system

Abstract

We provide the system. [Solution] A means of collecting past sales data and customer behavior history from a database, A means of predicting customer preferences and purchasing behavior using a generative model based on collected data, and generating individual sales proposals, Based on the generated proposals, a means of providing customers with a virtual experience of products or services using virtual reality or augmented reality technology, A means of collecting customer feedback and incorporating it into the next data analysis, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 modern sales activities, formulating an efficient and effective sales strategy for specific customers has become an important issue. A customized approach that takes into account different preferences and purchasing behaviors for each customer is required, but it is difficult to implement this on a large scale. In particular, since the means of appealing to customers in real time are limited, there is a problem that the purchasing desire of customers cannot be maximally drawn out.

Means for Solving the Problems

[0005] This invention provides a system that collects past sales data and customer behavior history from a database and analyzes it to predict the preferences and purchasing behavior of each individual customer using a generative model. Furthermore, it includes means to allow customers to virtually experience products and services using virtual reality or augmented reality technology based on the generated suggestions, thereby enabling them to visually and concretely understand the features and benefits of the products. In addition, it includes means to collect customer feedback and reflect that data in subsequent data analysis to improve the accuracy of sales strategies. This enables efficient and effective sales activities and can improve customer satisfaction.

[0006] "Sales data" refers to information related to the buying and selling of goods, including past transaction information, amounts, dates, and details of the buyer.

[0007] "Customer behavior history" refers to a record of past activities that a customer has engaged in, such as purchasing products or browsing websites.

[0008] A "generative model" is an algorithm or program built to analyze collected data and predict specific outcomes.

[0009] A "sales proposal" is a specific proposal regarding products or services presented to a particular customer.

[0010] "Virtual reality technology" is a technology that uses computer simulations to provide users with experiences that are indistinguishable from reality.

[0011] Augmented reality technology is a technology that overlays digital information onto the physical environment, providing an interactive experience where reality and the digital world merge.

[0012] A "virtual experience" is an interaction that utilizes digital technology to allow users to virtually experience products and services.

[0013] "Feedback" refers to customer evaluations and opinions on a particular product or service, which are used to improve future products and services. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention provides a system that enables personalized sales proposals by utilizing customer data. This system mainly consists of a server, terminals, and users.

[0036] First, the server accesses the database to collect past sales data and behavioral history of customers. This provides foundational data for understanding customer purchasing patterns and preferences. Based on this data, the server uses a generative model to predict each customer's preferences and purchasing intent. The generative model is an algorithm that analyzes the collected data to select the most suitable products and services for each customer.

[0037] Next, the server generates individual sales proposals based on the analysis results. These proposals include the optimal product and related explanations to gain the customer's approval. The generated proposals also include a plan to visualize how the customer will actually use the product or service.

[0038] The device receiving this proposal has the capability to allow customers to experience the proposal using virtual reality (VR) or augmented reality (AR) technology. Specifically, it provides a realistic purchasing experience by visually showing customers the features of the product or service and simulating actual usage scenarios.

[0039] Meanwhile, users operate their devices and, through the provided virtual and augmented reality experiences, carefully review the details of the suggested products and services. User feedback is sent to the server via the device. This feedback plays a crucial role in subsequent data analysis and suggestion generation, leading to further improvements in accuracy.

[0040] As a concrete example, consider a telecommunications service company proposing a new internet plan to a specific customer. This customer has a history of preferring high-speed data services. The server analyzes this history and proposes a new plan that matches the customer's usage patterns. The terminal allows the customer to experience this plan through VR / AR technology, visualizing the speed and benefits that the new plan offers. After the user experiences this plan and provides feedback, the system incorporates this feedback to further improve future proposals and experiences.

[0041] This allows users to have a better purchasing experience, and enables telecommunications service companies to achieve increased customer satisfaction and sales.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server accesses the company's database and collects each customer's past sales data and behavioral history. This data includes purchase history, inquiry history, website visit history, and more.

[0045] Step 2:

[0046] The server formats the collected data and inputs it into a generative model. This generative model is designed to predict customer preferences and purchasing behavior using machine learning algorithms.

[0047] Step 3:

[0048] The server generates optimal sales proposals for each customer based on the analysis results of the generative model. These proposals detail the products and services recommended for the customer, along with the reasons why.

[0049] Step 4:

[0050] The server sends the generated proposal to the relevant terminal. The terminal receives this proposal data and uses virtual reality or augmented reality technology to prepare a visual presentation for the customer.

[0051] Step 5:

[0052] Based on the suggestions, the device generates interactive content that allows customers to experience products and services within a virtual environment. This includes features such as the ability to view products from a 360-degree perspective and simulations using the services.

[0053] Step 6:

[0054] Users can experience VR / AR through their devices while reviewing the features of the suggested products and services. This experience allows users to gain a deeper understanding of the actual product value and increase their desire to purchase.

[0055] Step 7:

[0056] Users provide feedback via their devices after the experience ends, including aspects they found interesting and areas for improvement.

[0057] Step 8:

[0058] The server analyzes user feedback data and stores it in a database. This data is used to improve the accuracy of future analyses and sales proposals.

[0059] (Example 1)

[0060] 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."

[0061] Traditional marketing methods often involve uniform sales proposals, making it difficult to provide personalized offers that adequately address diverse customer preferences and purchasing behaviors. Furthermore, opportunities for customers to actually experience and understand the features of products and services are limited, sometimes leading to a lack of understanding or mismatches. Therefore, to improve customer satisfaction and maximize sales, a new system is needed that provides proposals and experiences optimized for each customer.

[0062] 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.

[0063] In this invention, the server includes means for acquiring past sales data and consumer behavior history from an information storage device; means for predicting consumer preferences and purchasing behavior using a generated artificial intelligence model based on the acquired information and creating individual sales proposals; and means for providing consumers with a virtual experience of products and services using virtual reality or augmented reality technology based on the created proposals. This makes it possible to provide optimized sales proposals to each consumer, deepen their understanding of products and services, and achieve high customer satisfaction.

[0064] "Sales data" refers to information that describes the details of transactions and sales history that occur when a company sells goods or services to customers.

[0065] An "information storage device" is a computer system or related equipment for efficiently and securely storing and managing data.

[0066] A "generative artificial intelligence model" is a program or system that uses machine learning algorithms to generate new information or predictions based on consumer data.

[0067] "Consumer preferences" refer to the tendencies of individual consumers' likes and preferences for specific products or services.

[0068] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take when purchasing goods or services.

[0069] "Virtual reality technology" is a method that uses computer technology to generate and present realistic experiences to users visually and audibly.

[0070] Augmented reality technology is a technology that extends our perception of reality by overlaying computer-generated graphics and data onto information from the real world.

[0071] A "virtual experience" is a simulation that uses virtual reality or augmented reality technology to allow users to feel as if they are actually using a product or service.

[0072] "Opinions" refer to the evaluations and impressions that consumers have of the products and services provided, and are important information that serves as valuable feedback for future product and service improvements.

[0073] "Information analysis" is a series of processes that involve analyzing acquired data and feedback in detail to understand trends and patterns and use them to aid in decision-making.

[0074] This invention provides a system comprising a server, terminals, and users for making personalized sales proposals.

[0075] The server first accesses the data storage device to retrieve historical sales data and consumer behavior history. This information is extracted from an SQL database management system (e.g., MySQL®, PostgreSQL) and used as data for data analysis. Next, the server inputs this information into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. The generative model is built using a machine learning framework (e.g., TENSORFLOW®, PyTorch) and generates optimal suggestions for each consumer.

[0076] The generated sales proposals are delivered to the user through a device using virtual reality (VR) or augmented reality (AR) technology. The device uses a VR headset or AR glasses to visualize the features of the product or service in real time. For example, in a scenario where an internet service provider proposes a new high-speed data plan, the device can allow consumers to experience the benefits of the connection speed offered by that plan. This experience is built using development platforms such as Unity or Unreal Engine.

[0077] Users interact with the device and review the details of the products and services suggested through the provided experience. User feedback is sent to the server via the device and plays a crucial role in subsequent analyses. This feedback is used to improve the accuracy of the system's recommendations.

[0078] As a concrete example, a prompt message might say, "Based on the customer's past purchase history, please suggest the product they are most likely to purchase next." In this way, the present invention aims to improve sales potential and customer satisfaction by providing personalized suggestions and experiences that are tailored to consumer needs.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server retrieves historical sales data and consumer behavior history from the data storage device. The input at this stage is information queried from the database using SQL queries. The server then formats this retrieved raw data into structured data and temporarily stores it. The output is the formatted data that forms the basis for data analysis.

[0082] Step 2:

[0083] The server inputs formatted data into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. This data processing is performed using a machine learning framework, estimating future behavior based on past consumer behavior. The output is predictive data including each consumer's purchasing intent and preferences. This forms the basis for the server to generate personalized sales proposals.

[0084] Step 3:

[0085] The server creates personalized sales proposals for individual consumers based on predictive data. This proposal generation process uses a generative AI model to create proposals in natural language that are easy for consumers to understand. The input is predictive data, and the output is an attractive proposal document tailored to each consumer. For example, a proposal might be something like, "Would you like to improve your daily digital experience with a high-speed data plan?"

[0086] Step 4:

[0087] The device delivers the generated proposal to the user using virtual reality (VR) or augmented reality (AR) technology. At this stage, the proposal document is converted into visual content, providing the user with an interactive experience. The input is the proposal document, and the output is a virtual environment designed by Unity or Unreal Engine. Through this interface, the user concretely experiences the product or service.

[0088] Step 5:

[0089] Users interact with the device to view the provided VR / AR experience and evaluate the usefulness of the sales proposal. Input consists of impressions and thoughts about the product or service gained through the experience. User actions and feedback are collected by the device and recorded as qualitative data.

[0090] Step 6:

[0091] The server receives user feedback from the terminal and incorporates it into subsequent data analysis and proposal generation. The feedback is incorporated into the training dataset of the machine learning algorithm and treated as valuable data for improving model accuracy. The input is user feedback, and the output is the improved model prediction result. This enables more accurate and user-optimized proposals.

[0092] (Application Example 1)

[0093] 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."

[0094] Traditional customer service systems struggled to effectively provide personalized suggestions based on customer purchase history and preferences, and to allow customers to experience these suggestions in a virtual environment. Furthermore, the lack of means to incorporate customer feedback into future suggestions and provide a highly optimized product experience made improving customer satisfaction a challenge.

[0095] 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.

[0096] In this invention, the server includes means for collecting past sales information and customer behavior history from a storage device; means for predicting customer preferences and purchasing behavior using a generation algorithm based on the collected information and creating individual sales proposals; and means for providing customers with a virtual experience of products and services using augmented reality or virtual reality technology based on the created proposals. This makes it possible to effectively provide customers with an optimized product experience and to reflect customer evaluations in subsequent information analysis.

[0097] A "storage device" is a device or system used to store digital data.

[0098] A "generative algorithm" is a computational method that analyzes patterns based on data to create predictions or suggestions tailored to a specific purpose.

[0099] "Preference" is a concept that refers to an individual's preferences based on their interests and concerns.

[0100] "Virtual reality" is a technology that uses computer technology to create artificial environments that make the user feel like they are experiencing them in real life.

[0101] Augmented reality is a technology that overlays computer-generated information onto the real world environment.

[0102] A "virtual experience" is the use of digital technology to provide a simulation of an experience that does not exist in reality.

[0103] "Evaluation" is the process of judging value by aggregating the impressions and opinions gained by those who have experienced something.

[0104] "Information analysis" is the process of processing collected data and extracting useful insights and patterns from it.

[0105] The system for implementing the present invention consists of a server that handles the main processing, a terminal for providing proposals to customers, and a user who operates the system.

[0106] The server first collects past sales information and behavioral history of customers stored in storage. This builds a data base for understanding customer preferences and purchasing patterns. Next, the server feeds this data to a generation algorithm, which uses a machine learning model to predict the most suitable products and services for each customer. Machine learning frameworks such as TensorFlow are suitable for this generation algorithm. The output of the generation algorithm is converted into customized sales proposals for each customer.

[0107] The terminal serves to provide customers with suggestions. Specifically, this terminal is a device equipped with augmented reality or virtual reality technology, such as smart glasses like Microsoft HoloLens®. Using this, customers can actually experience the suggested products and services within the virtual store and visualize their usage scenarios. This experience stimulates customer purchasing intent and provides a higher-level purchasing experience.

[0108] Users accept or provide feedback on experiences suggested through their devices. This feedback is sent from the device to the server and used to improve data analysis and suggestion generation in the future, leading to increased accuracy. This cycle enhances customer satisfaction.

[0109] As a concrete example, consider a scenario where a customer is choosing sports shoes in a virtual store. This customer's past purchase history shows a high frequency of buying running shoes. Based on this information, the server generates suggestions highlighting the latest running shoes and their features. The terminal displays these suggestions using augmented reality, and the customer is supported in making a purchase decision by virtually trying on the shoes from various angles. Customer feedback is used to improve future suggestions.

[0110] An example of a prompt for a generative AI model might be: "Generate an algorithm for suggesting new products based on customer purchase history data. Display the generated suggestions using AR, collect feedback, and incorporate it into future suggestions."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server collects input from storage devices, including past sales information and customer behavior history. Based on this data, it builds a dataset to understand customer purchasing patterns and prepares it to be supplied to a generative AI model.

[0114] Step 2:

[0115] The server passes the collected data to a generation algorithm, which then uses machine learning models to perform data analysis that predicts individual customer preferences and purchasing behavior. This process generates an output in the form of a list of products and services best suited to each customer. This uses machine learning frameworks such as TensorFlow.

[0116] Step 3:

[0117] The server creates individual sales proposals based on the generated list of optimal products and services. Here, prompts are used to clarify the features of the products and services, refining the proposals and preparing data for visualization in the next stage.

[0118] Step 4:

[0119] The terminal uses augmented reality or virtual reality technology to present sales proposals to customers based on proposals received from the server. The terminal creates an environment where customers can virtually experience products and services through smart glasses such as Microsoft HoloLens, visually realizing the proposals. Customers then try out the products based on the visualized proposals.

[0120] Step 5:

[0121] Users interact with the device to examine visual suggestions and compare them to their actual purchase intent. If the suggestion is appropriate, they enter feedback on the device and send it to the server. The feedback collected here is used as customer evaluation to improve future suggestions.

[0122] Step 6:

[0123] The server incorporates user feedback into subsequent data analysis and suggestion generation, updating the generating AI model to improve accuracy. This feedback processing enhances the personalization accuracy of suggestions, which can then be used to improve future customer suggestions.

[0124] 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.

[0125] This invention is a system that provides personalized sales proposals by utilizing user sales data, behavioral history, and emotional data. The system consists of a server, terminals, users, and an emotional engine.

[0126] First, the server collects historical sales data and customer behavior history from the company's database. This provides foundational data for understanding customer purchasing patterns. Furthermore, the server uses a generative model based on the collected data to predict customer preferences and purchasing intent. This model is comprised of machine learning algorithms, enabling detailed analysis of customers.

[0127] Next, the server generates individual sales proposals based on the analysis results. These proposals are dynamically adjusted by an emotion engine to adapt to the user's emotional state. The emotion engine recognizes the user's emotions in real time from their facial expressions and voice input, and optimizes the proposal content accordingly.

[0128] The devices receiving these proposals will use virtual reality (VR) or augmented reality (AR) technology to prepare the customer to experience the proposal. This experience will be transformed into interactive content that highlights the features of the product or service and allows the user to visually understand its value.

[0129] Users can experience this VR / AR through their devices and view content that reflects their interests. User reactions and feedback, along with emotional data, are sent to the server and recorded in a database. This information will then be used for future data analysis and sales proposal creation.

[0130] As a concrete example, consider a scenario where a customer is considering purchasing a new home appliance. The server selects an appropriate product based on the customer's past purchase history, and the terminal prepares a program that allows the customer to experience the product's features in VR. At this time, the emotion engine recognizes the customer's facial expressions and adjusts the experience to emphasize the points the customer shows interest in. By analyzing the user's actual reactions and understanding how the proposal was received by the customer, it becomes possible to develop even more accurate sales strategies.

[0131] In this way, the system aims to improve customer satisfaction and business results by recognizing and utilizing user emotions to provide a more appropriate and engaging sales experience.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server accesses the company's database to collect each customer's past sales data and behavioral history. This collection includes customer purchase history, website visit history, and inquiry history. The collected data is converted to a standard format and stored in a way that is suitable for analysis.

[0135] Step 2:

[0136] The server inputs the collected data into a generative model to predict customer purchasing preferences and behavior. The generative model used here is based on machine learning algorithms. This model learns from past data patterns and forms the basis for new sales proposals.

[0137] Step 3:

[0138] Based on the analysis results, the server generates optimal sales proposals for each customer. These proposals address the customer's specific preferences and provide detailed explanations of recommended products and services, along with the reasons for selling them.

[0139] Step 4:

[0140] The emotion engine is activated and analyzes the emotional state of the user receiving the proposal in real time. The device uses the emotion engine to capture the user's facial expressions with a camera or to infer emotions from voice input. This emotional data is used to adjust sales proposals.

[0141] Step 5:

[0142] The device utilizes virtual reality (VR) or augmented reality (AR) technology to deliver personalized sales presentations to the user. These presentations are customized based on the user's emotional state and are presented as interactive content that enhances the visual experience of the product or service.

[0143] Step 6:

[0144] Users utilize VR / AR experiences provided through their devices to directly verify the features and benefits of the proposed products. This experience simulates realistic purchase scenarios, allowing users to gain a more concrete understanding of the product's usability and value.

[0145] Step 7:

[0146] After the experience, users input their thoughts and opinions as feedback via their device. This feedback includes their thoughts on the suggestions, points of interest, and areas for improvement.

[0147] Step 8:

[0148] The server integrates user feedback and sentiment data, and incorporates this information into subsequent data analysis. The feedback is stored in a database and used to improve the accuracy of future sales proposals.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] There is a need to improve the accuracy of personalized commercial recommendations and provide optimal experiences tailored to the user's emotional state in order to increase customer satisfaction and corporate sales. However, conventional systems do not fully utilize user behavioral data and emotional data, resulting in insufficient personalization of recommendations.

[0152] 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.

[0153] In this invention, the server includes means for collecting information on past sales and user behavior records from an information storage device; means for inferring user preferences and purchasing behavior using a generative model based on the collected information and generating individual commercial suggestions; and means for providing users with a virtual experience of goods or services using a virtual environment or augmented environment technology based on the generated suggestions. This makes it possible to provide a personalized experience that takes into account the user's emotional state, thereby improving customer satisfaction and corporate sales.

[0154] An "information storage device" is a device used to store and manage information such as past sales data and customer behavior records.

[0155] A "generative model" is a model that uses machine learning techniques to infer user preferences and purchasing behavior based on collected data.

[0156] A "virtual environment" is a system that uses computer technology to allow users to experience an environment different from the real world.

[0157] An "augmented environment" is a system that overlays digital information onto real-world information to provide users with new information.

[0158] An "emotion processing engine" is a device that has software or hardware functions to recognize the user's emotions and adjust the suggested content accordingly.

[0159] A "commercial proposal" is an introduction to products or services presented to users, and information intended to encourage their purchase.

[0160] This invention is a system that analyzes users' past sales data, behavioral records, and emotional data to provide personalized commercial recommendations. The system comprises a server, terminals, users, and an emotional processing engine.

[0161] The server uses an information storage device to collect sales-related information and user behavior records within the company. This information is retrieved and collected using data management techniques such as SQL queries. After collection, the data is analyzed by a generative model to predict user preferences and purchase intent. The generative model can use commonly used machine learning methods such as TensorFlow and PyTorch, and is a mechanism that improves prediction accuracy by learning from vast amounts of data.

[0162] The terminal receives personalized commercial proposals from the server and delivers experiences to users using virtual and augmented environments. Specifically, it uses content creation tools such as Unity and Unreal Engine to create a space where users can visually and interactively experience the feel and features of a product. This experience plays a crucial role in helping users deepen their understanding of the product or service.

[0163] Users can view information that reflects their interests based on the experiences provided through their device. The emotions and reactions expressed during this process are recognized by an emotion processing engine, and the content of the suggestions is dynamically adjusted accordingly. The emotion processing engine is equipped with a facial recognition camera and a voice recognition microphone, enabling real-time analysis of emotions.

[0164] As a concrete example, consider a scenario where a user is trying to purchase a specific home appliance. The server provides information on related products based on the user's past purchasing behavior, and the terminal prepares a virtual experience that shows the product's features in detail. The user can try out the product through VR or AR, and an emotion processing engine identifies the user's interests from their facial expressions and voice, highlighting the points that piqued their interest.

[0165] An example of a prompt message would be: "Use this user's past behavioral and sentiment data to identify the product they are most likely to purchase next."

[0166] Thus, the present invention aims to improve customer satisfaction and business performance by realizing more attractive and personalized commercial proposals through detailed recognition and response to users' emotions and behavioral patterns.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server retrieves users' past sales information and behavioral records from an information storage device. Inputs include vast amounts of transaction history and website behavioral data stored in the company's database. This data is retrieved via SQL queries and formatted using virtual tables. This process provides the foundational data needed to clarify users' purchasing patterns.

[0170] Step 2:

[0171] The server supplies the collected data to a generating AI model that infers the user's preferences and purchasing intent. Because this model uses machine learning algorithms, it learns and outputs the user's behavioral characteristics from newly provided data. Specifically, a neural network using TensorFlow processes the input data and quantifies the likelihood of purchasing a particular product. The output is the predicted preferences and purchasing intent.

[0172] Step 3:

[0173] The server generates personalized commercial proposals based on the prediction results. These proposals are based on data derived from the generative model used and include the selection of the most suitable products and services for the user. Here, prompt statements are created and incorporated into the commercial proposals. The output is a customized proposal statement provided to the user.

[0174] Step 4:

[0175] The server sends the generated proposal to the terminal, which receives it and presents it to the user through a virtual or extended environment. The input consists of commercial proposal content, which is then transformed into a visual experience using content creation tools such as Unity. This allows users to visualize the promotion of products and services.

[0176] Step 5:

[0177] Users view suggested virtual experiences using their devices and take actions based on their interests and preferences. The input is the VR or AR experience provided by the device, and the output is emotional data as a reaction. The user's facial expressions and actions are captured by the camera and microphone, and this information is used for future suggestions.

[0178] Step 6:

[0179] The server then stores the response data collected from users back into the data storage device. This strengthens the dataset used for future commercial proposals and training generative AI models. This feedback loop continuously improves the accuracy of proposals.

[0180] (Application Example 2)

[0181] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0182] Traditional sales proposals, while based on customer purchase history and preferences, failed to consider real-time emotional states, making it difficult to accurately address individual customer needs. Furthermore, the practical constraints of the in-store customer experience limited the appeal of products and services. Additionally, there was a lack of mechanisms to effectively incorporate feedback into sales proposals. As a result, improving customer satisfaction and streamlining sales promotion were significant challenges.

[0183] 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.

[0184] In this invention, the server includes a unit that collects past sales data and customer behavior history from a database; a unit that uses a generative model based on the collected information to predict user preferences and purchasing behavior and generate individual sales proposals; and a unit that uses augmented reality technology to provide users with a virtual experience of products and services based on the generated proposals. This enables personalized proposals through real-time emotion recognition, thereby improving the customer experience in stores.

[0185] "Past sales data" refers to records of products and services that users have previously purchased, and serves as the basis for analyzing customer purchasing trends.

[0186] "Behavioral history" refers to a record of a customer's actions online or in stores, and is information that helps understand the decision-making process leading up to a purchase.

[0187] A "database" is an aggregated information system for systematically storing collected data and for efficiently managing and retrieving it.

[0188] A "generative model" is a computational model that uses machine learning algorithms to analyze customer preferences and purchasing behavior, and predict the likelihood of future purchases.

[0189] Augmented reality technology is a technique that overlays digital information onto the real world's field of view, and is used to enhance the user's visual and immersive experience.

[0190] "Emotional state" refers to the psychological state analyzed in real time from the user's facial expressions and voice, and is information necessary to evaluate customer interest and acceptance.

[0191] A "display device for assisting customers" is a digital display device used by store staff to provide customers with information about products and services.

[0192] "Feedback" refers to the reactions and opinions collected from users, and it is important information that is analyzed and reflected in future sales strategies.

[0193] The system for implementing this invention mainly consists of three components: a server, a terminal, and a user. The server collects past sales data and behavioral history of customers from a database. This includes customer profiles, purchase history, and website visit records. The server then uses a generative AI model based on the collected data to predict customer preferences and purchasing behavior. This model performs detailed data analysis using machine learning algorithms to identify products and services suitable for the customer's next purchase.

[0194] Next, the server uses the generated data to create personalized suggestions, leveraging virtual reality (VR) or augmented reality (AR) technologies implemented by the device. The device analyzes the user's facial expressions and voice through an emotion engine that performs real-time emotion recognition. This allows the suggestions to adapt to the user's emotional state, providing a more personalized experience.

[0195] Users receive these customized suggestions through smart glasses, which are display devices used for customer interaction within the store. This rapid emotion recognition and personalized information presentation allows customers to instantly understand product features and determine if they match their interests. This feedback is collected from users in real time, sent to a server, and used for future data analysis and improvement of sales suggestions.

[0196] For example, if a customer is considering purchasing a smartphone in a store, a customer service display can facilitate effective sales by suggesting models that are suitable for the customer based on their past purchase history. An example of a prompt message would be, "Suggest new smartphones that the customer might be interested in. Analyze past purchase history and current sentiment to provide personalized recommendations."

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects historical sales data and customer behavior history from the database. This collection includes information such as customer purchase history and website visit records. The input data is organized and converted into a format that is easy for the generative AI model to analyze. Specifically, data cleansing is performed to output a neat dataset with noise removed.

[0200] Step 2:

[0201] The server uses a generative AI model, taking a well-organized dataset as input, to predict customer preferences and purchasing behavior. Here, machine learning algorithms play a key role in deriving the customer's future purchasing potential. This model extracts patterns from the data and predicts which products and services will attract customer interest. As an output of this process, personalized sales proposals are generated.

[0202] Step 3:

[0203] The server creates virtual reality (VR) or augmented reality (AR) content for the terminal to run, based on the prediction results and sales proposals. In this step, the visual content is designed to highlight the features of the proposed products and services. The generated content is then converted and prepared for use on the terminal.

[0204] Step 4:

[0205] Users wear smart glasses in the store and experience AR content provided via a device. An emotion engine analyzes the user's facial expressions and voice in real time, dynamically adjusting the content display based on the user's emotional state. Through this process, users can visually receive information tailored to their interests.

[0206] Step 5:

[0207] Users provide reactions and feedback on their experiences. The device collects this feedback and sends it to the server. Based on the feedback input, it is output as feedback information stored in the database to be used for future data analysis and improvement of sales proposals.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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".

[0224] This invention provides a system that enables personalized sales proposals by utilizing customer data. This system mainly consists of a server, terminals, and users.

[0225] First, the server accesses the database to collect past sales data and behavioral history of customers. This provides foundational data for understanding customer purchasing patterns and preferences. Based on this data, the server uses a generative model to predict each customer's preferences and purchasing intent. The generative model is an algorithm that analyzes the collected data to select the most suitable products and services for each customer.

[0226] Next, the server generates individual sales proposals based on the analysis results. These proposals include the optimal product and related explanations to gain the customer's approval. The generated proposals also include a plan to visualize how the customer will actually use the product or service.

[0227] The device receiving this proposal has the capability to allow customers to experience the proposal using virtual reality (VR) or augmented reality (AR) technology. Specifically, it provides a realistic purchasing experience by visually showing customers the features of the product or service and simulating actual usage scenarios.

[0228] Meanwhile, users operate their devices and, through the provided virtual and augmented reality experiences, carefully review the details of the suggested products and services. User feedback is sent to the server via the device. This feedback plays a crucial role in subsequent data analysis and suggestion generation, leading to further improvements in accuracy.

[0229] As a concrete example, consider a telecommunications service company proposing a new internet plan to a specific customer. This customer has a history of preferring high-speed data services. The server analyzes this history and proposes a new plan that matches the customer's usage patterns. The terminal allows the customer to experience this plan through VR / AR technology, visualizing the speed and benefits that the new plan offers. After the user experiences this plan and provides feedback, the system incorporates this feedback to further improve future proposals and experiences.

[0230] This allows users to have a better purchasing experience, and enables telecommunications service companies to achieve increased customer satisfaction and sales.

[0231] The following describes the processing flow.

[0232] Step 1:

[0233] The server accesses the company's database and collects each customer's past sales data and behavioral history. This data includes purchase history, inquiry history, website visit history, and more.

[0234] Step 2:

[0235] The server formats the collected data and inputs it into a generative model. This generative model is designed to predict customer preferences and purchasing behavior using machine learning algorithms.

[0236] Step 3:

[0237] The server generates optimal sales proposals for each customer based on the analysis results of the generative model. These proposals detail the products and services recommended for the customer, along with the reasons why.

[0238] Step 4:

[0239] The server sends the generated proposal to the relevant terminal. The terminal receives this proposal data and uses virtual reality or augmented reality technology to prepare a visual presentation for the customer.

[0240] Step 5:

[0241] Based on the suggestions, the device generates interactive content that allows customers to experience products and services within a virtual environment. This includes features such as the ability to view products from a 360-degree perspective and simulations using the services.

[0242] Step 6:

[0243] Users can experience VR / AR through their devices while reviewing the features of the suggested products and services. This experience allows users to gain a deeper understanding of the actual product value and increase their desire to purchase.

[0244] Step 7:

[0245] Users provide feedback via their devices after the experience ends, sharing their thoughts and opinions. This feedback includes aspects they found interesting and areas for improvement.

[0246] Step 8:

[0247] The server analyzes user feedback data and stores it in a database. This data is used to improve the accuracy of future analyses and sales proposals.

[0248] (Example 1)

[0249] 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."

[0250] Traditional marketing methods often involve uniform sales proposals, making it difficult to provide personalized offers that adequately address diverse customer preferences and purchasing behaviors. Furthermore, opportunities for customers to actually experience and understand the features of products and services are limited, sometimes leading to a lack of understanding or mismatches. Therefore, to improve customer satisfaction and maximize sales, a new system is needed that provides proposals and experiences optimized for each customer.

[0251] 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.

[0252] In this invention, the server includes means for acquiring past sales data and consumer behavior history from an information storage device; means for predicting consumer preferences and purchasing behavior using a generated artificial intelligence model based on the acquired information and creating individual sales proposals; and means for providing consumers with a virtual experience of products and services using virtual reality or augmented reality technology based on the created proposals. This makes it possible to provide optimized sales proposals to each consumer, deepen their understanding of products and services, and achieve high customer satisfaction.

[0253] "Sales data" refers to information that describes the details of transactions and sales history that occur when a company sells goods or services to customers.

[0254] An "information storage device" is a computer system or related equipment for efficiently and securely storing and managing data.

[0255] A "generative artificial intelligence model" is a program or system that uses machine learning algorithms to generate new information or predictions based on consumer data.

[0256] "Consumer preferences" refer to the tendencies of individual consumers' likes and preferences for specific products or services.

[0257] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take when purchasing goods or services.

[0258] "Virtual reality technology" is a method that uses computer technology to generate and present realistic experiences to users visually and audibly.

[0259] Augmented reality technology is a technology that extends our perception of reality by overlaying computer-generated graphics and data onto information from the real world.

[0260] A "virtual experience" is a simulation that uses virtual reality or augmented reality technology to allow users to feel as if they are actually using a product or service.

[0261] "Opinions" refer to the evaluations and impressions that consumers have of the products and services provided, and are important information that serves as valuable feedback for future product and service improvements.

[0262] "Information analysis" is a series of processes that involve analyzing acquired data and feedback in detail to understand trends and patterns and use them to aid in decision-making.

[0263] This invention provides a system comprising a server, terminals, and users for making personalized sales proposals.

[0264] The server first accesses the data storage device to retrieve historical sales data and consumer behavior history. This information is extracted from an SQL database management system (e.g., MySQL, PostgreSQL) and used as data for data analysis. Next, the server inputs this information into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. The generative model is built using a machine learning framework (e.g., TensorFlow, PyTorch) and generates optimal suggestions for each consumer.

[0265] The generated sales proposals are delivered to the user through a device using virtual reality (VR) or augmented reality (AR) technology. The device uses a VR headset or AR glasses to visualize the features of the product or service in real time. For example, in a scenario where an internet service provider proposes a new high-speed data plan, the device can allow consumers to experience the benefits of the connection speed offered by that plan. This experience is built using development platforms such as Unity or Unreal Engine.

[0266] Users interact with the device and review the details of the products and services suggested through the provided experience. User feedback is sent to the server via the device and plays a crucial role in subsequent analyses. This feedback is used to improve the accuracy of the system's recommendations.

[0267] As a concrete example, a prompt message might say, "Based on the customer's past purchase history, please suggest the product they are most likely to purchase next." In this way, the present invention aims to improve sales potential and customer satisfaction by providing personalized suggestions and experiences that are tailored to consumer needs.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server retrieves historical sales data and consumer behavior history from the data storage device. The input at this stage is information queried from the database using SQL queries. The server then formats this retrieved raw data into structured data and temporarily stores it. The output is the formatted data that forms the basis for data analysis.

[0271] Step 2:

[0272] The server inputs formatted data into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. This data processing is performed using a machine learning framework, estimating future behavior based on past consumer behavior. The output is predictive data including each consumer's purchasing intent and preferences. This forms the basis for the server to generate personalized sales proposals.

[0273] Step 3:

[0274] The server creates personalized sales proposals for individual consumers based on predictive data. This proposal generation process uses a generative AI model to create proposals in natural language that are easy for consumers to understand. The input is predictive data, and the output is an attractive proposal document tailored to each consumer. For example, a proposal might be something like, "Would you like to improve your daily digital experience with a high-speed data plan?"

[0275] Step 4:

[0276] The device delivers the generated proposal to the user using virtual reality (VR) or augmented reality (AR) technology. At this stage, the proposal document is converted into visual content, providing the user with an interactive experience. The input is the proposal document, and the output is a virtual environment designed by Unity or Unreal Engine. Through this interface, the user concretely experiences the product or service.

[0277] Step 5:

[0278] Users interact with the device to view the provided VR / AR experience and evaluate the usefulness of the sales proposal. Input consists of impressions and thoughts about the product or service gained through the experience. User actions and feedback are collected by the device and recorded as qualitative data.

[0279] Step 6:

[0280] The server receives user feedback from the terminal and incorporates it into subsequent data analysis and proposal generation. The feedback is incorporated into the training dataset of the machine learning algorithm and treated as valuable data for improving model accuracy. The input is user feedback, and the output is the improved model prediction result. This enables more accurate and user-optimized proposals.

[0281] (Application Example 1)

[0282] 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."

[0283] Traditional customer service systems struggled to effectively provide personalized suggestions based on customer purchase history and preferences, and to allow customers to experience these suggestions in a virtual environment. Furthermore, the lack of means to incorporate customer feedback into future suggestions and provide a highly optimized product experience made improving customer satisfaction a challenge.

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

[0285] In this invention, the server includes means for collecting past sales information and customer behavior history from a storage device, means for predicting customer preferences and purchase behavior using a generation algorithm based on the collected information and creating individual sales proposals, and means for providing customers with a virtual experience of products and services using augmented reality or virtual reality technology based on the created proposals. Thereby, it becomes possible to effectively provide an optimized product experience for customers and reflect the customers' evaluations in the next information analysis.

[0286] A "storage device" is a device or system for storing digital data.

[0287] A "generation algorithm" is a computational method for analyzing patterns based on data and creating predictions and proposals according to specific purposes.

[0288] "Preference" is a concept referring to preferences based on an individual's interests and concerns.

[0289] "Virtual reality" is a technology that makes a user feel a real artificial environment generated using computer technology.

[0290] "Augmented reality" is a technology that overlays computer-generated information on the real-world environment for display.

[0291] "Virtual experience" is to provide a simulation of an experience that does not actually exist by using digital technology.

[0292] "Evaluation" is to aggregate the impressions and opinions obtained by an experiencer and judge the value.

[0293] "Information analysis" is a process of processing the collected data and extracting useful insights and patterns from it.

[0294] The system for implementing the present invention consists of a server that handles the main processing, a terminal for providing proposals to customers, and a user who operates the system.

[0295] The server first collects past sales information and behavioral history of customers stored in storage. This builds a data base for understanding customer preferences and purchasing patterns. Next, the server feeds this data to a generation algorithm, which uses a machine learning model to predict the most suitable products and services for each customer. Machine learning frameworks such as TensorFlow are suitable for this generation algorithm. The output of the generation algorithm is converted into customized sales proposals for each customer.

[0296] The terminal serves to provide customers with suggestions. Specifically, this terminal is a device equipped with augmented reality or virtual reality technology, such as smart glasses like Microsoft HoloLens. Using this, customers can actually experience the suggested products and services within the virtual store and visualize their use. This experience stimulates customer purchasing intent and provides a higher-level purchasing experience.

[0297] Users accept or provide feedback on experiences suggested through their devices. This feedback is sent from the device to the server and used to improve data analysis and suggestion generation in the future, leading to increased accuracy. This cycle enhances customer satisfaction.

[0298] As a concrete example, consider a scenario where a customer is choosing sports shoes in a virtual store. This customer's past purchase history shows a high frequency of buying running shoes. Based on this information, the server generates suggestions highlighting the latest running shoes and their features. The terminal displays these suggestions using augmented reality, and the customer is supported in making a purchase decision by virtually trying on the shoes from various angles. Customer feedback is used to improve future suggestions.

[0299] As an example of a prompt sentence for a generative AI model, an instruction such as "Based on customer purchase history data, generate an algorithm for new product proposals. Display the generated proposal content in AR, collect feedback, and reflect it in the next proposal." can be considered.

[0300] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0301] Step 1:

[0302] The server collects inputs such as past sales information and customer behavior history from the storage device. Based on this data, it constructs a dataset for grasping the customer's purchase pattern and prepares to supply it to the generative AI model.

[0303] Step 2:

[0304] The server passes the collected data to a generation algorithm and performs data analysis to predict each customer's preferences and purchase behavior using a machine learning model. Through this process, an output of a list of optimal products and services for each customer is generated. For this, a machine learning framework such as TensorFlow is used.

[0305] Step 3:

[0306] Based on the generated list of optimal products and services, the server creates individual sales proposals. Here, using a prompt sentence to clarify the features of the products and services, the proposal content is refined to prepare visualization data for the next stage.

[0307] Step 4:

[0308] Based on the sales proposal received from the server, the terminal presents the proposal content to the customer using augmented reality or virtual reality technology. The terminal constructs an environment through smart glasses such as Microsoft HoloLens where the customer can virtually experience the products and services, and visually embodies the proposal. The customer tries out the products based on the visualized proposal.

[0309] Step 5:

[0310] Users interact with the device to examine visual suggestions and compare them to their actual purchase intent. If the suggestion is appropriate, they enter feedback on the device and send it to the server. The feedback collected here is used as customer evaluation to improve future suggestions.

[0311] Step 6:

[0312] The server incorporates user feedback into subsequent data analysis and suggestion generation, updating the generating AI model to improve accuracy. This feedback processing enhances the personalization accuracy of suggestions, which can then be used to improve future customer suggestions.

[0313] 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.

[0314] This invention is a system that provides personalized sales proposals by utilizing user sales data, behavioral history, and emotional data. The system consists of a server, terminals, users, and an emotional engine.

[0315] First, the server collects historical sales data and customer behavior history from the company's database. This provides foundational data for understanding customer purchasing patterns. Furthermore, the server uses a generative model based on the collected data to predict customer preferences and purchasing intent. This model is comprised of machine learning algorithms, enabling detailed analysis of customers.

[0316] Next, the server generates individual sales proposals based on the analysis results. These proposals are dynamically adjusted by an emotion engine to adapt to the user's emotional state. The emotion engine recognizes the user's emotions in real time from their facial expressions and voice input, and optimizes the proposal content accordingly.

[0317] The devices receiving these proposals will use virtual reality (VR) or augmented reality (AR) technology to prepare the customer to experience the proposal. This experience will be transformed into interactive content that highlights the features of the product or service and allows the user to visually understand its value.

[0318] Users can experience this VR / AR through their devices and view content that reflects their interests. User reactions and feedback, along with emotional data, are sent to the server and recorded in a database. This information will then be used for future data analysis and sales proposal creation.

[0319] As a concrete example, consider a scenario where a customer is considering purchasing a new home appliance. The server selects an appropriate product based on the customer's past purchase history, and the terminal prepares a program that allows the customer to experience the product's features in VR. At this time, the emotion engine recognizes the customer's facial expressions and adjusts the experience to emphasize the points the customer shows interest in. By analyzing the user's actual reactions and understanding how the proposal was received by the customer, it becomes possible to develop even more accurate sales strategies.

[0320] In this way, the system aims to improve customer satisfaction and business results by recognizing and utilizing user emotions to provide a more appropriate and engaging sales experience.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The server accesses the company's database to collect each customer's past sales data and behavioral history. This collection includes customer purchase history, website visit history, and inquiry history. The collected data is converted to a standard format and stored in a way that is suitable for analysis.

[0324] Step 2:

[0325] The server inputs the collected data into a generative model to predict customer purchasing preferences and behavior. The generative model used here is based on machine learning algorithms. This model learns from past data patterns and forms the basis for new sales proposals.

[0326] Step 3:

[0327] Based on the analysis results, the server generates optimal sales proposals for each customer. These proposals address the customer's specific preferences and provide detailed explanations of recommended products and services, along with the reasons for selling them.

[0328] Step 4:

[0329] The emotion engine is activated and analyzes the emotional state of the user receiving the proposal in real time. The device uses the emotion engine to capture the user's facial expressions with a camera or to infer emotions from voice input. This emotional data is used to adjust sales proposals.

[0330] Step 5:

[0331] The device utilizes virtual reality (VR) or augmented reality (AR) technology to deliver personalized sales presentations to the user. These presentations are customized based on the user's emotional state and are presented as interactive content that enhances the visual experience of the product or service.

[0332] Step 6:

[0333] Users utilize VR / AR experiences provided through their devices to directly verify the features and benefits of the proposed products. This experience simulates realistic purchase scenarios, allowing users to gain a more concrete understanding of the product's usability and value.

[0334] Step 7:

[0335] After the experience, users input their thoughts and opinions as feedback via their device. This feedback includes their thoughts on the suggestions, points of interest, and areas for improvement.

[0336] Step 8:

[0337] The server integrates user feedback and sentiment data, and incorporates this information into subsequent data analysis. The feedback is stored in a database and used to improve the accuracy of future sales proposals.

[0338] (Example 2)

[0339] 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".

[0340] There is a need to improve the accuracy of personalized commercial recommendations and provide optimal experiences tailored to the user's emotional state in order to increase customer satisfaction and corporate sales. However, conventional systems do not fully utilize user behavioral data and emotional data, resulting in insufficient personalization of recommendations.

[0341] 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.

[0342] In this invention, the server includes means for collecting information on past sales and user behavior records from an information storage device; means for inferring user preferences and purchasing behavior using a generative model based on the collected information and generating individual commercial suggestions; and means for providing users with a virtual experience of goods or services using a virtual environment or augmented environment technology based on the generated suggestions. This makes it possible to provide a personalized experience that takes into account the user's emotional state, thereby improving customer satisfaction and corporate sales.

[0343] An "information storage device" is a device used to store and manage information such as past sales data and customer behavior records.

[0344] A "generative model" is a model that uses machine learning techniques to infer user preferences and purchasing behavior based on collected data.

[0345] A "virtual environment" is a system that uses computer technology to allow users to experience an environment different from the real world.

[0346] An "augmented environment" is a system that overlays digital information onto real-world information to provide users with new information.

[0347] An "emotion processing engine" is a device that has software or hardware functions to recognize the user's emotions and adjust the suggested content accordingly.

[0348] A "commercial proposal" is an introduction to products or services presented to users, and information intended to encourage their purchase.

[0349] This invention is a system that analyzes users' past sales data, behavioral records, and emotional data to provide personalized commercial recommendations. The system comprises a server, terminals, users, and an emotional processing engine.

[0350] The server uses an information storage device to collect sales-related information and user behavior records within the company. This information is retrieved and collected using data management techniques such as SQL queries. After collection, the data is analyzed by a generative model to predict user preferences and purchase intent. The generative model can use commonly used machine learning methods such as TensorFlow and PyTorch, and is a mechanism that improves prediction accuracy by learning from vast amounts of data.

[0351] The terminal receives personalized commercial proposals from the server and delivers experiences to users using virtual and augmented environments. Specifically, it uses content creation tools such as Unity and Unreal Engine to create a space where users can visually and interactively experience the feel and features of a product. This experience plays a crucial role in helping users deepen their understanding of the product or service.

[0352] Users can view information that reflects their interests based on the experiences provided through their device. The emotions and reactions expressed during this process are recognized by an emotion processing engine, and the content of the suggestions is dynamically adjusted accordingly. The emotion processing engine is equipped with a facial recognition camera and a voice recognition microphone, enabling real-time analysis of emotions.

[0353] As a concrete example, consider a scenario where a user is trying to purchase a specific home appliance. The server provides information on related products based on the user's past purchasing behavior, and the terminal prepares a virtual experience that shows the product's features in detail. The user can try out the product through VR or AR, and an emotion processing engine identifies the user's interests from their facial expressions and voice, highlighting the points that piqued their interest.

[0354] An example of a prompt message would be: "Use this user's past behavioral and sentiment data to identify the product they are most likely to purchase next."

[0355] Thus, the present invention aims to improve customer satisfaction and business performance by realizing more attractive and personalized commercial proposals through detailed recognition and response to users' emotions and behavioral patterns.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Step 1:

[0358] The server retrieves users' past sales information and behavioral records from an information storage device. Inputs include vast amounts of transaction history and website behavioral data stored in the company's database. This data is retrieved via SQL queries and formatted using virtual tables. This process provides the foundational data needed to clarify users' purchasing patterns.

[0359] Step 2:

[0360] The server supplies the collected data to a generating AI model that infers the user's preferences and purchasing intent. Because this model uses machine learning algorithms, it learns and outputs the user's behavioral characteristics from newly provided data. Specifically, a neural network using TensorFlow processes the input data and quantifies the likelihood of purchasing a particular product. The output is the predicted preferences and purchasing intent.

[0361] Step 3:

[0362] The server generates personalized commercial proposals based on the prediction results. These proposals are based on data derived from the generative model used and include the selection of the most suitable products and services for the user. Here, prompt statements are created and incorporated into the commercial proposals. The output is a customized proposal statement provided to the user.

[0363] Step 4:

[0364] The server sends the generated proposal to the terminal, which receives it and presents it to the user through a virtual or extended environment. The input consists of commercial proposal content, which is then transformed into a visual experience using content creation tools such as Unity. This allows users to visualize the promotion of products and services.

[0365] Step 5:

[0366] Users view suggested virtual experiences using their devices and take actions based on their interests and preferences. The input is the VR or AR experience provided by the device, and the output is emotional data as a reaction. The user's facial expressions and actions are captured by the camera and microphone, and this information is used for future suggestions.

[0367] Step 6:

[0368] The server then stores the response data collected from users back into the data storage device. This strengthens the dataset used for future commercial proposals and training generative AI models. This feedback loop continuously improves the accuracy of the proposals.

[0369] (Application Example 2)

[0370] 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."

[0371] Traditional sales proposals, while based on customer purchase history and preferences, failed to consider real-time emotional states, making it difficult to accurately address individual customer needs. Furthermore, the practical constraints of the in-store customer experience limited the appeal of products and services. Additionally, there was a lack of mechanisms to effectively incorporate feedback into sales proposals. As a result, improving customer satisfaction and streamlining sales promotion were significant challenges.

[0372] 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.

[0373] In this invention, the server includes a unit that collects past sales data and customer behavior history from a database; a unit that uses a generative model based on the collected information to predict user preferences and purchasing behavior and generate individual sales proposals; and a unit that uses augmented reality technology to provide users with a virtual experience of products and services based on the generated proposals. This enables personalized proposals through real-time emotion recognition, thereby improving the customer experience in stores.

[0374] "Past sales data" refers to records of products and services that users have previously purchased, and serves as the basis for analyzing customer purchasing trends.

[0375] "Behavioral history" refers to a record of a customer's actions online or in stores, and is information that helps understand the decision-making process leading up to a purchase.

[0376] A "database" is an aggregated information system for systematically storing collected data and for efficiently managing and retrieving it.

[0377] A "generative model" is a computational model that uses machine learning algorithms to analyze customer preferences and purchasing behavior, and predict the likelihood of future purchases.

[0378] Augmented reality technology is a technique that overlays digital information onto the real world's field of view, and is used to enhance the user's visual and immersive experience.

[0379] "Emotional state" refers to the psychological state analyzed in real time from the user's facial expressions and voice, and is information necessary to evaluate customer interest and acceptance.

[0380] A "display device for assisting customers" is a digital display device used by store staff to provide customers with information about products and services.

[0381] "Feedback" refers to the reactions and opinions collected from users, and it is important information that is analyzed and reflected in future sales strategies.

[0382] The system for implementing this invention mainly consists of three components: a server, a terminal, and a user. The server collects past sales data and behavioral history of customers from a database. This includes customer profiles, purchase history, and website visit records. The server then uses a generative AI model based on the collected data to predict customer preferences and purchasing behavior. This model performs detailed data analysis using machine learning algorithms to identify products and services suitable for the customer's next purchase.

[0383] Next, the server uses the generated data to create personalized suggestions, leveraging virtual reality (VR) or augmented reality (AR) technologies implemented by the device. The device analyzes the user's facial expressions and voice through an emotion engine that performs real-time emotion recognition. This allows the suggestions to adapt to the user's emotional state, providing a more personalized experience.

[0384] Users receive these customized suggestions through smart glasses, which are display devices used for customer interaction within the store. This rapid emotion recognition and personalized information presentation allows customers to instantly understand product features and determine if they match their interests. This feedback is collected from users in real time, sent to a server, and used for future data analysis and improvement of sales suggestions.

[0385] For example, if a customer is considering purchasing a smartphone in a store, a customer service display can facilitate effective sales by suggesting models that are suitable for the customer based on their past purchase history. An example of a prompt message would be, "Suggest new smartphones that the customer might be interested in. Analyze past purchase history and current sentiment to provide personalized recommendations."

[0386] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0387] Step 1:

[0388] The server collects historical sales data and customer behavior history from the database. This collection includes information such as customer purchase history and website visit records. The input data is organized and converted into a format that is easy for the generative AI model to analyze. Specifically, data cleansing is performed to output a neat dataset with noise removed.

[0389] Step 2:

[0390] The server uses a generative AI model, taking a well-organized dataset as input, to predict customer preferences and purchasing behavior. Here, machine learning algorithms play a key role in deriving the customer's future purchasing potential. This model extracts patterns from the data and predicts which products and services will attract customer interest. As an output of this process, personalized sales proposals are generated.

[0391] Step 3:

[0392] The server creates virtual reality (VR) or augmented reality (AR) content for the terminal to run, based on the prediction results and sales proposals. In this step, the visual content is designed to highlight the features of the proposed products and services. The generated content is then converted and prepared for use on the terminal.

[0393] Step 4:

[0394] Users wear smart glasses in the store and experience AR content provided via a device. An emotion engine analyzes the user's facial expressions and voice in real time, dynamically adjusting the content display based on the user's emotional state. Through this process, users can visually receive information tailored to their interests.

[0395] Step 5:

[0396] Users provide reactions and feedback on their experiences. The device collects this feedback and sends it to the server. Based on the feedback input, it is output as feedback information stored in the database to be used for future data analysis and improvement of sales proposals.

[0397] 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.

[0398] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] 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.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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".

[0413] This invention provides a system that enables personalized sales proposals by utilizing customer data. This system mainly consists of a server, terminals, and users.

[0414] First, the server accesses the database to collect past sales data and behavioral history of customers. This provides foundational data for understanding customer purchasing patterns and preferences. Based on this data, the server uses a generative model to predict each customer's preferences and purchasing intent. The generative model is an algorithm that analyzes the collected data to select the most suitable products and services for each customer.

[0415] Next, the server generates individual sales proposals based on the analysis results. These proposals include the optimal product and related explanations to gain the customer's approval. The generated proposals also include a plan to visualize how the customer will actually use the product or service.

[0416] The device receiving this proposal has the capability to allow customers to experience the proposal using virtual reality (VR) or augmented reality (AR) technology. Specifically, it provides a realistic purchasing experience by visually showing customers the features of the product or service and simulating actual usage scenarios.

[0417] Meanwhile, users operate their devices and, through the provided virtual and augmented reality experiences, carefully review the details of the suggested products and services. User feedback is sent to the server via the device. This feedback plays a crucial role in subsequent data analysis and suggestion generation, leading to further improvements in accuracy.

[0418] As a concrete example, consider a telecommunications service company proposing a new internet plan to a specific customer. This customer has a history of preferring high-speed data services. The server analyzes this history and proposes a new plan that matches the customer's usage patterns. The terminal allows the customer to experience this plan through VR / AR technology, visualizing the speed and benefits that the new plan offers. After the user experiences this plan and provides feedback, the system incorporates this feedback to further improve future proposals and experiences.

[0419] This allows users to have a better purchasing experience, and enables telecommunications service companies to achieve increased customer satisfaction and sales.

[0420] The following describes the processing flow.

[0421] Step 1:

[0422] The server accesses the company's database and collects each customer's past sales data and behavioral history. This data includes purchase history, inquiry history, website visit history, and more.

[0423] Step 2:

[0424] The server formats the collected data and inputs it into a generative model. This generative model is designed to predict customer preferences and purchasing behavior using machine learning algorithms.

[0425] Step 3:

[0426] The server generates optimal sales proposals for each customer based on the analysis results of the generative model. These proposals detail the products and services recommended for the customer, along with the reasons why.

[0427] Step 4:

[0428] The server sends the generated proposal to the relevant terminal. The terminal receives this proposal data and uses virtual reality or augmented reality technology to prepare a visual presentation for the customer.

[0429] Step 5:

[0430] Based on the suggestions, the device generates interactive content that allows customers to experience products and services within a virtual environment. This includes features such as the ability to view products from a 360-degree perspective and simulations using the services.

[0431] Step 6:

[0432] Users can experience VR / AR through their devices while reviewing the features of the suggested products and services. This experience allows users to gain a deeper understanding of the actual product value and increase their desire to purchase.

[0433] Step 7:

[0434] Users provide feedback via their devices after the experience ends, sharing their thoughts and opinions. This feedback includes aspects they found interesting and areas for improvement.

[0435] Step 8:

[0436] The server analyzes user feedback data and stores it in a database. This data is used to improve the accuracy of future analyses and sales proposals.

[0437] (Example 1)

[0438] 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."

[0439] Traditional marketing methods often involve uniform sales proposals, making it difficult to provide personalized offers that adequately address diverse customer preferences and purchasing behaviors. Furthermore, opportunities for customers to actually experience and understand the features of products and services are limited, sometimes leading to a lack of understanding or mismatches. Therefore, to improve customer satisfaction and maximize sales, a new system is needed that provides proposals and experiences optimized for each customer.

[0440] 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.

[0441] In this invention, the server includes means for acquiring past sales data and consumer behavior history from an information storage device; means for predicting consumer preferences and purchasing behavior using a generated artificial intelligence model based on the acquired information and creating individual sales proposals; and means for providing consumers with a virtual experience of products and services using virtual reality or augmented reality technology based on the created proposals. This makes it possible to provide optimized sales proposals to each consumer, deepen their understanding of products and services, and achieve high customer satisfaction.

[0442] "Sales data" refers to information that describes the details of transactions and sales history that occur when a company sells goods or services to customers.

[0443] An "information storage device" is a computer system or related equipment for efficiently and securely storing and managing data.

[0444] A "generative artificial intelligence model" is a program or system that uses machine learning algorithms to generate new information or predictions based on consumer data.

[0445] "Consumer preferences" refer to the tendencies of individual consumers' likes and preferences for specific products or services.

[0446] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take when purchasing goods or services.

[0447] "Virtual reality technology" is a method that uses computer technology to generate and present realistic experiences to users visually and audibly.

[0448] Augmented reality technology is a technology that extends our perception of reality by overlaying computer-generated graphics and data onto information from the real world.

[0449] A "virtual experience" is a simulation that uses virtual reality or augmented reality technology to allow users to feel as if they are actually using a product or service.

[0450] "Opinions" refer to the evaluations and impressions that consumers have of the products and services provided, and are important information that serves as valuable feedback for future product and service improvements.

[0451] "Information analysis" is a series of processes that involve analyzing acquired data and feedback in detail to understand trends and patterns and use them to aid in decision-making.

[0452] This invention provides a system comprising a server, terminals, and users for making personalized sales proposals.

[0453] The server first accesses the data storage device to retrieve historical sales data and consumer behavior history. This information is extracted from an SQL database management system (e.g., MySQL, PostgreSQL) and used as data for data analysis. Next, the server inputs this information into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. The generative model is built using a machine learning framework (e.g., TensorFlow, PyTorch) and generates optimal suggestions for each consumer.

[0454] The generated sales proposals are delivered to the user through a device using virtual reality (VR) or augmented reality (AR) technology. The device uses a VR headset or AR glasses to visualize the features of the product or service in real time. For example, in a scenario where an internet service provider proposes a new high-speed data plan, the device can allow consumers to experience the benefits of the connection speed offered by that plan. This experience is built using development platforms such as Unity or Unreal Engine.

[0455] Users interact with the device and review the details of the products and services suggested through the provided experience. User feedback is sent to the server via the device and plays a crucial role in subsequent analyses. This feedback is used to improve the accuracy of the system's recommendations.

[0456] As a concrete example, a prompt message might say, "Based on the customer's past purchase history, please suggest the product they are most likely to purchase next." In this way, the present invention aims to improve sales potential and customer satisfaction by providing personalized suggestions and experiences that are tailored to consumer needs.

[0457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0458] Step 1:

[0459] The server retrieves historical sales data and consumer behavior history from the data storage device. The input at this stage is information queried from the database using SQL queries. The server then formats this retrieved raw data into structured data and temporarily stores it. The output is the formatted data that forms the basis for data analysis.

[0460] Step 2:

[0461] The server inputs formatted data into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. This data processing is performed using a machine learning framework, estimating future behavior based on past consumer behavior. The output is predictive data including each consumer's purchasing intent and preferences. This forms the basis for the server to generate personalized sales proposals.

[0462] Step 3:

[0463] The server creates personalized sales proposals for individual consumers based on predictive data. This proposal generation process uses a generative AI model to create proposals in natural language that are easy for consumers to understand. The input is predictive data, and the output is an attractive proposal document tailored to each consumer. For example, a proposal might be something like, "Would you like to improve your daily digital experience with a high-speed data plan?"

[0464] Step 4:

[0465] The device delivers the generated proposal to the user using virtual reality (VR) or augmented reality (AR) technology. At this stage, the proposal document is converted into visual content, providing the user with an interactive experience. The input is the proposal document, and the output is a virtual environment designed by Unity or Unreal Engine. Through this interface, the user concretely experiences the product or service.

[0466] Step 5:

[0467] Users interact with the device to view the provided VR / AR experience and evaluate the usefulness of the sales proposal. Input consists of impressions and thoughts about the product or service gained through the experience. User actions and feedback are collected by the device and recorded as qualitative data.

[0468] Step 6:

[0469] The server receives user feedback from the terminal and incorporates it into subsequent data analysis and proposal generation. The feedback is incorporated into the training dataset of the machine learning algorithm and treated as valuable data for improving model accuracy. The input is user feedback, and the output is the improved model prediction result. This enables more accurate and user-optimized proposals.

[0470] (Application Example 1)

[0471] 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."

[0472] Traditional customer service systems struggled to effectively provide personalized suggestions based on customer purchase history and preferences, and to allow customers to experience these suggestions in a virtual environment. Furthermore, the lack of means to incorporate customer feedback into future suggestions and provide a highly optimized product experience made improving customer satisfaction a challenge.

[0473] 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.

[0474] In this invention, the server includes means for collecting past sales information and customer behavior history from a storage device; means for predicting customer preferences and purchasing behavior using a generation algorithm based on the collected information and creating individual sales proposals; and means for providing customers with a virtual experience of products and services using augmented reality or virtual reality technology based on the created proposals. This makes it possible to effectively provide customers with an optimized product experience and to reflect customer evaluations in subsequent information analysis.

[0475] A "storage device" is a device or system used to store digital data.

[0476] A "generative algorithm" is a computational method that analyzes patterns based on data to create predictions or suggestions tailored to a specific purpose.

[0477] "Preference" is a concept that refers to an individual's preferences based on their interests and concerns.

[0478] "Virtual reality" is a technology that uses computer technology to create artificial environments that make the user feel like they are experiencing them in real life.

[0479] Augmented reality is a technology that overlays computer-generated information onto the real world environment.

[0480] A "virtual experience" is the use of digital technology to provide a simulation of an experience that does not exist in reality.

[0481] "Evaluation" is the process of judging value by aggregating the impressions and opinions gained by those who have experienced something.

[0482] "Information analysis" is the process of processing collected data and extracting useful insights and patterns from it.

[0483] The system for implementing the present invention consists of a server that handles the main processing, a terminal for providing proposals to customers, and a user who operates the system.

[0484] The server first collects past sales information and behavioral history of customers stored in storage. This builds a data base for understanding customer preferences and purchasing patterns. Next, the server feeds this data to a generation algorithm, which uses a machine learning model to predict the most suitable products and services for each customer. Machine learning frameworks such as TensorFlow are suitable for this generation algorithm. The output of the generation algorithm is converted into customized sales proposals for each customer.

[0485] The terminal serves to provide customers with suggestions. Specifically, this terminal is a device equipped with augmented reality or virtual reality technology, such as smart glasses like Microsoft HoloLens. Using this, customers can actually experience the suggested products and services within the virtual store and visualize their use. This experience stimulates customer purchasing intent and provides a higher-level purchasing experience.

[0486] Users accept or provide feedback on experiences suggested through their devices. This feedback is sent from the device to the server and used to improve data analysis and suggestion generation in the future, leading to increased accuracy. This cycle enhances customer satisfaction.

[0487] As a concrete example, consider a scenario where a customer is choosing sports shoes in a virtual store. This customer's past purchase history shows a high frequency of buying running shoes. Based on this information, the server generates suggestions highlighting the latest running shoes and their features. The terminal displays these suggestions using augmented reality, and the customer is supported in making a purchase decision by virtually trying on the shoes from various angles. Customer feedback is used to improve future suggestions.

[0488] An example of a prompt for a generative AI model might be: "Generate an algorithm for suggesting new products based on customer purchase history data. Display the generated suggestions using AR, collect feedback, and incorporate it into future suggestions."

[0489] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0490] Step 1:

[0491] The server collects input from storage devices, including past sales information and customer behavior history. Based on this data, it builds a dataset to understand customer purchasing patterns and prepares it to be supplied to a generative AI model.

[0492] Step 2:

[0493] The server passes the collected data to a generation algorithm, which then uses machine learning models to perform data analysis that predicts individual customer preferences and purchasing behavior. This process generates an output in the form of a list of products and services best suited to each customer. This uses machine learning frameworks such as TensorFlow.

[0494] Step 3:

[0495] The server creates individual sales proposals based on the generated list of optimal products and services. Here, prompts are used to clarify the features of the products and services, refining the proposals and preparing data for visualization in the next stage.

[0496] Step 4:

[0497] The terminal uses augmented reality or virtual reality technology to present sales proposals to customers based on proposals received from the server. The terminal creates an environment where customers can virtually experience products and services through smart glasses such as Microsoft HoloLens, visually realizing the proposals. Customers then try out the products based on the visualized proposals.

[0498] Step 5:

[0499] Users interact with the device to examine visual suggestions and compare them to their actual purchase intent. If the suggestion is appropriate, they enter feedback on the device and send it to the server. The feedback collected here is used as customer evaluation to improve future suggestions.

[0500] Step 6:

[0501] The server incorporates user feedback into subsequent data analysis and suggestion generation, updating the generating AI model to improve accuracy. This feedback processing enhances the personalization accuracy of suggestions, which can then be used to improve future customer suggestions.

[0502] 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.

[0503] This invention is a system that provides personalized sales proposals by utilizing user sales data, behavioral history, and emotional data. The system consists of a server, terminals, users, and an emotional engine.

[0504] First, the server collects historical sales data and customer behavior history from the company's database. This provides foundational data for understanding customer purchasing patterns. Furthermore, the server uses a generative model based on the collected data to predict customer preferences and purchasing intent. This model is comprised of machine learning algorithms, enabling detailed analysis of customers.

[0505] Next, the server generates individual sales proposals based on the analysis results. These proposals are dynamically adjusted by an emotion engine to adapt to the user's emotional state. The emotion engine recognizes the user's emotions in real time from their facial expressions and voice input, and optimizes the proposal content accordingly.

[0506] The devices receiving these proposals will use virtual reality (VR) or augmented reality (AR) technology to prepare the customer to experience the proposal. This experience will be transformed into interactive content that highlights the features of the product or service and allows the user to visually understand its value.

[0507] Users can experience this VR / AR through their devices and view content that reflects their interests. User reactions and feedback, along with emotional data, are sent to the server and recorded in a database. This information will then be used for future data analysis and sales proposal creation.

[0508] As a concrete example, consider a scenario where a customer is considering purchasing a new home appliance. The server selects an appropriate product based on the customer's past purchase history, and the terminal prepares a program that allows the customer to experience the product's features in VR. At this time, the emotion engine recognizes the customer's facial expressions and adjusts the experience to emphasize the points the customer shows interest in. By analyzing the user's actual reactions and understanding how the proposal was received by the customer, it becomes possible to develop even more accurate sales strategies.

[0509] In this way, the system aims to improve customer satisfaction and business results by recognizing and utilizing user emotions to provide a more appropriate and engaging sales experience.

[0510] The following describes the processing flow.

[0511] Step 1:

[0512] The server accesses the company's database to collect each customer's past sales data and behavioral history. This collection includes customer purchase history, website visit history, and inquiry history. The collected data is converted to a standard format and stored in a way that is suitable for analysis.

[0513] Step 2:

[0514] The server inputs the collected data into a generative model to predict customer purchasing preferences and behavior. The generative model used here is based on machine learning algorithms. This model learns from past data patterns and forms the basis for new sales proposals.

[0515] Step 3:

[0516] Based on the analysis results, the server generates optimal sales proposals for each customer. These proposals address the customer's specific preferences and provide detailed explanations of recommended products and services, along with the reasons for selling them.

[0517] Step 4:

[0518] The emotion engine is activated and analyzes the emotional state of the user receiving the proposal in real time. The device uses the emotion engine to capture the user's facial expressions with a camera or to infer emotions from voice input. This emotional data is used to adjust sales proposals.

[0519] Step 5:

[0520] The device utilizes virtual reality (VR) or augmented reality (AR) technology to deliver personalized sales presentations to the user. These presentations are customized based on the user's emotional state and are presented as interactive content that enhances the visual experience of the product or service.

[0521] Step 6:

[0522] Users utilize VR / AR experiences provided through their devices to directly verify the features and benefits of the proposed products. This experience simulates realistic purchase scenarios, allowing users to gain a more concrete understanding of the product's usability and value.

[0523] Step 7:

[0524] After the experience, users input their thoughts and opinions as feedback via their device. This feedback includes their thoughts on the suggestions, points of interest, and areas for improvement.

[0525] Step 8:

[0526] The server integrates user feedback and sentiment data, and incorporates this information into subsequent data analysis. The feedback is stored in a database and used to improve the accuracy of future sales proposals.

[0527] (Example 2)

[0528] 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."

[0529] There is a need to improve the accuracy of personalized commercial recommendations and provide optimal experiences tailored to the user's emotional state in order to increase customer satisfaction and corporate sales. However, conventional systems do not fully utilize user behavioral data and emotional data, resulting in insufficient personalization of recommendations.

[0530] 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.

[0531] In this invention, the server includes means for collecting information on past sales and user behavior records from an information storage device; means for inferring user preferences and purchasing behavior using a generative model based on the collected information and generating individual commercial suggestions; and means for providing users with a virtual experience of goods or services using a virtual environment or augmented environment technology based on the generated suggestions. This makes it possible to provide a personalized experience that takes into account the user's emotional state, thereby improving customer satisfaction and corporate sales.

[0532] An "information storage device" is a device used to store and manage information such as past sales data and customer behavior records.

[0533] A "generative model" is a model that uses machine learning techniques to infer user preferences and purchasing behavior based on collected data.

[0534] A "virtual environment" is a system that uses computer technology to allow users to experience an environment different from the real world.

[0535] An "augmented environment" is a system that overlays digital information onto real-world information to provide users with new information.

[0536] An "emotion processing engine" is a device that has software or hardware functions to recognize the user's emotions and adjust the suggested content accordingly.

[0537] A "commercial proposal" is an introduction to products or services presented to users, and information intended to encourage their purchase.

[0538] This invention is a system that analyzes users' past sales data, behavioral records, and emotional data to provide personalized commercial recommendations. The system comprises a server, terminals, users, and an emotional processing engine.

[0539] The server uses an information storage device to collect sales-related information and user behavior records within the company. This information is retrieved and collected using data management techniques such as SQL queries. After collection, the data is analyzed by a generative model to predict user preferences and purchase intent. The generative model can use commonly used machine learning methods such as TensorFlow and PyTorch, and is a mechanism that improves prediction accuracy by learning from vast amounts of data.

[0540] The terminal receives personalized commercial proposals from the server and delivers experiences to users using virtual and augmented environments. Specifically, it uses content creation tools such as Unity and Unreal Engine to create a space where users can visually and interactively experience the feel and features of a product. This experience plays a crucial role in helping users deepen their understanding of the product or service.

[0541] Users can view information that reflects their interests based on the experiences provided through their device. The emotions and reactions expressed during this process are recognized by an emotion processing engine, and the content of the suggestions is dynamically adjusted accordingly. The emotion processing engine is equipped with a facial recognition camera and a voice recognition microphone, enabling real-time analysis of emotions.

[0542] As a concrete example, consider a scenario where a user is trying to purchase a specific home appliance. The server provides information on related products based on the user's past purchasing behavior, and the terminal prepares a virtual experience that shows the product's features in detail. The user can try out the product through VR or AR, and an emotion processing engine identifies the user's interests from their facial expressions and voice, highlighting the points that piqued their interest.

[0543] An example of a prompt message would be: "Use this user's past behavioral and sentiment data to identify the product they are most likely to purchase next."

[0544] Thus, the present invention aims to improve customer satisfaction and business performance by realizing more attractive and personalized commercial proposals through detailed recognition and response to users' emotions and behavioral patterns.

[0545] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0546] Step 1:

[0547] The server retrieves users' past sales information and behavioral records from an information storage device. Inputs include vast amounts of transaction history and website behavioral data stored in the company's database. This data is retrieved via SQL queries and formatted using virtual tables. This process provides the foundational data needed to clarify users' purchasing patterns.

[0548] Step 2:

[0549] The server supplies the collected data to a generating AI model that infers the user's preferences and purchasing intent. Because this model uses machine learning algorithms, it learns and outputs the user's behavioral characteristics from newly provided data. Specifically, a neural network using TensorFlow processes the input data and quantifies the likelihood of purchasing a particular product. The output is the predicted preferences and purchasing intent.

[0550] Step 3:

[0551] The server generates personalized commercial proposals based on the prediction results. These proposals are based on data derived from the generative model used and include the selection of the most suitable products and services for the user. Here, prompt statements are created and incorporated into the commercial proposals. The output is a customized proposal statement provided to the user.

[0552] Step 4:

[0553] The server sends the generated proposal to the terminal, which receives it and presents it to the user through a virtual or extended environment. The input consists of commercial proposal content, which is then transformed into a visual experience using content creation tools such as Unity. This allows users to visualize the promotion of products and services.

[0554] Step 5:

[0555] Users view suggested virtual experiences using their devices and take actions based on their interests and preferences. The input is the VR or AR experience provided by the device, and the output is emotional data as a reaction. The user's facial expressions and actions are captured by the camera and microphone, and this information is used for future suggestions.

[0556] Step 6:

[0557] The server then stores the response data collected from users back into the data storage device. This strengthens the dataset used for future commercial proposals and training generative AI models. This feedback loop continuously improves the accuracy of proposals.

[0558] (Application Example 2)

[0559] 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."

[0560] Traditional sales proposals, while based on customer purchase history and preferences, failed to consider real-time emotional states, making it difficult to accurately address individual customer needs. Furthermore, the practical constraints of the in-store customer experience limited the appeal of products and services. Additionally, there was a lack of mechanisms to effectively incorporate feedback into sales proposals. As a result, improving customer satisfaction and streamlining sales promotion were significant challenges.

[0561] 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.

[0562] In this invention, the server includes a unit that collects past sales data and customer behavior history from a database; a unit that uses a generative model based on the collected information to predict user preferences and purchasing behavior and generate individual sales proposals; and a unit that uses augmented reality technology to provide users with a virtual experience of products and services based on the generated proposals. This enables personalized proposals through real-time emotion recognition, thereby improving the customer experience in stores.

[0563] "Past sales data" refers to records of products and services that users have previously purchased, and serves as the basis for analyzing customer purchasing trends.

[0564] "Behavioral history" refers to a record of a customer's actions online or in stores, and is information that helps understand the decision-making process leading up to a purchase.

[0565] A "database" is an aggregated information system for systematically storing collected data and for efficiently managing and retrieving it.

[0566] A "generative model" is a computational model that uses machine learning algorithms to analyze customer preferences and purchasing behavior, and predict the likelihood of future purchases.

[0567] Augmented reality technology is a technique that overlays digital information onto the real world's field of view, and is used to enhance the user's visual and immersive experience.

[0568] "Emotional state" refers to the psychological state analyzed in real time from the user's facial expressions and voice, and is information necessary to evaluate customer interest and acceptance.

[0569] A "display device for assisting customers" is a digital display device used by store staff to provide customers with information about products and services.

[0570] "Feedback" refers to the reactions and opinions collected from users, and it is important information that is analyzed and reflected in future sales strategies.

[0571] The system for implementing this invention mainly consists of three components: a server, a terminal, and a user. The server collects past sales data and behavioral history of customers from a database. This includes customer profiles, purchase history, and website visit records. The server then uses a generative AI model based on the collected data to predict customer preferences and purchasing behavior. This model performs detailed data analysis using machine learning algorithms to identify products and services suitable for the customer's next purchase.

[0572] Next, the server uses the generated data to create personalized suggestions, leveraging virtual reality (VR) or augmented reality (AR) technologies implemented by the device. The device analyzes the user's facial expressions and voice through an emotion engine that performs real-time emotion recognition. This allows the suggestions to adapt to the user's emotional state, providing a more personalized experience.

[0573] Users receive these customized suggestions through smart glasses, which are display devices used for customer interaction within the store. This rapid emotion recognition and personalized information presentation allows customers to instantly understand product features and determine if they match their interests. This feedback is collected from users in real time, sent to a server, and used for future data analysis and improvement of sales suggestions.

[0574] For example, if a customer is considering purchasing a smartphone in a store, a customer service display can facilitate effective sales by suggesting models that are suitable for the customer based on their past purchase history. An example of a prompt message would be, "Suggest new smartphones that the customer might be interested in. Analyze past purchase history and current sentiment to provide personalized recommendations."

[0575] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0576] Step 1:

[0577] The server collects historical sales data and customer behavior history from the database. This collection includes information such as customer purchase history and website visit records. The input data is organized and converted into a format that is easy for the generative AI model to analyze. Specifically, data cleansing is performed to output a neat dataset with noise removed.

[0578] Step 2:

[0579] The server uses a generative AI model, taking a well-organized dataset as input, to predict customer preferences and purchasing behavior. Here, machine learning algorithms play a key role in deriving the customer's future purchasing potential. This model extracts patterns from the data and predicts which products and services will attract customer interest. As an output of this process, personalized sales proposals are generated.

[0580] Step 3:

[0581] The server creates virtual reality (VR) or augmented reality (AR) content for the terminal to run, based on the prediction results and sales proposals. In this step, the visual content is designed to highlight the features of the proposed products and services. The generated content is then converted and prepared for use on the terminal.

[0582] Step 4:

[0583] Users wear smart glasses in the store and experience AR content provided via a device. An emotion engine analyzes the user's facial expressions and voice in real time, dynamically adjusting the content display based on the user's emotional state. Through this process, users can visually receive information tailored to their interests.

[0584] Step 5:

[0585] Users provide reactions and feedback on their experiences. The device collects this feedback and sends it to the server. Based on the feedback input, it is output as feedback information stored in the database to be used for future data analysis and improvement of sales proposals.

[0586] 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.

[0587] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0588] 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.

[0589] [Fourth Embodiment]

[0590] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0591] 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.

[0592] 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).

[0593] 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.

[0594] 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.

[0595] 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).

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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".

[0603] This invention provides a system that enables personalized sales proposals by utilizing customer data. This system mainly consists of a server, terminals, and users.

[0604] First, the server accesses the database to collect past sales data and behavioral history of customers. This provides foundational data for understanding customer purchasing patterns and preferences. Based on this data, the server uses a generative model to predict each customer's preferences and purchasing intent. The generative model is an algorithm that analyzes the collected data to select the most suitable products and services for each customer.

[0605] Next, the server generates individual sales proposals based on the analysis results. These proposals include the optimal product and related explanations to gain the customer's approval. The generated proposals also include a plan to visualize how the customer will actually use the product or service.

[0606] The device receiving this proposal has the capability to allow customers to experience the proposal using virtual reality (VR) or augmented reality (AR) technology. Specifically, it provides a realistic purchasing experience by visually showing customers the features of the product or service and simulating actual usage scenarios.

[0607] Meanwhile, users operate their devices and, through the provided virtual and augmented reality experiences, carefully review the details of the suggested products and services. User feedback is sent to the server via the device. This feedback plays a crucial role in subsequent data analysis and suggestion generation, leading to further improvements in accuracy.

[0608] As a concrete example, consider a telecommunications service company proposing a new internet plan to a specific customer. This customer has a history of preferring high-speed data services. The server analyzes this history and proposes a new plan that matches the customer's usage patterns. The terminal allows the customer to experience this plan through VR / AR technology, visualizing the speed and benefits that the new plan offers. After the user experiences this plan and provides feedback, the system incorporates this feedback to further improve future proposals and experiences.

[0609] This allows users to have a better purchasing experience, and enables telecommunications service companies to achieve increased customer satisfaction and sales.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] The server accesses the company's database and collects each customer's past sales data and behavioral history. This data includes purchase history, inquiry history, website visit history, and more.

[0613] Step 2:

[0614] The server formats the collected data and inputs it into a generative model. This generative model is designed to predict customer preferences and purchasing behavior using machine learning algorithms.

[0615] Step 3:

[0616] The server generates optimal sales proposals for each customer based on the analysis results of the generative model. These proposals detail the products and services recommended for the customer, along with the reasons why.

[0617] Step 4:

[0618] The server sends the generated proposal to the relevant terminal. The terminal receives this proposal data and uses virtual reality or augmented reality technology to prepare a visual presentation for the customer.

[0619] Step 5:

[0620] Based on the suggestions, the device generates interactive content that allows customers to experience products and services within a virtual environment. This includes features such as the ability to view products from a 360-degree perspective and simulations using the services.

[0621] Step 6:

[0622] Users can experience VR / AR through their devices while reviewing the features of the suggested products and services. This experience allows users to gain a deeper understanding of the actual product value and increase their desire to purchase.

[0623] Step 7:

[0624] Users provide feedback via their devices after the experience ends, sharing their thoughts and opinions. This feedback includes aspects they found interesting and areas for improvement.

[0625] Step 8:

[0626] The server analyzes user feedback data and stores it in a database. This data is used to improve the accuracy of future analyses and sales proposals.

[0627] (Example 1)

[0628] 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".

[0629] Traditional marketing methods often involve uniform sales proposals, making it difficult to provide personalized offers that adequately address diverse customer preferences and purchasing behaviors. Furthermore, opportunities for customers to actually experience and understand the features of products and services are limited, sometimes leading to a lack of understanding or mismatches. Therefore, to improve customer satisfaction and maximize sales, a new system is needed that provides proposals and experiences optimized for each customer.

[0630] 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.

[0631] In this invention, the server includes means for acquiring past sales data and consumer behavior history from an information storage device; means for predicting consumer preferences and purchasing behavior using a generated artificial intelligence model based on the acquired information and creating individual sales proposals; and means for providing consumers with a virtual experience of products and services using virtual reality or augmented reality technology based on the created proposals. This makes it possible to provide optimized sales proposals to each consumer, deepen their understanding of products and services, and achieve high customer satisfaction.

[0632] "Sales data" refers to information that describes the details of transactions and sales history that occur when a company sells goods or services to customers.

[0633] An "information storage device" is a computer system or related equipment for efficiently and securely storing and managing data.

[0634] A "generative artificial intelligence model" is a program or system that uses machine learning algorithms to generate new information or predictions based on consumer data.

[0635] "Consumer preferences" refer to the tendencies of individual consumers' likes and preferences for specific products or services.

[0636] "Purchasing behavior" refers to the series of actions and decision-making processes that consumers take when purchasing goods or services.

[0637] "Virtual reality technology" is a method that uses computer technology to generate and present realistic experiences to users visually and audibly.

[0638] Augmented reality technology is a technology that extends our perception of reality by overlaying computer-generated graphics and data onto information from the real world.

[0639] A "virtual experience" is a simulation that uses virtual reality or augmented reality technology to allow users to feel as if they are actually using a product or service.

[0640] "Opinions" refer to the evaluations and impressions that consumers have of the products and services provided, and are important information that serves as valuable feedback for future product and service improvements.

[0641] "Information analysis" is a series of processes that involve analyzing acquired data and feedback in detail to understand trends and patterns and use them to aid in decision-making.

[0642] This invention provides a system comprising a server, terminals, and users for making personalized sales proposals.

[0643] The server first accesses the data storage device to retrieve historical sales data and consumer behavior history. This information is extracted from an SQL database management system (e.g., MySQL, PostgreSQL) and used as data for data analysis. Next, the server inputs this information into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. The generative model is built using a machine learning framework (e.g., TensorFlow, PyTorch) and generates optimal suggestions for each consumer.

[0644] The generated sales proposals are delivered to the user through a device using virtual reality (VR) or augmented reality (AR) technology. The device uses a VR headset or AR glasses to visualize the features of the product or service in real time. For example, in a scenario where an internet service provider proposes a new high-speed data plan, the device can allow consumers to experience the benefits of the connection speed offered by that plan. This experience is built using development platforms such as Unity or Unreal Engine.

[0645] Users interact with the device and review the details of the products and services suggested through the provided experience. User feedback is sent to the server via the device and plays a crucial role in subsequent analyses. This feedback is used to improve the accuracy of the system's recommendations.

[0646] As a concrete example, a prompt message might say, "Based on the customer's past purchase history, please suggest the product they are most likely to purchase next." In this way, the present invention aims to improve sales potential and customer satisfaction by providing personalized suggestions and experiences that are tailored to consumer needs.

[0647] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0648] Step 1:

[0649] The server retrieves historical sales data and consumer behavior history from the data storage device. The input at this stage is information queried from the database using SQL queries. The server then formats this retrieved raw data into structured data and temporarily stores it. The output is the formatted data that forms the basis for data analysis.

[0650] Step 2:

[0651] The server inputs formatted data into a generative artificial intelligence model to predict consumer preferences and purchasing behavior. This data processing is performed using a machine learning framework, estimating future behavior based on past consumer behavior. The output is predictive data including each consumer's purchasing intent and preferences. This forms the basis for the server to generate personalized sales proposals.

[0652] Step 3:

[0653] The server creates personalized sales proposals for individual consumers based on predictive data. This proposal generation process uses a generative AI model to create proposals in natural language that are easy for consumers to understand. The input is predictive data, and the output is an attractive proposal document tailored to each consumer. For example, a proposal might be something like, "Would you like to improve your daily digital experience with a high-speed data plan?"

[0654] Step 4:

[0655] The device delivers the generated proposal to the user using virtual reality (VR) or augmented reality (AR) technology. At this stage, the proposal document is converted into visual content, providing the user with an interactive experience. The input is the proposal document, and the output is a virtual environment designed by Unity or Unreal Engine. Through this interface, the user concretely experiences the product or service.

[0656] Step 5:

[0657] Users interact with the device to view the provided VR / AR experience and evaluate the usefulness of the sales proposal. Input consists of impressions and thoughts about the product or service gained through the experience. User actions and feedback are collected by the device and recorded as qualitative data.

[0658] Step 6:

[0659] The server receives user feedback from the terminal and incorporates it into subsequent data analysis and proposal generation. The feedback is incorporated into the training dataset of the machine learning algorithm and treated as valuable data for improving model accuracy. The input is user feedback, and the output is the improved model prediction result. This enables more accurate and user-optimized proposals.

[0660] (Application Example 1)

[0661] 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".

[0662] Traditional customer service systems struggled to effectively provide personalized suggestions based on customer purchase history and preferences, and to allow customers to experience these suggestions in a virtual environment. Furthermore, the lack of means to incorporate customer feedback into future suggestions and provide a highly optimized product experience made improving customer satisfaction a challenge.

[0663] 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.

[0664] In this invention, the server includes means for collecting past sales information and customer behavior history from a storage device; means for predicting customer preferences and purchasing behavior using a generation algorithm based on the collected information and creating individual sales proposals; and means for providing customers with a virtual experience of products and services using augmented reality or virtual reality technology based on the created proposals. This makes it possible to effectively provide customers with an optimized product experience and to reflect customer evaluations in subsequent information analysis.

[0665] A "storage device" is a device or system used to store digital data.

[0666] A "generative algorithm" is a computational method that analyzes patterns based on data to create predictions or suggestions tailored to a specific purpose.

[0667] "Preference" is a concept that refers to an individual's preferences based on their interests and concerns.

[0668] "Virtual reality" is a technology that uses computer technology to create artificial environments that make the user feel like they are experiencing them in real life.

[0669] Augmented reality is a technology that overlays computer-generated information onto the real world environment.

[0670] A "virtual experience" is the use of digital technology to provide a simulation of an experience that does not exist in reality.

[0671] "Evaluation" is the process of judging value by aggregating the impressions and opinions gained by those who have experienced something.

[0672] "Information analysis" is the process of processing collected data and extracting useful insights and patterns from it.

[0673] The system for implementing the present invention consists of a server that handles the main processing, a terminal for providing proposals to customers, and a user who operates the system.

[0674] The server first collects past sales information and behavioral history of customers stored in storage. This builds a data base for understanding customer preferences and purchasing patterns. Next, the server feeds this data to a generation algorithm, which uses a machine learning model to predict the most suitable products and services for each customer. Machine learning frameworks such as TensorFlow are suitable for this generation algorithm. The output of the generation algorithm is converted into customized sales proposals for each customer.

[0675] The terminal serves to provide customers with suggestions. Specifically, this terminal is a device equipped with augmented reality or virtual reality technology, such as smart glasses like Microsoft HoloLens. Using this, customers can actually experience the suggested products and services within the virtual store and visualize their use. This experience stimulates customer purchasing intent and provides a higher-level purchasing experience.

[0676] Users accept or provide feedback on experiences suggested through their devices. This feedback is sent from the device to the server and used to improve data analysis and suggestion generation in the future, leading to increased accuracy. This cycle enhances customer satisfaction.

[0677] As a concrete example, consider a scenario where a customer is choosing sports shoes in a virtual store. This customer's past purchase history shows a high frequency of buying running shoes. Based on this information, the server generates suggestions highlighting the latest running shoes and their features. The terminal displays these suggestions using augmented reality, and the customer is supported in making a purchase decision by virtually trying on the shoes from various angles. Customer feedback is used to improve future suggestions.

[0678] An example of a prompt for a generative AI model might be: "Generate an algorithm for suggesting new products based on customer purchase history data. Display the generated suggestions using AR, collect feedback, and incorporate it into future suggestions."

[0679] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0680] Step 1:

[0681] The server collects input from storage devices, including past sales information and customer behavior history. Based on this data, it builds a dataset to understand customer purchasing patterns and prepares it to be supplied to a generative AI model.

[0682] Step 2:

[0683] The server passes the collected data to a generation algorithm, which then uses machine learning models to perform data analysis that predicts individual customer preferences and purchasing behavior. This process generates an output in the form of a list of products and services best suited to each customer. This uses machine learning frameworks such as TensorFlow.

[0684] Step 3:

[0685] The server creates individual sales proposals based on the generated list of optimal products and services. Here, prompts are used to clarify the features of the products and services, refining the proposals and preparing data for visualization in the next stage.

[0686] Step 4:

[0687] The terminal uses augmented reality or virtual reality technology to present sales proposals to customers based on proposals received from the server. The terminal creates an environment where customers can virtually experience products and services through smart glasses such as Microsoft HoloLens, visually realizing the proposals. Customers then try out the products based on the visualized proposals.

[0688] Step 5:

[0689] Users interact with the device to examine visual suggestions and compare them to their actual purchase intent. If the suggestion is appropriate, they enter feedback on the device and send it to the server. The feedback collected here is used as customer evaluation to improve future suggestions.

[0690] Step 6:

[0691] The server incorporates user feedback into subsequent data analysis and suggestion generation, updating the generating AI model to improve accuracy. This feedback process enhances the personalization accuracy of suggestions, which can then be used to improve future customer suggestions.

[0692] 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.

[0693] This invention is a system that provides personalized sales proposals by utilizing user sales data, behavioral history, and emotional data. The system consists of a server, terminals, users, and an emotional engine.

[0694] First, the server collects historical sales data and customer behavior history from the company's database. This provides foundational data for understanding customer purchasing patterns. Furthermore, the server uses a generative model based on the collected data to predict customer preferences and purchasing intent. This model is comprised of machine learning algorithms, enabling detailed analysis of customers.

[0695] Next, the server generates individual sales proposals based on the analysis results. These proposals are dynamically adjusted by an emotion engine to adapt to the user's emotional state. The emotion engine recognizes the user's emotions in real time from their facial expressions and voice input, and optimizes the proposal content accordingly.

[0696] The devices receiving these proposals will use virtual reality (VR) or augmented reality (AR) technology to prepare the customer to experience the proposal. This experience will be transformed into interactive content that highlights the features of the product or service and allows the user to visually understand its value.

[0697] Users can experience this VR / AR through their devices and view content that reflects their interests. User reactions and feedback, along with emotional data, are sent to the server and recorded in a database. This information will then be used for future data analysis and sales proposal creation.

[0698] As a concrete example, consider a scenario where a customer is considering purchasing a new home appliance. The server selects an appropriate product based on the customer's past purchase history, and the terminal prepares a program that allows the customer to experience the product's features in VR. At this time, the emotion engine recognizes the customer's facial expressions and adjusts the experience to emphasize the points the customer shows interest in. By analyzing the user's actual reactions and understanding how the proposal was received by the customer, it becomes possible to develop even more accurate sales strategies.

[0699] In this way, the system aims to improve customer satisfaction and business results by recognizing and utilizing user emotions to provide a more appropriate and engaging sales experience.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] The server accesses the company's database to collect each customer's past sales data and behavioral history. This collection includes customer purchase history, website visit history, and inquiry history. The collected data is converted to a standard format and stored in a way that is suitable for analysis.

[0703] Step 2:

[0704] The server inputs the collected data into a generative model to predict customer purchasing preferences and behavior. The generative model used here is based on machine learning algorithms. This model learns from past data patterns and forms the basis for new sales proposals.

[0705] Step 3:

[0706] Based on the analysis results, the server generates optimal sales proposals for each customer. These proposals address the customer's specific preferences and provide detailed explanations of recommended products and services, along with the reasons for selling them.

[0707] Step 4:

[0708] The emotion engine is activated and analyzes the emotional state of the user receiving the proposal in real time. The device uses the emotion engine to capture the user's facial expressions with a camera or to infer emotions from voice input. This emotional data is used to adjust sales proposals.

[0709] Step 5:

[0710] The device utilizes virtual reality (VR) or augmented reality (AR) technology to deliver personalized sales presentations to the user. These presentations are customized based on the user's emotional state and are presented as interactive content that enhances the visual experience of the product or service.

[0711] Step 6:

[0712] Users utilize VR / AR experiences provided through their devices to directly verify the features and benefits of the proposed products. This experience simulates realistic purchase scenarios, allowing users to gain a more concrete understanding of the product's usability and value.

[0713] Step 7:

[0714] After the experience, users input their thoughts and opinions as feedback via their device. This feedback includes their thoughts on the suggestions, points of interest, and areas for improvement.

[0715] Step 8:

[0716] The server integrates user feedback and sentiment data, and incorporates this information into subsequent data analysis. The feedback is stored in a database and used to improve the accuracy of future sales proposals.

[0717] (Example 2)

[0718] 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".

[0719] There is a need to improve the accuracy of personalized commercial recommendations and provide optimal experiences tailored to the user's emotional state in order to increase customer satisfaction and corporate sales. However, conventional systems do not fully utilize user behavioral data and emotional data, resulting in insufficient personalization of recommendations.

[0720] 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.

[0721] In this invention, the server includes means for collecting information on past sales and user behavior records from an information storage device; means for inferring user preferences and purchasing behavior using a generative model based on the collected information and generating individual commercial suggestions; and means for providing users with a virtual experience of goods or services using a virtual environment or augmented environment technology based on the generated suggestions. This makes it possible to provide a personalized experience that takes into account the user's emotional state, thereby improving customer satisfaction and corporate sales.

[0722] An "information storage device" is a device used to store and manage information such as past sales data and customer behavior records.

[0723] A "generative model" is a model that uses machine learning techniques to infer user preferences and purchasing behavior based on collected data.

[0724] A "virtual environment" is a system that uses computer technology to allow users to experience an environment different from the real world.

[0725] An "augmented environment" is a system that overlays digital information onto real-world information to provide users with new information.

[0726] An "emotion processing engine" is a device that has software or hardware functions to recognize the user's emotions and adjust the suggested content accordingly.

[0727] A "commercial proposal" is an introduction to products or services presented to users, and information intended to encourage their purchase.

[0728] This invention is a system that analyzes users' past sales data, behavioral records, and emotional data to provide personalized commercial recommendations. The system comprises a server, terminals, users, and an emotional processing engine.

[0729] The server uses an information storage device to collect sales-related information and user behavior records within the company. This information is retrieved and collected using data management techniques such as SQL queries. After collection, the data is analyzed by a generative model to predict user preferences and purchase intent. The generative model can use commonly used machine learning methods such as TensorFlow and PyTorch, and is a mechanism that improves prediction accuracy by learning from vast amounts of data.

[0730] The terminal receives personalized commercial proposals from the server and delivers experiences to users using virtual and augmented environments. Specifically, it uses content creation tools such as Unity and Unreal Engine to create a space where users can visually and interactively experience the feel and features of a product. This experience plays a crucial role in helping users deepen their understanding of the product or service.

[0731] Users can view information that reflects their interests based on the experiences provided through their device. The emotions and reactions expressed during this process are recognized by an emotion processing engine, and the content of the suggestions is dynamically adjusted accordingly. The emotion processing engine is equipped with a facial recognition camera and a voice recognition microphone, enabling real-time analysis of emotions.

[0732] As a concrete example, consider a scenario where a user is trying to purchase a specific home appliance. The server provides information on related products based on the user's past purchasing behavior, and the terminal prepares a virtual experience that shows the product's features in detail. The user can try out the product through VR or AR, and an emotion processing engine identifies the user's interests from their facial expressions and voice, highlighting the points that piqued their interest.

[0733] An example of a prompt message would be: "Use this user's past behavioral and sentiment data to identify the product they are most likely to purchase next."

[0734] Thus, the present invention aims to improve customer satisfaction and business performance by realizing more attractive and personalized commercial proposals through detailed recognition and response to users' emotions and behavioral patterns.

[0735] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0736] Step 1:

[0737] The server retrieves users' past sales information and behavioral records from an information storage device. Inputs include vast amounts of transaction history and website behavioral data stored in the company's database. This data is retrieved via SQL queries and formatted using virtual tables. This process provides the foundational data needed to clarify users' purchasing patterns.

[0738] Step 2:

[0739] The server supplies the collected data to a generating AI model that infers the user's preferences and purchasing intent. Because this model uses machine learning algorithms, it learns and outputs the user's behavioral characteristics from newly provided data. Specifically, a neural network using TensorFlow processes the input data and quantifies the likelihood of purchasing a particular product. The output is the predicted preferences and purchasing intent.

[0740] Step 3:

[0741] The server generates personalized commercial proposals based on the prediction results. These proposals are based on data derived from the generative model used and include the selection of the most suitable products and services for the user. Here, prompt statements are created and incorporated into the commercial proposals. The output is a customized proposal statement provided to the user.

[0742] Step 4:

[0743] The server sends the generated proposal to the terminal, which receives it and presents it to the user through a virtual or extended environment. The input consists of commercial proposal content, which is then transformed into a visual experience using content creation tools such as Unity. This allows users to visualize the promotion of products and services.

[0744] Step 5:

[0745] Users view suggested virtual experiences using their devices and take actions based on their interests and preferences. The input is the VR or AR experience provided by the device, and the output is emotional data as a reaction. The user's facial expressions and actions are captured by the camera and microphone, and this information is used for future suggestions.

[0746] Step 6:

[0747] The server then stores the response data collected from users back into the data storage device. This strengthens the dataset used for future commercial proposals and training generative AI models. This feedback loop continuously improves the accuracy of proposals.

[0748] (Application Example 2)

[0749] 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".

[0750] Traditional sales proposals, while based on customer purchase history and preferences, failed to consider real-time emotional states, making it difficult to accurately address individual customer needs. Furthermore, the practical constraints of the in-store customer experience limited the appeal of products and services. Additionally, there was a lack of mechanisms to effectively incorporate feedback into sales proposals. As a result, improving customer satisfaction and streamlining sales promotion were significant challenges.

[0751] 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.

[0752] In this invention, the server includes a unit that collects past sales data and customer behavior history from a database; a unit that uses a generative model based on the collected information to predict user preferences and purchasing behavior and generate individual sales proposals; and a unit that uses augmented reality technology to provide users with a virtual experience of products and services based on the generated proposals. This enables personalized proposals through real-time emotion recognition, thereby improving the customer experience in stores.

[0753] "Past sales data" refers to records of products and services that users have previously purchased, and serves as the basis for analyzing customer purchasing trends.

[0754] "Behavioral history" refers to a record of a customer's actions online or in stores, and is information that helps understand the decision-making process leading up to a purchase.

[0755] A "database" is an aggregated information system for systematically storing collected data and for efficiently managing and retrieving it.

[0756] A "generative model" is a computational model that uses machine learning algorithms to analyze customer preferences and purchasing behavior, and predict the likelihood of future purchases.

[0757] Augmented reality technology is a technique that overlays digital information onto the real world's field of view, and is used to enhance the user's visual and immersive experience.

[0758] "Emotional state" refers to the psychological state analyzed in real time from the user's facial expressions and voice, and is information necessary to evaluate customer interest and acceptance.

[0759] A "display device for assisting customers" is a digital display device used by store staff to provide customers with information about products and services.

[0760] "Feedback" refers to the reactions and opinions collected from users, and it is important information that is analyzed and reflected in future sales strategies.

[0761] The system for implementing this invention mainly consists of three components: a server, a terminal, and a user. The server collects past sales data and behavioral history of customers from a database. This includes customer profiles, purchase history, and website visit records. The server then uses a generative AI model based on the collected data to predict customer preferences and purchasing behavior. This model performs detailed data analysis using machine learning algorithms to identify products and services suitable for the customer's next purchase.

[0762] Next, the server uses the generated data to create personalized suggestions, leveraging virtual reality (VR) or augmented reality (AR) technologies implemented by the device. The device analyzes the user's facial expressions and voice through an emotion engine that performs real-time emotion recognition. This allows the suggestions to adapt to the user's emotional state, providing a more personalized experience.

[0763] Users receive these customized suggestions through smart glasses, which are display devices used for customer interaction within the store. This rapid emotion recognition and personalized information presentation allows customers to instantly understand product features and determine if they match their interests. This feedback is collected from users in real time, sent to a server, and used for future data analysis and improvement of sales suggestions.

[0764] For example, if a customer is considering purchasing a smartphone in a store, a customer service display can facilitate effective sales by suggesting models that are suitable for the customer based on their past purchase history. An example of a prompt message would be, "Suggest new smartphones that the customer might be interested in. Analyze past purchase history and current sentiment to provide personalized recommendations."

[0765] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0766] Step 1:

[0767] The server collects historical sales data and customer behavior history from the database. This collection includes information such as customer purchase history and website visit records. The input data is organized and converted into a format that is easy for the generative AI model to analyze. Specifically, data cleansing is performed to output a neat dataset with noise removed.

[0768] Step 2:

[0769] The server uses a generative AI model, taking a well-organized dataset as input, to predict customer preferences and purchasing behavior. Here, machine learning algorithms play a key role in deriving the customer's future purchasing potential. This model extracts patterns from the data and predicts which products and services will attract customer interest. As an output of this process, personalized sales proposals are generated.

[0770] Step 3:

[0771] The server creates virtual reality (VR) or augmented reality (AR) content for the terminal to run, based on the prediction results and sales proposals. In this step, the visual content is designed to highlight the features of the proposed products and services. The generated content is then converted and prepared for use on the terminal.

[0772] Step 4:

[0773] Users wear smart glasses in the store and experience AR content provided via a device. An emotion engine analyzes the user's facial expressions and voice in real time, dynamically adjusting the content display based on the user's emotional state. Through this process, users can visually receive information tailored to their interests.

[0774] Step 5:

[0775] Users provide reactions and feedback on their experiences. The device collects this feedback and sends it to the server. Based on the feedback input, it is output as feedback information stored in the database to be used for future data analysis and improvement of sales proposals.

[0776] 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.

[0777] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0778] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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."

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] The following is further disclosed regarding the embodiments described above.

[0798] (Claim 1)

[0799] A means of collecting past sales data and customer behavior history from a database,

[0800] A means of predicting customer preferences and purchasing behavior using a generative model based on collected data, and generating individual sales proposals,

[0801] Based on the generated proposals, a means of providing customers with a virtual experience of products or services using virtual reality or augmented reality technology,

[0802] A means of collecting customer feedback and incorporating it into the next data analysis,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, further comprising a means for predicting customer preferences using a machine learning algorithm in a generative model.

[0806] (Claim 3)

[0807] The system according to claim 1, further comprising means for including content that highlights the features of a product or service, which is an experience provided by virtual reality or augmented reality.

[0808] "Example 1"

[0809] (Claim 1)

[0810] A means for obtaining past sales data and consumer behavior history from an information storage device,

[0811] A method for creating individualized sales proposals by using an artificial intelligence model based on acquired information to predict consumer preferences and purchasing behavior,

[0812] Based on the proposed solutions, means of providing consumers with a virtual experience of products or services using virtual reality or augmented reality technology,

[0813] A means of collecting consumer opinions and applying them to subsequent information analysis,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, further comprising a means for predicting consumer preferences using a machine learning algorithm for a generative artificial intelligence model.

[0817] (Claim 3)

[0818] The system according to claim 1, further comprising means for the experience provided by virtual reality or augmented reality to include content that highlights the features of a product or service.

[0819] "Application Example 1"

[0820] (Claim 1)

[0821] A means of collecting past sales information and customer behavior history from storage devices,

[0822] A method for creating individualized sales proposals by using a generation algorithm based on collected information to predict customer preferences and purchasing behavior,

[0823] Based on the proposals created, a means of providing customers with a virtual experience of products and services using augmented reality or virtual reality technology,

[0824] A means of collecting customer feedback and reflecting it in the next data analysis,

[0825] A means of analyzing collected information to generate a product list optimized for each customer and displaying the products in a virtual store using augmented reality,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising a means for predicting customer preferences using a machine learning algorithm for the generation algorithm.

[0829] (Claim 3)

[0830] The system according to claim 1, further comprising means for including content that highlights the characteristics of a product or service, which is an experience provided by augmented reality or virtual reality.

[0831] "Example 2 of combining an emotion engine"

[0832] (Claim 1)

[0833] A means for collecting information on past sales and user behavior records from an information storage device,

[0834] A means of generating individual commercial proposals by using a generative model to infer user preferences and purchasing behavior based on collected information,

[0835] Based on the generated proposals, a means of providing users with a virtual experience of goods or tasks using virtual or augmented environment technology,

[0836] A means including an emotion processing engine that recognizes the user's emotions and responses and dynamically adjusts suggestions,

[0837] A means of collecting user feedback and reflecting it in the next data analysis,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising a means for predicting user preferences using machine learning techniques in a generative model.

[0841] (Claim 3)

[0842] The system according to claim 1, further comprising means that the experience provided by the virtual or extended environment includes content that highlights the features of an item or service.

[0843] "Application example 2 when combining with an emotional engine"

[0844] (Claim 1)

[0845] A unit that collects past sales data and customer behavior history from a database,

[0846] Based on the collected information, a generative model is used to predict user preferences and purchasing behavior, and a unit is used to generate individual sales proposals.

[0847] Based on the generated proposals, a unit will be created that uses augmented reality technology to provide users with a virtual experience of products and services.

[0848] A unit that recognizes the user's emotional state in real time and dynamically adjusts the suggested content,

[0849] A unit that provides content suggested through a display device for customer service,

[0850] A unit that collects user feedback and incorporates it into future data analysis,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, further comprising a means for a generative model to predict user preferences using a machine learning algorithm and for displaying product information on a display device for assisting customers.

[0854] (Claim 3)

[0855] The system according to claim 1, wherein the content provided through the virtual experience includes content that highlights the features of a product or service, and further comprises means for adjusting the suggestions in response to the user's reaction. [Explanation of Symbols]

[0856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past sales data and customer behavior history from a database, A means of predicting customer preferences and purchasing behavior using a generative model based on collected data, and generating individual sales proposals, Based on the generated proposals, a means of providing customers with a virtual experience of products or services using virtual reality or augmented reality technology, A means of collecting customer feedback and incorporating it into the next data analysis, A system that includes this.

2. The system according to claim 1, further comprising a means for predicting customer preferences using a machine learning algorithm in a generative model.

3. The system according to claim 1, further comprising means for including content that highlights the features of a product or service, which is an experience provided by virtual reality or augmented reality.

Images