system

Abstract

We provide the system. [Solution] A means of retrieving information from a database that stores customer information, sales representative information, and past transaction history, A means for executing a machine learning algorithm to generate a product proposal method suitable for the customer based on acquired customer information, A means of customizing the generated product proposal method based on the characteristics of the sales representative, A means of providing a user interface for presenting customized product proposal methods to sales representatives, A means of recording the results of sales activities as feedback and accumulating them in a database, 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 takes time for a person in charge to accumulate experience, and the individual business styles being personal promotes the instability of business performance. Furthermore, there is a problem that the proposal methods for commercial products are different for each person in charge, making it difficult to improve the efficiency of overall business activities. Also, there is a need to solve the problem that there is insufficient systematic support for finding optimal methods for approaching new customers and building relationships with existing customers.

Means for Solving the Problems

[0005] To solve these problems, the present invention provides a means for using a machine learning algorithm that retrieves information from a database storing customer information, sales representative information, and past transaction history, and generates a product proposal method suitable for the customer based on the retrieved information. Furthermore, it includes means for customizing the generated product proposal method based on the characteristics of the sales representative and providing a user interface for presenting the results to the sales representative. In addition, by building a feedback loop that records the results of sales activities as feedback in the database and continuously learns from it, the invention realizes efficient and effective sales activities.

[0006] "Customer information" refers to data about customer companies, including information such as industry, size, location, and purchase history.

[0007] "Sales representative information" refers to data about sales representatives, including their characteristics, performance, and past sales approach styles.

[0008] "Past transaction history" refers to records of commercial transactions conducted to date, including information such as the details of the transaction, the date and time, and records of customer interactions.

[0009] A "database" is an information system that collects large amounts of data and makes it available for use when needed.

[0010] A "machine learning algorithm" is a computational procedure that allows a computer to learn from data and automatically improve specific tasks or models.

[0011] "Product proposal method" refers to the methodology for selecting and presenting products and services to customers.

[0012] "Customization" means adjusting or modifying something to suit a specific purpose or need.

[0013] A "user interface" is a means of display and input that facilitates the exchange of information between a computer system and its user.

[0014] "Feedback" is a means of collecting reactions and information about the results of a certain action or process, and using that information to improve the process.

[0015] A "feedback loop" is a cyclical mechanism that evaluates the results of actions and processes performed within a system and uses that information to improve or adjust the system. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention relates to a system for proposing the most suitable products to customers during sales activities, and its embodiments are described in detail below. This system mainly consists of three elements: a server, a terminal, and a user.

[0038] Server operation

[0039] The server first collects customer information, sales representative information, and past transaction history from the database. The server cleans this data and converts it into a consistent format, making it suitable for subsequent analysis. Next, the server runs machine learning algorithms to analyze the collected information and generate successful sales techniques and customer-tailored product proposals. These algorithms learn from past sales performance and optimize product proposals based on different sales styles. After the proposals are generated, the server customizes them to suit the characteristics of each sales representative and optimizes them for effective results.

[0040] Terminal operation

[0041] The terminal receives customized proposals sent from the server and presents them visually to the sales representative. This presentation is designed to allow sales representatives to easily understand the proposals and use them to communicate with customers. The terminal also provides an interface for receiving user feedback. This interface is simple and allows for quick recording of results from sales activities and customer reactions.

[0042] User actions

[0043] The user, i.e., the sales representative, reviews the proposed product details via their terminal. Based on the proposal method, the user conducts sales activities with the customer and feeds the results back into the system. The feedback recorded by the user is sent to the server as data to improve the accuracy of future proposals. This feedback information is collected again by the server and stored in a database, which is then used for future product proposals.

[0044] Specific example

[0045] For example, when making a sales pitch to customer A in the construction industry, the server analyzes industry trends and customer A's past purchasing history. If the analysis determines that customer A tends to prioritize cost, a proposal emphasizing cost performance will be displayed on the terminal. The user then conducts negotiations with customer A based on this proposal and feeds the results back into the system. This feedback information is used to improve future proposals for similar industries and customers.

[0046] As a result, this invention functions as a system that streamlines and improves the accuracy of sales activities and supports the improvement of sales representatives' performance.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server connects to the database and retrieves necessary customer information, sales representative information, and past transaction history. This data includes the customer company's industry, size, location, purchase history, and the sales performance and characteristics of the sales representative.

[0050] Step 2:

[0051] The server performs data cleaning to organize the acquired data. It imputes missing values, standardizes data formats, and builds a consistent dataset. This ensures the data is ready for analysis.

[0052] Step 3:

[0053] The server analyzes the data, which has been prepared using machine learning algorithms. In this process, the learning model is trained to extract past successful sales methods and proposal methods that are suitable for customer characteristics.

[0054] Step 4:

[0055] The server uses a trained model to generate product recommendations tailored to the customer. These recommendations include the most appropriate products and approaches from the product lineup.

[0056] Step 5:

[0057] The server customizes the product proposal methods obtained based on the characteristics and skills of the sales representative. This ensures that proposals are prepared that allow the representative to approach customers in a way that maximizes their strengths.

[0058] Step 6:

[0059] The server sends customized proposals to the terminal. The terminal displays the proposals in a visually easy-to-understand format, making them user-friendly for sales representatives.

[0060] Step 7:

[0061] Users conduct sales activities based on the proposals displayed on their devices. They record customer reactions and results obtained during sales activities.

[0062] Step 8:

[0063] The terminal sends feedback on sales activities to the server. The feedback information entered by the user is stored in a database so that it can be used for future proposals.

[0064] This allows the system to continuously improve the accuracy of its proposals and support sales activities.

[0065] (Example 1)

[0066] 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."

[0067] In modern sales activities, there is a demand for efficient and effective responses to the diversifying needs of customers. However, with traditional methods, it is extremely time-consuming for sales representatives to meticulously analyze the needs of each individual customer and create optimal proposals, resulting in inefficiencies for companies. Furthermore, there is a lack of mechanisms to effectively utilize the feedback obtained from sales activities and incorporate it into future sales efforts. This creates a challenge in improving sales performance.

[0068] 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.

[0069] In this invention, the server includes means for acquiring sales-related information and historical information from a storage device that stores information, means for executing an algorithm for generating product proposals using pre-processed information, and means for adjusting the generated product proposals based on the characteristics of individual agents. This makes it possible to improve the efficiency and accuracy of proposals in sales activities.

[0070] A "storage device for storing information" is a device that stores data and allows data to be read out as needed.

[0071] "Sales-related information" refers to data such as customer information, transaction history, and product information related to the sale of goods and services.

[0072] "Historical information" refers to detailed information about past transactions, and is a record of how customers have used products and services.

[0073] "Preprocessing" refers to initial processing to improve the quality of data and prepare it for analysis, including data cleaning and formatting.

[0074] An "algorithm" refers to a series of computational steps, a method for analyzing data and generating suggestions to solve a specific problem.

[0075] "Activist" refers to someone who sells goods or provides services, and usually means a sales representative.

[0076] "Feedback" refers to information recorded from sales activities and customer reactions, used to improve future proposals.

[0077] This invention provides a system that enables efficient product proposals and their customization in sales activities. This system primarily consists of a server, terminals, and users, with each component working in coordination.

[0078] Server operation

[0079] The server collects data, including sales-related and historical information, from storage devices. Data collection can be done using SQL queries, and the information is exported, for example, in CSV format. After data collection, the server uses the Python Pandas library to preprocess and clean the data. Techniques such as imputing incomplete data with the mean are applied. Next, the server executes machine learning algorithms using libraries such as Scikit-learn and TENSORFLOW®. This generates product recommendations tailored to the customer. The generated recommendations are then adjusted according to the characteristics of each individual user.

[0080] Terminal operation

[0081] The terminal receives suggestions sent from the server. These suggestions are visually presented to the user via a user interface. This allows the user to easily understand the suggestions and utilize them in sales activities. The terminal also provides an interface for collecting activity results and sending feedback to the server. This information is used to improve the accuracy of future suggestions.

[0082] User actions

[0083] Users, or participants, conduct business negotiations with customers based on the provided product proposals. They send feedback on the negotiation results and customer reactions to the system via their terminals. This feedback information is stored on the server and used when generating future proposals.

[0084] Specific example

[0085] For example, consider sales activities targeting customer B in the food industry. The server analyzes market trends in the food industry and customer B's purchase history. This analysis reveals that customer B prefers health-conscious products. As a result, a suggestion emphasizing organic products is displayed on the terminal. The user conducts a business negotiation with customer B based on this suggestion, records the response on the terminal, and sends it as feedback. This information is used to improve future proposals.

[0086] Example of a prompt

[0087] "Analyze customer B's market trends and past purchase history to generate appropriate product recommendations."

[0088] In this way, this system aims to streamline sales activities and improve the accuracy of the proposals provided.

[0089] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0090] Step 1:

[0091] The server retrieves sales-related and historical information from storage devices. Specifically, it extracts the necessary information from the database using SQL queries. The input is a database query, and the output is a raw dataset.

[0092] Step 2:

[0093] The server preprocesses and cleans the acquired data. It uses the Python Pandas library to impute missing values ​​and standardize the format. The input is a raw dataset, and the output is a clean, analysis-ready dataset.

[0094] Step 3:

[0095] The server runs machine learning algorithms using cleaned data. This process involves training predictive models using Scikit-learn and TensorFlow to generate customer recommendations. The input is a clean dataset, and the output is the generated product recommendations.

[0096] Step 4:

[0097] The server adjusts the generated product proposals based on the characteristics of individual agents, ensuring that sales representatives can use the proposals most effectively. The input is the generated product proposal, and the output is the customized proposal.

[0098] Step 5:

[0099] The server sends a customized proposal to the terminal. The terminal receives this proposal and presents it to the agent through the user interface. The agent uses this proposal during sales activities. The input is the customized proposal, and the output is a visual presentation to the agent.

[0100] Step 6:

[0101] Users conduct sales activities based on proposals displayed on their devices. They feed back the results of negotiations and customer reactions to the system via their devices. The input is the results of sales activities, and the output is feedback information.

[0102] Step 7:

[0103] The server stores the collected feedback information in a database and uses it to generate suggestions for the next generation. This improves the accuracy of the algorithm. The input is the feedback information, and the output is the updated database.

[0104] (Application Example 1)

[0105] 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."

[0106] Modern retail strategies require personalized product recommendations for each customer. However, doing this manually is time-consuming and labor-intensive, placing a heavy burden on sales staff. Furthermore, there is a lack of means to provide real-time recommendations that instantly reflect customer purchase history and individual needs. Therefore, a system is needed to efficiently suggest suitable products to customers and improve the customer experience.

[0107] 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.

[0108] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales data, and past transaction history; means for executing a machine learning process to generate a product proposal method suitable for the customer based on the acquired customer information; and means for personalizing the generated product proposal method based on the characteristics of the sales representative. This makes it possible to visually display the personalized product proposal in real time through a smart device and to communicate effectively with the customer.

[0109] "Customer information" refers to data about customers, such as their attributes and purchase history, that is referenced when providing products and services.

[0110] "Sales data" refers to information related to sales activities, including digital data such as the activity history of sales representatives, details of business negotiations, and results.

[0111] "Past transaction history" refers to records of purchases and contracts made by customers in the past, and is data used to analyze purchasing trends and preferences.

[0112] A "storage device" is a piece of hardware or digital media used to store information for long periods of time, and is a device that enables the storage and retrieval of data.

[0113] A "machine learning process" is a learning process that uses algorithms to identify patterns and rules based on data and to predict or generate new information.

[0114] "Personalization" is the process of adjusting content to suit individual needs and characteristics based on specific information.

[0115] A "user interface" is a screen or means of operation designed to facilitate the exchange of information between a system and a user.

[0116] A "smart device" is an electronic device that has internet connectivity and data processing capabilities, and is equipped with functions to assist user operation.

[0117] This invention is a system that automatically proposes the most suitable products to customers based on customer information, sales data, and past transaction history. The system mainly consists of three elements: a server, a terminal, and a user.

[0118] The server first retrieves customer information, sales data, and historical transaction history from storage devices. This information undergoes a data cleaning process to integrate it into a consistent and analyzable format. Next, the server runs a machine learning process to generate the most suitable product recommendations for customers in real time. This uses machine learning frameworks such as TensorFlow. The machine learning process analyzes and optimizes different sales styles based on the collected data. After the recommendations are generated, the server personalizes the recommendations based on the characteristics of the sales representative. This entire data flow is carried out using cloud services such as AWS® Lambda and Google® Cloud Functions.

[0119] The terminal receives personalized product suggestions sent from the server and presents them to sales representatives through a user interface. This information is conveyed to sales representatives visually using smart devices, such as smart glasses. This visual presentation allows sales representatives to communicate more smoothly with customers. The terminal also provides an interface for easily recording sales activity results as feedback and sending it to the server.

[0120] Users wear a smart device attached to their terminal to view visually personalized product suggestions. This enables personalized product recommendations to be made to customers, contributing to an improved customer experience. Based on these suggestions, users conduct actual sales activities and send the results as feedback to the system via the terminal. This feedback data is recorded and analyzed again on the server, improving the accuracy of the suggestions.

[0121] As a concrete example, when a regular customer returns to the store, the smart glasses display will show information such as, "A new model of the product you purchased last time has arrived. Please recommend it to the customer." In this process, the sales representative uses a generative AI model to generate prompt messages such as, "When a specific customer visits the store, generate a prompt that suggests a new product based on their past purchase history."

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The server retrieves customer information, sales data, and historical transaction history from storage devices. This input data serves as the foundation for analyzing sales performance and customer purchasing trends. The server prepares this data for subsequent processing by converting and cleaning it into a consistent format.

[0125] Step 2:

[0126] The server executes machine learning algorithms based on the prepared data. A generative AI model is used to generate optimal product recommendations tailored to customer purchasing trends and needs. The output includes a list of optimal products and recommendations for a specific customer.

[0127] Step 3:

[0128] The server personalizes the generated product proposals based on the sales representative's characteristics and past performance. It uses data on the representative's performance and areas of expertise as input. As a result, the output proposals are more effective and tailored to the sales representative.

[0129] Step 4:

[0130] The terminal transmits personalized suggestions received from the server to a smart device. The input data is suggestion information from the server, and the output is a product suggestion visually displayed through a user interface. Information is provided to sales representatives in real time using devices such as smart glasses.

[0131] Step 5:

[0132] The sales representative, acting as the user, communicates with customers based on proposals provided through the terminal. By recording the content of the conversation with the customer and the results of the sales negotiation, feedback data for the next step is generated. This data is sent to the system for use in the next analysis.

[0133] Step 6:

[0134] The server receives feedback data sent from the terminals and stores it in its memory. It receives feedback data as input and uses it as new analytical material for future sales improvements. This continuously improves the overall accuracy of the system's proposals.

[0135] 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.

[0136] This invention is a system that proposes the most suitable products to customers during sales activities, and features an emotion engine. This system mainly consists of three elements: a server, a terminal, and a user.

[0137] Server operation

[0138] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. It also aggregates emotional data provided by the emotion engine. The server uses machine learning algorithms to analyze this information and generate product recommendations tailored to each customer. This analysis takes into account the customer's emotional state and reactions, enabling more personalized recommendations. The generated recommendations are then customized based on the sales representative's characteristics.

[0139] How the emotion engine works

[0140] The emotion engine detects the user's emotional state in real time during sales activities. This is done through analysis of the user's voice, facial expressions, and words. The emotional data is sent to a server and used to adjust product proposal methods and sales approaches.

[0141] Terminal operation

[0142] The terminal receives customized suggestions sent from the server and presents them to the sales representative. The suggestions may be updated in real time based on the user's emotional state. The terminal also provides an interface for recording emotional data input via an emotion engine and feedback on sales activities.

[0143] User actions

[0144] The user, i.e., the sales representative, reviews the proposed product information via a terminal. During sales activities, the proposal is adjusted in real time based on the customer's emotional state, supporting optimal communication. The user records the results of the sales activities and inputs them into the system as feedback.

[0145] Specific example

[0146] For example, during a business negotiation with customer B, the emotion engine captures the moment the customer shows interest. Based on this information, the proposal displayed on the device is immediately changed to specific guidance such as "We will explain this point in more detail." The sales representative can then use this to provide a detailed explanation tailored to the customer's interests, thereby improving the closing rate of the deal.

[0147] Thus, this invention is a system that enhances the effectiveness of sales activities and realizes a more sophisticated proposal method by combining an emotion engine.

[0148] The following describes the processing flow.

[0149] Step 1:

[0150] The server accesses the database to retrieve customer information, sales representative information, and past transaction history. In addition, it prepares sentiment data provided in real time from the sentiment engine.

[0151] Step 2:

[0152] The server applies machine learning algorithms to analyze collected customer information and sales data. Based on the analysis results, it generates the optimal product recommendation method for each customer. At this stage, past transaction trends and sentiment data are also taken into consideration.

[0153] Step 3:

[0154] The server customizes the generated product proposal methods according to the characteristics of each sales representative. This enables efficient proposals that leverage the unique strengths of each representative.

[0155] Step 4:

[0156] The emotion engine analyzes the user's emotions in real time through the device and sends the data to the server. This allows the user's emotional state during sales activities to be monitored and reflected in the proposals.

[0157] Step 5:

[0158] The device displays customized suggestions received from the server to the user. These suggestions may be updated in real time based on feedback from the sentiment engine.

[0159] Step 6:

[0160] Users conduct sales activities with customers based on suggestions displayed on their devices. During sales activities, the device reflects emotional data recorded by the user and adjusts the suggestions as needed.

[0161] Step 7:

[0162] The terminal sends user feedback to the server after sales activities are completed. This feedback includes sales results, customer reactions, and the user's subjective impressions.

[0163] Step 8:

[0164] The server stores feedback in a database and uses it to improve future analysis and proposal methods. Simultaneously, integrating emotional data will be used to inform future product proposals.

[0165] This series of processes enables the system to quickly and effectively propose products that meet customer needs.

[0166] (Example 2)

[0167] 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 will be referred to as the "terminal."

[0168] In sales activities, accurately understanding customer emotions and interests and making personalized product proposals based on that understanding is a major challenge for sales representatives. With conventional technology, it was difficult to generate proposals that reflected the customer's emotional state in real time, making it difficult to maximize sales conversion rates and effectiveness. Furthermore, there were insufficient systems to effectively feed back the results of sales activities and continuously improve the accuracy of proposal methods.

[0169] 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.

[0170] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales representative information, and past transaction history; means for executing a calculation method for generating a product proposal method suitable for the customer based on the acquired customer information; and means for providing a user screen for presenting the personalized product proposal method to the sales representative. As a result, the sales representative can make optimal proposals that reflect the customer's emotions in real time, thereby improving the accuracy of sales activities and the closing rate.

[0171] A "storage device" is a device or system used to store data and information for a long period of time.

[0172] A "calculation method" is a method for processing and calculating data using acquired data and deriving a result.

[0173] "Personalization" refers to specially adjusting the content according to the customer and their circumstances, resulting in a form optimized for each individual.

[0174] A "user interface" refers to an interface function that allows users to visually view and manipulate information.

[0175] "Emotional information" refers to data that indicates a user's emotions and reactions, and is collected through functions such as an emotion engine.

[0176] This invention is configured as a system for streamlining sales activities and proposing the most suitable products to customers. It includes a server, terminals, and an emotion engine, each playing a specific role.

[0177] Server operation

[0178] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. SQL database queries are used for this purpose. Sentimental information provided by the sentiment engine is also aggregated on the server. The aggregated data is analyzed using machine learning algorithms. This analysis allows a generative AI model to generate optimal product recommendations for each customer. These product recommendations are further personalized based on the characteristics of each sales representative.

[0179] How the emotion engine works

[0180] The emotion engine analyzes the user's voice, facial expressions, and words in real time during sales activities. This analysis utilizes speech recognition software and facial expression analysis technology, and the resulting emotional information is transmitted to a server. This emotional information is then used to adjust product proposal methods and sales approaches.

[0181] Terminal operation

[0182] The terminal presents personalized suggestions sent from the server to the sales representative. The suggestions are displayed via a dedicated user interface. The user interface operates on devices such as tablets and smartphones, and also records feedback and emotional information from an emotion engine.

[0183] User actions

[0184] Users, i.e., sales representatives, review the proposed products and services through their terminals. During sales activities, the proposals are adjusted in real time based on customer sentiment, supporting optimal communication. After the meeting, the sales results are entered into the system as feedback, enabling continuous learning.

[0185] As a concrete example, if the emotion engine detects that customer B has shown interest during a business negotiation, the suggestion on the device will change in real time to "Please explain this point in more detail." This mechanism allows sales representatives to provide explanations tailored to the customer's interests, thereby improving the closing rate of deals.

[0186] Example prompt: "Identify the factors that interest Customer B and generate specific guidance to adjust the product proposal."

[0187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0188] Step 1:

[0189] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. The input consists of various types of information stored in the database, and the output is an integrated set of information. This process uses SQL queries to extract information and integrate it in the format required by the system.

[0190] Step 2:

[0191] The emotion engine analyzes the user's voice, facial expressions, and words in real time to acquire emotional information. Inputs include audio and video data from business negotiations, and output is the analyzed emotional information. This process involves using speech recognition software and facial expression analysis algorithms to determine the emotional state.

[0192] Step 3:

[0193] The server combines acquired customer information and sentiment information, and uses a generative AI model to generate the most suitable product recommendation method for each customer. The input includes an integrated information set and sentiment information, and the output is a personalized product recommendation method. This process involves data analysis and prompt message generation using machine learning algorithms.

[0194] Step 4:

[0195] The server customizes the generated product proposal method based on the sales representative's characteristics and sends it to the terminal. The input consists of the generated product proposal method and the sales representative's characteristics information, and the output is a proposal method tailored to the sales representative. Here, the proposal content is individualized by taking into account each representative's past performance and characteristics.

[0196] Step 5:

[0197] The terminal presents personalized product proposal methods received from the server to the sales representative. The input is the personalized product proposal method, and the output is the displayed proposal content. The proposal method is presented intuitively to the sales representative via a dedicated user interface on the terminal.

[0198] Step 6:

[0199] During sales activities, users review product proposal methods presented via a terminal and adjust their approach in real time based on customer sentiment information. Inputs include sentiment information and presented proposals, while output is optimized proposals and communication tailored to the customer. After the sales meeting concludes, the system feeds back the activity results.

[0200] (Application Example 2)

[0201] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0202] In traditional customer service, it is difficult to grasp customer emotions in real time, and product suggestions may not align with the customer's interests or emotional state. This can lead to inaccurate suggestions and decreased customer satisfaction. Furthermore, customer service relies heavily on the experience of the salesperson, making it difficult for new employees to maintain the same level of quality. There is a need to address these challenges and enable efficient and personalized customer service that transcends individual sales capabilities.

[0203] 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.

[0204] In this invention, the server includes means for acquiring information from data storage that stores customer information, customer service staff information, and past transaction history; means for executing a data analysis algorithm for generating product suggestion information suitable for the target person based on the acquired customer information; and means for using an emotion analysis engine to detect the customer's emotional state in real time and dynamically adjust the product suggestion information. This makes it possible to make optimal product suggestions tailored to each individual customer and improve the quality of customer service.

[0205] "Customer information" refers to data about the recipients of products or services, including personal attributes, purchase history, and preferences.

[0206] "Customer service information" refers to data about individuals who are responsible for providing products or services, including details such as experience, areas of expertise, and work history.

[0207] "Past transaction history" refers to data on all transactions that have taken place with the customer in the past, including records of purchased goods, services, payment methods, dates, etc.

[0208] "Data storage" refers to any data storage device that can securely store large amounts of digital information and retrieve it quickly when needed.

[0209] A "data analysis algorithm" is a set of procedures and calculations used to derive useful information or results from a specific dataset.

[0210] "Product suggestion information" refers to suggestions created to provide the most suitable products and services to individual customers, and includes personalized details.

[0211] An "emotion analysis engine" is software designed to detect and analyze a customer's emotions and psychological state, and it has the function of evaluating emotions from inputs such as facial expressions and voice.

[0212] A "user interface" is a screen or operating device used by a system and a user to exchange information, and is designed with an emphasis on ease of use and visibility.

[0213] The server utilizes multiple hardware and software components to support customer service activities. First, customer information, customer service representative information, and past transaction history are stored in data storage. To quickly retrieve this data, the server is equipped with a high-performance database management system. For example, it uses a non-relational database such as MongoDB to enable fast data searching and retrieval.

[0214] The data analysis algorithm, developed using Python and TensorFlow, analyzes customers' past behavioral data and emotional states to generate personalized product recommendations. This generated product recommendation information is sent via the server to the customer service staff's terminals and displayed in real time.

[0215] The emotion analysis engine uses the device's camera and microphone to capture the customer's facial expressions and voice, and analyzes their emotions by combining OpenCV and various natural language processing (NLP) technologies. The acquired emotion data is sent to a server and used to adjust product recommendations.

[0216] Users, i.e., customer service representatives, view suggested product information using tablets or smartphones. The user interface is developed using React Native, enabling intuitive and user-friendly operation. Suggestions are dynamically updated in response to customer reactions, allowing customer service representatives to communicate more effectively.

[0217] For example, when a customer picks up an item they're interested in at a fashion store, the emotion analysis engine detects the customer's facial expression indicating interest. Based on this, the server generates a product suggestion such as, "This item is on-trend this season, and this color is particularly popular," which is then displayed on the sales associate's terminal. An example of a prompt to be fed into the generating AI model is, "Please provide detailed information and reasons for recommending the item the customer showed interest in." This makes it possible to maximize sales opportunities.

[0218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0219] Step 1:

[0220] The server retrieves customer information, customer service representative information, and past transaction history from data storage. This information is treated as a dataset showing customer purchase history and preferences. The input consists of various data stored in data storage, and the output is cleansed data for use in analysis.

[0221] Step 2:

[0222] The server executes data analysis algorithms based on the acquired data. Specifically, it runs a model using Python and TensorFlow to generate optimal product recommendations for customers. Here, customer behavior patterns and sales history are used as input data, and a list of appropriate product and service recommendations is obtained as output.

[0223] Step 3:

[0224] The terminal receives generated product suggestion information sent from the server. These suggestions are displayed visually on the customer service representative's terminal. The input is the suggestion information sent from the server, and the output is what is displayed on the user interface on the terminal's display.

[0225] Step 4:

[0226] The device uses its built-in camera and microphone to detect the customer's emotional state through an emotion analysis engine. It analyzes emotions from facial expression and voice data using OpenCV and natural language processing techniques. Input is real-time collected audio and video data, and output is the result of classifying the customer's emotions.

[0227] Step 5:

[0228] The server receives emotional data obtained from the emotion analysis engine and uses it to further optimize product recommendation information. The input is the result of the emotion analysis, and the output is product recommendation information updated to reflect the customer's emotional state.

[0229] Step 6:

[0230] Based on updated product suggestion information, users provide effective customer service through their devices. The input here is optimized suggestion content displayed on the device, and the output is a conversation that contributes to further customer interest and engagement.

[0231] Step 7:

[0232] The server stores the results of customer service activities as feedback in data storage. This data will then be used for future data analysis and product recommendations. The input is feedback data recorded at the end of the customer service activity, and the output is new data added to the training dataset.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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".

[0249] This invention relates to a system for proposing the most suitable products to customers during sales activities, and its embodiments are described in detail below. This system mainly consists of three elements: a server, a terminal, and a user.

[0250] Server operation

[0251] The server first collects customer information, sales representative information, and past transaction history from the database. The server cleans this data and converts it into a consistent format, making it suitable for subsequent analysis. Next, the server runs machine learning algorithms to analyze the collected information and generate successful sales techniques and customer-tailored product proposals. These algorithms learn from past sales performance and optimize product proposals based on different sales styles. After the proposals are generated, the server customizes them to suit the characteristics of each sales representative and optimizes them for effective results.

[0252] Terminal operation

[0253] The terminal receives customized proposals sent from the server and presents them visually to the sales representative. This presentation is designed to allow sales representatives to easily understand the proposals and use them to communicate with customers. The terminal also provides an interface for receiving user feedback. This interface is simple and allows for quick recording of results from sales activities and customer reactions.

[0254] User actions

[0255] The user, i.e., the sales representative, reviews the proposed product details via their terminal. Based on the proposal method, the user conducts sales activities with the customer and feeds the results back into the system. The feedback recorded by the user is sent to the server as data to improve the accuracy of future proposals. This feedback information is collected again by the server and stored in a database, which is then used for future product proposals.

[0256] Specific example

[0257] For example, when making a sales pitch to customer A in the construction industry, the server analyzes industry trends and customer A's past purchasing history. If the analysis determines that customer A tends to prioritize cost, a proposal emphasizing cost performance will be displayed on the terminal. The user then conducts negotiations with customer A based on this proposal and feeds the results back into the system. This feedback information is used to improve future proposals for similar industries and customers.

[0258] As a result, this invention functions as a system that streamlines and improves the accuracy of sales activities and supports the improvement of sales representatives' performance.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] The server connects to the database and retrieves necessary customer information, sales representative information, and past transaction history. This data includes the customer company's industry, size, location, purchase history, and the sales performance and characteristics of the sales representative.

[0262] Step 2:

[0263] The server performs data cleaning to organize the acquired data. It imputes missing values, standardizes data formats, and builds a consistent dataset. This ensures the data is ready for analysis.

[0264] Step 3:

[0265] The server analyzes the data, which has been prepared using machine learning algorithms. In this process, the learning model is trained to extract past successful sales methods and proposal methods that are suitable for customer characteristics.

[0266] Step 4:

[0267] The server uses a trained model to generate product recommendations tailored to the customer. These recommendations include the most appropriate products and approaches from the product lineup.

[0268] Step 5:

[0269] The server customizes the product proposal methods obtained based on the characteristics and skills of the sales representative. This ensures that proposals are prepared that allow the representative to approach customers in a way that maximizes their strengths.

[0270] Step 6:

[0271] The server sends customized proposals to the terminal. The terminal displays the proposals in a visually easy-to-understand format, making them user-friendly for sales representatives.

[0272] Step 7:

[0273] Users conduct sales activities based on the proposals displayed on their devices. They record customer reactions and results obtained during sales activities.

[0274] Step 8:

[0275] The terminal sends feedback on sales activities to the server. The feedback information entered by the user is stored in a database so that it can be used for future proposals.

[0276] This allows the system to continuously improve the accuracy of its proposals and support sales activities.

[0277] (Example 1)

[0278] 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."

[0279] In modern business activities, it is required to efficiently and effectively respond to the diverse needs of customers. However, with conventional methods, it takes a great deal of effort for sales staff to carefully analyze the needs of each individual customer and create optimal proposals, leaving inefficiency for the company. Furthermore, there is a lack of a mechanism to effectively utilize the feedback obtained from business activities and reflect it in the next business operation. As a result, there is a problem that it is difficult to improve business performance.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following respective means.

[0281] In this invention, the server includes means for acquiring sales-related information and history information from a storage device that stores information, means for executing an algorithm for generating a product proposal using the preprocessed information, and means for adjusting the generated product proposal based on the characteristics of individual actors. This enables the efficiency and accuracy of proposals in business activities to be improved.

[0282] The "storage device that stores information" is a device that stores data and can read out the data as needed.

[0283] The "sales-related information" refers to data such as customer information, transaction history, and product information related to the sales of products and services.

[0284] The "history information" is detailed information regarding past transactions and is a record of how customers have used products and services.

[0285] The "preprocessing" is an initial process for improving the quality of data and arranging it in a form suitable for analysis, and includes data cleaning and formatting.

[0286] The "algorithm" refers to a series of calculation procedures and is a method for analyzing data and generating proposals to solve specific problems.

[0287] "Activist" refers to someone who sells goods or provides services, and usually means a sales representative.

[0288] "Feedback" refers to information recorded from sales activities and customer reactions, used to improve future proposals.

[0289] This invention provides a system that enables efficient product proposals and their customization in sales activities. This system primarily consists of a server, terminals, and users, with each component working in coordination.

[0290] Server operation

[0291] The server collects data, including sales-related and historical information, from storage devices. Data collection can be done using SQL queries, and the information is exported, for example, in CSV format. After data collection, the server uses the Python Pandas library to preprocess and clean the data. Techniques such as imputing incomplete data with the mean are applied. Next, the server executes machine learning algorithms using libraries such as Scikit-learn and TensorFlow. This generates product recommendations tailored to the customer. The generated recommendations are then adjusted according to the characteristics of each individual user.

[0292] Terminal operation

[0293] The terminal receives suggestions sent from the server. These suggestions are visually presented to the user via a user interface. This allows the user to easily understand the suggestions and utilize them in sales activities. The terminal also provides an interface for collecting activity results and sending feedback to the server. This information is used to improve the accuracy of future suggestions.

[0294] User actions

[0295] Users, or participants, conduct business negotiations with customers based on the provided product proposals. They send feedback on the negotiation results and customer reactions to the system via their terminals. This feedback information is stored on the server and used when generating future proposals.

[0296] Specific example

[0297] For example, consider sales activities targeting customer B in the food industry. The server analyzes market trends in the food industry and customer B's purchase history. This analysis reveals that customer B prefers health-conscious products. As a result, a suggestion emphasizing organic products is displayed on the terminal. The user conducts a business negotiation with customer B based on this suggestion, records the response on the terminal, and sends it as feedback. This information is used to improve future proposals.

[0298] Example of a prompt

[0299] "Analyze customer B's market trends and past purchase history to generate appropriate product recommendations."

[0300] In this way, this system aims to streamline sales activities and improve the accuracy of the proposals provided.

[0301] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0302] Step 1:

[0303] The server retrieves sales-related and historical information from storage devices. Specifically, it extracts the necessary information from the database using SQL queries. The input is a database query, and the output is a raw dataset.

[0304] Step 2:

[0305] The server preprocesses and cleans the acquired data. Using the Pandas library in Python, it fills in missing values and unifies formats. The input is the raw dataset, and the output is a clean and analysis-suitable dataset.

[0306] Step 3:

[0307] The server executes a machine learning algorithm using the cleaned data. During this process, it uses Scikit-learn or TensorFlow to train a prediction model and generate proposals for customers. The input is the clean dataset, and the output is the generated product proposals.

[0308] Step 4:

[0309] The server adjusts the generated product proposals based on the characteristics of individual actors. This enables sales representatives to make the most effective use of the proposals. The input is the generated product proposals, and the output is the customized proposals.

[0310] Step 5:

[0311] The server sends the customized proposals to the terminal. The terminal receives this proposal and presents it to the actor with a user interface. The actor uses this proposal during sales activities. The input is the customized proposal, and the output is a visual presentation to the actor.

[0312] Step 6:

[0313] The user conducts sales activities based on the proposal on the terminal. The results of business negotiations and customer reactions are fed back to the system through the terminal. The input is the result of the sales activity, and the output is feedback information.

[0314] Step 7:

[0315] The server stores the collected feedback information in a database and uses it to generate suggestions for the next generation. This improves the accuracy of the algorithm. The input is the feedback information, and the output is the updated database.

[0316] (Application Example 1)

[0317] 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."

[0318] Modern retail strategies require personalized product recommendations for each customer. However, doing this manually is time-consuming and labor-intensive, placing a heavy burden on sales staff. Furthermore, there is a lack of means to provide real-time recommendations that instantly reflect customer purchase history and individual needs. Therefore, a system is needed to efficiently suggest suitable products to customers and improve the customer experience.

[0319] 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.

[0320] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales data, and past transaction history; means for executing a machine learning process to generate a product proposal method suitable for the customer based on the acquired customer information; and means for personalizing the generated product proposal method based on the characteristics of the sales representative. This makes it possible to visually display the personalized product proposal in real time through a smart device and to communicate effectively with the customer.

[0321] "Customer information" refers to data about customers, such as their attributes and purchase history, that is referenced when providing products and services.

[0322] "Sales data" refers to information related to sales activities, including digital data such as the activity history of sales representatives, details of business negotiations, and results.

[0323] "Past transaction history" refers to records of purchases and contracts made by customers in the past, and is data used to analyze purchasing trends and preferences.

[0324] A "storage device" is a piece of hardware or digital media used to store information for long periods of time, and is a device that enables the storage and retrieval of data.

[0325] A "machine learning process" is a learning process that uses algorithms to identify patterns and rules based on data and to predict or generate new information.

[0326] "Personalization" is the process of adjusting content to suit individual needs and characteristics based on specific information.

[0327] A "user interface" is a screen or means of operation designed to facilitate the exchange of information between a system and a user.

[0328] A "smart device" is an electronic device that has internet connectivity and data processing capabilities, and is equipped with functions to assist user operation.

[0329] This invention is a system that automatically proposes the most suitable products to customers based on customer information, sales data, and past transaction history. The system mainly consists of three elements: a server, a terminal, and a user.

[0330] The server first retrieves customer information, sales data, and historical transaction history from storage devices. This information undergoes a data cleaning process to integrate it into a consistent and analyzable format. Next, the server runs a machine learning process to generate the most suitable product recommendations for customers in real time. This uses machine learning frameworks such as TensorFlow. The machine learning process analyzes and optimizes different sales styles based on the collected data. After the recommendations are generated, the server personalizes the recommendations based on the characteristics of the sales representatives. This entire data flow is carried out using cloud services such as AWS Lambda and Google Cloud Functions.

[0331] The terminal receives personalized product suggestions sent from the server and presents them to sales representatives through a user interface. This information is conveyed to sales representatives visually using smart devices, such as smart glasses. This visual presentation allows sales representatives to communicate more smoothly with customers. The terminal also provides an interface for easily recording sales activity results as feedback and sending it to the server.

[0332] Users wear a smart device attached to their terminal to view visually personalized product suggestions. This enables personalized product recommendations to be made to customers, contributing to an improved customer experience. Based on these suggestions, users conduct actual sales activities and send the results as feedback to the system via the terminal. This feedback data is recorded and analyzed again on the server, improving the accuracy of the suggestions.

[0333] As a concrete example, when a regular customer returns to the store, the smart glasses display will show information such as, "A new model of the product you purchased last time has arrived. Please recommend it to the customer." In this process, the sales representative uses a generative AI model to generate prompt messages such as, "When a specific customer visits the store, generate a prompt that suggests a new product based on their past purchase history."

[0334] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0335] Step 1:

[0336] The server retrieves customer information, sales data, and historical transaction history from storage devices. This input data serves as the foundation for analyzing sales performance and customer purchasing trends. The server prepares this data for subsequent processing by converting and cleaning it into a consistent format.

[0337] Step 2:

[0338] The server executes machine learning algorithms based on the prepared data. A generative AI model is used to generate optimal product recommendations tailored to customer purchasing trends and needs. The output includes a list of optimal products and recommendations for a specific customer.

[0339] Step 3:

[0340] The server personalizes the generated product proposals based on the sales representative's characteristics and past performance. It uses data on the representative's performance and areas of expertise as input. As a result, the output proposals are more effective and tailored to the sales representative.

[0341] Step 4:

[0342] The terminal transmits personalized suggestions received from the server to a smart device. The input data is suggestion information from the server, and the output is a product suggestion visually displayed through a user interface. Information is provided to sales representatives in real time using devices such as smart glasses.

[0343] Step 5:

[0344] The sales representative, acting as the user, communicates with customers based on proposals provided through the terminal. By recording the content of the conversation with the customer and the results of the sales negotiation, feedback data for the next step is generated. This data is sent to the system for use in the next analysis.

[0345] Step 6:

[0346] The server receives feedback data sent from the terminals and stores it in its memory. It receives feedback data as input and uses it as new analytical material for future sales improvements. This continuously improves the overall accuracy of the system's proposals.

[0347] 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.

[0348] This invention is a system that proposes the most suitable products to customers during sales activities, and features an emotion engine. This system mainly consists of three elements: a server, a terminal, and a user.

[0349] Server operation

[0350] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. It also aggregates emotional data provided by the emotion engine. The server uses machine learning algorithms to analyze this information and generate product recommendations tailored to each customer. This analysis takes into account the customer's emotional state and reactions, enabling more personalized recommendations. The generated recommendations are then customized based on the sales representative's characteristics.

[0351] How the emotion engine works

[0352] The emotion engine detects the user's emotional state in real time during sales activities. This is done through analysis of the user's voice, facial expressions, and words. The emotional data is sent to a server and used to adjust product proposal methods and sales approaches.

[0353] Terminal operation

[0354] The terminal receives customized suggestions sent from the server and presents them to the sales representative. The suggestions may be updated in real time based on the user's emotional state. The terminal also provides an interface for recording emotional data input via an emotion engine and feedback on sales activities.

[0355] User actions

[0356] The user, i.e., the sales representative, reviews the proposed product information via a terminal. During sales activities, the proposal is adjusted in real time based on the customer's emotional state, supporting optimal communication. The user records the results of the sales activities and inputs them into the system as feedback.

[0357] Specific example

[0358] For example, during a business negotiation with customer B, the emotion engine captures the moment the customer shows interest. Based on this information, the proposal displayed on the device is immediately changed to specific guidance such as "We will explain this point in more detail." The sales representative can then use this to provide a detailed explanation tailored to the customer's interests, thereby improving the closing rate of the deal.

[0359] Thus, this invention is a system that enhances the effectiveness of sales activities and realizes a more sophisticated proposal method by combining an emotion engine.

[0360] The following describes the processing flow.

[0361] Step 1:

[0362] The server accesses the database to retrieve customer information, sales representative information, and past transaction history. In addition, it prepares sentiment data provided in real time from the sentiment engine.

[0363] Step 2:

[0364] The server applies machine learning algorithms to analyze collected customer information and sales data. Based on the analysis results, it generates the optimal product recommendation method for each customer. At this stage, past transaction trends and sentiment data are also taken into consideration.

[0365] Step 3:

[0366] The server customizes the generated product proposal methods according to the characteristics of each sales representative. This enables efficient proposals that leverage the unique strengths of each representative.

[0367] Step 4:

[0368] The emotion engine analyzes the user's emotions in real time through the device and sends the data to the server. This allows the user's emotional state during sales activities to be monitored and reflected in the proposals.

[0369] Step 5:

[0370] The device displays customized suggestions received from the server to the user. These suggestions may be updated in real time based on feedback from the sentiment engine.

[0371] Step 6:

[0372] Users conduct sales activities with customers based on suggestions displayed on their devices. During sales activities, the device reflects emotional data recorded by the user and adjusts the suggestions as needed.

[0373] Step 7:

[0374] The terminal sends user feedback to the server after sales activities are completed. This feedback includes sales results, customer reactions, and the user's subjective impressions.

[0375] Step 8:

[0376] The server stores feedback in a database and uses it to improve future analysis and proposal methods. Simultaneously, integrating emotional data will be used to inform future product proposals.

[0377] This series of processes enables the system to quickly and effectively propose products that meet customer needs.

[0378] (Example 2)

[0379] 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".

[0380] In sales activities, accurately understanding customer emotions and interests and making personalized product proposals based on that understanding is a major challenge for sales representatives. With conventional technology, it was difficult to generate proposals that reflected the customer's emotional state in real time, making it difficult to maximize sales conversion rates and effectiveness. Furthermore, there were insufficient systems to effectively feed back the results of sales activities and continuously improve the accuracy of proposal methods.

[0381] 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.

[0382] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales representative information, and past transaction history; means for executing a calculation method for generating a product proposal method suitable for the customer based on the acquired customer information; and means for providing a user screen for presenting the personalized product proposal method to the sales representative. As a result, the sales representative can make optimal proposals that reflect the customer's emotions in real time, thereby improving the accuracy of sales activities and the closing rate.

[0383] A "storage device" is a device or system used to store data and information for a long period of time.

[0384] A "calculation method" is a method for processing and calculating data using acquired data and deriving a result.

[0385] "Personalization" refers to specially adjusting the content according to the customer and their circumstances, resulting in a form optimized for each individual.

[0386] A "user interface" refers to an interface function that allows users to visually view and manipulate information.

[0387] "Emotional information" refers to data that indicates a user's emotions and reactions, and is collected through functions such as an emotion engine.

[0388] This invention is configured as a system for streamlining sales activities and proposing the most suitable products to customers. It includes a server, terminals, and an emotion engine, each playing a specific role.

[0389] Server operation

[0390] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. SQL database queries are used for this purpose. Sentimental information provided by the sentiment engine is also aggregated on the server. The aggregated data is analyzed using machine learning algorithms. This analysis allows a generative AI model to generate optimal product recommendations for each customer. These product recommendations are further personalized based on the characteristics of each sales representative.

[0391] How the emotion engine works

[0392] The emotion engine analyzes the user's voice, facial expressions, and words in real time during sales activities. This analysis utilizes speech recognition software and facial expression analysis technology, and the resulting emotional information is transmitted to a server. This emotional information is then used to adjust product proposal methods and sales approaches.

[0393] Terminal operation

[0394] The terminal presents personalized suggestions sent from the server to the sales representative. The suggestions are displayed via a dedicated user interface. The user interface operates on devices such as tablets and smartphones, and also records feedback and emotional information from an emotion engine.

[0395] User actions

[0396] Users, i.e., sales representatives, review the proposed products and services through their terminals. During sales activities, the proposals are adjusted in real time based on customer sentiment, supporting optimal communication. After the meeting, the sales results are entered into the system as feedback, enabling continuous learning.

[0397] As a concrete example, if the emotion engine detects that customer B has shown interest during a business negotiation, the suggestion on the device will change in real time to "Please explain this point in more detail." This mechanism allows sales representatives to provide explanations tailored to the customer's interests, thereby improving the closing rate of deals.

[0398] Example prompt: "Identify the factors that interest Customer B and generate specific guidance to adjust the product proposal."

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. The input consists of various types of information stored in the database, and the output is an integrated set of information. This process uses SQL queries to extract information and integrate it in the format required by the system.

[0402] Step 2:

[0403] The emotion engine analyzes the user's voice, facial expressions, and words in real time to acquire emotional information. Inputs include audio and video data from business negotiations, and output is the analyzed emotional information. This process involves using speech recognition software and facial expression analysis algorithms to determine the emotional state.

[0404] Step 3:

[0405] The server combines acquired customer information and sentiment information, and uses a generative AI model to generate the most suitable product recommendation method for each customer. The input includes an integrated information set and sentiment information, and the output is a personalized product recommendation method. This process involves data analysis and prompt message generation using machine learning algorithms.

[0406] Step 4:

[0407] The server customizes the generated product proposal method based on the sales representative's characteristics and sends it to the terminal. The input consists of the generated product proposal method and the sales representative's characteristics information, and the output is a proposal method tailored to the sales representative. Here, the proposal content is individualized by taking into account each representative's past performance and characteristics.

[0408] Step 5:

[0409] The terminal presents personalized product proposal methods received from the server to the sales representative. The input is the personalized product proposal method, and the output is the displayed proposal content. The proposal method is presented intuitively to the sales representative via a dedicated user interface on the terminal.

[0410] Step 6:

[0411] During sales activities, users review product proposal methods presented via a terminal and adjust their approach in real time based on customer sentiment information. Inputs include sentiment information and presented proposals, while output is optimized proposals and communication tailored to the customer. After the sales meeting concludes, the system feeds back the activity results.

[0412] (Application Example 2)

[0413] 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."

[0414] In traditional customer service, it is difficult to grasp customer emotions in real time, and product suggestions may not align with the customer's interests or emotional state. This can lead to inaccurate suggestions and decreased customer satisfaction. Furthermore, customer service relies heavily on the experience of the salesperson, making it difficult for new employees to maintain the same level of quality. There is a need to address these challenges and enable efficient and personalized customer service that transcends individual sales capabilities.

[0415] 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.

[0416] In this invention, the server includes means for acquiring information from data storage that stores customer information, customer service staff information, and past transaction history; means for executing a data analysis algorithm for generating product suggestion information suitable for the target person based on the acquired customer information; and means for using an emotion analysis engine to detect the customer's emotional state in real time and dynamically adjust the product suggestion information. This makes it possible to make optimal product suggestions tailored to each individual customer and improve the quality of customer service.

[0417] "Customer information" refers to data about the recipients of products or services, including personal attributes, purchase history, and preferences.

[0418] "Customer service information" refers to data about individuals who are responsible for providing products or services, including details such as experience, areas of expertise, and work history.

[0419] "Past transaction history" refers to data on all transactions that have taken place with the customer in the past, including records of purchased goods, services, payment methods, dates, etc.

[0420] "Data storage" refers to any data storage device that can securely store large amounts of digital information and retrieve it quickly when needed.

[0421] A "data analysis algorithm" is a set of procedures and calculations used to derive useful information or results from a specific dataset.

[0422] "Product suggestion information" refers to suggestions created to provide the most suitable products and services to individual customers, and includes personalized details.

[0423] An "emotion analysis engine" is software designed to detect and analyze a customer's emotions and psychological state, and it has the function of evaluating emotions from inputs such as facial expressions and voice.

[0424] A "user interface" is a screen or operating device used by a system and a user to exchange information, and is designed with an emphasis on ease of use and visibility.

[0425] The server utilizes multiple hardware and software components to support customer service activities. First, customer information, customer service representative information, and past transaction history are stored in data storage. To quickly retrieve this data, the server is equipped with a high-performance database management system. For example, it uses a non-relational database such as MongoDB to enable fast data searching and retrieval.

[0426] The data analysis algorithm, developed using Python and TensorFlow, analyzes customers' past behavioral data and emotional states to generate personalized product recommendations. This generated product recommendation information is sent via the server to the customer service staff's terminals and displayed in real time.

[0427] The emotion analysis engine uses the device's camera and microphone to capture the customer's facial expressions and voice, and analyzes their emotions by combining OpenCV and various natural language processing (NLP) technologies. The acquired emotion data is sent to a server and used to adjust product recommendations.

[0428] Users, i.e., customer service representatives, view suggested product information using tablets or smartphones. The user interface is developed using React Native, enabling intuitive and user-friendly operation. Suggestions are dynamically updated in response to customer reactions, allowing customer service representatives to communicate more effectively.

[0429] For example, when a customer picks up an item they're interested in at a fashion store, the emotion analysis engine detects the customer's facial expression indicating interest. Based on this, the server generates a product suggestion such as, "This item is on-trend this season, and this color is particularly popular," which is then displayed on the sales associate's terminal. An example of a prompt to be fed into the generating AI model is, "Please provide detailed information and reasons for recommending the item the customer showed interest in." This makes it possible to maximize sales opportunities.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The server retrieves customer information, customer service representative information, and past transaction history from data storage. This information is treated as a dataset showing customer purchase history and preferences. The input consists of various data stored in data storage, and the output is cleansed data for use in analysis.

[0433] Step 2:

[0434] The server executes data analysis algorithms based on the acquired data. Specifically, it runs a model using Python and TensorFlow to generate optimal product recommendations for customers. Here, customer behavior patterns and sales history are used as input data, and a list of appropriate product and service recommendations is obtained as output.

[0435] Step 3:

[0436] The terminal receives generated product suggestion information sent from the server. These suggestions are displayed visually on the customer service representative's terminal. The input is the suggestion information sent from the server, and the output is what is displayed on the user interface on the terminal's display.

[0437] Step 4:

[0438] The device uses its built-in camera and microphone to detect the customer's emotional state through an emotion analysis engine. It analyzes emotions from facial expression and voice data using OpenCV and natural language processing techniques. Input is real-time collected audio and video data, and output is the result of classifying the customer's emotions.

[0439] Step 5:

[0440] The server receives emotional data obtained from the emotion analysis engine and uses it to further optimize product recommendation information. The input is the result of the emotion analysis, and the output is product recommendation information updated to reflect the customer's emotional state.

[0441] Step 6:

[0442] Based on updated product suggestion information, users provide effective customer service through their devices. The input here is optimized suggestion content displayed on the device, and the output is a conversation that contributes to further customer interest and engagement.

[0443] Step 7:

[0444] The server stores the results of customer service activities as feedback in data storage. This data will then be used for future data analysis and product recommendations. The input is feedback data recorded at the end of the customer service activity, and the output is new data added to the training dataset.

[0445] 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.

[0446] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0447] 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.

[0448] [Third Embodiment]

[0449] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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".

[0461] This invention relates to a system for proposing the most suitable products to customers during sales activities, and its embodiments are described in detail below. This system mainly consists of three elements: a server, a terminal, and a user.

[0462] Server operation

[0463] The server first collects customer information, sales representative information, and past transaction history from the database. The server cleans this data and converts it into a consistent format, making it suitable for subsequent analysis. Next, the server runs machine learning algorithms to analyze the collected information and generate successful sales techniques and customer-tailored product proposals. These algorithms learn from past sales performance and optimize product proposals based on different sales styles. After the proposals are generated, the server customizes them to suit the characteristics of each sales representative and optimizes them for effective results.

[0464] Terminal operation

[0465] The terminal receives customized proposals sent from the server and presents them visually to the sales representative. This presentation is designed to allow sales representatives to easily understand the proposals and use them to communicate with customers. The terminal also provides an interface for receiving user feedback. This interface is simple and allows for quick recording of results from sales activities and customer reactions.

[0466] User actions

[0467] The user, i.e., the sales representative, reviews the proposed product details via their terminal. Based on the proposal method, the user conducts sales activities with the customer and feeds the results back into the system. The feedback recorded by the user is sent to the server as data to improve the accuracy of future proposals. This feedback information is collected again by the server and stored in a database, which is then used for future product proposals.

[0468] Specific example

[0469] For example, when making a sales pitch to customer A in the construction industry, the server analyzes industry trends and customer A's past purchasing history. If the analysis determines that customer A tends to prioritize cost, a proposal emphasizing cost performance will be displayed on the terminal. The user then conducts negotiations with customer A based on this proposal and feeds the results back into the system. This feedback information is used to improve future proposals for similar industries and customers.

[0470] As a result, this invention functions as a system that streamlines and improves the accuracy of sales activities and supports the improvement of sales representatives' performance.

[0471] The following describes the processing flow.

[0472] Step 1:

[0473] The server connects to the database and retrieves necessary customer information, sales representative information, and past transaction history. This data includes the customer company's industry, size, location, purchase history, and the sales performance and characteristics of the sales representative.

[0474] Step 2:

[0475] The server performs data cleaning to organize the acquired data. It imputes missing values, standardizes data formats, and builds a consistent dataset. This ensures the data is ready for analysis.

[0476] Step 3:

[0477] The server analyzes the data, which has been prepared using machine learning algorithms. In this process, the learning model is trained to extract past successful sales methods and proposal methods that are suitable for customer characteristics.

[0478] Step 4:

[0479] The server uses a trained model to generate product recommendations tailored to the customer. These recommendations include the most appropriate products and approaches from the product lineup.

[0480] Step 5:

[0481] The server customizes the product proposal methods obtained based on the characteristics and skills of the sales representative. This ensures that proposals are prepared that allow the representative to approach customers in a way that maximizes their strengths.

[0482] Step 6:

[0483] The server sends customized proposals to the terminal. The terminal displays the proposals in a visually easy-to-understand format, making them user-friendly for sales representatives.

[0484] Step 7:

[0485] Users conduct sales activities based on the proposals displayed on their devices. They record customer reactions and results obtained during sales activities.

[0486] Step 8:

[0487] The terminal sends feedback on sales activities to the server. The feedback information entered by the user is stored in a database so that it can be used for future proposals.

[0488] This allows the system to continuously improve the accuracy of its proposals and support sales activities.

[0489] (Example 1)

[0490] 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."

[0491] In modern sales activities, there is a demand for efficient and effective responses to the diversifying needs of customers. However, with traditional methods, it is extremely time-consuming for sales representatives to meticulously analyze the needs of each individual customer and create optimal proposals, resulting in inefficiencies for companies. Furthermore, there is a lack of mechanisms to effectively utilize the feedback obtained from sales activities and incorporate it into future sales efforts. This creates a challenge in improving sales performance.

[0492] 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.

[0493] In this invention, the server includes means for acquiring sales-related information and historical information from a storage device that stores information, means for executing an algorithm for generating product proposals using pre-processed information, and means for adjusting the generated product proposals based on the characteristics of individual agents. This makes it possible to improve the efficiency and accuracy of proposals in sales activities.

[0494] A "storage device for storing information" is a device that stores data and allows data to be read out as needed.

[0495] "Sales-related information" refers to data such as customer information, transaction history, and product information related to the sale of goods and services.

[0496] "Historical information" refers to detailed information about past transactions, and is a record of how customers have used products and services.

[0497] "Preprocessing" refers to initial processing to improve the quality of data and prepare it for analysis, including data cleaning and formatting.

[0498] An "algorithm" refers to a series of computational steps, a method for analyzing data and generating suggestions to solve a specific problem.

[0499] "Activist" refers to someone who sells goods or provides services, and usually means a sales representative.

[0500] "Feedback" refers to information recorded from sales activities and customer reactions, used to improve future proposals.

[0501] This invention provides a system that enables efficient product proposals and their customization in sales activities. This system primarily consists of a server, terminals, and users, with each component working in coordination.

[0502] Server operation

[0503] The server collects data, including sales-related and historical information, from storage devices. Data collection can be done using SQL queries, and the information is exported, for example, in CSV format. After data collection, the server uses the Python Pandas library to preprocess and clean the data. Techniques such as imputing incomplete data with the mean are applied. Next, the server executes machine learning algorithms using libraries such as Scikit-learn and TensorFlow. This generates product recommendations tailored to the customer. The generated recommendations are then adjusted according to the characteristics of each individual user.

[0504] Terminal operation

[0505] The terminal receives suggestions sent from the server. These suggestions are visually presented to the user via a user interface. This allows the user to easily understand the suggestions and utilize them in sales activities. The terminal also provides an interface for collecting activity results and sending feedback to the server. This information is used to improve the accuracy of future suggestions.

[0506] User actions

[0507] Users, or participants, conduct business negotiations with customers based on the provided product proposals. They send feedback on the negotiation results and customer reactions to the system via their terminals. This feedback information is stored on the server and used when generating future proposals.

[0508] Specific example

[0509] For example, consider sales activities targeting customer B in the food industry. The server analyzes market trends in the food industry and customer B's purchase history. This analysis reveals that customer B prefers health-conscious products. As a result, a suggestion emphasizing organic products is displayed on the terminal. The user conducts a business negotiation with customer B based on this suggestion, records the response on the terminal, and sends it as feedback. This information is used to improve future proposals.

[0510] Example of a prompt

[0511] "Analyze customer B's market trends and past purchase history to generate appropriate product recommendations."

[0512] In this way, this system aims to streamline sales activities and improve the accuracy of the proposals provided.

[0513] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0514] Step 1:

[0515] The server retrieves sales-related and historical information from storage devices. Specifically, it extracts the necessary information from the database using SQL queries. The input is a database query, and the output is a raw dataset.

[0516] Step 2:

[0517] The server preprocesses and cleans the acquired data. It uses the Python Pandas library to impute missing values ​​and standardize the format. The input is a raw dataset, and the output is a clean, analysis-ready dataset.

[0518] Step 3:

[0519] The server runs machine learning algorithms using cleaned data. This process involves training predictive models using Scikit-learn and TensorFlow to generate customer recommendations. The input is a clean dataset, and the output is the generated product recommendations.

[0520] Step 4:

[0521] The server adjusts the generated product proposals based on the characteristics of individual agents, ensuring that sales representatives can use the proposals most effectively. The input is the generated product proposal, and the output is the customized proposal.

[0522] Step 5:

[0523] The server sends a customized proposal to the terminal. The terminal receives this proposal and presents it to the agent through the user interface. The agent uses this proposal during sales activities. The input is the customized proposal, and the output is a visual presentation to the agent.

[0524] Step 6:

[0525] Users conduct sales activities based on proposals displayed on their devices. They feed back the results of negotiations and customer reactions to the system via their devices. The input is the results of sales activities, and the output is feedback information.

[0526] Step 7:

[0527] The server stores the collected feedback information in a database and uses it to generate suggestions for the next generation. This improves the accuracy of the algorithm. The input is the feedback information, and the output is the updated database.

[0528] (Application Example 1)

[0529] 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."

[0530] Modern retail strategies require personalized product recommendations for each customer. However, doing this manually is time-consuming and labor-intensive, placing a heavy burden on sales staff. Furthermore, there is a lack of means to provide real-time recommendations that instantly reflect customer purchase history and individual needs. Therefore, a system is needed to efficiently suggest suitable products to customers and improve the customer experience.

[0531] 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.

[0532] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales data, and past transaction history; means for executing a machine learning process to generate a product proposal method suitable for the customer based on the acquired customer information; and means for personalizing the generated product proposal method based on the characteristics of the sales representative. This makes it possible to visually display the personalized product proposal in real time through a smart device and to communicate effectively with the customer.

[0533] "Customer information" refers to data about customers, such as their attributes and purchase history, that is referenced when providing products and services.

[0534] "Sales data" refers to information related to sales activities, including digital data such as the activity history of sales representatives, details of business negotiations, and results.

[0535] "Past transaction history" refers to records of purchases and contracts made by customers in the past, and is data used to analyze purchasing trends and preferences.

[0536] A "storage device" is a piece of hardware or digital media used to store information for long periods of time, and is a device that enables the storage and retrieval of data.

[0537] A "machine learning process" is a learning process that uses algorithms to identify patterns and rules based on data and to predict or generate new information.

[0538] "Personalization" is the process of adjusting content to suit individual needs and characteristics based on specific information.

[0539] A "user interface" is a screen or means of operation designed to facilitate the exchange of information between a system and a user.

[0540] A "smart device" is an electronic device that has internet connectivity and data processing capabilities, and is equipped with functions to assist user operation.

[0541] This invention is a system that automatically proposes the most suitable products to customers based on customer information, sales data, and past transaction history. The system mainly consists of three elements: a server, a terminal, and a user.

[0542] The server first retrieves customer information, sales data, and historical transaction history from storage devices. This information undergoes a data cleaning process to integrate it into a consistent and analyzable format. Next, the server runs a machine learning process to generate the most suitable product recommendations for customers in real time. This uses machine learning frameworks such as TensorFlow. The machine learning process analyzes and optimizes different sales styles based on the collected data. After the recommendations are generated, the server personalizes the recommendations based on the characteristics of the sales representatives. This entire data flow is carried out using cloud services such as AWS Lambda and Google Cloud Functions.

[0543] The terminal receives personalized product suggestions sent from the server and presents them to sales representatives through a user interface. This information is conveyed to sales representatives visually using smart devices, such as smart glasses. This visual presentation allows sales representatives to communicate more smoothly with customers. The terminal also provides an interface for easily recording sales activity results as feedback and sending it to the server.

[0544] Users wear a smart device attached to their terminal to view visually personalized product suggestions. This enables personalized product recommendations to be made to customers, contributing to an improved customer experience. Based on these suggestions, users conduct actual sales activities and send the results as feedback to the system via the terminal. This feedback data is recorded and analyzed again on the server, improving the accuracy of the suggestions.

[0545] As a concrete example, when a regular customer returns to the store, the smart glasses display will show information such as, "A new model of the product you purchased last time has arrived. Please recommend it to the customer." In this process, the sales representative uses a generative AI model to generate prompt messages such as, "When a specific customer visits the store, generate a prompt that suggests a new product based on their past purchase history."

[0546] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0547] Step 1:

[0548] The server retrieves customer information, sales data, and historical transaction history from storage devices. This input data serves as the foundation for analyzing sales performance and customer purchasing trends. The server prepares this data for subsequent processing by converting and cleaning it into a consistent format.

[0549] Step 2:

[0550] The server executes machine learning algorithms based on the prepared data. A generative AI model is used to generate optimal product recommendations tailored to customer purchasing trends and needs. The output includes a list of optimal products and recommendations for a specific customer.

[0551] Step 3:

[0552] The server personalizes the generated product proposals based on the sales representative's characteristics and past performance. It uses data on the representative's performance and areas of expertise as input. As a result, the output proposals are more effective and tailored to the sales representative.

[0553] Step 4:

[0554] The terminal transmits personalized suggestions received from the server to a smart device. The input data is suggestion information from the server, and the output is a product suggestion visually displayed through a user interface. Information is provided to sales representatives in real time using devices such as smart glasses.

[0555] Step 5:

[0556] The sales representative, acting as the user, communicates with customers based on proposals provided through the terminal. By recording the content of the conversation with the customer and the results of the sales negotiation, feedback data for the next step is generated. This data is sent to the system for use in the next analysis.

[0557] Step 6:

[0558] The server receives feedback data sent from the terminals and stores it in its memory. It receives feedback data as input and uses it as new analytical material for future sales improvements. This continuously improves the overall accuracy of the system's proposals.

[0559] 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.

[0560] This invention is a system that proposes the most suitable products to customers during sales activities, and features an emotion engine. This system mainly consists of three elements: a server, a terminal, and a user.

[0561] Server operation

[0562] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. It also aggregates emotional data provided by the emotion engine. The server uses machine learning algorithms to analyze this information and generate product recommendations tailored to each customer. This analysis takes into account the customer's emotional state and reactions, enabling more personalized recommendations. The generated recommendations are then customized based on the sales representative's characteristics.

[0563] How the emotion engine works

[0564] The emotion engine detects the user's emotional state in real time during sales activities. This is done through analysis of the user's voice, facial expressions, and words. The emotional data is sent to a server and used to adjust product proposal methods and sales approaches.

[0565] Terminal operation

[0566] The terminal receives customized suggestions sent from the server and presents them to the sales representative. The suggestions may be updated in real time based on the user's emotional state. The terminal also provides an interface for recording emotional data input via an emotion engine and feedback on sales activities.

[0567] User actions

[0568] The user, i.e., the sales representative, reviews the proposed product information via a terminal. During sales activities, the proposal is adjusted in real time based on the customer's emotional state, supporting optimal communication. The user records the results of the sales activities and inputs them into the system as feedback.

[0569] Specific example

[0570] For example, during a business negotiation with customer B, the emotion engine captures the moment the customer shows interest. Based on this information, the proposal displayed on the device is immediately changed to specific guidance such as "We will explain this point in more detail." The sales representative can then use this to provide a detailed explanation tailored to the customer's interests, thereby improving the closing rate of the deal.

[0571] Thus, this invention is a system that enhances the effectiveness of sales activities and realizes a more sophisticated proposal method by combining an emotion engine.

[0572] The following describes the processing flow.

[0573] Step 1:

[0574] The server accesses the database to retrieve customer information, sales representative information, and past transaction history. In addition, it prepares sentiment data provided in real time from the sentiment engine.

[0575] Step 2:

[0576] The server applies machine learning algorithms to analyze collected customer information and sales data. Based on the analysis results, it generates the optimal product recommendation method for each customer. At this stage, past transaction trends and sentiment data are also taken into consideration.

[0577] Step 3:

[0578] The server customizes the generated product proposal methods according to the characteristics of each sales representative. This enables efficient proposals that leverage the unique strengths of each representative.

[0579] Step 4:

[0580] The emotion engine analyzes the user's emotions in real time through the device and sends the data to the server. This allows the user's emotional state during sales activities to be monitored and reflected in the proposals.

[0581] Step 5:

[0582] The device displays customized suggestions received from the server to the user. These suggestions may be updated in real time based on feedback from the sentiment engine.

[0583] Step 6:

[0584] Users conduct sales activities with customers based on suggestions displayed on their devices. During sales activities, the device reflects emotional data recorded by the user and adjusts the suggestions as needed.

[0585] Step 7:

[0586] The terminal sends user feedback to the server after sales activities are completed. This feedback includes sales results, customer reactions, and the user's subjective impressions.

[0587] Step 8:

[0588] The server stores feedback in a database and uses it to improve future analysis and proposal methods. Simultaneously, integrating emotional data will be used to inform future product proposals.

[0589] This series of processes enables the system to quickly and effectively propose products that meet customer needs.

[0590] (Example 2)

[0591] 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."

[0592] In sales activities, accurately understanding customer emotions and interests and making personalized product proposals based on that understanding is a major challenge for sales representatives. With conventional technology, it was difficult to generate proposals that reflected the customer's emotional state in real time, making it difficult to maximize sales conversion rates and effectiveness. Furthermore, there were insufficient systems to effectively feed back the results of sales activities and continuously improve the accuracy of proposal methods.

[0593] 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.

[0594] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales representative information, and past transaction history; means for executing a calculation method for generating a product proposal method suitable for the customer based on the acquired customer information; and means for providing a user screen for presenting the personalized product proposal method to the sales representative. As a result, the sales representative can make optimal proposals that reflect the customer's emotions in real time, thereby improving the accuracy of sales activities and the closing rate.

[0595] A "storage device" is a device or system used to store data and information for a long period of time.

[0596] A "calculation method" is a method for processing and calculating data using acquired data and deriving a result.

[0597] "Personalization" refers to specially adjusting the content according to the customer and their circumstances, resulting in a form optimized for each individual.

[0598] A "user interface" refers to an interface function that allows users to visually view and manipulate information.

[0599] "Emotional information" refers to data that indicates a user's emotions and reactions, and is collected through functions such as an emotion engine.

[0600] This invention is configured as a system for streamlining sales activities and proposing the most suitable products to customers. It includes a server, terminals, and an emotion engine, each playing a specific role.

[0601] Server operation

[0602] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. SQL database queries are used for this purpose. Sentimental information provided by the sentiment engine is also aggregated on the server. The aggregated data is analyzed using machine learning algorithms. This analysis allows a generative AI model to generate optimal product recommendations for each customer. These product recommendations are further personalized based on the characteristics of each sales representative.

[0603] How the emotion engine works

[0604] The emotion engine analyzes the user's voice, facial expressions, and words in real time during sales activities. This analysis utilizes speech recognition software and facial expression analysis technology, and the resulting emotional information is transmitted to a server. This emotional information is then used to adjust product proposal methods and sales approaches.

[0605] Terminal operation

[0606] The terminal presents personalized suggestions sent from the server to the sales representative. The suggestions are displayed via a dedicated user interface. The user interface operates on devices such as tablets and smartphones, and also records feedback and emotional information from an emotion engine.

[0607] User actions

[0608] Users, i.e., sales representatives, review the proposed products and services through their terminals. During sales activities, the proposals are adjusted in real time based on customer sentiment, supporting optimal communication. After the meeting, the sales results are entered into the system as feedback, enabling continuous learning.

[0609] As a concrete example, if the emotion engine detects that customer B has shown interest during a business negotiation, the suggestion on the device will change in real time to "Please explain this point in more detail." This mechanism allows sales representatives to provide explanations tailored to the customer's interests, thereby improving the closing rate of deals.

[0610] Example prompt: "Identify the factors that interest Customer B and generate specific guidance to adjust the product proposal."

[0611] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0612] Step 1:

[0613] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. The input consists of various types of information stored in the database, and the output is an integrated set of information. This process uses SQL queries to extract information and integrate it in the format required by the system.

[0614] Step 2:

[0615] The emotion engine analyzes the user's voice, facial expressions, and words in real time to acquire emotional information. Inputs include audio and video data from business negotiations, and output is the analyzed emotional information. This process involves using speech recognition software and facial expression analysis algorithms to determine the emotional state.

[0616] Step 3:

[0617] The server combines acquired customer information and sentiment information, and uses a generative AI model to generate the most suitable product recommendation method for each customer. The input includes an integrated information set and sentiment information, and the output is a personalized product recommendation method. This process involves data analysis and prompt message generation using machine learning algorithms.

[0618] Step 4:

[0619] The server customizes the generated product proposal method based on the sales representative's characteristics and sends it to the terminal. The input consists of the generated product proposal method and the sales representative's characteristics information, and the output is a proposal method tailored to the sales representative. Here, the proposal content is individualized by taking into account each representative's past performance and characteristics.

[0620] Step 5:

[0621] The terminal presents personalized product proposal methods received from the server to the sales representative. The input is the personalized product proposal method, and the output is the displayed proposal content. The proposal method is presented intuitively to the sales representative via a dedicated user interface on the terminal.

[0622] Step 6:

[0623] During sales activities, users review product proposal methods presented via a terminal and adjust their approach in real time based on customer sentiment information. Inputs include sentiment information and presented proposals, while output is optimized proposals and communication tailored to the customer. After the sales meeting concludes, the system feeds back the activity results.

[0624] (Application Example 2)

[0625] 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."

[0626] In traditional customer service, it is difficult to grasp customer emotions in real time, and product suggestions may not align with the customer's interests or emotional state. This can lead to inaccurate suggestions and decreased customer satisfaction. Furthermore, customer service relies heavily on the experience of the salesperson, making it difficult for new employees to maintain the same level of quality. There is a need to address these challenges and enable efficient and personalized customer service that transcends individual sales capabilities.

[0627] 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.

[0628] In this invention, the server includes means for acquiring information from data storage that stores customer information, customer service staff information, and past transaction history; means for executing a data analysis algorithm for generating product suggestion information suitable for the target person based on the acquired customer information; and means for using an emotion analysis engine to detect the customer's emotional state in real time and dynamically adjust the product suggestion information. This makes it possible to make optimal product suggestions tailored to each individual customer and improve the quality of customer service.

[0629] "Customer information" refers to data about the recipients of products or services, including personal attributes, purchase history, and preferences.

[0630] "Customer service information" refers to data about individuals who are responsible for providing products or services, including details such as experience, areas of expertise, and work history.

[0631] "Past transaction history" refers to data on all transactions that have taken place with the customer in the past, including records of purchased goods, services, payment methods, dates, etc.

[0632] "Data storage" refers to any data storage device that can securely store large amounts of digital information and retrieve it quickly when needed.

[0633] A "data analysis algorithm" is a set of procedures and calculations used to derive useful information or results from a specific dataset.

[0634] "Product suggestion information" refers to suggestions created to provide the most suitable products and services to individual customers, and includes personalized details.

[0635] An "emotion analysis engine" is software designed to detect and analyze a customer's emotions and psychological state, and it has the function of evaluating emotions from inputs such as facial expressions and voice.

[0636] A "user interface" is a screen or operating device used by a system and a user to exchange information, and is designed with an emphasis on ease of use and visibility.

[0637] The server utilizes multiple hardware and software components to support customer service activities. First, customer information, customer service representative information, and past transaction history are stored in data storage. To quickly retrieve this data, the server is equipped with a high-performance database management system. For example, it uses a non-relational database such as MongoDB to enable fast data searching and retrieval.

[0638] The data analysis algorithm, developed using Python and TensorFlow, analyzes customers' past behavioral data and emotional states to generate personalized product recommendations. This generated product recommendation information is sent via the server to the customer service staff's terminals and displayed in real time.

[0639] The emotion analysis engine uses the device's camera and microphone to capture the customer's facial expressions and voice, and analyzes their emotions by combining OpenCV and various natural language processing (NLP) technologies. The acquired emotion data is sent to a server and used to adjust product recommendations.

[0640] Users, i.e., customer service representatives, view suggested product information using tablets or smartphones. The user interface is developed using React Native, enabling intuitive and user-friendly operation. Suggestions are dynamically updated in response to customer reactions, allowing customer service representatives to communicate more effectively.

[0641] For example, when a customer picks up an item they're interested in at a fashion store, the emotion analysis engine detects the customer's facial expression indicating interest. Based on this, the server generates a product suggestion such as, "This item is on-trend this season, and this color is particularly popular," which is then displayed on the sales associate's terminal. An example of a prompt to be fed into the generating AI model is, "Please provide detailed information and reasons for recommending the item the customer showed interest in." This makes it possible to maximize sales opportunities.

[0642] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0643] Step 1:

[0644] The server retrieves customer information, customer service representative information, and past transaction history from data storage. This information is treated as a dataset showing customer purchase history and preferences. The input consists of various data stored in data storage, and the output is cleansed data for use in analysis.

[0645] Step 2:

[0646] The server executes data analysis algorithms based on the acquired data. Specifically, it runs a model using Python and TensorFlow to generate optimal product recommendations for customers. Here, customer behavior patterns and sales history are used as input data, and a list of appropriate product and service recommendations is obtained as output.

[0647] Step 3:

[0648] The terminal receives generated product suggestion information sent from the server. These suggestions are displayed visually on the customer service representative's terminal. The input is the suggestion information sent from the server, and the output is what is displayed on the user interface on the terminal's display.

[0649] Step 4:

[0650] The device uses its built-in camera and microphone to detect the customer's emotional state through an emotion analysis engine. It analyzes emotions from facial expression and voice data using OpenCV and natural language processing techniques. Input is real-time collected audio and video data, and output is the result of classifying the customer's emotions.

[0651] Step 5:

[0652] The server receives emotional data obtained from the emotion analysis engine and uses it to further optimize product recommendation information. The input is the result of the emotion analysis, and the output is product recommendation information updated to reflect the customer's emotional state.

[0653] Step 6:

[0654] Based on updated product suggestion information, users provide effective customer service through their devices. The input here is optimized suggestion content displayed on the device, and the output is a conversation that contributes to further customer interest and engagement.

[0655] Step 7:

[0656] The server stores the results of customer service activities as feedback in data storage. This data will then be used for future data analysis and product recommendations. The input is feedback data recorded at the end of the customer service activity, and the output is new data added to the training dataset.

[0657] 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.

[0658] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0659] 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.

[0660] [Fourth Embodiment]

[0661] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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).

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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".

[0674] This invention relates to a system for proposing the most suitable products to customers during sales activities, and its embodiments are described in detail below. This system mainly consists of three elements: a server, a terminal, and a user.

[0675] Server operation

[0676] The server first collects customer information, sales representative information, and past transaction history from the database. The server cleans this data and converts it into a consistent format, making it suitable for subsequent analysis. Next, the server runs machine learning algorithms to analyze the collected information and generate successful sales techniques and customer-tailored product proposals. These algorithms learn from past sales performance and optimize product proposals based on different sales styles. After the proposals are generated, the server customizes them to suit the characteristics of each sales representative and optimizes them for effective results.

[0677] Terminal operation

[0678] The terminal receives customized proposals sent from the server and presents them visually to the sales representative. This presentation is designed to allow sales representatives to easily understand the proposals and use them to communicate with customers. The terminal also provides an interface for receiving user feedback. This interface is simple and allows for quick recording of results from sales activities and customer reactions.

[0679] User actions

[0680] The user, i.e., the sales representative, reviews the proposed product details via their terminal. Based on the proposal method, the user conducts sales activities with the customer and feeds the results back into the system. The feedback recorded by the user is sent to the server as data to improve the accuracy of future proposals. This feedback information is collected again by the server and stored in a database, which is then used for future product proposals.

[0681] Specific example

[0682] For example, when making a sales pitch to customer A in the construction industry, the server analyzes industry trends and customer A's past purchasing history. If the analysis determines that customer A tends to prioritize cost, a proposal emphasizing cost performance will be displayed on the terminal. The user then conducts negotiations with customer A based on this proposal and feeds the results back into the system. This feedback information is used to improve future proposals for similar industries and customers.

[0683] As a result, this invention functions as a system that streamlines and improves the accuracy of sales activities and supports the improvement of sales representatives' performance.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] The server connects to the database and retrieves necessary customer information, sales representative information, and past transaction history. This data includes the customer company's industry, size, location, purchase history, and the sales performance and characteristics of the sales representative.

[0687] Step 2:

[0688] The server performs data cleaning to organize the acquired data. It imputes missing values, standardizes data formats, and builds a consistent dataset. This ensures the data is ready for analysis.

[0689] Step 3:

[0690] The server analyzes the data, which has been prepared using machine learning algorithms. In this process, the learning model is trained to extract past successful sales methods and proposal methods that are suitable for customer characteristics.

[0691] Step 4:

[0692] The server uses a trained model to generate product recommendations tailored to the customer. These recommendations include the most appropriate products and approaches from the product lineup.

[0693] Step 5:

[0694] The server customizes the product proposal methods obtained based on the characteristics and skills of the sales representative. This ensures that proposals are prepared that allow the representative to approach customers in a way that maximizes their strengths.

[0695] Step 6:

[0696] The server sends customized proposals to the terminal. The terminal displays the proposals in a visually easy-to-understand format, making them user-friendly for sales representatives.

[0697] Step 7:

[0698] Users conduct sales activities based on the proposals displayed on their devices. They record customer reactions and results obtained during sales activities.

[0699] Step 8:

[0700] The terminal sends feedback on sales activities to the server. The feedback information entered by the user is stored in a database so that it can be used for future proposals.

[0701] This allows the system to continuously improve the accuracy of its proposals and support sales activities.

[0702] (Example 1)

[0703] 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".

[0704] In modern sales activities, there is a demand for efficient and effective responses to the diversifying needs of customers. However, with traditional methods, it is extremely time-consuming for sales representatives to meticulously analyze the needs of each individual customer and create optimal proposals, resulting in inefficiencies for companies. Furthermore, there is a lack of mechanisms to effectively utilize the feedback obtained from sales activities and incorporate it into future sales efforts. This creates a challenge in improving sales performance.

[0705] 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.

[0706] In this invention, the server includes means for acquiring sales-related information and historical information from a storage device that stores information, means for executing an algorithm for generating product proposals using pre-processed information, and means for adjusting the generated product proposals based on the characteristics of individual agents. This makes it possible to improve the efficiency and accuracy of proposals in sales activities.

[0707] A "storage device for storing information" is a device that stores data and allows data to be read out as needed.

[0708] "Sales-related information" refers to data such as customer information, transaction history, and product information related to the sale of goods and services.

[0709] "Historical information" refers to detailed information about past transactions, and is a record of how customers have used products and services.

[0710] "Preprocessing" refers to initial processing to improve the quality of data and prepare it for analysis, including data cleaning and formatting.

[0711] An "algorithm" refers to a series of computational steps, a method for analyzing data and generating suggestions to solve a specific problem.

[0712] "Activist" refers to someone who sells goods or provides services, and usually means a sales representative.

[0713] "Feedback" refers to information recorded from sales activities and customer reactions, used to improve future proposals.

[0714] This invention provides a system that enables efficient product proposals and their customization in sales activities. This system primarily consists of a server, terminals, and users, with each component working in coordination.

[0715] Server operation

[0716] The server collects data, including sales-related and historical information, from storage devices. Data collection can be done using SQL queries, and the information is exported, for example, in CSV format. After data collection, the server uses the Python Pandas library to preprocess and clean the data. Techniques such as imputing incomplete data with the mean are applied. Next, the server executes machine learning algorithms using libraries such as Scikit-learn and TensorFlow. This generates product recommendations tailored to the customer. The generated recommendations are then adjusted according to the characteristics of each individual user.

[0717] Terminal operation

[0718] The terminal receives suggestions sent from the server. These suggestions are visually presented to the user via a user interface. This allows the user to easily understand the suggestions and utilize them in sales activities. The terminal also provides an interface for collecting activity results and sending feedback to the server. This information is used to improve the accuracy of future suggestions.

[0719] User actions

[0720] Users, or participants, conduct business negotiations with customers based on the provided product proposals. They send feedback on the negotiation results and customer reactions to the system via their terminals. This feedback information is stored on the server and used when generating future proposals.

[0721] Specific example

[0722] For example, consider sales activities targeting customer B in the food industry. The server analyzes market trends in the food industry and customer B's purchase history. This analysis reveals that customer B prefers health-conscious products. As a result, a suggestion emphasizing organic products is displayed on the terminal. The user conducts a business negotiation with customer B based on this suggestion, records the response on the terminal, and sends it as feedback. This information is used to improve future proposals.

[0723] Example of a prompt

[0724] "Analyze customer B's market trends and past purchase history to generate appropriate product recommendations."

[0725] In this way, this system aims to streamline sales activities and improve the accuracy of the proposals provided.

[0726] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0727] Step 1:

[0728] The server retrieves sales-related and historical information from storage devices. Specifically, it extracts the necessary information from the database using SQL queries. The input is a database query, and the output is a raw dataset.

[0729] Step 2:

[0730] The server preprocesses and cleans the acquired data. It uses the Python Pandas library to impute missing values ​​and standardize the format. The input is a raw dataset, and the output is a clean, analysis-ready dataset.

[0731] Step 3:

[0732] The server runs machine learning algorithms using cleaned data. This process involves training predictive models using Scikit-learn and TensorFlow to generate customer recommendations. The input is a clean dataset, and the output is the generated product recommendations.

[0733] Step 4:

[0734] The server adjusts the generated product proposals based on the characteristics of individual agents, ensuring that sales representatives can use the proposals most effectively. The input is the generated product proposal, and the output is the customized proposal.

[0735] Step 5:

[0736] The server sends a customized proposal to the terminal. The terminal receives this proposal and presents it to the agent through the user interface. The agent uses this proposal during sales activities. The input is the customized proposal, and the output is a visual presentation to the agent.

[0737] Step 6:

[0738] Users conduct sales activities based on proposals displayed on their devices. They feed back the results of negotiations and customer reactions to the system via their devices. The input is the results of sales activities, and the output is feedback information.

[0739] Step 7:

[0740] The server stores the collected feedback information in a database and uses it to generate suggestions for the next generation. This improves the accuracy of the algorithm. The input is the feedback information, and the output is the updated database.

[0741] (Application Example 1)

[0742] 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".

[0743] Modern retail strategies require personalized product recommendations for each customer. However, doing this manually is time-consuming and labor-intensive, placing a heavy burden on sales staff. Furthermore, there is a lack of means to provide real-time recommendations that instantly reflect customer purchase history and individual needs. Therefore, a system is needed to efficiently suggest suitable products to customers and improve the customer experience.

[0744] 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.

[0745] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales data, and past transaction history; means for executing a machine learning process to generate a product proposal method suitable for the customer based on the acquired customer information; and means for personalizing the generated product proposal method based on the characteristics of the sales representative. This makes it possible to visually display the personalized product proposal in real time through a smart device and to communicate effectively with the customer.

[0746] "Customer information" refers to data about customers, such as their attributes and purchase history, that is referenced when providing products and services.

[0747] "Sales data" refers to information related to sales activities, including digital data such as the activity history of sales representatives, details of business negotiations, and results.

[0748] "Past transaction history" refers to records of purchases and contracts made by customers in the past, and is data used to analyze purchasing trends and preferences.

[0749] A "storage device" is a piece of hardware or digital media used to store information for long periods of time, and is a device that enables the storage and retrieval of data.

[0750] A "machine learning process" is a learning process that uses algorithms to identify patterns and rules based on data and to predict or generate new information.

[0751] "Personalization" is the process of adjusting content to suit individual needs and characteristics based on specific information.

[0752] A "user interface" is a screen or means of operation designed to facilitate the exchange of information between a system and a user.

[0753] A "smart device" is an electronic device that has internet connectivity and data processing capabilities, and is equipped with functions to assist user operation.

[0754] This invention is a system that automatically proposes the most suitable products to customers based on customer information, sales data, and past transaction history. The system mainly consists of three elements: a server, a terminal, and a user.

[0755] The server first retrieves customer information, sales data, and historical transaction history from storage devices. This information undergoes a data cleaning process to integrate it into a consistent and analyzable format. Next, the server runs a machine learning process to generate the most suitable product recommendations for customers in real time. This uses machine learning frameworks such as TensorFlow. The machine learning process analyzes and optimizes different sales styles based on the collected data. After the recommendations are generated, the server personalizes the recommendations based on the characteristics of the sales representatives. This entire data flow is carried out using cloud services such as AWS Lambda and Google Cloud Functions.

[0756] The terminal receives personalized product suggestions sent from the server and presents them to sales representatives through a user interface. This information is conveyed to sales representatives visually using smart devices, such as smart glasses. This visual presentation allows sales representatives to communicate more smoothly with customers. The terminal also provides an interface for easily recording sales activity results as feedback and sending it to the server.

[0757] Users wear a smart device attached to their terminal to view visually personalized product suggestions. This enables personalized product recommendations to be made to customers, contributing to an improved customer experience. Based on these suggestions, users conduct actual sales activities and send the results as feedback to the system via the terminal. This feedback data is recorded and analyzed again on the server, improving the accuracy of the suggestions.

[0758] As a concrete example, when a regular customer returns to the store, the smart glasses display will show information such as, "A new model of the product you purchased last time has arrived. Please recommend it to the customer." In this process, the sales representative uses a generative AI model to generate prompt messages such as, "When a specific customer visits the store, generate a prompt that suggests a new product based on their past purchase history."

[0759] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0760] Step 1:

[0761] The server retrieves customer information, sales data, and historical transaction history from storage devices. This input data serves as the foundation for analyzing sales performance and customer purchasing trends. The server prepares this data for subsequent processing by converting and cleaning it into a consistent format.

[0762] Step 2:

[0763] The server executes machine learning algorithms based on the prepared data. A generative AI model is used to generate optimal product recommendations tailored to customer purchasing trends and needs. The output includes a list of optimal products and recommendations for a specific customer.

[0764] Step 3:

[0765] The server personalizes the generated product proposals based on the sales representative's characteristics and past performance. It uses data on the representative's performance and areas of expertise as input. As a result, the output proposals are more effective and tailored to the sales representative.

[0766] Step 4:

[0767] The terminal transmits personalized suggestions received from the server to a smart device. The input data is suggestion information from the server, and the output is a product suggestion visually displayed through a user interface. Information is provided to sales representatives in real time using devices such as smart glasses.

[0768] Step 5:

[0769] The sales representative, acting as the user, communicates with customers based on proposals provided through the terminal. By recording the content of the conversation with the customer and the results of the sales negotiation, feedback data for the next step is generated. This data is sent to the system for use in the next analysis.

[0770] Step 6:

[0771] The server receives feedback data sent from the terminals and stores it in its memory. It receives feedback data as input and uses it as new analytical material for future sales improvements. This continuously improves the overall accuracy of the system's proposals.

[0772] 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.

[0773] This invention is a system that proposes the most suitable products to customers during sales activities, and features an emotion engine. This system mainly consists of three elements: a server, a terminal, and a user.

[0774] Server operation

[0775] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. It also aggregates emotional data provided by the emotion engine. The server uses machine learning algorithms to analyze this information and generate product recommendations tailored to each customer. This analysis takes into account the customer's emotional state and reactions, enabling more personalized recommendations. The generated recommendations are then customized based on the sales representative's characteristics.

[0776] How the emotion engine works

[0777] The emotion engine detects the user's emotional state in real time during sales activities. This is done through analysis of the user's voice, facial expressions, and words. The emotional data is sent to a server and used to adjust product proposal methods and sales approaches.

[0778] Terminal operation

[0779] The terminal receives customized suggestions sent from the server and presents them to the sales representative. The suggestions may be updated in real time based on the user's emotional state. The terminal also provides an interface for recording emotional data input via an emotion engine and feedback on sales activities.

[0780] User actions

[0781] The user, i.e., the sales representative, reviews the proposed product information via a terminal. During sales activities, the proposal is adjusted in real time based on the customer's emotional state, supporting optimal communication. The user records the results of the sales activities and inputs them into the system as feedback.

[0782] Specific example

[0783] For example, during a business negotiation with customer B, the emotion engine captures the moment the customer shows interest. Based on this information, the proposal displayed on the device is immediately changed to specific guidance such as "We will explain this point in more detail." The sales representative can then use this to provide a detailed explanation tailored to the customer's interests, thereby improving the closing rate of the deal.

[0784] Thus, this invention is a system that enhances the effectiveness of sales activities and realizes a more sophisticated proposal method by combining an emotion engine.

[0785] The following describes the processing flow.

[0786] Step 1:

[0787] The server accesses the database to retrieve customer information, sales representative information, and past transaction history. In addition, it prepares sentiment data provided in real time from the sentiment engine.

[0788] Step 2:

[0789] The server applies machine learning algorithms to analyze collected customer information and sales data. Based on the analysis results, it generates the optimal product recommendation method for each customer. At this stage, past transaction trends and sentiment data are also taken into consideration.

[0790] Step 3:

[0791] The server customizes the generated product proposal methods according to the characteristics of each sales representative. This enables efficient proposals that leverage the unique strengths of each representative.

[0792] Step 4:

[0793] The emotion engine analyzes the user's emotions in real time through the device and sends the data to the server. This allows the user's emotional state during sales activities to be monitored and reflected in the proposals.

[0794] Step 5:

[0795] The device displays customized suggestions received from the server to the user. These suggestions may be updated in real time based on feedback from the sentiment engine.

[0796] Step 6:

[0797] Users conduct sales activities with customers based on suggestions displayed on their devices. During sales activities, the device reflects emotional data recorded by the user and adjusts the suggestions as needed.

[0798] Step 7:

[0799] The terminal sends user feedback to the server after sales activities are completed. This feedback includes sales results, customer reactions, and the user's subjective impressions.

[0800] Step 8:

[0801] The server stores feedback in a database and uses it to improve future analysis and proposal methods. Simultaneously, integrating emotional data will be used to inform future product proposals.

[0802] This series of processes enables the system to quickly and effectively propose products that meet customer needs.

[0803] (Example 2)

[0804] 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".

[0805] In sales activities, accurately understanding customer emotions and interests and making personalized product proposals based on that understanding is a major challenge for sales representatives. With conventional technology, it was difficult to generate proposals that reflected the customer's emotional state in real time, making it difficult to maximize sales conversion rates and effectiveness. Furthermore, there were insufficient systems to effectively feed back the results of sales activities and continuously improve the accuracy of proposal methods.

[0806] 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.

[0807] In this invention, the server includes means for acquiring information from a storage device that stores customer information, sales representative information, and past transaction history; means for executing a calculation method for generating a product proposal method suitable for the customer based on the acquired customer information; and means for providing a user screen for presenting the personalized product proposal method to the sales representative. As a result, the sales representative can make optimal proposals that reflect the customer's emotions in real time, thereby improving the accuracy of sales activities and the closing rate.

[0808] A "storage device" is a device or system used to store data and information for a long period of time.

[0809] A "calculation method" is a method for processing and calculating data using acquired data and deriving a result.

[0810] "Personalization" refers to specially adjusting the content according to the customer and their circumstances, resulting in a form optimized for each individual.

[0811] A "user interface" refers to an interface function that allows users to visually view and manipulate information.

[0812] "Emotional information" refers to data that indicates a user's emotions and reactions, and is collected through functions such as an emotion engine.

[0813] This invention is configured as a system for streamlining sales activities and proposing the most suitable products to customers. It includes a server, terminals, and an emotion engine, each playing a specific role.

[0814] Server operation

[0815] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. SQL database queries are used for this purpose. Sentimental information provided by the sentiment engine is also aggregated on the server. The aggregated data is analyzed using machine learning algorithms. This analysis allows a generative AI model to generate optimal product recommendations for each customer. These product recommendations are further personalized based on the characteristics of each sales representative.

[0816] How the emotion engine works

[0817] The emotion engine analyzes the user's voice, facial expressions, and words in real time during sales activities. This analysis utilizes speech recognition software and facial expression analysis technology, and the resulting emotional information is transmitted to a server. This emotional information is then used to adjust product proposal methods and sales approaches.

[0818] Terminal operation

[0819] The terminal presents personalized suggestions sent from the server to the sales representative. The suggestions are displayed via a dedicated user interface. The user interface operates on devices such as tablets and smartphones, and also records feedback and emotional information from an emotion engine.

[0820] User actions

[0821] Users, i.e., sales representatives, review the proposed products and services through their terminals. During sales activities, the proposals are adjusted in real time based on customer sentiment, supporting optimal communication. After the meeting, the sales results are entered into the system as feedback, enabling continuous learning.

[0822] As a concrete example, if the emotion engine detects that customer B has shown interest during a business negotiation, the suggestion on the device will change in real time to "Please explain this point in more detail." This mechanism allows sales representatives to provide explanations tailored to the customer's interests, thereby improving the closing rate of deals.

[0823] Example prompt: "Identify the factors that interest Customer B and generate specific guidance to adjust the product proposal."

[0824] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0825] Step 1:

[0826] The server connects to the database to retrieve customer information, sales representative information, and past transaction history. The input consists of various types of information stored in the database, and the output is an integrated set of information. This process uses SQL queries to extract information and integrate it in the format required by the system.

[0827] Step 2:

[0828] The emotion engine analyzes the user's voice, facial expressions, and words in real time to acquire emotional information. Inputs include audio and video data from business negotiations, and output is the analyzed emotional information. This process involves using speech recognition software and facial expression analysis algorithms to determine the emotional state.

[0829] Step 3:

[0830] The server combines acquired customer information and sentiment information, and uses a generative AI model to generate the most suitable product recommendation method for each customer. The input includes an integrated information set and sentiment information, and the output is a personalized product recommendation method. This process involves data analysis and prompt message generation using machine learning algorithms.

[0831] Step 4:

[0832] The server customizes the generated product proposal method based on the sales representative's characteristics and sends it to the terminal. The input consists of the generated product proposal method and the sales representative's characteristics information, and the output is a proposal method tailored to the sales representative. Here, the proposal content is individualized by taking into account each representative's past performance and characteristics.

[0833] Step 5:

[0834] The terminal presents personalized product proposal methods received from the server to the sales representative. The input is the personalized product proposal method, and the output is the displayed proposal content. The proposal method is presented intuitively to the sales representative via a dedicated user interface on the terminal.

[0835] Step 6:

[0836] During sales activities, users review product proposal methods presented via a terminal and adjust their approach in real time based on customer sentiment information. Inputs include sentiment information and presented proposals, while output is optimized proposals and communication tailored to the customer. After the sales meeting concludes, the system feeds back the activity results.

[0837] (Application Example 2)

[0838] 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".

[0839] In traditional customer service, it is difficult to grasp customer emotions in real time, and product suggestions may not align with the customer's interests or emotional state. This can lead to inaccurate suggestions and decreased customer satisfaction. Furthermore, customer service relies heavily on the experience of the salesperson, making it difficult for new employees to maintain the same level of quality. There is a need to address these challenges and enable efficient and personalized customer service that transcends individual sales capabilities.

[0840] 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.

[0841] In this invention, the server includes means for acquiring information from data storage that stores customer information, customer service staff information, and past transaction history; means for executing a data analysis algorithm for generating product suggestion information suitable for the target person based on the acquired customer information; and means for using an emotion analysis engine to detect the customer's emotional state in real time and dynamically adjust the product suggestion information. This makes it possible to make optimal product suggestions tailored to each individual customer and improve the quality of customer service.

[0842] "Customer information" refers to data about the recipients of products or services, including personal attributes, purchase history, and preferences.

[0843] "Customer service information" refers to data about individuals who are responsible for providing products or services, including details such as experience, areas of expertise, and work history.

[0844] "Past transaction history" refers to data on all transactions that have taken place with the customer in the past, including records of purchased goods, services, payment methods, dates, etc.

[0845] "Data storage" refers to any data storage device that can securely store large amounts of digital information and retrieve it quickly when needed.

[0846] A "data analysis algorithm" is a set of procedures and calculations used to derive useful information or results from a specific dataset.

[0847] "Product suggestion information" refers to suggestions created to provide the most suitable products and services to individual customers, and includes personalized details.

[0848] An "emotion analysis engine" is software designed to detect and analyze a customer's emotions and psychological state, and it has the function of evaluating emotions from inputs such as facial expressions and voice.

[0849] A "user interface" is a screen or operating device used by a system and a user to exchange information, and is designed with an emphasis on ease of use and visibility.

[0850] The server utilizes multiple hardware and software components to support customer service activities. First, customer information, customer service representative information, and past transaction history are stored in data storage. To quickly retrieve this data, the server is equipped with a high-performance database management system. For example, it uses a non-relational database such as MongoDB to enable fast data searching and retrieval.

[0851] The data analysis algorithm, developed using Python and TensorFlow, analyzes customers' past behavioral data and emotional states to generate personalized product recommendations. This generated product recommendation information is sent via the server to the customer service staff's terminals and displayed in real time.

[0852] The emotion analysis engine uses the device's camera and microphone to capture the customer's facial expressions and voice, and analyzes their emotions by combining OpenCV and various natural language processing (NLP) technologies. The acquired emotion data is sent to a server and used to adjust product recommendations.

[0853] Users, i.e., customer service representatives, view suggested product information using tablets or smartphones. The user interface is developed using React Native, enabling intuitive and user-friendly operation. Suggestions are dynamically updated in response to customer reactions, allowing customer service representatives to communicate more effectively.

[0854] For example, when a customer picks up an item they're interested in at a fashion store, the emotion analysis engine detects the customer's facial expression indicating interest. Based on this, the server generates a product suggestion such as, "This item is on-trend this season, and this color is particularly popular," which is then displayed on the sales associate's terminal. An example of a prompt to be fed into the generating AI model is, "Please provide detailed information and reasons for recommending the item the customer showed interest in." This makes it possible to maximize sales opportunities.

[0855] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0856] Step 1:

[0857] The server retrieves customer information, customer service representative information, and past transaction history from data storage. This information is treated as a dataset showing customer purchase history and preferences. The input consists of various data stored in data storage, and the output is cleansed data for use in analysis.

[0858] Step 2:

[0859] The server executes data analysis algorithms based on the acquired data. Specifically, it runs a model using Python and TensorFlow to generate optimal product recommendations for customers. Here, customer behavior patterns and sales history are used as input data, and a list of appropriate product and service recommendations is obtained as output.

[0860] Step 3:

[0861] The terminal receives generated product suggestion information sent from the server. These suggestions are displayed visually on the customer service representative's terminal. The input is the suggestion information sent from the server, and the output is what is displayed on the user interface on the terminal's display.

[0862] Step 4:

[0863] The device uses its built-in camera and microphone to detect the customer's emotional state through an emotion analysis engine. It analyzes emotions from facial expression and voice data using OpenCV and natural language processing techniques. Input is real-time collected audio and video data, and output is the result of classifying the customer's emotions.

[0864] Step 5:

[0865] The server receives emotional data obtained from the emotion analysis engine and uses it to further optimize product recommendation information. The input is the result of the emotion analysis, and the output is product recommendation information updated to reflect the customer's emotional state.

[0866] Step 6:

[0867] Based on updated product suggestion information, users provide effective customer service through their devices. The input here is optimized suggestion content displayed on the device, and the output is a conversation that contributes to further customer interest and engagement.

[0868] Step 7:

[0869] The server stores the results of customer service activities as feedback in data storage. This data will then be used for future data analysis and product recommendations. The input is feedback data recorded at the end of the customer service activity, and the output is new data added to the training dataset.

[0870] 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.

[0871] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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."

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] The following is further disclosed regarding the embodiments described above.

[0892] (Claim 1)

[0893] A means of retrieving information from a database that stores customer information, sales representative information, and past transaction history,

[0894] A means for executing a machine learning algorithm to generate a product proposal method suitable for the customer based on acquired customer information,

[0895] A means of customizing the generated product proposal method based on the characteristics of the sales representative,

[0896] A means of providing a user interface for presenting customized product proposal methods to sales representatives,

[0897] A means of recording the results of sales activities as feedback and accumulating them in a database,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, which optimizes multiple sales styles based on customer needs and generates different proposal methods according to each sales style.

[0901] (Claim 3)

[0902] The system according to claim 1, which continuously learns from the results of sales activities and builds a feedback loop to improve the accuracy of proposal methods.

[0903] "Example 1"

[0904] (Claim 1)

[0905] A means for obtaining sales-related information and historical information from a storage device that stores information,

[0906] A means of preprocessing acquired sales-related information and performing data cleaning,

[0907] A means for executing an algorithm to generate product proposals using pre-processed information,

[0908] A means of adjusting the generated product proposals based on the characteristics of individual participants,

[0909] A display means for visually presenting adjusted product proposals to the participants,

[0910] A means of recording and storing feedback on sales activities in a memory device,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, which optimizes multiple sales methods based on customer characteristics and generates proposals suitable for each sales method.

[0914] (Claim 3)

[0915] The system according to claim 1, which continuously analyzes the results of sales activities and forms a feedback loop for improving the accuracy of proposals.

[0916] "Application Example 1"

[0917] (Claim 1)

[0918] A means for obtaining information from a storage device that stores customer information, sales data, and past transaction history,

[0919] A means for executing a machine learning process to generate product suggestion methods suitable for customers based on acquired customer information,

[0920] A means of personalizing the generated product proposal method based on the characteristics of the sales representative,

[0921] A means of providing a user interface for presenting personalized product proposal methods to sales representatives,

[0922] A means of recording the results of sales activities as feedback and storing them in a memory device,

[0923] A means of providing customers with visual displays using smart devices,

[0924] A system that includes this.

[0925] (Claim 2)

[0926] The system according to claim 1, which optimizes multiple sales styles based on customer demand and generates different proposal methods corresponding to each sales style.

[0927] (Claim 3)

[0928] The system according to claim 1, which continuously learns from the results of sales activities and establishes a feedback process to improve the accuracy of proposal methods.

[0929] "Example 2 of combining an emotion engine"

[0930] (Claim 1)

[0931] A means for obtaining information from a storage device that stores customer information, sales representative information, and past transaction history,

[0932] A means for executing a computation method to generate a product proposal method suitable for the customer based on acquired customer information,

[0933] A means of personalizing the generated product proposal methods based on the characteristics of the sales representative,

[0934] A means of providing a user screen for sales representatives to present personalized product proposal methods,

[0935] A means of acquiring emotional information detected during use and adjusting the suggested content,

[0936] A means of recording the results of sales activities as feedback and storing them in a memory device,

[0937] A system that includes this.

[0938] (Claim 2)

[0939] The system according to claim 1, which optimizes multiple sales styles based on customer requirements and generates different proposal methods corresponding to each sales style.

[0940] (Claim 3)

[0941] The system according to claim 1, which continuously learns the results of sales activities and emotional information, and builds a feedback loop to improve the accuracy of proposal methods.

[0942] "Application example 2 when combining with an emotional engine"

[0943] (Claim 1)

[0944] A means of retrieving information from data storage that stores customer information, customer service representative information, and past transaction history,

[0945] A means for executing a data analysis algorithm to generate product suggestion information suitable for the target person based on acquired customer information,

[0946] A means to optimize the generated product suggestion information based on the characteristics of the customer service representative,

[0947] A means of providing a user interface for presenting optimized product suggestion information to customer service staff,

[0948] A means of using an emotion analysis engine to detect the customer's emotional state in real time and dynamically adjust product suggestion information,

[0949] A means of recording the results of customer service activities as feedback and storing them in data storage,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, which optimizes multiple customer service styles based on customer needs and emotional states, and generates different product suggestion information corresponding to each customer service style.

[0953] (Claim 3)

[0954] The system according to claim 1, which continuously learns from the results of customer service activities and sentiment analysis data, and builds a feedback loop to improve the accuracy of product suggestion information. [Explanation of Symbols]

[0955] 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 retrieving information from a database that stores customer information, sales representative information, and past transaction history, A means for executing a machine learning algorithm to generate a product proposal method suitable for the customer based on acquired customer information, A means of customizing the generated product proposal method based on the characteristics of the sales representative, A means of providing a user interface for presenting customized product proposal methods to sales representatives, A means of recording the results of sales activities as feedback and accumulating them in a database, A system that includes this.

2. The system according to claim 1, which optimizes multiple sales styles based on customer needs and generates different proposal methods corresponding to each sales style.

3. The system according to claim 1, which continuously learns from the results of sales activities and builds a feedback loop to improve the accuracy of proposal methods.

Images