system

Abstract

We provide the system. [Solution] A means for inputting customer information, A means of converting the entered customer information into a data format and sending it to the server, A means of storing received customer information in a database, Means for verifying and pre-processing stored customer information, A means for performing analysis based on pre-processed customer information and generating optimal proposals, A means of sending the generated proposal content to a terminal into which customer information has been entered, A means of displaying the proposed content on a terminal, 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 method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance 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 on-site sales activities, in order for new sales staff and other staff to make effective proposals to customers, information and analysis results based on past closing data are required. However, these data are often managed manually and may not be accessible quickly when needed. Also, in a proposal method that depends on the experience and knowledge of individual staff, there may be variations in the quality of proposals and the closing rate. Furthermore, in order to find an optimal plan for each applicant, it is necessary to efficiently analyze various data. Therefore, there is a need for a system that effectively supports such on-site sales activities and improves the closing rate.

Means for Solving the Problems

[0005] To solve the above-mentioned problems, the present invention provides means for inputting customer information, means for converting the input customer information into a data format and transmitting it to a server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal from which the customer information was input, and means for displaying the proposal content on the terminal. In particular, by analyzing past high-conversion rate data using a machine learning algorithm and predicting the optimal proposal method, it is possible to make proposals with a high conversion rate without relying on experience or knowledge. Furthermore, by formatting the proposal content based on customer information and converting it into a data format before transmitting it to the terminal, appropriate proposals can be displayed efficiently. In this way, the present invention provides a system that effectively supports on-site sales activities and improves the conversion rate.

[0006] "Customer information" refers to data related to customers in sales activities, including items such as "current carrier," "current charges," "number of devices used by the family," "internet environment," and "intended use."

[0007] "Input method" refers to the interface means by which users (sales staff) input customer information into the system, and includes devices such as keyboards and touchscreens.

[0008] "Means of converting to data format" refers to a function that converts the entered customer information into a format that is easy for the server to process (e.g., JSON format).

[0009] "Transmission means" refers to communication means for sending information converted into data format to a server, and includes communication protocols via the internet or local networks.

[0010] A "server" refers to a computer system that receives customer information transmitted from an input device, stores it, analyzes it, generates suggestions, and retransmits it.

[0011] A "database" refers to a data storage system that a server uses to centrally manage and store customer information.

[0012] "Verification means" refers to functions that check the consistency, accuracy, and completeness of received and stored customer information.

[0013] "Preprocessing means" refers to processes that format data into an appropriate format before analysis, and includes categorization and standardization.

[0014] "Analysis means" refers to a function that generates optimal proposals using machine learning algorithms and the like, based on pre-processed customer information.

[0015] "Generation means" refers to the function that generates optimal proposals for customers based on the analyzed results.

[0016] "Transmission means" refers to communication means for retransmitting the generated proposal content to the original input means.

[0017] "Display means" refers to interface means for visually displaying the retransmitted proposal content to the user, and includes monitors and touchscreens.

[0018] A "machine learning algorithm" refers to a computational method that learns patterns based on past data and makes predictions or suggestions for new data.

[0019] "High conversion rate data" refers to past sales data that particularly resulted in successful transactions, and serves as benchmark information for evaluating the effectiveness of proposals.

[0020] "Formatting means" refers to a function that formats the generated proposal content into a specific format. [Brief explanation of the drawing]

[0021] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0022] ]>Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0023] First, let's explain the terminology used in the following explanation.

[0024] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0025] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0026] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0027] 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).

[0028] 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."

[0029] [First Embodiment]

[0030] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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".

[0042] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The system aims to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[0043] The user (sales staff) enters customer information using a terminal. The terminal converts this information into an appropriate data format (e.g., JSON format) and sends it to the server. The server receives this information and stores it in a database. Furthermore, the server validates and preprocesses the data and performs analysis to generate optimal recommendations based on this information. The generated recommendations are then sent back to the terminal and displayed to the user.

[0044] Explanation of the program's processing

[0045] Data entry and transmission

[0046] The user enters customer information using their device. For example, they might enter information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". The entered information is converted to JSON format by the device and sent to the server via an HTTP request.

[0047] Data storage and management

[0048] The server parses the JSON data received from the terminal and stores it in the database. The database organizes and stores customer information so that it can be used for analysis later.

[0049] Data validation and preprocessing

[0050] The server verifies the stored data, checking for inaccuracies or missing data. Next, it performs preprocessing such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale).

[0051] Data Analysis

[0052] The server uses historical high-conversion rate data to apply machine learning algorithms and generate optimal proposals for customers. In this process, it compares and analyzes historical data with newly entered customer information, using a model to predict the best proposal.

[0053] Proposal generation and submission

[0054] Based on the analysis results, the server generates optimal recommendations for the customer. For example, it might generate a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use." The generated recommendations are converted to JSON format and sent to the device.

[0055] Suggestion display

[0056] The terminal analyzes the suggestions received from the server and displays them visually to the user. The user can then make suggestions to customers based on these displayed suggestions.

[0057] Explanation of specific examples

[0058] For example, a user might input customer information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of devices used by family: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[0059] Based on past high conversion rate data, the server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice and generates this proposal. This generated proposal is sent to the terminal and displayed to the user. The user can then use this proposal to improve their conversion rate.

[0060] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal proposals based on customer information and effectively support sales activities.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] The user enters customer information into an input form on their device. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Once the user has finished entering the information, they press the submit button.

[0064] Step 2:

[0065] The terminal verifies the entered customer information in real time, checking for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format, such as JSON.

[0066] Step 3:

[0067] The terminal sends the converted JSON-formatted customer information to the server using an HTTP request. It is recommended to use the SSL / TLS protocol for security purposes during this process.

[0068] Step 4:

[0069] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory in preparation for the next processing step.

[0070] Step 5:

[0071] The server stores the received customer information in a database. Specifically, it inserts information such as customer ID, carrier information, charges, number of family members using the service, internet environment, and usage purpose into the corresponding tables.

[0072] Step 6:

[0073] The server verifies the stored customer information. It checks whether the data is consistent, free from non-numeric data, and free from missing data. If any deficiencies are found, it records an error log and sends an alert to the relevant parties.

[0074] Step 7:

[0075] The server preprocesses the verified data. Specifically, it performs categorization, such as coding carrier names, and standardization, such as converting charges to a specific scale.

[0076] Step 8:

[0077] The server performs analysis based on pre-processed data. It uses historical high-conversion rate data to apply machine learning algorithms (e.g., decision trees and random forests) to predict the optimal proposal.

[0078] Step 9:

[0079] The server generates optimal recommendations based on the analysis results. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0080] Step 10:

[0081] The server converts the generated proposal into JSON format and sends it to the terminal. It also uses an HTTP response for this process, applying the SSL / TLS protocol as needed.

[0082] Step 11:

[0083] The terminal analyzes the received suggestions and displays them visually to the user. The suggestions are displayed appropriately in a GUI (Graphical User Interface) to make them easy for the user to understand.

[0084] Step 12:

[0085] The user makes a proposal to the customer based on the proposal displayed on the device. If the customer agrees to the proposal, the user proceeds with the contract closing procedure.

[0086] (Example 1)

[0087] 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."

[0088] Traditional systems often involve manual processes from customer information input to the generation and display of optimal proposals, resulting in low efficiency. Furthermore, proposals are uniform across all customers, making it difficult to tailor them to individual needs. Consequently, there are limitations to improving the conversion rate, hindering efficient sales activities.

[0089] 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.

[0090] In this invention, the server includes means for inputting customer information using a device used by the user, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for applying a machine learning algorithm using past high conversion rate data to generate optimal proposal content, means for transmitting the generated proposal content to the device into which the customer information was input, and means for displaying the proposal content on the device. This makes it possible to automatically generate optimal proposal content based on customer information and to make proposals to customers quickly and efficiently.

[0091] "User" refers to an individual or organization that uses the system to input and verify customer information.

[0092] "Device" refers to a device used for inputting customer information and displaying proposals (e.g., personal computer, smartphone, tablet, etc.).

[0093] "Customer information" refers to detailed data about a customer (e.g., current carrier, charges, number of devices used, internet environment, usage purpose, etc.).

[0094] "Data format" refers to a specific structure (e.g., JSON format) that a computer system uses to understand and process data.

[0095] A "server" refers to a computer system that receives, stores, analyzes, generates, and transmits data.

[0096] A "database" refers to a structured data storage system used to efficiently store and manage data such as customer information and analytical results.

[0097] "Preprocessing" refers to the steps of standardizing, categorizing, and validating data for analysis.

[0098] A "machine learning algorithm" refers to a computational method that automatically learns patterns and rules from data and uses that knowledge to make predictions and classifications.

[0099] "Optimal proposal content" refers to a proposal message that is deemed most effective or appropriate for a particular customer, based on their customer information.

[0100] "Past high conversion rate data" refers to proposals and sales data that were effective in the past, and is used as data for training machine learning algorithms.

[0101] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The purpose of this system is for a server to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal.

[0102] The user (sales staff) enters customer information using a terminal. Specifically, they use devices such as smartphones, tablets, or personal computers to enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." This information is converted to JSON format by the terminal and sent to the server via an HTTP request.

[0103] The server is hardware that runs programs using Python or Java (registered trademark). It first parses JSON data received from terminals and stores it in a database. Customer information is organized and stored in this database using SQL or NoSQL technologies. The stored data is first verified for accuracy and completeness. After that, preprocessing is performed, such as coding carrier names and standardizing charges.

[0104] The server analyzes data using machine learning algorithms. Specifically, it uses Python's Scikit-learn library and TENSORFLOW® to compare and analyze historical high-conversion rate data with newly entered customer information. This builds a model that predicts the optimal recommendation. Based on this model, the server generates the optimal recommendation. For example, it might generate a specific recommendation message such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[0105] The generated proposals are converted back into JSON format and sent to the terminal using an HTTP request. The terminal parses the received proposals and displays them in the user interface. Based on these displayed proposals, the user can then make the most appropriate proposals for the customer.

[0106] As a concrete example, a user enters customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." This information is converted to JSON format by the device and sent to the server. The server stores and preprocesses the information, and uses a machine learning algorithm to generate a recommendation that "NTT Docomo's family discount plan is optimal" based on this information. This recommendation is sent to the device and displayed to the user.

[0107] Examples of prompt statements are as follows:

[0108] "Please generate the optimal proposal based on the customer information. The customer's current carrier is NTT Docomo, their current monthly fee is 5,000 yen, they use 3 devices, their internet connection is fiber optic, and their usage is video streaming, social media, and phone calls."

[0109] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0110] Program processing steps

[0111] Step 1: Data entry and submission

[0112] 1. The user enters customer information using the device. For example, they enter information such as: "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices used: 3", "Internet environment: Fiber optic connection", and "Usage: Watching videos, using social media, making calls".

[0113] 2. The terminal converts the entered information into JSON format. Specifically, it formats the data from the input form as a JSON object using JavaScript® or Python.

[0114] 3. The terminal sends the generated JSON data to the server using an HTTP POST request. This communication is performed by specifying the endpoint URL.

[0115] Input: Customer information entered by the user (carrier, fee, number of devices used, etc.)

[0116] Output: Customer information converted to JSON format is sent to the server.

[0117] Step 2: Data storage and management

[0118] 1. The server parses the JSON data received from the terminal. Specifically, it decodes the received data using Python's JSON library or Java's Gson library.

[0119] 2. The server connects to the database and stores the received customer information. Specifically, it executes commands to insert data using SQL statements or NoSQL queries.

[0120] 3. The server generates a confirmation message that the save was successful and sends it back to the terminal. This message notifies the user that the save was performed successfully.

[0121] Input: Customer information in JSON format sent from the terminal.

[0122] Output: Customer information is saved to the database and a confirmation message is sent to the terminal.

[0123] Step 3: Data validation and preprocessing

[0124] 1. The server reads the data stored in the database. Specifically, it executes SQL queries.

[0125] 2. The server checks for inaccurate or missing data. For example, it uses validation scripts to ensure that all required fields are present.

[0126] 3. The server categorizes and standardizes the data. Specifically, it codes carrier names and performs preprocessing to convert pricing data to a specific scale.

[0127] Input: Stored customer information data

[0128] Output: Verified and pre-processed customer information data

[0129] Step 4: Data Analysis

[0130] 1. The server applies machine learning algorithms using historical high-conversion rate data. Specifically, it uses the Scikit-learn library in Python.

[0131] 2. The server compares newly entered customer information with past data to predict the optimal recommendation. Algorithms such as logistic regression and decision trees are used.

[0132] 3. The server retrieves the analysis results and generates optimal suggestions. For example, it generates suggestions based on the prediction results of a machine learning model.

[0133] Input: Verified and pre-processed customer information data, historical high conversion rate data

[0134] Output: Optimal proposal content

[0135] Step 5: Generate and submit proposals

[0136] 1. The server creates a specific message based on the optimal recommendation. For example, it might generate a suggestion such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0137] 2. The server converts the generated proposal content into JSON format. Specifically, it formats the proposal content as a JSON object.

[0138] 3. The server sends the generated JSON data to the terminal using an HTTP POST request.

[0139] Input: Optimal proposal content

[0140] Output: The suggested content, converted to JSON format, is sent to the terminal.

[0141] Step 6: Proposal Display

[0142] 1. The terminal parses the JSON-formatted proposal received from the server. Specifically, it decodes the received data using JavaScript or Python's JSON library.

[0143] 2. The terminal displays the analyzed suggestions in the user interface. Specifically, it uses HTML and CSS to display the suggestion messages on the screen.

[0144] 3. Users can make suggestions to customers based on the displayed suggestions. Specifically, this can involve reading aloud messages displayed on the device or showing the screen.

[0145] Input: Proposal content in JSON format sent from the server

[0146] Output: Suggestions displayed in the user interface

[0147] The above describes the processing flow of this system's program.

[0148] (Application Example 1)

[0149] 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."

[0150] In physical stores, it is difficult for sales staff to quickly and accurately make the best recommendations to customers. Understanding customer needs and purchase history, and then proposing appropriate products and services based on that, requires the ability to process a large amount of information instantly. Furthermore, there is a need for a system that automatically generates optimal recommendations based on customer information and delivers those recommendations to customers in a timely manner. This creates a need for a system that can reduce the burden on sales staff and improve the closing rate.

[0151] 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.

[0152] In this invention, the server includes means for inputting customer information, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information, means for displaying the proposal content on the terminal, means including a terminal that runs a sales support application in a physical store, means for enabling sales staff to confirm the generated proposal content in real time, and means for automatically generating proposal content using a generation AI model and providing it to sales staff as a prompt message. This makes it possible for sales staff to receive optimal proposals in real time based on customer information and immediately make proposals to customers.

[0153] "Customer information" refers to personal attributes, purchase history, interests, and other information obtained through input by sales staff.

[0154] "Data format" refers to a form of data that can be processed by a computer, and in this context, it specifically refers to the JSON format.

[0155] A "server" is a computer system that receives, processes, stores, and analyzes customer information.

[0156] A "database" is a digital storage medium used to systematically organize and store received customer information.

[0157] "Verification" is the process of confirming that stored customer information is accurate and identifying inaccurate or incomplete data.

[0158] "Preprocessing" refers to the procedure of converting customer information into a format that is easy to analyze, and includes, for example, data categorization and standardization.

[0159] "Analysis" is the process of analyzing data to generate appropriate proposals based on pre-processed customer information.

[0160] "Proposed content" refers to information about products and services that are best suited to the customer, generated through analysis.

[0161] A "terminal" refers to a device operated by sales staff to input customer information or display sales proposals. In this context, it mainly refers to smartphones and tablets.

[0162] A "physical store" is a physical commercial facility where customers actually visit and make purchases.

[0163] A "sales support application" is software that runs on a device and provides information to help sales staff make the best possible proposals to customers.

[0164] "Real-time" means that the time between information being entered, processing it immediately, and the display of results is extremely short, almost instantaneous.

[0165] A "generative AI model" is an algorithm or program that uses machine learning to automatically generate new suggestions.

[0166] A "prompt message" is a guidance message output by a generation AI model, used by sales staff when making suggestions to customers.

[0167] This invention relates to a system for enabling sales staff in physical stores to make optimal suggestions in real time based on customer information. The system aims to perform a series of steps including inputting customer information, converting it to a data format, transmitting it to a server, storing the customer information in a database, verifying and preprocessing the data, generating optimal suggestions through analysis, and transmitting and displaying the generated suggestions to a terminal.

[0168] The hardware required to implement the system includes devices such as smartphones and tablets, servers, and a database management system (e.g., MySQL®). The software includes libraries for implementing machine learning algorithms (e.g., TensorFlow), the HTTP protocol for data transmission and reception, and sales support applications for physical stores.

[0169] Entering and submitting customer information

[0170] The user (sales staff) enters customer information using a smartphone or tablet. This information includes the customer's name, age, purchase history, and product categories of interest. The entered information is converted to JSON format on the device and sent to the server via an HTTP POST request.

[0171] Data processing on the server

[0172] The server parses the JSON data received from the terminal and stores it in the database. Next, it verifies the stored data to check for any inaccuracies or incomplete data. After this, as a data preprocessing step, it performs categorization and standardization, such as mapping ages to specific age groups.

[0173] Analysis of customer information and generation of proposals

[0174] The server uses a machine learning model (e.g., TensorFlow) to generate optimal suggestions based on pre-processed customer information and past high-conversion rate data. In this process, a generative AI model is used to create prompt messages based on the customer information.

[0175] Submitting and displaying proposals

[0176] The generated suggestions are converted back into JSON format and sent to the terminal. This information is displayed visually on the terminal, allowing sales staff to check it in real time. Based on the displayed suggestions, users can then propose products and services to customers.

[0177] Specific example

[0178] When a customer visits a physical store, the sales staff enters the following information into a smartphone app:

[0179] Name: Customer A

[0180] Age: 35

[0181] Purchase history: Smartphones, tablets

[0182] Product categories of interest: Home appliances, audio equipment

[0183] This information is converted to JSON format and sent to the server. The server stores the data and uses a machine learning model to generate a suggestion such as, "If customer A is particular about sound quality, we recommend the latest Bluetooth speaker." This information is then sent back to the application, where sales staff can review it in real time and make suggestions to customers.

[0184] Example of a prompt

[0185] "Customer A, 35 years old, has come into the store. He has previously purchased a smartphone and a tablet, and is currently interested in home electronics and audio equipment. Please provide him with the best product recommendations."

[0186] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0187] Step 1:

[0188] User enters customer information

[0189] The user (sales staff) uses a smartphone or tablet to enter information such as the customer's name, age, purchase history, and product categories of interest. This information is converted into JSON format.

[0190] Input: Customer information (name, age, purchase history, product categories of interest)

[0191] Output: Customer information in JSON format

[0192] Step 2:

[0193] The terminal sends customer information to the server.

[0194] The terminal sends customer information, converted to JSON format, to the server via an HTTP POST request.

[0195] Input: Customer information in JSON format

[0196] Output: HTTP request to the server

[0197] Step 3:

[0198] The server saves customer information to the database.

[0199] The server parses the received JSON data and saves it to the database.

[0200] Input: Customer information in JSON format

[0201] Output: Customer information stored in the database

[0202] Step 4:

[0203] The server verifies customer information.

[0204] The server verifies the stored customer information to check for inaccurate or incomplete data. Inaccurate data is corrected, and incomplete data is assigned appropriate default values.

[0205] Input: Customer information stored in the database

[0206] Output: Verified customer information

[0207] Step 5:

[0208] The server preprocesses customer information.

[0209] The server categorizes and standardizes verified customer information. For example, it maps age to a specific age group.

[0210] Input: Verified customer information

[0211] Output: Preprocessed customer information

[0212] Step 6:

[0213] The server analyzes customer information.

[0214] The server generates optimal proposals using a generative AI model (e.g., TensorFlow) based on pre-processed customer information and past high conversion rate data.

[0215] Input: Pre-processed customer information, historical high conversion rate data

[0216] Output: Optimal proposal content

[0217] Step 7:

[0218] The server formats the proposal based on customer information.

[0219] The server formats the generated proposal based on customer information and converts it back into JSON format.

[0220] Input: Optimal proposal content

[0221] Output: Proposal in JSON format

[0222] Step 8:

[0223] The server sends the proposal to the terminal.

[0224] The server sends the proposed content, converted to JSON format, to the terminal via an HTTP request.

[0225] Input: Proposal content in JSON format

[0226] Output: HTTP request to terminal

[0227] Step 9:

[0228] The device displays the suggested content.

[0229] The terminal analyzes the received proposal and displays it visually. Sales staff then review the proposal and make it to the customer.

[0230] Input: Proposal content in JSON format

[0231] Output: Suggestion displayed to sales staff

[0232] Step 10:

[0233] The user makes a proposal to the customer based on the proposed content.

[0234] The user (sales staff) makes product and service recommendations to the customer based on the displayed suggestions.

[0235] Input: Suggestion displayed to the sales staff

[0236] Output: Proposals for the best products and services for customers

[0237] 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.

[0238] This invention relates to a system that generates optimal proposals using customer information to improve the conversion rate. Furthermore, by combining this with an emotion engine that recognizes user emotions, the system can personalize proposals and provide more accurate suggestions. The purpose of this system is for the server to analyze customer information and emotion information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[0239] Explanation of the program's processing

[0240] Data entry and transmission

[0241] The user enters customer information into an input form on the device. For example, they might enter information such as "Current carrier: NTT Docomo," "Current monthly fee: 5,000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." Simultaneously, an emotion engine built into the device analyzes the user's facial expressions and voice to collect emotion data.

[0242] Conversion to data format and transmission

[0243] The terminal verifies the entered customer information and sentiment data in real time to check for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format such as JSON and sends it to the server via an HTTP request.

[0244] Data reception and storage

[0245] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. The server then stores this customer information and sentiment data in the database. The database organizes and stores the customer information and sentiment data so that it can be used for analysis later.

[0246] Data validation and preprocessing

[0247] The server verifies the stored data, checking for inaccuracies or missing data. Next, preprocessing is performed, such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[0248] Data analysis and proposal generation

[0249] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical high-conversion rate data to predict optimal recommendations. By incorporating sentiment data into the analysis, it can generate recommendations tailored to the user's psychological state. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[0250] Submitting and displaying proposals

[0251] The server converts the generated proposal content into JSON format and sends it to the terminal. The terminal parses the proposal content received from the server and displays it visually to the user. The proposal content is displayed in an easy-to-understand manner using a GUI (Graphical User Interface). The user can review this displayed proposal content and make a proposal to the customer.

[0252] Explanation of specific examples

[0253] For example, a user might input customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." The emotion engine then analyzes the user's facial expressions and voice to determine that "User's emotional state: Positive." When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[0254] The server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice, based on past high conversion rate data, current customer information, and sentiment data. Furthermore, based on sentiment data, it predicts that this offer will be even more effective because the user is in a positive state. This generated offer is sent to the device and displayed to the user. The user can then use this offer to their customers to improve their conversion rate.

[0255] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal suggestions based on customer information and emotional information, thereby effectively supporting sales activities.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] Users enter customer information into input forms on their devices. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine analyzes this to generate emotion data.

[0259] Step 2:

[0260] The terminal verifies the entered customer information and sentiment data in real time, checking for any missing or inaccurate data. Once verification is complete, it converts the information into an appropriate data format, such as JSON.

[0261] Step 3:

[0262] The terminal sends the converted JSON-formatted customer information and sentiment data to the server using an HTTP request. SSL / TLS protocol is used to ensure security during this process.

[0263] Step 4:

[0264] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory and added to a queue for later processing.

[0265] Step 5:

[0266] The server stores received customer information and sentiment data in a database. Specifically, it inserts customer ID, carrier information, charges, number of family members using the service, internet environment, usage purpose, and sentiment data into the corresponding tables.

[0267] Step 6:

[0268] The server verifies the stored data. This verification includes checking for data consistency, the presence of invalid data, and missing data. If errors are detected, appropriate error handling and logging are performed.

[0269] Step 7:

[0270] The server preprocesses the verified data. This includes categorization (e.g., converting carrier names to codes) and standardization (e.g., converting rates to a unified scale), and sentiment data is also standardized.

[0271] Step 8:

[0272] The server analyzes pre-processed data. It uses machine learning algorithms (e.g., decision trees, random forests) to analyze historical high-conversion rate data and newly entered customer information to generate optimal recommendations. By including emotional data in the analysis, it provides recommendations tailored to the user's psychological state.

[0273] Step 9:

[0274] The server generates recommendations based on the analysis results. For example, it might set up a specific recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0275] Step 10:

[0276] The server converts the generated proposal content back into JSON format and sends it to the terminal. SSL / TLS protocol is used to ensure security during this process.

[0277] Step 11:

[0278] The terminal analyzes the suggestions received from the server and displays them visually to the user. The suggestions are displayed through a GUI in a way that is easy for the user to understand.

[0279] Step 12:

[0280] Users review the proposals displayed on their devices and then submit them to customers. If the customer agrees to the proposal, the user proceeds with the closing process. This approach can improve the closing rate.

[0281] (Example 2)

[0282] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0283] Proposals based only on customer information tend to remain general and uniform proposals and often cannot fully meet the needs of individual customers. Therefore, it is difficult to improve the conversion rate, and the generation of more personalized proposals has become an issue. In addition, since conventional systems cannot generate proposals considering the psychological state of users, it is difficult to increase customer satisfaction.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting customer information and emotion data, means for converting the input customer information and emotion data into a data format and transmitting it to the server, means for storing the received customer information and emotion data in a database, means for verifying and preprocessing the stored customer information and emotion data, means for performing analysis based on the preprocessed customer information and emotion data and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information, and means for displaying the proposal content on the terminal. Thereby, it becomes possible to generate more accurate and personalized proposals according to the needs and psychological states of individual customers.

[0285] "Customer information" is detailed data regarding an individual or a company that is the target of providing services or products.

[0286] "Emotion data" is data indicating a psychological state analyzed from a user's expression, voice, body movements, etc.

[0287] "Data format" is data organized according to specific structures and rules, and is a format for facilitating processing and communication.

[0288] A "server" is a computer system that stores, processes, and transmits data.

[0289] A "database" is a system for efficiently and systematically storing and managing digital information.

[0290] "Preprocessing" refers to a series of processes that prepare data for easier analysis, including imputation of missing values ​​and standardization.

[0291] A "machine learning algorithm" is a computational method that learns patterns and regularities based on large amounts of data, and uses that learning to make predictions and classifications on new data.

[0292] "Recommended content" refers to recommendations for the most suitable services and products for the customer, generated based on the analysis results.

[0293] A "terminal" is a device that a user directly operates to input or display information.

[0294] "Transmission" is the process of transferring data or information to a specific receiving device.

[0295] "Display" refers to the act of making information visible, or the technology used for that purpose.

[0296] This invention is a system that generates optimal proposals based on customer information and emotional data, thereby improving the conversion rate. This system is realized through the cooperation of a server and terminals.

[0297] The user operates the terminal and enters customer information. This customer information includes items such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the terminal is equipped with an emotion engine that analyzes the user's facial expressions and voice to collect emotional data. This emotion engine also allows the user's psychological state to be understood in real time.

[0298] The terminal verifies the entered customer information and sentiment data in real time to check for any missing or inaccurate data. If there are no problems, it converts the information to JSON format and sends it to the server via an HTTP request. The server receives the data sent from the terminal, temporarily stores it in memory, and then stores the customer information and sentiment data in the database.

[0299] The server re-verifies the stored data to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., charges are converted to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[0300] The server uses machine learning libraries such as Python's Scikit-learn to perform analysis based on pre-processed customer information and sentiment data. It applies algorithms using historical high-conversion rate data to predict the optimal proposal. By incorporating sentiment data into the analysis, it can generate personalized proposals tailored to the user's psychological state. The generated proposals are then converted to JSON format and sent to the terminal.

[0301] The terminal analyzes the proposals received from the server and displays them visually to the user. This display is designed to be user-friendly using front-end frameworks such as React.js and Vue.js. Users can review the displayed proposals and present them to customers to improve their conversion rates.

[0302] Explanation of specific examples

[0303] For example, a user enters the following customer information:

[0304] Current carrier: NTT Docomo

[0305] Current fee: 5000 yen per month

[0306] Number of devices used by the family: 3 units

[0307] Internet environment: Fiber optic line

[0308] Usage: Video viewing, SNS use, calling

[0309] Furthermore, it is recognized by the emotion engine that "User's emotional state: Positive". The terminal converts this information into JSON format and sends it to the server. After the server receives the data and stores it in the database, it applies a machine learning algorithm using Scikit-learn of Python. Based on the high success rate data, it is determined that the "NTT Docomo family plan" is optimal, and it is predicted that the proposal will be effective because the user is in a positive state.

[0310] The generated proposal content is as follows:

[0311] The NTT Docomo family plan is recommended. It is especially optimal for customers who value video viewing and SNS use.

[0312] The server sends this proposal content to the terminal, and the terminal displays it to the user using the GUI. The user can view this proposal content and present it to the customer to improve the success rate.

[0313] In this way, the system of the present invention can generate optimal proposal content based on customer information and emotion data, and effectively support sales activities.

[0314] The flow of specific processing in Example 2 will be described using FIG. 13.

[0315] Step 1: Data input and emotion analysis

[0316] The user enters customer information into an input form on the device. This customer information includes items such as "current carrier," "current charges," "number of family devices," "internet environment," and "intended use." The entered data is stored in the input fields on the device. Simultaneously, the device's built-in emotion engine analyzes the user's facial expressions and voice to collect emotion data. The obtained emotion data is saved in the input fields as emotion categories such as "joy," "sadness," and "surprise."

[0317] Step 2: Convert to data format and send

[0318] The terminal verifies the entered customer information and sentiment data in real time to ensure there is no missing or inaccurate data. Once this verification is complete, the terminal converts the information into JSON format. In this conversion process, text and numerical data are organized into a specific key-value pair format. The converted data is then sent to the server as an HTTP request.

[0319] Step 3: Data reception and storage

[0320] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. Next, the server stores this customer information and sentiment data in a database system. Assigning a unique identifier when storing the data in the database enables efficient searching.

[0321] Step 4: Data validation and preprocessing

[0322] The server re-verifies the data stored in the database to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., prices are scaled). At this time, sentiment data is also smoothed and formatted to a format suitable for analysis. The preprocessed data is stored in temporary memory to move on to the next analysis step.

[0323] Step 5: Data Analysis and Proposal Generation

[0324] The server uses machine learning libraries such as Python's Scikit-learn to analyze pre-processed data. Based on past high-conversion rate data, the server applies a machine learning algorithm to predict the optimal proposal. This algorithm finds patterns based on input customer information and sentiment data and generates appropriate proposals. For example, it might suggest a family discount plan to users with large families.

[0325] Step 6: Submit and view your proposal

[0326] The server converts the generated proposal content into JSON format and sends it to the terminal as an HTTP response. The terminal parses the proposal content received from the server and displays it visually to the user. This display uses front-end frameworks such as React.js or Vue.js and is formatted for easy viewing. The user can review this displayed proposal content and offer it to customers to improve the conversion rate.

[0327] The above outlines the specific processing steps of the system. Through the specific actions, inputs, and outputs in each step, the system can efficiently generate and display optimal suggestions.

[0328] (Application Example 2)

[0329] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0330] In brick-and-mortar stores, there is a need to quickly and accurately provide optimal product recommendations based on customer requests. However, conventional systems have difficulty considering customer emotional information, resulting in recommendations that do not adequately address the customer's psychological state. This can lead to lower conversion rates and reduced customer satisfaction. Therefore, there was a need for a system that could analyze customer emotional information in real time and provide optimal product recommendations.

[0331] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment information, means for converting the input customer information and sentiment information into a data format and transmitting it to the server, means for storing the received customer information and sentiment information in a database, means for verifying and pre-processing the stored customer information and sentiment information, means for performing analysis based on the pre-processed customer information and sentiment information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information and sentiment information, means for displaying the proposal content on the terminal, and means for visually displaying the proposal content via a smart device. This makes it possible to make highly accurate product proposals in real time, taking into account customer sentiment information.

[0332] "Customer information" refers to detailed information about a customer, such as their age, gender, products of interest, and purpose of use.

[0333] "Emotional information" refers to information indicating a customer's psychological state, obtained by analyzing their facial expressions and voice.

[0334] "Data format" refers to the format used to structure information according to certain rules and to exchange it between computers.

[0335] A "server" refers to a computer system that stores, processes, and analyzes data, and delivers the results to terminals.

[0336] A "database" refers to a system for efficiently storing and managing a collection of information.

[0337] "Preprocessing" refers to the process of standardizing data and formatting it into a suitable format for analysis prior to the analysis itself.

[0338] A "machine learning algorithm" refers to a computer algorithm that learns from customer information, emotional data, and past transaction data to predict the most suitable proposal.

[0339] A "smart device" refers to an electronic device with advanced functions for collecting emotional information and displaying suggestions, such as smart glasses or smartphones.

[0340] "Recommended content" refers to the optimal product or service recommendations generated based on customer information and emotional information.

[0341] This invention is a system for improving the efficiency of customer service in physical stores and increasing the conversion rate. This system implements a series of processes for inputting customer information and emotional information, and for generating and displaying optimal suggestions. The specific embodiments of this system are described in detail below.

[0342] Hardware and software usage

[0343] 1. Hardware

[0344] Smart devices: Smart glasses and smartphones are used to collect customer information and sentiment data, and to display suggested content. In this example, Google® Glass® and Vuzix Blade are assumed.

[0345] Server: A high-performance computer system is used to store, process, and analyze data. For example, a Dell PowerEdge is suitable.

[0346] 2. Software

[0347] Emotion Analysis Engine: To collect emotional information by analyzing customer facial expressions and voices, we utilize Microsoft® Azure® Cognitive Services and IBM Watson®.

[0348] Database Management System: Database management software such as MySQL or PostgreSQL is used to centrally manage customer information and sentiment information.

[0349] Machine learning algorithms: We use machine learning libraries such as TensorFlow and PyTorch to analyze customer information and sentiment information and generate optimal recommendations.

[0350] Data processing and data calculation

[0351] 1. Data entry and transmission

[0352] The user enters customer information using the voice input function of smart glasses. For example, they might enter information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase."

[0353] Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information.

[0354] 2. Conversion to data format and transmission

[0355] The system verifies the entered customer information and sentiment data in real time, and if there are no problems, converts it to an appropriate data format (e.g., JSON format) and sends it to the server.

[0356] 3. Data reception and storage

[0357] The server receives the transmitted data, temporarily stores it in memory, and then stores it in the database.

[0358] 4. Data validation and preprocessing

[0359] The server verifies the received data, checking for inaccuracies or missing information. Next, it standardizes the data (for example, converting charges to a specific scale) and formats it into a format suitable for analysis.

[0360] 5. Data Analysis and Proposal Generation

[0361] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical conversion rate data to predict the optimal proposal.

[0362] By incorporating emotional data into the analysis, it becomes possible to generate suggestions tailored to the user's psychological state.

[0363] 6. Submitting and displaying proposals

[0364] The server converts the generated suggestions into JSON format and sends them to the smart glasses.

[0365] Smart glasses display suggested items, and store staff make these suggestions to customers.

[0366] Specific example

[0367] For example, if a woman in her 30s comes into the store looking for a skincare product as a gift, a store employee wearing smart glasses will collect and input the information as follows:

[0368] "Gender: Female", "Age: 30s", "Products of Interest: Skincare", "Purpose: Gift purchase".

[0369] Furthermore, if the emotion analysis engine determines that "the customer's emotional state is positive," this information is used to perform analysis on the server, and a "highly moisturizing skincare set" will be suggested.

[0370] Example of a prompt

[0371] "A woman in her 30s, interested in skincare products, intended use as a gift, and experiencing positive emotions."

[0372] "Male in his 40s, interested in electronic products, intended use is personal, emotional state is neutral."

[0373] This makes it possible to provide product suggestions optimized to customer needs in real time, which is expected to improve the conversion rate.

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] The user wears smart glasses and inputs basic customer information by voice. For example, they might input information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase." This input information is stored as metadata in the smart glasses. Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information such as "positive."

[0377] Input: User voice input, customer facial expressions and voice

[0378] Data processing: Speech-to-text conversion, emotional information analysis.

[0379] Output: Customer information (text format), sentiment information

[0380] Step 2:

[0381] The device (smart glasses) verifies customer information and sentiment information in real time to check for inaccurate or missing data. Data that is free of problems is converted to JSON format and sent to the server via an HTTP request.

[0382] Input: Customer information (text format), sentiment information

[0383] Data processing: Real-time verification, conversion to JSON format.

[0384] Output: Customer information and sentiment information in JSON format, HTTP request

[0385] Step 3:

[0386] The server receives JSON data sent from the terminal and temporarily stores it in memory. Then, it stores customer information and sentiment information in the database. This data is then organized for subsequent processing.

[0387] Input: Customer information and sentiment information in JSON format

[0388] Data processing: Data reception, saving to memory, storage in database.

[0389] Output: Customer information and sentiment information stored in the database

[0390] Step 4:

[0391] The server verifies the stored data, checking for inaccuracies or missing information. Next, it standardizes the data and formats it into a suitable format for analysis. This process may involve tasks such as converting charges to a specific scale.

[0392] Input: Customer information and sentiment information stored in the database

[0393] Data processing: Data validation, standardization, and formatting.

[0394] Output: Data in a format suitable for analysis

[0395] Step 5:

[0396] The server uses machine learning algorithms to analyze pre-processed customer information and emotional data. It generates optimal recommendations based on high conversion rate data. In this process, emotional information is also taken into consideration; for example, if the user is in a positive state, it might suggest a skincare set as a particularly easy product to recommend.

[0397] Input: Pre-processed customer information and sentiment information

[0398] Data processing: Analysis using machine learning algorithms

[0399] Output: Optimal proposal content

[0400] Step 6:

[0401] The server converts the generated proposal into JSON format and sends it to the terminal as an HTTP response.

[0402] Input: Optimal proposal content

[0403] Data processing: Conversion to JSON format

[0404] Output: Proposal content in JSON format, HTTP response

[0405] Step 7:

[0406] The device (smart glasses) analyzes the suggested content received from the server and displays it visually. Based on this information, the store clerk makes the most suitable product suggestions to the customer. The suggested content is designed to be easy on the user's eyes.

[0407] Input: Proposal content in JSON format

[0408] Data processing: Parsing of JSON data, GUI display.

[0409] Output: Visually displayed proposal content

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Second Embodiment]

[0414] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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".

[0426] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The system aims to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[0427] The user (sales staff) enters customer information using a terminal. The terminal converts this information into an appropriate data format (e.g., JSON format) and sends it to the server. The server receives this information and stores it in a database. Furthermore, the server validates and preprocesses the data and performs analysis to generate optimal recommendations based on this information. The generated recommendations are then sent back to the terminal and displayed to the user.

[0428] Explanation of the program's processing

[0429] Data entry and transmission

[0430] The user enters customer information using their device. For example, they might enter information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". The entered information is converted to JSON format by the device and sent to the server via an HTTP request.

[0431] Data storage and management

[0432] The server parses the JSON data received from the terminal and stores it in the database. The database organizes and stores customer information so that it can be used for analysis later.

[0433] Data validation and preprocessing

[0434] The server verifies the stored data, checking for inaccuracies or missing data. Next, it performs preprocessing such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale).

[0435] Data Analysis

[0436] The server uses historical high-conversion rate data to apply machine learning algorithms and generate optimal proposals for customers. In this process, it compares and analyzes historical data with newly entered customer information, using a model to predict the best proposal.

[0437] Proposal generation and submission

[0438] Based on the analysis results, the server generates optimal recommendations for the customer. For example, it might generate a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use." The generated recommendations are converted to JSON format and sent to the device.

[0439] Suggestion display

[0440] The terminal analyzes the suggestions received from the server and displays them visually to the user. The user can then make suggestions to customers based on these displayed suggestions.

[0441] Explanation of specific examples

[0442] For example, a user might input customer information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of devices used by family: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[0443] Based on past high conversion rate data, the server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice and generates this proposal. This generated proposal is sent to the terminal and displayed to the user. The user can then use this proposal to improve their conversion rate.

[0444] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal proposals based on customer information and effectively support sales activities.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The user enters customer information into an input form on their device. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Once the user has finished entering the information, they press the submit button.

[0448] Step 2:

[0449] The terminal verifies the entered customer information in real time, checking for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format, such as JSON.

[0450] Step 3:

[0451] The terminal sends the converted JSON-formatted customer information to the server using an HTTP request. It is recommended to use the SSL / TLS protocol for security purposes during this process.

[0452] Step 4:

[0453] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory in preparation for the next processing step.

[0454] Step 5:

[0455] The server stores the received customer information in a database. Specifically, it inserts information such as customer ID, carrier information, charges, number of family members using the service, internet environment, and usage purpose into the corresponding tables.

[0456] Step 6:

[0457] The server verifies the stored customer information. It checks whether the data is consistent, free from non-numeric data, and free from missing data. If any deficiencies are found, it records an error log and sends an alert to the relevant parties.

[0458] Step 7:

[0459] The server preprocesses the verified data. Specifically, it performs categorization, such as coding carrier names, and standardization, such as converting charges to a specific scale.

[0460] Step 8:

[0461] The server performs analysis based on pre-processed data. It uses historical high-conversion rate data to apply machine learning algorithms (e.g., decision trees and random forests) to predict the optimal proposal.

[0462] Step 9:

[0463] The server generates optimal recommendations based on the analysis results. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0464] Step 10:

[0465] The server converts the generated proposal into JSON format and sends it to the terminal. It also uses an HTTP response for this process, applying the SSL / TLS protocol as needed.

[0466] Step 11:

[0467] The terminal analyzes the received suggestions and displays them visually to the user. The suggestions are displayed appropriately in a GUI (Graphical User Interface) to make them easy for the user to understand.

[0468] Step 12:

[0469] The user makes a proposal to the customer based on the proposal displayed on the device. If the customer agrees to the proposal, the user proceeds with the contract closing procedure.

[0470] (Example 1)

[0471] 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".

[0472] Traditional systems often involve manual processes from customer information input to the generation and display of optimal proposals, resulting in low efficiency. Furthermore, proposals are uniform across all customers, making it difficult to tailor them to individual needs. Consequently, there are limitations to improving the conversion rate, hindering efficient sales activities.

[0473] 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.

[0474] In this invention, the server includes means for inputting customer information using a device used by the user, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for applying a machine learning algorithm using past high conversion rate data to generate optimal proposal content, means for transmitting the generated proposal content to the device into which the customer information was input, and means for displaying the proposal content on the device. This makes it possible to automatically generate optimal proposal content based on customer information and to make proposals to customers quickly and efficiently.

[0475] "User" refers to an individual or organization that uses the system to input and verify customer information.

[0476] "Device" refers to a device used for inputting customer information and displaying proposals (e.g., personal computer, smartphone, tablet, etc.).

[0477] "Customer information" refers to detailed data about a customer (e.g., current carrier, charges, number of devices used, internet environment, usage purpose, etc.).

[0478] "Data format" refers to a specific structure (e.g., JSON format) that a computer system uses to understand and process data.

[0479] A "server" refers to a computer system that receives, stores, analyzes, generates, and transmits data.

[0480] A "database" refers to a structured data storage system used to efficiently store and manage data such as customer information and analytical results.

[0481] "Preprocessing" refers to the steps of standardizing, categorizing, and validating data for analysis.

[0482] A "machine learning algorithm" refers to a computational method that automatically learns patterns and rules from data and uses that knowledge to make predictions and classifications.

[0483] "Optimal proposal content" refers to a proposal message that is deemed most effective or appropriate for a particular customer, based on their customer information.

[0484] "Past high conversion rate data" refers to proposals and sales data that were effective in the past, and is used as data for training machine learning algorithms.

[0485] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The purpose of this system is for a server to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal.

[0486] The user (sales staff) enters customer information using a terminal. Specifically, they use devices such as smartphones, tablets, or personal computers to enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." This information is converted to JSON format by the terminal and sent to the server via an HTTP request.

[0487] The server is hardware that runs programs written in Python or Java. It first parses JSON data received from terminals and stores it in a database. Customer information is organized and stored in this database using SQL or NoSQL technologies. The stored data is first verified for accuracy and completeness. After that, preprocessing is performed, such as coding carrier names and standardizing pricing.

[0488] The server analyzes data using machine learning algorithms. Specifically, it uses Python's Scikit-learn library and TensorFlow to compare and analyze historical high-conversion rate data with newly entered customer information. This builds a model that predicts the optimal recommendation. Based on this model, the server generates the optimal recommendation. For example, it might generate a specific recommendation message such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[0489] The generated proposals are converted back into JSON format and sent to the terminal using an HTTP request. The terminal parses the received proposals and displays them in the user interface. Based on these displayed proposals, the user can then make the most appropriate proposals for the customer.

[0490] As a concrete example, a user enters customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." This information is converted to JSON format by the device and sent to the server. The server stores and preprocesses the information, and uses a machine learning algorithm to generate a recommendation that "NTT Docomo's family discount plan is optimal" based on this information. This recommendation is sent to the device and displayed to the user.

[0491] Examples of prompt statements are as follows:

[0492] "Please generate the optimal proposal based on the customer information. The customer's current carrier is NTT Docomo, their current monthly fee is 5,000 yen, they use 3 devices, their internet connection is fiber optic, and their usage is video streaming, social media, and phone calls."

[0493] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0494] Program processing steps

[0495] Step 1: Data entry and submission

[0496] 1. The user enters customer information using the device. For example, they enter information such as: "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices used: 3", "Internet environment: Fiber optic connection", and "Usage: Watching videos, using social media, making calls".

[0497] 2. The terminal converts the entered information into JSON format. Specifically, it formats the data from the input form as a JSON object using JavaScript or Python.

[0498] 3. The terminal sends the generated JSON data to the server using an HTTP POST request. This communication is performed by specifying the endpoint URL.

[0499] Input: Customer information entered by the user (carrier, fee, number of devices used, etc.)

[0500] Output: Customer information converted to JSON format is sent to the server.

[0501] Step 2: Data storage and management

[0502] 1. The server parses the JSON data received from the terminal. Specifically, it decodes the received data using Python's JSON library or Java's Gson library.

[0503] 2. The server connects to the database and stores the received customer information. Specifically, it executes commands to insert data using SQL statements or NoSQL queries.

[0504] 3. The server generates a confirmation message that the save was successful and sends it back to the terminal. This message notifies the user that the save was performed successfully.

[0505] Input: Customer information in JSON format sent from the terminal.

[0506] Output: Customer information is saved to the database and a confirmation message is sent to the terminal.

[0507] Step 3: Data validation and preprocessing

[0508] 1. The server reads the data stored in the database. Specifically, it executes SQL queries.

[0509] 2. The server checks for inaccurate or missing data. For example, it uses validation scripts to ensure that all required fields are present.

[0510] 3. The server categorizes and standardizes the data. Specifically, it codes carrier names and performs preprocessing to convert pricing data to a specific scale.

[0511] Input: Stored customer information data

[0512] Output: Verified and pre-processed customer information data

[0513] Step 4: Data Analysis

[0514] 1. The server applies machine learning algorithms using historical high-conversion rate data. Specifically, it uses the Scikit-learn library in Python.

[0515] 2. The server compares newly entered customer information with past data to predict the optimal recommendation. Algorithms such as logistic regression and decision trees are used.

[0516] 3. The server retrieves the analysis results and generates optimal suggestions. For example, it generates suggestions based on the prediction results of a machine learning model.

[0517] Input: Verified and pre-processed customer information data, historical high conversion rate data

[0518] Output: Optimal proposal content

[0519] Step 5: Generate and submit proposals

[0520] 1. The server creates a specific message based on the optimal recommendation. For example, it might generate a suggestion such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0521] 2. The server converts the generated proposal content into JSON format. Specifically, it formats the proposal content as a JSON object.

[0522] 3. The server sends the generated JSON data to the terminal using an HTTP POST request.

[0523] Input: Optimal proposal content

[0524] Output: The suggested content, converted to JSON format, is sent to the terminal.

[0525] Step 6: Proposal Display

[0526] 1. The terminal parses the JSON-formatted proposal received from the server. Specifically, it decodes the received data using JavaScript or Python's JSON library.

[0527] 2. The terminal displays the analyzed suggestions in the user interface. Specifically, it uses HTML and CSS to display the suggestion messages on the screen.

[0528] 3. Users can make suggestions to customers based on the displayed suggestions. Specifically, this can involve reading aloud messages displayed on the device or showing the screen.

[0529] Input: Proposal content in JSON format sent from the server

[0530] Output: Suggestions displayed in the user interface

[0531] The above describes the processing flow of this system's program.

[0532] (Application Example 1)

[0533] 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."

[0534] In physical stores, it is difficult for sales staff to quickly and accurately make the best recommendations to customers. Understanding customer needs and purchase history, and then proposing appropriate products and services based on that, requires the ability to process a large amount of information instantly. Furthermore, there is a need for a system that automatically generates optimal recommendations based on customer information and delivers those recommendations to customers in a timely manner. This creates a need for a system that can reduce the burden on sales staff and improve the closing rate.

[0535] 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.

[0536] In this invention, the server includes means for inputting customer information, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information, means for displaying the proposal content on the terminal, means including a terminal that runs a sales support application in a physical store, means for enabling sales staff to confirm the generated proposal content in real time, and means for automatically generating proposal content using a generation AI model and providing it to sales staff as a prompt message. This makes it possible for sales staff to receive optimal proposals in real time based on customer information and immediately make proposals to customers.

[0537] "Customer information" refers to personal attributes, purchase history, interests, and other information obtained through input by sales staff.

[0538] "Data format" refers to a form of data that can be processed by a computer, and in this context, it specifically refers to the JSON format.

[0539] A "server" is a computer system that receives, processes, stores, and analyzes customer information.

[0540] A "database" is a digital storage medium used to systematically organize and store received customer information.

[0541] "Verification" is the process of confirming that stored customer information is accurate and identifying inaccurate or incomplete data.

[0542] "Preprocessing" refers to the procedure of converting customer information into a format that is easy to analyze, and includes, for example, data categorization and standardization.

[0543] "Analysis" is the process of analyzing data to generate appropriate proposals based on pre-processed customer information.

[0544] "Proposed content" refers to information about products and services that are best suited to the customer, generated through analysis.

[0545] A "terminal" refers to a device operated by sales staff to input customer information or display sales proposals. In this context, it mainly refers to smartphones and tablets.

[0546] A "physical store" is a physical commercial facility where customers actually visit and make purchases.

[0547] A "sales support application" is software that runs on a device and provides information to help sales staff make the best possible proposals to customers.

[0548] "Real-time" means that the time between information being entered, processing it immediately, and the display of results is extremely short, almost instantaneous.

[0549] A "generative AI model" is an algorithm or program that uses machine learning to automatically generate new suggestions.

[0550] A "prompt message" is a guidance message output by a generation AI model, used by sales staff when making suggestions to customers.

[0551] This invention relates to a system for enabling sales staff in physical stores to make optimal suggestions in real time based on customer information. The system aims to perform a series of steps including inputting customer information, converting it to a data format, transmitting it to a server, storing the customer information in a database, verifying and preprocessing the data, generating optimal suggestions through analysis, and transmitting and displaying the generated suggestions to a terminal.

[0552] The hardware required to implement the system includes devices such as smartphones and tablets, servers, and a database management system (e.g., MySQL). The software includes libraries for implementing machine learning algorithms (e.g., TensorFlow), the HTTP protocol for data transmission and reception, and sales support applications for physical stores.

[0553] Entering and submitting customer information

[0554] The user (sales staff) enters customer information using a smartphone or tablet. This information includes the customer's name, age, purchase history, and product categories of interest. The entered information is converted to JSON format on the device and sent to the server via an HTTP POST request.

[0555] Data processing on the server

[0556] The server parses the JSON data received from the terminal and stores it in the database. Next, it verifies the stored data to check for any inaccuracies or incomplete data. After this, as a data preprocessing step, it performs categorization and standardization, such as mapping ages to specific age groups.

[0557] Analysis of customer information and generation of proposals

[0558] The server uses a machine learning model (e.g., TensorFlow) to generate optimal suggestions based on pre-processed customer information and past high-conversion rate data. In this process, a generative AI model is used to create prompt messages based on the customer information.

[0559] Submitting and displaying proposals

[0560] The generated suggestions are converted back into JSON format and sent to the terminal. This information is displayed visually on the terminal, allowing sales staff to check it in real time. Based on the displayed suggestions, users can then propose products and services to customers.

[0561] Specific example

[0562] When a customer visits a physical store, the sales staff enters the following information into a smartphone app:

[0563] Name: Customer A

[0564] Age: 35

[0565] Purchase history: Smartphones, tablets

[0566] Product categories of interest: Home appliances, audio equipment

[0567] This information is converted to JSON format and sent to the server. The server stores the data and uses a machine learning model to generate a suggestion such as, "If customer A is particular about sound quality, we recommend the latest Bluetooth speaker." This information is then sent back to the application, where sales staff can review it in real time and make suggestions to customers.

[0568] Example of a prompt

[0569] "Customer A, 35 years old, has come into the store. He has previously purchased a smartphone and a tablet, and is currently interested in home electronics and audio equipment. Please provide him with the best product recommendations."

[0570] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0571] Step 1:

[0572] User enters customer information

[0573] The user (sales staff) uses a smartphone or tablet to enter information such as the customer's name, age, purchase history, and product categories of interest. This information is converted into JSON format.

[0574] Input: Customer information (name, age, purchase history, product categories of interest)

[0575] Output: Customer information in JSON format

[0576] Step 2:

[0577] The terminal sends customer information to the server.

[0578] The terminal sends customer information, converted to JSON format, to the server via an HTTP POST request.

[0579] Input: Customer information in JSON format

[0580] Output: HTTP request to the server

[0581] Step 3:

[0582] The server saves customer information to the database.

[0583] The server parses the received JSON data and saves it to the database.

[0584] Input: Customer information in JSON format

[0585] Output: Customer information stored in the database

[0586] Step 4:

[0587] The server verifies customer information.

[0588] The server verifies the stored customer information to check for inaccurate or incomplete data. Inaccurate data is corrected, and incomplete data is assigned appropriate default values.

[0589] Input: Customer information stored in the database

[0590] Output: Verified customer information

[0591] Step 5:

[0592] The server preprocesses customer information.

[0593] The server categorizes and standardizes verified customer information. For example, it maps age to a specific age group.

[0594] Input: Verified customer information

[0595] Output: Preprocessed customer information

[0596] Step 6:

[0597] The server analyzes customer information.

[0598] The server generates optimal proposals using a generative AI model (e.g., TensorFlow) based on pre-processed customer information and past high conversion rate data.

[0599] Input: Pre-processed customer information, historical high conversion rate data

[0600] Output: Optimal proposal content

[0601] Step 7:

[0602] The server formats the proposal based on customer information.

[0603] The server formats the generated proposal based on customer information and converts it back into JSON format.

[0604] Input: Optimal proposal content

[0605] Output: Proposal in JSON format

[0606] Step 8:

[0607] The server sends the proposal to the terminal.

[0608] The server sends the proposed content, converted to JSON format, to the terminal via an HTTP request.

[0609] Input: Proposal content in JSON format

[0610] Output: HTTP request to terminal

[0611] Step 9:

[0612] The device displays the suggested content.

[0613] The terminal analyzes the received proposal and displays it visually. Sales staff then review the proposal and make it to the customer.

[0614] Input: Proposal content in JSON format

[0615] Output: Suggestion displayed to sales staff

[0616] Step 10:

[0617] The user makes a proposal to the customer based on the proposed content.

[0618] The user (sales staff) makes product and service recommendations to the customer based on the displayed suggestions.

[0619] Input: Suggestion displayed to the sales staff

[0620] Output: Proposals for the best products and services for customers

[0621] 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.

[0622] This invention relates to a system that generates optimal proposals using customer information to improve the conversion rate. Furthermore, by combining this with an emotion engine that recognizes user emotions, the system can personalize proposals and provide more accurate suggestions. The purpose of this system is for the server to analyze customer information and emotion information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[0623] Explanation of the program's processing

[0624] Data entry and transmission

[0625] The user enters customer information into an input form on the device. For example, they might enter information such as "Current carrier: NTT Docomo," "Current monthly fee: 5,000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." Simultaneously, an emotion engine built into the device analyzes the user's facial expressions and voice to collect emotion data.

[0626] Conversion to data format and transmission

[0627] The terminal verifies the entered customer information and sentiment data in real time to check for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format such as JSON and sends it to the server via an HTTP request.

[0628] Data reception and storage

[0629] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. The server then stores this customer information and sentiment data in the database. The database organizes and stores the customer information and sentiment data so that it can be used for analysis later.

[0630] Data validation and preprocessing

[0631] The server verifies the stored data, checking for inaccuracies or missing data. Next, preprocessing is performed, such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[0632] Data analysis and proposal generation

[0633] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical high-conversion rate data to predict optimal recommendations. By incorporating sentiment data into the analysis, it can generate recommendations tailored to the user's psychological state. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[0634] Submitting and displaying proposals

[0635] The server converts the generated proposal content into JSON format and sends it to the terminal. The terminal parses the proposal content received from the server and displays it visually to the user. The proposal content is displayed in an easy-to-understand manner using a GUI (Graphical User Interface). The user can review this displayed proposal content and make a proposal to the customer.

[0636] Explanation of specific examples

[0637] For example, a user might input customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." The emotion engine then analyzes the user's facial expressions and voice to determine that "User's emotional state: Positive." When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[0638] The server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice, based on past high conversion rate data, current customer information, and sentiment data. Furthermore, based on sentiment data, it predicts that this offer will be even more effective because the user is in a positive state. This generated offer is sent to the device and displayed to the user. The user can then use this offer to their customers to improve their conversion rate.

[0639] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal suggestions based on customer information and emotional information, thereby effectively supporting sales activities.

[0640] The following describes the processing flow.

[0641] Step 1:

[0642] Users enter customer information into input forms on their devices. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine analyzes this to generate emotion data.

[0643] Step 2:

[0644] The terminal verifies the entered customer information and sentiment data in real time, checking for any missing or inaccurate data. Once verification is complete, it converts the information into an appropriate data format, such as JSON.

[0645] Step 3:

[0646] The terminal sends the converted JSON-formatted customer information and sentiment data to the server using an HTTP request. SSL / TLS protocol is used to ensure security during this process.

[0647] Step 4:

[0648] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory and added to a queue for later processing.

[0649] Step 5:

[0650] The server stores received customer information and sentiment data in a database. Specifically, it inserts customer ID, carrier information, charges, number of family members using the service, internet environment, usage purpose, and sentiment data into the corresponding tables.

[0651] Step 6:

[0652] The server verifies the stored data. This verification includes checking for data consistency, the presence of invalid data, and missing data. If errors are detected, appropriate error handling and logging are performed.

[0653] Step 7:

[0654] The server preprocesses the verified data. This includes categorization (e.g., converting carrier names to codes) and standardization (e.g., converting rates to a unified scale), and sentiment data is also standardized.

[0655] Step 8:

[0656] The server analyzes pre-processed data. It uses machine learning algorithms (e.g., decision trees, random forests) to analyze historical high-conversion rate data and newly entered customer information to generate optimal recommendations. By including emotional data in the analysis, it provides recommendations tailored to the user's psychological state.

[0657] Step 9:

[0658] The server generates recommendations based on the analysis results. For example, it might set up a specific recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0659] Step 10:

[0660] The server converts the generated proposal content back into JSON format and sends it to the terminal. SSL / TLS protocol is used to ensure security during this process.

[0661] Step 11:

[0662] The terminal analyzes the suggestions received from the server and displays them visually to the user. The suggestions are displayed through a GUI in a way that is easy for the user to understand.

[0663] Step 12:

[0664] Users review the proposals displayed on their devices and then submit them to customers. If the customer agrees to the proposal, the user proceeds with the closing process. This approach can improve the closing rate.

[0665] (Example 2)

[0666] 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".

[0667] Proposals based solely on customer information tend to be generic and uniform, often failing to fully address the individual needs of each customer. This makes it difficult to improve conversion rates, and generating more personalized proposals is a challenge. Furthermore, traditional systems cannot consider the user's psychological state when making proposals, making it difficult to increase customer satisfaction.

[0668] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment data, means for converting the input customer information and sentiment data into a data format and transmitting it to the server, means for storing the received customer information and sentiment data in a database, means for verifying and pre-processing the stored customer information and sentiment data, means for performing analysis based on the pre-processed customer information and sentiment data and generating optimal proposal content, means for transmitting the generated proposal content to the terminal into which the customer information was input, and means for displaying the proposal content on the terminal. This makes it possible to generate more accurate personalized proposals that are tailored to the individual needs and psychological state of each customer.

[0669] "Customer information" refers to detailed data about the individuals or companies to whom services or products are provided.

[0670] "Emotional data" refers to data that indicates a user's psychological state, analyzed from their facial expressions, voice, body movements, and other factors.

[0671] A "data format" is a way of organizing data according to a specific structure or set of rules, making it easier to process and communicate.

[0672] A "server" is a computer system that stores, processes, and transmits data.

[0673] A "database" is a system for efficiently and systematically storing and managing digital information.

[0674] "Preprocessing" refers to a series of processes that prepare data for easier analysis, including imputation of missing values ​​and standardization.

[0675] A "machine learning algorithm" is a computational method that learns patterns and regularities based on large amounts of data, and uses that learning to make predictions and classifications on new data.

[0676] "Recommended content" refers to recommendations for the most suitable services and products for the customer, generated based on the analysis results.

[0677] A "terminal" is a device that a user directly operates to input or display information.

[0678] "Transmission" is the process of transferring data or information to a specific receiving device.

[0679] "Display" refers to the act of making information visible, or the technology used for that purpose.

[0680] This invention is a system that generates optimal proposals based on customer information and emotional data, thereby improving the conversion rate. This system is realized through the cooperation of a server and terminals.

[0681] The user operates the terminal and enters customer information. This customer information includes items such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the terminal is equipped with an emotion engine that analyzes the user's facial expressions and voice to collect emotional data. This emotion engine also allows the user's psychological state to be understood in real time.

[0682] The terminal verifies the entered customer information and sentiment data in real time to check for any missing or inaccurate data. If there are no problems, it converts the information to JSON format and sends it to the server via an HTTP request. The server receives the data sent from the terminal, temporarily stores it in memory, and then stores the customer information and sentiment data in the database.

[0683] The server re-verifies the stored data to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., charges are converted to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[0684] The server uses machine learning libraries such as Python's Scikit-learn to perform analysis based on pre-processed customer information and sentiment data. It applies algorithms using historical high-conversion rate data to predict the optimal proposal. By incorporating sentiment data into the analysis, it can generate personalized proposals tailored to the user's psychological state. The generated proposals are then converted to JSON format and sent to the terminal.

[0685] The terminal analyzes the proposals received from the server and displays them visually to the user. This display is designed to be user-friendly using front-end frameworks such as React.js and Vue.js. Users can review the displayed proposals and present them to customers to improve their conversion rates.

[0686] Explanation of specific examples

[0687] For example, a user enters the following customer information:

[0688] Current carrier: NTT Docomo

[0689] Current fee: 5000 yen per month

[0690] Number of devices used by the family: 3

[0691] Internet connection: Fiber optic

[0692] Usage: Watching videos, using social media, making phone calls

[0693] Furthermore, the emotion engine recognizes the user's emotional state as "positive." The device converts this information into JSON format and sends it to the server. The server receives the data, stores it in a database, and then applies a machine learning algorithm using Python's Scikit-learn. Based on high conversion rate data, it determines that "NTT Docomo's Family Discount Plan" is optimal and predicts that the suggestion will be effective because the user is in a positive state.

[0694] The generated proposal is as follows:

[0695] NTT Docomo's family discount plan is highly recommended. It's especially ideal for customers who prioritize watching videos and using social media.

[0696] The server sends this proposal to the terminal, which then displays it to the user using a GUI. The user can review this proposal and present it to the customer to improve the conversion rate.

[0697] Thus, the system of the present invention makes it possible to generate optimal proposals based on customer information and emotional data, thereby effectively supporting sales activities.

[0698] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0699] Step 1: Data entry and sentiment analysis

[0700] The user enters customer information into an input form on the device. This customer information includes items such as "current carrier," "current charges," "number of family devices," "internet environment," and "intended use." The entered data is stored in the input fields on the device. Simultaneously, the device's built-in emotion engine analyzes the user's facial expressions and voice to collect emotion data. The obtained emotion data is saved in the input fields as emotion categories such as "joy," "sadness," and "surprise."

[0701] Step 2: Convert to data format and send

[0702] The terminal verifies the entered customer information and sentiment data in real time to ensure there is no missing or inaccurate data. Once this verification is complete, the terminal converts the information into JSON format. In this conversion process, text and numerical data are organized into a specific key-value pair format. The converted data is then sent to the server as an HTTP request.

[0703] Step 3: Data reception and storage

[0704] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. Next, the server stores this customer information and sentiment data in a database system. Assigning a unique identifier when storing the data in the database enables efficient searching.

[0705] Step 4: Data validation and preprocessing

[0706] The server re-verifies the data stored in the database to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., prices are scaled). At this time, sentiment data is also smoothed and formatted to a format suitable for analysis. The preprocessed data is stored in temporary memory to move on to the next analysis step.

[0707] Step 5: Data Analysis and Proposal Generation

[0708] The server uses machine learning libraries such as Python's Scikit-learn to analyze pre-processed data. Based on past high-conversion rate data, the server applies a machine learning algorithm to predict the optimal proposal. This algorithm finds patterns based on input customer information and sentiment data and generates appropriate proposals. For example, it might suggest a family discount plan to users with large families.

[0709] Step 6: Submit and view your proposal

[0710] The server converts the generated proposal content into JSON format and sends it to the terminal as an HTTP response. The terminal parses the proposal content received from the server and displays it visually to the user. This display uses front-end frameworks such as React.js or Vue.js and is formatted for easy viewing. The user can review this displayed proposal content and offer it to customers to improve the conversion rate.

[0711] The above outlines the specific processing steps of the system. Through the specific actions, inputs, and outputs in each step, the system can efficiently generate and display optimal suggestions.

[0712] (Application Example 2)

[0713] 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."

[0714] In brick-and-mortar stores, there is a need to quickly and accurately provide optimal product recommendations based on customer requests. However, conventional systems have difficulty considering customer emotional information, resulting in recommendations that do not adequately address the customer's psychological state. This can lead to lower conversion rates and reduced customer satisfaction. Therefore, there was a need for a system that could analyze customer emotional information in real time and provide optimal product recommendations.

[0715] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment information, means for converting the input customer information and sentiment information into a data format and transmitting it to the server, means for storing the received customer information and sentiment information in a database, means for verifying and pre-processing the stored customer information and sentiment information, means for performing analysis based on the pre-processed customer information and sentiment information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information and sentiment information, means for displaying the proposal content on the terminal, and means for visually displaying the proposal content via a smart device. This makes it possible to make highly accurate product proposals in real time, taking into account customer sentiment information.

[0716] "Customer information" refers to detailed information about a customer, such as their age, gender, products of interest, and purpose of use.

[0717] "Emotional information" refers to information indicating a customer's psychological state, obtained by analyzing their facial expressions and voice.

[0718] "Data format" refers to the format used to structure information according to certain rules and to exchange it between computers.

[0719] A "server" refers to a computer system that stores, processes, and analyzes data, and delivers the results to terminals.

[0720] A "database" refers to a system for efficiently storing and managing a collection of information.

[0721] "Preprocessing" refers to the process of standardizing data and formatting it into a suitable format for analysis prior to the analysis itself.

[0722] A "machine learning algorithm" refers to a computer algorithm that learns from customer information, emotional data, and past transaction data to predict the most suitable proposal.

[0723] A "smart device" refers to an electronic device with advanced functions for collecting emotional information and displaying suggestions, such as smart glasses or smartphones.

[0724] "Recommended content" refers to the optimal product or service recommendations generated based on customer information and emotional information.

[0725] This invention is a system for improving the efficiency of customer service in physical stores and increasing the conversion rate. This system implements a series of processes for inputting customer information and emotional information, and for generating and displaying optimal suggestions. The specific embodiments of this system are described in detail below.

[0726] Hardware and software usage

[0727] 1. Hardware

[0728] Smart devices: Smart glasses and smartphones are used to collect customer information and sentiment data, and to display suggested content. This example assumes devices such as Google Glass or Vuzix Blade.

[0729] Server: A high-performance computer system is used to store, process, and analyze data. For example, a Dell PowerEdge is suitable.

[0730] 2. Software

[0731] Emotion Analysis Engine: Microsoft Azure Cognitive Services and IBM Watson are used to collect emotional information by analyzing customers' facial expressions and voices.

[0732] Database Management System: Database management software such as MySQL or PostgreSQL is used to centrally manage customer information and sentiment information.

[0733] Machine learning algorithms: We use machine learning libraries such as TensorFlow and PyTorch to analyze customer information and sentiment information and generate optimal recommendations.

[0734] Data processing and data calculation

[0735] 1. Data entry and transmission

[0736] The user enters customer information using the voice input function of smart glasses. For example, they might enter information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase."

[0737] Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information.

[0738] 2. Conversion to data format and transmission

[0739] The system verifies the entered customer information and sentiment data in real time, and if there are no problems, converts it to an appropriate data format (e.g., JSON format) and sends it to the server.

[0740] 3. Data reception and storage

[0741] The server receives the transmitted data, temporarily stores it in memory, and then stores it in the database.

[0742] 4. Data validation and preprocessing

[0743] The server verifies the received data, checking for inaccuracies or missing information. Next, it standardizes the data (for example, converting charges to a specific scale) and formats it into a format suitable for analysis.

[0744] 5. Data Analysis and Proposal Generation

[0745] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical conversion rate data to predict the optimal proposal.

[0746] By incorporating emotional data into the analysis, it becomes possible to generate suggestions tailored to the user's psychological state.

[0747] 6. Submitting and displaying proposals

[0748] The server converts the generated suggestions into JSON format and sends them to the smart glasses.

[0749] Smart glasses display suggested items, and store staff make these suggestions to customers.

[0750] Specific example

[0751] For example, if a woman in her 30s comes into the store looking for a skincare product as a gift, a store employee wearing smart glasses will collect and input the information as follows:

[0752] "Gender: Female", "Age: 30s", "Products of Interest: Skincare", "Purpose: Gift purchase".

[0753] Furthermore, if the emotion analysis engine determines that "the customer's emotional state is positive," this information is used to perform analysis on the server, and a "highly moisturizing skincare set" will be suggested.

[0754] Example of a prompt

[0755] "A woman in her 30s, interested in skincare products, intended use as a gift, and experiencing positive emotions."

[0756] "Male in his 40s, interested in electronic products, intended use is personal, emotional state is neutral."

[0757] This makes it possible to provide product suggestions optimized to customer needs in real time, which is expected to improve the conversion rate.

[0758] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0759] Step 1:

[0760] The user wears smart glasses and inputs basic customer information by voice. For example, they might input information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase." This input information is stored as metadata in the smart glasses. Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information such as "positive."

[0761] Input: User voice input, customer facial expressions and voice

[0762] Data processing: Speech-to-text conversion, emotional information analysis.

[0763] Output: Customer information (text format), sentiment information

[0764] Step 2:

[0765] The device (smart glasses) verifies customer information and sentiment information in real time to check for inaccurate or missing data. Data that is free of problems is converted to JSON format and sent to the server via an HTTP request.

[0766] Input: Customer information (text format), sentiment information

[0767] Data processing: Real-time verification, conversion to JSON format.

[0768] Output: Customer information and sentiment information in JSON format, HTTP request

[0769] Step 3:

[0770] The server receives JSON data sent from the terminal and temporarily stores it in memory. Then, it stores customer information and sentiment information in the database. This data is then organized for subsequent processing.

[0771] Input: Customer information and sentiment information in JSON format

[0772] Data processing: Data reception, saving to memory, storage in database.

[0773] Output: Customer information and sentiment information stored in the database

[0774] Step 4:

[0775] The server verifies the stored data, checking for inaccuracies or missing information. Next, it standardizes the data and formats it into a suitable format for analysis. This process may involve tasks such as converting charges to a specific scale.

[0776] Input: Customer information and sentiment information stored in the database

[0777] Data processing: Data validation, standardization, and formatting.

[0778] Output: Data in a format suitable for analysis

[0779] Step 5:

[0780] The server uses machine learning algorithms to analyze pre-processed customer information and emotional data. It generates optimal recommendations based on high conversion rate data. In this process, emotional information is also taken into consideration; for example, if the user is in a positive state, it might suggest a skincare set as a particularly easy product to recommend.

[0781] Input: Pre-processed customer information and sentiment information

[0782] Data processing: Analysis using machine learning algorithms

[0783] Output: Optimal proposal content

[0784] Step 6:

[0785] The server converts the generated proposal into JSON format and sends it to the terminal as an HTTP response.

[0786] Input: Optimal proposal content

[0787] Data processing: Conversion to JSON format

[0788] Output: Proposal content in JSON format, HTTP response

[0789] Step 7:

[0790] The device (smart glasses) analyzes the suggested content received from the server and displays it visually. Based on this information, the store clerk makes the most suitable product suggestions to the customer. The suggested content is designed to be easy on the user's eyes.

[0791] Input: Proposal content in JSON format

[0792] Data processing: Parsing of JSON data, GUI display.

[0793] Output: Visually displayed proposal content

[0794] 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.

[0795] 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.

[0796] 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.

[0797] [Third Embodiment]

[0798] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0799] 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.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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".

[0810] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The system aims to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[0811] The user (sales staff) enters customer information using a terminal. The terminal converts this information into an appropriate data format (e.g., JSON format) and sends it to the server. The server receives this information and stores it in a database. Furthermore, the server validates and preprocesses the data and performs analysis to generate optimal recommendations based on this information. The generated recommendations are then sent back to the terminal and displayed to the user.

[0812] Explanation of the program's processing

[0813] Data entry and transmission

[0814] The user enters customer information using their device. For example, they might enter information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". The entered information is converted to JSON format by the device and sent to the server via an HTTP request.

[0815] Data storage and management

[0816] The server parses the JSON data received from the terminal and stores it in the database. The database organizes and stores customer information so that it can be used for analysis later.

[0817] Data validation and preprocessing

[0818] The server verifies the stored data, checking for inaccuracies or missing data. Next, it performs preprocessing such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale).

[0819] Data Analysis

[0820] The server uses historical high-conversion rate data to apply machine learning algorithms and generate optimal proposals for customers. In this process, it compares and analyzes historical data with newly entered customer information, using a model to predict the best proposal.

[0821] Proposal generation and submission

[0822] Based on the analysis results, the server generates optimal recommendations for the customer. For example, it might generate a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use." The generated recommendations are converted to JSON format and sent to the device.

[0823] Suggestion display

[0824] The terminal analyzes the suggestions received from the server and displays them visually to the user. The user can then make suggestions to customers based on these displayed suggestions.

[0825] Explanation of specific examples

[0826] For example, a user might input customer information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of devices used by family: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[0827] Based on past high conversion rate data, the server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice and generates this proposal. This generated proposal is sent to the terminal and displayed to the user. The user can then use this proposal to improve their conversion rate.

[0828] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal proposals based on customer information and effectively support sales activities.

[0829] The following describes the processing flow.

[0830] Step 1:

[0831] The user enters customer information into an input form on their device. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Once the user has finished entering the information, they press the submit button.

[0832] Step 2:

[0833] The terminal verifies the entered customer information in real time, checking for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format, such as JSON.

[0834] Step 3:

[0835] The terminal sends the converted JSON-formatted customer information to the server using an HTTP request. It is recommended to use the SSL / TLS protocol for security purposes during this process.

[0836] Step 4:

[0837] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory in preparation for the next processing step.

[0838] Step 5:

[0839] The server stores the received customer information in a database. Specifically, it inserts information such as customer ID, carrier information, charges, number of family members using the service, internet environment, and usage purpose into the corresponding tables.

[0840] Step 6:

[0841] The server verifies the stored customer information. It checks whether the data is consistent, free from non-numeric data, and free from missing data. If any deficiencies are found, it records an error log and sends an alert to the relevant parties.

[0842] Step 7:

[0843] The server preprocesses the verified data. Specifically, it performs categorization, such as coding carrier names, and standardization, such as converting charges to a specific scale.

[0844] Step 8:

[0845] The server performs analysis based on pre-processed data. It uses historical high-conversion rate data to apply machine learning algorithms (e.g., decision trees and random forests) to predict the optimal proposal.

[0846] Step 9:

[0847] The server generates optimal recommendations based on the analysis results. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0848] Step 10:

[0849] The server converts the generated proposal into JSON format and sends it to the terminal. It also uses an HTTP response for this process, applying the SSL / TLS protocol as needed.

[0850] Step 11:

[0851] The terminal analyzes the received suggestions and displays them visually to the user. The suggestions are displayed appropriately in a GUI (Graphical User Interface) to make them easy for the user to understand.

[0852] Step 12:

[0853] The user makes a proposal to the customer based on the proposal displayed on the device. If the customer agrees to the proposal, the user proceeds with the contract closing procedure.

[0854] (Example 1)

[0855] 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."

[0856] Traditional systems often involve manual processes from customer information input to the generation and display of optimal proposals, resulting in low efficiency. Furthermore, proposals are uniform across all customers, making it difficult to tailor them to individual needs. Consequently, there are limitations to improving the conversion rate, hindering efficient sales activities.

[0857] 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.

[0858] In this invention, the server includes means for inputting customer information using a device used by the user, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for applying a machine learning algorithm using past high conversion rate data to generate optimal proposal content, means for transmitting the generated proposal content to the device into which the customer information was input, and means for displaying the proposal content on the device. This makes it possible to automatically generate optimal proposal content based on customer information and to make proposals to customers quickly and efficiently.

[0859] "User" refers to an individual or organization that uses the system to input and verify customer information.

[0860] "Device" refers to a device used for inputting customer information and displaying proposals (e.g., personal computer, smartphone, tablet, etc.).

[0861] "Customer information" refers to detailed data about a customer (e.g., current carrier, charges, number of devices used, internet environment, usage purpose, etc.).

[0862] "Data format" refers to a specific structure (e.g., JSON format) that a computer system uses to understand and process data.

[0863] A "server" refers to a computer system that receives, stores, analyzes, generates, and transmits data.

[0864] A "database" refers to a structured data storage system used to efficiently store and manage data such as customer information and analytical results.

[0865] "Preprocessing" refers to the steps of standardizing, categorizing, and validating data for analysis.

[0866] A "machine learning algorithm" refers to a computational method that automatically learns patterns and rules from data and uses that knowledge to make predictions and classifications.

[0867] "Optimal proposal content" refers to a proposal message that is deemed most effective or appropriate for a particular customer, based on their customer information.

[0868] "Past high conversion rate data" refers to proposals and sales data that were effective in the past, and is used as data for training machine learning algorithms.

[0869] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The purpose of this system is for a server to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal.

[0870] The user (sales staff) enters customer information using a terminal. Specifically, they use devices such as smartphones, tablets, or personal computers to enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." This information is converted to JSON format by the terminal and sent to the server via an HTTP request.

[0871] The server is hardware that runs programs written in Python or Java. It first parses JSON data received from terminals and stores it in a database. Customer information is organized and stored in this database using SQL or NoSQL technologies. The stored data is first verified for accuracy and completeness. After that, preprocessing is performed, such as coding carrier names and standardizing pricing.

[0872] The server analyzes data using machine learning algorithms. Specifically, it uses Python's Scikit-learn library and TensorFlow to compare and analyze historical high-conversion rate data with newly entered customer information. This builds a model that predicts the optimal recommendation. Based on this model, the server generates the optimal recommendation. For example, it might generate a specific recommendation message such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[0873] The generated proposals are converted back into JSON format and sent to the terminal using an HTTP request. The terminal parses the received proposals and displays them in the user interface. Based on these displayed proposals, the user can then make the most appropriate proposals for the customer.

[0874] As a concrete example, a user enters customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." This information is converted to JSON format by the device and sent to the server. The server stores and preprocesses the information, and uses a machine learning algorithm to generate a recommendation that "NTT Docomo's family discount plan is optimal" based on this information. This recommendation is sent to the device and displayed to the user.

[0875] Examples of prompt statements are as follows:

[0876] "Please generate the optimal proposal based on the customer information. The customer's current carrier is NTT Docomo, their current monthly fee is 5,000 yen, they use 3 devices, their internet connection is fiber optic, and their usage is video streaming, social media, and phone calls."

[0877] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0878] Program processing steps

[0879] Step 1: Data entry and submission

[0880] 1. The user enters customer information using the device. For example, they enter information such as: "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices used: 3", "Internet environment: Fiber optic connection", and "Usage: Watching videos, using social media, making calls".

[0881] 2. The terminal converts the entered information into JSON format. Specifically, it formats the data from the input form as a JSON object using JavaScript or Python.

[0882] 3. The terminal sends the generated JSON data to the server using an HTTP POST request. This communication is performed by specifying the endpoint URL.

[0883] Input: Customer information entered by the user (carrier, fee, number of devices used, etc.)

[0884] Output: Customer information converted to JSON format is sent to the server.

[0885] Step 2: Data storage and management

[0886] 1. The server parses the JSON data received from the terminal. Specifically, it decodes the received data using Python's JSON library or Java's Gson library.

[0887] 2. The server connects to the database and stores the received customer information. Specifically, it executes commands to insert data using SQL statements or NoSQL queries.

[0888] 3. The server generates a confirmation message that the save was successful and sends it back to the terminal. This message notifies the user that the save was performed successfully.

[0889] Input: Customer information in JSON format sent from the terminal.

[0890] Output: Customer information is saved to the database and a confirmation message is sent to the terminal.

[0891] Step 3: Data validation and preprocessing

[0892] 1. The server reads the data stored in the database. Specifically, it executes SQL queries.

[0893] 2. The server checks for inaccurate or missing data. For example, it uses validation scripts to ensure that all required fields are present.

[0894] 3. The server categorizes and standardizes the data. Specifically, it codes carrier names and performs preprocessing to convert pricing data to a specific scale.

[0895] Input: Stored customer information data

[0896] Output: Verified and pre-processed customer information data

[0897] Step 4: Data Analysis

[0898] 1. The server applies machine learning algorithms using historical high-conversion rate data. Specifically, it uses the Scikit-learn library in Python.

[0899] 2. The server compares newly entered customer information with past data to predict the optimal recommendation. Algorithms such as logistic regression and decision trees are used.

[0900] 3. The server retrieves the analysis results and generates optimal suggestions. For example, it generates suggestions based on the prediction results of a machine learning model.

[0901] Input: Verified and pre-processed customer information data, historical high conversion rate data

[0902] Output: Optimal proposal content

[0903] Step 5: Generate and submit proposals

[0904] 1. The server creates a specific message based on the optimal recommendation. For example, it might generate a suggestion such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[0905] 2. The server converts the generated proposal content into JSON format. Specifically, it formats the proposal content as a JSON object.

[0906] 3. The server sends the generated JSON data to the terminal using an HTTP POST request.

[0907] Input: Optimal proposal content

[0908] Output: The suggested content, converted to JSON format, is sent to the terminal.

[0909] Step 6: Proposal Display

[0910] 1. The terminal parses the JSON-formatted proposal received from the server. Specifically, it decodes the received data using JavaScript or Python's JSON library.

[0911] 2. The terminal displays the analyzed suggestions in the user interface. Specifically, it uses HTML and CSS to display the suggestion messages on the screen.

[0912] 3. Users can make suggestions to customers based on the displayed suggestions. Specifically, this can involve reading aloud messages displayed on the device or showing the screen.

[0913] Input: Proposal content in JSON format sent from the server

[0914] Output: Suggestions displayed in the user interface

[0915] The above describes the processing flow of this system's program.

[0916] (Application Example 1)

[0917] 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."

[0918] In physical stores, it is difficult for sales staff to quickly and accurately make the best recommendations to customers. Understanding customer needs and purchase history, and then proposing appropriate products and services based on that, requires the ability to process a large amount of information instantly. Furthermore, there is a need for a system that automatically generates optimal recommendations based on customer information and delivers those recommendations to customers in a timely manner. This creates a need for a system that can reduce the burden on sales staff and improve the closing rate.

[0919] 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.

[0920] In this invention, the server includes means for inputting customer information, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information, means for displaying the proposal content on the terminal, means including a terminal that runs a sales support application in a physical store, means for enabling sales staff to confirm the generated proposal content in real time, and means for automatically generating proposal content using a generation AI model and providing it to sales staff as a prompt message. This makes it possible for sales staff to receive optimal proposals in real time based on customer information and immediately make proposals to customers.

[0921] "Customer information" refers to personal attributes, purchase history, interests, and other information obtained through input by sales staff.

[0922] "Data format" refers to a form of data that can be processed by a computer, and in this context, it specifically refers to the JSON format.

[0923] A "server" is a computer system that receives, processes, stores, and analyzes customer information.

[0924] A "database" is a digital storage medium used to systematically organize and store received customer information.

[0925] "Verification" is the process of confirming that stored customer information is accurate and identifying inaccurate or incomplete data.

[0926] "Preprocessing" refers to the procedure of converting customer information into a format that is easy to analyze, and includes, for example, data categorization and standardization.

[0927] "Analysis" is the process of analyzing data to generate appropriate proposals based on pre-processed customer information.

[0928] "Proposed content" refers to information about products and services that are best suited to the customer, generated through analysis.

[0929] A "terminal" refers to a device operated by sales staff to input customer information or display sales proposals. In this context, it mainly refers to smartphones and tablets.

[0930] A "physical store" is a physical commercial facility where customers actually visit and make purchases.

[0931] A "sales support application" is software that runs on a device and provides information to help sales staff make the best possible proposals to customers.

[0932] "Real-time" means that the time between information being entered, processing it immediately, and the display of results is extremely short, almost instantaneous.

[0933] A "generative AI model" is an algorithm or program that uses machine learning to automatically generate new suggestions.

[0934] A "prompt message" is a guidance message output by a generation AI model, used by sales staff when making suggestions to customers.

[0935] This invention relates to a system for enabling sales staff in physical stores to make optimal suggestions in real time based on customer information. The system aims to perform a series of steps including inputting customer information, converting it to a data format, transmitting it to a server, storing the customer information in a database, verifying and preprocessing the data, generating optimal suggestions through analysis, and transmitting and displaying the generated suggestions to a terminal.

[0936] The hardware required to implement the system includes devices such as smartphones and tablets, servers, and a database management system (e.g., MySQL). The software includes libraries for implementing machine learning algorithms (e.g., TensorFlow), the HTTP protocol for data transmission and reception, and sales support applications for physical stores.

[0937] Entering and submitting customer information

[0938] The user (sales staff) enters customer information using a smartphone or tablet. This information includes the customer's name, age, purchase history, and product categories of interest. The entered information is converted to JSON format on the device and sent to the server via an HTTP POST request.

[0939] Data processing on the server

[0940] The server parses the JSON data received from the terminal and stores it in the database. Next, it verifies the stored data to check for any inaccuracies or incomplete data. After this, as a data preprocessing step, it performs categorization and standardization, such as mapping ages to specific age groups.

[0941] Analysis of customer information and generation of proposals

[0942] The server uses a machine learning model (e.g., TensorFlow) to generate optimal suggestions based on pre-processed customer information and past high-conversion rate data. In this process, a generative AI model is used to create prompt messages based on the customer information.

[0943] Submitting and displaying proposals

[0944] The generated suggestions are converted back into JSON format and sent to the terminal. This information is displayed visually on the terminal, allowing sales staff to check it in real time. Based on the displayed suggestions, users can then propose products and services to customers.

[0945] Specific example

[0946] When a customer visits a physical store, the sales staff enters the following information into a smartphone app:

[0947] Name: Customer A

[0948] Age: 35

[0949] Purchase history: Smartphones, tablets

[0950] Product categories of interest: Home appliances, audio equipment

[0951] This information is converted to JSON format and sent to the server. The server stores the data and uses a machine learning model to generate a suggestion such as, "If customer A is particular about sound quality, we recommend the latest Bluetooth speaker." This information is then sent back to the application, where sales staff can review it in real time and make suggestions to customers.

[0952] Example of a prompt

[0953] "Customer A, 35 years old, has come into the store. He has previously purchased a smartphone and a tablet, and is currently interested in home electronics and audio equipment. Please provide him with the best product recommendations."

[0954] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0955] Step 1:

[0956] User enters customer information

[0957] The user (sales staff) uses a smartphone or tablet to enter information such as the customer's name, age, purchase history, and product categories of interest. This information is converted into JSON format.

[0958] Input: Customer information (name, age, purchase history, product categories of interest)

[0959] Output: Customer information in JSON format

[0960] Step 2:

[0961] The terminal sends customer information to the server.

[0962] The terminal sends customer information, converted to JSON format, to the server via an HTTP POST request.

[0963] Input: Customer information in JSON format

[0964] Output: HTTP request to the server

[0965] Step 3:

[0966] The server saves customer information to the database.

[0967] The server parses the received JSON data and saves it to the database.

[0968] Input: Customer information in JSON format

[0969] Output: Customer information stored in the database

[0970] Step 4:

[0971] The server verifies customer information.

[0972] The server verifies the stored customer information to check for inaccurate or incomplete data. Inaccurate data is corrected, and incomplete data is assigned appropriate default values.

[0973] Input: Customer information stored in the database

[0974] Output: Verified customer information

[0975] Step 5:

[0976] The server preprocesses customer information.

[0977] The server categorizes and standardizes verified customer information. For example, it maps age to a specific age group.

[0978] Input: Verified customer information

[0979] Output: Preprocessed customer information

[0980] Step 6:

[0981] The server analyzes customer information.

[0982] The server generates optimal proposals using a generative AI model (e.g., TensorFlow) based on pre-processed customer information and past high conversion rate data.

[0983] Input: Pre-processed customer information, historical high conversion rate data

[0984] Output: Optimal proposal content

[0985] Step 7:

[0986] The server formats the proposal based on customer information.

[0987] The server formats the generated proposal based on customer information and converts it back into JSON format.

[0988] Input: Optimal proposal content

[0989] Output: Proposal in JSON format

[0990] Step 8:

[0991] The server sends the proposal to the terminal.

[0992] The server sends the proposed content, converted to JSON format, to the terminal via an HTTP request.

[0993] Input: Proposal content in JSON format

[0994] Output: HTTP request to terminal

[0995] Step 9:

[0996] The device displays the suggested content.

[0997] The terminal analyzes the received proposal and displays it visually. Sales staff then review the proposal and make it to the customer.

[0998] Input: Proposal content in JSON format

[0999] Output: Suggestion displayed to sales staff

[1000] Step 10:

[1001] The user makes a proposal to the customer based on the proposed content.

[1002] The user (sales staff) makes product and service recommendations to the customer based on the displayed suggestions.

[1003] Input: Suggestion displayed to the sales staff

[1004] Output: Proposals for the best products and services for customers

[1005] 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.

[1006] This invention relates to a system that generates optimal proposals using customer information to improve the conversion rate. Furthermore, by combining this with an emotion engine that recognizes user emotions, the system can personalize proposals and provide more accurate suggestions. The purpose of this system is for the server to analyze customer information and emotion information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[1007] Explanation of the program's processing

[1008] Data entry and transmission

[1009] The user enters customer information into an input form on the device. For example, they might enter information such as "Current carrier: NTT Docomo," "Current monthly fee: 5,000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." Simultaneously, an emotion engine built into the device analyzes the user's facial expressions and voice to collect emotion data.

[1010] Conversion to data format and transmission

[1011] The terminal verifies the entered customer information and sentiment data in real time to check for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format such as JSON and sends it to the server via an HTTP request.

[1012] Data reception and storage

[1013] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. The server then stores this customer information and sentiment data in the database. The database organizes and stores the customer information and sentiment data so that it can be used for analysis later.

[1014] Data validation and preprocessing

[1015] The server verifies the stored data, checking for inaccuracies or missing data. Next, preprocessing is performed, such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[1016] Data analysis and proposal generation

[1017] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical high-conversion rate data to predict optimal recommendations. By incorporating sentiment data into the analysis, it can generate recommendations tailored to the user's psychological state. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[1018] Submitting and displaying proposals

[1019] The server converts the generated proposal content into JSON format and sends it to the terminal. The terminal parses the proposal content received from the server and displays it visually to the user. The proposal content is displayed in an easy-to-understand manner using a GUI (Graphical User Interface). The user can review this displayed proposal content and make a proposal to the customer.

[1020] Explanation of specific examples

[1021] For example, a user might input customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." The emotion engine then analyzes the user's facial expressions and voice to determine that "User's emotional state: Positive." When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[1022] The server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice, based on past high conversion rate data, current customer information, and sentiment data. Furthermore, based on sentiment data, it predicts that this offer will be even more effective because the user is in a positive state. This generated offer is sent to the device and displayed to the user. The user can then use this offer to their customers to improve their conversion rate.

[1023] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal suggestions based on customer information and emotional information, thereby effectively supporting sales activities.

[1024] The following describes the processing flow.

[1025] Step 1:

[1026] Users enter customer information into input forms on their devices. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine analyzes this to generate emotion data.

[1027] Step 2:

[1028] The terminal verifies the entered customer information and sentiment data in real time, checking for any missing or inaccurate data. Once verification is complete, it converts the information into an appropriate data format, such as JSON.

[1029] Step 3:

[1030] The terminal sends the converted JSON-formatted customer information and sentiment data to the server using an HTTP request. SSL / TLS protocol is used to ensure security during this process.

[1031] Step 4:

[1032] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory and added to a queue for later processing.

[1033] Step 5:

[1034] The server stores received customer information and sentiment data in a database. Specifically, it inserts customer ID, carrier information, charges, number of family members using the service, internet environment, usage purpose, and sentiment data into the corresponding tables.

[1035] Step 6:

[1036] The server verifies the stored data. This verification includes checking for data consistency, the presence of invalid data, and missing data. If errors are detected, appropriate error handling and logging are performed.

[1037] Step 7:

[1038] The server preprocesses the verified data. This includes categorization (e.g., converting carrier names to codes) and standardization (e.g., converting rates to a unified scale), and sentiment data is also standardized.

[1039] Step 8:

[1040] The server analyzes pre-processed data. It uses machine learning algorithms (e.g., decision trees, random forests) to analyze historical high-conversion rate data and newly entered customer information to generate optimal recommendations. By including emotional data in the analysis, it provides recommendations tailored to the user's psychological state.

[1041] Step 9:

[1042] The server generates recommendations based on the analysis results. For example, it might set up a specific recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[1043] Step 10:

[1044] The server converts the generated proposal content back into JSON format and sends it to the terminal. SSL / TLS protocol is used to ensure security during this process.

[1045] Step 11:

[1046] The terminal analyzes the suggestions received from the server and displays them visually to the user. The suggestions are displayed through a GUI in a way that is easy for the user to understand.

[1047] Step 12:

[1048] Users review the proposals displayed on their devices and then submit them to customers. If the customer agrees to the proposal, the user proceeds with the closing process. This approach can improve the closing rate.

[1049] (Example 2)

[1050] 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."

[1051] Proposals based solely on customer information tend to be generic and uniform, often failing to fully address the individual needs of each customer. This makes it difficult to improve conversion rates, and generating more personalized proposals is a challenge. Furthermore, traditional systems cannot consider the user's psychological state when making proposals, making it difficult to increase customer satisfaction.

[1052] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment data, means for converting the input customer information and sentiment data into a data format and transmitting it to the server, means for storing the received customer information and sentiment data in a database, means for verifying and pre-processing the stored customer information and sentiment data, means for performing analysis based on the pre-processed customer information and sentiment data and generating optimal proposal content, means for transmitting the generated proposal content to the terminal into which the customer information was input, and means for displaying the proposal content on the terminal. This makes it possible to generate more accurate personalized proposals that are tailored to the individual needs and psychological state of each customer.

[1053] "Customer information" refers to detailed data about the individuals or companies to whom services or products are provided.

[1054] "Emotional data" refers to data that indicates a user's psychological state, analyzed from their facial expressions, voice, body movements, and other factors.

[1055] A "data format" is a way of organizing data according to a specific structure or set of rules, making it easier to process and communicate.

[1056] A "server" is a computer system that stores, processes, and transmits data.

[1057] A "database" is a system for efficiently and systematically storing and managing digital information.

[1058] "Preprocessing" refers to a series of processes that prepare data for easier analysis, including imputation of missing values ​​and standardization.

[1059] A "machine learning algorithm" is a computational method that learns patterns and regularities based on large amounts of data, and uses that learning to make predictions and classifications on new data.

[1060] "Recommended content" refers to recommendations for the most suitable services and products for the customer, generated based on the analysis results.

[1061] A "terminal" is a device that a user directly operates to input or display information.

[1062] "Transmission" is the process of transferring data or information to a specific receiving device.

[1063] "Display" refers to the act of making information visible, or the technology used for that purpose.

[1064] This invention is a system that generates optimal proposals based on customer information and emotional data, thereby improving the conversion rate. This system is realized through the cooperation of a server and terminals.

[1065] The user operates the terminal and enters customer information. This customer information includes items such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the terminal is equipped with an emotion engine that analyzes the user's facial expressions and voice to collect emotional data. This emotion engine also allows the user's psychological state to be understood in real time.

[1066] The terminal verifies the entered customer information and sentiment data in real time to check for any missing or inaccurate data. If there are no problems, it converts the information to JSON format and sends it to the server via an HTTP request. The server receives the data sent from the terminal, temporarily stores it in memory, and then stores the customer information and sentiment data in the database.

[1067] The server re-verifies the stored data to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., charges are converted to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[1068] The server uses machine learning libraries such as Python's Scikit-learn to perform analysis based on pre-processed customer information and sentiment data. It applies algorithms using historical high-conversion rate data to predict the optimal proposal. By incorporating sentiment data into the analysis, it can generate personalized proposals tailored to the user's psychological state. The generated proposals are then converted to JSON format and sent to the terminal.

[1069] The terminal analyzes the proposals received from the server and displays them visually to the user. This display is designed to be user-friendly using front-end frameworks such as React.js and Vue.js. Users can review the displayed proposals and present them to customers to improve their conversion rates.

[1070] Explanation of specific examples

[1071] For example, a user enters the following customer information:

[1072] Current carrier: NTT Docomo

[1073] Current fee: 5000 yen per month

[1074] Number of devices used by the family: 3

[1075] Internet connection: Fiber optic

[1076] Usage: Watching videos, using social media, making phone calls

[1077] Furthermore, the emotion engine recognizes the user's emotional state as "positive." The device converts this information into JSON format and sends it to the server. The server receives the data, stores it in a database, and then applies a machine learning algorithm using Python's Scikit-learn. Based on high conversion rate data, it determines that "NTT Docomo's Family Discount Plan" is optimal and predicts that the suggestion will be effective because the user is in a positive state.

[1078] The generated proposal is as follows:

[1079] NTT Docomo's family discount plan is highly recommended. It's especially ideal for customers who prioritize watching videos and using social media.

[1080] The server sends this proposal to the terminal, which then displays it to the user using a GUI. The user can review this proposal and present it to the customer to improve the conversion rate.

[1081] Thus, the system of the present invention makes it possible to generate optimal proposals based on customer information and emotional data, thereby effectively supporting sales activities.

[1082] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1083] Step 1: Data entry and sentiment analysis

[1084] The user enters customer information into an input form on the device. This customer information includes items such as "current carrier," "current charges," "number of family devices," "internet environment," and "intended use." The entered data is stored in the input fields on the device. Simultaneously, the device's built-in emotion engine analyzes the user's facial expressions and voice to collect emotion data. The obtained emotion data is saved in the input fields as emotion categories such as "joy," "sadness," and "surprise."

[1085] Step 2: Convert to data format and send

[1086] The terminal verifies the entered customer information and sentiment data in real time to ensure there is no missing or inaccurate data. Once this verification is complete, the terminal converts the information into JSON format. In this conversion process, text and numerical data are organized into a specific key-value pair format. The converted data is then sent to the server as an HTTP request.

[1087] Step 3: Data reception and storage

[1088] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. Next, the server stores this customer information and sentiment data in a database system. Assigning a unique identifier when storing the data in the database enables efficient searching.

[1089] Step 4: Data validation and preprocessing

[1090] The server re-verifies the data stored in the database to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., prices are scaled). At this time, sentiment data is also smoothed and formatted to a format suitable for analysis. The preprocessed data is stored in temporary memory to move on to the next analysis step.

[1091] Step 5: Data Analysis and Proposal Generation

[1092] The server uses machine learning libraries such as Python's Scikit-learn to analyze pre-processed data. Based on past high-conversion rate data, the server applies a machine learning algorithm to predict the optimal proposal. This algorithm finds patterns based on input customer information and sentiment data and generates appropriate proposals. For example, it might suggest a family discount plan to users with large families.

[1093] Step 6: Submit and view your proposal

[1094] The server converts the generated proposal content into JSON format and sends it to the terminal as an HTTP response. The terminal parses the proposal content received from the server and displays it visually to the user. This display uses front-end frameworks such as React.js or Vue.js and is formatted for easy viewing. The user can review this displayed proposal content and offer it to customers to improve the conversion rate.

[1095] The above outlines the specific processing steps of the system. Through the specific actions, inputs, and outputs in each step, the system can efficiently generate and display optimal suggestions.

[1096] (Application Example 2)

[1097] 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."

[1098] In brick-and-mortar stores, there is a need to quickly and accurately provide optimal product recommendations based on customer requests. However, conventional systems have difficulty considering customer emotional information, resulting in recommendations that do not adequately address the customer's psychological state. This can lead to lower conversion rates and reduced customer satisfaction. Therefore, there was a need for a system that could analyze customer emotional information in real time and provide optimal product recommendations.

[1099] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment information, means for converting the input customer information and sentiment information into a data format and transmitting it to the server, means for storing the received customer information and sentiment information in a database, means for verifying and pre-processing the stored customer information and sentiment information, means for performing analysis based on the pre-processed customer information and sentiment information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information and sentiment information, means for displaying the proposal content on the terminal, and means for visually displaying the proposal content via a smart device. This makes it possible to make highly accurate product proposals in real time, taking into account customer sentiment information.

[1100] "Customer information" refers to detailed information about a customer, such as their age, gender, products of interest, and purpose of use.

[1101] "Emotional information" refers to information indicating a customer's psychological state, obtained by analyzing their facial expressions and voice.

[1102] "Data format" refers to the format used to structure information according to certain rules and to exchange it between computers.

[1103] A "server" refers to a computer system that stores, processes, and analyzes data, and delivers the results to terminals.

[1104] A "database" refers to a system for efficiently storing and managing a collection of information.

[1105] "Preprocessing" refers to the process of standardizing data and formatting it into a suitable format for analysis prior to the analysis itself.

[1106] A "machine learning algorithm" refers to a computer algorithm that learns from customer information, emotional data, and past transaction data to predict the most suitable proposal.

[1107] A "smart device" refers to an electronic device with advanced functions for collecting emotional information and displaying suggestions, such as smart glasses or smartphones.

[1108] "Recommended content" refers to the optimal product or service recommendations generated based on customer information and emotional information.

[1109] This invention is a system for improving the efficiency of customer service in physical stores and increasing the conversion rate. This system implements a series of processes for inputting customer information and emotional information, and for generating and displaying optimal suggestions. The specific embodiments of this system are described in detail below.

[1110] Hardware and software usage

[1111] 1. Hardware

[1112] Smart devices: Smart glasses and smartphones are used to collect customer information and sentiment data, and to display suggested content. This example assumes devices such as Google Glass or Vuzix Blade.

[1113] Server: A high-performance computer system is used to store, process, and analyze data. For example, a Dell PowerEdge is suitable.

[1114] 2. Software

[1115] Emotion Analysis Engine: Microsoft Azure Cognitive Services and IBM Watson are used to collect emotional information by analyzing customers' facial expressions and voices.

[1116] Database Management System: Database management software such as MySQL or PostgreSQL is used to centrally manage customer information and sentiment information.

[1117] Machine learning algorithms: We use machine learning libraries such as TensorFlow and PyTorch to analyze customer information and sentiment information and generate optimal recommendations.

[1118] Data processing and data calculation

[1119] 1. Data entry and transmission

[1120] The user enters customer information using the voice input function of smart glasses. For example, they might enter information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase."

[1121] Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information.

[1122] 2. Conversion to data format and transmission

[1123] The system verifies the entered customer information and sentiment data in real time, and if there are no problems, converts it to an appropriate data format (e.g., JSON format) and sends it to the server.

[1124] 3. Data reception and storage

[1125] The server receives the transmitted data, temporarily stores it in memory, and then stores it in the database.

[1126] 4. Data validation and preprocessing

[1127] The server verifies the received data, checking for inaccuracies or missing information. Next, it standardizes the data (for example, converting charges to a specific scale) and formats it into a format suitable for analysis.

[1128] 5. Data Analysis and Proposal Generation

[1129] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical conversion rate data to predict the optimal proposal.

[1130] By incorporating emotional data into the analysis, it becomes possible to generate suggestions tailored to the user's psychological state.

[1131] 6. Submitting and displaying proposals

[1132] The server converts the generated suggestions into JSON format and sends them to the smart glasses.

[1133] Smart glasses display suggested items, and store staff make these suggestions to customers.

[1134] Specific example

[1135] For example, if a woman in her 30s comes into the store looking for a skincare product as a gift, a store employee wearing smart glasses will collect and input the information as follows:

[1136] "Gender: Female", "Age: 30s", "Products of Interest: Skincare", "Purpose: Gift purchase".

[1137] Furthermore, if the emotion analysis engine determines that "the customer's emotional state is positive," this information is used to perform analysis on the server, and a "highly moisturizing skincare set" will be suggested.

[1138] Example of a prompt

[1139] "A woman in her 30s, interested in skincare products, intended use as a gift, and experiencing positive emotions."

[1140] "Male in his 40s, interested in electronic products, intended use is personal, emotional state is neutral."

[1141] This makes it possible to provide product suggestions optimized to customer needs in real time, which is expected to improve the conversion rate.

[1142] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1143] Step 1:

[1144] The user wears smart glasses and inputs basic customer information by voice. For example, they might input information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase." This input information is stored as metadata in the smart glasses. Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information such as "positive."

[1145] Input: User voice input, customer facial expressions and voice

[1146] Data processing: Speech-to-text conversion, emotional information analysis.

[1147] Output: Customer information (text format), sentiment information

[1148] Step 2:

[1149] The device (smart glasses) verifies customer information and sentiment information in real time to check for inaccurate or missing data. Data that is free of problems is converted to JSON format and sent to the server via an HTTP request.

[1150] Input: Customer information (text format), sentiment information

[1151] Data processing: Real-time verification, conversion to JSON format.

[1152] Output: Customer information and sentiment information in JSON format, HTTP request

[1153] Step 3:

[1154] The server receives JSON data sent from the terminal and temporarily stores it in memory. Then, it stores customer information and sentiment information in the database. This data is then organized for subsequent processing.

[1155] Input: Customer information and sentiment information in JSON format

[1156] Data processing: Data reception, saving to memory, storage in database.

[1157] Output: Customer information and sentiment information stored in the database

[1158] Step 4:

[1159] The server verifies the stored data, checking for inaccuracies or missing information. Next, it standardizes the data and formats it into a suitable format for analysis. This process may involve tasks such as converting charges to a specific scale.

[1160] Input: Customer information and sentiment information stored in the database

[1161] Data processing: Data validation, standardization, and formatting.

[1162] Output: Data in a format suitable for analysis

[1163] Step 5:

[1164] The server uses machine learning algorithms to analyze pre-processed customer information and emotional data. It generates optimal recommendations based on high conversion rate data. In this process, emotional information is also taken into consideration; for example, if the user is in a positive state, it might suggest a skincare set as a particularly easy product to recommend.

[1165] Input: Pre-processed customer information and sentiment information

[1166] Data processing: Analysis using machine learning algorithms

[1167] Output: Optimal proposal content

[1168] Step 6:

[1169] The server converts the generated proposal into JSON format and sends it to the terminal as an HTTP response.

[1170] Input: Optimal proposal content

[1171] Data processing: Conversion to JSON format

[1172] Output: Proposal content in JSON format, HTTP response

[1173] Step 7:

[1174] The device (smart glasses) analyzes the suggested content received from the server and displays it visually. Based on this information, the store clerk makes the most suitable product suggestions to the customer. The suggested content is designed to be easy on the user's eyes.

[1175] Input: Proposal content in JSON format

[1176] Data processing: Parsing of JSON data, GUI display.

[1177] Output: Visually displayed proposal content

[1178] 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.

[1179] 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.

[1180] 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.

[1181] [Fourth Embodiment]

[1182] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1183] 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.

[1184] 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).

[1185] 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.

[1186] 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.

[1187] 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).

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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.

[1192] 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.

[1193] 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.

[1194] 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".

[1195] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The system aims to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[1196] The user (sales staff) enters customer information using a terminal. The terminal converts this information into an appropriate data format (e.g., JSON format) and sends it to the server. The server receives this information and stores it in a database. Furthermore, the server validates and preprocesses the data and performs analysis to generate optimal recommendations based on this information. The generated recommendations are then sent back to the terminal and displayed to the user.

[1197] Explanation of the program's processing

[1198] Data entry and transmission

[1199] The user enters customer information using their device. For example, they might enter information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". The entered information is converted to JSON format by the device and sent to the server via an HTTP request.

[1200] Data storage and management

[1201] The server parses the JSON data received from the terminal and stores it in the database. The database organizes and stores customer information so that it can be used for analysis later.

[1202] Data validation and preprocessing

[1203] The server verifies the stored data, checking for inaccuracies or missing data. Next, it performs preprocessing such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale).

[1204] Data Analysis

[1205] The server uses historical high-conversion rate data to apply machine learning algorithms and generate optimal proposals for customers. In this process, it compares and analyzes historical data with newly entered customer information, using a model to predict the best proposal.

[1206] Proposal generation and submission

[1207] Based on the analysis results, the server generates optimal recommendations for the customer. For example, it might generate a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use." The generated recommendations are converted to JSON format and sent to the device.

[1208] Suggestion display

[1209] The terminal analyzes the suggestions received from the server and displays them visually to the user. The user can then make suggestions to customers based on these displayed suggestions.

[1210] Explanation of specific examples

[1211] For example, a user might input customer information such as "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of devices used by family: 3", "Internet environment: Fiber optic", and "Usage: Watching videos, using social media, making calls". When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[1212] Based on past high conversion rate data, the server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice and generates this proposal. This generated proposal is sent to the terminal and displayed to the user. The user can then use this proposal to improve their conversion rate.

[1213] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal proposals based on customer information and effectively support sales activities.

[1214] The following describes the processing flow.

[1215] Step 1:

[1216] The user enters customer information into an input form on their device. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Once the user has finished entering the information, they press the submit button.

[1217] Step 2:

[1218] The terminal verifies the entered customer information in real time, checking for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format, such as JSON.

[1219] Step 3:

[1220] The terminal sends the converted JSON-formatted customer information to the server using an HTTP request. It is recommended to use the SSL / TLS protocol for security purposes during this process.

[1221] Step 4:

[1222] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory in preparation for the next processing step.

[1223] Step 5:

[1224] The server stores the received customer information in a database. Specifically, it inserts information such as customer ID, carrier information, charges, number of family members using the service, internet environment, and usage purpose into the corresponding tables.

[1225] Step 6:

[1226] The server verifies the stored customer information. It checks whether the data is consistent, free from non-numeric data, and free from missing data. If any deficiencies are found, it records an error log and sends an alert to the relevant parties.

[1227] Step 7:

[1228] The server preprocesses the verified data. Specifically, it performs categorization, such as coding carrier names, and standardization, such as converting charges to a specific scale.

[1229] Step 8:

[1230] The server performs analysis based on pre-processed data. It uses historical high-conversion rate data to apply machine learning algorithms (e.g., decision trees and random forests) to predict the optimal proposal.

[1231] Step 9:

[1232] The server generates optimal recommendations based on the analysis results. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[1233] Step 10:

[1234] The server converts the generated proposal into JSON format and sends it to the terminal. It also uses an HTTP response for this process, applying the SSL / TLS protocol as needed.

[1235] Step 11:

[1236] The terminal analyzes the received suggestions and displays them visually to the user. The suggestions are displayed appropriately in a GUI (Graphical User Interface) to make them easy for the user to understand.

[1237] Step 12:

[1238] The user makes a proposal to the customer based on the proposal displayed on the device. If the customer agrees to the proposal, the user proceeds with the contract closing procedure.

[1239] (Example 1)

[1240] 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".

[1241] Traditional systems often involve manual processes from customer information input to the generation and display of optimal proposals, resulting in low efficiency. Furthermore, proposals are uniform across all customers, making it difficult to tailor them to individual needs. Consequently, there are limitations to improving the conversion rate, hindering efficient sales activities.

[1242] 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.

[1243] In this invention, the server includes means for inputting customer information using a device used by the user, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for applying a machine learning algorithm using past high conversion rate data to generate optimal proposal content, means for transmitting the generated proposal content to the device into which the customer information was input, and means for displaying the proposal content on the device. This makes it possible to automatically generate optimal proposal content based on customer information and to make proposals to customers quickly and efficiently.

[1244] "User" refers to an individual or organization that uses the system to input and verify customer information.

[1245] "Device" refers to a device used for inputting customer information and displaying proposals (e.g., personal computer, smartphone, tablet, etc.).

[1246] "Customer information" refers to detailed data about a customer (e.g., current carrier, charges, number of devices used, internet environment, usage purpose, etc.).

[1247] "Data format" refers to a specific structure (e.g., JSON format) that a computer system uses to understand and process data.

[1248] A "server" refers to a computer system that receives, stores, analyzes, generates, and transmits data.

[1249] A "database" refers to a structured data storage system used to efficiently store and manage data such as customer information and analytical results.

[1250] "Preprocessing" refers to the steps of standardizing, categorizing, and validating data for analysis.

[1251] A "machine learning algorithm" refers to a computational method that automatically learns patterns and rules from data and uses that knowledge to make predictions and classifications.

[1252] "Optimal proposal content" refers to a proposal message that is deemed most effective or appropriate for a particular customer, based on their customer information.

[1253] "Past high conversion rate data" refers to proposals and sales data that were effective in the past, and is used as data for training machine learning algorithms.

[1254] This invention relates to a system that generates optimal proposals using customer information and improves the conversion rate. The purpose of this system is for a server to analyze customer information entered by the user, generate optimal proposals, and display them on the terminal.

[1255] The user (sales staff) enters customer information using a terminal. Specifically, they use devices such as smartphones, tablets, or personal computers to enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." This information is converted to JSON format by the terminal and sent to the server via an HTTP request.

[1256] The server is hardware that runs programs written in Python or Java. It first parses JSON data received from terminals and stores it in a database. Customer information is organized and stored in this database using SQL or NoSQL technologies. The stored data is first verified for accuracy and completeness. After that, preprocessing is performed, such as coding carrier names and standardizing pricing.

[1257] The server analyzes data using machine learning algorithms. Specifically, it uses Python's Scikit-learn library and TensorFlow to compare and analyze historical high-conversion rate data with newly entered customer information. This builds a model that predicts the optimal recommendation. Based on this model, the server generates the optimal recommendation. For example, it might generate a specific recommendation message such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[1258] The generated proposals are converted back into JSON format and sent to the terminal using an HTTP request. The terminal parses the received proposals and displays them in the user interface. Based on these displayed proposals, the user can then make the most appropriate proposals for the customer.

[1259] As a concrete example, a user enters customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." This information is converted to JSON format by the device and sent to the server. The server stores and preprocesses the information, and uses a machine learning algorithm to generate a recommendation that "NTT Docomo's family discount plan is optimal" based on this information. This recommendation is sent to the device and displayed to the user.

[1260] Examples of prompt statements are as follows:

[1261] "Please generate the optimal proposal based on the customer information. The customer's current carrier is NTT Docomo, their current monthly fee is 5,000 yen, they use 3 devices, their internet connection is fiber optic, and their usage is video streaming, social media, and phone calls."

[1262] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1263] Program processing steps

[1264] Step 1: Data entry and submission

[1265] 1. The user enters customer information using the device. For example, they enter information such as: "Current carrier: NTT Docomo", "Current monthly fee: 5000 yen", "Number of family devices used: 3", "Internet environment: Fiber optic connection", and "Usage: Watching videos, using social media, making calls".

[1266] 2. The terminal converts the entered information into JSON format. Specifically, it formats the data from the input form as a JSON object using JavaScript or Python.

[1267] 3. The terminal sends the generated JSON data to the server using an HTTP POST request. This communication is performed by specifying the endpoint URL.

[1268] Input: Customer information entered by the user (carrier, fee, number of devices used, etc.)

[1269] Output: Customer information converted to JSON format is sent to the server.

[1270] Step 2: Data storage and management

[1271] 1. The server parses the JSON data received from the terminal. Specifically, it decodes the received data using Python's JSON library or Java's Gson library.

[1272] 2. The server connects to the database and stores the received customer information. Specifically, it executes commands to insert data using SQL statements or NoSQL queries.

[1273] 3. The server generates a confirmation message that the save was successful and sends it back to the terminal. This message notifies the user that the save was performed successfully.

[1274] Input: Customer information in JSON format sent from the terminal.

[1275] Output: Customer information is saved to the database and a confirmation message is sent to the terminal.

[1276] Step 3: Data validation and preprocessing

[1277] 1. The server reads the data stored in the database. Specifically, it executes SQL queries.

[1278] 2. The server checks for inaccurate or missing data. For example, it uses validation scripts to ensure that all required fields are present.

[1279] 3. The server categorizes and standardizes the data. Specifically, it codes carrier names and performs preprocessing to convert pricing data to a specific scale.

[1280] Input: Stored customer information data

[1281] Output: Verified and pre-processed customer information data

[1282] Step 4: Data Analysis

[1283] 1. The server applies machine learning algorithms using historical high-conversion rate data. Specifically, it uses the Scikit-learn library in Python.

[1284] 2. The server compares newly entered customer information with past data to predict the optimal recommendation. Algorithms such as logistic regression and decision trees are used.

[1285] 3. The server retrieves the analysis results and generates optimal suggestions. For example, it generates suggestions based on the prediction results of a machine learning model.

[1286] Input: Verified and pre-processed customer information data, historical high conversion rate data

[1287] Output: Optimal proposal content

[1288] Step 5: Generate and submit proposals

[1289] 1. The server creates a specific message based on the optimal recommendation. For example, it might generate a suggestion such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[1290] 2. The server converts the generated proposal content into JSON format. Specifically, it formats the proposal content as a JSON object.

[1291] 3. The server sends the generated JSON data to the terminal using an HTTP POST request.

[1292] Input: Optimal proposal content

[1293] Output: The suggested content, converted to JSON format, is sent to the terminal.

[1294] Step 6: Proposal Display

[1295] 1. The terminal parses the JSON-formatted proposal received from the server. Specifically, it decodes the received data using JavaScript or Python's JSON library.

[1296] 2. The terminal displays the analyzed suggestions in the user interface. Specifically, it uses HTML and CSS to display the suggestion messages on the screen.

[1297] 3. Users can make suggestions to customers based on the displayed suggestions. Specifically, this can involve reading aloud messages displayed on the device or showing the screen.

[1298] Input: Proposal content in JSON format sent from the server

[1299] Output: Suggestions displayed in the user interface

[1300] The above describes the processing flow of this system's program.

[1301] (Application Example 1)

[1302] 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".

[1303] In physical stores, it is difficult for sales staff to quickly and accurately make the best recommendations to customers. Understanding customer needs and purchase history, and then proposing appropriate products and services based on that, requires the ability to process a large amount of information instantly. Furthermore, there is a need for a system that automatically generates optimal recommendations based on customer information and delivers those recommendations to customers in a timely manner. This creates a need for a system that can reduce the burden on sales staff and improve the closing rate.

[1304] 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.

[1305] In this invention, the server includes means for inputting customer information, means for converting the input customer information into a data format and transmitting it to the server, means for storing the received customer information in a database, means for verifying and pre-processing the stored customer information, means for performing analysis based on the pre-processed customer information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information, means for displaying the proposal content on the terminal, means including a terminal that runs a sales support application in a physical store, means for enabling sales staff to confirm the generated proposal content in real time, and means for automatically generating proposal content using a generation AI model and providing it to sales staff as a prompt message. This makes it possible for sales staff to receive optimal proposals in real time based on customer information and immediately make proposals to customers.

[1306] "Customer information" refers to personal attributes, purchase history, interests, and other information obtained through input by sales staff.

[1307] "Data format" refers to a form of data that can be processed by a computer, and in this context, it specifically refers to the JSON format.

[1308] A "server" is a computer system that receives, processes, stores, and analyzes customer information.

[1309] A "database" is a digital storage medium used to systematically organize and store received customer information.

[1310] "Verification" is the process of confirming that stored customer information is accurate and identifying inaccurate or incomplete data.

[1311] "Preprocessing" refers to the procedure of converting customer information into a format that is easy to analyze, and includes, for example, data categorization and standardization.

[1312] "Analysis" is the process of analyzing data to generate appropriate proposals based on pre-processed customer information.

[1313] "Proposed content" refers to information about products and services that are best suited to the customer, generated through analysis.

[1314] A "terminal" refers to a device operated by sales staff to input customer information or display sales proposals. In this context, it mainly refers to smartphones and tablets.

[1315] A "physical store" is a physical commercial facility where customers actually visit and make purchases.

[1316] A "sales support application" is software that runs on a device and provides information to help sales staff make the best possible proposals to customers.

[1317] "Real-time" means that the time between information being entered, processing it immediately, and the display of results is extremely short, almost instantaneous.

[1318] A "generative AI model" is an algorithm or program that uses machine learning to automatically generate new suggestions.

[1319] A "prompt message" is a guidance message output by a generation AI model, used by sales staff when making suggestions to customers.

[1320] This invention relates to a system for enabling sales staff in physical stores to make optimal suggestions in real time based on customer information. The system aims to perform a series of steps including inputting customer information, converting it to a data format, transmitting it to a server, storing the customer information in a database, verifying and preprocessing the data, generating optimal suggestions through analysis, and transmitting and displaying the generated suggestions to a terminal.

[1321] The hardware required to implement the system includes devices such as smartphones and tablets, servers, and a database management system (e.g., MySQL). The software includes libraries for implementing machine learning algorithms (e.g., TensorFlow), the HTTP protocol for data transmission and reception, and sales support applications for physical stores.

[1322] Entering and submitting customer information

[1323] The user (sales staff) enters customer information using a smartphone or tablet. This information includes the customer's name, age, purchase history, and product categories of interest. The entered information is converted to JSON format on the device and sent to the server via an HTTP POST request.

[1324] Data processing on the server

[1325] The server parses the JSON data received from the terminal and stores it in the database. Next, it verifies the stored data to check for any inaccuracies or incomplete data. After this, as a data preprocessing step, it performs categorization and standardization, such as mapping ages to specific age groups.

[1326] Analysis of customer information and generation of proposals

[1327] The server uses a machine learning model (e.g., TensorFlow) to generate optimal suggestions based on pre-processed customer information and past high-conversion rate data. In this process, a generative AI model is used to create prompt messages based on the customer information.

[1328] Submitting and displaying proposals

[1329] The generated suggestions are converted back into JSON format and sent to the terminal. This information is displayed visually on the terminal, allowing sales staff to check it in real time. Based on the displayed suggestions, users can then propose products and services to customers.

[1330] Specific example

[1331] When a customer visits a physical store, the sales staff enters the following information into a smartphone app:

[1332] Name: Customer A

[1333] Age: 35

[1334] Purchase history: Smartphones, tablets

[1335] Product categories of interest: Home appliances, audio equipment

[1336] This information is converted to JSON format and sent to the server. The server stores the data and uses a machine learning model to generate a suggestion such as, "If customer A is particular about sound quality, we recommend the latest Bluetooth speaker." This information is then sent back to the application, where sales staff can review it in real time and make suggestions to customers.

[1337] Example of a prompt

[1338] "Customer A, 35 years old, has come into the store. He has previously purchased a smartphone and a tablet, and is currently interested in home electronics and audio equipment. Please provide him with the best product recommendations."

[1339] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1340] Step 1:

[1341] User enters customer information

[1342] The user (sales staff) uses a smartphone or tablet to enter information such as the customer's name, age, purchase history, and product categories of interest. This information is converted into JSON format.

[1343] Input: Customer information (name, age, purchase history, product categories of interest)

[1344] Output: Customer information in JSON format

[1345] Step 2:

[1346] The terminal sends customer information to the server.

[1347] The terminal sends customer information, converted to JSON format, to the server via an HTTP POST request.

[1348] Input: Customer information in JSON format

[1349] Output: HTTP request to the server

[1350] Step 3:

[1351] The server saves customer information to the database.

[1352] The server parses the received JSON data and saves it to the database.

[1353] Input: Customer information in JSON format

[1354] Output: Customer information stored in the database

[1355] Step 4:

[1356] The server verifies customer information.

[1357] The server verifies the stored customer information to check for inaccurate or incomplete data. Inaccurate data is corrected, and incomplete data is assigned appropriate default values.

[1358] Input: Customer information stored in the database

[1359] Output: Verified customer information

[1360] Step 5:

[1361] The server preprocesses customer information.

[1362] The server categorizes and standardizes verified customer information. For example, it maps age to a specific age group.

[1363] Input: Verified customer information

[1364] Output: Preprocessed customer information

[1365] Step 6:

[1366] The server analyzes customer information.

[1367] The server generates optimal proposals using a generative AI model (e.g., TensorFlow) based on pre-processed customer information and past high conversion rate data.

[1368] Input: Pre-processed customer information, historical high conversion rate data

[1369] Output: Optimal proposal content

[1370] Step 7:

[1371] The server formats the proposal based on customer information.

[1372] The server formats the generated proposal based on customer information and converts it back into JSON format.

[1373] Input: Optimal proposal content

[1374] Output: Proposal in JSON format

[1375] Step 8:

[1376] The server sends the proposal to the terminal.

[1377] The server sends the proposed content, converted to JSON format, to the terminal via an HTTP request.

[1378] Input: Proposal content in JSON format

[1379] Output: HTTP request to terminal

[1380] Step 9:

[1381] The device displays the suggested content.

[1382] The terminal analyzes the received proposal and displays it visually. Sales staff then review the proposal and make it to the customer.

[1383] Input: Proposal content in JSON format

[1384] Output: Suggestion displayed to sales staff

[1385] Step 10:

[1386] The user makes a proposal to the customer based on the proposed content.

[1387] The user (sales staff) makes product and service recommendations to the customer based on the displayed suggestions.

[1388] Input: Suggestion displayed to the sales staff

[1389] Output: Proposals for the best products and services for customers

[1390] 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.

[1391] This invention relates to a system that generates optimal proposals using customer information to improve the conversion rate. Furthermore, by combining this with an emotion engine that recognizes user emotions, the system can personalize proposals and provide more accurate suggestions. The purpose of this system is for the server to analyze customer information and emotion information entered by the user, generate optimal proposals, and display them on the terminal. Specific embodiments will be described in detail below.

[1392] Explanation of the program's processing

[1393] Data entry and transmission

[1394] The user enters customer information into an input form on the device. For example, they might enter information such as "Current carrier: NTT Docomo," "Current monthly fee: 5,000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." Simultaneously, an emotion engine built into the device analyzes the user's facial expressions and voice to collect emotion data.

[1395] Conversion to data format and transmission

[1396] The terminal verifies the entered customer information and sentiment data in real time to check for missing or inaccurate data. If there are no problems, it converts the information into an appropriate data format such as JSON and sends it to the server via an HTTP request.

[1397] Data reception and storage

[1398] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. The server then stores this customer information and sentiment data in the database. The database organizes and stores the customer information and sentiment data so that it can be used for analysis later.

[1399] Data validation and preprocessing

[1400] The server verifies the stored data, checking for inaccuracies or missing data. Next, preprocessing is performed, such as categorizing the data (e.g., coding carrier names) and standardizing it (e.g., converting charges to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[1401] Data analysis and proposal generation

[1402] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical high-conversion rate data to predict optimal recommendations. By incorporating sentiment data into the analysis, it can generate recommendations tailored to the user's psychological state. For example, it might create a recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize video viewing and social media use."

[1403] Submitting and displaying proposals

[1404] The server converts the generated proposal content into JSON format and sends it to the terminal. The terminal parses the proposal content received from the server and displays it visually to the user. The proposal content is displayed in an easy-to-understand manner using a GUI (Graphical User Interface). The user can review this displayed proposal content and make a proposal to the customer.

[1405] Explanation of specific examples

[1406] For example, a user might input customer information such as "Current carrier: NTT Docomo," "Current monthly fee: 5000 yen," "Number of family devices: 3," "Internet environment: Fiber optic," and "Usage: Watching videos, using social media, making calls." The emotion engine then analyzes the user's facial expressions and voice to determine that "User's emotional state: Positive." When the device sends this information to the server, the server receives the data, stores it in a database, and then performs analysis.

[1407] The server uses a machine learning algorithm to determine that "NTT Docomo's Family Discount Plan" is the optimal choice, based on past high conversion rate data, current customer information, and sentiment data. Furthermore, based on sentiment data, it predicts that this offer will be even more effective because the user is in a positive state. This generated offer is sent to the device and displayed to the user. The user can then use this offer to their customers to improve their conversion rate.

[1408] The above describes a specific embodiment for carrying out the present invention. This embodiment makes it possible to automatically generate optimal suggestions based on customer information and emotional information, thereby effectively supporting sales activities.

[1409] The following describes the processing flow.

[1410] Step 1:

[1411] Users enter customer information into input forms on their devices. Specifically, they enter information such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the device's camera and microphone are used to capture the user's facial expressions and voice, and an emotion engine analyzes this to generate emotion data.

[1412] Step 2:

[1413] The terminal verifies the entered customer information and sentiment data in real time, checking for any missing or inaccurate data. Once verification is complete, it converts the information into an appropriate data format, such as JSON.

[1414] Step 3:

[1415] The terminal sends the converted JSON-formatted customer information and sentiment data to the server using an HTTP request. SSL / TLS protocol is used to ensure security during this process.

[1416] Step 4:

[1417] The server receives JSON data sent from the terminal. The received data is temporarily stored in memory and added to a queue for later processing.

[1418] Step 5:

[1419] The server stores received customer information and sentiment data in a database. Specifically, it inserts customer ID, carrier information, charges, number of family members using the service, internet environment, usage purpose, and sentiment data into the corresponding tables.

[1420] Step 6:

[1421] The server verifies the stored data. This verification includes checking for data consistency, the presence of invalid data, and missing data. If errors are detected, appropriate error handling and logging are performed.

[1422] Step 7:

[1423] The server preprocesses the verified data. This includes categorization (e.g., converting carrier names to codes) and standardization (e.g., converting rates to a unified scale), and sentiment data is also standardized.

[1424] Step 8:

[1425] The server analyzes pre-processed data. It uses machine learning algorithms (e.g., decision trees, random forests) to analyze historical high-conversion rate data and newly entered customer information to generate optimal recommendations. By including emotional data in the analysis, it provides recommendations tailored to the user's psychological state.

[1426] Step 9:

[1427] The server generates recommendations based on the analysis results. For example, it might set up a specific recommendation such as, "NTT Docomo's family discount plan is recommended. It's especially ideal for customers who prioritize watching videos and using social media."

[1428] Step 10:

[1429] The server converts the generated proposal content back into JSON format and sends it to the terminal. SSL / TLS protocol is used to ensure security during this process.

[1430] Step 11:

[1431] The terminal analyzes the suggestions received from the server and displays them visually to the user. The suggestions are displayed through a GUI in a way that is easy for the user to understand.

[1432] Step 12:

[1433] Users review the proposals displayed on their devices and then submit them to customers. If the customer agrees to the proposal, the user proceeds with the closing process. This approach can improve the closing rate.

[1434] (Example 2)

[1435] 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".

[1436] Proposals based solely on customer information tend to be generic and uniform, often failing to fully address the individual needs of each customer. This makes it difficult to improve conversion rates, and generating more personalized proposals is a challenge. Furthermore, traditional systems cannot consider the user's psychological state when making proposals, making it difficult to increase customer satisfaction.

[1437] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment data, means for converting the input customer information and sentiment data into a data format and transmitting it to the server, means for storing the received customer information and sentiment data in a database, means for verifying and pre-processing the stored customer information and sentiment data, means for performing analysis based on the pre-processed customer information and sentiment data and generating optimal proposal content, means for transmitting the generated proposal content to the terminal into which the customer information was input, and means for displaying the proposal content on the terminal. This makes it possible to generate more accurate personalized proposals that are tailored to the individual needs and psychological state of each customer.

[1438] "Customer information" refers to detailed data about the individuals or companies to whom services or products are provided.

[1439] "Emotional data" refers to data that indicates a user's psychological state, analyzed from their facial expressions, voice, body movements, and other factors.

[1440] A "data format" is a way of organizing data according to a specific structure or set of rules, making it easier to process and communicate.

[1441] A "server" is a computer system that stores, processes, and transmits data.

[1442] A "database" is a system for efficiently and systematically storing and managing digital information.

[1443] "Preprocessing" refers to a series of processes that prepare data for easier analysis, including imputation of missing values ​​and standardization.

[1444] A "machine learning algorithm" is a computational method that learns patterns and regularities based on large amounts of data, and uses that learning to make predictions and classifications on new data.

[1445] "Recommended content" refers to recommendations for the most suitable services and products for the customer, generated based on the analysis results.

[1446] A "terminal" is a device that a user directly operates to input or display information.

[1447] "Transmission" is the process of transferring data or information to a specific receiving device.

[1448] "Display" refers to the act of making information visible, or the technology used for that purpose.

[1449] This invention is a system that generates optimal proposals based on customer information and emotional data, thereby improving the conversion rate. This system is realized through the cooperation of a server and terminals.

[1450] The user operates the terminal and enters customer information. This customer information includes items such as "current carrier," "current charges," "number of family members using the service," "internet environment," and "intended use." Furthermore, the terminal is equipped with an emotion engine that analyzes the user's facial expressions and voice to collect emotional data. This emotion engine also allows the user's psychological state to be understood in real time.

[1451] The terminal verifies the entered customer information and sentiment data in real time to check for any missing or inaccurate data. If there are no problems, it converts the information to JSON format and sends it to the server via an HTTP request. The server receives the data sent from the terminal, temporarily stores it in memory, and then stores the customer information and sentiment data in the database.

[1452] The server re-verifies the stored data to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., charges are converted to a specific scale). Sentimental data is also standardized and smoothed in a similar manner to prepare it for analysis.

[1453] The server uses machine learning libraries such as Python's Scikit-learn to perform analysis based on pre-processed customer information and sentiment data. It applies algorithms using historical high-conversion rate data to predict the optimal proposal. By incorporating sentiment data into the analysis, it can generate personalized proposals tailored to the user's psychological state. The generated proposals are then converted to JSON format and sent to the terminal.

[1454] The terminal analyzes the proposals received from the server and displays them visually to the user. This display is designed to be user-friendly using front-end frameworks such as React.js and Vue.js. Users can review the displayed proposals and present them to customers to improve their conversion rates.

[1455] Explanation of specific examples

[1456] For example, a user enters the following customer information:

[1457] Current carrier: NTT Docomo

[1458] Current fee: 5000 yen per month

[1459] Number of devices used by the family: 3

[1460] Internet connection: Fiber optic

[1461] Usage: Watching videos, using social media, making phone calls

[1462] Furthermore, the emotion engine recognizes the user's emotional state as "positive." The device converts this information into JSON format and sends it to the server. The server receives the data, stores it in a database, and then applies a machine learning algorithm using Python's Scikit-learn. Based on high conversion rate data, it determines that "NTT Docomo's Family Discount Plan" is optimal and predicts that the suggestion will be effective because the user is in a positive state.

[1463] The generated proposal is as follows:

[1464] NTT Docomo's family discount plan is highly recommended. It's especially ideal for customers who prioritize watching videos and using social media.

[1465] The server sends this proposal to the terminal, which then displays it to the user using a GUI. The user can review this proposal and present it to the customer to improve the conversion rate.

[1466] Thus, the system of the present invention makes it possible to generate optimal proposals based on customer information and emotional data, thereby effectively supporting sales activities.

[1467] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1468] Step 1: Data entry and sentiment analysis

[1469] The user enters customer information into an input form on the device. This customer information includes items such as "current carrier," "current charges," "number of family devices," "internet environment," and "intended use." The entered data is stored in the input fields on the device. Simultaneously, the device's built-in emotion engine analyzes the user's facial expressions and voice to collect emotion data. The obtained emotion data is saved in the input fields as emotion categories such as "joy," "sadness," and "surprise."

[1470] Step 2: Convert to data format and send

[1471] The terminal verifies the entered customer information and sentiment data in real time to ensure there is no missing or inaccurate data. Once this verification is complete, the terminal converts the information into JSON format. In this conversion process, text and numerical data are organized into a specific key-value pair format. The converted data is then sent to the server as an HTTP request.

[1472] Step 3: Data reception and storage

[1473] The server receives data in JSON format sent from the terminal. The received data is temporarily stored in memory. Next, the server stores this customer information and sentiment data in a database system. Assigning a unique identifier when storing the data in the database enables efficient searching.

[1474] Step 4: Data validation and preprocessing

[1475] The server re-verifies the data stored in the database to check for inaccuracies or missing data. Next, as a preprocessing step, the data is categorized (e.g., carrier names are coded) and standardized (e.g., prices are scaled). At this time, sentiment data is also smoothed and formatted to a format suitable for analysis. The preprocessed data is stored in temporary memory to move on to the next analysis step.

[1476] Step 5: Data Analysis and Proposal Generation

[1477] The server uses machine learning libraries such as Python's Scikit-learn to analyze pre-processed data. Based on past high-conversion rate data, the server applies a machine learning algorithm to predict the optimal proposal. This algorithm finds patterns based on input customer information and sentiment data and generates appropriate proposals. For example, it might suggest a family discount plan to users with large families.

[1478] Step 6: Submit and view your proposal

[1479] The server converts the generated proposal content into JSON format and sends it to the terminal as an HTTP response. The terminal parses the proposal content received from the server and displays it visually to the user. This display uses front-end frameworks such as React.js or Vue.js and is formatted for easy viewing. The user can review this displayed proposal content and offer it to customers to improve the conversion rate.

[1480] The above outlines the specific processing steps of the system. Through the specific actions, inputs, and outputs in each step, the system can efficiently generate and display optimal suggestions.

[1481] (Application Example 2)

[1482] 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".

[1483] In brick-and-mortar stores, there is a need to quickly and accurately provide optimal product recommendations based on customer requests. However, conventional systems have difficulty considering customer emotional information, resulting in recommendations that do not adequately address the customer's psychological state. This can lead to lower conversion rates and reduced customer satisfaction. Therefore, there was a need for a system that could analyze customer emotional information in real time and provide optimal product recommendations.

[1484] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting customer information and sentiment information, means for converting the input customer information and sentiment information into a data format and transmitting it to the server, means for storing the received customer information and sentiment information in a database, means for verifying and pre-processing the stored customer information and sentiment information, means for performing analysis based on the pre-processed customer information and sentiment information and generating optimal proposal content, means for transmitting the generated proposal content to the terminal that input the customer information and sentiment information, means for displaying the proposal content on the terminal, and means for visually displaying the proposal content via a smart device. This makes it possible to make highly accurate product proposals in real time, taking into account customer sentiment information.

[1485] "Customer information" refers to detailed information about a customer, such as their age, gender, products of interest, and purpose of use.

[1486] "Emotional information" refers to information indicating a customer's psychological state, obtained by analyzing their facial expressions and voice.

[1487] "Data format" refers to the format used to structure information according to certain rules and to exchange it between computers.

[1488] A "server" refers to a computer system that stores, processes, and analyzes data, and delivers the results to terminals.

[1489] A "database" refers to a system for efficiently storing and managing a collection of information.

[1490] "Preprocessing" refers to the process of standardizing data and formatting it into a suitable format for analysis prior to the analysis itself.

[1491] A "machine learning algorithm" refers to a computer algorithm that learns from customer information, emotional data, and past transaction data to predict the most suitable proposal.

[1492] A "smart device" refers to an electronic device with advanced functions for collecting emotional information and displaying suggestions, such as smart glasses or smartphones.

[1493] "Recommended content" refers to the optimal product or service recommendations generated based on customer information and emotional information.

[1494] This invention is a system for improving the efficiency of customer service in physical stores and increasing the conversion rate. This system implements a series of processes for inputting customer information and emotional information, and for generating and displaying optimal suggestions. The specific embodiments of this system are described in detail below.

[1495] Hardware and software usage

[1496] 1. Hardware

[1497] Smart devices: Smart glasses and smartphones are used to collect customer information and sentiment data, and to display suggested content. This example assumes devices such as Google Glass or Vuzix Blade.

[1498] Server: A high-performance computer system is used to store, process, and analyze data. For example, a Dell PowerEdge is suitable.

[1499] 2. Software

[1500] Emotion Analysis Engine: Microsoft Azure Cognitive Services and IBM Watson are used to collect emotional information by analyzing customers' facial expressions and voices.

[1501] Database Management System: Database management software such as MySQL or PostgreSQL is used to centrally manage customer information and sentiment information.

[1502] Machine learning algorithms: We use machine learning libraries such as TensorFlow and PyTorch to analyze customer information and sentiment information and generate optimal recommendations.

[1503] Data processing and data calculation

[1504] 1. Data entry and transmission

[1505] The user enters customer information using the voice input function of smart glasses. For example, they might enter information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase."

[1506] Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information.

[1507] 2. Conversion to data format and transmission

[1508] The system verifies the entered customer information and sentiment data in real time, and if there are no problems, converts it to an appropriate data format (e.g., JSON format) and sends it to the server.

[1509] 3. Data reception and storage

[1510] The server receives the transmitted data, temporarily stores it in memory, and then stores it in the database.

[1511] 4. Data validation and preprocessing

[1512] The server verifies the received data, checking for inaccuracies or missing information. Next, it standardizes the data (for example, converting charges to a specific scale) and formats it into a format suitable for analysis.

[1513] 5. Data Analysis and Proposal Generation

[1514] The server performs analysis based on pre-processed customer information and sentiment data. It applies machine learning algorithms using historical conversion rate data to predict the optimal proposal.

[1515] By incorporating emotional data into the analysis, it becomes possible to generate suggestions tailored to the user's psychological state.

[1516] 6. Submitting and displaying proposals

[1517] The server converts the generated suggestions into JSON format and sends them to the smart glasses.

[1518] Smart glasses display suggested items, and store staff make these suggestions to customers.

[1519] Specific example

[1520] For example, if a woman in her 30s comes into the store looking for a skincare product as a gift, a store employee wearing smart glasses will collect and input the information as follows:

[1521] "Gender: Female", "Age: 30s", "Products of Interest: Skincare", "Purpose: Gift purchase".

[1522] Furthermore, if the emotion analysis engine determines that "the customer's emotional state is positive," this information is used to perform analysis on the server, and a "highly moisturizing skincare set" will be suggested.

[1523] Example of a prompt

[1524] "A woman in her 30s, interested in skincare products, intended use as a gift, and experiencing positive emotions."

[1525] "Male in his 40s, interested in electronic products, intended use is personal, emotional state is neutral."

[1526] This makes it possible to provide product suggestions optimized to customer needs in real time, which is expected to improve the conversion rate.

[1527] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1528] Step 1:

[1529] The user wears smart glasses and inputs basic customer information by voice. For example, they might input information such as "Gender: Female," "Age: 30s," "Products of Interest: Skincare," and "Purpose: Gift Purchase." This input information is stored as metadata in the smart glasses. Simultaneously, an emotion analysis engine analyzes the customer's facial expressions and voice to collect emotional information such as "positive."

[1530] Input: User voice input, customer facial expressions and voice

[1531] Data processing: Speech-to-text conversion, emotional information analysis.

[1532] Output: Customer information (text format), sentiment information

[1533] Step 2:

[1534] The device (smart glasses) verifies customer information and sentiment information in real time to check for inaccurate or missing data. Data that is free of problems is converted to JSON format and sent to the server via an HTTP request.

[1535] Input: Customer information (text format), sentiment information

[1536] Data processing: Real-time verification, conversion to JSON format.

[1537] Output: Customer information and sentiment information in JSON format, HTTP request

[1538] Step 3:

[1539] The server receives JSON data sent from the terminal and temporarily stores it in memory. Then, it stores customer information and sentiment information in the database. This data is then organized for subsequent processing.

[1540] Input: Customer information and sentiment information in JSON format

[1541] Data processing: Data reception, saving to memory, storage in database.

[1542] Output: Customer information and sentiment information stored in the database

[1543] Step 4:

[1544] The server verifies the stored data, checking for inaccuracies or missing information. Next, it standardizes the data and formats it into a suitable format for analysis. This process may involve tasks such as converting charges to a specific scale.

[1545] Input: Customer information and sentiment information stored in the database

[1546] Data processing: Data validation, standardization, and formatting.

[1547] Output: Data in a format suitable for analysis

[1548] Step 5:

[1549] The server uses machine learning algorithms to analyze pre-processed customer information and emotional data. It generates optimal recommendations based on high conversion rate data. In this process, emotional information is also taken into consideration; for example, if the user is in a positive state, it might suggest a skincare set as a particularly easy product to recommend.

[1550] Input: Pre-processed customer information and sentiment information

[1551] Data processing: Analysis using machine learning algorithms

[1552] Output: Optimal proposal content

[1553] Step 6:

[1554] The server converts the generated proposal into JSON format and sends it to the terminal as an HTTP response.

[1555] Input: Optimal proposal content

[1556] Data processing: Conversion to JSON format

[1557] Output: Proposal content in JSON format, HTTP response

[1558] Step 7:

[1559] The device (smart glasses) analyzes the suggested content received from the server and displays it visually. Based on this information, the store clerk makes the most suitable product suggestions to the customer. The suggested content is designed to be easy on the user's eyes.

[1560] Input: Proposal content in JSON format

[1561] Data processing: Parsing of JSON data, GUI display.

[1562] Output: Visually displayed proposal content

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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."

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] The following is further disclosed regarding the embodiments described above.

[1585] (Claim 1)

[1586] [Methods for entering customer information,

[1587] [Methods for converting entered customer information into a data format and sending it to the server,

[1588] [Means for saving received customer information in a database,

[1589] [Means for verifying and pre-processing stored customer information,

[1590] [Methods for performing analysis based on pre-processed customer information and generating optimal proposals,

[1591] [Means for sending the generated proposal content to a terminal where customer information has been entered,

[1592] [Means for displaying the proposed content on the terminal,

[1593] A system that includes this.

[1594] (Claim 2)

[1595] [The system according to claim 1, which analyzes past high conversion rate data using a machine learning algorithm and predicts the optimal proposal method.

[1596] (Claim 3)

[1597] [The system according to claim 1, which formats the proposed content based on customer information and converts it into a data format before sending it to the terminal.

[1598] "Example 1"

[1599] (Claim 1)

[1600] [Means of inputting customer information using a device used by the user,

[1601] [Methods for converting entered customer information into a data format and sending it to the server,

[1602] [Means for saving received customer information in a database,

[1603] [Means for verifying and pre-processing stored customer information,

[1604] [Methods for performing analysis based on pre-processed customer information and generating optimal proposals,

[1605] [A means of generating optimal proposals by applying machine learning algorithms using past high conversion rate data,

[1606] [Means for transmitting the generated proposal content to a device into which customer information has been entered,

[1607] [Means for displaying the proposed content on the device,

[1608] A system that includes this.

[1609] (Claim 2)

[1610] [The system according to claim 1, wherein a user inputs customer information, converts it into an appropriate data format, and transmits it to a server.

[1611] (Claim 3)

[1612] [The system according to claim 1, which formats the proposed content based on customer information and converts it into a data format before sending it to the device.

[1613] "Application Example 1"

[1614] (Claim 1)

[1615] [Methods for entering customer information,

[1616] [Methods for converting entered customer information into a data format and sending it to the server,

[1617] [Means for saving received customer information in a database,

[1618] [Means for verifying and pre-processing stored customer information,

[1619] [Methods for performing analysis based on pre-processed customer information and generating optimal proposals,

[1620] [Means for sending the generated proposal content to a terminal where customer information has been entered,

[1621] [Means for displaying the proposed content on the terminal,

[1622] [Means including a terminal for running a sales support application in a physical store,

[1623] [A means to allow sales staff to check the generated proposals in real time,

[1624] A system that includes this.

[1625] (Claim 2)

[1626] [The system according to claim 1, which analyzes past high conversion rate data using a machine learning algorithm and predicts the optimal proposal method.

[1627] (Claim 3)

[1628] [The system according to claim 1, which formats the proposed content based on customer information and converts it into a data format before sending it to the terminal.

[1629] (Claim 4)

[1630] [The system according to claim 1, which automatically generates suggested content using a generative AI model and provides it to sales staff as a prompt message.

[1631] "Example 2 of combining an emotion engine"

[1632] (Claim 1)

[1633] [Means for inputting customer information and sentiment data,

[1634] [Means for converting entered customer information and sentiment data into a data format and sending it to the server,

[1635] [Means for storing received customer information and sentiment data in a database,

[1636] [Means for verifying and pre-processing stored customer information and sentiment data,

[1637] [Means for performing analysis based on pre-processed customer information and sentiment data to generate optimal proposals,

[1638] [Means for sending the generated proposal content to a terminal where customer information has been entered,

[1639] [Means for displaying the proposed content on the terminal,

[1640] A system that includes this.

[1641] (Claim 2)

[1642] [The system according to claim 1, which analyzes past high conversion rate data using a machine learning algorithm and predicts the optimal proposal content.

[1643] (Claim 3)

[1644] [The system according to claim 1, which formats the proposed content based on customer information and sentiment data, and converts it into a data format before sending it to the terminal.

[1645] "Application example 2 of combining emotional engines"

[1646] (Claim 1)

[1647] [Means for inputting customer information and emotional information,

[1648] [Means for converting entered customer information and sentiment information into a data format and sending it to a server,

[1649] [Means for storing received customer information and sentiment information in a database,

[1650] [Means for verifying and pre-processing stored customer information and sentiment information,

[1651] [Means for performing analysis based on pre-processed customer information and sentiment information to generate optimal proposals,

[1652] [Means for sending the generated proposal content to a terminal into which customer information and sentiment information have been entered,

[1653] [Means for displaying the proposed content on the terminal,

[1654] [Means for visually displaying the proposed content via a smart device,

[1655] A system that includes this.

[1656] (Claim 2)

[1657] [The system according to claim 1, which uses a machine learning algorithm to analyze past high conversion rate data and current customer information and sentiment information to predict the optimal proposal method.]

[1658] (Claim 3)

[1659] [The system according to claim 1, which formats the proposed content based on customer information and sentiment information, and converts it into a data format before sending it to the terminal. [Explanation of symbols]

[1660] 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 of entering customer information, A means of converting the entered customer information into a data format and sending it to the server, A means of storing received customer information in a database, Means for verifying and pre-processing stored customer information, A means for performing analysis based on pre-processed customer information and generating optimal proposals, A means of sending the generated proposal content to a terminal into which customer information has been entered, A means of displaying the proposed content on a terminal, A system that includes this.

2. The system according to claim 1, which analyzes past high conversion rate data using a machine learning algorithm and predicts the optimal proposal method.

3. The system according to claim 1, which formats the proposed content based on customer information and converts it into a data format before sending it to a terminal.

Images