system

Abstract

We provide the system. [Solution] A means of collecting customer information and identifying potential customers to be processed, A means of conducting customer analysis based on collected information and developing sales strategies, A means to monitor the progress of business negotiations and provide advice for the success of those negotiations, A method for predicting the likelihood of closing a deal based on past sales negotiation data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In business activities, it is difficult to accurately evaluate the priority of customers or predict the success probability of business negotiations. For this reason, the sales team spends excessive time and labor on analysis and administrative work, which hinders efficient sales activities. There is also a problem that it is difficult to optimize limited sales resources to approach customers.

Means for Solving the Problems

[0005] This invention provides a system that collects customer information, identifies potential customers, determines priorities, and recommends sales resources accordingly. Furthermore, it conducts detailed analysis of customers based on the collected information and builds effective sales strategies. It can also improve the probability of successful deals by monitoring the progress of negotiations and providing advice for their success. In addition, it optimizes overall sales activities by predicting the likelihood of closing deals based on past negotiation data, creating risk management guidelines based on that information, and presenting cross-selling and upselling opportunities.

[0006] "Customer information" refers to all data relating to individuals or entities that are the target of sales and marketing activities, including purchase history, inquiries, behavioral history, and relevant public data.

[0007] A "potential customer" refers to an individual or company that has shown interest in a product or service and has the potential to enter into a contract in the future, even though they have not yet entered into a contract.

[0008] "Priority" is an indicator used to improve the efficiency of sales activities by indicating a ranking based on specific criteria or metrics to determine the allocation of sales resources and the order in which to respond.

[0009] "Sales resources" refer to the resources that a sales team uses to carry out its activities, and include personnel, time, budget, equipment, and information.

[0010] A "sales strategy" refers to a set of actions and measures planned and implemented to achieve a specific commercial objective, and may include customer needs analysis, pricing, and promotional activities.

[0011] "Business negotiation" refers to the process of negotiating the sale of goods or services as part of sales activities, and is an activity aimed at adjusting terms and closing a deal through communication with the customer.

[0012] "Progress" is an indicator that shows how far a business deal or project is progressing towards its plan, and is used to evaluate the completion status of each step and the degree to which deliverables are achieved.

[0013] "Past sales negotiation data" refers to records of previous sales negotiations, including information such as factors contributing to success or failure, customer reactions, and the terms of the negotiation.

[0014] "Probability of closing a deal" refers to the probability that a particular business negotiation will be successful and lead to a contract, and it is a numerical value that is predicted by taking various factors into consideration.

[0015] "Risk management" refers to a systematic process for identifying, evaluating, and responding to risks in business activities, with the aim of eliminating or mitigating those risks.

[0016] "Cross-selling" refers to a sales technique that involves suggesting other products related to what a customer is currently considering purchasing, thereby encouraging them to make a purchase.

[0017] "Upselling" refers to a sales technique that involves suggesting a higher-end or more expensive product to a customer than the one they are currently considering, thereby boosting sales. [Brief explanation of the drawing]

[0018] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the language used in the following description will be explained.

[0021] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention is an automation tool for streamlining sales activities, and it builds sales strategies by acquiring and analyzing customer information. The system operates via a network, and is configured so that the server and user terminals communicate with each other.

[0040] The server collects publicly available customer information from multiple data sources and extracts key information through a data cleansing process. This information is used to identify and prioritize potential customers. For example, the server can prioritize listing customers belonging to specific regions or industries based on industry standards and existing customer profiles.

[0041] Next, the server performs a detailed customer analysis. This aims to identify customer needs and formulate targeted approaches based on historical data and market trends. For example, it can analyze past purchase history to predict product replacement cycles. As a result, the terminal displays the analyzed data along with suggested sales strategies.

[0042] Furthermore, the server monitors the progress of the business negotiation in real time and provides specific advice to improve the probability of success. Specific suggestions tailored to the issues to be resolved and the prospect's areas of interest are fed back to the user's terminal.

[0043] Furthermore, the server is equipped with a system that uses past sales negotiation data to predict the likelihood of closing a deal, and can estimate future sales outcomes by applying machine learning technology. User terminals visually display these prediction results and provide concrete suggestions to support risk management, cross-selling, and upselling strategies.

[0044] For example, the server can analyze past data for specific products with high campaign performance and suggest to the user that they run similar promotions on other untapped customers. In this way, the present invention can improve the accuracy and efficiency of sales activities with an interface that is easy for users without specialized knowledge to use.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects publicly available customer information from the internet and affiliated database systems. Specifically, it automatically retrieves company profiles, industry data, contact information, and other data, and stores it in the database.

[0048] Step 2:

[0049] The server filters the collected data to remove unnecessary information and performs data cleansing to correct for duplicates and missing data. This refines the list of potential customers.

[0050] Step 3:

[0051] Based on the cleansed data, the server applies analytical algorithms to customer attributes and behavioral history to identify potential customers and set priorities.

[0052] Step 4:

[0053] The terminal displays a prioritized list of potential customers sent from the server on a dashboard, making it viewable by the user.

[0054] Step 5:

[0055] When a user selects a specific customer, the server performs a detailed analysis of that customer. It refers to past transaction history and market trends to understand the customer's purchasing tendencies.

[0056] Step 6:

[0057] Based on the analysis results, the server develops an effective approach strategy and sends it to the user's terminal as a recommended plan.

[0058] Step 7:

[0059] The device presents the user with recommended approach strategies, which the user then uses to plan their sales activities.

[0060] Step 8:

[0061] The server monitors the progress of the deal in real time and generates advice based on the progress. It predicts the next steps necessary for the deal's success and provides guidelines.

[0062] Step 9:

[0063] The device provides users with advice and success stories related to business negotiations, supporting them through the process of the negotiation.

[0064] Step 10:

[0065] The server predicts the likelihood of closing a current deal based on a machine learning model and identifies related risks and opportunities.

[0066] Step 11:

[0067] The terminal reports to the user the predicted probability of closing a deal, along with risk management strategies and cross-selling / upselling suggestions based on that prediction. This allows the user to select the optimal sales strategy.

[0068] (Example 1)

[0069] 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."

[0070] In modern sales activities, efficiently collecting vast amounts of customer information and effectively identifying potential customers is a significant challenge. Furthermore, there is a lack of concrete guidelines for developing sales strategies tailored to customer needs, effectively conducting negotiations, and accurately predicting the likelihood of closing a deal. This makes optimizing sales resources difficult and hinders the maximization of sales results.

[0071] 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.

[0072] In this invention, the server includes means for collecting customer information to identify potential customers to be processed, means for performing analysis on customers based on the collected information to build sales strategies, means for monitoring the progress of negotiations and providing advice for the success of those negotiations, means for improving sales strategy proposals by analyzing the characteristics of potential customers using a generative AI model, and means for providing follow-up proposals tailored to the progress of negotiations through a user interface. This makes it possible to improve the accuracy and results of sales activities through efficient collection and analysis of customer information.

[0073] "Customer information" refers to all data related to the customer, such as customer profiles, purchase history, and industry attributes.

[0074] "Methods for identifying potential customers" refers to the process of analyzing customer information from diverse data sources to identify new customers who are likely to make a purchase.

[0075] "Methods for developing a sales strategy" refer to methods for analyzing customer needs and market trends based on collected data, and formulating the optimal sales approach.

[0076] "Means for monitoring the progress of business negotiations" refers to a system for tracking and evaluating the current status and progress of business negotiations in real time.

[0077] "Means of providing advice" refers to methods of generating and providing specific suggestions and instructions to improve the probability of sales success, depending on the situation of the business negotiation.

[0078] "Methods for predicting the likelihood of closing a deal" refer to a process for statistically estimating the probability that a future deal will be closed, based on past sales negotiation data.

[0079] A "generative AI model" is an artificial intelligence technology that supports decision-making by analyzing large amounts of data and extracting patterns and relationships.

[0080] A "user interface" is the visual and manipulative environment through which a user interacts with a system's functions and retrieves information.

[0081] This invention is implemented as an integrated system for collecting and analyzing customer information, formulating sales strategies, and managing the progress of business negotiations. The server automatically collects customer information from various external data sources using APIs and web scraping techniques. Specific software used includes the Python libraries "requests" and "BeautifulSoup".

[0082] The collected data is processed by the server through a data cleansing process to extract important information. Data processing libraries such as Pandas and NumPy are used for this process. Based on this organized information, the server utilizes a generative AI model to identify potential customers, analyze their characteristics, and build an optimal sales strategy.

[0083] Furthermore, the server uses machine learning libraries such as Scikit-learn to analyze past sales data and predict the likelihood of closing a deal. This prediction can generate specific guidelines and advice to increase the success rate of the deal and provide them to the user's terminal. On the terminal, these results and advice are visually displayed through the user interface to help with decision-making for the next steps.

[0084] In actual implementation, the server prompts the user with a message such as, "Based on past sales data, formulate a sales strategy for the next quarter and propose it along with key KPIs," providing input to the AI ​​model. Based on this prompt, the AI ​​performs the necessary analysis and generates specific proposals. Through this process, the user can conduct sales activities efficiently and make optimal use of resources.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server collects customer information from external data sources. The input specifies initial information about the target customer group, and the Python "requests" library is used to retrieve data from APIs and web pages. The data collected in this process includes customer profiles, past transaction information, and industry information. The output is a collection of available raw data.

[0088] Step 2:

[0089] The server performs data cleansing on the collected customer data. The raw data collected in step 1 is used as input. The data is processed using Pandas or NumPy to handle missing values, remove duplicate data, and standardize data formats. The output is the refined, cleansed data.

[0090] Step 3:

[0091] The server performs analysis to identify potential customers using the cleansed data. The cleansed data obtained in step 2 is used as input. The server uses a generative AI model to perform scoring and target customer prioritization based on customer characteristics. The output is a prioritized list of potential customers.

[0092] Step 4:

[0093] The server builds sales strategies based on historical data and market trends. The input is the list of potential customers obtained in step 3 and historical sales data, which is analyzed using machine learning techniques. Scikit-learn is used to predict customer behavior, identify the purchase cycle, and determine the optimal approach. The output is a set of recommended sales strategies.

[0094] Step 5:

[0095] The terminal visually displays the sales strategy and analysis results sent from the server. The input is the sales strategy built in Step 4. Through the user interface, the terminal visualizes key KPIs and strategies in a dashboard format, presenting them in an easy-to-understand manner for the user. The output is a visually clear display of the sales strategy.

[0096] Step 6:

[0097] The server monitors the progress of sales negotiations in real time and generates follow-up suggestions. It uses current negotiation progress information and past customer response data as input. The server utilizes a generation AI model to suggest specific next steps and generate guidelines to increase the success rate of the negotiation. The output is personalized follow-up suggestions.

[0098] Step 7:

[0099] The terminal receives advice from the server and presents it to the user. The input is the follow-up suggestions generated in step 6. The terminal displays these suggestions on the user interface, providing information that helps the user decide on their next course of action. The output is a presentation of specific follow-up actions to the user.

[0100] (Application Example 1)

[0101] 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."

[0102] In sales activities, it is difficult to quickly develop effective sales strategies and make appropriate approaches to potential customers. Furthermore, there is a lack of efficient means to propose products and promotions to target customers. As a result, sales representatives find it difficult to develop personalized strategies for individual customers, leading to missed sales opportunities.

[0103] 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.

[0104] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed; means for performing analysis on customers based on the collected information and building sales strategies; means for monitoring the progress of negotiations and providing advice for the success of those negotiations; means for predicting the likelihood of closing a deal based on past negotiation data; means for visually presenting the analysis results to the user; and means for proposing products and promotions suitable for target customers. This enables sales representatives to quickly and efficiently develop sales strategies and implement personalized approaches to customers.

[0105] "Customer information" refers to all data based on a customer's publicly available profile, purchase history, behavioral history, etc.

[0106] "Potential customers to be processed" refers to prospective customers who should be prioritized for approach in commercial activities.

[0107] "Methods for conducting analysis and developing sales strategies" refers to methods of analyzing collected data and formulating effective sales policies and strategies based on that analysis.

[0108] "A means of monitoring the progress of a business deal and providing advice to help it succeed" refers to a procedure for monitoring the status of ongoing business deals and providing appropriate advice to increase the chances of success.

[0109] "Methods for predicting the likelihood of closing a deal" refer to techniques that use data from past business negotiations to estimate the probability of future business negotiations being successful.

[0110] "Means of visually presenting analysis results to the user" refers to methods of displaying the analyzed data to the user in a visual format such as graphs or charts.

[0111] "Means of proposing products and promotions suitable for target customers" refers to an approach to suggesting the most relevant products and promotional activities to specific customers.

[0112] The system for implementing this invention is to acquire customer information via a network, perform analysis, and build effective sales strategies for customers. The server is built using Python and the Flask framework and collects customer information from multiple data sources. PostgreSQL is used as the database for storing and managing customer data. The server processes the collected data using scikit-learn and analyzes customer purchasing patterns and needs.

[0113] The analysis results generated by the server are sent to the device via API, where they are visually presented to the user as a cross-platform application using React Native. The device displays target customer information, suitable products, and promotional suggestions to the user, and provides real-time updates on the progress of the sales negotiation.

[0114] As a concrete example, by analyzing past customer purchase history, the device can identify that a particular customer regularly purchases products in the same category. In this case, the device can notify that customer of new product suggestions or upsells on related products. This allows users to quickly develop efficient sales strategies.

[0115] As an example of a prompt using a generative AI model, the server will perform appropriate analysis by issuing the instruction, "Identify target customers based on their past purchase history and suggest the most suitable promotion."

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

[0117] Step 1:

[0118] The server collects customer information from multiple data sources over the network. Inputs include public customer profiles and purchase history, while output is centralized customer data. The server uses an API to ingest this data and stores it in a PostgreSQL database.

[0119] Step 2:

[0120] The server cleanses the collected customer data and prepares it for analysis. The input is raw data and may contain unnecessary or inconsistent information. It performs a cleansing process and outputs data formatted to provide useful information. Specifically, it removes duplicate data and imputes missing values.

[0121] Step 3:

[0122] The server uses scikit-learn to perform data analysis and identify target customers and their needs. Cleansed customer data is used as input, and a machine learning model is employed to analyze purchasing patterns. The output is targeting information for individual customers. Specific processing includes customer segmentation and purchase prediction.

[0123] Step 4:

[0124] The server uses an AI model that generates optimal products and promotions for target customers based on the analysis results to make suggestions. The input is targeting information and data on existing promotions, and the output is a customized promotion strategy for each customer. Specifically, it generates prompt messages and provides them to the AI ​​model.

[0125] Step 5:

[0126] The device visually presents suggestions received from the server to the user. The input is suggestion data from the server. Using React Native, it displays graphs and recommendation lists, and delivers them to the customer as push notifications at the appropriate time. Specific actions include UI updates and triggering the notification system.

[0127] Step 6:

[0128] Users conduct sales activities based on information received through their terminals and input the progress of sales negotiations. Input includes the current status and progress data of sales negotiations, which are then sent back to the server. Output provides information that enables the review of sales strategies and the planning of the next actions. Specific actions include data entry and decision-making regarding the next step.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention is a system designed to support sales activities, combining customer information collection, sales strategy development, negotiation progress management, and probability of closing deals with an emotion engine that recognizes user emotions and incorporates them into the strategy. The system communicates between a central server and terminals via a network, providing a user-friendly interface.

[0131] First, the server collects customer information from the internet and linked databases. The collected information is processed by analytical algorithms to identify potential customers. These customers are then prioritized and applied to sales activities.

[0132] In parallel, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by the user to detect the user's emotional state. Based on the analyzed emotional data, the emotion engine can further optimize the user's sales strategy.

[0133] Specifically, when the terminal displays real-time progress information on sales negotiations, it takes user emotional data into account and provides situation-appropriate advice and sales strategies to the user. For example, if the user is feeling stressed, the system will simplify the proposal or highlight detailed information about high-priority sales negotiations.

[0134] Furthermore, the system analyzes past sales data to predict the likelihood of closing a deal, and, taking into account the results of the emotion engine analysis, proposes risk management guidelines and opportunities for cross-selling and upselling. The terminal visualizes these prediction results in an easy-to-understand manner and presents them to help the user plan their next actions.

[0135] As a concrete example, the server can adjust the plan based on the customer's response when they use certain words or tones. For instance, if the customer shows positive emotions, proactive follow-up is recommended. In this way, the present invention supports sales activities from an emotional perspective, enabling more sophisticated sales strategies. This system aims to improve the user experience and increase sales efficiency.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server automatically collects customer information from the internet and related databases and stores it in the database. This information includes basic company information, contact details, and past sales history.

[0139] Step 2:

[0140] The server structures the collected data and uses analytical algorithms to identify potential customers. Criteria such as industry, region, and past transaction history are used for identification.

[0141] Step 3:

[0142] The server scores the priority of each customer and creates a list of sales activities. This information is used to optimize the allocation of sales resources.

[0143] Step 4:

[0144] The terminal displays a prioritized list of potential customers received from the server in the user interface. The user uses this list to select target customers.

[0145] Step 5:

[0146] The server performs detailed analysis on selected customers, integrating purchase history and market trend data to generate customer profiles.

[0147] Step 6:

[0148] When a user initiates a business negotiation, the server uses an emotion engine to analyze the user's voice and input text in real time and evaluate their emotional state.

[0149] Step 7:

[0150] The emotion engine adjusts the user's emotional state based on the analysis results and optimizes the content of the sales strategy presentation. For example, if the user is feeling anxious, it provides a simplified mode that summarizes key information.

[0151] Step 8:

[0152] The server monitors the progress of sales negotiations and sends system-recommended action plans and guidelines to the user's terminal. This includes identifying success stories and early detection of problems.

[0153] Step 9:

[0154] The device displays received action plans and guidelines on its screen, helping users make situation-appropriate decisions.

[0155] Step 10:

[0156] The server uses machine learning to analyze past sales data and predict the likelihood of closing a deal. Based on this predictive information, it identifies opportunities for risk management and cross-selling / upselling.

[0157] Step 11:

[0158] The device presents the user with predicted conversion rates and suggested action plans, providing information to effectively plan the next steps.

[0159] (Example 2)

[0160] 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".

[0161] In sales activities, the inability to adequately analyze customer information and understand their emotional state makes it difficult to develop effective sales strategies, resulting in a lower success rate for deals. Furthermore, there is a need for methods to improve sales efficiency by utilizing past sales data to predict the likelihood of closing a deal.

[0162] 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.

[0163] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing emotional data and optimizing sales strategies according to the user's emotional state. This enables effective analysis of customer information and understanding of emotional states, thereby improving the success rate of business negotiations. It also makes it possible to predict the likelihood of closing a deal and support the efficient allocation of sales resources.

[0164] "Customer information" refers to data that includes attributes, history, behavior, and preferences of individual customers, and is important information that serves as a basis for decision-making in sales activities.

[0165] A "potential customer" refers to a prospective customer who is not currently a customer but is considered highly likely to become a customer in the future.

[0166] "Emotional data" refers to information that represents the emotional state of users and customers, and is collected through voice, text, behavioral patterns, and other means.

[0167] "Sales strategy" refers to the policies and methods of sales activities planned to effectively provide the most suitable products and services to a specific customer segment.

[0168] "Progress of the sales negotiation" refers to the progress of the sales process from the initial contact to the closing of the deal.

[0169] "Closing probability" is an indicator that shows the degree of likelihood that a particular business negotiation will actually result in a successful deal.

[0170] An "analytical algorithm" refers to a set of computational procedures and methods used to analyze data and extract useful information from it.

[0171] "Sales resources" refers to all human, material, and informational resources used to carry out sales activities.

[0172] This invention is an advanced system for streamlining sales activities, and is a device that integrates and manages a series of processes from customer information collection and analysis to sales forecasting. The system connects servers and terminals via a network and provides a user-friendly interface.

[0173] The server utilizes an internet-connected database to collect customer information. The collected data is processed using analytical algorithms to identify potential customers. Software used includes database management systems and machine learning libraries. Examples include cloud-based database services and customer segmentation using Python's Scikit-learn.

[0174] Furthermore, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by users. This analysis utilizes speech recognition software and emotion analysis tools. For example, text generated by speech recognition is analyzed by an emotion analysis tool to identify the user's emotional state. This data is then used to optimize sales strategies.

[0175] The terminal displays real-time progress information on sales negotiations and provides sales strategies and advice tailored to the user's emotional state. Data visualization tools are used for this purpose. Specifically, the terminal displays progress and forecast information of the sales pipeline on its screen, helping users plan their next actions.

[0176] As a concrete example, the server analyzes a series of customer data and, based on the results, uses an emotion engine to evaluate the user's current emotional state. Based on this information, the terminal suggests the optimal follow-up method for the sales negotiation to the user. By using a generative AI model, it is possible to optimize the user experience and improve the efficiency of the entire sales process. In this case, the generative AI model can be input with prompts such as: "Predict the likelihood of closing a deal based on customer data, and propose the optimal sales strategy using emotion data."

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The server collects customer information from the internet and linked databases. The information is obtained through website scraping and database searches using SQL queries. This information is collected as a dataset, including basic customer attributes, purchase history, and inquiry history, and is output as the basis for analysis in the next step.

[0180] Step 2:

[0181] The server processes the collected customer information using an analysis algorithm. Specifically, it performs clustering analysis using a machine learning algorithm based on Python's Scikit-learn to identify potential customer segments with common characteristics. The input for this step is the customer information collected in step 1, and the output is a list of the identified potential customers.

[0182] Step 3:

[0183] The server uses an emotion engine to analyze voice and text input from the user. In this step, speech recognition software is used to convert the speech into text, and then emotion analysis is performed. By analyzing the input voice and text data, the user's emotional state is quantified, and the results are output.

[0184] Step 4:

[0185] The terminal develops sales strategies based on the progress of a business negotiation, using sentiment analysis results provided by the server. Specifically, it uses numerical data on emotional state to determine in real time what actions should be taken in the negotiation and presents the user with optimal advice and action plans. The input includes sentiment analysis results, and the output includes specific sales strategies and advice.

[0186] Step 5:

[0187] The terminal visualizes and provides users with the progress and likelihood of closing a deal. Using a data visualization tool, it visually displays the deal status and closing prediction. The input for this step is historical deal data and closing probability predictions, and the output generates visualization information to support the user's next course of action.

[0188] (Application Example 2)

[0189] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0190] In sales activities, developing strategies that take into account customer emotions and circumstances has been difficult with traditional methods. In particular, quickly understanding a customer's emotional state and adjusting sales policies accordingly was a significant burden for many sales representatives. Furthermore, appropriately prioritizing potential customers and efficiently allocating resources was also a challenge.

[0191] 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.

[0192] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing user emotional data and optimizing sales strategies based on emotional states. This makes it possible to provide optimal sales strategies that take customer emotions into consideration.

[0193] "Customer information" refers to personal information, purchase history, behavioral patterns, and emotional states of customers that are necessary for conducting sales activities.

[0194] A "potential customer" refers to a customer who has not yet made an actual purchase but is likely to make one in the future.

[0195] "Sales strategy" refers to a plan or method for effectively selling products or services, taking into account customer needs and market trends.

[0196] "Progress of the deal" refers to the current status or stage in the sales process with the customer.

[0197] "Possibility of closing a deal" refers to the degree to which a business negotiation is likely to be successful and ultimately lead to a contract.

[0198] "Emotional data" refers to information that indicates a user's emotional state, and is obtained from voice, behavior, and text.

[0199] "Optimizing sales strategies" refers to adjusting and improving strategies based on collected data and analysis results to achieve the most effective sales activities.

[0200] "Sales communication" refers to the method of conveying the value of a product or service through dialogue and information exchange with customers.

[0201] This system enables the collection and analysis of customer information and the optimization of sales strategies based on sentiment data. The server collects customer-related information from various data sources, including the internet and databases. The collected data is then processed by advanced analytical algorithms to identify potential customers.

[0202] To understand user emotions in real time, the server is equipped with an emotion engine. This emotion engine uses speech recognition software and behavioral pattern detection algorithms to analyze the voice, text, and actions provided by the user. This allows the server to grasp the user's emotional state and adapt sales strategies accordingly.

[0203] The terminal displays the progress of a sales negotiation in real time and provides situation-specific advice based on the user's emotional data. For example, if the user is feeling stressed, the system can simplify the negotiation content and highlight high-priority items to reduce the user's burden. In this way, the system aims to improve the user experience.

[0204] Furthermore, by analyzing past sales data, the system predicts the likelihood of closing a deal and presents users with risk management guidelines, cross-selling opportunities, and upselling opportunities tailored to the situation. These predictions are displayed visually and clearly on the terminal.

[0205] The hardware utilizes a high-sensitivity microphone and camera, while the software employs advanced machine learning models for speech recognition and emotion analysis. For example, by leveraging a generative AI model, if a user says, "Work has been really stressful lately," the emotion engine can interpret this as negative and suggest relaxing services.

[0206] An example of a prompt for a generative AI model might be: "Consider the current emotional state of the customer and generate an appropriate sales pitch. The customer's words are 'Work has been tough lately,' and their emotion is negative."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server collects basic customer information from the internet and linked databases. Input data includes individual customer information, purchase history, and web behavior records. This data is then structured and stored in the database. Specifically, APIs are used to query external databases, retrieve the necessary information, and convert it into an internal format.

[0210] Step 2:

[0211] The server uses advanced analytical algorithms to analyze customer behavior trends based on collected customer information. Here, the collected customer data is used as input, and the output includes identifying potential customers and calculating their priority. This process uses machine learning models to compare customers' past history with market trends, highlighting potentially high-profit customers.

[0212] Step 3:

[0213] The server analyzes the voice and text data provided by the user in real time and uses an emotion engine to evaluate the user's emotional state. Inputs include voice and text data collected via microphone and keyboard. Emotion analysis is performed using natural language processing algorithms, and the user's emotional state is determined as a result.

[0214] Step 4:

[0215] The terminal receives information from the server regarding the progress of a sales negotiation and, taking into account the user's emotional data, displays situation-appropriate advice to the user. Inputs are progress information and emotional state evaluation results provided by the server. Outputs include a sales negotiation progress report and a sales strategy optimized for the user. The terminal uses a GUI to visually present data to the user, providing immediate information for decision-making.

[0216] Step 5:

[0217] Using historical sales data, the server predicts the likelihood of closing a deal. The input is existing sales data, and the output is a score indicating the probability of closing the deal. This prediction combines statistical methods and machine learning models to evaluate future business opportunities. The generated information is useful for risk management and identifying additional sales opportunities.

[0218] Step 6:

[0219] The user plans their next actions based on the prediction results. To support this, the device visualizes and displays cross-sell and up-sell opportunities along with a conversion probability score. The entered prediction score is processed into an easily understandable format on the user interface using visualization tools. As a result, the user can quickly develop a more effective sales plan.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention is an automation tool for streamlining sales activities, and it builds sales strategies by acquiring and analyzing customer information. The system operates via a network, and is configured so that the server and user terminals communicate with each other.

[0237] The server collects publicly available customer information from multiple data sources and extracts key information through a data cleansing process. This information is used to identify and prioritize potential customers. For example, the server can prioritize listing customers belonging to specific regions or industries based on industry standards and existing customer profiles.

[0238] Next, the server performs a detailed customer analysis. This aims to identify customer needs and formulate targeted approaches based on historical data and market trends. For example, it can analyze past purchase history to predict product replacement cycles. As a result, the terminal displays the analyzed data along with suggested sales strategies.

[0239] Furthermore, the server monitors the progress of the business negotiation in real time and provides specific advice to improve the probability of success. Specific suggestions tailored to the issues to be resolved and the prospect's areas of interest are fed back to the user's terminal.

[0240] Furthermore, the server is equipped with a system that uses past sales negotiation data to predict the likelihood of closing a deal, and can estimate future sales outcomes by applying machine learning technology. User terminals visually display these prediction results and provide concrete suggestions to support risk management, cross-selling, and upselling strategies.

[0241] For example, the server can analyze past data for specific products with high campaign performance and suggest to the user that they run similar promotions on other untapped customers. In this way, the present invention can improve the accuracy and efficiency of sales activities with an interface that is easy for users without specialized knowledge to use.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server collects publicly available customer information from the internet and affiliated database systems. Specifically, it automatically retrieves company profiles, industry data, contact information, and other data, and stores it in the database.

[0245] Step 2:

[0246] The server filters the collected data to remove unnecessary information and performs data cleansing to correct for duplicates and missing data. This refines the list of potential customers.

[0247] Step 3:

[0248] Based on the cleansed data, the server applies analytical algorithms to customer attributes and behavioral history to identify potential customers and set priorities.

[0249] Step 4:

[0250] The terminal displays a prioritized list of potential customers sent from the server on a dashboard, making it viewable by the user.

[0251] Step 5:

[0252] When a user selects a specific customer, the server performs a detailed analysis of that customer. It refers to past transaction history and market trends to understand the customer's purchasing tendencies.

[0253] Step 6:

[0254] Based on the analysis results, the server develops an effective approach strategy and sends it to the user's terminal as a recommended plan.

[0255] Step 7:

[0256] The device presents the user with recommended approach strategies, which the user then uses to plan their sales activities.

[0257] Step 8:

[0258] The server monitors the progress of the deal in real time and generates advice based on the progress. It predicts the next steps necessary for the deal's success and provides guidelines.

[0259] Step 9:

[0260] The device provides users with advice and success stories related to business negotiations, supporting them through the process of the negotiation.

[0261] Step 10:

[0262] The server predicts the likelihood of closing a current deal based on a machine learning model and identifies related risks and opportunities.

[0263] Step 11:

[0264] The terminal reports to the user the predicted probability of closing a deal, along with risk management strategies and cross-selling / upselling suggestions based on that prediction. This allows the user to select the optimal sales strategy.

[0265] (Example 1)

[0266] 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."

[0267] In modern sales activities, efficiently collecting vast amounts of customer information and effectively identifying potential customers is a significant challenge. Furthermore, there is a lack of concrete guidelines for developing sales strategies tailored to customer needs, effectively conducting negotiations, and accurately predicting the likelihood of closing a deal. This makes optimizing sales resources difficult and hinders the maximization of sales results.

[0268] 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.

[0269] In this invention, the server includes means for collecting customer information to identify potential customers to be processed, means for performing analysis on customers based on the collected information to build sales strategies, means for monitoring the progress of negotiations and providing advice for the success of those negotiations, means for improving sales strategy proposals by analyzing the characteristics of potential customers using a generative AI model, and means for providing follow-up proposals tailored to the progress of negotiations through a user interface. This makes it possible to improve the accuracy and results of sales activities through efficient collection and analysis of customer information.

[0270] "Customer information" refers to all data related to the customer, such as customer profiles, purchase history, and industry attributes.

[0271] "Methods for identifying potential customers" refers to the process of analyzing customer information from diverse data sources to identify new customers who are likely to make a purchase.

[0272] "Methods for developing a sales strategy" refer to methods for analyzing customer needs and market trends based on collected data, and formulating the optimal sales approach.

[0273] "Means for monitoring the progress of business negotiations" refers to a system for tracking and evaluating the current status and progress of business negotiations in real time.

[0274] "Means of providing advice" refers to methods of generating and providing specific suggestions and instructions to improve the probability of sales success, depending on the situation of the business negotiation.

[0275] "Methods for predicting the likelihood of closing a deal" refer to a process for statistically estimating the probability that a future deal will be closed, based on past sales negotiation data.

[0276] A "generative AI model" is an artificial intelligence technology that supports decision-making by analyzing large amounts of data and extracting patterns and relationships.

[0277] A "user interface" is the visual and manipulative environment through which a user interacts with a system's functions and retrieves information.

[0278] This invention is implemented as an integrated system for collecting and analyzing customer information, formulating sales strategies, and managing the progress of business negotiations. The server automatically collects customer information from various external data sources using APIs and web scraping techniques. Specific software used includes the Python libraries "requests" and "BeautifulSoup".

[0279] The collected data is processed by the server through a data cleansing process to extract important information. Data processing libraries such as Pandas and NumPy are used for this process. Based on this organized information, the server utilizes a generative AI model to identify potential customers, analyze their characteristics, and build an optimal sales strategy.

[0280] Furthermore, the server uses machine learning libraries such as Scikit-learn to analyze past sales data and predict the likelihood of closing a deal. This prediction can generate specific guidelines and advice to increase the success rate of the deal and provide them to the user's terminal. On the terminal, these results and advice are visually displayed through the user interface to help with decision-making for the next steps.

[0281] In actual implementation, the server prompts the user with a message such as, "Based on past sales data, formulate a sales strategy for the next quarter and propose it along with key KPIs," providing input to the AI ​​model. Based on this prompt, the AI ​​performs the necessary analysis and generates specific proposals. Through this process, the user can conduct sales activities efficiently and make optimal use of resources.

[0282] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0283] Step 1:

[0284] The server collects customer information from external data sources. As input, initial information regarding the target customer group is specified, and the "requests" library in Python is used to obtain data from APIs and web pages. The data collected in this process includes customer profiles, past transaction information, industry type information, etc. The output is a set of available raw data.

[0285] Step 2:

[0286] The server performs data cleaning on the collected customer data. As input, the raw data collected in Step 1 is used. Using Pandas and NumPy, the data is processed such as filling in missing values, deleting duplicate data, and unifying data formats. The output is refined, cleaned data.

[0287] Step 3:

[0288] The server conducts analysis to identify potential customers using the cleaned data. As input, the cleaned data obtained in Step 2 is utilized. The server uses a generative AI model to perform scoring and prioritize target customers based on customer characteristics. The output is a prioritized list of potential customers.

[0289] Step 4: [[ID=2​​​​​​​​​The terminal visually displays the sales strategy and analysis results sent from the server. The input is the sales strategy built in Step 4. Through the user interface, the terminal visualizes key KPIs and strategies in a dashboard format, presenting them in an easy-to-understand manner for the user. The output is a visually clear display of the sales strategy.

[0293] Step 6:

[0294] The server monitors the progress of sales negotiations in real time and generates follow-up suggestions. It uses current negotiation progress information and past customer response data as input. The server utilizes a generation AI model to suggest specific next steps and generate guidelines to increase the success rate of the negotiation. The output is personalized follow-up suggestions.

[0295] Step 7:

[0296] The terminal receives advice from the server and presents it to the user. The input is the follow-up suggestions generated in step 6. The terminal displays these suggestions on the user interface, providing information that helps the user decide on their next course of action. The output is a presentation of specific follow-up actions to the user.

[0297] (Application Example 1)

[0298] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0299] In sales activities, it is difficult to quickly develop effective sales strategies and make appropriate approaches to potential customers. Furthermore, there is a lack of efficient means to propose products and promotions to target customers. As a result, sales representatives find it difficult to develop personalized strategies for individual customers, leading to missed sales opportunities.

[0300] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0301] In this invention, the server includes means for collecting information about customers, identifying potential customers to be processed, analyzing the collected information to construct a sales strategy for customers, monitoring the progress of negotiations, providing advice for successful negotiations, predicting the likelihood of conclusion based on past negotiation data, visually presenting the analysis results to users, and proposing products and promotions suitable for target customers. As a result, it becomes possible for sales staff to quickly establish an efficient sales strategy and execute a personalized approach to customers.

[0302] "Information about customers" refers to all data based on customers' public profiles, purchase histories, behavioral histories, etc.

[0303] "Potential customers to be processed" refers to prospective customers who should be preferentially approached as targets of business activities.

[0304] "Means for analyzing and constructing a sales strategy" refers to a method of analyzing the collected data and formulating effective sales policies and strategies based on it.

[0305] "Means for monitoring the progress of negotiations and providing advice for successful negotiations" refers to a procedure for monitoring the status of ongoing negotiations and providing appropriate advice to increase the success rate.

[0306] "Means for predicting the likelihood of conclusion" refers to a technique for estimating the probability of future negotiations being successful using past negotiation data.

[0307] "Means for visually presenting the analysis results to users" refers to a method of displaying the analyzed data to users in a visual form such as graphs or charts.

[0308] "Means of proposing products and promotions suitable for target customers" refers to an approach to suggesting the most relevant products and promotional activities to specific customers.

[0309] The system for implementing this invention is to acquire customer information via a network, perform analysis, and build effective sales strategies for customers. The server is built using Python and the Flask framework and collects customer information from multiple data sources. PostgreSQL is used as the database for storing and managing customer data. The server processes the collected data using scikit-learn and analyzes customer purchasing patterns and needs.

[0310] The analysis results generated by the server are sent to the device via API, where they are visually presented to the user as a cross-platform application using React Native. The device displays target customer information, suitable products, and promotional suggestions to the user, and provides real-time updates on the progress of the sales negotiation.

[0311] As a concrete example, by analyzing past customer purchase history, the device can identify that a particular customer regularly purchases products in the same category. In this case, the device can notify that customer of new product suggestions or upsells on related products. This allows users to quickly develop efficient sales strategies.

[0312] As an example of a prompt using a generative AI model, the server will perform appropriate analysis by issuing the instruction, "Identify target customers based on their past purchase history and suggest the most suitable promotion."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server collects customer information from multiple data sources over the network. Inputs include public customer profiles and purchase history, while output is centralized customer data. The server uses an API to ingest this data and stores it in a PostgreSQL database.

[0316] Step 2:

[0317] The server cleanses the collected customer data and prepares it for analysis. The input is raw data and may contain unnecessary or inconsistent information. It performs a cleansing process and outputs data formatted to provide useful information. Specifically, it removes duplicate data and imputes missing values.

[0318] Step 3:

[0319] The server uses scikit-learn to perform data analysis and identify target customers and their needs. Cleansed customer data is used as input, and a machine learning model is employed to analyze purchasing patterns. The output is targeting information for individual customers. Specific processing includes customer segmentation and purchase prediction.

[0320] Step 4:

[0321] The server uses an AI model that generates optimal products and promotions for target customers based on the analysis results to make suggestions. The input is targeting information and data on existing promotions, and the output is a customized promotion strategy for each customer. Specifically, it generates prompt messages and provides them to the AI ​​model.

[0322] Step 5:

[0323] The device visually presents suggestions received from the server to the user. The input is suggestion data from the server. Using React Native, it displays graphs and recommendation lists, and delivers them to the customer as push notifications at the appropriate time. Specific actions include UI updates and triggering the notification system.

[0324] Step 6:

[0325] Users conduct sales activities based on information received through their terminals and input the progress of sales negotiations. Input includes the current status and progress data of sales negotiations, which are then sent back to the server. Output provides information that enables the review of sales strategies and the planning of the next actions. Specific actions include data entry and decision-making regarding the next step.

[0326] 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.

[0327] This invention is a system designed to support sales activities, combining customer information collection, sales strategy development, negotiation progress management, and probability of closing deals with an emotion engine that recognizes user emotions and incorporates them into the strategy. The system communicates between a central server and terminals via a network, providing a user-friendly interface.

[0328] First, the server collects customer information from the internet and linked databases. The collected information is processed by analytical algorithms to identify potential customers. These customers are then prioritized and applied to sales activities.

[0329] In parallel, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by the user to detect the user's emotional state. Based on the analyzed emotional data, the emotion engine can further optimize the user's sales strategy.

[0330] Specifically, when the terminal displays real-time progress information on sales negotiations, it takes user emotional data into account and provides situation-appropriate advice and sales strategies to the user. For example, if the user is feeling stressed, the system will simplify the proposal or highlight detailed information about high-priority sales negotiations.

[0331] Furthermore, the system analyzes past sales data to predict the likelihood of closing a deal, and, taking into account the results of the emotion engine analysis, proposes risk management guidelines and opportunities for cross-selling and upselling. The terminal visualizes these prediction results in an easy-to-understand manner and presents them to help the user plan their next actions.

[0332] As a concrete example, the server can adjust the plan based on the customer's response when they use certain words or tones. For instance, if the customer shows positive emotions, proactive follow-up is recommended. In this way, the present invention supports sales activities from an emotional perspective, enabling more sophisticated sales strategies. This system aims to improve the user experience and increase sales efficiency.

[0333] The following describes the processing flow.

[0334] Step 1:

[0335] The server automatically collects customer information from the internet and related databases and stores it in the database. This information includes basic company information, contact details, and past sales history.

[0336] Step 2:

[0337] The server structures the collected data and uses analytical algorithms to identify potential customers. Criteria such as industry, region, and past transaction history are used for identification.

[0338] Step 3:

[0339] The server scores the priority of each customer and creates a list of sales activities. This information is used to optimize the allocation of sales resources.

[0340] Step 4:

[0341] The terminal displays a prioritized list of potential customers received from the server in the user interface. The user uses this list to select target customers.

[0342] Step 5:

[0343] The server performs detailed analysis on selected customers, integrating purchase history and market trend data to generate customer profiles.

[0344] Step 6:

[0345] When a user initiates a business negotiation, the server uses an emotion engine to analyze the user's voice and input text in real time and evaluate their emotional state.

[0346] Step 7:

[0347] The emotion engine adjusts the user's emotional state based on the analysis results and optimizes the content of the sales strategy presentation. For example, if the user is feeling anxious, it provides a simplified mode that summarizes key information.

[0348] Step 8:

[0349] The server monitors the progress of sales negotiations and sends system-proposed action plans and guidelines to the user's terminal. This includes identifying success stories and early detection of problems.

[0350] Step 9:

[0351] The device displays received action plans and guidelines on its screen, helping users make situation-appropriate decisions.

[0352] Step 10:

[0353] The server uses machine learning to analyze past sales data and predict the likelihood of closing a deal. Based on this predictive information, it identifies opportunities for risk management and cross-selling / upselling.

[0354] Step 11:

[0355] The device presents the user with predicted conversion rates and suggested action plans, providing information to effectively plan the next steps.

[0356] (Example 2)

[0357] 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".

[0358] In sales activities, the inability to adequately analyze customer information and understand their emotional state makes it difficult to develop effective sales strategies, resulting in a lower success rate for deals. Furthermore, there is a need for methods to improve sales efficiency by utilizing past sales data to predict the likelihood of closing a deal.

[0359] 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.

[0360] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing emotional data and optimizing sales strategies according to the user's emotional state. This enables effective analysis of customer information and understanding of emotional states, thereby improving the success rate of business negotiations. It also makes it possible to predict the likelihood of closing a deal and support the efficient allocation of sales resources.

[0361] "Customer information" refers to data that includes attributes, history, behavior, and preferences of individual customers, and is important information that serves as a basis for decision-making in sales activities.

[0362] A "potential customer" refers to a prospective customer who is not currently a customer but is considered highly likely to become a customer in the future.

[0363] "Emotional data" refers to information that represents the emotional state of users and customers, and is collected through voice, text, behavioral patterns, and other means.

[0364] "Sales strategy" refers to the policies and methods of sales activities planned to effectively provide the most suitable products and services to a specific customer segment.

[0365] "Progress of the sales negotiation" refers to the progress of the sales process from the initial contact to the closing of the deal.

[0366] "Closing probability" is an indicator that shows the degree of likelihood that a particular business negotiation will actually result in a successful deal.

[0367] An "analytical algorithm" refers to a set of computational procedures and methods used to analyze data and extract useful information from it.

[0368] "Sales resources" refers to all human, material, and informational resources used to carry out sales activities.

[0369] This invention is an advanced system for streamlining sales activities, and is a device that integrates and manages a series of processes from customer information collection and analysis to sales forecasting. The system connects servers and terminals via a network and provides a user-friendly interface.

[0370] The server utilizes an internet-connected database to collect customer information. The collected data is processed using analytical algorithms to identify potential customers. Software used includes database management systems and machine learning libraries. Examples include cloud-based database services and customer segmentation using Python's Scikit-learn.

[0371] Furthermore, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by users. This analysis utilizes speech recognition software and emotion analysis tools. For example, text generated by speech recognition is analyzed by an emotion analysis tool to identify the user's emotional state. This data is then used to optimize sales strategies.

[0372] The terminal displays real-time progress information on sales negotiations and provides sales strategies and advice tailored to the user's emotional state. Data visualization tools are used for this purpose. Specifically, the terminal displays progress and forecast information of the sales pipeline on its screen, helping users plan their next actions.

[0373] As a concrete example, the server analyzes a series of customer data and, based on the results, uses an emotion engine to evaluate the user's current emotional state. Based on this information, the terminal suggests the optimal follow-up method for the sales negotiation to the user. By using a generative AI model, it is possible to optimize the user experience and improve the efficiency of the entire sales process. In this case, the generative AI model can be input with prompts such as: "Predict the likelihood of closing a deal based on customer data, and propose the optimal sales strategy using emotion data."

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1:

[0376] The server collects customer information from the internet and linked databases. The information is obtained through website scraping and database searches using SQL queries. This information is collected as a dataset, including basic customer attributes, purchase history, and inquiry history, and is output as the basis for analysis in the next step.

[0377] Step 2:

[0378] The server processes the collected customer information using an analysis algorithm. Specifically, it performs clustering analysis using a machine learning algorithm based on Python's Scikit-learn to identify potential customer segments with common characteristics. The input for this step is the customer information collected in step 1, and the output is a list of the identified potential customers.

[0379] Step 3:

[0380] The server uses an emotion engine to analyze voice and text input from the user. In this step, speech recognition software is used to convert the speech into text, and then emotion analysis is performed. By analyzing the input voice and text data, the user's emotional state is quantified, and the results are output.

[0381] Step 4:

[0382] The terminal develops sales strategies based on the progress of a business negotiation, using sentiment analysis results provided by the server. Specifically, it uses numerical data on emotional state to determine in real time what actions should be taken in the negotiation and presents the user with optimal advice and action plans. The input includes sentiment analysis results, and the output includes specific sales strategies and advice.

[0383] Step 5:

[0384] The terminal visualizes and provides users with the progress and likelihood of closing a deal. Using a data visualization tool, it visually displays the deal status and closing prediction. The input for this step is historical deal data and closing probability predictions, and the output generates visualization information to support the user's next course of action.

[0385] (Application Example 2)

[0386] 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."

[0387] In sales activities, developing strategies that take into account customer emotions and circumstances has been difficult with traditional methods. In particular, quickly understanding a customer's emotional state and adjusting sales policies accordingly was a significant burden for many sales representatives. Furthermore, appropriately prioritizing potential customers and efficiently allocating resources was also a challenge.

[0388] 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.

[0389] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing user emotional data and optimizing sales strategies based on emotional states. This makes it possible to provide optimal sales strategies that take customer emotions into consideration.

[0390] "Customer information" refers to personal information, purchase history, behavioral patterns, and emotional states of customers that are necessary for conducting sales activities.

[0391] A "potential customer" refers to a customer who has not yet made an actual purchase but is likely to make one in the future.

[0392] "Sales strategy" refers to a plan or method for effectively selling products or services, taking into account customer needs and market trends.

[0393] "Progress of the deal" refers to the current status or stage in the sales process with the customer.

[0394] "Possibility of closing a deal" refers to the degree to which a business negotiation is likely to be successful and ultimately lead to a contract.

[0395] "Emotional data" refers to information that indicates a user's emotional state, and is obtained from voice, behavior, and text.

[0396] "Optimizing sales strategies" refers to adjusting and improving strategies based on collected data and analysis results to achieve the most effective sales activities.

[0397] "Sales communication" refers to the method of conveying the value of a product or service through dialogue and information exchange with customers.

[0398] This system enables the collection and analysis of customer information and the optimization of sales strategies based on sentiment data. The server collects customer-related information from various data sources, including the internet and databases. The collected data is then processed by advanced analytical algorithms to identify potential customers.

[0399] To understand user emotions in real time, the server is equipped with an emotion engine. This emotion engine uses speech recognition software and behavioral pattern detection algorithms to analyze the voice, text, and actions provided by the user. This allows the server to grasp the user's emotional state and adapt sales strategies accordingly.

[0400] The terminal displays the progress of a sales negotiation in real time and provides situation-specific advice based on the user's emotional data. For example, if the user is feeling stressed, the system can simplify the negotiation content and highlight high-priority items to reduce the user's burden. In this way, the system aims to improve the user experience.

[0401] Furthermore, by analyzing past sales data, the system predicts the likelihood of closing a deal and presents users with risk management guidelines, cross-selling opportunities, and upselling opportunities tailored to the situation. These predictions are displayed visually and clearly on the terminal.

[0402] The hardware utilizes a high-sensitivity microphone and camera, while the software employs advanced machine learning models for speech recognition and emotion analysis. For example, by leveraging a generative AI model, if a user says, "Work has been really stressful lately," the emotion engine can interpret this as negative and suggest relaxing services.

[0403] An example of a prompt for a generative AI model might be: "Consider the current emotional state of the customer and generate an appropriate sales pitch. The customer's words are 'Work has been tough lately,' and their emotion is negative."

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The server collects basic customer information from the internet and linked databases. Input data includes individual customer information, purchase history, and web behavior records. This data is then structured and stored in the database. Specifically, APIs are used to query external databases, retrieve the necessary information, and convert it into an internal format.

[0407] Step 2:

[0408] The server uses advanced analytical algorithms to analyze customer behavior trends based on collected customer information. Here, the collected customer data is used as input, and the output includes identifying potential customers and calculating their priority. This process uses machine learning models to compare customers' past history with market trends, highlighting potentially high-profit customers.

[0409] Step 3:

[0410] The server analyzes the voice and text data provided by the user in real time and uses an emotion engine to evaluate the user's emotional state. Inputs include voice and text data collected via microphone and keyboard. Emotion analysis is performed using natural language processing algorithms, and the user's emotional state is determined as a result.

[0411] Step 4:

[0412] The terminal receives information from the server regarding the progress of a sales negotiation and, taking into account the user's emotional data, displays situation-appropriate advice to the user. Inputs are progress information and emotional state evaluation results provided by the server. Outputs include a sales negotiation progress report and a sales strategy optimized for the user. The terminal uses a GUI to visually present data to the user, providing immediate information for decision-making.

[0413] Step 5:

[0414] Using historical sales data, the server predicts the likelihood of closing a deal. The input is existing sales data, and the output is a score indicating the probability of closing the deal. This prediction combines statistical methods and machine learning models to evaluate future business opportunities. The generated information is useful for risk management and identifying additional sales opportunities.

[0415] Step 6:

[0416] The user plans their next actions based on the prediction results. To support this, the device visualizes and displays cross-sell and up-sell opportunities along with a conversion probability score. The entered prediction score is processed into an easily understandable format on the user interface using visualization tools. As a result, the user can quickly develop a more effective sales plan.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] This invention is an automation tool for streamlining sales activities, and it builds sales strategies by acquiring and analyzing customer information. The system operates via a network, and is configured so that the server and user terminals communicate with each other.

[0434] The server collects publicly available customer information from multiple data sources and extracts key information through a data cleansing process. This information is used to identify and prioritize potential customers. For example, the server can prioritize listing customers belonging to specific regions or industries based on industry standards and existing customer profiles.

[0435] Next, the server performs a detailed customer analysis. This aims to identify customer needs and formulate targeted approaches based on historical data and market trends. For example, it can analyze past purchase history to predict product replacement cycles. As a result, the terminal displays the analyzed data along with suggested sales strategies.

[0436] Furthermore, the server monitors the progress of the business negotiation in real time and provides specific advice to improve the probability of success. Specific suggestions tailored to the issues to be resolved and the prospect's areas of interest are fed back to the user's terminal.

[0437] Furthermore, the server is equipped with a system that uses past sales negotiation data to predict the likelihood of closing a deal, and can estimate future sales outcomes by applying machine learning technology. User terminals visually display these prediction results and provide concrete suggestions to support risk management, cross-selling, and upselling strategies.

[0438] For example, the server can analyze past data for specific products with high campaign performance and suggest to the user that they run similar promotions on other untapped customers. In this way, the present invention can improve the accuracy and efficiency of sales activities with an interface that is easy for users without specialized knowledge to use.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] The server collects publicly available customer information from the internet and affiliated database systems. Specifically, it automatically retrieves company profiles, industry data, contact information, and other data, and stores it in the database.

[0442] Step 2:

[0443] The server filters the collected data to remove unnecessary information and performs data cleansing to correct for duplicates and missing data. This refines the list of potential customers.

[0444] Step 3:

[0445] Based on the cleansed data, the server applies analytical algorithms to customer attributes and behavioral history to identify potential customers and set priorities.

[0446] Step 4:

[0447] The terminal displays a prioritized list of potential customers sent from the server on a dashboard, making it viewable by the user.

[0448] Step 5:

[0449] When a user selects a specific customer, the server performs a detailed analysis of that customer. It refers to past transaction history and market trends to understand the customer's purchasing tendencies.

[0450] Step 6:

[0451] Based on the analysis results, the server develops an effective approach strategy and sends it to the user's terminal as a recommended plan.

[0452] Step 7:

[0453] The device presents the user with recommended approach strategies, which the user then uses to plan their sales activities.

[0454] Step 8:

[0455] The server monitors the progress of the deal in real time and generates advice based on the progress. It predicts the next steps necessary for the deal's success and provides guidelines.

[0456] Step 9:

[0457] The device provides users with advice and success stories related to business negotiations, supporting them through the process of the negotiation.

[0458] Step 10:

[0459] The server predicts the likelihood of closing a current deal based on a machine learning model and identifies related risks and opportunities.

[0460] Step 11:

[0461] The terminal reports to the user the predicted probability of closing a deal, along with risk management strategies and cross-selling / upselling suggestions based on that prediction. This allows the user to select the optimal sales strategy.

[0462] (Example 1)

[0463] 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."

[0464] In modern sales activities, efficiently collecting vast amounts of customer information and effectively identifying potential customers is a significant challenge. Furthermore, there is a lack of concrete guidelines for developing sales strategies tailored to customer needs, effectively conducting negotiations, and accurately predicting the likelihood of closing a deal. This makes optimizing sales resources difficult and hinders the maximization of sales results.

[0465] 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.

[0466] In this invention, the server includes means for collecting customer information to identify potential customers to be processed, means for performing analysis on customers based on the collected information to build sales strategies, means for monitoring the progress of negotiations and providing advice for the success of those negotiations, means for improving sales strategy proposals by analyzing the characteristics of potential customers using a generative AI model, and means for providing follow-up proposals tailored to the progress of negotiations through a user interface. This makes it possible to improve the accuracy and results of sales activities through efficient collection and analysis of customer information.

[0467] "Customer information" refers to all data related to the customer, such as customer profiles, purchase history, and industry attributes.

[0468] "Methods for identifying potential customers" refers to the process of analyzing customer information from diverse data sources to identify new customers who are likely to make a purchase.

[0469] "Methods for developing a sales strategy" refer to methods for analyzing customer needs and market trends based on collected data, and formulating the optimal sales approach.

[0470] "Means for monitoring the progress of business negotiations" refers to a system for tracking and evaluating the current status and progress of business negotiations in real time.

[0471] "Means of providing advice" refers to methods of generating and providing specific suggestions and instructions to improve the probability of sales success, depending on the situation of the business negotiation.

[0472] "Methods for predicting the likelihood of closing a deal" refer to a process for statistically estimating the probability that a future deal will be closed, based on past sales negotiation data.

[0473] A "generative AI model" is an artificial intelligence technology that supports decision-making by analyzing large amounts of data and extracting patterns and relationships.

[0474] A "user interface" is the visual and manipulative environment through which a user interacts with a system's functions and retrieves information.

[0475] This invention is implemented as an integrated system for collecting and analyzing customer information, formulating sales strategies, and managing the progress of business negotiations. The server automatically collects customer information from various external data sources using APIs and web scraping techniques. Specific software used includes the Python libraries "requests" and "BeautifulSoup".

[0476] The collected data is processed by the server through a data cleansing process to extract important information. Data processing libraries such as Pandas and NumPy are used for this process. Based on this organized information, the server utilizes a generative AI model to identify potential customers, analyze their characteristics, and build an optimal sales strategy.

[0477] Furthermore, the server uses machine learning libraries such as Scikit-learn to analyze past sales data and predict the likelihood of closing a deal. This prediction can generate specific guidelines and advice to increase the success rate of the deal and provide them to the user's terminal. On the terminal, these results and advice are visually displayed through the user interface to help with decision-making for the next steps.

[0478] In actual implementation, the server prompts the user with a message such as, "Based on past sales data, formulate a sales strategy for the next quarter and propose it along with key KPIs," providing input to the AI ​​model. Based on this prompt, the AI ​​performs the necessary analysis and generates specific proposals. Through this process, the user can conduct sales activities efficiently and make optimal use of resources.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The server collects customer information from external data sources. The input specifies initial information about the target customer group, and the Python "requests" library is used to retrieve data from APIs and web pages. The data collected in this process includes customer profiles, past transaction information, and industry information. The output is a collection of available raw data.

[0482] Step 2:

[0483] The server performs data cleansing on the collected customer data. The raw data collected in step 1 is used as input. The data is processed using Pandas or NumPy to handle missing values, remove duplicate data, and standardize data formats. The output is the refined, cleansed data.

[0484] Step 3:

[0485] The server performs analysis to identify potential customers using the cleansed data. The cleansed data obtained in step 2 is used as input. The server uses a generative AI model to perform scoring and target customer prioritization based on customer characteristics. The output is a prioritized list of potential customers.

[0486] Step 4:

[0487] The server builds sales strategies based on historical data and market trends. The input is the list of potential customers obtained in step 3 and historical sales data, which is analyzed using machine learning techniques. Scikit-learn is used to predict customer behavior, identify the purchase cycle, and determine the optimal approach. The output is a set of recommended sales strategies.

[0488] Step 5:

[0489] The terminal visually displays the sales strategy and analysis results sent from the server. The input is the sales strategy built in Step 4. Through the user interface, the terminal visualizes key KPIs and strategies in a dashboard format, presenting them in an easy-to-understand manner for the user. The output is a visually clear display of the sales strategy.

[0490] Step 6:

[0491] The server monitors the progress of sales negotiations in real time and generates follow-up suggestions. It uses current negotiation progress information and past customer response data as input. The server utilizes a generation AI model to suggest specific next steps and generate guidelines to increase the success rate of the negotiation. The output is personalized follow-up suggestions.

[0492] Step 7:

[0493] The terminal receives advice from the server and presents it to the user. The input is the follow-up suggestions generated in step 6. The terminal displays these suggestions on the user interface, providing information that helps the user decide on their next course of action. The output is a presentation of specific follow-up actions to the user.

[0494] (Application Example 1)

[0495] 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."

[0496] In sales activities, it is difficult to quickly develop effective sales strategies and make appropriate approaches to potential customers. Furthermore, there is a lack of efficient means to propose products and promotions to target customers. As a result, sales representatives find it difficult to develop personalized strategies for individual customers, leading to missed sales opportunities.

[0497] 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.

[0498] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed; means for performing analysis on customers based on the collected information and building sales strategies; means for monitoring the progress of negotiations and providing advice for the success of those negotiations; means for predicting the likelihood of closing a deal based on past negotiation data; means for visually presenting the analysis results to the user; and means for proposing products and promotions suitable for target customers. This enables sales representatives to quickly and efficiently develop sales strategies and implement personalized approaches to customers.

[0499] "Customer information" refers to all data based on a customer's publicly available profile, purchase history, behavioral history, etc.

[0500] "Potential customers to be processed" refers to prospective customers who should be prioritized for approach in commercial activities.

[0501] "Methods for conducting analysis and building sales strategies" refers to methods of analyzing collected data and formulating effective sales policies and strategies based on that analysis.

[0502] "A means of monitoring the progress of a business deal and providing advice to help it succeed" refers to a procedure for monitoring the status of ongoing business deals and providing appropriate advice to increase the chances of success.

[0503] "Methods for predicting the likelihood of closing a deal" refer to techniques that use data from past business negotiations to estimate the probability of future business negotiations being successful.

[0504] "Means of visually presenting analysis results to the user" refers to methods of displaying the analyzed data to the user in a visual format such as graphs or charts.

[0505] "Means of proposing products and promotions suitable for target customers" refers to an approach to suggesting the most relevant products and promotional activities to specific customers.

[0506] The system for implementing this invention is to acquire customer information via a network, perform analysis, and build effective sales strategies for customers. The server is built using Python and the Flask framework and collects customer information from multiple data sources. PostgreSQL is used as the database for storing and managing customer data. The server processes the collected data using scikit-learn and analyzes customer purchasing patterns and needs.

[0507] The analysis results generated by the server are sent to the device via API, where they are visually presented to the user as a cross-platform application using React Native. The device displays target customer information, suitable products, and promotional suggestions to the user, and provides real-time updates on the progress of the sales negotiation.

[0508] As a concrete example, by analyzing past customer purchase history, the device can identify that a particular customer regularly purchases products in the same category. In this case, the device can notify that customer of new product suggestions or upsells on related products. This allows users to quickly develop efficient sales strategies.

[0509] As an example of a prompt using a generative AI model, the server will perform appropriate analysis by issuing the instruction, "Identify target customers based on their past purchase history and suggest the most suitable promotion."

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server collects customer information from multiple data sources over the network. Inputs include public customer profiles and purchase history, while output is centralized customer data. The server uses an API to ingest this data and stores it in a PostgreSQL database.

[0513] Step 2:

[0514] The server cleanses the collected customer data and prepares it for analysis. The input is raw data and may contain unnecessary or inconsistent information. It performs a cleansing process and outputs data formatted to provide useful information. Specifically, it removes duplicate data and imputes missing values.

[0515] Step 3:

[0516] The server uses scikit-learn to perform data analysis and identify target customers and their needs. Cleansed customer data is used as input, and a machine learning model is employed to analyze purchasing patterns. The output is targeting information for individual customers. Specific processing includes customer segmentation and purchase prediction.

[0517] Step 4:

[0518] The server uses an AI model that generates optimal products and promotions for target customers based on the analysis results to make suggestions. The input is targeting information and data on existing promotions, and the output is a customized promotion strategy for each customer. Specifically, it generates prompt messages and provides them to the AI ​​model.

[0519] Step 5:

[0520] The device visually presents suggestions received from the server to the user. The input is suggestion data from the server. Using React Native, it displays graphs and recommendation lists, and delivers them to the customer as push notifications at the appropriate time. Specific actions include UI updates and triggering the notification system.

[0521] Step 6:

[0522] Users conduct sales activities based on information received through their terminals and input the progress of sales negotiations. Input includes the current status and progress data of sales negotiations, which are then sent back to the server. Output provides information that enables the review of sales strategies and the planning of the next actions. Specific actions include data entry and decision-making regarding the next step.

[0523] 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.

[0524] This invention is a system designed to support sales activities, combining customer information collection, sales strategy development, negotiation progress management, and probability of closing deals with an emotion engine that recognizes user emotions and incorporates them into the strategy. The system communicates between a central server and terminals via a network, providing a user-friendly interface.

[0525] First, the server collects customer information from the internet and linked databases. The collected information is processed by analytical algorithms to identify potential customers. These customers are then prioritized and applied to sales activities.

[0526] In parallel, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by the user to detect the user's emotional state. Based on the analyzed emotional data, the emotion engine can further optimize the user's sales strategy.

[0527] Specifically, when the terminal displays real-time progress information on sales negotiations, it takes user emotional data into account and provides situation-appropriate advice and sales strategies to the user. For example, if the user is feeling stressed, the system will simplify the proposal or highlight detailed information about high-priority sales negotiations.

[0528] Furthermore, the system analyzes past sales data to predict the likelihood of closing a deal, and, taking into account the results of the emotion engine analysis, proposes risk management guidelines and opportunities for cross-selling and upselling. The terminal visualizes these prediction results in an easy-to-understand manner and presents them to help the user plan their next actions.

[0529] As a concrete example, the server can adjust the plan based on the customer's response when they use certain words or tones. For instance, if the customer shows positive emotions, proactive follow-up is recommended. In this way, the present invention supports sales activities from an emotional perspective, enabling more sophisticated sales strategies. This system aims to improve the user experience and increase sales efficiency.

[0530] The following describes the processing flow.

[0531] Step 1:

[0532] The server automatically collects customer information from the internet and related databases and stores it in the database. This information includes basic company information, contact details, and past sales history.

[0533] Step 2:

[0534] The server structures the collected data and uses analytical algorithms to identify potential customers. Criteria such as industry, region, and past transaction history are used for identification.

[0535] Step 3:

[0536] The server scores the priority of each customer and creates a list of sales activities. This information is used to optimize the allocation of sales resources.

[0537] Step 4:

[0538] The terminal displays a prioritized list of potential customers received from the server in the user interface. The user uses this list to select target customers.

[0539] Step 5:

[0540] The server performs detailed analysis on selected customers, integrating purchase history and market trend data to generate customer profiles.

[0541] Step 6:

[0542] When a user initiates a business negotiation, the server uses an emotion engine to analyze the user's voice and input text in real time and evaluate their emotional state.

[0543] Step 7:

[0544] The emotion engine adjusts the user's emotional state based on the analysis results and optimizes the content of the sales strategy presentation. For example, if the user is feeling anxious, it provides a simplified mode that summarizes key information.

[0545] Step 8:

[0546] The server monitors the progress of sales negotiations and sends system-proposed action plans and guidelines to the user's terminal. This includes identifying success stories and early detection of problems.

[0547] Step 9:

[0548] The device displays received action plans and guidelines on its screen, helping users make situation-appropriate decisions.

[0549] Step 10:

[0550] The server uses machine learning to analyze past sales data and predict the likelihood of closing a deal. Based on this predictive information, it identifies opportunities for risk management and cross-selling / upselling.

[0551] Step 11:

[0552] The device presents the user with predicted conversion rates and suggested action plans, providing information to effectively plan the next steps.

[0553] (Example 2)

[0554] 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."

[0555] In sales activities, the inability to adequately analyze customer information and understand their emotional state makes it difficult to develop effective sales strategies, resulting in a lower success rate for deals. Furthermore, there is a need for methods to improve sales efficiency by utilizing past sales data to predict the likelihood of closing a deal.

[0556] 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.

[0557] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing emotional data and optimizing sales strategies according to the user's emotional state. This enables effective analysis of customer information and understanding of emotional states, thereby improving the success rate of business negotiations. It also makes it possible to predict the likelihood of closing a deal and support the efficient allocation of sales resources.

[0558] "Customer information" refers to data that includes attributes, history, behavior, and preferences of individual customers, and is important information that serves as a basis for decision-making in sales activities.

[0559] A "potential customer" refers to a prospective customer who is not currently a customer but is considered highly likely to become a customer in the future.

[0560] "Emotional data" refers to information that represents the emotional state of users and customers, and is collected through voice, text, behavioral patterns, and other means.

[0561] "Sales strategy" refers to the policies and methods of sales activities planned to effectively provide the most suitable products and services to a specific customer segment.

[0562] "Progress of the sales negotiation" refers to the progress of the sales process from the initial contact to the closing of the deal.

[0563] "Closing probability" is an indicator that shows the degree of likelihood that a particular business negotiation will actually result in a successful deal.

[0564] An "analytical algorithm" refers to a set of computational procedures and methods used to analyze data and extract useful information from it.

[0565] "Sales resources" refers to all human, material, and informational resources used to carry out sales activities.

[0566] This invention is an advanced system for streamlining sales activities, and is a device that comprehensively manages a series of processes from customer information collection and analysis to sales conversion prediction. The system connects servers and terminals via a network and provides a user-friendly interface.

[0567] The server utilizes an internet-connected database to collect customer information. The collected data is processed using analytical algorithms to identify potential customers. Software used includes database management systems and machine learning libraries. Examples include cloud-based database services and customer segmentation using Python's Scikit-learn.

[0568] Furthermore, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by users. This analysis utilizes speech recognition software and emotion analysis tools. For example, text generated by speech recognition is analyzed by an emotion analysis tool to identify the user's emotional state. This data is then used to optimize sales strategies.

[0569] The terminal displays real-time progress information on sales negotiations and provides sales strategies and advice tailored to the user's emotional state. Data visualization tools are used for this purpose. Specifically, the terminal displays progress and forecast information of the sales pipeline on its screen, helping users plan their next actions.

[0570] As a concrete example, the server analyzes a series of customer data and, based on the results, uses an emotion engine to evaluate the user's current emotional state. Based on this information, the terminal suggests the optimal follow-up method for the sales negotiation to the user. By using a generative AI model, it is possible to optimize the user experience and improve the efficiency of the entire sales process. In this case, the generative AI model can be input with prompts such as: "Predict the likelihood of closing a deal based on customer data, and propose the optimal sales strategy using emotion data."

[0571] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0572] Step 1:

[0573] The server collects customer information from the internet and linked databases. The information is obtained through website scraping and database searches using SQL queries. This information is collected as a dataset, including basic customer attributes, purchase history, and inquiry history, and is output as the basis for analysis in the next step.

[0574] Step 2:

[0575] The server processes the collected customer information using an analysis algorithm. Specifically, it performs clustering analysis using a machine learning algorithm based on Python's Scikit-learn to identify potential customer segments with common characteristics. The input for this step is the customer information collected in step 1, and the output is a list of the identified potential customers.

[0576] Step 3:

[0577] The server uses an emotion engine to analyze voice and text input from the user. In this step, speech recognition software is used to convert the speech into text, and then emotion analysis is performed. By analyzing the input voice and text data, the user's emotional state is quantified, and the results are output.

[0578] Step 4:

[0579] The terminal develops sales strategies based on the progress of a business negotiation, using sentiment analysis results provided by the server. Specifically, it uses numerical data on emotional state to determine in real time what actions should be taken in the negotiation and presents the user with optimal advice and action plans. The input includes sentiment analysis results, and the output includes specific sales strategies and advice.

[0580] Step 5:

[0581] The terminal visualizes and provides users with the progress and likelihood of closing a deal. Using a data visualization tool, it visually displays the deal status and closing prediction. The input for this step is historical deal data and closing probability predictions, and the output generates visualization information to support the user's next course of action.

[0582] (Application Example 2)

[0583] 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."

[0584] In sales activities, developing strategies that take into account customer emotions and circumstances has been difficult with traditional methods. In particular, quickly understanding a customer's emotional state and adjusting sales policies accordingly was a significant burden for many sales representatives. Furthermore, appropriately prioritizing potential customers and efficiently allocating resources was also a challenge.

[0585] 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.

[0586] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing user emotional data and optimizing sales strategies based on emotional states. This makes it possible to provide optimal sales strategies that take customer emotions into consideration.

[0587] "Customer information" refers to personal information, purchase history, behavioral patterns, and emotional states of customers that are necessary for conducting sales activities.

[0588] A "potential customer" refers to a customer who has not yet made an actual purchase but is likely to make one in the future.

[0589] "Sales strategy" refers to a plan or method for effectively selling products or services, taking into account customer needs and market trends.

[0590] "Progress of the deal" refers to the current status or stage in the sales process with the customer.

[0591] "Possibility of closing a deal" refers to the degree to which a business negotiation is likely to be successful and ultimately lead to a contract.

[0592] "Emotional data" refers to information that indicates a user's emotional state, and is obtained from voice, behavior, and text.

[0593] "Optimizing sales strategies" refers to adjusting and improving strategies based on collected data and analysis results to achieve the most effective sales activities.

[0594] "Sales communication" refers to the method of conveying the value of a product or service through dialogue and information exchange with customers.

[0595] This system enables the collection and analysis of customer information and the optimization of sales strategies based on sentiment data. The server collects customer-related information from various data sources, including the internet and databases. The collected data is then processed by advanced analytical algorithms to identify potential customers.

[0596] To understand user emotions in real time, the server is equipped with an emotion engine. This emotion engine uses speech recognition software and behavioral pattern detection algorithms to analyze the voice, text, and actions provided by the user. This allows the server to grasp the user's emotional state and adapt sales strategies accordingly.

[0597] The terminal displays the progress of a sales negotiation in real time and provides situation-specific advice based on the user's emotional data. For example, if the user is feeling stressed, the system can simplify the negotiation content and highlight high-priority items to reduce the user's burden. In this way, the system aims to improve the user experience.

[0598] Furthermore, by analyzing past sales data, the system predicts the likelihood of closing a deal and presents users with risk management guidelines, cross-selling opportunities, and upselling opportunities tailored to the situation. These predictions are displayed visually and clearly on the terminal.

[0599] The hardware utilizes a high-sensitivity microphone and camera, while the software employs advanced machine learning models for speech recognition and emotion analysis. For example, by leveraging a generative AI model, if a user says, "Work has been really stressful lately," the emotion engine can interpret this as negative and suggest relaxing services.

[0600] An example of a prompt for a generative AI model might be: "Consider the current emotional state of the customer and generate an appropriate sales pitch. The customer's words are 'Work has been tough lately,' and their emotion is negative."

[0601] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0602] Step 1:

[0603] The server collects basic customer information from the internet and linked databases. Input data includes individual customer information, purchase history, and web behavior records. This data is then structured and stored in the database. Specifically, APIs are used to query external databases, retrieve the necessary information, and convert it into an internal format.

[0604] Step 2:

[0605] The server uses advanced analytical algorithms to analyze customer behavior trends based on collected customer information. Here, the collected customer data is used as input, and the output includes identifying potential customers and calculating their priority. This process uses machine learning models to compare customers' past history with market trends, highlighting potentially high-profit customers.

[0606] Step 3:

[0607] The server analyzes the voice and text data provided by the user in real time and uses an emotion engine to evaluate the user's emotional state. Inputs include voice and text data collected via microphone and keyboard. Emotion analysis is performed using natural language processing algorithms, and the user's emotional state is determined as a result.

[0608] Step 4:

[0609] The terminal receives information from the server regarding the progress of a sales negotiation and, taking into account the user's emotional data, displays situation-appropriate advice to the user. Inputs are progress information and emotional state evaluation results provided by the server. Outputs include a sales negotiation progress report and a sales strategy optimized for the user. The terminal uses a GUI to visually present data to the user, providing immediate information for decision-making.

[0610] Step 5:

[0611] Using historical sales data, the server predicts the likelihood of closing a deal. The input is existing sales data, and the output is a score indicating the probability of closing the deal. This prediction combines statistical methods and machine learning models to evaluate future business opportunities. The generated information is useful for risk management and identifying additional sales opportunities.

[0612] Step 6:

[0613] The user plans their next actions based on the prediction results. To support this, the device visualizes and displays cross-sell and up-sell opportunities along with a conversion probability score. The entered prediction score is processed into an easily understandable format on the user interface using visualization tools. As a result, the user can quickly develop a more effective sales plan.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] [Fourth Embodiment]

[0618] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0619] 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.

[0620] 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).

[0621] 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.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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".

[0631] This invention is an automation tool for streamlining sales activities, and it builds sales strategies by acquiring and analyzing customer information. The system operates via a network, and is configured so that the server and user terminals communicate with each other.

[0632] The server collects publicly available customer information from multiple data sources and extracts key information through a data cleansing process. This information is used to identify and prioritize potential customers. For example, the server can prioritize listing customers belonging to specific regions or industries based on industry standards and existing customer profiles.

[0633] Next, the server performs a detailed customer analysis. This aims to identify customer needs and formulate targeted approaches based on historical data and market trends. For example, it can analyze past purchase history to predict product replacement cycles. As a result, the terminal displays the analyzed data along with suggested sales strategies.

[0634] Furthermore, the server monitors the progress of the business negotiation in real time and provides specific advice to improve the probability of success. Specific suggestions tailored to the issues to be resolved and the prospect's areas of interest are fed back to the user's terminal.

[0635] Furthermore, the server is equipped with a system that uses past sales negotiation data to predict the likelihood of closing a deal, and can estimate future sales outcomes by applying machine learning technology. User terminals visually display these prediction results and provide concrete suggestions to support risk management, cross-selling, and upselling strategies.

[0636] For example, the server can analyze past data for specific products with high campaign performance and suggest to the user that they run similar promotions on other untapped customers. In this way, the present invention can improve the accuracy and efficiency of sales activities with an interface that is easy for users without specialized knowledge to use.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The server collects publicly available customer information from the internet and affiliated database systems. Specifically, it automatically retrieves company profiles, industry data, contact information, and other data, and stores it in the database.

[0640] Step 2:

[0641] The server filters the collected data to remove unnecessary information and performs data cleansing to correct for duplicates and missing data. This refines the list of potential customers.

[0642] Step 3:

[0643] Based on the cleansed data, the server applies analytical algorithms to customer attributes and behavioral history to identify potential customers and set priorities.

[0644] Step 4:

[0645] The terminal displays a prioritized list of potential customers sent from the server on a dashboard, making it viewable by the user.

[0646] Step 5:

[0647] When a user selects a specific customer, the server performs a detailed analysis of that customer. It refers to past transaction history and market trends to understand the customer's purchasing tendencies.

[0648] Step 6:

[0649] Based on the analysis results, the server develops an effective approach strategy and sends it to the user's terminal as a recommended plan.

[0650] Step 7:

[0651] The device presents the user with recommended approach strategies, which the user then uses to plan their sales activities.

[0652] Step 8:

[0653] The server monitors the progress of the deal in real time and generates advice based on the progress. It predicts the next steps necessary for the deal's success and provides guidelines.

[0654] Step 9:

[0655] The device provides users with advice and success stories related to business negotiations, supporting them through the process of the negotiation.

[0656] Step 10:

[0657] The server predicts the likelihood of closing a current deal based on a machine learning model and identifies related risks and opportunities.

[0658] Step 11:

[0659] The terminal reports to the user the predicted probability of closing a deal, along with risk management strategies and cross-selling / upselling suggestions based on that prediction. This allows the user to select the optimal sales strategy.

[0660] (Example 1)

[0661] 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".

[0662] In modern sales activities, efficiently collecting vast amounts of customer information and effectively identifying potential customers is a significant challenge. Furthermore, there is a lack of concrete guidelines for developing sales strategies tailored to customer needs, effectively conducting negotiations, and accurately predicting the likelihood of closing a deal. This makes optimizing sales resources difficult and hinders the maximization of sales results.

[0663] 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.

[0664] In this invention, the server includes means for collecting customer information to identify potential customers to be processed, means for performing analysis on customers based on the collected information to build sales strategies, means for monitoring the progress of negotiations and providing advice for the success of those negotiations, means for improving sales strategy proposals by analyzing the characteristics of potential customers using a generative AI model, and means for providing follow-up proposals tailored to the progress of negotiations through a user interface. This makes it possible to improve the accuracy and results of sales activities through efficient collection and analysis of customer information.

[0665] "Customer information" refers to all data related to the customer, such as customer profiles, purchase history, and industry attributes.

[0666] "Methods for identifying potential customers" refers to the process of analyzing customer information from diverse data sources to identify new customers who are likely to make a purchase.

[0667] "Methods for developing a sales strategy" refer to methods for analyzing customer needs and market trends based on collected data, and formulating the optimal sales approach.

[0668] "Means for monitoring the progress of business negotiations" refers to a system for tracking and evaluating the current status and progress of business negotiations in real time.

[0669] "Means of providing advice" refers to methods of generating and providing specific suggestions and instructions to improve the probability of sales success, depending on the situation of the business negotiation.

[0670] "Methods for predicting the likelihood of closing a deal" refer to a process for statistically estimating the probability that a future deal will be closed, based on past sales negotiation data.

[0671] A "generative AI model" is an artificial intelligence technology that supports decision-making by analyzing large amounts of data and extracting patterns and relationships.

[0672] A "user interface" is the visual and manipulative environment through which a user interacts with a system's functions and retrieves information.

[0673] This invention is implemented as an integrated system for collecting and analyzing customer information, formulating sales strategies, and managing the progress of business negotiations. The server automatically collects customer information from various external data sources using APIs and web scraping techniques. Specific software used includes the Python libraries "requests" and "BeautifulSoup".

[0674] The collected data is processed by the server through a data cleansing process to extract important information. Data processing libraries such as Pandas and NumPy are used for this process. Based on this organized information, the server utilizes a generative AI model to identify potential customers, analyze their characteristics, and build an optimal sales strategy.

[0675] Furthermore, the server uses machine learning libraries such as Scikit-learn to analyze past sales data and predict the likelihood of closing a deal. This prediction can generate specific guidelines and advice to increase the success rate of the deal and provide them to the user's terminal. On the terminal, these results and advice are visually displayed through the user interface to help with decision-making for the next steps.

[0676] In actual implementation, the server prompts the user with a message such as, "Based on past sales data, formulate a sales strategy for the next quarter and propose it along with key KPIs," providing input to the AI ​​model. Based on this prompt, the AI ​​performs the necessary analysis and generates specific proposals. Through this process, the user can conduct sales activities efficiently and make optimal use of resources.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] The server collects customer information from external data sources. The input specifies initial information about the target customer group, and the Python "requests" library is used to retrieve data from APIs and web pages. The data collected in this process includes customer profiles, past transaction information, and industry information. The output is a collection of available raw data.

[0680] Step 2:

[0681] The server performs data cleansing on the collected customer data. The raw data collected in step 1 is used as input. The data is processed using Pandas or NumPy to handle missing values, remove duplicate data, and standardize data formats. The output is the refined, cleansed data.

[0682] Step 3:

[0683] The server performs analysis to identify potential customers using the cleansed data. The cleansed data obtained in step 2 is used as input. The server uses a generative AI model to perform scoring and target customer prioritization based on customer characteristics. The output is a prioritized list of potential customers.

[0684] Step 4:

[0685] The server builds sales strategies based on historical data and market trends. The input is the list of potential customers obtained in step 3 and historical sales data, which is analyzed using machine learning techniques. Scikit-learn is used to predict customer behavior, identify the purchase cycle, and determine the optimal approach. The output is a set of recommended sales strategies.

[0686] Step 5:

[0687] The terminal visually displays the sales strategy and analysis results sent from the server. The input is the sales strategy built in Step 4. Through the user interface, the terminal visualizes key KPIs and strategies in a dashboard format, presenting them in an easy-to-understand manner for the user. The output is a visually clear display of the sales strategy.

[0688] Step 6:

[0689] The server monitors the progress of sales negotiations in real time and generates follow-up suggestions. It uses current negotiation progress information and past customer response data as input. The server utilizes a generation AI model to suggest specific next steps and generate guidelines to increase the success rate of the negotiation. The output is personalized follow-up suggestions.

[0690] Step 7:

[0691] The terminal receives advice from the server and presents it to the user. The input is the follow-up suggestions generated in step 6. The terminal displays these suggestions on the user interface, providing information that helps the user decide on their next course of action. The output is a presentation of specific follow-up actions to the user.

[0692] (Application Example 1)

[0693] 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".

[0694] In sales activities, it is difficult to quickly develop effective sales strategies and make appropriate approaches to potential customers. Furthermore, there is a lack of efficient means to propose products and promotions to target customers. As a result, sales representatives find it difficult to develop personalized strategies for individual customers, leading to missed sales opportunities.

[0695] 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.

[0696] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed; means for performing analysis on customers based on the collected information and building sales strategies; means for monitoring the progress of negotiations and providing advice for the success of those negotiations; means for predicting the likelihood of closing a deal based on past negotiation data; means for visually presenting the analysis results to the user; and means for proposing products and promotions suitable for target customers. This enables sales representatives to quickly and efficiently develop sales strategies and implement personalized approaches to customers.

[0697] "Customer information" refers to all data based on a customer's publicly available profile, purchase history, behavioral history, etc.

[0698] "Potential customers to be processed" refers to prospective customers who should be prioritized for approach in commercial activities.

[0699] "Methods for conducting analysis and building sales strategies" refers to methods of analyzing collected data and formulating effective sales policies and strategies based on that analysis.

[0700] "A means of monitoring the progress of a business deal and providing advice to help it succeed" refers to a procedure for monitoring the status of ongoing business deals and providing appropriate advice to increase the chances of success.

[0701] "Methods for predicting the likelihood of closing a deal" refer to techniques that use data from past business negotiations to estimate the probability of future business negotiations being successful.

[0702] "Means of visually presenting analysis results to the user" refers to methods of displaying the analyzed data to the user in a visual format such as graphs or charts.

[0703] "Means of proposing products and promotions suitable for target customers" refers to an approach to suggesting the most relevant products and promotional activities to specific customers.

[0704] The system for implementing this invention is to acquire customer information via a network, perform analysis, and build effective sales strategies for customers. The server is built using Python and the Flask framework and collects customer information from multiple data sources. PostgreSQL is used as the database for storing and managing customer data. The server processes the collected data using scikit-learn and analyzes customer purchasing patterns and needs.

[0705] The analysis results generated by the server are sent to the device via API, where they are visually presented to the user as a cross-platform application using React Native. The device displays target customer information, suitable products, and promotional suggestions to the user, and provides real-time updates on the progress of the sales negotiation.

[0706] As a concrete example, by analyzing past customer purchase history, the device can identify that a particular customer regularly purchases products in the same category. In this case, the device can notify that customer of new product suggestions or upsells on related products. This allows users to quickly develop efficient sales strategies.

[0707] As an example of a prompt using a generative AI model, the server will perform appropriate analysis by issuing the instruction, "Identify target customers based on their past purchase history and suggest the most suitable promotion."

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The server collects customer information from multiple data sources over the network. Inputs include public customer profiles and purchase history, while output is centralized customer data. The server uses an API to ingest this data and stores it in a PostgreSQL database.

[0711] Step 2:

[0712] The server cleanses the collected customer data and prepares it for analysis. The input is raw data and may contain unnecessary or inconsistent information. It performs a cleansing process and outputs data formatted to provide useful information. Specifically, it removes duplicate data and imputes missing values.

[0713] Step 3:

[0714] The server uses scikit-learn to perform data analysis and identify target customers and their needs. Cleansed customer data is used as input, and a machine learning model is employed to analyze purchasing patterns. The output is targeting information for individual customers. Specific processing includes customer segmentation and purchase prediction.

[0715] Step 4:

[0716] The server uses an AI model that generates optimal products and promotions for target customers based on the analysis results to make suggestions. The input is targeting information and data on existing promotions, and the output is a customized promotion strategy for each customer. Specifically, it generates prompt messages and provides them to the AI ​​model.

[0717] Step 5:

[0718] The device visually presents suggestions received from the server to the user. The input is suggestion data from the server. Using React Native, it displays graphs and recommendation lists, and delivers them to the customer as push notifications at the appropriate time. Specific actions include UI updates and triggering the notification system.

[0719] Step 6:

[0720] Users conduct sales activities based on information received through their terminals and input the progress of sales negotiations. Input includes the current status and progress data of sales negotiations, which are then sent back to the server. Output provides information that enables the review of sales strategies and the planning of the next actions. Specific actions include data entry and decision-making regarding the next step.

[0721] 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.

[0722] This invention is a system designed to support sales activities, combining customer information collection, sales strategy development, negotiation progress management, and probability of closing deals with an emotion engine that recognizes user emotions and incorporates them into the strategy. The system communicates between a central server and terminals via a network, providing a user-friendly interface.

[0723] First, the server collects customer information from the internet and linked databases. The collected information is processed by analytical algorithms to identify potential customers. These customers are then prioritized and applied to sales activities.

[0724] In parallel, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by the user to detect the user's emotional state. Based on the analyzed emotional data, the emotion engine can further optimize the user's sales strategy.

[0725] Specifically, when the terminal displays real-time progress information on sales negotiations, it takes user emotional data into account and provides situation-appropriate advice and sales strategies to the user. For example, if the user is feeling stressed, the system will simplify the proposal or highlight detailed information about high-priority sales negotiations.

[0726] Furthermore, the system analyzes past sales data to predict the likelihood of closing a deal, and, taking into account the results of the emotion engine analysis, proposes risk management guidelines and opportunities for cross-selling and upselling. The terminal visualizes these prediction results in an easy-to-understand manner and presents them to help the user plan their next actions.

[0727] As a concrete example, the server can adjust the plan based on the customer's response when they use certain words or tones. For instance, if the customer shows positive emotions, proactive follow-up is recommended. In this way, the present invention supports sales activities from an emotional perspective, enabling more sophisticated sales strategies. This system aims to improve the user experience and increase sales efficiency.

[0728] The following describes the processing flow.

[0729] Step 1:

[0730] The server automatically collects customer information from the internet and related databases and stores it in the database. This information includes basic company information, contact details, and past sales history.

[0731] Step 2:

[0732] The server structures the collected data and uses analytical algorithms to identify potential customers. Criteria such as industry, region, and past transaction history are used for identification.

[0733] Step 3:

[0734] The server scores the priority of each customer and creates a list of sales activities. This information is used to optimize the allocation of sales resources.

[0735] Step 4:

[0736] The terminal displays a prioritized list of potential customers received from the server in the user interface. The user uses this list to select target customers.

[0737] Step 5:

[0738] The server performs detailed analysis on selected customers, integrating purchase history and market trend data to generate customer profiles.

[0739] Step 6:

[0740] When a user initiates a business negotiation, the server uses an emotion engine to analyze the user's voice and input text in real time and evaluate their emotional state.

[0741] Step 7:

[0742] The emotion engine adjusts the user's emotional state based on the analysis results and optimizes the content of the sales strategy presentation. For example, if the user is feeling anxious, it provides a simplified mode that summarizes key information.

[0743] Step 8:

[0744] The server monitors the progress of sales negotiations and sends system-proposed action plans and guidelines to the user's terminal. This includes identifying success stories and early detection of problems.

[0745] Step 9:

[0746] The device displays received action plans and guidelines on its screen, helping users make situation-appropriate decisions.

[0747] Step 10:

[0748] The server uses machine learning to analyze past sales data and predict the likelihood of closing a deal. Based on this predictive information, it identifies opportunities for risk management and cross-selling / upselling.

[0749] Step 11:

[0750] The device presents the user with predicted conversion rates and suggested action plans, providing information to effectively plan the next steps.

[0751] (Example 2)

[0752] 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".

[0753] In sales activities, the inability to adequately analyze customer information and understand their emotional state makes it difficult to develop effective sales strategies, resulting in a lower success rate for deals. Furthermore, there is a need for methods to improve sales efficiency by utilizing past sales data to predict the likelihood of closing a deal.

[0754] 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.

[0755] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing emotional data and optimizing sales strategies according to the user's emotional state. This enables effective analysis of customer information and understanding of emotional states, thereby improving the success rate of business negotiations. It also makes it possible to predict the likelihood of closing a deal and support the efficient allocation of sales resources.

[0756] "Customer information" refers to data that includes attributes, history, behavior, and preferences of individual customers, and is important information that serves as a basis for decision-making in sales activities.

[0757] A "potential customer" refers to a prospective customer who is not currently a customer but is considered highly likely to become a customer in the future.

[0758] "Emotional data" refers to information that represents the emotional state of users and customers, and is collected through voice, text, behavioral patterns, and other means.

[0759] "Sales strategy" refers to the policies and methods of sales activities planned to effectively provide the most suitable products and services to a specific customer segment.

[0760] "Progress of the sales negotiation" refers to the progress of the sales process from the initial contact to the closing of the deal.

[0761] "Closing probability" is an indicator that shows the degree of likelihood that a particular business negotiation will actually result in a successful deal.

[0762] An "analytical algorithm" refers to a set of computational procedures and methods used to analyze data and extract useful information from it.

[0763] "Sales resources" refers to all human, material, and informational resources used to carry out sales activities.

[0764] This invention is an advanced system for streamlining sales activities, and is a device that integrates and manages a series of processes from customer information collection and analysis to sales forecasting. The system connects servers and terminals via a network and provides a user-friendly interface.

[0765] The server utilizes an internet-connected database to collect customer information. The collected data is processed using analytical algorithms to identify potential customers. Software used includes database management systems and machine learning libraries. Examples include cloud-based database services and customer segmentation using Python's Scikit-learn.

[0766] Furthermore, the server is equipped with an emotion engine that analyzes voice, text, and behavioral patterns provided by users. This analysis utilizes speech recognition software and emotion analysis tools. For example, text generated by speech recognition is analyzed by an emotion analysis tool to identify the user's emotional state. This data is then used to optimize sales strategies.

[0767] The terminal displays real-time progress information on sales negotiations and provides sales strategies and advice tailored to the user's emotional state. Data visualization tools are used for this purpose. Specifically, the terminal displays progress and forecast information of the sales pipeline on its screen, helping users plan their next actions.

[0768] As a concrete example, the server analyzes a series of customer data and, based on the results, uses an emotion engine to evaluate the user's current emotional state. Based on this information, the terminal suggests the optimal follow-up method for the sales negotiation to the user. By using a generative AI model, it is possible to optimize the user experience and improve the efficiency of the entire sales process. In this case, the generative AI model can be input with prompts such as: "Predict the likelihood of closing a deal based on customer data, and propose the optimal sales strategy using emotion data."

[0769] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0770] Step 1:

[0771] The server collects customer information from the internet and linked databases. The information is obtained through website scraping and database searches using SQL queries. This information is collected as a dataset, including basic customer attributes, purchase history, and inquiry history, and is output as the basis for analysis in the next step.

[0772] Step 2:

[0773] The server processes the collected customer information using an analysis algorithm. Specifically, it performs clustering analysis using a machine learning algorithm based on Python's Scikit-learn to identify potential customer segments with common characteristics. The input for this step is the customer information collected in step 1, and the output is a list of the identified potential customers.

[0774] Step 3:

[0775] The server uses an emotion engine to analyze voice and text input from the user. In this step, speech recognition software is used to convert the speech into text, and then emotion analysis is performed. By analyzing the input voice and text data, the user's emotional state is quantified, and the results are output.

[0776] Step 4:

[0777] The terminal develops sales strategies based on the progress of a business negotiation, using sentiment analysis results provided by the server. Specifically, it uses numerical data on emotional state to determine in real time what actions should be taken in the negotiation and presents the user with optimal advice and action plans. The input includes sentiment analysis results, and the output includes specific sales strategies and advice.

[0778] Step 5:

[0779] The terminal visualizes and provides users with the progress and likelihood of closing a deal. Using a data visualization tool, it visually displays the deal status and closing prediction. The input for this step is historical deal data and closing probability predictions, and the output generates visualization information to support the user's next course of action.

[0780] (Application Example 2)

[0781] 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".

[0782] In sales activities, developing strategies that take into account customer emotions and circumstances has been difficult with traditional methods. In particular, quickly understanding a customer's emotional state and adjusting sales policies accordingly was a significant burden for many sales representatives. Furthermore, appropriately prioritizing potential customers and efficiently allocating resources was also a challenge.

[0783] 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.

[0784] In this invention, the server includes means for collecting customer information and identifying potential customers to be processed, means for performing analysis on customers based on the collected information and constructing sales strategies, and means for analyzing user emotional data and optimizing sales strategies based on emotional states. This makes it possible to provide optimal sales strategies that take customer emotions into consideration.

[0785] "Customer information" refers to personal information, purchase history, behavioral patterns, and emotional states of customers that are necessary for conducting sales activities.

[0786] A "potential customer" refers to a customer who has not yet made an actual purchase but is likely to make one in the future.

[0787] "Sales strategy" refers to a plan or method for effectively selling products or services, taking into account customer needs and market trends.

[0788] "Progress of the deal" refers to the current status or stage in the sales process with the customer.

[0789] "Possibility of closing a deal" refers to the degree to which a business negotiation is likely to be successful and ultimately lead to a contract.

[0790] "Emotional data" refers to information that indicates a user's emotional state, and is obtained from voice, behavior, and text.

[0791] "Optimizing sales strategies" refers to adjusting and improving strategies based on collected data and analysis results to achieve the most effective sales activities.

[0792] "Sales communication" refers to the method of conveying the value of a product or service through dialogue and information exchange with customers.

[0793] This system enables the collection and analysis of customer information and the optimization of sales strategies based on sentiment data. The server collects customer-related information from various data sources, including the internet and databases. The collected data is then processed by advanced analytical algorithms to identify potential customers.

[0794] To understand user emotions in real time, the server is equipped with an emotion engine. This emotion engine uses speech recognition software and behavioral pattern detection algorithms to analyze the voice, text, and actions provided by the user. This allows the server to grasp the user's emotional state and adapt sales strategies accordingly.

[0795] The terminal displays the progress of a sales negotiation in real time and provides situation-specific advice based on the user's emotional data. For example, if the user is feeling stressed, the system can simplify the negotiation content and highlight high-priority items to reduce the user's burden. In this way, the system aims to improve the user experience.

[0796] Furthermore, by analyzing past sales data, the system predicts the likelihood of closing a deal and presents users with risk management guidelines, cross-selling opportunities, and upselling opportunities tailored to the situation. These predictions are displayed visually and clearly on the terminal.

[0797] The hardware utilizes a high-sensitivity microphone and camera, while the software employs advanced machine learning models for speech recognition and emotion analysis. For example, by leveraging a generative AI model, if a user says, "Work has been really stressful lately," the emotion engine can interpret this as negative and suggest relaxing services.

[0798] An example of a prompt for a generative AI model might be: "Consider the current emotional state of the customer and generate an appropriate sales pitch. The customer's words are 'Work has been tough lately,' and their emotion is negative."

[0799] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0800] Step 1:

[0801] The server collects basic customer information from the internet and linked databases. Input data includes individual customer information, purchase history, and web behavior records. This data is then structured and stored in the database. Specifically, APIs are used to query external databases, retrieve the necessary information, and convert it into an internal format.

[0802] Step 2:

[0803] The server uses advanced analytical algorithms to analyze customer behavior trends based on collected customer information. Here, the collected customer data is used as input, and the output includes identifying potential customers and calculating their priority. This process uses machine learning models to compare customers' past history with market trends, highlighting potentially high-profit customers.

[0804] Step 3:

[0805] The server analyzes the voice and text data provided by the user in real time and uses an emotion engine to evaluate the user's emotional state. Inputs include voice and text data collected via microphone and keyboard. Emotion analysis is performed using natural language processing algorithms, and the user's emotional state is determined as a result.

[0806] Step 4:

[0807] The terminal receives information from the server regarding the progress of a sales negotiation and, taking into account the user's emotional data, displays situation-appropriate advice to the user. Inputs are progress information and emotional state evaluation results provided by the server. Outputs include a sales negotiation progress report and a sales strategy optimized for the user. The terminal uses a GUI to visually present data to the user, providing immediate information for decision-making.

[0808] Step 5:

[0809] Using historical sales data, the server predicts the likelihood of closing a deal. The input is existing sales data, and the output is a score indicating the probability of closing the deal. This prediction combines statistical methods and machine learning models to evaluate future business opportunities. The generated information is useful for risk management and identifying additional sales opportunities.

[0810] Step 6:

[0811] The user plans their next actions based on the prediction results. To support this, the device visualizes and displays cross-sell and up-sell opportunities along with a conversion probability score. The entered prediction score is processed into an easily understandable format on the user interface using visualization tools. As a result, the user can quickly develop a more effective sales plan.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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."

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] A means of collecting customer information and identifying potential customers to be processed,

[0836] A means of conducting customer analysis based on collected information and developing sales strategies,

[0837] A means to monitor the progress of business negotiations and provide advice for the success of those negotiations,

[0838] A method for predicting the likelihood of closing a deal based on past sales negotiation data,

[0839] A system that includes this.

[0840] (Claim 2)

[0841] The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

[0842] (Claim 3)

[0843] The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities.

[0844] "Example 1"

[0845] (Claim 1)

[0846] A means of collecting customer information and identifying potential customers to be processed,

[0847] A means of conducting customer analysis based on collected information and developing sales strategies,

[0848] A means to monitor the progress of business negotiations and provide advice for the success of those negotiations,

[0849] A method for predicting the likelihood of closing a deal based on past sales negotiation data,

[0850] By using generative AI models to analyze the characteristics of potential customers, we can improve our sales strategy proposals.

[0851] A means of providing follow-up proposals tailored to the progress of the business negotiation through the user interface,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

[0855] (Claim 3)

[0856] The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities.

[0857] "Application Example 1"

[0858] (Claim 1)

[0859] A means of collecting customer information and identifying potential customers to be processed,

[0860] A means of conducting customer analysis based on collected information and developing sales strategies,

[0861] A means to monitor the progress of business negotiations and provide advice for the success of those negotiations,

[0862] A method for predicting the likelihood of closing a deal based on past sales negotiation data,

[0863] A means of visually presenting the analysis results to the user,

[0864] A means of proposing products and promotions suitable for target customers,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

[0868] (Claim 3)

[0869] The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities.

[0870] "Example 2 of combining an emotion engine"

[0871] (Claim 1)

[0872] A means of collecting customer information and identifying potential customers to be processed,

[0873] A means of conducting customer analysis based on collected information and developing sales strategies,

[0874] A means to monitor the progress of business negotiations and provide advice for the success of those negotiations,

[0875] A method for predicting the likelihood of closing a deal based on past sales negotiation data,

[0876] A means of analyzing emotional data and optimizing sales strategies according to the user's emotional state,

[0877] A means of providing information to users through the visualization of customer data,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

[0881] (Claim 3)

[0882] The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities.

[0883] "Application example 2 when combining with an emotional engine"

[0884] (Claim 1)

[0885] A means of collecting customer information and identifying potential customers to be processed,

[0886] A means of conducting customer analysis based on collected information and developing sales strategies,

[0887] A means to monitor the progress of business negotiations and provide advice for the success of those negotiations,

[0888] A method for predicting the likelihood of closing a deal based on past sales negotiation data,

[0889] A means of analyzing user emotional data and optimizing sales strategies based on emotional states,

[0890] A means of proposing appropriate sales communication by considering emotional data and the status of the business negotiation,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

[0894] (Claim 3)

[0895] The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities. [Explanation of symbols]

[0896] 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 means of collecting customer information and identifying potential customers to be processed, A means of conducting customer analysis based on collected information and developing sales strategies, A means to monitor the progress of business negotiations and provide advice for the success of those negotiations, A method for predicting the likelihood of closing a deal based on past sales negotiation data, A system that includes this.

2. The system according to claim 1, comprising means for determining the priority of potential customers and recommending sales resources based on that priority.

3. The system according to claim 1, further comprising means for creating risk management guidelines based on the likelihood of closing a deal and for presenting cross-selling and upselling opportunities.

Images