system

Abstract

Provide a system. 【Solution means】 Data collection means for sorting and managing business information, Data analysis means for analyzing the business information using a generative model to identify business patterns and success factors, Customer discovery means for identifying potential customers and generating sales strategies based on these customers, Schedule management means for automatically setting appointments and notifying sales staff of relevant information, Interactive agent means for responding in real time to inquiries from customers, Product recommendation means for making product recommendations based on the user's past behavior data, User interface means for receiving product information proposed by users on the sales platform, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In business activities in enterprises, especially for junior sales members, it is difficult to perform tasks efficiently due to their lack of experience, and there may be variations in the quality of customer service. As a result, there is a problem that the sales results become unstable and the overall performance improvement is hindered. Furthermore, the formulation of strategies that make full use of sales data and the automation of customer service have not advanced much, and there are many cases where opportunities for efficiency improvement are lost.

Means for Solving the Problems

[0005] This invention provides a data collection means for organizing and managing sales data, a data analysis means for analyzing sales data using a generation model to identify sales patterns and success factors, a new lead discovery means for identifying potential customers and generating sales strategies, a schedule management means for automatically setting appointments and notifying sales representatives, and an automated response means for responding to customer inquiries in real time. This invention aims to compensate for the lack of experience among young sales members, achieve efficient sales activities and high-quality customer service, and improve sales results as a solution to this problem.

[0006] "Sales data" refers to information related to a company's sales activities, and is a general term for data including customer information, transaction history, and sales activity logs.

[0007] A "generative model" is a machine learning model used to analyze large amounts of data, and is particularly used to identify sales patterns and success factors.

[0008] "Data collection means" refers to a process or device that provides the functionality to acquire, organize, and store necessary data from CRM systems and other sources.

[0009] "Data analysis means" refers to a process or device that has the function of analyzing collected sales data and deriving sales patterns and success factors.

[0010] A "means for discovering new business opportunities" refers to a process or device that has the function of identifying potential customers based on analysis results and generating sales strategies for them.

[0011] A "schedule management system" is a process or device that provides the functionality to automatically set appointments and notify sales representatives.

[0012] An "automated response system" is a process or device that has the function of automatically responding to customer inquiries made in real time. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

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

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

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

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

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

[0019] 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).

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

[0021] [First Embodiment]

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

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

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

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

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

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

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0034] This invention is a system for supporting sales activities and automating customer service. With servers, terminals, and users as the main components, this system operates as follows:

[0035] The core of the system is a server, which has a mechanism to periodically collect sales data from the CRM system. This makes it possible to comprehensively manage customer information, transaction history, sales activity logs, and more. The server analyzes the collected data using a generative model. This model extracts success patterns from past sales activities and customer attributes, and based on this, proposes improvements to the sales strategy.

[0036] In identifying new business opportunities, the server utilizes analysis results to identify potential customers. These potential customers are listed based on past patterns and purchase history, indicating they are likely to be interested but have not yet been approached. This allows the sales team to target efficiently.

[0037] In scheduling scenarios, the server automatically suggests appointments using information from the CRM system and integrates them into the sales representative's calendar. The terminal then notifies each user of this information. Sales representatives can then easily check the notifications from their terminals and approach customers at the appropriate time.

[0038] When a customer makes an inquiry, the server operates a chatbot that provides an automated response. The chatbot uses natural language processing to respond quickly and accurately to customer questions and provide the necessary information. This allows users to receive high-quality customer support at any time.

[0039] As a concrete example, when a customer makes an inquiry about a new product, the server automatically generates detailed information such as product specifications, pricing, and case studies via a chatbot and provides it to the customer in real time. This entire process streamlines sales activities and improves customer satisfaction.

[0040] This invention enables each sales team member, regardless of experience, to perform high-quality sales activities and customer service with the help of data and automation technology, thereby dramatically improving the overall sales performance of the company.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses the CRM system and automatically collects sales data. Customer information, transaction history, sales activity logs, etc., are periodically extracted and stored in the database.

[0044] Step 2:

[0045] The server launches a generative model and analyzes the collected sales data. From the analyzed data, it identifies past success patterns and factors that can lead to improvements in the efficiency of the sales process.

[0046] Step 3:

[0047] The server performs a process to identify potential customers based on the analysis results. This process lists groups of customers who have not yet been approached but are likely to show high interest, and provides this list to the sales team.

[0048] Step 4:

[0049] The server generates appointment suggestions. It automatically adjusts the schedule, calculates the optimal appointment date and time, and registers it in the sales representative's calendar.

[0050] Step 5:

[0051] The terminal sends scheduled appointments and strategic proposals to sales representatives via its notification function. This allows representatives to start sales activities quickly and efficiently.

[0052] Step 6:

[0053] Users check device notifications and approach customers based on recommended actions. Chatbots are used as needed to quickly respond to customer inquiries.

[0054] Step 7:

[0055] The server operates a chatbot in real time to provide automated responses to customer inquiries. By utilizing natural language processing to provide appropriate information, customer satisfaction is improved.

[0056] Step 8:

[0057] The server records all interactions and results, updating the generative model through a feedback loop. Based on this training data, the accuracy of the next proposal is improved.

[0058] (Example 1)

[0059] 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."

[0060] Traditional sales activities and customer service require efficient information management and prompt responses, but manual data processing and communication are prevalent, resulting in a heavy burden on employees. Furthermore, identifying potential customers and managing schedules in a timely manner are difficult, hindering improvements in sales efficiency and customer satisfaction.

[0061] 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.

[0062] In this invention, the server includes data collection means for organizing and managing information, data analysis means for analyzing the information using a generative model and identifying activity patterns and success factors, and new project discovery means for identifying potential targets and generating strategies based on these targets. This enables efficient sales activities and high-quality customer service.

[0063] "Information" refers to a variety of content and records, including data, and serves as the basis for analysis and decision-making.

[0064] "Means" refers to the methods, devices, or mechanisms used to achieve a specific objective.

[0065] A "generative model" is a set of algorithms and methods used to analyze data and discover new insights and patterns.

[0066] "Activity patterns" refer to common movements or tendencies that are repeatedly observed within a particular action or process.

[0067] "Success factors" refer to the conditions or components necessary for a particular activity or project to succeed.

[0068] A "potential target" refers to elements or individuals that have not yet become apparent but have the potential to attract attention in the future.

[0069] A "strategy" is a set of guidelines or policies that are systematically established to achieve a specific objective.

[0070] "Schedule" refers to the planned time and sequence of activities or events that will take place in the future.

[0071] "Person in charge" refers to a person responsible for performing a specific task or role.

[0072] This invention aims to provide a system that streamlines operations and automates customer service by coordinating a server, terminal, and user. The server is the core of this system and uses data collection means to organize information. The server automatically retrieves customer information and transaction history from the CRM system via an API. The server then performs data analysis by feeding this information into a generative AI model to extract activity patterns and success factors. The generative AI model uses Python and TENSORFLOW®, and provides highly accurate analysis results through iterative learning.

[0073] Based on the analysis, the server identifies potential targets and generates strategies. Specifically, it uses clustering techniques to list customers and projects that should be approached next based on past data. This list helps in discovering new opportunities and improves the efficiency of sales activities.

[0074] Furthermore, the server uses a scheduling management system to automatically generate schedules for assigned personnel. It utilizes the Google Calendar API to directly input schedules into the personnel's calendars and notifies them via their devices. This allows for smooth confirmation and modification of schedules.

[0075] For customer inquiries, the server operates a chatbot that provides real-time automated responses. The chatbot uses Dialogflow, which utilizes natural language processing to accurately respond to customer questions, thereby increasing customer satisfaction at any time.

[0076] For example, if a user wants to know about a new product, the server uses a chatbot to immediately provide the user with product details and pricing information. Accordingly, by using the prompt "Please output improvement suggestions based on the latest sales data" as the prompt to the generating AI model, the AI ​​model will automatically provide appropriate improvement suggestions.

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

[0078] Step 1:

[0079] The server connects to the CRM system to periodically collect sales data. Inputs include customer information, transaction history, and sales activity logs. This data is retrieved using an API and stored in a database. The output is a well-organized dataset.

[0080] Step 2:

[0081] The server inputs the collected sales data into a generating AI model. Based on the input data, the AI ​​model performs pattern recognition and predictive analysis. Specifically, data analysis is performed using Python and TensorFlow, and successful sales activity patterns are extracted. The output is the successful patterns as a result of the analysis and proposed sales strategies.

[0082] Step 3:

[0083] The server identifies potential customers using the analysis results. The input consists of success patterns and targeting conditions provided by the AI ​​model. Clustering techniques are used to generate a list of potential customers based on their past purchase history and attributes. The output is a list of potential customers that the sales team should target.

[0084] Step 4:

[0085] The server manages schedules based on information within the CRM system. It automatically generates new appointments, taking into account suggestions from an AI model. Inputs include the sales representative's existing calendar information and AI-generated suggestions. As output, new appointments are added to the representative's schedule using the Google Calendar API, and the representative is notified via their device. This allows sales representatives to manage their schedules efficiently.

[0086] Step 5:

[0087] The server operates a chatbot to respond to user inquiries in real time. Input consists of questions and requests sent by users to the chatbot. Dialogflow is used for natural language processing to automatically generate appropriate answers to inquiries. The output provides users with immediate information and answers, thereby improving customer satisfaction.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] Modern sales platforms demand rapid product recommendations and responses that meet diverse user needs. However, traditional systems fail to effectively utilize accumulated data, resulting in insufficient optimal product recommendations and immediate responses to individual user inquiries. Consequently, improving customer satisfaction and increasing sales efficiency is difficult. Therefore, to address these challenges, a system is needed that leverages users' past behavioral data to automate and timely product recommendations.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes data collection means for organizing and managing sales information, data analysis means for analyzing the sales information using a generative model and identifying sales patterns and success factors, customer discovery means for identifying potential customers and generating sales strategies based on these customers, and product recommendation means. This makes it possible to make effective product suggestions to each user. Furthermore, by using interactive agent means, real-time inquiry response is possible, leading to an improved user experience.

[0093] "Data collection methods for organizing and managing sales information" refers to methods for efficiently accumulating and systematically managing data related to sales activities.

[0094] "Data analysis means for analyzing sales information using a generative model to identify sales patterns and success factors" refers to a method that finds patterns based on past sales data and provides insights for effective sales strategies.

[0095] "Customer discovery methods for identifying potential customers and generating sales strategies based on these customers" refers to methods for finding potential new customers and planning sales activities targeting them.

[0096] "Schedule management methods" refer to methods for appropriately coordinating and managing appointment and event schedules in sales activities.

[0097] "Interactive agent systems" are technologies that automatically respond to customer inquiries and communicate in real time.

[0098] A "product recommendation method that suggests products based on the user's past behavioral data" is a method that analyzes a user's past purchase and browsing history to present the most suitable products for each individual.

[0099] "User interface means for users to receive suggested product information on a sales platform" refers to the design of screens and applications that allow users to receive product suggestions visually and intuitively.

[0100] The system for realizing this invention revolves around a server. The server is equipped with data collection means for organizing and managing sales information, centrally managing various customer data and sales activity logs. This data is stored in Amazon AWS® S3 and retrieved periodically using AWS Lambda.

[0101] The server has a data analysis mechanism that uses a generating AI model to analyze the collected data. This model extracts successful patterns from past sales activities and also functions as a product recommendation mechanism that suggests products based on user behavior data. Specifically, it analyzes stored data to create a list of products most relevant to the user. In addition, it can respond to user inquiries in real time using an interactive agent mechanism that uses Google Dialogflow.

[0102] The user's device is equipped with a user interface for receiving product information suggested by the sales platform. Developed using React Native, it is designed to allow users to intuitively access information. Furthermore, it utilizes Firebase Cloud Messaging to push important notifications and campaign information to users.

[0103] For example, if a user has purchased many summer accessories, the system will suggest autumn outfits and send a notification about the start of a campaign. Also, if a user inquires about the size of an "autumn jacket," an interactive agent will immediately provide the relevant information.

[0104] The following are examples of prompt statements in a generative AI model.

[0105] "Based on the user's past purchase history, suggest the three most relevant products. However, avoid products from the same category."

[0106] "Generate five frequently asked questions about this product and create answers for each."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects customer information and transaction history from multiple data sources to gather sales information and stores it in Amazon AWS S3. Input data comes from CRM systems and other sales databases. This data is automatically retrieved using AWS Lambda and neatly stored in S3. The output is an organized data file stored in cloud storage.

[0110] Step 2:

[0111] The server performs analysis using a generative AI model based on the collected data. Sales data retrieved from AWS S3 is provided as input. The generative AI model analyzes this data to extract sales patterns and successful strategies. In this process, machine learning algorithms detect trends and patterns from historical data, and the output is sales insights as analytical results.

[0112] Step 3:

[0113] The server generates a product suggestion list using the analysis results obtained from the generating AI model. The inputs are sales insights (output from step 2) and past user behavior data. Based on this, a product suggestion list is generated for each user. The output is a personalized product list.

[0114] Step 4:

[0115] The device sends product suggestions and important notifications to the user via Firebase Cloud Messaging. The input is a list of product suggestions provided by the server. The device pushes this information to the user in real time, encouraging direct interaction. The output is a notification displayed on the user's device.

[0116] Step 5:

[0117] When a user makes a product inquiry on their device, the server processes it using Google Dialogflow. The input is a natural language question from the user. The server parses this inquiry via Dialogflow and quickly generates an appropriate response. The output is the specific response sent to the user.

[0118] 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.

[0119] This invention combines a system that supports sales activities and automates customer service with an emotion engine that recognizes user emotions. This system operates primarily with a server, terminals, and users.

[0120] First, the server periodically collects sales data from the CRM system, organizes the information for each customer, and stores it in a database. The collected data is analyzed using a generative model to identify past sales success patterns and propose the optimal sales strategy based on customer attributes.

[0121] The emotion engine analyzes emotions in real time from text data acquired during customer interactions. The server uses this analysis to dynamically optimize the content of communication; for example, if a customer is showing negative emotions, it will respond in a more courteous and attentive manner. This improves the customer experience and increases customer satisfaction.

[0122] The server also handles the identification of new leads and the automatic scheduling of appointments. Here, recommended sales dates are automatically incorporated into the sales representative's calendar, and they are notified via their device. This makes it easier for sales representatives to approach customers at the appropriate time.

[0123] For customer inquiries, the server uses a chatbot to provide real-time responses. The emotion engine recognizes emotions from text and voice and generates responses appropriate to those emotions. For example, if it determines that a customer is not satisfied, the chatbot will quickly provide a solution, enhancing customer support.

[0124] For example, when a customer inquires about an unclear billing issue, the server uses an emotion engine to detect the customer's anxiety or frustration and provides information and supplementary explanations to alleviate it. Throughout this entire process, the server constantly optimizes measures to improve customer satisfaction.

[0125] Thus, this invention improves the efficiency of sales activities and the quality of customer service, reducing the burden on sales representatives while promoting overall improvement in corporate performance. Furthermore, the introduction of emotion recognition technology enables highly accurate customization not possible with conventional sales support systems.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server collects sales data from the CRM system and stores it in a database. This data includes customer information, transaction history, and sales activity logs.

[0129] Step 2:

[0130] The server activates a generative model and analyzes the collected sales data. Here, the server identifies past sales success patterns and characteristics of customer profiles.

[0131] Step 3:

[0132] The server identifies potential customers based on the analysis results. These potential customers are extracted from past similar customer profiles and transaction patterns and listed as targets to whom specific sales strategies can be applied.

[0133] Step 4:

[0134] The server uses an automatic scheduling function to register the most suitable appointments in the sales representative's calendar. Appointments are set considering the priority of potential customers and the sales representative's availability.

[0135] Step 5:

[0136] The terminal notifies sales representatives of proposed appointments and potential customer lists from the server. This notification allows sales representatives to immediately put their sales strategies into action.

[0137] Step 6:

[0138] Users check device notifications and carry out recommended sales activities. By accessing detailed customer information from their devices and selecting the appropriate approach, users can improve the quality of customer interactions.

[0139] Step 7:

[0140] The server activates an emotion engine and analyzes text and voice data during communication with the customer. The server then determines the customer's emotional state and generates a response that corresponds to that emotion.

[0141] Step 8:

[0142] The server generates responses and delivers them to the customer in real time via a chatbot. If the customer shows positive emotions, it offers praise or additional offers; if negative emotions are expressed, it prioritizes problem resolution.

[0143] Step 9:

[0144] The server feeds back the sentiment analysis results to the database and updates the generative model. This learning process continuously improves the accuracy of sentiment analysis and the quality of customer service.

[0145] Step 10:

[0146] The terminal then re-notifies sales representatives of these updates and analysis results, allowing them to use them to improve their next sales activities. Through this cycle, the aim is to improve the efficiency of sales activities and enhance customer satisfaction.

[0147] (Example 2)

[0148] 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".

[0149] In sales activities, there is a need for a system that integrates the acquisition and analysis of customer information, the development of effective sales strategies, and the optimization of communication with customers. In this area, information dispersion and inefficient communication are challenges, making it difficult to conduct efficient sales activities and improve customer satisfaction. Furthermore, it is difficult to quickly grasp and respond to customer emotions, which can lead to a decline in the customer experience.

[0150] 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.

[0151] In this invention, the server includes information gathering means for organizing and managing sales information, information analysis means for analyzing the sales information using a generation artificial intelligence model to identify sales patterns and success factors, and business opportunity discovery means for identifying potential customers and generating sales strategies based on these customers. This enables centralized information and efficient strategy planning. Furthermore, it includes scheduling means for automatically setting up meetings and notifying the relevant personnel of the details, dialogue response means for responding to inquiries from communication partners in real time, emotion analysis means for determining the emotions of the other party from data acquired during communication using an emotion analysis device, and communication optimization means for optimizing the content of the dialogue based on the determined emotions. This dramatically improves the efficiency of communication with customers and enables further improvement in customer satisfaction.

[0152] "Information gathering means" refers to devices and functions used to collect, organize, and manage various types of information related to sales activities.

[0153] "Information analysis means" refers to devices or functions that utilize generative artificial intelligence models to analyze collected sales information in detail and identify specific success patterns and key factors.

[0154] "Sales opportunity generation tools" are devices or functions that help identify potential customers and generate optimal sales strategies based on these customers.

[0155] A "schedule management system" refers to a device or function that automatically sets meeting dates and efficiently notifies the relevant personnel of the information.

[0156] A "dialogue response system" refers to a device or function that responds to customer inquiries in real time and enables smooth communication.

[0157] "Emotional analysis means" refers to a device or function that determines the emotions of the other party based on data acquired during communication through an emotional analysis device.

[0158] A "means for optimizing communication" refers to a device or function that optimizes the content of a conversation according to the emotions that have been identified, thereby enabling higher-quality communication.

[0159] This invention provides an advanced system to support sales activities and automate customer service. The system operates primarily with a server, terminals, and users. Specific embodiments are described below.

[0160] The server collects sales information by linking with a data management system and periodically retrieving sales-related data. This information is diverse, including customer information, past transaction history, and records of sales activities. This information is organized and stored in a database and used as material for later analysis.

[0161] Next, the server uses a generative artificial intelligence model to perform a detailed analysis of the stored sales information. This generative AI model is built using the Python programming language and the TensorFlow library. Specifically, it identifies successful patterns in past sales activities and, based on these, proposes sales strategies tailored to customer attributes. This analysis significantly improves the efficiency of sales activities.

[0162] The terminal is equipped with an emotion analyzer and processes text data acquired during real-time interactions with customers. Using natural language processing technology, it analyzes customer emotions and is designed to prompt gentle and courteous responses to customers exhibiting undesirable emotions. However, the specific response content is provided by the server.

[0163] Users (sales representatives) receive optimized sales schedules provided by the server, enabling them to smoothly carry out sales activities. The automatically set meeting schedules are notified to the user via their device and reflected in their calendar. This allows representatives to approach customers at the appropriate time.

[0164] Furthermore, the server uses a chatbot to respond to customer inquiries in real time. For example, if a customer asks about something unclear regarding their bill, the server will generate a prompt such as, "The customer may be dissatisfied with their statement. Please take prompt and specific action."

[0165] This allows for more efficient communication with customers and improves customer satisfaction. Through such a system, it is possible to achieve both increased efficiency in sales activities and higher quality customer service.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The server collects sales information from the CRM system. Inputs include customer information, transaction history, and sales activity records. The server organizes and integrates this data and stores it in a database. Data processing includes removing duplicate data and standardizing formats. The organized sales information is then stored in the database as output.

[0169] Step 2:

[0170] The server analyzes sales information using a generative artificial intelligence model. It takes the sales information organized in Step 1 as input data. The model performs data calculations to identify past success patterns and generates optimal sales strategies based on customer attributes. Specifically, the model uses TensorFlow to classify and analyze the data. The output is a sales strategy optimized for each customer.

[0171] Step 3:

[0172] The terminal uses an emotion analysis device to analyze the text of conversations with customers. The input is text data acquired in real time. Data processing is performed using natural language processing technology to determine the customer's emotional state. Specifically, it analyzes emotions from the text and sends the results to the server. The output is the customer's emotional state.

[0173] Step 4:

[0174] The server optimizes customer interactions using the results of sentiment analysis. The input is the customer's emotional state, sent from step 3. The server dynamically generates prompts and instructs the user (sales representative) to respond appropriately. Specifically, the AI ​​model generates prompts by applying response templates corresponding to specific emotional states. The output is an optimized communication strategy provided to the user.

[0175] Step 5:

[0176] The server automatically identifies new customers and schedules meetings. Inputs include the sales strategy obtained in step 2 and the sales representative's schedule information. The server compares the data and automatically enters the optimal dates into the calendar. Specifically, recommended business days are selected and notified to the user via their terminal. The automatically arranged meeting schedule is then sent to the sales representative.

[0177] Step 6:

[0178] The server responds to inquiries in real time using a chatbot. Input includes the customer's inquiry and sentiment analysis results. The chatbot performs data calculations based on this information to generate the most appropriate response. Specifically, it adjusts the wording to be more friendly based on the customer's sentiment. The adjusted response is then provided to the customer.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0181] Traditional sales support systems do not take customer emotions into consideration, making it difficult to communicate effectively with individual customers and potentially leading to decreased customer satisfaction. Furthermore, challenges remain in determining the appropriate timing for sales and identifying potential customers. Therefore, there is a need for a solution that improves customer service while reducing the burden on sales representatives.

[0182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0183] In this invention, the server includes information gathering means for organizing and managing sales data, information analysis means for analyzing the sales data using a generative model to identify sales types and success factors, and new lead discovery means for identifying potential customers and generating sales policies based on these customers. This enables increased efficiency in sales activities and the provision of advanced customer service adapted to customer sentiment.

[0184] "Information gathering means" refers to a device or method for systematically collecting and organizing sales data related to customers.

[0185] "Information analysis means" refers to a process or apparatus that uses a generative model to analyze sales data and identify sales patterns and success factors.

[0186] "Methods for discovering new business opportunities" refer to technologies or systems for identifying potential customers and generating sales strategies based on them.

[0187] A "schedule management device" is a device or method for automatically setting sales schedules and notifying sales representatives of that information.

[0188] "Machine response means" refers to a function or device for automatically generating responses in real time to customer inquiries.

[0189] "Emotion recognition means" refers to a function or technology that analyzes a customer's emotions in real time and adapts the response based on the analysis results.

[0190] In the system implementing this invention, a server plays a central role. The server is responsible for organizing and managing sales data, receiving and storing data from the CRM system via information gathering means. This data is analyzed by information analysis means using a generative model, identifying sales patterns based on successful patterns from past sales activities and customer characteristics. The results of this analysis are used to identify potential customers and generate optimal sales strategies. New lead discovery means evaluate customer behavior and attributes to obtain new business opportunities.

[0191] For users, sales schedules and important notifications that are automatically set through the schedule management system are displayed on their devices, helping sales representatives approach customers at the appropriate time.

[0192] Furthermore, the server is equipped with a machine response system for customer inquiries, automatically generating responses in real time. In this process, emotion recognition analyzes customer emotions from text and voice data and customizes the response based on the results. For example, if a customer expresses dissatisfaction, the server takes special measures to mitigate those emotions.

[0193] Related hardware and software may include IBM Watson® Tone Analyzer and Google Cloud Natural Language API for emotion recognition technology. SQL-based databases are also used for the database system.

[0194] For example, if a customer inquires, "I haven't received my order confirmation email yet," the emotion recognition system will detect dissatisfaction and respond quickly with a message such as, "We apologize for the inconvenience. We are working on the confirmation process, so please wait a moment."

[0195] An example of a prompt to the generating AI model is, "Generate a reassuring explanation for customers who have not received an order confirmation email." Based on this prompt, appropriate countermeasures and communication methods will be suggested.

[0196] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0197] Step 1:

[0198] The server periodically collects sales data from the CRM system and stores it in a database. The input is raw data retrieved from the CRM system, and the output is a cleaned database entry. The data is cleansed and corrected for duplicates and missing data before being stored.

[0199] Step 2:

[0200] The server uses a generative AI model to analyze sales data in the database. The input is organized sales data, and the output is a report on sales patterns and success factors. The data analysis tool performs pattern recognition to identify past success stories.

[0201] Step 3:

[0202] The server identifies potential customers using new lead generation methods. The input is customer attribute data obtained as analysis results, and the output is a list of recommended sales strategies. This allows for the presentation of the optimal approach for each market segment.

[0203] Step 4:

[0204] The server notifies sales representatives of their sales schedules via a scheduling system. Inputs include recommended sales strategies and the sales representative's calendar data, while output is an automatically generated sales schedule. The server then sends this information to the terminal via a notification system.

[0205] Step 5:

[0206] The user receives customer inquiries from a terminal and uses a machine response system to provide real-time responses. The input is the customer inquiry text, and the output is the generated response message. An emotion recognition system analyzes the customer's emotions and adjusts the nuances of the text.

[0207] Step 6:

[0208] The server customizes its responses based on emotion recognition results. The input is emotion analysis data, and the output is a response corresponding to that emotion. To enhance user satisfaction, the server uses natural language generation technology to refine its responses.

[0209] Step 7:

[0210] The server provides users with suggestions based on prompts generated by an AI model. The input consists of prompts regarding sales policies and response methods, while the output is the suggested content. This dynamically optimizes sales activities and customer support.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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".

[0227] This invention is a system for supporting sales activities and automating customer service. With servers, terminals, and users as the main components, this system operates as follows:

[0228] The core of the system is a server, which has a mechanism to periodically collect sales data from the CRM system. This makes it possible to comprehensively manage customer information, transaction history, sales activity logs, and more. The server analyzes the collected data using a generative model. This model extracts success patterns from past sales activities and customer attributes, and based on this, proposes improvements to the sales strategy.

[0229] In identifying new business opportunities, the server utilizes analysis results to identify potential customers. These potential customers are listed based on past patterns and purchase history, indicating they are likely to be interested but have not yet been approached. This allows the sales team to target efficiently.

[0230] In scheduling scenarios, the server automatically suggests appointments using information from the CRM system and integrates them into the sales representative's calendar. The terminal then notifies each user of this information. Sales representatives can then easily check the notifications from their terminals and approach customers at the appropriate time.

[0231] When a customer makes an inquiry, the server operates a chatbot that provides an automated response. The chatbot uses natural language processing to respond quickly and accurately to customer questions and provide the necessary information. This allows users to receive high-quality customer support at any time.

[0232] As a concrete example, when a customer makes an inquiry about a new product, the server automatically generates detailed information such as product specifications, pricing, and case studies via a chatbot and provides it to the customer in real time. This entire process streamlines sales activities and improves customer satisfaction.

[0233] This invention enables each sales team member, regardless of experience, to perform high-quality sales activities and customer service with the help of data and automation technology, thereby dramatically improving the overall sales performance of the company.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server accesses the CRM system and automatically collects sales data. Customer information, transaction history, sales activity logs, etc., are periodically extracted and stored in the database.

[0237] Step 2:

[0238] The server launches a generative model and analyzes the collected sales data. From the analyzed data, it identifies past success patterns and factors that can lead to improvements in the efficiency of the sales process.

[0239] Step 3:

[0240] The server performs a process to identify potential customers based on the analysis results. This process lists groups of customers who have not yet been approached but are likely to show high interest, and provides this list to the sales team.

[0241] Step 4:

[0242] The server generates appointment suggestions. It automatically adjusts the schedule, calculates the optimal appointment date and time, and registers it in the sales representative's calendar.

[0243] Step 5:

[0244] The terminal sends scheduled appointments and strategic proposals to sales representatives via its notification function. This allows representatives to start sales activities quickly and efficiently.

[0245] Step 6:

[0246] Users check device notifications and approach customers based on recommended actions. Chatbots are used as needed to quickly respond to customer inquiries.

[0247] Step 7:

[0248] The server operates a chatbot in real time to provide automated responses to customer inquiries. By utilizing natural language processing to provide appropriate information, customer satisfaction is improved.

[0249] Step 8:

[0250] The server records all interactions and results, updating the generative model through a feedback loop. Based on this training data, the accuracy of the next proposal is improved.

[0251] (Example 1)

[0252] 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".

[0253] Traditional sales activities and customer service require efficient information management and prompt responses, but manual data processing and communication are prevalent, resulting in a heavy burden on employees. Furthermore, identifying potential customers and managing schedules in a timely manner are difficult, hindering improvements in sales efficiency and customer satisfaction.

[0254] 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.

[0255] In this invention, the server includes data collection means for organizing and managing information, data analysis means for analyzing the information using a generative model and identifying activity patterns and success factors, and new project discovery means for identifying potential targets and generating strategies based on these targets. This enables efficient sales activities and high-quality customer service.

[0256] "Information" refers to a variety of content and records, including data, and serves as the basis for analysis and decision-making.

[0257] "Means" refers to the methods, devices, or mechanisms used to achieve a specific objective.

[0258] A "generative model" is a set of algorithms and methods used to analyze data and discover new insights and patterns.

[0259] "Activity patterns" refer to common movements or tendencies that are repeatedly observed within a particular action or process.

[0260] "Success factors" refer to the conditions or components necessary for a particular activity or project to succeed.

[0261] A "potential target" refers to elements or individuals that have not yet become apparent but have the potential to attract attention in the future.

[0262] A "strategy" is a set of guidelines or policies that are systematically established to achieve a specific objective.

[0263] "Schedule" refers to the planned time and sequence of activities or events that will take place in the future.

[0264] "Person in charge" refers to a person responsible for performing a specific task or role.

[0265] This invention implements a system that streamlines operations and automates customer service by coordinating a server, terminal, and user. The server is the core of this system and uses data collection means to organize information. The server automatically retrieves customer information and transaction history from the CRM system via an API. The server then performs data analysis by feeding this information into a generative AI model to extract activity patterns and success factors. Python and TensorFlow are used for the generative AI model, and iterative learning provides highly accurate analysis results.

[0266] Based on the analysis, the server identifies potential targets and generates strategies. Specifically, it uses clustering techniques to list customers and projects that should be approached next based on past data. This list helps in discovering new opportunities and improves the efficiency of sales activities.

[0267] Furthermore, the server uses a scheduling system to automatically generate schedules for assigned personnel. It utilizes the Google Calendar API to directly input schedules into the personnel's calendars and notifies them via their devices. This allows for smooth confirmation and modification of schedules.

[0268] For customer inquiries, the server operates a chatbot that provides real-time automated responses. The chatbot uses Dialogflow, which utilizes natural language processing to accurately respond to customer questions, thereby increasing customer satisfaction at any time.

[0269] For example, if a user wants to know about a new product, the server uses a chatbot to immediately provide the user with product details and pricing information. Accordingly, by using the prompt "Please output improvement suggestions based on the latest sales data" as the prompt to the generating AI model, the AI ​​model will automatically provide appropriate improvement suggestions.

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] The server connects to the CRM system to periodically collect sales data. Inputs include customer information, transaction history, and sales activity logs. This data is retrieved using an API and stored in a database. The output is a well-organized dataset.

[0273] Step 2:

[0274] The server inputs the collected sales data into a generating AI model. Based on the input data, the AI ​​model performs pattern recognition and predictive analysis. Specifically, data analysis is performed using Python and TensorFlow, and successful sales activity patterns are extracted. The output is the successful patterns as a result of the analysis and proposed sales strategies.

[0275] Step 3:

[0276] The server identifies potential customers using the analysis results. The input consists of success patterns and targeting conditions provided by the AI ​​model. Clustering techniques are used to generate a list of potential customers based on their past purchase history and attributes. The output is a list of potential customers that the sales team should target.

[0277] Step 4:

[0278] The server manages schedules based on information within the CRM system. It automatically generates new appointments, taking into account suggestions from an AI model. Inputs include the sales representative's existing calendar information and AI-generated suggestions. As output, new appointments are added to the representative's schedule using the Google Calendar API, and the representative is notified via their device. This allows sales representatives to manage their schedules efficiently.

[0279] Step 5:

[0280] The server operates a chatbot to respond to user inquiries in real time. Input consists of questions and requests sent by users to the chatbot. Dialogflow is used for natural language processing to automatically generate appropriate answers to inquiries. The output provides users with immediate information and answers, thereby improving customer satisfaction.

[0281] (Application Example 1)

[0282] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0283] In modern sales platforms, there is a demand for product recommendations tailored to diverse user needs and faster responses. However, in conventional systems, the accumulated data cannot be effectively utilized, and optimal product recommendations for individual users and immediate inquiry responses are not fully carried out. As a result, it is difficult to improve customer satisfaction and enhance sales efficiency. Therefore, in order to solve these problems, a system that utilizes users' past behavior data and automatically and timely executes product recommendations is necessary.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0285] In this invention, the server includes data collection means for organizing and managing business information, data analysis means for analyzing the business information using a generation model to identify business patterns and success factors, customer discovery means for identifying potential customers and generating sales strategies based on these customers, and product recommendation means. Thereby, it becomes possible to make effective product recommendations for each user. Also, by using the dialogue agent means, it is possible to respond to inquiries in real time, leading to an improvement in the user experience.

[0286] The "data collection means for organizing and managing business information" is a method for efficiently accumulating and systematically managing data related to business activities.

[0287] The "data analysis means for analyzing the business information using a generation model to identify business patterns and success factors" is a method for finding patterns based on past business data and providing insights for effective sales strategies.

[0288] "Customer discovery methods for identifying potential customers and generating sales strategies based on these customers" refers to methods for finding potential new customers and planning sales activities targeting them.

[0289] "Schedule management methods" refer to methods for appropriately coordinating and managing appointment and event schedules in sales activities.

[0290] "Interactive agent systems" are technologies that automatically respond to customer inquiries and communicate in real time.

[0291] A "product recommendation method that suggests products based on the user's past behavioral data" is a method that analyzes a user's past purchase and browsing history to present the most suitable products for each individual.

[0292] "User interface means for users to receive suggested product information on a sales platform" refers to the design of screens and applications that allow users to receive product suggestions visually and intuitively.

[0293] The system for realizing this invention revolves around a server. The server is equipped with data collection means for organizing and managing sales information, centrally managing various customer data and sales activity logs. This data is stored in Amazon AWS S3 and retrieved periodically using AWS Lambda.

[0294] The server has a data analysis mechanism that uses a generating AI model to analyze the collected data. This model extracts successful patterns from past sales activities and also functions as a product recommendation mechanism that suggests products based on user behavior data. Specifically, it analyzes stored data to create a list of products most relevant to the user. In addition, it can respond to user inquiries in real time using an interactive agent mechanism that uses Google Dialogflow.

[0295] The user's device is equipped with a user interface for receiving product information suggested by the sales platform. Developed using React Native, it is designed to allow users to intuitively access information. Furthermore, it utilizes Firebase Cloud Messaging to push important notifications and campaign information to users.

[0296] For example, if a user has purchased many summer accessories, the system will suggest autumn outfits and send a notification about the start of a campaign. Also, if a user inquires about the size of an "autumn jacket," an interactive agent will immediately provide the relevant information.

[0297] The following are examples of prompt statements in a generative AI model.

[0298] "Based on the user's past purchase history, suggest the three most relevant products. However, avoid products from the same category."

[0299] "Generate five frequently asked questions about this product and create answers for each."

[0300] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0301] Step 1:

[0302] The server collects customer information and transaction history from multiple data sources to gather sales information and stores it in Amazon AWS S3. Input data comes from CRM systems and other sales databases. This data is automatically retrieved using AWS Lambda and neatly stored in S3. The output is an organized data file stored in cloud storage.

[0303] Step 2:

[0304] The server performs analysis using a generated AI model based on the collected data. As input, sales data obtained from AWS S3 is provided. The generated AI model analyzes this data to extract sales patterns and successful strategies. In this process, a machine learning algorithm detects trends and patterns from past data, and as output, sales insights as analysis results are obtained.

[0305] Step 3:

[0306] The server generates a product recommendation list using the analysis results obtained by the generated AI model. As input, there are the sales insights that are the output of Step 2 and the user's past behavior data. Based on this, a product recommendation list for each user is generated. The output is a list of personalized products.

[0307] Step 4:

[0308] The terminal sends product recommendations and important notifications to the user through Firebase Cloud Messaging. As input, there is the product recommendation list provided by the server. The terminal pushes this information to the user in real time to encourage direct interaction. The output is a notification displayed on the user device.

[0309] Step 5:

[0310] When the user makes an inquiry about a product on the terminal, the server processes this using Google Dialogflow. As input, there is a question in natural language from the user. The server analyzes this inquiry through Dialogflow and quickly generates an appropriate answer. As output, there is a specific answer sent to the user.

[0311] 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.

[0312] This invention combines a system that supports sales activities and automates customer service with an emotion engine that recognizes user emotions. This system operates primarily with a server, terminals, and users.

[0313] First, the server periodically collects sales data from the CRM system, organizes the information for each customer, and stores it in a database. The collected data is analyzed using a generative model to identify past sales success patterns and propose the optimal sales strategy based on customer attributes.

[0314] The emotion engine analyzes emotions in real time from text data acquired during customer interactions. The server uses this analysis to dynamically optimize the content of communication; for example, if a customer is showing negative emotions, it will respond in a more courteous and attentive manner. This improves the customer experience and increases customer satisfaction.

[0315] The server also handles the identification of new leads and the automatic scheduling of appointments. Here, recommended sales dates are automatically incorporated into the sales representative's calendar, and they are notified via their device. This makes it easier for sales representatives to approach customers at the appropriate time.

[0316] For customer inquiries, the server uses a chatbot to provide real-time responses. The emotion engine recognizes emotions from text and voice and generates responses appropriate to those emotions. For example, if it determines that a customer is not satisfied, the chatbot will quickly provide a solution, enhancing customer support.

[0317] For example, when a customer inquires about an unclear billing issue, the server uses an emotion engine to detect the customer's anxiety or frustration and provides information and supplementary explanations to alleviate it. Throughout this entire process, the server constantly optimizes measures to improve customer satisfaction.

[0318] Thus, this invention improves the efficiency of sales activities and the quality of customer service, reducing the burden on sales representatives while promoting overall improvement in corporate performance. Furthermore, the introduction of emotion recognition technology enables highly accurate customization not possible with conventional sales support systems.

[0319] The following describes the processing flow.

[0320] Step 1:

[0321] The server collects sales data from the CRM system and stores it in a database. This data includes customer information, transaction history, and sales activity logs.

[0322] Step 2:

[0323] The server activates a generative model and analyzes the collected sales data. Here, the server identifies past sales success patterns and characteristics of customer profiles.

[0324] Step 3:

[0325] The server identifies potential customers based on the analysis results. These potential customers are extracted from past similar customer profiles and transaction patterns and listed as targets to whom specific sales strategies can be applied.

[0326] Step 4:

[0327] The server uses an automatic scheduling function to register the most suitable appointments in the sales representative's calendar. Appointments are set considering the priority of potential customers and the sales representative's availability.

[0328] Step 5:

[0329] The terminal notifies sales representatives of proposed appointments and potential customer lists from the server. This notification allows sales representatives to immediately put their sales strategies into action.

[0330] Step 6:

[0331] Users check device notifications and carry out recommended sales activities. By accessing detailed customer information from their devices and selecting the appropriate approach, users can improve the quality of customer interactions.

[0332] Step 7:

[0333] The server activates an emotion engine and analyzes text and voice data during communication with the customer. The server then determines the customer's emotional state and generates a response that corresponds to that emotion.

[0334] Step 8:

[0335] The server generates responses and delivers them to the customer in real time via a chatbot. If the customer shows positive emotions, it offers praise or additional offers; if negative emotions are expressed, it prioritizes problem resolution.

[0336] Step 9:

[0337] The server feeds back the sentiment analysis results to the database and updates the generative model. This learning process continuously improves the accuracy of sentiment analysis and the quality of customer service.

[0338] Step 10:

[0339] The terminal then re-notifies sales representatives of these updates and analysis results, allowing them to use them to improve their next sales activities. Through this cycle, the aim is to improve the efficiency of sales activities and enhance customer satisfaction.

[0340] (Example 2)

[0341] 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".

[0342] In sales activities, there is a need for a system that integrates the acquisition and analysis of customer information, the development of effective sales strategies, and the optimization of communication with customers. In this area, information dispersion and inefficient communication are challenges, making it difficult to conduct efficient sales activities and improve customer satisfaction. Furthermore, it is difficult to quickly grasp and respond to customer emotions, which can lead to a decline in the customer experience.

[0343] 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.

[0344] In this invention, the server includes information gathering means for organizing and managing sales information, information analysis means for analyzing the sales information using a generation artificial intelligence model to identify sales patterns and success factors, and business opportunity discovery means for identifying potential customers and generating sales strategies based on these customers. This enables centralized information and efficient strategy planning. Furthermore, it includes scheduling means for automatically setting up meetings and notifying the relevant personnel of the details, dialogue response means for responding to inquiries from communication partners in real time, emotion analysis means for determining the emotions of the other party from data acquired during communication using an emotion analysis device, and communication optimization means for optimizing the content of the dialogue based on the determined emotions. This dramatically improves the efficiency of communication with customers and enables further improvement in customer satisfaction.

[0345] "Information gathering means" refers to devices and functions used to collect, organize, and manage various types of information related to sales activities.

[0346] "Information analysis means" refers to devices or functions that utilize generative artificial intelligence models to analyze collected sales information in detail and identify specific success patterns and key factors.

[0347] "Sales opportunity generation tools" are devices or functions that help identify potential customers and generate optimal sales strategies based on these customers.

[0348] A "schedule management system" refers to a device or function that automatically sets meeting dates and efficiently notifies the relevant personnel of the information.

[0349] A "dialogue response system" refers to a device or function that responds to customer inquiries in real time and enables smooth communication.

[0350] "Emotional analysis means" refers to a device or function that determines the emotions of the other party based on data acquired during communication through an emotional analysis device.

[0351] A "means for optimizing communication" refers to a device or function that optimizes the content of a conversation according to the emotions that have been identified, thereby enabling higher-quality communication.

[0352] This invention provides an advanced system to support sales activities and automate customer service. The system operates primarily with a server, terminals, and users. Specific embodiments are described below.

[0353] The server collects sales information by linking with a data management system and periodically retrieving sales-related data. This information is diverse, including customer information, past transaction history, and records of sales activities. This information is organized and stored in a database and used as material for later analysis.

[0354] Next, the server uses a generative artificial intelligence model to perform a detailed analysis of the stored sales information. This generative AI model is built using the Python programming language and the TensorFlow library. Specifically, it identifies successful patterns in past sales activities and, based on these, proposes sales strategies tailored to customer attributes. This analysis significantly improves the efficiency of sales activities.

[0355] The terminal is equipped with an emotion analyzer and processes text data acquired during real-time interactions with customers. Using natural language processing technology, it analyzes customer emotions and is designed to prompt gentle and courteous responses to customers exhibiting undesirable emotions. However, the specific response content is provided by the server.

[0356] Users (sales representatives) receive optimized sales schedules provided by the server, enabling them to smoothly carry out sales activities. The automatically set meeting schedules are notified to the user via their device and reflected in their calendar. This allows representatives to approach customers at the appropriate time.

[0357] Furthermore, the server uses a chatbot to respond to customer inquiries in real time. For example, if a customer asks about something unclear regarding their bill, the server will generate a prompt such as, "The customer may be dissatisfied with their statement. Please take prompt and specific action."

[0358] This allows for more efficient communication with customers and improves customer satisfaction. Through such a system, it is possible to achieve both increased efficiency in sales activities and higher quality customer service.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server collects sales information from the CRM system. Inputs include customer information, transaction history, and sales activity records. The server organizes and integrates this data and stores it in a database. Data processing includes removing duplicate data and standardizing formats. The organized sales information is then stored in the database as output.

[0362] Step 2:

[0363] The server analyzes sales information using a generative artificial intelligence model. It takes the sales information organized in Step 1 as input data. The model performs data calculations to identify past success patterns and generates optimal sales strategies based on customer attributes. Specifically, the model uses TensorFlow to classify and analyze the data. The output is a sales strategy optimized for each customer.

[0364] Step 3:

[0365] The terminal uses an emotion analysis device to analyze the text of conversations with customers. The input is text data acquired in real time. Data processing is performed using natural language processing technology to determine the customer's emotional state. Specifically, it analyzes emotions from the text and sends the results to the server. The output is the customer's emotional state.

[0366] Step 4:

[0367] The server optimizes customer interactions using the results of sentiment analysis. The input is the customer's emotional state, sent from step 3. The server dynamically generates prompts and instructs the user (sales representative) to respond appropriately. Specifically, the AI ​​model generates prompts by applying response templates corresponding to specific emotional states. The output is an optimized communication strategy provided to the user.

[0368] Step 5:

[0369] The server automatically identifies new customers and schedules meetings. Inputs include the sales strategy obtained in step 2 and the sales representative's schedule information. The server compares the data and automatically enters the optimal dates into the calendar. Specifically, recommended business days are selected and notified to the user via their terminal. The automatically arranged meeting schedule is then sent to the sales representative.

[0370] Step 6:

[0371] The server responds to inquiries in real time using a chatbot. Input includes the customer's inquiry and sentiment analysis results. The chatbot performs data calculations based on this information to generate the most appropriate response. Specifically, it adjusts the wording to be more friendly based on the customer's sentiment. The adjusted response is then provided to the customer.

[0372] (Application Example 2)

[0373] 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."

[0374] Traditional sales support systems do not take customer emotions into consideration, making it difficult to communicate effectively with individual customers and potentially leading to decreased customer satisfaction. Furthermore, challenges remain in determining the appropriate timing for sales and identifying potential customers. Therefore, there is a need for a solution that improves customer service while reducing the burden on sales representatives.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes information gathering means for organizing and managing sales data, information analysis means for analyzing the sales data using a generative model to identify sales types and success factors, and new lead discovery means for identifying potential customers and generating sales policies based on these customers. This enables increased efficiency in sales activities and the provision of advanced customer service adapted to customer sentiment.

[0377] "Information gathering means" refers to a device or method for systematically collecting and organizing sales data related to customers.

[0378] "Information analysis means" refers to a process or apparatus that uses a generative model to analyze sales data and identify sales patterns and success factors.

[0379] "Methods for discovering new business opportunities" refer to technologies or systems for identifying potential customers and generating sales strategies based on them.

[0380] A "schedule management device" is a device or method for automatically setting sales schedules and notifying sales representatives of that information.

[0381] "Machine response means" refers to a function or device for automatically generating responses in real time to customer inquiries.

[0382] "Emotion recognition means" refers to a function or technology that analyzes a customer's emotions in real time and adapts the response based on the analysis results.

[0383] In the system implementing this invention, a server plays a central role. The server is responsible for organizing and managing sales data, receiving and storing data from the CRM system via information gathering means. This data is analyzed by information analysis means using a generative model, identifying sales patterns based on successful patterns from past sales activities and customer characteristics. The results of this analysis are used to identify potential customers and generate optimal sales strategies. New lead discovery means evaluate customer behavior and attributes to obtain new business opportunities.

[0384] For users, sales schedules and important notifications that are automatically set through the schedule management system are displayed on their devices, helping sales representatives approach customers at the appropriate time.

[0385] Furthermore, the server is equipped with a machine response system for customer inquiries, automatically generating responses in real time. In this process, emotion recognition analyzes customer emotions from text and voice data and customizes the response based on the results. For example, if a customer expresses dissatisfaction, the server takes special measures to mitigate those emotions.

[0386] Related hardware and software may include IBM Watson Tone Analyzer and Google Cloud Natural Language API for emotion recognition technology. SQL-based databases are also used for the database system.

[0387] For example, if a customer inquires, "I haven't received my order confirmation email yet," the emotion recognition system will detect dissatisfaction and respond quickly with a message such as, "We apologize for the inconvenience. We are working on the confirmation process, so please wait a moment."

[0388] An example of a prompt to the generating AI model is, "Generate a reassuring explanation for customers who have not received an order confirmation email." Based on this prompt, appropriate countermeasures and communication methods will be suggested.

[0389] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0390] Step 1:

[0391] The server periodically collects sales data from the CRM system and stores it in a database. The input is raw data retrieved from the CRM system, and the output is a cleaned database entry. The data is cleansed and corrected for duplicates and missing data before being stored.

[0392] Step 2:

[0393] The server uses a generative AI model to analyze sales data in the database. The input is organized sales data, and the output is a report on sales patterns and success factors. The data analysis tool performs pattern recognition to identify past success stories.

[0394] Step 3:

[0395] The server identifies potential customers using new lead generation methods. The input is customer attribute data obtained as analysis results, and the output is a list of recommended sales strategies. This allows for the presentation of the optimal approach for each market segment.

[0396] Step 4:

[0397] The server notifies sales representatives of their sales schedules via a scheduling system. Inputs include recommended sales strategies and the sales representative's calendar data, while output is an automatically generated sales schedule. The server then sends this information to the terminal via a notification system.

[0398] Step 5:

[0399] The user receives customer inquiries from a terminal and uses a machine response system to provide real-time responses. The input is the customer inquiry text, and the output is the generated response message. An emotion recognition system analyzes the customer's emotions and adjusts the nuances of the text.

[0400] Step 6:

[0401] The server customizes its responses based on emotion recognition results. The input is emotion analysis data, and the output is a response corresponding to that emotion. To enhance user satisfaction, the server uses natural language generation technology to refine its responses.

[0402] Step 7:

[0403] The server provides users with suggestions based on prompts generated by an AI model. The input consists of prompts regarding sales policies and response methods, while the output is the suggested content. This dynamically optimizes sales activities and customer support.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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".

[0420] This invention is a system for supporting sales activities and automating customer service. With servers, terminals, and users as the main components, this system operates as follows:

[0421] The core of the system is a server, which has a mechanism to periodically collect sales data from the CRM system. This makes it possible to comprehensively manage customer information, transaction history, sales activity logs, and more. The server analyzes the collected data using a generative model. This model extracts success patterns from past sales activities and customer attributes, and based on this, proposes improvements to the sales strategy.

[0422] In identifying new business opportunities, the server utilizes analysis results to identify potential customers. These potential customers are listed based on past patterns and purchase history, indicating they are likely to be interested but have not yet been approached. This allows the sales team to target efficiently.

[0423] In scheduling scenarios, the server automatically suggests appointments using information from the CRM system and integrates them into the sales representative's calendar. The terminal then notifies each user of this information. Sales representatives can then easily check the notifications from their terminals and approach customers at the appropriate time.

[0424] When a customer makes an inquiry, the server operates a chatbot that provides an automated response. The chatbot uses natural language processing to respond quickly and accurately to customer questions and provide the necessary information. This allows users to receive high-quality customer support at any time.

[0425] As a concrete example, when a customer makes an inquiry about a new product, the server automatically generates detailed information such as product specifications, pricing, and case studies via a chatbot and provides it to the customer in real time. This entire process streamlines sales activities and improves customer satisfaction.

[0426] This invention enables each sales team member, regardless of experience, to perform high-quality sales activities and customer service with the help of data and automation technology, thereby dramatically improving the overall sales performance of the company.

[0427] The following describes the processing flow.

[0428] Step 1:

[0429] The server accesses the CRM system and automatically collects sales data. Customer information, transaction history, sales activity logs, etc., are periodically extracted and stored in the database.

[0430] Step 2:

[0431] The server launches a generative model and analyzes the collected sales data. From the analyzed data, it identifies past success patterns and factors that can lead to improvements in the efficiency of the sales process.

[0432] Step 3:

[0433] The server performs a process to identify potential customers based on the analysis results. This process lists groups of customers who have not yet been approached but are likely to show high interest, and provides this list to the sales team.

[0434] Step 4:

[0435] The server generates appointment suggestions. It automatically adjusts the schedule, calculates the optimal appointment date and time, and registers it in the sales representative's calendar.

[0436] Step 5:

[0437] The terminal sends scheduled appointments and strategic proposals to sales representatives via its notification function. This allows representatives to start sales activities quickly and efficiently.

[0438] Step 6:

[0439] Users check device notifications and approach customers based on recommended actions. Chatbots are used as needed to quickly respond to customer inquiries.

[0440] Step 7:

[0441] The server operates a chatbot in real time to provide automated responses to customer inquiries. By utilizing natural language processing to provide appropriate information, customer satisfaction is improved.

[0442] Step 8:

[0443] The server records all interactions and results, updating the generative model through a feedback loop. Based on this training data, the accuracy of the next proposal is improved.

[0444] (Example 1)

[0445] 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."

[0446] Traditional sales activities and customer service require efficient information management and prompt responses, but manual data processing and communication are prevalent, resulting in a heavy burden on employees. Furthermore, identifying potential customers and managing schedules in a timely manner are difficult, hindering improvements in sales efficiency and customer satisfaction.

[0447] 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.

[0448] In this invention, the server includes data collection means for organizing and managing information, data analysis means for analyzing the information using a generative model and identifying activity patterns and success factors, and new project discovery means for identifying potential targets and generating strategies based on these targets. This enables efficient sales activities and high-quality customer service.

[0449] "Information" refers to a variety of content and records, including data, and serves as the basis for analysis and decision-making.

[0450] "Means" refers to the methods, devices, or mechanisms used to achieve a specific objective.

[0451] A "generative model" is a set of algorithms and methods used to analyze data and discover new insights and patterns.

[0452] "Activity patterns" refer to common movements or tendencies that are repeatedly observed within a particular action or process.

[0453] "Success factors" refer to the conditions or components necessary for a particular activity or project to succeed.

[0454] A "potential target" refers to elements or individuals that have not yet become apparent but have the potential to attract attention in the future.

[0455] A "strategy" is a set of guidelines or policies that are systematically established to achieve a specific objective.

[0456] "Schedule" refers to the planned time and sequence of activities or events that will take place in the future.

[0457] "Person in charge" refers to a person responsible for performing a specific task or role.

[0458] This invention implements a system that streamlines operations and automates customer service by coordinating a server, terminal, and user. The server is the core of this system and uses data collection means to organize information. The server automatically retrieves customer information and transaction history from the CRM system via an API. The server then performs data analysis by feeding this information into a generative AI model to extract activity patterns and success factors. Python and TensorFlow are used for the generative AI model, and iterative learning provides highly accurate analysis results.

[0459] Based on the analysis, the server identifies potential targets and generates strategies. Specifically, it uses clustering techniques to list customers and projects that should be approached next based on past data. This list helps in discovering new opportunities and improves the efficiency of sales activities.

[0460] Furthermore, the server uses a scheduling system to automatically generate schedules for assigned personnel. It utilizes the Google Calendar API to directly input schedules into the personnel's calendars and notifies them via their devices. This allows for smooth confirmation and modification of schedules.

[0461] For customer inquiries, the server operates a chatbot that provides real-time automated responses. The chatbot uses Dialogflow, which utilizes natural language processing to accurately respond to customer questions, thereby increasing customer satisfaction at any time.

[0462] For example, if a user wants to know about a new product, the server uses a chatbot to immediately provide the user with product details and pricing information. Accordingly, by using the prompt "Please output improvement suggestions based on the latest sales data" as the prompt to the generating AI model, the AI ​​model will automatically provide appropriate improvement suggestions.

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] The server connects to the CRM system to periodically collect sales data. Inputs include customer information, transaction history, and sales activity logs. This data is retrieved using an API and stored in a database. The output is a well-organized dataset.

[0466] Step 2:

[0467] The server inputs the collected sales data into a generating AI model. Based on the input data, the AI ​​model performs pattern recognition and predictive analysis. Specifically, data analysis is performed using Python and TensorFlow, and successful sales activity patterns are extracted. The output is the successful patterns as a result of the analysis and proposed sales strategies.

[0468] Step 3:

[0469] The server identifies potential customers using the analysis results. The input consists of success patterns and targeting conditions provided by the AI ​​model. Clustering techniques are used to generate a list of potential customers based on their past purchase history and attributes. The output is a list of potential customers that the sales team should target.

[0470] Step 4:

[0471] The server manages schedules based on information within the CRM system. It automatically generates new appointments, taking into account suggestions from an AI model. Inputs include the sales representative's existing calendar information and AI-generated suggestions. As output, new appointments are added to the representative's schedule using the Google Calendar API, and the representative is notified via their device. This allows sales representatives to manage their schedules efficiently.

[0472] Step 5:

[0473] The server operates a chatbot to respond to user inquiries in real time. Input consists of questions and requests sent by users to the chatbot. Dialogflow is used for natural language processing to automatically generate appropriate answers to inquiries. The output provides users with immediate information and answers, thereby improving customer satisfaction.

[0474] (Application Example 1)

[0475] 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."

[0476] Modern sales platforms demand rapid product recommendations and responses that meet diverse user needs. However, traditional systems fail to effectively utilize accumulated data, resulting in insufficient optimal product recommendations and immediate responses to individual user inquiries. Consequently, improving customer satisfaction and increasing sales efficiency is difficult. Therefore, to address these challenges, a system is needed that leverages users' past behavioral data to automate and timely product recommendations.

[0477] 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.

[0478] In this invention, the server includes data collection means for organizing and managing sales information, data analysis means for analyzing the sales information using a generative model and identifying sales patterns and success factors, customer discovery means for identifying potential customers and generating sales strategies based on these customers, and product recommendation means. This makes it possible to make effective product suggestions to each user. Furthermore, by using interactive agent means, real-time inquiry response is possible, leading to an improved user experience.

[0479] "Data collection methods for organizing and managing sales information" refers to methods for efficiently accumulating and systematically managing data related to sales activities.

[0480] "Data analysis means for analyzing sales information using a generative model to identify sales patterns and success factors" refers to a method that finds patterns based on past sales data and provides insights for effective sales strategies.

[0481] "Customer discovery methods for identifying potential customers and generating sales strategies based on these customers" refers to methods for finding potential new customers and planning sales activities targeting them.

[0482] "Schedule management methods" refer to methods for appropriately coordinating and managing appointment and event schedules in sales activities.

[0483] "Interactive agent systems" are technologies that automatically respond to customer inquiries and communicate in real time.

[0484] A "product recommendation method that suggests products based on the user's past behavioral data" is a method that analyzes a user's past purchase and browsing history to present the most suitable products for each individual.

[0485] "User interface means for users to receive suggested product information on a sales platform" refers to the design of screens and applications that allow users to receive product suggestions visually and intuitively.

[0486] The system for realizing this invention revolves around a server. The server is equipped with data collection means for organizing and managing sales information, centrally managing various customer data and sales activity logs. This data is stored in Amazon AWS S3 and retrieved periodically using AWS Lambda.

[0487] The server has a data analysis mechanism that uses a generating AI model to analyze the collected data. This model extracts successful patterns from past sales activities and also functions as a product recommendation mechanism that suggests products based on user behavior data. Specifically, it analyzes stored data to create a list of products most relevant to the user. In addition, it can respond to user inquiries in real time using an interactive agent mechanism that uses Google Dialogflow.

[0488] The user's device is equipped with a user interface for receiving product information suggested by the sales platform. Developed using React Native, it is designed to allow users to intuitively access information. Furthermore, it utilizes Firebase Cloud Messaging to push important notifications and campaign information to users.

[0489] For example, if a user has purchased many summer accessories, the system will suggest autumn outfits and send a notification about the start of a campaign. Also, if a user inquires about the size of an "autumn jacket," an interactive agent will immediately provide the relevant information.

[0490] The following are examples of prompt statements in a generative AI model.

[0491] "Based on the user's past purchase history, suggest the three most relevant products. However, avoid products from the same category."

[0492] "Generate five frequently asked questions about this product and create answers for each."

[0493] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0494] Step 1:

[0495] The server collects customer information and transaction history from multiple data sources to gather sales information and stores it in Amazon AWS S3. Input data comes from CRM systems and other sales databases. This data is automatically retrieved using AWS Lambda and neatly stored in S3. The output is an organized data file stored in cloud storage.

[0496] Step 2:

[0497] The server performs analysis using a generative AI model based on the collected data. Sales data retrieved from AWS S3 is provided as input. The generative AI model analyzes this data to extract sales patterns and successful strategies. In this process, machine learning algorithms detect trends and patterns from historical data, and the output is sales insights as analytical results.

[0498] Step 3:

[0499] The server generates a product suggestion list using the analysis results obtained from the generating AI model. The inputs are sales insights (output from step 2) and past user behavior data. Based on this, a product suggestion list is generated for each user. The output is a personalized product list.

[0500] Step 4:

[0501] The device sends product suggestions and important notifications to the user via Firebase Cloud Messaging. The input is a list of product suggestions provided by the server. The device pushes this information to the user in real time, encouraging direct interaction. The output is a notification displayed on the user's device.

[0502] Step 5:

[0503] When a user makes a product inquiry on their device, the server processes it using Google Dialogflow. The input is a natural language question from the user. The server parses this inquiry via Dialogflow and quickly generates an appropriate response. The output is the specific response sent to the user.

[0504] 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.

[0505] This invention combines a system that supports sales activities and automates customer service with an emotion engine that recognizes user emotions. This system operates primarily with a server, terminals, and users.

[0506] First, the server periodically collects sales data from the CRM system, organizes the information for each customer, and stores it in a database. The collected data is analyzed using a generative model to identify past sales success patterns and propose the optimal sales strategy based on customer attributes.

[0507] The emotion engine analyzes emotions in real time from text data acquired during customer interactions. The server uses this analysis to dynamically optimize the content of communication; for example, if a customer is showing negative emotions, it will respond in a more courteous and attentive manner. This improves the customer experience and increases customer satisfaction.

[0508] The server also handles the identification of new leads and the automatic scheduling of appointments. Here, recommended sales dates are automatically incorporated into the sales representative's calendar, and they are notified via their device. This makes it easier for sales representatives to approach customers at the appropriate time.

[0509] For customer inquiries, the server uses a chatbot to provide real-time responses. The emotion engine recognizes emotions from text and voice and generates responses appropriate to those emotions. For example, if it determines that a customer is not satisfied, the chatbot will quickly provide a solution, enhancing customer support.

[0510] For example, when a customer inquires about an unclear billing issue, the server uses an emotion engine to detect the customer's anxiety or frustration and provides information and supplementary explanations to alleviate it. Throughout this entire process, the server constantly optimizes measures to improve customer satisfaction.

[0511] Thus, this invention improves the efficiency of sales activities and the quality of customer service, reducing the burden on sales representatives while promoting overall improvement in corporate performance. Furthermore, the introduction of emotion recognition technology enables highly accurate customization not possible with conventional sales support systems.

[0512] The following describes the processing flow.

[0513] Step 1:

[0514] The server collects sales data from the CRM system and stores it in a database. This data includes customer information, transaction history, and sales activity logs.

[0515] Step 2:

[0516] The server activates a generative model and analyzes the collected sales data. Here, the server identifies past sales success patterns and characteristics of customer profiles.

[0517] Step 3:

[0518] The server identifies potential customers based on the analysis results. These potential customers are extracted from past similar customer profiles and transaction patterns and listed as targets to whom specific sales strategies can be applied.

[0519] Step 4:

[0520] The server uses an automatic scheduling function to register the most suitable appointments in the sales representative's calendar. Appointments are set considering the priority of potential customers and the sales representative's availability.

[0521] Step 5:

[0522] The terminal notifies sales representatives of proposed appointments and potential customer lists from the server. This notification allows sales representatives to immediately put their sales strategies into action.

[0523] Step 6:

[0524] Users check device notifications and carry out recommended sales activities. By accessing detailed customer information from their devices and selecting the appropriate approach, users can improve the quality of customer interactions.

[0525] Step 7:

[0526] The server activates an emotion engine and analyzes text and voice data during communication with the customer. The server then determines the customer's emotional state and generates a response that corresponds to that emotion.

[0527] Step 8:

[0528] The server generates responses and delivers them to the customer in real time via a chatbot. If the customer shows positive emotions, it offers praise or additional offers; if negative emotions are expressed, it prioritizes problem resolution.

[0529] Step 9:

[0530] The server feeds back the sentiment analysis results to the database and updates the generative model. This learning process continuously improves the accuracy of sentiment analysis and the quality of customer service.

[0531] Step 10:

[0532] The terminal then re-notifies sales representatives of these updates and analysis results, allowing them to use them to improve their next sales activities. Through this cycle, the aim is to improve the efficiency of sales activities and enhance customer satisfaction.

[0533] (Example 2)

[0534] 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."

[0535] In sales activities, there is a need for a system that integrates the acquisition and analysis of customer information, the development of effective sales strategies, and the optimization of communication with customers. In this area, information dispersion and inefficient communication are challenges, making it difficult to conduct efficient sales activities and improve customer satisfaction. Furthermore, it is difficult to quickly grasp and respond to customer emotions, which can lead to a decline in the customer experience.

[0536] 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.

[0537] In this invention, the server includes information gathering means for organizing and managing sales information, information analysis means for analyzing the sales information using a generation artificial intelligence model to identify sales patterns and success factors, and business opportunity discovery means for identifying potential customers and generating sales strategies based on these customers. This enables centralized information and efficient strategy planning. Furthermore, it includes scheduling means for automatically setting up meetings and notifying the relevant personnel of the details, dialogue response means for responding to inquiries from communication partners in real time, emotion analysis means for determining the emotions of the other party from data acquired during communication using an emotion analysis device, and communication optimization means for optimizing the content of the dialogue based on the determined emotions. This dramatically improves the efficiency of communication with customers and enables further improvement in customer satisfaction.

[0538] "Information gathering means" refers to devices and functions used to collect, organize, and manage various types of information related to sales activities.

[0539] "Information analysis means" refers to devices or functions that utilize generative artificial intelligence models to analyze collected sales information in detail and identify specific success patterns and key factors.

[0540] "Sales opportunity generation tools" are devices or functions that help identify potential customers and generate optimal sales strategies based on these customers.

[0541] A "schedule management system" refers to a device or function that automatically sets meeting dates and efficiently notifies the relevant personnel of the information.

[0542] A "dialogue response system" refers to a device or function that responds to customer inquiries in real time and enables smooth communication.

[0543] "Emotional analysis means" refers to a device or function that determines the emotions of the other party based on data acquired during communication through an emotional analysis device.

[0544] A "means for optimizing communication" refers to a device or function that optimizes the content of a conversation according to the emotions that have been identified, thereby enabling higher-quality communication.

[0545] This invention provides an advanced system to support sales activities and automate customer service. The system operates primarily with a server, terminals, and users. Specific embodiments are described below.

[0546] The server collects sales information by linking with a data management system and periodically retrieving sales-related data. This information is diverse, including customer information, past transaction history, and records of sales activities. This information is organized and stored in a database and used as material for later analysis.

[0547] Next, the server uses a generative artificial intelligence model to perform a detailed analysis of the stored sales information. This generative AI model is built using the Python programming language and the TensorFlow library. Specifically, it identifies successful patterns in past sales activities and, based on these, proposes sales strategies tailored to customer attributes. This analysis significantly improves the efficiency of sales activities.

[0548] The terminal is equipped with an emotion analyzer and processes text data acquired during real-time interactions with customers. Using natural language processing technology, it analyzes customer emotions and is designed to prompt gentle and courteous responses to customers exhibiting undesirable emotions. However, the specific response content is provided by the server.

[0549] Users (sales representatives) receive optimized sales schedules provided by the server, enabling them to smoothly carry out sales activities. The automatically set meeting schedules are notified to the user via their device and reflected in their calendar. This allows representatives to approach customers at the appropriate time.

[0550] Furthermore, the server uses a chatbot to respond to customer inquiries in real time. For example, if a customer asks about something unclear regarding their bill, the server will generate a prompt such as, "The customer may be dissatisfied with their statement. Please take prompt and specific action."

[0551] This allows for more efficient communication with customers and improves customer satisfaction. Through such a system, it is possible to achieve both increased efficiency in sales activities and higher quality customer service.

[0552] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0553] Step 1:

[0554] The server collects sales information from the CRM system. Inputs include customer information, transaction history, and sales activity records. The server organizes and integrates this data and stores it in a database. Data processing includes removing duplicate data and standardizing formats. The organized sales information is then stored in the database as output.

[0555] Step 2:

[0556] The server analyzes sales information using a generative artificial intelligence model. It takes the sales information organized in Step 1 as input data. The model performs data calculations to identify past success patterns and generates optimal sales strategies based on customer attributes. Specifically, the model uses TensorFlow to classify and analyze the data. The output is a sales strategy optimized for each customer.

[0557] Step 3:

[0558] The terminal uses an emotion analysis device to analyze the text of conversations with customers. The input is text data acquired in real time. Data processing is performed using natural language processing technology to determine the customer's emotional state. Specifically, it analyzes emotions from the text and sends the results to the server. The output is the customer's emotional state.

[0559] Step 4:

[0560] The server optimizes customer interactions using the results of sentiment analysis. The input is the customer's emotional state, sent from step 3. The server dynamically generates prompts and instructs the user (sales representative) to respond appropriately. Specifically, the AI ​​model generates prompts by applying response templates corresponding to specific emotional states. The output is an optimized communication strategy provided to the user.

[0561] Step 5:

[0562] The server automatically identifies new customers and schedules meetings. Inputs include the sales strategy obtained in step 2 and the sales representative's schedule information. The server compares the data and automatically enters the optimal dates into the calendar. Specifically, recommended business days are selected and notified to the user via their terminal. The automatically arranged meeting schedule is then sent to the sales representative.

[0563] Step 6:

[0564] The server responds to inquiries in real time using a chatbot. Input includes the customer's inquiry and sentiment analysis results. The chatbot performs data calculations based on this information to generate the most appropriate response. Specifically, it adjusts the wording to be more friendly based on the customer's sentiment. The adjusted response is then provided to the customer.

[0565] (Application Example 2)

[0566] 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."

[0567] Traditional sales support systems do not take customer emotions into consideration, making it difficult to communicate effectively with individual customers and potentially leading to decreased customer satisfaction. Furthermore, challenges remain in determining the appropriate timing for sales and identifying potential customers. Therefore, there is a need for a solution that improves customer service while reducing the burden on sales representatives.

[0568] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0569] In this invention, the server includes information gathering means for organizing and managing sales data, information analysis means for analyzing the sales data using a generative model to identify sales types and success factors, and new lead discovery means for identifying potential customers and generating sales policies based on these customers. This enables increased efficiency in sales activities and the provision of advanced customer service adapted to customer sentiment.

[0570] "Information gathering means" refers to a device or method for systematically collecting and organizing sales data related to customers.

[0571] "Information analysis means" refers to a process or apparatus that uses a generative model to analyze sales data and identify sales patterns and success factors.

[0572] "Methods for discovering new business opportunities" refer to technologies or systems for identifying potential customers and generating sales strategies based on them.

[0573] A "schedule management device" is a device or method for automatically setting sales schedules and notifying sales representatives of that information.

[0574] "Machine response means" refers to a function or device for automatically generating responses in real time to customer inquiries.

[0575] "Emotion recognition means" refers to a function or technology that analyzes a customer's emotions in real time and adapts the response based on the analysis results.

[0576] In the system implementing this invention, a server plays a central role. The server is responsible for organizing and managing sales data, receiving and storing data from the CRM system via information gathering means. This data is analyzed by information analysis means using a generative model, identifying sales patterns based on successful patterns from past sales activities and customer characteristics. The results of this analysis are used to identify potential customers and generate optimal sales strategies. New lead discovery means evaluate customer behavior and attributes to obtain new business opportunities.

[0577] For users, sales schedules and important notifications that are automatically set through the schedule management system are displayed on their devices, helping sales representatives approach customers at the appropriate time.

[0578] Furthermore, the server is equipped with a machine response system for customer inquiries, automatically generating responses in real time. In this process, emotion recognition analyzes customer emotions from text and voice data and customizes the response based on the results. For example, if a customer expresses dissatisfaction, the server takes special measures to mitigate those emotions.

[0579] Related hardware and software may include IBM Watson Tone Analyzer and Google Cloud Natural Language API for emotion recognition technology. SQL-based databases are also used for the database system.

[0580] For example, if a customer inquires, "I haven't received my order confirmation email yet," the emotion recognition system will detect dissatisfaction and respond quickly with a message such as, "We apologize for the inconvenience. We are working on the confirmation process, so please wait a moment."

[0581] An example of a prompt to the generating AI model is, "Generate a reassuring explanation for customers who have not received an order confirmation email." Based on this prompt, appropriate countermeasures and communication methods will be suggested.

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The server periodically collects sales data from the CRM system and stores it in a database. The input is raw data retrieved from the CRM system, and the output is a cleaned database entry. The data is cleansed and corrected for duplicates and missing data before being stored.

[0585] Step 2:

[0586] The server uses a generative AI model to analyze sales data in the database. The input is organized sales data, and the output is a report on sales patterns and success factors. The data analysis tool performs pattern recognition to identify past success stories.

[0587] Step 3:

[0588] The server identifies potential customers using new lead generation methods. The input is customer attribute data obtained as analysis results, and the output is a list of recommended sales strategies. This allows for the presentation of the optimal approach for each market segment.

[0589] Step 4:

[0590] The server notifies sales representatives of their sales schedules via a scheduling system. Inputs include recommended sales strategies and the sales representative's calendar data, while output is an automatically generated sales schedule. The server then sends this information to the terminal via a notification system.

[0591] Step 5:

[0592] The user receives customer inquiries from a terminal and uses a machine response system to provide real-time responses. The input is the customer inquiry text, and the output is the generated response message. An emotion recognition system analyzes the customer's emotions and adjusts the nuances of the text.

[0593] Step 6:

[0594] The server customizes its responses based on emotion recognition results. The input is emotion analysis data, and the output is a response corresponding to that emotion. To enhance user satisfaction, the server uses natural language generation technology to refine its responses.

[0595] Step 7:

[0596] The server provides users with suggestions based on prompts generated by an AI model. The input consists of prompts regarding sales policies and response methods, while the output is the suggested content. This dynamically optimizes sales activities and customer support.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] [Fourth Embodiment]

[0601] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0602] 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.

[0603] 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).

[0604] 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.

[0605] 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.

[0606] 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).

[0607] 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.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] 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".

[0614] This invention is a system for supporting sales activities and automating customer service. With servers, terminals, and users as the main components, this system operates as follows:

[0615] The core of the system is a server, which has a mechanism to periodically collect sales data from the CRM system. This makes it possible to comprehensively manage customer information, transaction history, sales activity logs, and more. The server analyzes the collected data using a generative model. This model extracts success patterns from past sales activities and customer attributes, and based on this, proposes improvements to the sales strategy.

[0616] In identifying new business opportunities, the server utilizes analysis results to identify potential customers. These potential customers are listed based on past patterns and purchase history, indicating they are likely to be interested but have not yet been approached. This allows the sales team to target efficiently.

[0617] In scheduling scenarios, the server automatically suggests appointments using information from the CRM system and integrates them into the sales representative's calendar. The terminal then notifies each user of this information. Sales representatives can then easily check the notifications from their terminals and approach customers at the appropriate time.

[0618] When a customer makes an inquiry, the server operates a chatbot that provides an automated response. The chatbot uses natural language processing to respond quickly and accurately to customer questions and provide the necessary information. This allows users to receive high-quality customer support at any time.

[0619] As a concrete example, when a customer makes an inquiry about a new product, the server automatically generates detailed information such as product specifications, pricing, and case studies via a chatbot and provides it to the customer in real time. This entire process streamlines sales activities and improves customer satisfaction.

[0620] This invention enables each sales team member, regardless of experience, to perform high-quality sales activities and customer service with the help of data and automation technology, thereby dramatically improving the overall sales performance of the company.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The server accesses the CRM system and automatically collects sales data. Customer information, transaction history, sales activity logs, etc., are periodically extracted and stored in the database.

[0624] Step 2:

[0625] The server launches a generative model and analyzes the collected sales data. From the analyzed data, it identifies past success patterns and factors that can lead to improvements in the efficiency of the sales process.

[0626] Step 3:

[0627] The server performs a process to identify potential customers based on the analysis results. This process lists groups of customers who have not yet been approached but are likely to show high interest, and provides this list to the sales team.

[0628] Step 4:

[0629] The server generates appointment suggestions. It automatically adjusts the schedule, calculates the optimal appointment date and time, and registers it in the sales representative's calendar.

[0630] Step 5:

[0631] The terminal sends scheduled appointments and strategic proposals to sales representatives via its notification function. This allows representatives to start sales activities quickly and efficiently.

[0632] Step 6:

[0633] Users check device notifications and approach customers based on recommended actions. Chatbots are used as needed to quickly respond to customer inquiries.

[0634] Step 7:

[0635] The server operates a chatbot in real time to provide automated responses to customer inquiries. By utilizing natural language processing to provide appropriate information, customer satisfaction is improved.

[0636] Step 8:

[0637] The server records all interactions and results, updating the generative model through a feedback loop. Based on this training data, the accuracy of the next proposal is improved.

[0638] (Example 1)

[0639] 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".

[0640] Traditional sales activities and customer service require efficient information management and prompt responses, but manual data processing and communication are prevalent, resulting in a heavy burden on employees. Furthermore, identifying potential customers and managing schedules in a timely manner are difficult, hindering improvements in sales efficiency and customer satisfaction.

[0641] 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.

[0642] In this invention, the server includes data collection means for organizing and managing information, data analysis means for analyzing the information using a generative model and identifying activity patterns and success factors, and new project discovery means for identifying potential targets and generating strategies based on these targets. This enables efficient sales activities and high-quality customer service.

[0643] "Information" refers to a variety of content and records, including data, and serves as the basis for analysis and decision-making.

[0644] "Means" refers to the methods, devices, or mechanisms used to achieve a specific objective.

[0645] A "generative model" is a set of algorithms and methods used to analyze data and discover new insights and patterns.

[0646] "Activity patterns" refer to common movements or tendencies that are repeatedly observed within a particular action or process.

[0647] "Success factors" refer to the conditions or components necessary for a particular activity or project to succeed.

[0648] A "potential target" refers to elements or individuals that have not yet become apparent but have the potential to attract attention in the future.

[0649] A "strategy" is a set of guidelines or policies that are systematically established to achieve a specific objective.

[0650] "Schedule" refers to the planned time and sequence of activities or events that will take place in the future.

[0651] "Person in charge" refers to a person responsible for performing a specific task or role.

[0652] This invention implements a system that streamlines operations and automates customer service by coordinating a server, terminal, and user. The server is the core of this system and uses data collection means to organize information. The server automatically retrieves customer information and transaction history from the CRM system via an API. The server then performs data analysis by feeding this information into a generative AI model to extract activity patterns and success factors. Python and TensorFlow are used for the generative AI model, and iterative learning provides highly accurate analysis results.

[0653] Based on the analysis, the server identifies potential targets and generates strategies. Specifically, it uses clustering techniques to list customers and projects that should be approached next based on past data. This list helps in discovering new opportunities and improves the efficiency of sales activities.

[0654] Furthermore, the server uses a scheduling system to automatically generate schedules for assigned personnel. It utilizes the Google Calendar API to directly input schedules into the personnel's calendars and notifies them via their devices. This allows for smooth confirmation and modification of schedules.

[0655] For customer inquiries, the server operates a chatbot that provides real-time automated responses. The chatbot uses Dialogflow, which utilizes natural language processing to accurately respond to customer questions, thereby increasing customer satisfaction at any time.

[0656] For example, if a user wants to know about a new product, the server uses a chatbot to immediately provide the user with product details and pricing information. Accordingly, by using the prompt "Please output improvement suggestions based on the latest sales data" as the prompt to the generating AI model, the AI ​​model will automatically provide appropriate improvement suggestions.

[0657] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0658] Step 1:

[0659] The server connects to the CRM system to periodically collect sales data. Inputs include customer information, transaction history, and sales activity logs. This data is retrieved using an API and stored in a database. The output is a well-organized dataset.

[0660] Step 2:

[0661] The server inputs the collected sales data into a generating AI model. Based on the input data, the AI ​​model performs pattern recognition and predictive analysis. Specifically, data analysis is performed using Python and TensorFlow, and successful sales activity patterns are extracted. The output is the successful patterns as a result of the analysis and proposed sales strategies.

[0662] Step 3:

[0663] The server identifies potential customers using the analysis results. The input consists of success patterns and targeting conditions provided by the AI ​​model. Clustering techniques are used to generate a list of potential customers based on their past purchase history and attributes. The output is a list of potential customers that the sales team should target.

[0664] Step 4:

[0665] The server manages schedules based on information within the CRM system. It automatically generates new appointments, taking into account suggestions from an AI model. Inputs include the sales representative's existing calendar information and AI-generated suggestions. As output, new appointments are added to the representative's schedule using the Google Calendar API, and the representative is notified via their device. This allows sales representatives to manage their schedules efficiently.

[0666] Step 5:

[0667] The server operates a chatbot to respond to user inquiries in real time. Input consists of questions and requests sent by users to the chatbot. Dialogflow is used for natural language processing to automatically generate appropriate answers to inquiries. The output provides users with immediate information and answers, thereby improving customer satisfaction.

[0668] (Application Example 1)

[0669] 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".

[0670] Modern sales platforms demand rapid product recommendations and responses that meet diverse user needs. However, traditional systems fail to effectively utilize accumulated data, resulting in insufficient optimal product recommendations and immediate responses to individual user inquiries. Consequently, improving customer satisfaction and increasing sales efficiency is difficult. Therefore, to address these challenges, a system is needed that leverages users' past behavioral data to automate and timely product recommendations.

[0671] 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.

[0672] In this invention, the server includes data collection means for organizing and managing sales information, data analysis means for analyzing the sales information using a generative model and identifying sales patterns and success factors, customer discovery means for identifying potential customers and generating sales strategies based on these customers, and product recommendation means. This makes it possible to make effective product suggestions to each user. Furthermore, by using interactive agent means, real-time inquiry response is possible, leading to an improved user experience.

[0673] "Data collection methods for organizing and managing sales information" refers to methods for efficiently accumulating and systematically managing data related to sales activities.

[0674] "Data analysis means for analyzing sales information using a generative model to identify sales patterns and success factors" refers to a method that finds patterns based on past sales data and provides insights for effective sales strategies.

[0675] "Customer discovery methods for identifying potential customers and generating sales strategies based on these customers" refers to methods for finding potential new customers and planning sales activities targeting them.

[0676] "Schedule management methods" refer to methods for appropriately coordinating and managing appointment and event schedules in sales activities.

[0677] "Interactive agent systems" are technologies that automatically respond to customer inquiries and communicate in real time.

[0678] A "product recommendation method that suggests products based on the user's past behavioral data" is a method that analyzes a user's past purchase and browsing history to present the most suitable products for each individual.

[0679] "User interface means for users to receive suggested product information on a sales platform" refers to the design of screens and applications that allow users to receive product suggestions visually and intuitively.

[0680] The system for realizing this invention revolves around a server. The server is equipped with data collection means for organizing and managing sales information, centrally managing various customer data and sales activity logs. This data is stored in Amazon AWS S3 and retrieved periodically using AWS Lambda.

[0681] The server has a data analysis mechanism that uses a generating AI model to analyze the collected data. This model extracts successful patterns from past sales activities and also functions as a product recommendation mechanism that suggests products based on user behavior data. Specifically, it analyzes stored data to create a list of products most relevant to the user. In addition, it can respond to user inquiries in real time using an interactive agent mechanism that uses Google Dialogflow.

[0682] The user's device is equipped with a user interface for receiving product information suggested by the sales platform. Developed using React Native, it is designed to allow users to intuitively access information. Furthermore, it utilizes Firebase Cloud Messaging to push important notifications and campaign information to users.

[0683] For example, if a user has purchased many summer accessories, the system will suggest autumn outfits and send a notification about the start of a campaign. Also, if a user inquires about the size of an "autumn jacket," an interactive agent will immediately provide the relevant information.

[0684] The following are examples of prompt statements in a generative AI model.

[0685] "Based on the user's past purchase history, suggest the three most relevant products. However, avoid products from the same category."

[0686] "Generate five frequently asked questions about this product and create answers for each."

[0687] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0688] Step 1:

[0689] The server collects customer information and transaction history from multiple data sources to gather sales information and stores it in Amazon AWS S3. Input data comes from CRM systems and other sales databases. This data is automatically retrieved using AWS Lambda and neatly stored in S3. The output is an organized data file stored in cloud storage.

[0690] Step 2:

[0691] The server performs analysis using a generative AI model based on the collected data. Sales data retrieved from AWS S3 is provided as input. The generative AI model analyzes this data to extract sales patterns and successful strategies. In this process, machine learning algorithms detect trends and patterns from historical data, and the output is sales insights as analytical results.

[0692] Step 3:

[0693] The server generates a product suggestion list using the analysis results obtained from the generating AI model. The inputs are sales insights (output from step 2) and past user behavior data. Based on this, a product suggestion list is generated for each user. The output is a personalized product list.

[0694] Step 4:

[0695] The device sends product suggestions and important notifications to the user via Firebase Cloud Messaging. The input is a list of product suggestions provided by the server. The device pushes this information to the user in real time, encouraging direct interaction. The output is a notification displayed on the user's device.

[0696] Step 5:

[0697] When a user makes a product inquiry on their device, the server processes it using Google Dialogflow. The input is a natural language question from the user. The server parses this inquiry via Dialogflow and quickly generates an appropriate response. The output is the specific response sent to the user.

[0698] 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.

[0699] This invention combines a system that supports sales activities and automates customer service with an emotion engine that recognizes user emotions. This system operates primarily with a server, terminals, and users.

[0700] First, the server periodically collects sales data from the CRM system, organizes the information for each customer, and stores it in a database. The collected data is analyzed using a generative model to identify past sales success patterns and propose the optimal sales strategy based on customer attributes.

[0701] The emotion engine analyzes emotions in real time from text data acquired during customer interactions. The server uses this analysis to dynamically optimize the content of communication; for example, if a customer is showing negative emotions, it will respond in a more courteous and attentive manner. This improves the customer experience and increases customer satisfaction.

[0702] The server also handles the identification of new leads and the automatic scheduling of appointments. Here, recommended sales dates are automatically incorporated into the sales representative's calendar, and they are notified via their device. This makes it easier for sales representatives to approach customers at the appropriate time.

[0703] For customer inquiries, the server uses a chatbot to provide real-time responses. The emotion engine recognizes emotions from text and voice and generates responses appropriate to those emotions. For example, if it determines that a customer is not satisfied, the chatbot will quickly provide a solution, enhancing customer support.

[0704] For example, when a customer inquires about an unclear billing issue, the server uses an emotion engine to detect the customer's anxiety or frustration and provides information and supplementary explanations to alleviate it. Throughout this entire process, the server constantly optimizes measures to improve customer satisfaction.

[0705] Thus, this invention improves the efficiency of sales activities and the quality of customer service, reducing the burden on sales representatives while promoting overall improvement in corporate performance. Furthermore, the introduction of emotion recognition technology enables highly accurate customization not possible with conventional sales support systems.

[0706] The following describes the processing flow.

[0707] Step 1:

[0708] The server collects sales data from the CRM system and stores it in a database. This data includes customer information, transaction history, and sales activity logs.

[0709] Step 2:

[0710] The server activates a generative model and analyzes the collected sales data. Here, the server identifies past sales success patterns and characteristics of customer profiles.

[0711] Step 3:

[0712] The server identifies potential customers based on the analysis results. These potential customers are extracted from past similar customer profiles and transaction patterns and listed as targets to whom specific sales strategies can be applied.

[0713] Step 4:

[0714] The server uses an automatic scheduling function to register the most suitable appointments in the sales representative's calendar. Appointments are set considering the priority of potential customers and the sales representative's availability.

[0715] Step 5:

[0716] The terminal notifies sales representatives of proposed appointments and potential customer lists from the server. This notification allows sales representatives to immediately put their sales strategies into action.

[0717] Step 6:

[0718] Users check device notifications and carry out recommended sales activities. By accessing detailed customer information from their devices and selecting the appropriate approach, users can improve the quality of customer interactions.

[0719] Step 7:

[0720] The server activates an emotion engine and analyzes text and voice data during communication with the customer. The server then determines the customer's emotional state and generates a response that corresponds to that emotion.

[0721] Step 8:

[0722] The server generates responses and delivers them to the customer in real time via a chatbot. If the customer shows positive emotions, it offers praise or additional offers; if negative emotions are expressed, it prioritizes problem resolution.

[0723] Step 9:

[0724] The server feeds back the sentiment analysis results to the database and updates the generative model. This learning process continuously improves the accuracy of sentiment analysis and the quality of customer service.

[0725] Step 10:

[0726] The terminal then re-notifies sales representatives of these updates and analysis results, allowing them to use them to improve their next sales activities. Through this cycle, the aim is to improve the efficiency of sales activities and enhance customer satisfaction.

[0727] (Example 2)

[0728] 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".

[0729] In sales activities, there is a need for a system that integrates the acquisition and analysis of customer information, the development of effective sales strategies, and the optimization of communication with customers. In this area, information dispersion and inefficient communication are challenges, making it difficult to conduct efficient sales activities and improve customer satisfaction. Furthermore, it is difficult to quickly grasp and respond to customer emotions, which can lead to a decline in the customer experience.

[0730] 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.

[0731] In this invention, the server includes information gathering means for organizing and managing sales information, information analysis means for analyzing the sales information using a generation artificial intelligence model to identify sales patterns and success factors, and business opportunity discovery means for identifying potential customers and generating sales strategies based on these customers. This enables centralized information and efficient strategy planning. Furthermore, it includes scheduling means for automatically setting up meetings and notifying the relevant personnel of the details, dialogue response means for responding to inquiries from communication partners in real time, emotion analysis means for determining the emotions of the other party from data acquired during communication using an emotion analysis device, and communication optimization means for optimizing the content of the dialogue based on the determined emotions. This dramatically improves the efficiency of communication with customers and enables further improvement in customer satisfaction.

[0732] "Information gathering means" refers to devices and functions used to collect, organize, and manage various types of information related to sales activities.

[0733] "Information analysis means" refers to devices or functions that utilize generative artificial intelligence models to analyze collected sales information in detail and identify specific success patterns and key factors.

[0734] "Sales opportunity generation tools" are devices or functions that help identify potential customers and generate optimal sales strategies based on these customers.

[0735] A "schedule management system" refers to a device or function that automatically sets meeting dates and efficiently notifies the relevant personnel of the information.

[0736] A "dialogue response system" refers to a device or function that responds to customer inquiries in real time and enables smooth communication.

[0737] "Emotional analysis means" refers to a device or function that determines the emotions of the other party based on data acquired during communication through an emotional analysis device.

[0738] A "means for optimizing communication" refers to a device or function that optimizes the content of a conversation according to the emotions that have been identified, thereby enabling higher-quality communication.

[0739] This invention provides an advanced system to support sales activities and automate customer service. The system operates primarily with a server, terminals, and users. Specific embodiments are described below.

[0740] The server collects sales information by linking with a data management system and periodically retrieving sales-related data. This information is diverse, including customer information, past transaction history, and records of sales activities. This information is organized and stored in a database and used as material for later analysis.

[0741] Next, the server uses a generative artificial intelligence model to perform a detailed analysis of the stored sales information. This generative AI model is built using the Python programming language and the TensorFlow library. Specifically, it identifies successful patterns in past sales activities and, based on these, proposes sales strategies tailored to customer attributes. This analysis significantly improves the efficiency of sales activities.

[0742] The terminal is equipped with an emotion analyzer and processes text data acquired during real-time interactions with customers. Using natural language processing technology, it analyzes customer emotions and is designed to prompt gentle and courteous responses to customers exhibiting undesirable emotions. However, the specific response content is provided by the server.

[0743] Users (sales representatives) receive optimized sales schedules provided by the server, enabling them to smoothly carry out sales activities. The automatically set meeting schedules are notified to the user via their device and reflected in their calendar. This allows representatives to approach customers at the appropriate time.

[0744] Furthermore, the server uses a chatbot to respond to customer inquiries in real time. For example, if a customer asks about something unclear regarding their bill, the server will generate a prompt such as, "The customer may be dissatisfied with their statement. Please take prompt and specific action."

[0745] This allows for more efficient communication with customers and improves customer satisfaction. Through such a system, it is possible to achieve both increased efficiency in sales activities and higher quality customer service.

[0746] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0747] Step 1:

[0748] The server collects sales information from the CRM system. Inputs include customer information, transaction history, and sales activity records. The server organizes and integrates this data and stores it in a database. Data processing includes removing duplicate data and standardizing formats. The organized sales information is then stored in the database as output.

[0749] Step 2:

[0750] The server analyzes sales information using a generative artificial intelligence model. It takes the sales information organized in Step 1 as input data. The model performs data calculations to identify past success patterns and generates optimal sales strategies based on customer attributes. Specifically, the model uses TensorFlow to classify and analyze the data. The output is a sales strategy optimized for each customer.

[0751] Step 3:

[0752] The terminal uses an emotion analysis device to analyze the text of conversations with customers. The input is text data acquired in real time. Data processing is performed using natural language processing technology to determine the customer's emotional state. Specifically, it analyzes emotions from the text and sends the results to the server. The output is the customer's emotional state.

[0753] Step 4:

[0754] The server optimizes customer interactions using the results of sentiment analysis. The input is the customer's emotional state, sent from step 3. The server dynamically generates prompts and instructs the user (sales representative) to respond appropriately. Specifically, the AI ​​model generates prompts by applying response templates corresponding to specific emotional states. The output is an optimized communication strategy provided to the user.

[0755] Step 5:

[0756] The server automatically identifies new customers and schedules meetings. Inputs include the sales strategy obtained in step 2 and the sales representative's schedule information. The server compares the data and automatically enters the optimal dates into the calendar. Specifically, recommended business days are selected and notified to the user via their terminal. The automatically arranged meeting schedule is then sent to the sales representative.

[0757] Step 6:

[0758] The server responds to inquiries in real time using a chatbot. Input includes the customer's inquiry and sentiment analysis results. The chatbot performs data calculations based on this information to generate the most appropriate response. Specifically, it adjusts the wording to be more friendly based on the customer's sentiment. The adjusted response is then provided to the customer.

[0759] (Application Example 2)

[0760] 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".

[0761] Traditional sales support systems do not take customer emotions into consideration, making it difficult to communicate effectively with individual customers and potentially leading to decreased customer satisfaction. Furthermore, challenges remain in determining the appropriate timing for sales and identifying potential customers. Therefore, there is a need for a solution that improves customer service while reducing the burden on sales representatives.

[0762] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0763] In this invention, the server includes information gathering means for organizing and managing sales data, information analysis means for analyzing the sales data using a generative model to identify sales types and success factors, and new lead discovery means for identifying potential customers and generating sales policies based on these customers. This enables increased efficiency in sales activities and the provision of advanced customer service adapted to customer sentiment.

[0764] "Information gathering means" refers to a device or method for systematically collecting and organizing sales data related to customers.

[0765] "Information analysis means" refers to a process or apparatus that uses a generative model to analyze sales data and identify sales patterns and success factors.

[0766] "Methods for discovering new business opportunities" refer to technologies or systems for identifying potential customers and generating sales strategies based on them.

[0767] A "schedule management device" is a device or method for automatically setting sales schedules and notifying sales representatives of that information.

[0768] "Machine response means" refers to a function or device for automatically generating responses in real time to customer inquiries.

[0769] "Emotion recognition means" refers to a function or technology that analyzes a customer's emotions in real time and adapts the response based on the analysis results.

[0770] In the system implementing this invention, a server plays a central role. The server is responsible for organizing and managing sales data, receiving and storing data from the CRM system via information gathering means. This data is analyzed by information analysis means using a generative model, identifying sales patterns based on successful patterns from past sales activities and customer characteristics. The results of this analysis are used to identify potential customers and generate optimal sales strategies. New lead discovery means evaluate customer behavior and attributes to obtain new business opportunities.

[0771] For users, sales schedules and important notifications that are automatically set through the schedule management system are displayed on their devices, helping sales representatives approach customers at the appropriate time.

[0772] Furthermore, the server is equipped with a machine response system for customer inquiries, automatically generating responses in real time. In this process, emotion recognition analyzes customer emotions from text and voice data and customizes the response based on the results. For example, if a customer expresses dissatisfaction, the server takes special measures to mitigate those emotions.

[0773] Related hardware and software may include IBM Watson Tone Analyzer and Google Cloud Natural Language API for emotion recognition technology. SQL-based databases are also used for the database system.

[0774] For example, if a customer inquires, "I haven't received my order confirmation email yet," the emotion recognition system will detect dissatisfaction and respond quickly with a message such as, "We apologize for the inconvenience. We are working on the confirmation process, so please wait a moment."

[0775] An example of a prompt to the generating AI model is, "Generate a reassuring explanation for customers who have not received an order confirmation email." Based on this prompt, appropriate countermeasures and communication methods will be suggested.

[0776] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0777] Step 1:

[0778] The server periodically collects sales data from the CRM system and stores it in a database. The input is raw data retrieved from the CRM system, and the output is a cleaned database entry. The data is cleansed and corrected for duplicates and missing data before being stored.

[0779] Step 2:

[0780] The server uses a generative AI model to analyze sales data in the database. The input is organized sales data, and the output is a report on sales patterns and success factors. The data analysis tool performs pattern recognition to identify past success stories.

[0781] Step 3:

[0782] The server identifies potential customers using new lead generation methods. The input is customer attribute data obtained as analysis results, and the output is a list of recommended sales strategies. This allows for the presentation of the optimal approach for each market segment.

[0783] Step 4:

[0784] The server notifies sales representatives of their sales schedules via a scheduling system. Inputs include recommended sales strategies and the sales representative's calendar data, while output is an automatically generated sales schedule. The server then sends this information to the terminal via a notification system.

[0785] Step 5:

[0786] The user receives customer inquiries from a terminal and uses a machine response system to provide real-time responses. The input is the customer inquiry text, and the output is the generated response message. An emotion recognition system analyzes the customer's emotions and adjusts the nuances of the text.

[0787] Step 6:

[0788] The server customizes its responses based on emotion recognition results. The input is emotion analysis data, and the output is a response corresponding to that emotion. To enhance user satisfaction, the server uses natural language generation technology to refine its responses.

[0789] Step 7:

[0790] The server provides users with suggestions based on prompts generated by an AI model. The input consists of prompts regarding sales policies and response methods, while the output is the suggested content. This dynamically optimizes sales activities and customer support.

[0791] 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.

[0792] 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.

[0793] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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."

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] The following is further disclosed regarding the embodiments described above.

[0813] (Claim 1)

[0814] A data collection method for organizing and managing sales data,

[0815] A data analysis means that uses a generative model to analyze the sales data and identify sales patterns and success factors,

[0816] A method for identifying potential customers and generating new business opportunities based on these customers,

[0817] A scheduling management system that automatically sets appointments and notifies sales representatives of the relevant information,

[0818] A system that includes an automated response mechanism for responding to customer inquiries in real time.

[0819] (Claim 2)

[0820] The system according to claim 1, wherein the data analysis means extracts successful patterns from past sales activities and optimizes sales strategies based on specific customer attributes.

[0821] (Claim 3)

[0822] The system according to claim 1, wherein the schedule management means synchronizes with the sales representative's calendar system and automatically inputs proposed appointments.

[0823] "Example 1"

[0824] (Claim 1)

[0825] A data collection method for organizing and managing information,

[0826] A data analysis means that analyzes the information using a generative model to identify activity patterns and success factors,

[0827] A method for identifying potential targets and generating strategies based on these targets to discover new projects,

[0828] A schedule management system that automatically sets schedules and notifies the person in charge of the relevant information,

[0829] A system that includes an automated response mechanism to respond to user inquiries in real time.

[0830] (Claim 2)

[0831] The system according to claim 1, wherein the data analysis means extracts successful patterns from past activities and optimizes strategies based on specific attributes.

[0832] (Claim 3)

[0833] The system according to claim 1, wherein the schedule management means synchronizes with the schedule system of the person in charge and automatically inputs the proposed schedule.

[0834] "Application Example 1"

[0835] (Claim 1)

[0836] A data collection method for organizing and managing sales information,

[0837] A data analysis means that analyzes the sales information using a generative model and identifies sales patterns and success factors,

[0838] A customer acquisition method for identifying potential customers and generating sales strategies based on these customers,

[0839] A scheduling management system that automatically sets appointments and notifies sales representatives of the relevant information,

[0840] A conversational agent system that responds to customer inquiries in real time,

[0841] A product recommendation method that suggests products based on the user's past behavioral data,

[0842] A user interface means for users to receive product information suggested on a sales platform,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, wherein the data analysis means extracts successful patterns from past sales activities, optimizes sales strategies based on specific customer attributes, and makes product recommendations.

[0846] (Claim 3)

[0847] The system according to claim 1, wherein the scheduling means synchronizes with the sales representative's schedule management system, automatically enters proposed appointments, and sends important notifications on the sales platform.

[0848] "Example 2 of combining an emotion engine"

[0849] (Claim 1)

[0850] Information gathering means for organizing and managing sales information,

[0851] An information analysis means that uses a generative artificial intelligence model to analyze the sales information and identify sales patterns and success factors,

[0852] A method for identifying potential customers and generating sales strategies based on these successful customers,

[0853] A scheduling tool that automatically sets up meetings and notifies the relevant personnel of the details,

[0854] A dialogue response system that responds in real time to inquiries from the communication partner,

[0855] An emotion analysis means that uses an emotion analysis device to determine the emotions of the other party from data acquired during communication,

[0856] A system including a communication optimization means that optimizes dialogue content based on identified emotions.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the information analysis means extracts successful patterns from past sales activities and optimizes sales strategies based on specific customer characteristics.

[0859] (Claim 3)

[0860] The system according to claim 1, wherein the scheduling means synchronizes with the schedule management system of the person in charge of the work and automatically inputs the proposed meeting.

[0861] "Application example 2 when combining with an emotional engine"

[0862] (Claim 1)

[0863] Information gathering means for organizing and managing sales data,

[0864] An information analysis means that uses a generative model to analyze the sales data and identify the type of sales and success factors,

[0865] A method for identifying potential customers and generating new business opportunities based on these customers,

[0866] A scheduling management system that automatically sets dates and notifies sales representatives of the relevant information,

[0867] A machine response system that responds to customer inquiries in real time,

[0868] A system that includes emotion recognition means to analyze customer emotions in real time and adapt the content of responses based on those emotions.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein the information analysis means extracts successful patterns from past sales activities and optimizes sales policies based on specific customer characteristics.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein the schedule management means synchronizes with the schedule management system of sales representatives and automatically inputs proposed dates. [Explanation of Symbols]

[0873] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method for organizing and managing sales information, A data analysis means that analyzes the sales information using a generative model and identifies sales patterns and success factors, A customer acquisition method for identifying potential customers and generating sales strategies based on these customers, A scheduling management system that automatically sets appointments and notifies sales representatives of the relevant information, A conversational agent system that responds to customer inquiries in real time, A product recommendation method that suggests products based on the user's past behavioral data, A user interface means for users to receive product information suggested on a sales platform, A system that includes this.

2. The system according to claim 1, wherein the data analysis means extracts successful patterns from past sales activities, optimizes sales strategies based on specific customer attributes, and makes product recommendations.

3. The system according to claim 1, wherein the scheduling means synchronizes with the sales representative's schedule management system, automatically inputs proposed appointments, and sends important notifications on the sales platform.

Images