system

Abstract

We provide the system. [Solution] Means for collecting and storing customer information, A means of identifying customer needs by analyzing collected customer information, A means of automatically generating proposals based on identified customer needs, A means of providing the generated suggestions to the user, A means of collecting user feedback on suggestions and incorporating it into the 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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the business activities of small and medium-sized enterprises, it is required to make efficient and accurate proposals. However, it is not easy to quickly identify the needs of each customer and generate an optimal proposal. In addition, there is a lack of utilization of feedback for sales staff to continuously improve the appropriateness of proposals. Therefore, effective means for improving customer satisfaction while improving the efficiency of the sales process are needed.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, means for automatically generating proposals based on the identified customer needs, means for providing the generated proposals to users, and means for collecting user feedback on the proposals and incorporating it into the analysis. This system makes it possible to make efficient proposals that are tailored to customer needs, improving the efficiency of sales activities and continuously improving the accuracy of proposals.

[0006] "Customer information" refers to data about individual customers, including basic information, past purchase history, and industry information.

[0007] "Means of collection" refers to the processes or tools that sales representatives or systems use to acquire and store customer-related information.

[0008] "Means of storage" refers to a method or apparatus for recording acquired information and maintaining it so that it can be accessed or used as needed.

[0009] "Means of analysis" refers to the process or tools used to identify patterns and relationships in stored data and to pinpoint customer needs.

[0010] "Means of identification" refers to a method or process of recognizing and clarifying a customer's potential desires and requirements based on the analyzed information.

[0011] "Means of automatic generation" refers to an algorithm or process for creating proposals without human intervention, based on needs identified by the system.

[0012] "Means of providing" refers to a method or apparatus for displaying or communicating the generated proposal to the user.

[0013] "Means of collecting feedback" refers to methods or systems for obtaining evaluations and opinions from users and incorporating them into the analysis process.

[0014] "Means of incorporating into analysis" refers to methods or processes for integrating collected feedback into data analysis and improving the proposal generation process. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the 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 disk (e.g., hard disk), or magnetic tape, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] As an embodiment of this invention, a platform for streamlining the sales activities of small and medium-sized enterprises and providing optimal proposals to each customer is described below. This platform mainly consists of a server, terminals, and users.

[0037] Overall system flow

[0038] 1. Information Gathering

[0039] The terminal inputs basic customer information through the user interface and sends it to the server. This includes the customer's name, contact information, past purchase history, and industry information.

[0040] 2. Data storage and analysis

[0041] The server stores the received customer data in a database. The stored data is analyzed by an analysis module and used to identify customer needs. Machine learning algorithms are used in the analysis to predict customers' potential needs based on historical data.

[0042] 3. Proposal generation and distribution

[0043] The server automatically generates suggestions based on identified needs. These suggestions include recommended products and services, pricing information, and reasons for the suggestions. The generated suggestions are sent to the user's device and displayed to them. The user can then proceed with the business negotiation based on the provided suggestions.

[0044] 4. Gathering and implementing feedback

[0045] After a business meeting, users provide feedback on the suitability and areas for improvement of the proposal. This feedback, collected via the terminal, is sent to the server. The server analyzes the feedback and incorporates it into the next proposal generation process. This feedback cycle allows the system to continuously improve the accuracy of its proposals.

[0046] Specific example

[0047] A sales representative for a small to medium-sized enterprise (SME) considers a scenario where they propose a new product to a customer in the construction industry. The sales representative (user) inputs the customer's past purchase history and current market trend information via a terminal. The server analyzes this information and automatically generates a proposal for the optimal new product for that customer. This proposal is immediately sent to the terminal, and the user uses it to effectively advance the sales negotiation. After the negotiation, the user fills out feedback on the proposal and sends it back to the server. This feedback improves the accuracy of future proposals, thereby promoting the overall business growth of the company.

[0048] Thus, the platform of the present invention streamlines sales activities and enables the rapid automation of proposals that meet customer needs.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The terminal provides an interface for users to input basic customer information. This information includes customer name, contact details, past purchase history, and industry information, which the terminal then transmits to the server.

[0052] Step 2:

[0053] The server stores the received customer data in a database. The database organizes information by customer and is configured for quick access. Data integrity and security are also ensured.

[0054] Step 3:

[0055] The server performs analysis using the stored data. It applies machine learning algorithms to identify customer needs through data analysis. This analysis predicts potential customer demands based on past purchasing patterns and market trends.

[0056] Step 4:

[0057] The server automatically generates suggestions based on identified needs. These suggestions include suitable products and services for the customer, pricing information, and relevant promotions. In this process, the algorithm optimizes itself by referencing past successful suggestions.

[0058] Step 5:

[0059] The server sends the generated proposal to the terminal. The terminal displays the proposal in a user-friendly format. Because the proposal includes all the information necessary for sales activities, the user can use it to effectively conduct business negotiations with customers.

[0060] Step 6:

[0061] After the business negotiation, the user enters feedback on the proposal via their device. This feedback includes the suitability of the proposal, areas for improvement, and the outcome of the negotiation. The device then sends this feedback data to the server.

[0062] Step 7:

[0063] The server records the collected feedback in a database and uses it for analysis. This feedback is used to improve the proposal generation algorithm, contributing to increased proposal accuracy in future generations. The overall proposal quality of the system continuously improves.

[0064] (Example 1)

[0065] 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."

[0066] In the sales activities of small and medium-sized enterprises (SMEs), there is a need to efficiently provide optimal proposals to each customer. However, traditional methods require manually collecting and analyzing individual customer information, which is time-consuming and labor-intensive. Furthermore, the use of feedback to improve the accuracy of the proposals provided has been insufficient.

[0067] 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.

[0068] In this invention, the server includes means for collecting and storing customer information using an information processing device, means for analyzing the stored customer information using an analysis device to identify customer needs, and automatic generation means including a generation device that generates proposals based on the identified customer needs. This makes it possible to automatically generate proposals based on customer needs and to conduct sales activities efficiently and accurately.

[0069] An "information processing device" refers to a computer system used to collect and store customer information in digital format.

[0070] An "analysis device" is a combination of a computer and software used to analyze stored data and identify customer needs.

[0071] A "generator" is a device or system for automatically creating proposals based on identified needs.

[0072] "Automated generation method" refers to a system that generates proposals using algorithms without human intervention.

[0073] A "display device" is hardware used to visually present generated proposals to the user, such as a monitor or display device.

[0074] "Information users" refers to sales representatives or related employees who receive the generated proposals and use them to advance business negotiations.

[0075] A "generative AI model" refers to a set of algorithms that use artificial intelligence technology to generate optimal suggestions from accumulated data.

[0076] This invention is a system designed to streamline the sales activities of small and medium-sized enterprises and provide optimal proposals to each customer. The specific implementation of this system is described below.

[0077] The server collects customer information digitally using an information processing device and stores it in a database. This information processing device, acting as a high-performance computer, can utilize specialized software for business use. The collected data is analyzed using an analysis device. Here, machine learning techniques implemented in Python, such as scikit-learn or TENSORFLOW®, are used to identify customer needs.

[0078] Based on identified needs, the server automatically generates suggestions using a generator. This generative AI model constructs appropriate prompt sentences based on the dataset and utilizes a specific set of algorithms to generate optimal suggestions. These suggestions are transmitted to the terminal via a display device and presented to the user.

[0079] Users receive proposals and conduct business negotiations with customers based on them. After the negotiations, users provide feedback via their terminals. The terminals send this feedback to the server, which analyzes the feedback to improve the overall accuracy of the proposals in the system.

[0080] As a concrete example, consider the case of proposing a new product to a customer in the construction industry. The user inputs the customer's past purchase history and market trend information via a terminal. The server analyzes this information and proposes the new product best suited to that customer. An example of this prompt message would be, "Generate a new product proposal for customer X in the construction industry. Please consider past purchase history and market trends." This process enables small and medium-sized enterprises to conduct more effective and efficient sales activities.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The terminal inputs customer information through a user interface, including the customer's name, contact information, past purchase history, and industry information. This input data is transmitted to a server via the internet. The server receives this information and stores it in a database. The server performs error checking to verify the accuracy of the data.

[0084] Step 2:

[0085] The server analyzes stored customer information using an analysis tool. It uses machine learning algorithms implemented in Python, for example, utilizing the scikit-learn library to identify customers' potential needs. The input is customer information stored in a database, and the output is a list of identified needs. The server processes the data, filtering out outliers as it proceeds with the analysis.

[0086] Step 3:

[0087] The server automatically generates suggestions using a generative AI model based on the identified needs derived from the analysis. In this process, specific prompt sentences are input into the generative AI model, and the output is a suggestion best suited to the customer. The suggestion includes product and service recommendations, pricing information, and reasons for the suggestion. The server then structures the generated suggestions and prepares them for the next step.

[0088] Step 4:

[0089] The server sends the generated proposal to the terminal, which then displays this information on its screen. Specifically, the terminal displays a notification informing the user that a new proposal is available for viewing. The user can then initiate a business negotiation based on the displayed proposal. The user reviews the proposal and uses it to communicate with the customer as needed.

[0090] Step 5:

[0091] After a business meeting, users provide feedback via their terminal regarding the suitability and areas for improvement of the proposal. This feedback information is sent from the terminal to the server. The server receives the feedback data, evaluates its content using an analysis device, and uses it as learning material to improve future proposal generation. This allows the system to continuously improve the accuracy of its 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] There is a growing need for more efficient and personalized customer service in commercial environments. However, traditional methods involve cumbersome collection and analysis of customer information, making it difficult to provide real-time recommendations. Furthermore, while prompt and accurate product recommendations are necessary to improve the customer purchasing experience in stores, this is currently difficult to achieve. To address these challenges, a system is needed that utilizes smart devices to make in-store customer service more effective.

[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 and storing customer information, means for analyzing the collected customer information to identify customer needs, means for automatically generating suggestions based on the identified customer needs, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions and incorporating it into the analysis, and means for identifying targets using an identification device and displaying recommendation information in real time based on the identification information. This enables the rapid and appropriate provision of suggestions to customers in commercial settings, making it possible to realize a more personalized customer experience.

[0097] "Customer information" refers to data used to identify customer needs and preferences, such as basic information about the customer, past purchase history, and industry information.

[0098] "Means of collection" refers to methods and devices for acquiring customer information from external sources and importing it into the system.

[0099] "Means of storage" refers to methods and devices for properly retaining collected customer information and managing it so that it can be used at any time.

[0100] "Means of analysis" refer to computational models and algorithms used to analyze stored customer information and derive customer needs and trends.

[0101] "Means for automatically generating proposals" refer to devices or programs that mechanically create proposals for products and services suitable for customers based on analysis results.

[0102] "Means of delivery" refers to methods and devices for communicating the generated proposals to users.

[0103] "Means of collecting feedback" refers to methods and devices for compiling opinions and evaluations from customers and users.

[0104] "Means of incorporating into the analysis" refers to methods and devices for utilizing the collected feedback in the next analysis process to improve the accuracy of the proposals.

[0105] An "identification device" refers to a device or sensor used to identify a specific customer or item.

[0106] "Means for displaying recommended information in real time based on identification information" refers to technologies and devices that present appropriate information to the user on the spot based on information obtained by an identification device.

[0107] The system for carrying out this invention mainly consists of a server, a terminal, an identification device, and a smart device.

[0108] The server has the function of aggregating and properly storing customer information. This customer information includes basic customer attributes, past purchase history, and industry information. This data is stored in a cloud database, enabling efficient management.

[0109] The server uses machine learning algorithms to analyze stored customer information and identify each customer's needs. This analysis utilizes frameworks such as TensorFlow, which can predict future demand based on historical data.

[0110] The terminal's role is to deliver generated suggestions to the user. Users can receive real-time suggestions for products and services best suited to their specific customer needs, and use this information to conduct business negotiations and sales promotion activities.

[0111] The identification device identifies customers who enter the store and sends their identification information to a server. Based on this information, the server generates appropriate recommendations in real time. Smart devices, such as smart glasses, are used to display these recommendations to store staff, facilitating smoother interactions with customers.

[0112] As a concrete example, let's describe a usage scenario in a store. A store employee wears smart glasses, and when a customer enters the store, the identification device identifies the customer. The server generates product suggestions in real time based on the customer's past purchase history, and the results are displayed on the employee's smart glasses. Based on this information, the employee can immediately suggest appropriate products to the customer and facilitate a purchase.

[0113] Example prompt: "Based on the customer's past purchase history, predict the next product you should suggest. Then, briefly describe how you would like to explain that product."

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The terminal inputs customer information via the user and sends it to the server. This input includes the customer's name, past purchase history, and industry information. The server receives this data and stores it in a database. The stored data forms the basis for subsequent analysis.

[0117] Step 2:

[0118] The server runs machine learning algorithms to analyze the stored customer information. Using past purchase history and industry information as input data, the analysis module predicts the customer's potential needs. This prepares the system to make appropriate recommendations for specific customers.

[0119] Step 3:

[0120] The server automatically generates suggestions based on customer needs identified through machine learning. Analysis results are used as input, and the output generates recommended products and services, prices, and reasons for the suggestions. This output is then used in the next step.

[0121] Step 4:

[0122] The server sends the generated proposals to the terminal and provides them to the user. The outputted proposals are displayed on the user interface, and the user can use this information to proceed with business negotiations with customers.

[0123] Step 5:

[0124] After a business meeting, the user enters feedback on the proposal via their device and sends it to the server. This feedback includes the suitability of the proposal and areas for improvement, and this is treated as input data.

[0125] Step 6:

[0126] The server analyzes feedback and uses machine learning algorithms to improve the system. The feedback is then used as re-input, allowing the analysis module to improve the accuracy of future suggestions. This enables the system to continuously evolve.

[0127] 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.

[0128] As an embodiment of this invention, a system is constructed that automatically generates proposals that take into account the emotions of customers and users by incorporating an emotion engine into a platform that supports sales activities. This system consists of a server, terminals, and users, and the coordination of each component realizes an optimal sales process.

[0129] System Overview

[0130] First, the terminal provides an interface for users to input basic customer information, past purchase history, and industry information. The data entered by the user is then sent to the server.

[0131] The server stores received customer information in a database and analyzes customer needs using machine learning algorithms. In addition, the server has an emotion engine implemented, enabling it to recognize and analyze user and customer emotions. This emotion data is used to customize suggestions, adjusting them to better suit the customer.

[0132] The generated proposals are sent from the server to the terminal and presented to the user. The proposals include recommended products and pricing information, as well as the optimal approach to the customer based on sentiment analysis. The user can then use this information to proceed with negotiations and conduct effective sales activities.

[0133] After a business negotiation, the device receives feedback from the user. This feedback includes an evaluation of emotional changes during the negotiation and is sent to the server. The server analyzes the feedback and uses it to improve future proposal generation processes.

[0134] Specific example

[0135] For example, when proposing a new product to a technology company client, the sales representative (user) inputs the client's basic information and past transaction data into their terminal. Based on this, the server identifies the client's needs and further identifies elements that the client showed particular interest in using an emotion engine. It then generates a proposal that emphasizes the technology-specific advantages. This proposal is sent to the user's terminal, and the user uses it to formulate a strategy for the sales negotiation. After the negotiation, the user provides feedback on changes in their emotions, which the server analyzes.

[0136] Thus, the embodiment of the present invention realizes a system that enables small and medium-sized enterprises to conduct their sales activities more based on emotions and improve customer satisfaction.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The terminal provides an interface that allows users to input basic customer information and past transaction data. This interface includes input fields for customer name, contact information, and transaction history. The user enters the required information into the terminal and sends the data to the server.

[0140] Step 2:

[0141] The server records the received customer information in a database. This is done to quickly retrieve data for subsequent analysis processes. After recording is complete, the server uses machine learning algorithms to identify customer needs from the stored data.

[0142] Step 3:

[0143] The server activates an emotion engine to analyze the customer's emotional tendencies in past transactions. This engine analyzes the context of purchase history and inquiries, quantifying the customer's emotions and using this information to tailor suggestions.

[0144] Step 4:

[0145] The server automatically generates personalized recommendations based on identified customer needs and sentiment analysis results. These recommendations include suitable products, services, justifications, and pricing information, as well as suggestions for communication methods tailored to the customer's emotions.

[0146] Step 5:

[0147] The server sends the generated proposal to the terminal. The terminal displays the proposal to the user in a visually easy-to-understand format. Based on the information provided, the user can then appropriately proceed with business negotiations with customers.

[0148] Step 6:

[0149] After a business negotiation, the user provides feedback on the customer's reactions during the negotiation and their perception of the proposal. This feedback includes changes in emotions, agreed-upon points, and areas for improvement. The device then sends this feedback to the server.

[0150] Step 7:

[0151] The server stores user feedback in a database, analyzes the feedback, and incorporates it into future suggestion generation. This allows the system to improve the accuracy of suggestions and enhance customer satisfaction.

[0152] (Example 2)

[0153] 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".

[0154] Traditional sales support systems could generate proposals based on basic customer information and past purchase history, but they could not create proposals that took into account changes in customer or user emotions. As a result, proposals sometimes did not match the actual needs and emotions of customers, leading to a problem of limited effectiveness in sales activities.

[0155] 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.

[0156] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, and means for analyzing customer and user sentiment and considering the results when generating suggestions. This makes it possible to generate suggestions that take sentiment into account.

[0157] "Customer information" refers to basic information about customers in sales activities, such as past purchase history and industry information, and serves as the foundational data for generating proposals.

[0158] "Sentiment analysis" refers to the process of quantifying and analyzing customer and user emotions, with the aim of incorporating emotional elements into proposals.

[0159] "Automatic proposal generation" refers to the process of analyzing customer needs based on collected data and automatically creating appropriate product and service proposals based on the analysis results.

[0160] "Feedback" refers to evaluations provided by users who have received a proposal, as well as information about customer reactions during negotiations. This feedback is used to improve the proposal generation process for future proposals.

[0161] A "machine learning algorithm" is a computational method that learns patterns in data and uses that knowledge to make predictions and perform analyses on unknown data.

[0162] This invention enables more customer-oriented sales activities by incorporating a system that automatically generates proposals that take into account the emotions of customers and users into a platform that supports sales activities. This system consists of a server, terminals, and users working together.

[0163] First, the terminal provides the user with an interface for entering basic customer information, past purchase history, and industry information. This information is then transmitted from the terminal to the server. The terminal is implemented using a standard computer or mobile device and features a user-friendly graphical user interface (GUI) for easy information entry.

[0164] Next, the server stores the received information in a database and analyzes customer needs using machine learning algorithms. For example, a model can be built using the Python programming language and the scikit-learn library. Furthermore, the server is equipped with an emotion engine that analyzes emotions from text data using NLP libraries. This process allows the server to understand the customer's emotional state and reflect it in its recommendations.

[0165] The generated suggestions are sent to the terminal and presented to the user. In some cases, prompts powered by generative AI models are used to generate suggestions. For example, a prompt such as, "When introducing a new product to a technology company, highlight the elements that customers will be interested in," can be used to generate appropriate suggestions using AI.

[0166] Users proceed with negotiations based on the presented proposals and input feedback into their terminals after the negotiations. This feedback includes evaluations of the customer's emotional changes and responses during the negotiations. The server receives this feedback and uses it to generate future proposals, further optimizing the proposal content.

[0167] This system allows sales activities to be conducted based on customer emotions, which is expected to improve customer satisfaction.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The terminal provides the user with an interface for entering customer information. The user enters basic customer information, past purchase history, and industry information. Specifically, the user manually enters data into a form on the terminal and completes the input by pressing the submit button. The entered information is stored on the terminal as customer data.

[0171] Step 2:

[0172] The terminal sends the entered customer information to the server. This transmission process is performed using encrypted communication via the HTTPS protocol. The terminal converts the data to JSON format and sends it to the server over the network. The input is customer information, and the output is encrypted data sent to the server.

[0173] Step 3:

[0174] The server saves the received data to the database. Specifically, the server uses SQL to create a new customer information entry in the database. The input is customer information in JSON format, and the output is the record saved in the database.

[0175] Step 4:

[0176] The server analyzes customer needs using machine learning algorithms. The algorithms are executed using Python and the scikit-learn library to identify customer interests. The input is customer data retrieved from a database, and the output is the identified customer needs.

[0177] Step 5:

[0178] The server analyzes user and customer emotions using an emotion engine. It extracts emotions from text data using a natural language processing library and generates quantified emotional states. The input is the user and customer communication history, and the output is emotional data.

[0179] Step 6:

[0180] The server automatically generates suggestions based on customer needs and sentiment data. Utilizing a generative AI model, it creates multiple suggestions based on prompts and selects the most suitable one. The input is customer needs and sentiment data, and the output is the generated suggestions.

[0181] Step 7:

[0182] The server sends the proposal to the terminal and provides it to the user. The server formats the generated proposal and converts it into a format that can be displayed on the user's terminal. The input is the generated proposal, and the output is the proposal information displayed on the user's terminal.

[0183] Step 8:

[0184] The terminal receives feedback from the user after a business negotiation. This feedback includes changes in emotions during the negotiation and the customer's reactions. Specifically, the user enters information into a feedback form on the terminal and sends it to the server. The input is the user's feedback information, and the output is the submission of that feedback.

[0185] Step 9:

[0186] The server analyzes the received feedback and incorporates it into the proposal generation process. The server stores the feedback in a database and updates the algorithm for future proposal generation. The input is user feedback, and the output is the updated proposal generation algorithm.

[0187] (Application Example 2)

[0188] 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".

[0189] Traditional customer suggestion systems simply identify needs and make suggestions based on customer purchase history and industry information, making it difficult to provide appropriate suggestions that take into account customer emotions and real-time impact. As a result, challenges remain regarding the effectiveness of suggestions and customer satisfaction.

[0190] 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.

[0191] In this invention, the server includes a device for collecting and storing customer information, a device for analyzing the collected customer information to identify customer needs, and a device for recognizing and analyzing user emotions based on voice and image data. This enables the automatic generation of optimized suggestions that take into account not only customer needs but also emotional aspects.

[0192] "Customer information" refers to basic data about customers, including purchase history, industry information, and past behavioral patterns, which form the basis for analysis.

[0193] A "storage device" is an electronic device used to safely and efficiently store information recorded as digital data.

[0194] An "analytical device" is a device that processes input data based on a specific algorithm and has the function of finding useful patterns and trends within that data.

[0195] A "device that recognizes emotions" is a device that analyzes a user's facial expressions and tone of voice through audio and image data to determine their emotional state.

[0196] A "proposal generation device" is a device that automatically creates optimized proposals for each customer based on analyzed needs and sentiment data.

[0197] An "information processing device" is a computer system that combines hardware and software for inputting, processing, and outputting data.

[0198] A "feedback collection device" is a device that records user reactions and evaluations and uses them for subsequent analysis and improvement.

[0199] As a means of implementing this invention, a system is realized that automatically generates suggestions that take into account the emotions of customers and users, thereby improving customer satisfaction on e-commerce sites. The system consists of a server, an information terminal, and a user.

[0200] The server stores customer information collected from information terminals and manages it as digital data. This includes customers' past purchase history and industry information. The server also has machine learning algorithms implemented to analyze and identify customer needs. It is also equipped with an emotion analysis device that can recognize and analyze user emotions in real time based on voice and image data. Possible software to be used includes OpenCV and Google Cloud Vision API.

[0201] An information terminal is a means for users to access a server and input / update necessary information. Through the terminal, users input past purchase data and current industry information, and receive suggestions.

[0202] The generated suggestions include product recommendations that take into account the customer's emotional state. For example, a customer who wants to relax will be recommended relaxation-related products. These suggestions are generated using an algorithm based on TensorFlow and provided to the information terminal.

[0203] Users can propose the most suitable products to customers based on suggestions provided from their information terminals. After the business negotiation, feedback on the proposals is collected from the information terminals and sent to the server. The server analyzes this feedback and uses it to improve the accuracy of future proposals.

[0204] A concrete example would be analyzing the emotions of a user who is relaxing on a holiday while browsing an online shopping site, and then recommending products that are suitable for them in real time. This allows users to receive suggestions that are more likely to be accepted.

[0205] Example of a prompt:

[0206] "Please provide a description of a system that analyzes users' facial expressions and voice data in real time and suggests relaxation-related products tailored to their emotions."

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

[0208] Step 1:

[0209] The information terminal receives basic customer information, past purchase history, and industry information as input from the user. This input data is then transmitted to the server in digital format. The server stores the transmitted information in a database and prepares it as foundational data for identifying customer needs.

[0210] Step 2:

[0211] The server uses data received from information terminals to execute machine learning algorithms. This analyzes customer purchase history and industry information to identify customer needs. The customer needs inferred based on the generative AI model are stored in a database.

[0212] Step 3:

[0213] The device acquires audio and image data in real time from its camera and microphone and sends it to an emotion analysis device. The server processes this data using the emotion analysis device to determine the user's emotional state. Using OpenCV and the Google Cloud Vision API, it analyzes voice tone and facial expressions and reflects the emotions as numerical data in a database.

[0214] Step 4:

[0215] The server combines customer needs and user emotional state data identified in the previous step to generate recommendations. Based on the generative AI model, it automatically selects the products and services best suited to the needs and emotions and outputs them as recommendations. This uses an algorithm based on TensorFlow.

[0216] Step 5:

[0217] The server sends the generated proposals to the information terminal and provides them to the user. The user then recommends products to customers and conducts business negotiations based on these proposals. They can also develop strategies to increase the likelihood of the proposals being accepted.

[0218] Step 6:

[0219] After the business negotiation, the information terminal collects feedback from the user. This feedback includes evaluations of emotional changes during the negotiation and the degree to which the proposal was accepted. The feedback data is sent from the terminal to the server.

[0220] Step 7:

[0221] The server analyzes the feedback it receives and improves the system's proposed model. This adjusts the algorithm so that subsequent proposals using the generative AI model become more accurate.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] As an embodiment of this invention, a platform for streamlining the sales activities of small and medium-sized enterprises and providing optimal proposals to each customer is described below. This platform mainly consists of a server, terminals, and users.

[0239] Overall system flow

[0240] 1. Information Gathering

[0241] The terminal inputs basic customer information through the user interface and sends it to the server. This includes the customer's name, contact information, past purchase history, and industry information.

[0242] 2. Data storage and analysis

[0243] The server stores the received customer data in a database. The stored data is analyzed by an analysis module and used to identify customer needs. Machine learning algorithms are used in the analysis to predict customers' potential needs based on historical data.

[0244] 3. Proposal generation and distribution

[0245] The server automatically generates suggestions based on identified needs. These suggestions include recommended products and services, pricing information, and reasons for the suggestions. The generated suggestions are sent to the user's device and displayed to them. The user can then proceed with the business negotiation based on the provided suggestions.

[0246] 4. Gathering and implementing feedback

[0247] After a business meeting, users provide feedback on the suitability and areas for improvement of the proposal. This feedback, collected via the terminal, is sent to the server. The server analyzes the feedback and incorporates it into the next proposal generation process. This feedback cycle allows the system to continuously improve the accuracy of its proposals.

[0248] Specific example

[0249] A sales representative for a small to medium-sized enterprise (SME) considers a scenario where they propose a new product to a customer in the construction industry. The sales representative (user) inputs the customer's past purchase history and current market trend information via a terminal. The server analyzes this information and automatically generates a proposal for the optimal new product for that customer. This proposal is immediately sent to the terminal, and the user uses it to effectively advance the sales negotiation. After the negotiation, the user fills out feedback on the proposal and sends it back to the server. This feedback improves the accuracy of future proposals, thereby promoting the overall business growth of the company.

[0250] Thus, the platform of the present invention streamlines sales activities and enables the rapid automation of proposals that meet customer needs.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] The terminal provides an interface for users to input basic customer information. This information includes customer name, contact details, past purchase history, and industry information, which the terminal then transmits to the server.

[0254] Step 2:

[0255] The server stores the received customer data in a database. The database organizes information by customer and is configured for quick access. Data integrity and security are also ensured.

[0256] Step 3:

[0257] The server performs analysis using the stored data. It applies machine learning algorithms to identify customer needs through data analysis. This analysis predicts potential customer demands based on past purchasing patterns and market trends.

[0258] Step 4:

[0259] The server automatically generates suggestions based on identified needs. These suggestions include suitable products and services for the customer, pricing information, and relevant promotions. In this process, the algorithm optimizes itself by referencing past successful suggestions.

[0260] Step 5:

[0261] The server sends the generated proposal to the terminal. The terminal displays the proposal in a user-friendly format. Because the proposal includes all the information necessary for sales activities, the user can use it to effectively conduct business negotiations with customers.

[0262] Step 6:

[0263] After the business negotiation, the user enters feedback on the proposal via their device. This feedback includes the suitability of the proposal, areas for improvement, and the outcome of the negotiation. The device then sends this feedback data to the server.

[0264] Step 7:

[0265] The server records the collected feedback in a database and uses it for analysis. This feedback is used to improve the proposal generation algorithm, contributing to increased proposal accuracy in future generations. The overall proposal quality of the system continuously improves.

[0266] (Example 1)

[0267] 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."

[0268] In the sales activities of small and medium-sized enterprises (SMEs), there is a need to efficiently provide optimal proposals to each customer. However, traditional methods require manually collecting and analyzing individual customer information, which is time-consuming and labor-intensive. Furthermore, the use of feedback to improve the accuracy of the proposals provided has been insufficient.

[0269] 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.

[0270] In this invention, the server includes means for collecting and storing customer information using an information processing device, means for analyzing the stored customer information using an analysis device to identify customer needs, and automatic generation means including a generation device that generates proposals based on the identified customer needs. This makes it possible to automatically generate proposals based on customer needs and to conduct sales activities efficiently and accurately.

[0271] An "information processing device" refers to a computer system used to collect and store customer information in digital format.

[0272] An "analysis device" is a combination of a computer and software used to analyze stored data and identify customer needs.

[0273] A "generator" is a device or system for automatically creating proposals based on identified needs.

[0274] "Automated generation method" refers to a system that generates proposals using algorithms without human intervention.

[0275] A "display device" is hardware used to visually present generated proposals to the user, such as a monitor or display device.

[0276] "Information users" refers to sales representatives or related employees who receive the generated proposals and use them to advance business negotiations.

[0277] A "generative AI model" refers to a set of algorithms that use artificial intelligence technology to generate optimal suggestions from accumulated data.

[0278] This invention is a system designed to streamline the sales activities of small and medium-sized enterprises and provide optimal proposals to each customer. The specific implementation of this system is described below.

[0279] The server collects customer information in digital form using an information processing device and stores it in a database. This information processing device, as a high-performance computer, can utilize specialized software for business use. The collected data is analyzed using an analysis device. Here, machine learning techniques implemented in Python, such as scikit-learn and TensorFlow, are used to identify customer needs.

[0280] Based on the identified needs, the server automatically creates proposals using a generation device. This generation AI model constructs appropriate prompt sentences based on a dataset and utilizes a specific group of algorithms to generate optimal proposals. These proposals are sent to the terminal through a display device and presented to the user.

[0281] The user receives the proposal and conducts negotiations with the customer based on it. After the negotiation, the user provides opinions through the terminal. The terminal sends this to the server, and the server analyzes the feedback to improve the proposal accuracy of the entire system.

[0282] As a specific example, consider the case of proposing new products to customers in the construction industry. The user inputs the customer's past purchase history and market trend information from the terminal. The server analyzes this information and proposes the most suitable new products for that customer. As an example of this prompt sentence, "Please generate a proposal for new products for customer X in the construction industry. Please consider the past purchase history and market trends." is used. Through this process, small and medium-sized enterprises can carry out more effective and efficient sales activities.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The terminal inputs customer information through the user interface, which includes the customer's name, contact information, past purchase history, and information about the industry. This input data is sent to the server via the Internet. The server receives this information and stores it in the database. The server performs error checking to confirm the accuracy of the data.

[0286] Step 2:

[0287] The server analyzes the stored customer information using an analysis device. It uses a machine learning algorithm implemented in Python, for example, leveraging the scikit-learn library to identify the potential needs of the customer. The input is the customer information stored in the database, and the output is a list of identified needs. The server proceeds with the analysis while shaping the data and filtering out outliers.

[0288] Step 3:

[0289] Based on the identified needs which are the analysis results, the server automatically generates proposals using a generative AI model. In this process, specific prompt texts are input into the generative AI model, and the optimal proposals for the customer are created as the output. The proposals include recommendations for products or services, price information, and reasons for the proposals. The server structures the generated proposals and prepares them for the next step.

[0290] Step 4:

[0291] The server sends the generated proposals to the terminal, and the terminal displays this information on the screen. As a specific operation, the terminal displays a notification to inform the user that new proposals are available for viewing. The user can start negotiations based on the displayed proposals. The user views the proposal content and utilizes it for communication with the customer as needed.

[0292] Step 5:

[0293] After a business meeting, users provide feedback via their terminal regarding the suitability and areas for improvement of the proposal. This feedback information is sent from the terminal to the server. The server receives the feedback data, evaluates its content using an analysis device, and uses it as learning material to improve future proposal generation. This allows the system to continuously improve the accuracy of its proposals.

[0294] (Application Example 1)

[0295] 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."

[0296] There is a growing need for more efficient and personalized customer service in commercial environments. However, traditional methods involve cumbersome collection and analysis of customer information, making it difficult to provide real-time recommendations. Furthermore, while prompt and accurate product recommendations are necessary to improve the customer purchasing experience in stores, this is currently difficult to achieve. To address these challenges, a system is needed that utilizes smart devices to make in-store customer service more effective.

[0297] 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.

[0298] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, means for automatically generating suggestions based on the identified customer needs, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions and incorporating it into the analysis, and means for identifying targets using an identification device and displaying recommendation information in real time based on the identification information. This enables the rapid and appropriate provision of suggestions to customers in commercial settings, making it possible to realize a more personalized customer experience.

[0299] "Customer information" refers to data for identifying customer needs and preferences, such as basic information about customers, past purchase histories, and industry information.

[0300] "Means for collection" refers to methods and devices for obtaining customer information from external sources and importing it into the system.

[0301] "Means for storage" refers to methods and devices for appropriately holding the collected customer information and managing it for use at any time.

[0302] "Means for analysis" refers to computational models and algorithms for analyzing the stored customer information to derive customer needs and trends.

[0303] "Means for automatically generating proposals" refers to devices and programs for mechanically creating proposals for products and services suitable for customers based on the analysis results.

[0304] "Means for providing" refers to methods and devices for communicating the generated proposals to users.

[0305] "Means for collecting feedback" refers to methods and devices for collecting opinions and evaluations from customers and users.

[0306] "Means for reflecting in analysis" refers to methods and devices for utilizing the collected feedback in the next analysis process to improve the accuracy of proposals.

[0307] "Identification device" refers to devices and sensors for identifying target customers and articles.

[0308] "Means for displaying recommended information in real time based on identification information" refers to technologies and devices for presenting appropriate information to users on the spot based on information obtained by an identification device.

[0309] The system for implementing this invention is mainly composed of a server, a terminal, an identification device, and a smart device.

[0310] The server has the function of aggregating and properly storing customer information. This customer information includes basic customer attributes, past purchase history, and industry information. This data is stored in a cloud database, enabling efficient management.

[0311] The server uses machine learning algorithms to analyze stored customer information and identify each customer's needs. This analysis utilizes frameworks such as TensorFlow, which can predict future demand based on historical data.

[0312] The terminal's role is to deliver generated suggestions to the user. Users can receive real-time suggestions for products and services best suited to their specific customer needs, and use this information to conduct business negotiations and sales promotion activities.

[0313] The identification device identifies customers who enter the store and sends their identification information to a server. Based on this information, the server generates appropriate recommendations in real time. Smart devices, such as smart glasses, are used to display these recommendations to store staff, facilitating smoother interactions with customers.

[0314] As a concrete example, let's describe a usage scenario in a store. A store employee wears smart glasses, and when a customer enters the store, the identification device identifies the customer. The server generates product suggestions in real time based on the customer's past purchase history, and the results are displayed on the employee's smart glasses. Based on this information, the employee can immediately suggest appropriate products to the customer and facilitate a purchase.

[0315] Example prompt: "Based on the customer's past purchase history, predict the next product you should suggest. Then, briefly describe how you would like to explain that product."

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The terminal inputs customer information via the user and sends it to the server. This input includes the customer's name, past purchase history, and industry information. The server receives this data and stores it in a database. The stored data forms the basis for subsequent analysis.

[0319] Step 2:

[0320] The server runs machine learning algorithms to analyze the stored customer information. Using past purchase history and industry information as input data, the analysis module predicts the customer's potential needs. This prepares the system to make appropriate recommendations for specific customers.

[0321] Step 3:

[0322] The server automatically generates suggestions based on customer needs identified through machine learning. Analysis results are used as input, and the output generates recommended products and services, prices, and reasons for the suggestions. This output is then used in the next step.

[0323] Step 4:

[0324] The server sends the generated proposals to the terminal and provides them to the user. The outputted proposals are displayed on the user interface, and the user can use this information to proceed with business negotiations with customers.

[0325] Step 5:

[0326] After a business meeting, the user enters feedback on the proposal via their device and sends it to the server. This feedback includes the suitability of the proposal and areas for improvement, and this is treated as input data.

[0327] Step 6:

[0328] The server analyzes feedback and uses machine learning algorithms to improve the system. The feedback is then used as re-input, allowing the analysis module to improve the accuracy of future suggestions. This enables the system to continuously evolve.

[0329] 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.

[0330] As an embodiment of this invention, a system is constructed that automatically generates proposals that take into account the emotions of customers and users by incorporating an emotion engine into a platform that supports sales activities. This system consists of a server, terminals, and users, and the coordination of each component realizes an optimal sales process.

[0331] System Overview

[0332] First, the terminal provides an interface for users to input basic customer information, past purchase history, and industry information. The data entered by the user is then sent to the server.

[0333] The server stores received customer information in a database and analyzes customer needs using machine learning algorithms. In addition, the server has an emotion engine implemented, enabling it to recognize and analyze user and customer emotions. This emotion data is used to customize suggestions, adjusting them to better suit the customer.

[0334] The generated proposals are sent from the server to the terminal and presented to the user. The proposals include recommended products and pricing information, as well as the optimal approach to the customer based on sentiment analysis. The user can then use this information to proceed with negotiations and conduct effective sales activities.

[0335] After a business negotiation, the device receives feedback from the user. This feedback includes an evaluation of emotional changes during the negotiation and is sent to the server. The server analyzes the feedback and uses it to improve future proposal generation processes.

[0336] Specific example

[0337] For example, when proposing a new product to a technology company client, the sales representative (user) inputs the client's basic information and past transaction data into their terminal. Based on this, the server identifies the client's needs and further identifies elements that the client showed particular interest in using an emotion engine. It then generates a proposal that emphasizes the technology-specific advantages. This proposal is sent to the user's terminal, and the user uses it to formulate a strategy for the sales negotiation. After the negotiation, the user provides feedback on changes in their emotions, which the server analyzes.

[0338] Thus, the embodiment of the present invention realizes a system that enables small and medium-sized enterprises to conduct their sales activities more based on emotions and improve customer satisfaction.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The terminal provides an interface that allows users to input basic customer information and past transaction data. This interface includes input fields for customer name, contact information, and transaction history. The user enters the required information into the terminal and sends the data to the server.

[0342] Step 2:

[0343] The server records the received customer information in a database. This is done to quickly retrieve data for subsequent analysis processes. After recording is complete, the server uses machine learning algorithms to identify customer needs from the stored data.

[0344] Step 3:

[0345] The server activates an emotion engine to analyze the customer's emotional tendencies in past transactions. This engine analyzes the context of purchase history and inquiries, quantifying the customer's emotions and using this information to tailor suggestions.

[0346] Step 4:

[0347] The server automatically generates personalized recommendations based on identified customer needs and sentiment analysis results. These recommendations include suitable products, services, justifications, and pricing information, as well as suggestions for communication methods tailored to the customer's emotions.

[0348] Step 5:

[0349] The server sends the generated proposal to the terminal. The terminal displays the proposal to the user in a visually easy-to-understand format. Based on the information provided, the user can then appropriately proceed with business negotiations with customers.

[0350] Step 6:

[0351] After a business negotiation, the user provides feedback on the customer's reactions during the negotiation and their perception of the proposal. This feedback includes changes in emotions, agreed-upon points, and areas for improvement. The device then sends this feedback to the server.

[0352] Step 7:

[0353] The server stores user feedback in a database, analyzes the feedback, and incorporates it into future suggestion generation. This allows the system to improve the accuracy of suggestions and enhance customer satisfaction.

[0354] (Example 2)

[0355] 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".

[0356] Traditional sales support systems could generate proposals based on basic customer information and past purchase history, but they could not create proposals that took into account changes in customer or user emotions. As a result, proposals sometimes did not match the actual needs and emotions of customers, leading to a problem of limited effectiveness in sales activities.

[0357] 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.

[0358] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, and means for analyzing customer and user sentiment and considering the results when generating suggestions. This makes it possible to generate suggestions that take sentiment into account.

[0359] "Customer information" refers to basic information about customers in sales activities, such as past purchase history and industry information, and serves as the foundational data for generating proposals.

[0360] "Sentiment analysis" refers to the process of quantifying and analyzing customer and user emotions, with the aim of incorporating emotional elements into proposals.

[0361] "Automatic proposal generation" refers to the process of analyzing customer needs based on collected data and automatically creating appropriate product and service proposals based on the analysis results.

[0362] "Feedback" refers to evaluations provided by users who have received a proposal, as well as information about customer reactions during negotiations. This feedback is used to improve the proposal generation process for future proposals.

[0363] A "machine learning algorithm" is a computational method that learns patterns in data and uses that knowledge to make predictions and perform analyses on unknown data.

[0364] This invention enables more customer-oriented sales activities by incorporating a system that automatically generates proposals that take into account the emotions of customers and users into a platform that supports sales activities. This system consists of a server, terminals, and users working together.

[0365] First, the terminal provides the user with an interface for entering basic customer information, past purchase history, and industry information. This information is then transmitted from the terminal to the server. The terminal is implemented using a standard computer or mobile device and features a user-friendly graphical user interface (GUI) for easy information entry.

[0366] Next, the server stores the received information in a database and analyzes customer needs using machine learning algorithms. For example, a model can be built using the Python programming language and the scikit-learn library. Furthermore, the server is equipped with an emotion engine that analyzes emotions from text data using NLP libraries. This process allows the server to understand the customer's emotional state and reflect it in its recommendations.

[0367] The generated suggestions are sent to the terminal and presented to the user. In some cases, prompts powered by generative AI models are used to generate suggestions. For example, a prompt such as, "When introducing a new product to a technology company, highlight the elements that customers will be interested in," can be used to generate appropriate suggestions using AI.

[0368] Users proceed with negotiations based on the presented proposals and input feedback into their terminals after the negotiations. This feedback includes evaluations of the customer's emotional changes and responses during the negotiations. The server receives this feedback and uses it to generate future proposals, further optimizing the proposal content.

[0369] This system allows sales activities to be conducted based on customer emotions, which is expected to improve customer satisfaction.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The terminal provides the user with an interface for entering customer information. The user enters basic customer information, past purchase history, and industry information. Specifically, the user manually enters data into a form on the terminal and completes the input by pressing the submit button. The entered information is stored on the terminal as customer data.

[0373] Step 2:

[0374] The terminal sends the entered customer information to the server. This transmission process is performed using encrypted communication via the HTTPS protocol. The terminal converts the data to JSON format and sends it to the server over the network. The input is customer information, and the output is encrypted data sent to the server.

[0375] Step 3:

[0376] The server saves the received data to the database. Specifically, the server uses SQL to create a new customer information entry in the database. The input is customer information in JSON format, and the output is the record saved in the database.

[0377] Step 4:

[0378] The server analyzes customer needs using machine learning algorithms. The algorithms are executed using Python and the scikit-learn library to identify customer interests. The input is customer data retrieved from a database, and the output is the identified customer needs.

[0379] Step 5:

[0380] The server analyzes user and customer emotions using an emotion engine. It extracts emotions from text data using a natural language processing library and generates quantified emotional states. The input is the user and customer communication history, and the output is emotional data.

[0381] Step 6:

[0382] The server automatically generates suggestions based on customer needs and sentiment data. Utilizing a generative AI model, it creates multiple suggestions based on prompts and selects the most suitable one. The input is customer needs and sentiment data, and the output is the generated suggestions.

[0383] Step 7:

[0384] The server sends the proposal to the terminal and provides it to the user. The server formats the generated proposal and converts it into a format that can be displayed on the user's terminal. The input is the generated proposal, and the output is the proposal information displayed on the user's terminal.

[0385] Step 8:

[0386] The terminal receives feedback from the user after a business negotiation. This feedback includes changes in emotions during the negotiation and the customer's reactions. Specifically, the user enters information into a feedback form on the terminal and sends it to the server. The input is the user's feedback information, and the output is the submission of that feedback.

[0387] Step 9:

[0388] The server analyzes the received feedback and incorporates it into the proposal generation process. The server stores the feedback in a database and updates the algorithm for future proposal generation. The input is user feedback, and the output is the updated proposal generation algorithm.

[0389] (Application Example 2)

[0390] 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."

[0391] Traditional customer suggestion systems simply identify needs and make suggestions based on customer purchase history and industry information, making it difficult to provide appropriate suggestions that take into account customer emotions and real-time impact. As a result, challenges remain regarding the effectiveness of suggestions and customer satisfaction.

[0392] 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.

[0393] In this invention, the server includes a device for collecting and storing customer information, a device for analyzing the collected customer information to identify customer needs, and a device for recognizing and analyzing user emotions based on voice and image data. This enables the automatic generation of optimized suggestions that take into account not only customer needs but also emotional aspects.

[0394] "Customer information" refers to basic data about customers, including purchase history, industry information, and past behavioral patterns, which form the basis for analysis.

[0395] A "storage device" is an electronic device used to safely and efficiently store information recorded as digital data.

[0396] An "analytical device" is a device that processes input data based on a specific algorithm and has the function of finding useful patterns and trends within that data.

[0397] A "device that recognizes emotions" is a device that analyzes a user's facial expressions and tone of voice through audio and image data to determine their emotional state.

[0398] A "proposal generation device" is a device that automatically creates optimized proposals for each customer based on analyzed needs and sentiment data.

[0399] An "information processing device" is a computer system that combines hardware and software for inputting, processing, and outputting data.

[0400] A "feedback collection device" is a device that records user reactions and evaluations and uses them for subsequent analysis and improvement.

[0401] As a means of implementing this invention, a system is realized that automatically generates suggestions that take into account the emotions of customers and users, thereby improving customer satisfaction on e-commerce sites. The system consists of a server, an information terminal, and a user.

[0402] The server stores customer information collected from information terminals and manages it as digital data. This includes customers' past purchase history and industry information. The server also has machine learning algorithms implemented to analyze and identify customer needs. It is also equipped with an emotion analysis device that can recognize and analyze user emotions in real time based on voice and image data. Possible software to be used includes OpenCV and Google Cloud Vision API.

[0403] An information terminal is a means for users to access a server and input / update necessary information. Through the terminal, users input past purchase data and current industry information, and receive suggestions.

[0404] The generated suggestions include product recommendations that take into account the customer's emotional state. For example, a customer who wants to relax will be recommended relaxation-related products. These suggestions are generated using an algorithm based on TensorFlow and provided to the information terminal.

[0405] Users can propose the most suitable products to customers based on suggestions provided from their information terminals. After the business negotiation, feedback on the proposals is collected from the information terminals and sent to the server. The server analyzes this feedback and uses it to improve the accuracy of future proposals.

[0406] A concrete example would be analyzing the emotions of a user who is relaxing on a holiday while browsing an online shopping site, and then recommending products that are suitable for them in real time. This allows users to receive suggestions that are more likely to be accepted.

[0407] Example of a prompt:

[0408] "Please provide a description of a system that analyzes users' facial expressions and voice data in real time and suggests relaxation-related products tailored to their emotions."

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The information terminal receives basic customer information, past purchase history, and industry information as input from the user. This input data is then transmitted to the server in digital format. The server stores the transmitted information in a database and prepares it as foundational data for identifying customer needs.

[0412] Step 2:

[0413] The server uses data received from information terminals to execute machine learning algorithms. This analyzes customer purchase history and industry information to identify customer needs. The customer needs inferred based on the generative AI model are stored in a database.

[0414] Step 3:

[0415] The device acquires audio and image data in real time from its camera and microphone and sends it to an emotion analysis device. The server processes this data using the emotion analysis device to determine the user's emotional state. Using OpenCV and the Google Cloud Vision API, it analyzes voice tone and facial expressions and reflects the emotions as numerical data in a database.

[0416] Step 4:

[0417] The server combines customer needs and user emotional state data identified in the previous step to generate recommendations. Based on the generative AI model, it automatically selects the products and services best suited to the needs and emotions and outputs them as recommendations. This uses an algorithm based on TensorFlow.

[0418] Step 5:

[0419] The server sends the generated proposals to the information terminal and provides them to the user. The user then recommends products to customers and conducts business negotiations based on these proposals. They can also develop strategies to increase the likelihood of the proposals being accepted.

[0420] Step 6:

[0421] After the business negotiation, the information terminal collects feedback from the user. This feedback includes evaluations of emotional changes during the negotiation and the degree to which the proposal was accepted. The feedback data is sent from the terminal to the server.

[0422] Step 7:

[0423] The server analyzes the feedback it receives and improves the system's proposed model. This adjusts the algorithm so that subsequent proposals using the generative AI model become more accurate.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] As an embodiment of this invention, a platform for streamlining the sales activities of small and medium-sized enterprises and providing optimal proposals to each customer is described below. This platform mainly consists of a server, terminals, and users.

[0441] Overall system flow

[0442] 1. Information Gathering

[0443] The terminal inputs basic customer information through the user interface and sends it to the server. This includes the customer's name, contact information, past purchase history, and industry information.

[0444] 2. Data storage and analysis

[0445] The server stores the received customer data in a database. The stored data is analyzed by an analysis module and used to identify customer needs. Machine learning algorithms are used in the analysis to predict customers' potential needs based on historical data.

[0446] 3. Proposal generation and distribution

[0447] The server automatically generates suggestions based on identified needs. These suggestions include recommended products and services, pricing information, and reasons for the suggestions. The generated suggestions are sent to the user's device and displayed to them. The user can then proceed with the business negotiation based on the provided suggestions.

[0448] 4. Gathering and implementing feedback

[0449] After a business meeting, users provide feedback on the suitability and areas for improvement of the proposal. This feedback, collected via the terminal, is sent to the server. The server analyzes the feedback and incorporates it into the next proposal generation process. This feedback cycle allows the system to continuously improve the accuracy of its proposals.

[0450] Specific example

[0451] A sales representative for a small to medium-sized enterprise (SME) considers a scenario where they propose a new product to a customer in the construction industry. The sales representative (user) inputs the customer's past purchase history and current market trend information via a terminal. The server analyzes this information and automatically generates a proposal for the optimal new product for that customer. This proposal is immediately sent to the terminal, and the user uses it to effectively advance the sales negotiation. After the negotiation, the user fills out feedback on the proposal and sends it back to the server. This feedback improves the accuracy of future proposals, thereby promoting the overall business growth of the company.

[0452] Thus, the platform of the present invention streamlines sales activities and enables the rapid automation of proposals that meet customer needs.

[0453] The following describes the processing flow.

[0454] Step 1:

[0455] The terminal provides an interface for users to input basic customer information. This information includes customer name, contact details, past purchase history, and industry information, which the terminal then transmits to the server.

[0456] Step 2:

[0457] The server stores the received customer data in a database. The database organizes information by customer and is configured for quick access. Data integrity and security are also ensured.

[0458] Step 3:

[0459] The server performs analysis using the stored data. It applies machine learning algorithms to identify customer needs through data analysis. This analysis predicts potential customer demands based on past purchasing patterns and market trends.

[0460] Step 4:

[0461] The server automatically generates suggestions based on identified needs. These suggestions include suitable products and services for the customer, pricing information, and relevant promotions. In this process, the algorithm optimizes itself by referencing past successful suggestions.

[0462] Step 5:

[0463] The server sends the generated proposal to the terminal. The terminal displays the proposal in a user-friendly format. Because the proposal includes all the information necessary for sales activities, the user can use it to effectively conduct business negotiations with customers.

[0464] Step 6:

[0465] After the business negotiation, the user enters feedback on the proposal via their device. This feedback includes the suitability of the proposal, areas for improvement, and the outcome of the negotiation. The device then sends this feedback data to the server.

[0466] Step 7:

[0467] The server records the collected feedback in a database and uses it for analysis. This feedback is used to improve the proposal generation algorithm, contributing to increased proposal accuracy in future generations. The overall proposal quality of the system continuously improves.

[0468] (Example 1)

[0469] 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."

[0470] In the sales activities of small and medium-sized enterprises (SMEs), there is a need to efficiently provide optimal proposals to each customer. However, traditional methods require manually collecting and analyzing individual customer information, which is time-consuming and labor-intensive. Furthermore, the use of feedback to improve the accuracy of the proposals provided has been insufficient.

[0471] 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.

[0472] In this invention, the server includes means for collecting and storing customer information using an information processing device, means for analyzing the stored customer information using an analysis device to identify customer needs, and automatic generation means including a generation device that generates proposals based on the identified customer needs. This makes it possible to automatically generate proposals based on customer needs and to conduct sales activities efficiently and accurately.

[0473] An "information processing device" refers to a computer system used to collect and store customer information in digital format.

[0474] An "analysis device" is a combination of a computer and software used to analyze stored data and identify customer needs.

[0475] A "generator" is a device or system for automatically creating proposals based on identified needs.

[0476] "Automated generation method" refers to a system that generates proposals using algorithms without human intervention.

[0477] A "display device" is hardware used to visually present generated proposals to the user, such as a monitor or display device.

[0478] "Information users" refers to sales representatives or related employees who receive the generated proposals and use them to advance business negotiations.

[0479] A "generative AI model" refers to a set of algorithms that use artificial intelligence technology to generate optimal suggestions from accumulated data.

[0480] This invention is a system designed to streamline the sales activities of small and medium-sized enterprises and provide optimal proposals to each customer. The specific implementation of this system is described below.

[0481] The server collects customer information digitally using an information processing device and stores it in a database. This information processing device, acting as a high-performance computer, can utilize specialized software for business use. The collected data is analyzed using an analysis device. Here, machine learning techniques implemented in Python, such as scikit-learn or TensorFlow, are used to identify customer needs.

[0482] Based on identified needs, the server automatically generates suggestions using a generator. This generative AI model constructs appropriate prompt sentences based on the dataset and utilizes a specific set of algorithms to generate optimal suggestions. These suggestions are transmitted to the terminal via a display device and presented to the user.

[0483] Users receive proposals and conduct business negotiations with customers based on them. After the negotiations, users provide feedback via their terminals. The terminals send this feedback to the server, which analyzes the feedback to improve the overall accuracy of the proposals in the system.

[0484] As a concrete example, consider the case of proposing a new product to a customer in the construction industry. The user inputs the customer's past purchase history and market trend information via a terminal. The server analyzes this information and proposes the new product best suited to that customer. An example of this prompt message would be, "Generate a new product proposal for customer X in the construction industry. Please consider past purchase history and market trends." This process enables small and medium-sized enterprises to conduct more effective and efficient sales activities.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The terminal inputs customer information through a user interface, including the customer's name, contact information, past purchase history, and industry information. This input data is transmitted to a server via the internet. The server receives this information and stores it in a database. The server performs error checking to verify the accuracy of the data.

[0488] Step 2:

[0489] The server analyzes stored customer information using an analysis tool. It uses machine learning algorithms implemented in Python, for example, utilizing the scikit-learn library to identify customers' potential needs. The input is customer information stored in a database, and the output is a list of identified needs. The server processes the data, filtering out outliers as it proceeds with the analysis.

[0490] Step 3:

[0491] The server automatically generates suggestions using a generative AI model based on the identified needs derived from the analysis. In this process, specific prompt sentences are input into the generative AI model, and the output is a suggestion best suited to the customer. The suggestion includes product and service recommendations, pricing information, and reasons for the suggestion. The server then structures the generated suggestions and prepares them for the next step.

[0492] Step 4:

[0493] The server sends the generated proposal to the terminal, which then displays this information on its screen. Specifically, the terminal displays a notification informing the user that a new proposal is available for viewing. The user can then initiate a business negotiation based on the displayed proposal. The user reviews the proposal and uses it to communicate with the customer as needed.

[0494] Step 5:

[0495] After a business meeting, users provide feedback via their terminal regarding the suitability and areas for improvement of the proposal. This feedback information is sent from the terminal to the server. The server receives the feedback data, evaluates its content using an analysis device, and uses it as learning material to improve future proposal generation. This allows the system to continuously improve the accuracy of its proposals.

[0496] (Application Example 1)

[0497] 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."

[0498] There is a growing need for more efficient and personalized customer service in commercial environments. However, traditional methods involve cumbersome collection and analysis of customer information, making it difficult to provide real-time recommendations. Furthermore, while prompt and accurate product recommendations are necessary to improve the customer purchasing experience in stores, this is currently difficult to achieve. To address these challenges, a system is needed that utilizes smart devices to make in-store customer service more effective.

[0499] 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.

[0500] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, means for automatically generating suggestions based on the identified customer needs, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions and incorporating it into the analysis, and means for identifying targets using an identification device and displaying recommendation information in real time based on the identification information. This enables the rapid and appropriate provision of suggestions to customers in commercial settings, making it possible to realize a more personalized customer experience.

[0501] "Customer information" refers to data used to identify customer needs and preferences, such as basic information about the customer, past purchase history, and industry information.

[0502] "Means of collection" refers to methods and devices for acquiring customer information from external sources and importing it into the system.

[0503] "Means of storage" refers to methods and devices for properly retaining collected customer information and managing it so that it can be used at any time.

[0504] "Means of analysis" refer to computational models and algorithms used to analyze stored customer information and derive customer needs and trends.

[0505] "Means for automatically generating proposals" refer to devices or programs that mechanically create proposals for products and services suitable for customers based on analysis results.

[0506] "Means of delivery" refers to methods and devices for communicating the generated proposals to users.

[0507] "Means of collecting feedback" refers to methods and devices for compiling opinions and evaluations from customers and users.

[0508] "Means of incorporating into the analysis" refers to methods and devices for utilizing the collected feedback in the next analysis process to improve the accuracy of the proposals.

[0509] An "identification device" refers to a device or sensor used to identify a specific customer or item.

[0510] "Means for displaying recommended information in real time based on identification information" refers to technologies and devices that present appropriate information to the user on the spot based on information obtained by an identification device.

[0511] The system for carrying out this invention mainly consists of a server, a terminal, an identification device, and a smart device.

[0512] The server has the function of aggregating and properly storing customer information. This customer information includes basic customer attributes, past purchase history, and industry information. This data is stored in a cloud database, enabling efficient management.

[0513] The server uses machine learning algorithms to analyze stored customer information and identify each customer's needs. This analysis utilizes frameworks such as TensorFlow, which can predict future demand based on historical data.

[0514] The terminal's role is to deliver generated suggestions to the user. Users can receive real-time suggestions for products and services best suited to their specific customer needs, and use this information to conduct business negotiations and sales promotion activities.

[0515] The identification device identifies customers who enter the store and sends their identification information to a server. Based on this information, the server generates appropriate recommendations in real time. Smart devices, such as smart glasses, are used to display these recommendations to store staff, facilitating smoother interactions with customers.

[0516] As a concrete example, let's describe a usage scenario in a store. A store employee wears smart glasses, and when a customer enters the store, the identification device identifies the customer. The server generates product suggestions in real time based on the customer's past purchase history, and the results are displayed on the employee's smart glasses. Based on this information, the employee can immediately suggest appropriate products to the customer and facilitate a purchase.

[0517] Example prompt: "Based on the customer's past purchase history, predict the next product you should suggest. Then, briefly describe how you would like to explain that product."

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The terminal inputs customer information via the user and sends it to the server. This input includes the customer's name, past purchase history, and industry information. The server receives this data and stores it in a database. The stored data forms the basis for subsequent analysis.

[0521] Step 2:

[0522] The server runs machine learning algorithms to analyze the stored customer information. Using past purchase history and industry information as input data, the analysis module predicts the customer's potential needs. This prepares the system to make appropriate recommendations for specific customers.

[0523] Step 3:

[0524] The server automatically generates suggestions based on customer needs identified through machine learning. Analysis results are used as input, and the output generates recommended products and services, prices, and reasons for the suggestions. This output is then used in the next step.

[0525] Step 4:

[0526] The server sends the generated proposals to the terminal and provides them to the user. The outputted proposals are displayed on the user interface, and the user can use this information to proceed with business negotiations with customers.

[0527] Step 5:

[0528] After a business meeting, the user enters feedback on the proposal via their device and sends it to the server. This feedback includes the suitability of the proposal and areas for improvement, and this is treated as input data.

[0529] Step 6:

[0530] The server analyzes feedback and uses machine learning algorithms to improve the system. The feedback is then used as re-input, allowing the analysis module to improve the accuracy of future suggestions. This enables the system to continuously evolve.

[0531] 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.

[0532] As an embodiment of this invention, a system is constructed that automatically generates proposals that take into account the emotions of customers and users by incorporating an emotion engine into a platform that supports sales activities. This system consists of a server, terminals, and users, and the coordination of each component realizes an optimal sales process.

[0533] System Overview

[0534] First, the terminal provides an interface for users to input basic customer information, past purchase history, and industry information. The data entered by the user is then sent to the server.

[0535] The server stores received customer information in a database and analyzes customer needs using machine learning algorithms. In addition, the server has an emotion engine implemented, enabling it to recognize and analyze user and customer emotions. This emotion data is used to customize suggestions, adjusting them to better suit the customer.

[0536] The generated proposals are sent from the server to the terminal and presented to the user. The proposals include recommended products and pricing information, as well as the optimal approach to the customer based on sentiment analysis. The user can then use this information to proceed with negotiations and conduct effective sales activities.

[0537] After a business negotiation, the device receives feedback from the user. This feedback includes an evaluation of emotional changes during the negotiation and is sent to the server. The server analyzes the feedback and uses it to improve future proposal generation processes.

[0538] Specific example

[0539] For example, when proposing a new product to a technology company client, the sales representative (user) inputs the client's basic information and past transaction data into their terminal. Based on this, the server identifies the client's needs and further identifies elements that the client showed particular interest in using an emotion engine. It then generates a proposal that emphasizes the technology-specific advantages. This proposal is sent to the user's terminal, and the user uses it to formulate a strategy for the sales negotiation. After the negotiation, the user provides feedback on changes in their emotions, which the server analyzes.

[0540] Thus, the embodiment of the present invention realizes a system that enables small and medium-sized enterprises to conduct their sales activities more based on emotions and improve customer satisfaction.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] The terminal provides an interface that allows users to input basic customer information and past transaction data. This interface includes input fields for customer name, contact information, and transaction history. The user enters the required information into the terminal and sends the data to the server.

[0544] Step 2:

[0545] The server records the received customer information in a database. This is done to quickly retrieve data for subsequent analysis processes. After recording is complete, the server uses machine learning algorithms to identify customer needs from the stored data.

[0546] Step 3:

[0547] The server activates an emotion engine to analyze the customer's emotional tendencies in past transactions. This engine analyzes the context of purchase history and inquiries, quantifying the customer's emotions and using this information to tailor suggestions.

[0548] Step 4:

[0549] The server automatically generates personalized recommendations based on identified customer needs and sentiment analysis results. These recommendations include suitable products, services, justifications, and pricing information, as well as suggestions for communication methods tailored to the customer's emotions.

[0550] Step 5:

[0551] The server sends the generated proposal to the terminal. The terminal displays the proposal to the user in a visually easy-to-understand format. Based on the information provided, the user can then appropriately proceed with business negotiations with customers.

[0552] Step 6:

[0553] After a business negotiation, the user provides feedback on the customer's reactions during the negotiation and their perception of the proposal. This feedback includes changes in emotions, agreed-upon points, and areas for improvement. The device then sends this feedback to the server.

[0554] Step 7:

[0555] The server stores user feedback in a database, analyzes the feedback, and incorporates it into future suggestion generation. This allows the system to improve the accuracy of suggestions and enhance customer satisfaction.

[0556] (Example 2)

[0557] 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."

[0558] Traditional sales support systems could generate proposals based on basic customer information and past purchase history, but they could not create proposals that took into account changes in customer or user emotions. As a result, proposals sometimes did not match the actual needs and emotions of customers, leading to a problem of limited effectiveness in sales activities.

[0559] 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.

[0560] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, and means for analyzing customer and user sentiment and considering the results when generating suggestions. This makes it possible to generate suggestions that take sentiment into account.

[0561] "Customer information" refers to basic information about customers in sales activities, such as past purchase history and industry information, and serves as the foundational data for generating proposals.

[0562] "Sentiment analysis" refers to the process of quantifying and analyzing customer and user emotions, with the aim of incorporating emotional elements into proposals.

[0563] "Automatic proposal generation" refers to the process of analyzing customer needs based on collected data and automatically creating appropriate product and service proposals based on the analysis results.

[0564] "Feedback" refers to evaluations provided by users who have received a proposal, as well as information about customer reactions during negotiations. This feedback is used to improve the proposal generation process for future proposals.

[0565] A "machine learning algorithm" is a computational method that learns patterns in data and uses that knowledge to make predictions and perform analyses on unknown data.

[0566] This invention enables more customer-oriented sales activities by incorporating a system that automatically generates proposals that take into account the emotions of customers and users into a platform that supports sales activities. This system consists of a server, terminals, and users working together.

[0567] First, the terminal provides the user with an interface for entering basic customer information, past purchase history, and industry information. This information is then transmitted from the terminal to the server. The terminal is implemented using a standard computer or mobile device and features a user-friendly graphical user interface (GUI) for easy information entry.

[0568] Next, the server stores the received information in a database and analyzes customer needs using machine learning algorithms. For example, a model can be built using the Python programming language and the scikit-learn library. Furthermore, the server is equipped with an emotion engine that analyzes emotions from text data using NLP libraries. This process allows the server to understand the customer's emotional state and reflect it in its recommendations.

[0569] The generated suggestions are sent to the terminal and presented to the user. In some cases, prompts powered by generative AI models are used to generate suggestions. For example, a prompt such as, "When introducing a new product to a technology company, highlight the elements that customers will be interested in," can be used to generate appropriate suggestions using AI.

[0570] Users proceed with negotiations based on the presented proposals and input feedback into their terminals after the negotiations. This feedback includes evaluations of the customer's emotional changes and responses during the negotiations. The server receives this feedback and uses it to generate future proposals, further optimizing the proposal content.

[0571] This system allows sales activities to be conducted based on customer emotions, which is expected to improve customer satisfaction.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The terminal provides the user with an interface for entering customer information. The user enters basic customer information, past purchase history, and industry information. Specifically, the user manually enters data into a form on the terminal and completes the input by pressing the submit button. The entered information is stored on the terminal as customer data.

[0575] Step 2:

[0576] The terminal sends the entered customer information to the server. This transmission process is performed using encrypted communication via the HTTPS protocol. The terminal converts the data to JSON format and sends it to the server over the network. The input is customer information, and the output is encrypted data sent to the server.

[0577] Step 3:

[0578] The server saves the received data to the database. Specifically, the server uses SQL to create a new customer information entry in the database. The input is customer information in JSON format, and the output is the record saved in the database.

[0579] Step 4:

[0580] The server analyzes customer needs using machine learning algorithms. The algorithms are executed using Python and the scikit-learn library to identify customer interests. The input is customer data retrieved from a database, and the output is the identified customer needs.

[0581] Step 5:

[0582] The server analyzes user and customer emotions using an emotion engine. It extracts emotions from text data using a natural language processing library and generates quantified emotional states. The input is the user and customer communication history, and the output is emotional data.

[0583] Step 6:

[0584] The server automatically generates suggestions based on customer needs and sentiment data. Utilizing a generative AI model, it creates multiple suggestions based on prompts and selects the most suitable one. The input is customer needs and sentiment data, and the output is the generated suggestions.

[0585] Step 7:

[0586] The server sends the proposal to the terminal and provides it to the user. The server formats the generated proposal and converts it into a format that can be displayed on the user's terminal. The input is the generated proposal, and the output is the proposal information displayed on the user's terminal.

[0587] Step 8:

[0588] The terminal receives feedback from the user after a business negotiation. This feedback includes changes in emotions during the negotiation and the customer's reactions. Specifically, the user enters information into a feedback form on the terminal and sends it to the server. The input is the user's feedback information, and the output is the submission of that feedback.

[0589] Step 9:

[0590] The server analyzes the received feedback and incorporates it into the proposal generation process. The server stores the feedback in a database and updates the algorithm for future proposal generation. The input is user feedback, and the output is the updated proposal generation algorithm.

[0591] (Application Example 2)

[0592] 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."

[0593] Traditional customer suggestion systems simply identify needs and make suggestions based on customer purchase history and industry information, making it difficult to provide appropriate suggestions that take into account customer emotions and real-time impact. As a result, challenges remain regarding the effectiveness of suggestions and customer satisfaction.

[0594] 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.

[0595] In this invention, the server includes a device for collecting and storing customer information, a device for analyzing the collected customer information to identify customer needs, and a device for recognizing and analyzing user emotions based on voice and image data. This enables the automatic generation of optimized suggestions that take into account not only customer needs but also emotional aspects.

[0596] "Customer information" refers to basic data about customers, including purchase history, industry information, and past behavioral patterns, which form the basis for analysis.

[0597] A "storage device" is an electronic device used to safely and efficiently store information recorded as digital data.

[0598] An "analytical device" is a device that processes input data based on a specific algorithm and has the function of finding useful patterns and trends within that data.

[0599] A "device that recognizes emotions" is a device that analyzes a user's facial expressions and tone of voice through audio and image data to determine their emotional state.

[0600] A "proposal generation device" is a device that automatically creates optimized proposals for each customer based on analyzed needs and sentiment data.

[0601] An "information processing device" is a computer system that combines hardware and software for inputting, processing, and outputting data.

[0602] A "feedback collection device" is a device that records user reactions and evaluations and uses them for subsequent analysis and improvement.

[0603] As a means of implementing this invention, a system is realized that automatically generates suggestions that take into account the emotions of customers and users, thereby improving customer satisfaction on e-commerce sites. The system consists of a server, an information terminal, and a user.

[0604] The server stores customer information collected from information terminals and manages it as digital data. This includes customers' past purchase history and industry information. The server also has machine learning algorithms implemented to analyze and identify customer needs. It is also equipped with an emotion analysis device that can recognize and analyze user emotions in real time based on voice and image data. Possible software to be used includes OpenCV and Google Cloud Vision API.

[0605] An information terminal is a means for users to access a server and input / update necessary information. Through the terminal, users input past purchase data and current industry information, and receive suggestions.

[0606] The generated suggestions include product recommendations that take into account the customer's emotional state. For example, a customer who wants to relax will be recommended relaxation-related products. These suggestions are generated using an algorithm based on TensorFlow and provided to the information terminal.

[0607] Users can propose the most suitable products to customers based on suggestions provided from their information terminals. After the business negotiation, feedback on the proposals is collected from the information terminals and sent to the server. The server analyzes this feedback and uses it to improve the accuracy of future proposals.

[0608] A concrete example would be analyzing the emotions of a user who is relaxing on a holiday while browsing an online shopping site, and then recommending products that are suitable for them in real time. This allows users to receive suggestions that are more likely to be accepted.

[0609] Example of a prompt:

[0610] "Please provide a description of a system that analyzes users' facial expressions and voice data in real time and suggests relaxation-related products tailored to their emotions."

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The information terminal receives basic customer information, past purchase history, and industry information as input from the user. This input data is then transmitted to the server in digital format. The server stores the transmitted information in a database and prepares it as foundational data for identifying customer needs.

[0614] Step 2:

[0615] The server uses data received from information terminals to execute machine learning algorithms. This analyzes customer purchase history and industry information to identify customer needs. The customer needs inferred based on the generative AI model are stored in a database.

[0616] Step 3:

[0617] The device acquires audio and image data in real time from its camera and microphone and sends it to an emotion analysis device. The server processes this data using the emotion analysis device to determine the user's emotional state. Using OpenCV and the Google Cloud Vision API, it analyzes voice tone and facial expressions and reflects the emotions as numerical data in a database.

[0618] Step 4:

[0619] The server combines customer needs and user emotional state data identified in the previous step to generate recommendations. Based on the generative AI model, it automatically selects the products and services best suited to the needs and emotions and outputs them as recommendations. This uses an algorithm based on TensorFlow.

[0620] Step 5:

[0621] The server sends the generated proposals to the information terminal and provides them to the user. The user then recommends products to customers and conducts business negotiations based on these proposals. They can also develop strategies to increase the likelihood of the proposals being accepted.

[0622] Step 6:

[0623] After the business negotiation, the information terminal collects feedback from the user. This feedback includes evaluations of emotional changes during the negotiation and the degree to which the proposal was accepted. The feedback data is sent from the terminal to the server.

[0624] Step 7:

[0625] The server analyzes the feedback it receives and improves the system's proposed model. This adjusts the algorithm so that subsequent proposals using the generative AI model become more accurate.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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".

[0643] As an embodiment of this invention, a platform for streamlining the sales activities of small and medium-sized enterprises and providing optimal proposals to each customer is described below. This platform mainly consists of a server, terminals, and users.

[0644] Overall system flow

[0645] 1. Information Gathering

[0646] The terminal inputs basic customer information through the user interface and sends it to the server. This includes the customer's name, contact information, past purchase history, and industry information.

[0647] 2. Data storage and analysis

[0648] The server stores the received customer data in a database. The stored data is analyzed by an analysis module and used to identify customer needs. Machine learning algorithms are used in the analysis to predict customers' potential needs based on historical data.

[0649] 3. Proposal generation and distribution

[0650] The server automatically generates suggestions based on identified needs. These suggestions include recommended products and services, pricing information, and reasons for the suggestions. The generated suggestions are sent to the user's device and displayed to them. The user can then proceed with the business negotiation based on the provided suggestions.

[0651] 4. Gathering and implementing feedback

[0652] After a business meeting, users provide feedback on the suitability and areas for improvement of the proposal. This feedback, collected via the terminal, is sent to the server. The server analyzes the feedback and incorporates it into the next proposal generation process. This feedback cycle allows the system to continuously improve the accuracy of its proposals.

[0653] Specific example

[0654] A sales representative for a small to medium-sized enterprise (SME) considers a scenario where they propose a new product to a customer in the construction industry. The sales representative (user) inputs the customer's past purchase history and current market trend information via a terminal. The server analyzes this information and automatically generates a proposal for the optimal new product for that customer. This proposal is immediately sent to the terminal, and the user uses it to effectively advance the sales negotiation. After the negotiation, the user fills out feedback on the proposal and sends it back to the server. This feedback improves the accuracy of future proposals, thereby promoting the overall business growth of the company.

[0655] Thus, the platform of the present invention streamlines sales activities and enables the rapid automation of proposals that meet customer needs.

[0656] The following describes the processing flow.

[0657] Step 1:

[0658] The terminal provides an interface for users to input basic customer information. This information includes customer name, contact details, past purchase history, and industry information, which the terminal then transmits to the server.

[0659] Step 2:

[0660] The server stores the received customer data in a database. The database organizes information by customer and is configured for quick access. Data integrity and security are also ensured.

[0661] Step 3:

[0662] The server performs analysis using the stored data. It applies machine learning algorithms to identify customer needs through data analysis. This analysis predicts potential customer demands based on past purchasing patterns and market trends.

[0663] Step 4:

[0664] The server automatically generates suggestions based on identified needs. These suggestions include suitable products and services for the customer, pricing information, and relevant promotions. In this process, the algorithm optimizes itself by referencing past successful suggestions.

[0665] Step 5:

[0666] The server sends the generated proposal to the terminal. The terminal displays the proposal in a user-friendly format. Because the proposal includes all the information necessary for sales activities, the user can use it to effectively conduct business negotiations with customers.

[0667] Step 6:

[0668] After the business negotiation, the user enters feedback on the proposal via their device. This feedback includes the suitability of the proposal, areas for improvement, and the outcome of the negotiation. The device then sends this feedback data to the server.

[0669] Step 7:

[0670] The server records the collected feedback in a database and uses it for analysis. This feedback is used to improve the proposal generation algorithm, contributing to increased proposal accuracy in future generations. The overall proposal quality of the system continuously improves.

[0671] (Example 1)

[0672] 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".

[0673] In the sales activities of small and medium-sized enterprises (SMEs), there is a need to efficiently provide optimal proposals to each customer. However, traditional methods require manually collecting and analyzing individual customer information, which is time-consuming and labor-intensive. Furthermore, the use of feedback to improve the accuracy of the proposals provided has been insufficient.

[0674] 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.

[0675] In this invention, the server includes means for collecting and storing customer information using an information processing device, means for analyzing the stored customer information using an analysis device to identify customer needs, and automatic generation means including a generation device that generates proposals based on the identified customer needs. This makes it possible to automatically generate proposals based on customer needs and to conduct sales activities efficiently and accurately.

[0676] An "information processing device" refers to a computer system used to collect and store customer information in digital format.

[0677] An "analysis device" is a combination of a computer and software used to analyze stored data and identify customer needs.

[0678] A "generator" is a device or system for automatically creating proposals based on identified needs.

[0679] "Automated generation method" refers to a system that generates proposals using algorithms without human intervention.

[0680] A "display device" is hardware used to visually present generated proposals to the user, such as a monitor or display device.

[0681] "Information users" refers to sales representatives or related employees who receive the generated proposals and use them to advance business negotiations.

[0682] A "generative AI model" refers to a set of algorithms that use artificial intelligence technology to generate optimal suggestions from accumulated data.

[0683] This invention is a system designed to streamline the sales activities of small and medium-sized enterprises and provide optimal proposals to each customer. The specific implementation of this system is described below.

[0684] The server collects customer information digitally using an information processing device and stores it in a database. This information processing device, acting as a high-performance computer, can utilize specialized software for business use. The collected data is analyzed using an analysis device. Here, machine learning techniques implemented in Python, such as scikit-learn or TensorFlow, are used to identify customer needs.

[0685] Based on identified needs, the server automatically generates suggestions using a generator. This generative AI model constructs appropriate prompt sentences based on the dataset and utilizes a specific set of algorithms to generate optimal suggestions. These suggestions are transmitted to the terminal via a display device and presented to the user.

[0686] Users receive proposals and conduct business negotiations with customers based on them. After the negotiations, users provide feedback via their terminals. The terminals send this feedback to the server, which analyzes the feedback to improve the overall accuracy of the proposals in the system.

[0687] As a concrete example, consider the case of proposing a new product to a customer in the construction industry. The user inputs the customer's past purchase history and market trend information via a terminal. The server analyzes this information and proposes the new product best suited to that customer. An example of this prompt message would be, "Generate a new product proposal for customer X in the construction industry. Please consider past purchase history and market trends." This process enables small and medium-sized enterprises to conduct more effective and efficient sales activities.

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] The terminal inputs customer information through a user interface, including the customer's name, contact information, past purchase history, and industry information. This input data is transmitted to a server via the internet. The server receives this information and stores it in a database. The server performs error checking to verify the accuracy of the data.

[0691] Step 2:

[0692] The server analyzes stored customer information using an analysis tool. It uses machine learning algorithms implemented in Python, for example, utilizing the scikit-learn library to identify customers' potential needs. The input is customer information stored in a database, and the output is a list of identified needs. The server processes the data, filtering out outliers as it proceeds with the analysis.

[0693] Step 3:

[0694] The server automatically generates suggestions using a generative AI model based on the identified needs derived from the analysis. In this process, specific prompt sentences are input into the generative AI model, and the output is a suggestion best suited to the customer. The suggestion includes product and service recommendations, pricing information, and reasons for the suggestion. The server then structures the generated suggestions and prepares them for the next step.

[0695] Step 4:

[0696] The server sends the generated proposal to the terminal, which then displays this information on its screen. Specifically, the terminal displays a notification informing the user that a new proposal is available for viewing. The user can then initiate a business negotiation based on the displayed proposal. The user reviews the proposal and uses it to communicate with the customer as needed.

[0697] Step 5:

[0698] After a business meeting, users provide feedback via their terminal regarding the suitability and areas for improvement of the proposal. This feedback information is sent from the terminal to the server. The server receives the feedback data, evaluates its content using an analysis device, and uses it as learning material to improve future proposal generation. This allows the system to continuously improve the accuracy of its proposals.

[0699] (Application Example 1)

[0700] 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".

[0701] There is a growing need for more efficient and personalized customer service in commercial environments. However, traditional methods involve cumbersome collection and analysis of customer information, making it difficult to provide real-time recommendations. Furthermore, while prompt and accurate product recommendations are necessary to improve the customer purchasing experience in stores, this is currently difficult to achieve. To address these challenges, a system is needed that utilizes smart devices to make in-store customer service more effective.

[0702] 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.

[0703] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, means for automatically generating suggestions based on the identified customer needs, means for providing the generated suggestions to the user, means for collecting user feedback on the suggestions and incorporating it into the analysis, and means for identifying targets using an identification device and displaying recommendation information in real time based on the identification information. This enables the rapid and appropriate provision of suggestions to customers in commercial settings, making it possible to realize a more personalized customer experience.

[0704] "Customer information" refers to data used to identify customer needs and preferences, such as basic information about the customer, past purchase history, and industry information.

[0705] "Means of collection" refers to methods and devices for acquiring customer information from external sources and importing it into the system.

[0706] "Means of storage" refers to methods and devices for properly retaining collected customer information and managing it so that it can be used at any time.

[0707] "Means of analysis" refer to computational models and algorithms used to analyze stored customer information and derive customer needs and trends.

[0708] "Means for automatically generating proposals" refer to devices or programs that mechanically create proposals for products and services suitable for customers based on analysis results.

[0709] "Means of delivery" refers to methods and devices for communicating the generated proposals to users.

[0710] "Means of collecting feedback" refers to methods and devices for compiling opinions and evaluations from customers and users.

[0711] "Means of incorporating into the analysis" refers to methods and devices for utilizing the collected feedback in the next analysis process to improve the accuracy of the proposals.

[0712] An "identification device" refers to a device or sensor used to identify a specific customer or item.

[0713] "Means for displaying recommended information in real time based on identification information" refers to technologies and devices that present appropriate information to the user on the spot based on information obtained by an identification device.

[0714] The system for carrying out this invention mainly consists of a server, a terminal, an identification device, and a smart device.

[0715] The server has the function of aggregating and properly storing customer information. This customer information includes basic customer attributes, past purchase history, and industry information. This data is stored in a cloud database, enabling efficient management.

[0716] The server uses machine learning algorithms to analyze stored customer information and identify each customer's needs. This analysis utilizes frameworks such as TensorFlow, which can predict future demand based on historical data.

[0717] The terminal's role is to deliver generated suggestions to the user. Users can receive real-time suggestions for products and services best suited to their specific customer needs, and use this information to conduct business negotiations and sales promotion activities.

[0718] The identification device identifies customers who enter the store and sends their identification information to a server. Based on this information, the server generates appropriate recommendations in real time. Smart devices, such as smart glasses, are used to display these recommendations to store staff, facilitating smoother interactions with customers.

[0719] As a concrete example, let's describe a usage scenario in a store. A store employee wears smart glasses, and when a customer enters the store, the identification device identifies the customer. The server generates product suggestions in real time based on the customer's past purchase history, and the results are displayed on the employee's smart glasses. Based on this information, the employee can immediately suggest appropriate products to the customer and facilitate a purchase.

[0720] Example prompt: "Based on the customer's past purchase history, predict the next product you should suggest. Then, briefly describe how you would like to explain that product."

[0721] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0722] Step 1:

[0723] The terminal inputs customer information via the user and sends it to the server. This input includes the customer's name, past purchase history, and industry information. The server receives this data and stores it in a database. The stored data forms the basis for subsequent analysis.

[0724] Step 2:

[0725] The server runs machine learning algorithms to analyze the stored customer information. Using past purchase history and industry information as input data, the analysis module predicts the customer's potential needs. This prepares the system to make appropriate recommendations for specific customers.

[0726] Step 3:

[0727] The server automatically generates suggestions based on customer needs identified through machine learning. Analysis results are used as input, and the output generates recommended products and services, prices, and reasons for the suggestions. This output is then used in the next step.

[0728] Step 4:

[0729] The server sends the generated proposals to the terminal and provides them to the user. The outputted proposals are displayed on the user interface, and the user can use this information to proceed with business negotiations with customers.

[0730] Step 5:

[0731] After a business meeting, the user enters feedback on the proposal via their device and sends it to the server. This feedback includes the suitability of the proposal and areas for improvement, and this is treated as input data.

[0732] Step 6:

[0733] The server analyzes feedback and uses machine learning algorithms to improve the system. The feedback is then used as re-input, allowing the analysis module to improve the accuracy of future suggestions. This enables the system to continuously evolve.

[0734] 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.

[0735] As an embodiment of this invention, a system is constructed that automatically generates proposals that take into account the emotions of customers and users by incorporating an emotion engine into a platform that supports sales activities. This system consists of a server, terminals, and users, and the coordination of each component realizes an optimal sales process.

[0736] System Overview

[0737] First, the terminal provides an interface for users to input basic customer information, past purchase history, and industry information. The data entered by the user is then sent to the server.

[0738] The server stores received customer information in a database and analyzes customer needs using machine learning algorithms. In addition, the server has an emotion engine implemented, enabling it to recognize and analyze user and customer emotions. This emotion data is used to customize suggestions, adjusting them to better suit the customer.

[0739] The generated proposals are sent from the server to the terminal and presented to the user. The proposals include recommended products and pricing information, as well as the optimal approach to the customer based on sentiment analysis. The user can then use this information to proceed with negotiations and conduct effective sales activities.

[0740] After a business negotiation, the device receives feedback from the user. This feedback includes an evaluation of emotional changes during the negotiation and is sent to the server. The server analyzes the feedback and uses it to improve future proposal generation processes.

[0741] Specific example

[0742] For example, when proposing a new product to a technology company client, the sales representative (user) inputs the client's basic information and past transaction data into their terminal. Based on this, the server identifies the client's needs and further identifies elements that the client showed particular interest in using an emotion engine. It then generates a proposal that emphasizes the technology-specific advantages. This proposal is sent to the user's terminal, and the user uses it to formulate a strategy for the sales negotiation. After the negotiation, the user provides feedback on changes in their emotions, which the server analyzes.

[0743] Thus, the embodiment of the present invention realizes a system that enables small and medium-sized enterprises to conduct their sales activities more based on emotions and improve customer satisfaction.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The terminal provides an interface that allows users to input basic customer information and past transaction data. This interface includes input fields for customer name, contact information, and transaction history. The user enters the required information into the terminal and sends the data to the server.

[0747] Step 2:

[0748] The server records the received customer information in a database. This is done to quickly retrieve data for subsequent analysis processes. After recording is complete, the server uses machine learning algorithms to identify customer needs from the stored data.

[0749] Step 3:

[0750] The server activates an emotion engine to analyze the customer's emotional tendencies in past transactions. This engine analyzes the context of purchase history and inquiries, quantifying the customer's emotions and using this information to tailor suggestions.

[0751] Step 4:

[0752] The server automatically generates personalized recommendations based on identified customer needs and sentiment analysis results. These recommendations include suitable products, services, justifications, and pricing information, as well as suggestions for communication methods tailored to the customer's emotions.

[0753] Step 5:

[0754] The server sends the generated proposal to the terminal. The terminal displays the proposal to the user in a visually easy-to-understand format. Based on the information provided, the user can then appropriately proceed with business negotiations with customers.

[0755] Step 6:

[0756] After a business negotiation, the user provides feedback on the customer's reactions during the negotiation and their perception of the proposal. This feedback includes changes in emotions, agreed-upon points, and areas for improvement. The device then sends this feedback to the server.

[0757] Step 7:

[0758] The server stores user feedback in a database, analyzes the feedback, and incorporates it into future suggestion generation. This allows the system to improve the accuracy of suggestions and enhance customer satisfaction.

[0759] (Example 2)

[0760] 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".

[0761] Traditional sales support systems could generate proposals based on basic customer information and past purchase history, but they could not create proposals that took into account changes in customer or user emotions. As a result, proposals sometimes did not match the actual needs and emotions of customers, leading to a problem of limited effectiveness in sales activities.

[0762] 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.

[0763] In this invention, the server includes means for collecting and storing customer information, means for analyzing the collected customer information to identify customer needs, and means for analyzing customer and user sentiment and considering the results when generating suggestions. This makes it possible to generate suggestions that take sentiment into account.

[0764] "Customer information" refers to basic information about customers in sales activities, such as past purchase history and industry information, and serves as the foundational data for generating proposals.

[0765] "Sentiment analysis" refers to the process of quantifying and analyzing customer and user emotions, with the aim of incorporating emotional elements into proposals.

[0766] "Automatic proposal generation" refers to the process of analyzing customer needs based on collected data and automatically creating appropriate product and service proposals based on the analysis results.

[0767] "Feedback" refers to evaluations provided by users who have received a proposal, as well as information about customer reactions during negotiations. This feedback is used to improve the proposal generation process for future proposals.

[0768] A "machine learning algorithm" is a computational method that learns patterns in data and uses that knowledge to make predictions and perform analyses on unknown data.

[0769] This invention enables more customer-oriented sales activities by incorporating a system that automatically generates proposals that take into account the emotions of customers and users into a platform that supports sales activities. This system consists of a server, terminals, and users working together.

[0770] First, the terminal provides the user with an interface for entering basic customer information, past purchase history, and industry information. This information is then transmitted from the terminal to the server. The terminal is implemented using a standard computer or mobile device and features a user-friendly graphical user interface (GUI) for easy information entry.

[0771] Next, the server stores the received information in a database and analyzes customer needs using machine learning algorithms. For example, a model can be built using the Python programming language and the scikit-learn library. Furthermore, the server is equipped with an emotion engine that analyzes emotions from text data using NLP libraries. This process allows the server to understand the customer's emotional state and reflect it in its recommendations.

[0772] The generated suggestions are sent to the terminal and presented to the user. In some cases, prompts powered by generative AI models are used to generate suggestions. For example, a prompt such as, "When introducing a new product to a technology company, highlight the elements that customers will be interested in," can be used to generate appropriate suggestions using AI.

[0773] Users proceed with negotiations based on the presented proposals and input feedback into their terminals after the negotiations. This feedback includes evaluations of the customer's emotional changes and responses during the negotiations. The server receives this feedback and uses it to generate future proposals, further optimizing the proposal content.

[0774] This system allows sales activities to be conducted based on customer emotions, which is expected to improve customer satisfaction.

[0775] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0776] Step 1:

[0777] The terminal provides the user with an interface for entering customer information. The user enters basic customer information, past purchase history, and industry information. Specifically, the user manually enters data into a form on the terminal and completes the input by pressing the submit button. The entered information is stored on the terminal as customer data.

[0778] Step 2:

[0779] The terminal sends the entered customer information to the server. This transmission process is performed using encrypted communication via the HTTPS protocol. The terminal converts the data to JSON format and sends it to the server over the network. The input is customer information, and the output is encrypted data sent to the server.

[0780] Step 3:

[0781] The server saves the received data to the database. Specifically, the server uses SQL to create a new customer information entry in the database. The input is customer information in JSON format, and the output is the record saved in the database.

[0782] Step 4:

[0783] The server analyzes customer needs using machine learning algorithms. The algorithms are executed using Python and the scikit-learn library to identify customer interests. The input is customer data retrieved from a database, and the output is the identified customer needs.

[0784] Step 5:

[0785] The server analyzes user and customer emotions using an emotion engine. It extracts emotions from text data using a natural language processing library and generates quantified emotional states. The input is the user and customer communication history, and the output is emotional data.

[0786] Step 6:

[0787] The server automatically generates suggestions based on customer needs and sentiment data. Utilizing a generative AI model, it creates multiple suggestions based on prompts and selects the most suitable one. The input is customer needs and sentiment data, and the output is the generated suggestions.

[0788] Step 7:

[0789] The server sends the proposal to the terminal and provides it to the user. The server formats the generated proposal and converts it into a format that can be displayed on the user's terminal. The input is the generated proposal, and the output is the proposal information displayed on the user's terminal.

[0790] Step 8:

[0791] The terminal receives feedback from the user after a business negotiation. This feedback includes changes in emotions during the negotiation and the customer's reactions. Specifically, the user enters information into a feedback form on the terminal and sends it to the server. The input is the user's feedback information, and the output is the submission of that feedback.

[0792] Step 9:

[0793] The server analyzes the received feedback and incorporates it into the proposal generation process. The server stores the feedback in a database and updates the algorithm for future proposal generation. The input is user feedback, and the output is the updated proposal generation algorithm.

[0794] (Application Example 2)

[0795] 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".

[0796] Traditional customer suggestion systems simply identify needs and make suggestions based on customer purchase history and industry information, making it difficult to provide appropriate suggestions that take into account customer emotions and real-time impact. As a result, challenges remain regarding the effectiveness of suggestions and customer satisfaction.

[0797] 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.

[0798] In this invention, the server includes a device for collecting and storing customer information, a device for analyzing the collected customer information to identify customer needs, and a device for recognizing and analyzing user emotions based on voice and image data. This enables the automatic generation of optimized suggestions that take into account not only customer needs but also emotional aspects.

[0799] "Customer information" refers to basic data about customers, including purchase history, industry information, and past behavioral patterns, which form the basis for analysis.

[0800] A "storage device" is an electronic device used to safely and efficiently store information recorded as digital data.

[0801] An "analytical device" is a device that processes input data based on a specific algorithm and has the function of finding useful patterns and trends within that data.

[0802] A "device that recognizes emotions" is a device that analyzes a user's facial expressions and tone of voice through audio and image data to determine their emotional state.

[0803] A "proposal generation device" is a device that automatically creates optimized proposals for each customer based on analyzed needs and sentiment data.

[0804] An "information processing device" is a computer system that combines hardware and software for inputting, processing, and outputting data.

[0805] A "feedback collection device" is a device that records user reactions and evaluations and uses them for subsequent analysis and improvement.

[0806] As a means of implementing this invention, a system is realized that automatically generates suggestions that take into account the emotions of customers and users, thereby improving customer satisfaction on e-commerce sites. The system consists of a server, an information terminal, and a user.

[0807] The server stores customer information collected from information terminals and manages it as digital data. This includes customers' past purchase history and industry information. The server also has machine learning algorithms implemented to analyze and identify customer needs. It is also equipped with an emotion analysis device that can recognize and analyze user emotions in real time based on voice and image data. Possible software to be used includes OpenCV and Google Cloud Vision API.

[0808] An information terminal is a means for users to access a server and input / update necessary information. Through the terminal, users input past purchase data and current industry information, and receive suggestions.

[0809] The generated suggestions include product recommendations that take into account the customer's emotional state. For example, a customer who wants to relax will be recommended relaxation-related products. These suggestions are generated using an algorithm based on TensorFlow and provided to the information terminal.

[0810] Users can propose the most suitable products to customers based on suggestions provided from their information terminals. After the business negotiation, feedback on the proposals is collected from the information terminals and sent to the server. The server analyzes this feedback and uses it to improve the accuracy of future proposals.

[0811] A concrete example would be analyzing the emotions of a user who is relaxing on a holiday while browsing an online shopping site, and then recommending products that are suitable for them in real time. This allows users to receive suggestions that are more likely to be accepted.

[0812] Example of a prompt:

[0813] "Please provide a description of a system that analyzes users' facial expressions and voice data in real time and suggests relaxation-related products tailored to their emotions."

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The information terminal receives basic customer information, past purchase history, and industry information as input from the user. This input data is then transmitted to the server in digital format. The server stores the transmitted information in a database and prepares it as foundational data for identifying customer needs.

[0817] Step 2:

[0818] The server uses data received from information terminals to execute machine learning algorithms. This analyzes customer purchase history and industry information to identify customer needs. The customer needs inferred based on the generative AI model are stored in a database.

[0819] Step 3:

[0820] The device acquires audio and image data in real time from its camera and microphone and sends it to an emotion analysis device. The server processes this data using the emotion analysis device to determine the user's emotional state. Using OpenCV and the Google Cloud Vision API, it analyzes voice tone and facial expressions and reflects the emotions as numerical data in a database.

[0821] Step 4:

[0822] The server combines customer needs and user emotional state data identified in the previous step to generate recommendations. Based on the generative AI model, it automatically selects the products and services best suited to the needs and emotions and outputs them as recommendations. This uses an algorithm based on TensorFlow.

[0823] Step 5:

[0824] The server sends the generated proposals to the information terminal and provides them to the user. The user then recommends products to customers and conducts business negotiations based on these proposals. They can also develop strategies to increase the likelihood of the proposals being accepted.

[0825] Step 6:

[0826] After the business negotiation, the information terminal collects feedback from the user. This feedback includes evaluations of emotional changes during the negotiation and the degree to which the proposal was accepted. The feedback data is sent from the terminal to the server.

[0827] Step 7:

[0828] The server analyzes the feedback it receives and improves the system's proposed model. This adjusts the algorithm so that subsequent proposals using the generative AI model become more accurate.

[0829] 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.

[0830] 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.

[0831] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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."

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] The following is further disclosed regarding the embodiments described above.

[0851] (Claim 1)

[0852] Means for collecting and storing customer information,

[0853] A means of identifying customer needs by analyzing collected customer information,

[0854] A means of automatically generating proposals based on identified customer needs,

[0855] A means of providing the generated suggestions to the user,

[0856] A means of collecting user feedback on suggestions and incorporating it into the analysis,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, which includes past purchase history and industry information as customer information.

[0860] (Claim 3)

[0861] The system according to claim 1, which uses a machine learning algorithm to identify customer needs.

[0862] "Example 1"

[0863] (Claim 1)

[0864] A means for collecting and storing customer information using an information processing device,

[0865] A means of identifying customer demand by analyzing stored customer information using an analysis device,

[0866] Automatic generation means including a generation device that generates proposals based on the needs of identified customers,

[0867] A means of presenting the generated proposal to the information user through a display device,

[0868] A means of collecting opinions on proposals from information users and reflecting them in the analysis results,

[0869] A means of receiving input from an information gathering terminal and operating a generated AI model,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, which includes past purchase history and market data as customer information.

[0873] (Claim 3)

[0874] The system according to claim 1, which uses machine learning techniques to identify customer demand.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] Means for collecting and storing customer information,

[0878] A means of identifying customer needs by analyzing collected customer information,

[0879] A means of automatically generating proposals based on identified customer needs,

[0880] A means of providing the generated suggestions to the user,

[0881] A means of collecting user feedback on suggestions and incorporating it into the analysis,

[0882] A means for identifying a target using an identification device and displaying recommended information in real time based on the identification information,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, which includes past purchase history and industry information as customer information.

[0886] (Claim 3)

[0887] The system according to claim 1, which uses a machine learning algorithm to identify customer needs.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] Means for collecting and storing customer information,

[0891] A means of identifying customer needs by analyzing collected customer information,

[0892] A means of automatically generating proposals based on identified customer needs,

[0893] When generating proposals, a means of analyzing customer and user sentiment and considering the results,

[0894] A means of providing the generated suggestions to the user,

[0895] A means of collecting user feedback on suggestions and incorporating it into the analysis,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, which includes past purchase history and field information as customer information.

[0899] (Claim 3)

[0900] The system according to claim 1, which uses a machine learning algorithm to identify customer needs.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A device for collecting and storing customer information,

[0904] A device that analyzes collected customer information to identify customer needs,

[0905] A device that recognizes and analyzes user emotions based on voice and image data,

[0906] A device that automatically generates suggestions based on identified customer needs and sentiment data,

[0907] A device that provides the generated proposals to an information processing device,

[0908] A device that collects feedback on proposals from information processing equipment and incorporates it into the analysis,

[0909] A device that includes this.

[0910] (Claim 2)

[0911] The apparatus according to claim 1, wherein customer information includes past purchase history and industry information, and further includes the user's emotional state.

[0912] (Claim 3)

[0913] The apparatus according to claim 1, which uses machine learning technology to identify customer needs and analyze the emotional state of a user. [Explanation of symbols]

[0914] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting and storing customer information, A means of identifying customer needs by analyzing collected customer information, A means of automatically generating proposals based on identified customer needs, A means of providing the generated suggestions to the user, A means of collecting user feedback on suggestions and incorporating it into the analysis, A system that includes this.

2. The system according to claim 1, which includes past purchase history and industry information as customer information.

3. The system according to claim 1, which uses a machine learning algorithm to identify customer needs.

Images