedback into their terminals.

[1829] Feedback data is sent to the server via Firebase Analytics.

[1830] Step 6: Retrain the analysis algorithm

[1831] The server analyzes the collected feedback data and retrains its analysis algorithms using TensorFlow and Keras. This improves the accuracy of individual advice provided in subsequent sessions.

[1832] Input: Collected feedback data

[1833] Output: Retrained analysis algorithm

[1834] Specific actions:

[1835] The collected feedback data is cleansed and analyzed.

[1836] The analysis algorithm will be retrained using TensorFlow or Keras.

[1837] Through these steps, a system is implemented that involves the coordination of servers, terminals, and users, making it possible to improve the accuracy of individual advice.

[1838] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1839] The system according to the present invention, in addition to functions for collecting and analyzing customer information, sales data, and records of sales activities, recognizes user emotions by combining them with an emotion engine and provides appropriate advice. This system comprises a server, terminals, and an emotion engine, each playing a specific role.

[1840] Server Role

[1841] Servers are the central components of a system and are responsible for the following main functions:

[1842] 1. Data collection:

[1843] The server connects to the database to retrieve customer information, sales data, and records of sales activities. This provides a foundation for analyzing the performance of individual sales members and the entire team.

[1844] 2. Data Analysis:

[1845] The server analyzes the collected data to understand the customer's economic situation, market trends, and sales trends. The analysis results help generate personalized advice.

[1846] 3. Generate personalized advice:

[1847] Based on the data analysis results, the server generates personalized advice for each sales member. The generated advice is tailored to the customer's specific needs and the timing of the sales negotiation.

[1848] 4. Advice distribution:

[1849] The server distributes the generated personalized advice to each sales member's terminal, providing information in real time.

[1850] 5. Gathering and analyzing feedback:

[1851] The server collects feedback entered by each sales member and uses it to continuously improve the system. It also analyzes this feedback and updates the analysis algorithms.

[1852] Terminal role

[1853] The terminal is a device used by sales members and provides the following functions:

[1854] 1. Data display:

[1855] The terminal displays personalized advice and analysis results delivered from the server, providing users with information in real time.

[1856] 2. Feedback Input:

[1857] Users input feedback using their devices and send it to the server.

[1858] The role of the emotional engine

[1859] The emotion engine is responsible for recognizing the user's emotions, which are built into the system.

[1860] 1. Speech analysis:

[1861] The emotion engine analyzes the user's voice input and recognizes their emotions. The recognized emotions are sent to the server and used to generate advice.

[1862] 2. Facial expression analysis:

[1863] The emotion engine collects user facial expression data through the camera and analyzes emotions. This allows for a more accurate recognition of the user's emotional state.

[1864] 3. Adjusting the advice:

[1865] The server adjusts the content and wording of the personalized advice it provides based on the emotional data recognized by the emotion engine. This process ensures that more personalized and effective advice is delivered.

[1866] Specific example

[1867] For example, the server analyzes the past two years of sales data for a specific customer (Customer A) and identifies seasonal fluctuations. Based on this data, the server generates advice such as "We should propose enhanced new products starting in May" and delivers it to sales member B's terminal. At that time, the emotion engine analyzes B's emotional state, and if B is feeling stressed, it provides the advice with more encouraging words.

[1868] When B submits a new product proposal to customer A in May and inputs the results as feedback, the server analyzes this information and updates its analysis algorithm to reflect it in the next strategy. In this way, the system can respond to the individual needs and emotional states of sales members and effectively plan and execute the team's overall strategy.

[1869] The following describes the processing flow.

[1870] Step 1:

[1871] Database connection

[1872] Server: Prepares to connect to the database and retrieve customer information, sales data, and records of sales activities. Specifically, it establishes a connection to execute SQL queries to retrieve the necessary data.

[1873] Step 2:

[1874] Data acquisition

[1875] Server: Executes SQL queries to retrieve historical sales data, customer details, and sales activity history from the database. The data is stored in temporary storage.

[1876] Step 3:

[1877] Data organization

[1878] Server: Organizes the acquired data and converts it into a format suitable for the data model. This process includes data cleansing (deleting unnecessary data, imputing missing values, etc.).

[1879] Step 4:

[1880] Data Analysis

[1881] Server: Inputs data into the data analysis engine to analyze customer economic conditions, sales trends, and market trends. Uses machine learning algorithms and statistical methods to extract useful insights from historical data.

[1882] Step 5:

[1883] Individual advice generation

[1884] Server: Based on the results of data analysis, it generates personalized advice for each sales team member. For example, it provides specific instructions on what kind of proposal to make to a particular customer and when.

[1885] Step 6:

[1886] Preparation for emotional analysis

[1887] Terminal: The sales team member's terminal activates the emotion engine and begins collecting voice and facial expression data. It prepares to acquire user emotion data via the camera and microphone.

[1888] Step 7:

[1889] Emotion analysis

[1890] Emotion Engine: Analyzes the user's (sales member's) voice input and facial expression data to recognize their emotional state. Specific emotions (stress, joy, anger, etc.) are detected.

[1891] Step 8:

[1892] Advice adjustment

[1893] Server: Based on the emotional data recognized by the emotion engine, the server adjusts the content and expression of the personalized advice it provides. This process generates more personalized and effective advice.

[1894] Step 9:

[1895] Advice distribution

[1896] Server: Distributes the generated advice to each sales member's terminal. In this process, the advice is converted to an appropriate format and delivered in real time.

[1897] Step 10:

[1898] Data display

[1899] Terminal: Displays advice and analysis results received from the server to sales members. Users refer to this information to plan and execute specific sales activities.

[1900] Step 11:

[1901] Sales activities

[1902] User: Based on the advice displayed on the device, conduct sales activities such as making proposals to customers and following up with them.

[1903] Step 12:

[1904] Feedback Input

[1905] User: Inputs sales activity results, new customer information, and changes in emotional state into the terminal. The entered information is sent to the server.

[1906] Step 13:

[1907] Save feedback

[1908] Server: Stores collected feedback in a database. The stored feedback is used for future analysis and advice generation.

[1909] Step 14:

[1910] Feedback analysis

[1911] Server: Analyze the collected feedback and identify areas for improvement to enhance the quality of advice.

[1912] Step 15:

[1913] Algorithm update

[1914] Server: The analysis algorithm will be updated based on the feedback analysis results. This will result in more accurate advice in the future.

[1915] Step 16:

[1916] Strategic Planning

[1917] Server: Integrates data from across the team and develops the next strategy. Creates concrete action plans to achieve the team's overall sales targets.

[1918] (Example 2)

[1919] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1920] Traditional sales support systems can collect and analyze customer and sales data, but they lack the functionality to provide effective, personalized advice based on this data. Furthermore, they lack adequate mechanisms for incorporating feedback from sales representatives, making continuous system improvement and sophisticated strategic planning difficult. Additionally, they fail to provide advice that takes into account the emotions of sales representatives, thus failing to contribute to increased motivation and more effective sales activities.

[1921] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1922] In this invention, the server includes means for acquiring customer data, sales information, and sales activity history from a data management system; means for analyzing the acquired data to evaluate the customer's economic status and market trends; means for generating individual advice for each sales representative based on the evaluation results; means for transferring the generated individual advice to each sales representative's device; means for collecting feedback provided by each sales representative and improving the advice and strategy; means for analyzing the user's emotions through voice and facial expressions; and means for dynamically adjusting the expression of the advice based on the analysis results. As a result, individual advice is provided taking into account the emotional state of the sales representative, and the system is constantly improved based on feedback, enabling more effective sales activities and strategic planning.

[1923] A "data management system" is a general term for software or hardware used to centrally collect, store, and manage customer data, sales information, and sales activity history.

[1924] "Customer data" refers to information about a customer, such as their name, contact information, purchase history, and financial status.

[1925] "Sales information" refers to data related to the sale of a product, including information such as sales figures and sales quantities for a specific period.

[1926] "Sales activity history" refers to a record of various sales activities carried out by a sales representative, including information such as visit history, negotiation details, and feedback.

[1927] "Means of acquisition" refers to mechanisms or methods for automatically retrieving necessary data from a database or external system.

[1928] "Means of analysis" refers to methods and systems for analyzing data using statistical and machine learning techniques to evaluate customers' economic status and market trends.

[1929] "Evaluation results" refer to information obtained from the analysis, including the customer's economic situation and market trends.

[1930] "Means for generating personalized advice" refers to systems and methods that automatically generate optimal proposals and action plans for sales representatives based on customer data and evaluation results.

[1931] "Transferring means" refers to the communication methods and protocols used to send the generated personalized advice to the sales representative's device.

[1932] "Provided feedback" refers to information that sales representatives record regarding the results of their actual sales activities and customer reactions, and then input into the system.

[1933] "Means for improving advice and strategies" refers to mechanisms and methods for analyzing the feedback received and formulating and improving new advice and strategies.

[1934] "Means of analyzing emotions through voice and facial expressions" refers to technologies and systems that analyze the voice and facial expressions of sales representatives to identify their emotional state.

[1935] "Means of dynamic adjustment" refers to mechanisms and methods that adjust the content and expression of generated advice in real time based on the results of emotion analysis.

[1936] The system according to the present invention is a system that collects and analyzes customer data, sales information, and sales activity history, and provides appropriate advice through sentiment analysis. This system comprises a server, terminals, and a sentiment analysis engine, each of which plays the following specific roles.

[1937] Server Role

[1938] Server processing:

[1939] The server retrieves customer data, sales information, and sales activity history from the data management system. This process uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. The server retrieves this data via SQL queries and extracts it from the database as follows:

[1940] Specific example:

[1941] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[1942] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[1943] SELECT FROM activities WHERE type = 'sales_visit';

[1944] Data analysis:

[1945] The server uses the Python Pandas library to analyze the collected data. This analysis includes data cleaning, formatting, and aggregation, which is used to evaluate the customers' economic status and market trends.

[1946] Specific example:

[1947] df_customers = pd.read_sql(query_customers, connection)

[1948] df_sales = pd.read_sql(query_sales, connection)

[1949] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[1950] Generate personalized advice:

[1951] Based on the analysis results, the server generates personalized advice for each sales representative. This generation process uses Python's Pandas and NumPy libraries.

[1952] Specific example:

[1953] The system generates advice such as, "It would be effective to propose a new product to customer A in May."

[1954] Advice delivery:

[1955] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[1956] Specific example:

[1957] api_url = 'https: / / api.company.com / advice'

[1958] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[1959] response = requests.post(api_url, json=payload)

[1960] Gathering and analyzing feedback:

[1961] Each sales representative enters feedback and sends it to the server via their terminal. This feedback is collected and analyzed on the server side and used to improve the system.

[1962] Specific example:

[1963] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[1964] response = requests.post(api_url, json=feedback)

[1965] The server updates its machine learning model based on feedback and incorporates it into future strategy planning. This utilizes tools such as scikit-learn and TensorFlow.

[1966] Terminal role

[1967] Data display:

[1968] The terminal displays personalized advice and analysis results received from the server, providing real-time information to sales representatives (users). This process utilizes React.js and Vue.js.

[1969] Feedback input:

[1970] Users enter feedback via their device and send it to the server. This feedback is sent using HTML forms and JavaScript.

[1971] The role of the emotional engine

[1972] Voice analysis:

[1973] The emotion engine analyzes the user's voice data to recognize emotions. This analysis uses the Google Cloud Speech-to-Text API and IBM Watson.

[1974] Facial expression analysis:

[1975] The emotion engine analyzes the user's facial expressions through the camera and identifies their emotional state. This process utilizes OpenCV and DeepFace.

[1976] Adjusting advice:

[1977] The server dynamically adjusts the content and wording of the advice provided to each sales representative based on emotional data obtained from the emotion engine.

[1978] Example of a prompt

[1979] "Analyze customer A's sales data for the past two years to identify seasonal sales fluctuations and generate optimal advice for determining the timing of the next proposal. Also, include flexible messaging that takes into account the emotional state of the sales representative making the proposal."

[1980] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1981] Step 1: Data Collection

[1982] Server operation:

[1983] The server connects to the data management system to retrieve customer data, sales information, and sales activity history. Specifically, it extracts data from databases such as MySQL and PostgreSQL using SQL queries.

[1984] Input: Database connection information, query for the required data.

[1985] Output: Extracted customer data, sales information, and sales activity history.

[1986] Specific examples of operation:

[1987] The server sends an SQL query to the database to retrieve data.

[1988] SELECT FROM customers WHERE updated_at >= '2023-01-01';

[1989] SELECT FROM sales WHERE date BETWEEN '2022-01-01' AND '2022-12-31';

[1990] SELECT FROM activities WHERE type = 'sales_visit';

[1991] Step 2: Data Analysis

[1992] Server operation:

[1993] The server analyzes the acquired data using the Python Pandas library. It performs data cleaning, formatting, and aggregation to evaluate the customer's economic status and market trends.

[1994] Input: Data acquired in the data collection step

[1995] Output: Analysis results (customer's economic status, market trends, etc.)

[1996] Specific examples of operation:

[1997] df_customers = pd.read_sql(query_customers, connection)

[1998] df_sales = pd.read_sql(query_sales, connection)

[1999] df_sales['monthly_sales'] = df_sales.groupby('month')['amount'].sum()

[2000] Step 3: Generate personalized advice

[2001] Server operation:

[2002] The server generates personalized advice for each sales representative based on the analysis results. This generation uses Python's Pandas and NumPy libraries.

[2003] Input: Analysis results

[2004] Output: Individual advice

[2005] Specific examples of operation:

[2006] Based on the analysis results, the system generates advice such as, "It would be effective to propose a new product to customer A in May."

[2007] Step 4: Delivering advice

[2008] Server operation:

[2009] The server distributes the generated personalized advice to each sales representative's terminal. A RESTful API is used for communication, and data is sent in JSON format.

[2010] Input: Individual advice

[2011] Output: Delivery results (status code, etc.)

[2012] Specific examples of operation:

[2013] api_url = 'https: / / api.company.com / advice'

[2014] payload = {'user_id': 'B', 'advice': 'We recommend proposing the new product to customer A in May.'}

[2015] response = requests.post(api_url, json=payload)

[2016] Step 5: Feedback Input

[2017] User actions:

[2018] Sales representatives (users) input feedback from their terminals. This feedback includes the results of proposals and customer reactions.

[2019] Input: Feedback content

[2020] Output: Feedback data

[2021] Specific examples of operation:

[2022] The user enters their feedback into a form on their device and presses the submit button.

[2023] Step 6: Gathering Feedback

[2024] Device operation:

[2025] The terminal receives user input and sends it to the server. The feedback is sent in JSON format.

[2026] Input: Feedback content

[2027] Output: Feedback submission result (status code, etc.)

[2028] Specific examples of operation:

[2029] feedback = {'user_id': 'B', 'feedback': 'Customer A showed interest in the proposal.'}

[2030] response = requests.post(api_url, json=feedback)

[2031] Step 7: Emotion Analysis

[2032] How the emotion engine works:

[2033] The emotion engine analyzes the user's voice and facial expressions to recognize their emotions. The analysis results are sent to the server.

[2034] Input: User voice data, facial expression data

[2035] Output: Emotion analysis results

[2036] Specific examples of operation:

[2037] emotion_data = {'stress_level': 'high', 'emotion': 'anxiety'}

[2038] response = requests.post(emotion_api_url, json=emotion_data)

[2039] Step 8: Advice Adjustment

[2040] Server operation:

[2041] The server dynamically adjusts the content and wording of the advice it provides based on the sentiment analysis results.

[2042] Input: Sentiment analysis results

[2043] Output: Adjusted advice

[2044] Specific examples of operation:

[2045] If the emotion analysis reveals that the sales representative is experiencing stress, the message will be adjusted to, "We recommend proposing the new product to customer A in May. Proceed at your own pace."

[2046] Step 9: Feedback Analysis and System Improvement

[2047] Server operation:

[2048] The server analyzes the collected feedback data to improve the system. It updates the analysis algorithm as needed and formulates the next strategy.

[2049] Input: Feedback data

[2050] Output: Updated analysis algorithm, next strategy planning

[2051] Specific examples of operation:

[2052] feedback_df = pd.read_sql(feedback_query, connection)

[2053] model = train_model(feedback_df)

[2054] save_model(model, 'strategy_model.pkl')

[2055] (Application Example 2)

[2056] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2057] In sales activities, it is difficult to grasp customer emotions in real time and provide appropriate advice based on them. Furthermore, there is still a lack of systems for continuously improving advice while collecting feedback. By solving these challenges, it is necessary to improve the performance of sales members and increase customer satisfaction.

[2058] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting customer information, sales data, and records of sales activities from a database; means for analyzing the collected data to analyze the customer's economic situation and market trends; means for generating individual advice for each sales member based on the analysis results; means for distributing the generated individual advice to each sales member's terminal; means for collecting feedback provided by each sales member and improving the advice and strategy; means for analyzing the user's emotions; means for adjusting the individual advice based on the analyzed emotion data; and means for displaying the adjusted advice to the user. This makes it possible to analyze customer emotions in real time and provide appropriate advice that meets individual needs.

[2059] A "database" is a system for storing, managing, and providing data such as customer information, sales data, and records of sales activities.

[2060] A "collection tool" is a device or program that has the function of obtaining necessary information from a database and sending it to a server for analysis.

[2061] "Analysis tools" refer to devices or programs that process collected data and have the function of analyzing customers' economic conditions and market trends.

[2062] "Generation means" refers to a device or program that has the function of creating individual advice for each sales member based on the analyzed data.

[2063] "Distribution method" refers to a device or program that has the function of sending the generated individual advice to each sales member's terminal.

[2064] A "feedback collection method" refers to a device or program that has the function of collecting feedback provided by sales members on a server.

[2065] An "emotion analysis tool" is a device or program that has the function of analyzing a user's voice and facial expressions to recognize their emotions.

[2066] An "advice adjustment tool" is a device or program that has the function of adjusting the content of individual advice based on analyzed emotional data.

[2067] "Display means" refers to a device or program that has the function of displaying adjusted advice to the user visually or audibly.

[2068] The system for implementing this invention consists of a server, a terminal, and an emotion analysis engine. The server collects customer information, sales data, and records of sales activities from a database, and analyzes this data to understand the customer's economic situation and market trends. Furthermore, it generates individual advice for each sales member based on the analysis results and delivers this advice to the terminal. The terminal displays the advice delivered from the server and collects feedback from the sales member. The emotion analysis engine analyzes the user's voice and facial expressions to recognize their emotions, and the server adjusts the content of the advice based on this.

[2069] Hardware and software to be used

[2070] Server: The server connects to the database and uses Python and SQL to collect, analyze, and generate advice. It also sends the collected feedback to the database in real time using Apache Kafka or similar tools.

[2071] Device: The device uses smart glasses or a tablet to display advice from the server in real time via a web browser or a dedicated application.

[2072] Emotion Analysis Engine: Uses OpenCV and TensorFlow to recognize emotions from user voice and facial expressions. Data is collected using devices such as cameras and microphones.

[2073] Processing flow

[2074] 1. The server collects customer information, sales data, and records of sales activities from the database.

[2075] 2. The server analyzes the collected data to understand the customer's economic situation and market trends.

[2076] 3. Based on the analysis results, the server generates individual advice for each sales member.

[2077] 4. The generated advice is delivered to the sales team members' devices.

[2078] 5. The emotion analysis engine analyzes the user's voice and facial expressions and sends that data to the server.

[2079] 6. The server adjusts the advice based on sentiment data and displays the content on the terminal.

[2080] 7. Sales members implement the advice and input the results as feedback into their terminals.

[2081] 8. The server collects feedback and incorporates it into the next strategy.

[2082] Specific example

[2083] For example, when sales member A wears smart glasses and interacts with customer B, the emotion analysis engine analyzes customer B's facial expressions in real time. If the analysis indicates that customer B is dissatisfied, the server generates advice appropriate to the situation, providing words of encouragement or suggestions for additional proposals. Sales member A adjusts their response based on this and inputs the outcome of the negotiation as feedback, allowing the server to update the data for future strategic planning.

[2084] Example of a prompt

[2085] "I'm designing a system that analyzes customer emotions in real time and provides appropriate advice to sales team members. This system uses smart glasses to analyze customer emotions from their facial expressions. Based on the collected data, it generates appropriate advice to support sales team members' responses. Please provide a detailed design incorporating specific examples."

[2086] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2087] Step 1:

[2088] The server collects customer information, sales data, and records of sales activities from the database. The collected data is then stored in the server's memory. The input is information from the database, and the output is aggregated data stored within the server.

[2089] Step 2:

[2090] The server analyzes the collected data to understand the customer's economic situation and market trends. The analysis is performed using Python and SQL, employing algorithms such as linear regression and time series analysis. The input for this step is the data collected in step 1, and the output is presented in the form of analysis reports and graphs.

[2091] Step 3:

[2092] The server generates personalized advice for each sales member based on the analysis results. This is done using a generative AI model, which extracts specific suggestions from the analysis report that will lead to improved performance for each sales member. The input for this step is the analysis results, and the output is personalized advice.

[2093] Step 4:

[2094] The server delivers the generated individual advice to each sales member's terminal. The advice is transmitted via API and received by the sales members in real time. The input is the generated advice, and the output is the information displayed on the sales member's terminal.

[2095] Step 5:

[2096] The emotion analysis engine analyzes the user's voice and facial expressions and sends the data to the server. The analysis is performed using OpenCV and TensorFlow, and an emotion recognition model is applied. The input for this step is voice and facial expression data collected by the camera and microphone, and the output is recognized emotion data.

[2097] Step 6:

[2098] The server adjusts the advice based on sentiment data. It combines the generated advice with the sentiment data to regenerate the optimal advice. The input is the generated individual advice and sentiment data, and the output is the adjusted advice that takes sentiment into account.

[2099] Step 7:

[2100] The device displays adjusted advice to the user. This is shown in real time on a display such as smart glasses or a tablet. The input is the adjusted advice, and the output is information provided visually or audibly.

[2101] Step 8:

[2102] Sales team members implement the advice and input the results as feedback into their terminals. This feedback is sent to the server and used for generating future advice and developing strategies. The input is feedback from the sales team members, and the output is new data collected by the server.

[2103] Step 9:

[2104] The server updates its analysis algorithm based on the collected feedback and incorporates it into the next strategy formulation. The algorithm improves through continuous learning from the data. The input for this step is the feedback data, and the output is the updated analysis algorithm.

[2105] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2106] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2107] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2108] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2109] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2110] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2111] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2112] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2113] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2114] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2115] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2116] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2117] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2118] 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.

[2119] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2120] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2121] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2122] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2123] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2124] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2125] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[2126] The following is further disclosed regarding the embodiments described above.

[2127] (Claim 1)

[2128] Means for collecting customer information, sales data, and records of sales activities from a database,

[2129] A means of analyzing the economic situation and market trends of customers by analyzing the collected data,

[2130] A means of generating individual advice for each sales member based on the analysis results,

[2131] A means of distributing the generated individual advice to each sales member's terminal,

[2132] A system that includes means to collect feedback from each sales member and improve advice and strategies.

[2133] (Claim 2)

[2134] The system according to claim 1, which updates the analysis algorithm based on feedback provided by each sales member and reflects it in the next strategic planning.

[2135] (Claim 3)

[2136] The system according to claim 1, further comprising means for integrating sales data for the entire team with individual advice to formulate a team strategy.

[2137] "Example 1"

[2138] (Claim 1)

[2139] Means for collecting customer information, sales data, and records of sales activities from a database,

[2140] A means of analyzing the economic situation and market trends of customers by analyzing the collected data,

[2141] A means of generating individual advice for each sales member based on the analysis results,

[2142] A means of inputting prompt sentences into a generative AI model to obtain appropriate advice,

[2143] A means of distributing the generated individual advice to each sales member's terminal,

[2144] We collect feedback from each sales member and use it as a means to improve advice and strategies.

[2145] A means of updating the analysis algorithm based on the collected feedback data,

[2146] A system that includes means for applying an updated analysis algorithm to the next analysis.

[2147] (Claim 2)

[2148] The system according to claim 1, which updates the analysis algorithm based on feedback provided by each sales member and reflects it in the next strategic planning.

[2149] (Claim 3)

[2150] The system according to claim 1, further comprising means for integrating sales data for the entire team with individual advice to formulate a team strategy.

[2151] "Application Example 1"

[2152] (Claim 1)

[2153] Means for collecting customer information, sales data, and records of sales activities from a database,

[2154] A means of analyzing the economic situation and market trends of customers by analyzing the collected data,

[2155] A means of generating individual advice for each sales member based on the analysis results,

[2156] A means of distributing the generated individual advice to each sales member's terminal,

[2157] We collect feedback from each sales member and use it as a means to improve advice and strategies,

[2158] A means of analyzing the collected feedback data and retraining the analysis algorithm,

[2159] A system that includes a means to improve the accuracy of individual advice in subsequent sessions by using a retrained analysis algorithm.

[2160] (Claim 2)

[2161] The system according to claim 1, comprising means for generating individual suggestions based on each user's purchasing data and economic situation, and delivering those suggestions to the user's smart device.

[2162] (Claim 3)

[2163] The system according to claim 1, further comprising means for generating optimal coupon and product suggestions based on an analysis of each user's purchasing patterns, delivering those suggestions to the user's device, and then collecting user responses and purchasing behavior to update the analysis algorithm.

[2164] "Example 2 of combining an emotion engine"

[2165] (Claim 1)

[2166] A means of obtaining customer data, sales information, and sales activity history from a data management system,

[2167] A means of analyzing acquired data to evaluate customers' economic status and market trends,

[2168] A means of generating individual advice for each sales representative based on the evaluation results,

[2169] A means of transferring the generated individual advice to each sales representative's device,

[2170] We collect feedback from each sales representative and use it as a means to improve advice and strategies.

[2171] A system including means for analyzing a user's emotions through voice and facial expressions, and means for dynamically adjusting the expression of advice based on the analysis results.

[2172] (Claim 2)

[2173] The system according to claim 1, which updates the analysis algorithm based on feedback provided by each sales representative and reflects it in the next strategic planning.

[2174] (Claim 3)

[2175] The system according to claim 1, further comprising means for integrating sales data from the entire team with individual advice to formulate a team strategy.

[2176] "Application example 2 when combining with an emotional engine"

[2177] (Claim 1)

[2178] Means for collecting customer information, sales data, and records of sales activities from a database,

[2179] A means of analyzing the economic situation and market trends of customers by analyzing the collected data,

[2180] A means of generating individual advice for each sales member based on the analysis results,

[2181] A means of distributing the generated individual advice to each sales member's terminal,

[2182] We collect feedback from each sales member and use it as a means to improve advice and strategies.

[2183] A means of analyzing user emotions,

[2184] A means of adjusting individual advice based on analyzed emotional data,

[2185] A means of displaying adjusted advice to the user,

[2186] A system that includes this.

[2187] (Claim 2)

[2188] The system according to claim 1, which updates the analysis algorithm based on feedback provided by each sales member and reflects it in the next strategic planning.

[2189] (Claim 3)

[2190] The system according to claim 1, further comprising means for integrating sales data for the entire team with individual advice to formulate a team strategy. [Explanation of Symbols]

[2191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting customer information, sales data, and records of sales activities from a database, A means of analyzing the economic situation and market trends of customers by analyzing the collected data, A means of generating individual advice for each sales member based on the analysis results, A means of distributing the generated individual advice to each sales member's terminal, A system that includes means to collect feedback from each sales member and improve advice and strategies.

2. The system according to claim 1, which updates the analysis algorithm based on feedback provided by each sales member and reflects it in the next strategic planning.

3. The system according to claim 1, further comprising means for integrating sales data for the entire team with individual advice to formulate a team strategy.

Images