System

Abstract

A system is provided.SOLUTION: A system comprising: input means for allowing a user to input a consulting request; data collection means for collecting relevant data based on input information; preprocessing means for preprocessing the collected data; data storage means for storing the preprocessed data; generation means for generating a proposal using the preprocessed data; transmission means for transmitting the generated proposal to a consultant terminal; review means for allowing a consultant to review and modify the proposal; and feedback means for feeding back a final proposal to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Today's consulting businesses require a large number of personnel, resulting in high service fees. This makes it difficult for many companies to obtain professional consulting services. Another problem is inconsistent quality due to variations in consultants' skills and knowledge. The objective of this invention is to automate many consulting tasks by utilizing generative AI and provide efficient and cost-effective consulting services. [Means for solving the problem]

[0005] The present invention is a system that includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for saving the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for sending the generated proposal to a consultant terminal, a review means for the consultant to review and modify the proposal content, and a feedback means for feeding back the final proposal to the user. With this system, the generation AI automates many tasks, reducing the workload of consultants and improving the quality of service.

[0006] "User" refers to a company or individual who uses the consulting services.

[0007] The "input means" refers to an interface through which a user inputs a consulting request, such as a web form or an application.

[0008] "Data collection means" refers to a mechanism for automatically collecting relevant data based on user input.

[0009] "Preprocessing means" refers to a function that performs processing to prepare collected data into a format that can be analyzed.

[0010] "Data storage means" refers to a storage system for temporarily or permanently storing pre-processed data.

[0011] "Generation means" refers to the AI ​​engine or algorithm that automatically generates suggestions based on stored data.

[0012] The "transmission means" refers to a communication function for transmitting the proposal created by the creation means to the consultant terminal.

[0013] "Consultant Device" refers to the device used by the actual consultant to review and revise the proposal.

[0014] "Review Procedure" refers to the process by which the consultant evaluates the proposals from the generation procedure and makes corrections as necessary.

[0015] "Feedback means" refers to the functionality for returning final recommendations to the user and providing actionable advice and instructions. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The present invention is a system that includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user.

[0038] Specific explanation of the system's operation

[0039] User Input

[0040] A user uses a web form or application to input the details of a consulting request. For example, the user inputs a request such as "I would like to improve my marketing strategy through the analysis of customer data."

[0041] Data collection and preprocessing

[0042] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0043] Proposal generation by generative AI

[0044] The server inputs the stored preprocessed data into a generative AI engine to generate proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific proposals that meet the user's requests. For example, it generates a proposal such as "Identify target segments and conduct social media campaigns."

[0045] Consultant review and follow-up

[0046] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0047] Specific examples

[0048] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[0049] 1. User Input: A user fills out a web form with "Improve marketing strategies through customer data analysis."

[0050] 2. Data collection: The server collects relevant data from internal databases and external APIs.

[0051] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0052] 4. Proposal Generation: The generative AI engine analyzes the data and proposes "identifying target segments and implementing social media campaigns."

[0053] 5. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0054] 6. Feedback: Send the final proposal to the user and provide implementation instructions or recommended actions.

[0055] This invention enables generative AI to automate many consulting tasks, providing efficient and cost-effective services. Users can receive high-quality consulting services quickly, and can meet a variety of needs, such as promoting digital transformation and strengthening risk management.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user enters the project outline and required consulting details into the input form. The entered information is sent to the server by the terminal.

[0059] Step 2:

[0060] The server processes the input information received from the user and initiates data collection methods to collect relevant data, which may include retrieving the required data from internal databases or external APIs.

[0061] Step 3:

[0062] The server preprocesses the collected data. Preprocessing includes data cleaning (for example, filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[0063] Step 4:

[0064] The server stores the preprocessed data in a data storage means, and the stored data is used for analysis by the generative AI engine.

[0065] Step 5:

[0066] The server launches a generative AI engine, which provides the stored preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate suggestions based on the user's requests.

[0067] Step 6:

[0068] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[0069] Step 7:

[0070] The terminal displays the proposal to the consultant, who reviews it and makes any necessary revisions.

[0071] Step 8:

[0072] The terminal sends the final proposal to the server, which then sends the revised final proposal to the user as feedback.

[0073] Step 9:

[0074] The user receives the final proposal and implements any actionable advice or instructions. If there is additional feedback from the user, the cycle begins again.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] In traditional consulting work, users manually input the details of requests, and the subsequent data collection, proposal generation, review, and feedback required a great deal of time and cost. In addition, due to a lack of automated processes, many aspects of the work depended on specific know-how and experience, and there was a need to improve efficiency.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes input means for a user to input a consulting request, data collection means for collecting related data based on the input information, preprocessing means for preprocessing the collected data, data storage means for storing the preprocessed data, generation means for a generative AI model to generate a proposal based on the preprocessed data, transmission means for transmitting the generated proposal to a consultant terminal, review means for the consultant to review and modify the proposal content, feedback means for feeding back the final proposal to the user, input means for inputting data to the generative AI model using a prompt sentence, and display means for the consultant to check and modify the proposal content on his terminal. This automates and streamlines the entire process in consulting work, from data collection to proposal generation, review, and feedback, enabling significant reductions in time and cost.

[0080] "User" refers to an individual or company that uses the system to input a consulting request.

[0081] "Input means" refers to an interface or device that allows a user to input the content of a consulting request.

[0082] "Data Collection Measures" refers to software or systems for collecting relevant data based on input information.

[0083] "Preprocessing means" refers to software or a system for processing collected data to convert it into a format suitable for analysis and for removing noise data.

[0084] "Data storage means" refers to a database or cloud storage for storing preprocessed data.

[0085] "Generator" means a generative artificial intelligence model and associated software for generating recommendations using the pre-processed data.

[0086] "Transmission means" refers to communication means for transmitting the generated proposal to the consultant terminal.

[0087] "Review Tool" means a specialized interface or software that allows a Consultant to review and modify the Proposal.

[0088] "Feedback means" refers to a means for providing feedback on the final proposal to the user.

[0089] A "generative artificial intelligence model" refers to a system that uses machine learning algorithms and natural language processing technology to automatically generate suggestions based on input data.

[0090] A "prompt" refers to a text-based instruction or question that is input to a generative artificial intelligence model.

[0091] "Terminal" refers to the device used by the consultant to review and revise the proposal.

[0092] "Display means" refers to the display or user interface that allows the consultant to check and modify the proposal content on a terminal.

[0093] A specific embodiment of the present invention will be described below. This system automates a series of processes: a user inputs a consulting request, collects and preprocesses data based on the request, generates a proposal using a generative AI model, and then a consultant reviews and modifies the final proposal, providing the final proposal as feedback to the user.

[0094] Specific configuration and operation

[0095] User Input

[0096] The user enters the details of the consulting request through a web form or application. This input method is provided, for example, as a form that runs on a web browser or a mobile application. The user enters specific details of the request into the form, such as "I would like to improve my marketing strategy through the analysis of customer data," and clicks the submit button.

[0097] Data collection and preprocessing

[0098] The server receives input from the user and collects relevant data based on that input, either from an internal database (MySQL or PostgreSQL) or an external API (Google Analytics API, Twitter API, etc.) The server communicates with these databases and APIs to retrieve data relevant to the user's request.

[0099] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes unnecessary noise data, and converts the data format (for example, converting it to a CSV file or data frame). This prepares the data in a format suitable for analysis. The preprocessed data is then stored in a database or cloud storage, which is used as a data storage method.

[0100] Proposal generation

[0101] The server inputs the preprocessed data into a generative AI engine, which uses OpenAI GPT-3 or similar natural language processing technology. This AI engine uses machine learning algorithms to generate specific suggestions that address the user's request. For example, a suggestion might be, "Identify target segments and run social media campaigns."

[0102] Examples of prompts used to generate suggestions are:

[0103] "The user wants to improve their marketing strategy by analyzing customer data. The relevant data has been collected and preprocessed. Based on this, you would like to generate specific recommendations for the user."

[0104] Consultant review and feedback

[0105] The generated proposal is sent from the server to the consultant's terminal. The consultant can check the proposal contents by displaying them on a dedicated interface and make corrections if necessary. This display means is designed to make it easy for the consultant to check the proposal contents.

[0106] After the consultant makes any necessary corrections, the final proposal is finalized. This final proposal is then sent back to the user via the server as a means of feedback. The user can then receive the feedback and confirm specific implementation steps and recommended action plans.

[0107] This system enables faster, higher-quality consulting services than traditional manual processes. By combining generative AI with data pre-processing and consultant review, we can deliver efficient and cost-effective services.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Step 1:

[0110] User Input

[0111] The user enters the details of the consulting request through a web form or application. Specifically, the user enters a request such as "I would like to improve my marketing strategy through the analysis of customer data" and clicks the "Submit" button. This input is sent to the server and used to collect data for the next step.

[0112] Input: User's request (e.g., "I want to improve my marketing strategy through customer data analysis.")

[0113] Output: The request sent to the server

[0114] Step 2:

[0115] Data collection

[0116] The server collects relevant data based on the request received from the user. Specifically, it obtains the necessary data using an internal database (e.g., MySQL, PostgreSQL) or an external API (e.g., Google Analytics API, Twitter API). The server temporarily stores the obtained data and passes it to the next preprocessing step.

[0117] Input: User's request

[0118] Output: Relevant data collected

[0119] Step 3:

[0120] Data Preprocessing

[0121] The server performs preprocessing on the collected data. Specifically, it performs data cleaning, including filling in missing values ​​and removing noise data, and converts the data into a format suitable for analysis (e.g., CSV file, data frame). After preprocessing, the data is stored in a database.

[0122] Input: Relevant data collected

[0123] Output: Preprocessed data

[0124] Step 4:

[0125] Proposal generation

[0126] The server inputs the preprocessed data into a generative AI engine (e.g., OpenAI GPT-3), which uses the prompt to generate specific suggestions based on the user's request. For example, a suggestion might be "Identify target segments and conduct social media campaigns."

[0127] Input: Preprocessed data, prompt (e.g., "The user requests that we improve our marketing strategy through the analysis of customer data. The relevant data has been collected and preprocessed. Based on this, please generate specific suggestions for the user.")

[0128] Output: Generated proposals

[0129] Step 5:

[0130] Proposal Review

[0131] The generated proposal is sent from the server to the terminal (consultant device). The consultant reviews the content and makes any necessary corrections. The reviewed proposal is then sent to the server as the final proposal.

[0132] Input: Generated proposals

[0133] Output: Reviewed final proposal

[0134] Step 6:

[0135] feedback

[0136] The server then sends the final proposal, reviewed and revised by the consultant, back to the user. Specifically, it sends the final proposal to the user's email address or a dedicated user interface. The user receives the feedback and checks specific implementation steps and recommended action plans.

[0137] Input: Reviewed final proposal

[0138] Output: Final proposals fed back to the user

[0139] (Application example 1)

[0140] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0141] Conventional consulting systems have difficulty efficiently processing consulting requests from users, and in particular, they have not adequately proposed personalized marketing strategies that utilize customer behavior data and sales data in virtual stores. This poses a challenge, making it difficult to maximize customer engagement and sales opportunities.

[0142] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0143] In this invention, the server includes an input means for users to input consulting requests, a data collection means for collecting related data based on the input information, and a preprocessing means for preprocessing the collected data. This allows for efficient collection and processing of data based on user requests, automatic proposal of personalized marketing strategies using a generative AI model, and the proposals can be reviewed and revised by consultants to reflect them in the final proposal. Furthermore, by adding functions for collecting and preprocessing customer behavior data and sales data within the virtual store, it is possible to provide users with more accurate personalized marketing strategies.

[0144] "User" refers to an individual or organization that submits a consulting request.

[0145] "Input means" refers to a mechanism or device that provides an interface for users to input consulting requests into the system.

[0146] "Data collection means" refers to a mechanism for collecting related data based on information input by a user.

[0147] "Pre-processing means" refers to a mechanism that processes collected data to convert it into a format suitable for analysis and generation of proposals by a generative AI model.

[0148] "Data storage means" refers to a mechanism for storing preprocessed data.

[0149] "Generative means" refers to the generative AI model or algorithm that uses pre-processed data to generate recommendations.

[0150] The "transmission means" refers to a mechanism for transmitting the generated proposal to the consultant terminal.

[0151] "Review procedures" refer to the mechanisms by which consultants review proposals and make corrections as necessary.

[0152] "Feedback means" refers to a mechanism for feeding back the final proposal to the user.

[0153] "Additional data collection means" refers to a mechanism for collecting customer behavior data and sales data within the virtual store.

[0154] "Additional pre-processing means" refers to a mechanism for pre-processing customer behavior data and sales data and converting them into a format for use in analysis.

[0155] "Generative AI model" refers to a model that uses machine learning algorithms and natural language processing techniques to generate suggestions.

[0156] "Strategy generation means" refers to a mechanism that uses a generative AI model to generate personalized marketing strategies for virtual stores.

[0157] The "strategy feedback means" refers to a mechanism for providing the generated marketing strategy to the user and providing feedback including implementation procedures and recommended actions.

[0158] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the proposal content, and a feedback means for feeding back the final proposal to the user.The system also includes an additional data collection means for collecting customer behavior data and sales data in a virtual store, an additional preprocessing means for preprocessing the customer behavior data and sales data and using it for analysis, a strategy generation means for generating a personalized marketing strategy using a generative AI model, and a strategy feedback means for providing the generated strategy to the user.

[0159] Program operation explanation

[0160] 1. User Input: A user enters a consulting request within a virtual store through a web form or mobile application. For example, a user might say, "Please tell me when there will be sales this month."

[0161] 2. Data collection: The server receives the input information and collects relevant data. The main data sources are customer behavior data (e.g., clickstream data) and sales data within the virtual store. These are obtained from internal databases and external APIs.

[0162] 3. Preprocessing: The server performs preprocessing on the collected data, such as filling in missing data and removing noise data, to generate preprocessed data.

[0163] 4. Proposal generation using generative AI: Using the preprocessed data, a generative AI model (e.g., GPT-3) is used to generate proposals. For example, a specific proposal such as "Hold a sale in the third week of this month" is generated.

[0164] 5. Review and follow-up by consultant: The proposal will be sent to the consultant's terminal, where the consultant will review the proposal and make any necessary corrections.

[0165] 6. Feedback: A final suggestion is given to the user, for example, "We'll have a sale in the third week of this month, and we'll focus on specific products."

[0166] Hardware and software used

[0167] Hardware: Servers, user devices (PCs, smartphones, etc.), consultant devices

[0168] Software: Databases (e.g., MySQL), external APIs, data preprocessing libraries (e.g., Pandas, SciPy), generative AI models (e.g., GPT-3), cloud storage (e.g., AWS, Google Cloud)

[0169] Specific examples

[0170] For example, if a company sends a request to "suggest the timing of the next sale based on customer behavior data and sales data," the process would go something like this:

[0171] 1. User Input: The user enters their "next sale timing suggestion" into a web form.

[0172] 2. Data collection: The server collects customer behavior data and sales data from the virtual store's database and external APIs.

[0173] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0174] 4. Proposal Generation: The generative AI model analyzes the data and generates a suggestion such as "the next sale should be held in the third week."

[0175] 5. Review: The consultant reviews the proposal and makes any necessary revisions.

[0176] 6. Feedback: Send the final proposal to the user, providing specific implementation steps and recommended actions.

[0177] Example prompt sentence:

[0178] "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0179] This allows users to receive personalized marketing strategy suggestions quickly and accurately.

[0180] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0181] Step 1: User Input

[0182] A user inputs a consulting request through a web form or mobile application. For example, they might input, "Please let me know when the sale will be this month." This input triggers the system. The input information is sent to the server, and the system proceeds to the next processing step.

[0183] Input: A consulting request entered by the user (e.g., "Please let me know when the sale will be this month.")

[0184] Output: The request sent to the server

[0185] Specific behavior:

[0186] The user enters the request details into the form and presses the send button.

[0187] This information is sent to the server via the HTTPS protocol.

[0188] Step 2: Data collection

[0189] The server collects relevant data based on the request received from the user. Specifically, it retrieves customer behavior data (e.g., clickstream data) and sales data within the virtual store from an internal database or external API. This data is then passed on to the next pre-processing step.

[0190] Input: User requests, access to internal databases and external APIs

[0191] Output: Collected customer behavior and sales data

[0192] Specific behavior:

[0193] The server executes database queries to obtain internal customer behavior and sales data.

[0194] Call an external API to retrieve additional data.

[0195] Step 3: Preprocessing

[0196] The server performs preprocessing on the collected data, such as filling in missing data, removing noise, and normalizing the data to generate preprocessed data, which is then converted into a format that is easier to analyze.

[0197] Input: Collected raw data (customer behavior data and sales data)

[0198] Output: Preprocessed data

[0199] Specific behavior:

[0200] The server cleans the data using Python libraries such as Pandas and SciPy.

[0201] Impute missing values ​​and remove outliers.

[0202] Normalize the data and convert it into a suitable format for analysis.

[0203] Step 4: Proposal generation by generative AI

[0204] Using the preprocessed data, the server uses a generative AI model (e.g., GPT-3) to generate suggestions, which may include specific details such as "Hold a sale in the third week of this month."

[0205] Input: Preprocessed data

[0206] Output: Generated proposals

[0207] Specific behavior:

[0208] The server inputs a prompt sentence into the generative AI model and generates a suggestion.

[0209] Example prompt: "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0210] Step 5: Consultant review and follow-up

[0211] The generated proposal is sent to the consultant's terminal, where the consultant reviews the proposal and makes any necessary corrections. After the consultant has confirmed and corrected the proposal, the final proposal is decided.

[0212] Input: Generated proposals

[0213] Output: Reviewed and revised final proposal

[0214] Specific behavior:

[0215] The server transmits the generated proposal to the consultant terminal.

[0216] The consultant reviews the proposal and enters any corrections into the system.

[0217] Step 6: Feedback

[0218] A final recommendation is provided to the user, such as "We're running a sale in the third week of this month, focusing on specific products."

[0219] Input: Reviewed and revised final proposal

[0220] Output: Feedback to the user

[0221] Specific behavior:

[0222] The server sends the final proposal to the user's terminal.

[0223] The user reviews the suggestions and decides on their next action.

[0224] The above processing flow enables the user to receive personalized marketing strategy proposals quickly and accurately.

[0225] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0226] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user, and further includes an emotion engine that recognizes the user's emotions.

[0227] Specific explanation of the system's operation

[0228] User Input

[0229] A user uses a web form or application to input the details of a consulting request. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[0230] emotion recognition

[0231] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[0232] Data collection and preprocessing

[0233] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0234] Proposal generation by generative AI

[0235] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[0236] Consultant review and follow-up

[0237] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0238] Specific examples

[0239] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[0240] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[0241] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[0242] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[0243] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0244] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[0245] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0246] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[0247] This invention enables generative AI to automate much of the consulting work, providing efficient and cost-effective services. Furthermore, the introduction of an emotion engine enables flexible responses according to the user's emotional state, which is expected to improve user satisfaction.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] The user inputs a consulting request. The user uses a web form or application to input information such as "I would like to improve my marketing strategy through customer data analysis." The input information is sent to the server by the terminal.

[0251] Step 2:

[0252] The server processes the input received from the user. The server then launches the data collection mechanism and executes scripts to collect relevant data based on the user input. The data source can be an internal database or an external API.

[0253] Step 3:

[0254] The server launches an emotion engine to analyze the user's input. The emotion engine uses text and voice analysis techniques to determine the user's emotional state (e.g., stress, anxiety, satisfaction, etc.).

[0255] Step 4:

[0256] The server preprocesses the collected data. Preprocessing includes data cleaning (filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[0257] Step 5:

[0258] The server stores the preprocessed data in the data storage means, and the stored data is used for analysis by the generating means.

[0259] Step 6:

[0260] The server launches the generative AI engine and provides the saved preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate specific suggestions that meet the user's needs. At this time, the user's emotional state, obtained from the emotion engine, is also reflected in the suggestion content and tone.

[0261] Step 7:

[0262] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[0263] Step 8:

[0264] The terminal displays the proposal to the consultant, who reviews it and makes any necessary corrections. The revised proposal is then sent back to the server.

[0265] Step 9:

[0266] The server then provides the user with a final, revised proposal, which includes specific steps to implement and a recommended action plan, taking into account the user's emotional state.

[0267] Step 10:

[0268] The user receives the final proposal and implements any actionable advice or instructions. If the user provides additional feedback, the cycle begins again, continually improving the quality of the consulting service.

[0269] Example 2

[0270] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0271] Conventional consulting systems have had difficulty generating proposals that take users' emotions into account, making it difficult to provide effective support that increases user satisfaction. Additionally, data preprocessing takes time, making it difficult to respond in real time.

[0272] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for the user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to the consultant terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, and an emotion engine means for recognizing the user's emotions. This makes it possible to quickly generate a proposal that takes the user's emotions into consideration and provide effective support to improve user satisfaction.

[0273] "User" means an individual or corporation that utilizes the system to input a consulting request and seek a solution.

[0274] The "input means" is an interface used by a user to input a consulting request, and may take the form of a web form, an application, or the like.

[0275] "Data collection means" has the function of collecting necessary data from an internal database or external API based on the input information.

[0276] The "preprocessing means" has the function of complementing missing values ​​and removing noise from the collected data, and shaping it into a format suitable for analysis.

[0277] "Data storage means" means a means that has a storage function for efficiently storing and managing preprocessed data, and includes cloud storage.

[0278] The "generation means" has a function of generating specific proposals based on the preprocessed data in accordance with the user's needs.

[0279] The "transmitting means" has a communication function for transmitting the generated proposal to the consultant terminal.

[0280] "Review tools" are functions that allow consultants to check the content of proposals and make necessary corrections, and may use artificial intelligence technology.

[0281] The "feedback means" has the function of returning the final proposal to the user and providing implementation procedures and recommended actions.

[0282] The "emotion engine means" has a function for analyzing emotions from the user's input data and generating a response according to the user's emotional state.

[0283] The present invention is a system that allows users to input a consulting request and generates optimal proposals based on the request. This system also includes an emotion engine that recognizes the user's emotions in real time, improving the user experience.

[0284] Hardware and software used

[0285] The main components of this system are the server, the terminal, and the user, and have the following specific functions:

[0286] Server: Performs data collection, pre-processing, proposal generation, emotion recognition, and proposal transmission. Software used includes natural language processing technology, voice analysis technology, machine learning algorithms, cloud storage, etc.

[0287] Terminal: A review terminal for the consultant, which serves as an interface for the consultant to review and modify the proposal.

[0288] User: A person requesting a consulting business and entering the details of their request via a web form or application.

[0289] Specific circumstances of data processing and calculation

[0290] User Input

[0291] A user enters a consulting request using a web form or application. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[0292] emotion recognition

[0293] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[0294] Data collection and preprocessing

[0295] The server receives user input and collects the necessary data based on it. The data source is mainly an internal database or an external API. The collected data undergoes preprocessing, such as processing missing values ​​and removing noise data, and is then stored in a database. This allows the data to be formatted so that it can be easily analyzed by the generating means.

[0296] Proposal generation by generative AI

[0297] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[0298] Consultant review and follow-up

[0299] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0300] Specific examples

[0301] For example, if a company submits a request to "improve marketing strategies through analysis of customer data," the system operates as follows:

[0302] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[0303] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[0304] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[0305] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0306] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[0307] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0308] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[0309] Prompt Sentence Examples

[0310] An example of a prompt to use for system input is:

[0311] 1. "The user requests improvement of their marketing strategy through analysis of customer data. Generate suggestions based on the collected data and the user's emotional state."

[0312] 2. "The user is feeling anxious. Generate support-focused marketing strategy suggestions that take this emotional state into account."

[0313] By combining generative AI technology with an emotion engine, the system of the present invention makes it possible to provide users with advanced and detailed consulting services.

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Step 1:

[0316] User Input

[0317] A user enters a specific consulting request using a web form or application. For example, the user enters a request such as "I would like to improve my marketing strategy through customer data analysis," and presses the submit button. At this time, the entered text data is sent to the server along with voice data and other contextual information.

[0318] Input: Text data: "I want to improve my marketing strategy through customer data analysis."

[0319] Output: User's consulting request data

[0320] Step 2:

[0321] emotion recognition

[0322] The server analyzes the received user input data and activates an emotion engine. The emotion engine uses natural language processing and speech analysis technologies to evaluate the input text data and voice data and determine the user's emotional state. For example, it can extract an emotional state such as "the user is feeling anxious" from the input text.

[0323] Input: User's consulting request text and voice data

[0324] Output: User's emotional state (e.g., anxiety)

[0325] Step 3:

[0326] Data collection

[0327] The server collects relevant data based on the user's input data and emotional state. This data is mainly obtained from internal databases and external APIs and is included in the required dataset. The data collection takes into account the user's consultation request.

[0328] Input: User's consulting request data and emotional state

[0329] Output: Collected related dataset

[0330] Step 4:

[0331] Data Preprocessing

[0332] The server performs preprocessing on the collected data, including missing value imputation, noise removal, and data shaping and normalization. The preprocessed data is stored in a database and prepared for the generative AI engine to generate suggestions.

[0333] Input: Collected relevant datasets

[0334] Output: Preprocessed data

[0335] Step 5:

[0336] Proposal generation by generative AI

[0337] The server inputs the preprocessed data into a generative AI engine, which generates proposals based on the user's request. The generative AI engine uses machine learning algorithms and natural language processing technology to create specific proposals. At this time, the user's emotional state obtained from the emotion engine is also reflected, resulting in more personalized proposals.

[0338] Input: Preprocessed data and user's emotional state

[0339] Output: Generated concrete consulting proposals

[0340] Step 6:

[0341] Submit a proposal

[0342] The server sends the proposal created by the generative AI engine to the consultant's device, where the proposal is encoded and sent via HTTP or other communication protocol.

[0343] Input: Generated specific consulting proposal

[0344] Output: Proposal data to consultant's terminal

[0345] Step 7:

[0346] Consultant Review

[0347] The terminal (consultant) checks the received proposal and makes corrections as necessary. The consultant checks the appropriateness and details of the proposal and improves the quality of the proposal by correcting any insufficiencies or errors. The corrected proposal is then sent back to the server.

[0348] Input: Proposal data displayed on the consultant's terminal

[0349] Output: Final revised proposal data

[0350] Step 8:

[0351] feedback

[0352] The server receives revised proposals from the consultant and provides the final proposal as feedback to the user, typically via the user's email address or application notification. The proposal includes specific implementation steps and a recommended action plan.

[0353] Input: Revised final proposal data

[0354] Output: Final proposal feedback to the user

[0355] (Application example 2)

[0356] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0357] Conventional consulting systems were unable to automatically generate proposals based on user-entered requests, and also had difficulty responding to requests that took the user's emotional state into account. Furthermore, while it is important for brick-and-mortar stores to recognize customers' emotions in real time and adjust proposals based on that information, there was a lack of efficient ways to do this. This resulted in lower customer satisfaction and the inability to provide effective proposals.

[0358] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0359] In this invention, the server includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a review terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, an emotion analysis means for recognizing the user's emotion, a proposal adjustment means for adjusting the proposal content based on the emotion analysis means, and an input assistance means for inputting the user's request into smart glasses or a smartphone. This enables flexible responses according to the user's emotional state and real-time customer service in a physical store.

[0360] The "input means for a user to input a consulting request" refers to a means for a user to input a consulting request using a device such as smart glasses or a smartphone.

[0361] The "data collection means for collecting related data based on input information" is a means for automatically collecting necessary related data based on information input by the user.

[0362] The "preprocessing means for preprocessing collected data" refers to a means for removing noise data from collected data, complementing missing values, and converting the data into a format suitable for analysis.

[0363] The "data storage means for storing the preprocessed data" refers to a means for safely and efficiently storing the preprocessed data, and cloud storage may be used.

[0364] The "means for generating a proposal using preprocessed data" refers to a means for generating a proposal suited to a user request based on the preprocessed data.

[0365] The "transmission means for transmitting the generated proposal to the review terminal" is a means for transmitting the generated proposal to a terminal where the consultant can review it.

[0366] The "review means for the consultant to review and modify the proposal content" refers to a means for the consultant to evaluate the generated proposal and modify it as necessary.

[0367] The "feedback means for feeding back the final proposal to the user" is a means for feeding back the final proposal after correction to the user.

[0368] The "emotion analysis means for recognizing the user's emotions" is a means for analyzing emotions from the user's voice or text input and recognizing the user's emotional state, such as stress or satisfaction.

[0369] The "proposal adjustment means for adjusting the proposal content based on the emotion analysis means" is a means for adjusting the proposal content and its tone based on the emotion information obtained from the emotion analysis means.

[0370] The "input assistance means for inputting a user's request into smart glasses or a smartphone" is a means for a user to input a request in real time using smart glasses or a smartphone.

[0371] The present invention is a system for improving the efficiency of customer service in brick-and-mortar stores and enhancing customer satisfaction. This system involves a series of processes in which a user inputs a consulting request using smart glasses or a smartphone, automatically generates a proposal based on the request, and finally provides feedback. The components of the system are as follows:

[0372] Program processing and the hardware and software used

[0373] 1. Input method: The user inputs a consulting request using smart glasses or a smartphone. For example, a customer in a physical store inputs a request such as "I'm looking for a suitable gift item for a wedding." This is done using the touch input or voice input functions of the smart glasses or smartphone.

[0374] 2. Emotion analysis: The server analyzes emotions from user input and voice data. Using the Emotion Engine, it recognizes the customer's emotional state in real time. The results of this analysis are used to determine whether or not support is required.

[0375] 3. Data collection method: The server automatically collects relevant data based on the user's input. The data source is mainly internal databases and external APIs. The data collection here uses the Python requests library.

[0376] 4. Preprocessing: The collected data is not suitable for analysis as it is, so it is preprocessed. This preprocessing includes filling in missing values ​​and removing noise data. For example, data cleaning and standardization of format are performed.

[0377] 5. Proposal generation method: Using the preprocessed data, the generative AI model creates specific proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate proposals that best fit the user's request. The proposal content is also adjusted taking into account the results of sentiment analysis.

[0378] 6. Transmission method: The generated proposal is sent to a device (smart glasses or smartphone) where the consultant can review it. This allows the consultant to check and modify the proposal in real time.

[0379] 7. Review method: The consultant's terminal reviews the proposal and makes any necessary corrections. The proposal may also be evaluated using artificial intelligence technology. At this stage, unnecessary information is removed and important information is added.

[0380] 8. Feedback: The final revised proposal is fed back to the user. This feedback includes implementation procedures and recommended action plans. For example, specific product names and purchasing instructions for "gift items the customer is looking for" are provided.

[0381] Examples of specific examples and prompts

[0382] For example, if a customer requests "I'm looking for a gift item suitable for a wedding" in a physical store and is a little nervous,

[0383] Example prompt sentence:

[0384] The request states, "I'm looking for a gift item suitable for a wedding." At this point, the customer is a little nervous.

[0385] Prompt for generative AI model:

[0386] A request is received saying, "I'm looking for a suitable gift item for a wedding." The customer is in a tense emotional state and is seeking suggestions that emphasize reassuring support.

[0387] This system enables flexible responses based on the user's emotional state and real-time customer support in physical stores, which is expected to improve customer satisfaction.

[0388] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0389] Step 1:

[0390] The user inputs a consulting request using smart glasses or a smartphone. The user enters the request details into an input form within the application, and can also input by voice. For example, the user might input, "I'm looking for a suitable gift item for a wedding." The input data is sent to the server.

[0391] Step 2:

[0392] The server analyzes the received user input data. Using the Emotion Engine, it recognizes the user's emotional state from the input text and voice data. The user's request data is used as input, and the user's emotional state is obtained as output. Specifically, it determines in real time whether the user is nervous or satisfied.

[0393] Step 3:

[0394] The server collects relevant data based on the sentiment analysis results and input data. It uses the Python requests library to automatically retrieve the necessary data from an internal database or external API. The input is the user's request and emotional state, and the output is the retrieved relevant data. For example, it can collect gift item candidates and rating data.

[0395] Step 4:

[0396] The collected data is preprocessed by the server. The preprocessing means complements missing values ​​and removes noise data from the collected data, and converts it into a format suitable for analysis. The collected data is used as input, and preprocessed data is obtained as output. Specific examples include removing duplicate data and standardizing formats.

[0397] Step 5:

[0398] The server uses the preprocessed data to generate a generative AI model to generate suggestions based on the user's request. The suggestion generator uses machine learning algorithms and natural language processing techniques to create appropriate suggestions. The preprocessed data and the results of the sentiment analysis are used as input, and the suggestion content is obtained as output. For example, a list of recommended gift items for a specific gift is generated. The prompt includes the request "I'm looking for gift items suitable for a wedding" and the user's emotional state.

[0399] Step 6:

[0400] The generated proposal is sent by the server to the review device. The consultant checks the proposal using smart glasses or a smartphone, and reviews and modifies it as necessary. The generated proposal is used as input, and a modified proposal is obtained as output. Specifically, the consultant checks the content of the proposal and adds points to be emphasized or supplementary information.

[0401] Step 7:

[0402] The final proposal is fed back to the user by the server. A feedback means provides the user with a revised proposal, including implementation steps and a recommended action plan. The revised proposal is used as input, and feedback is provided to the user as output. Specific feedback may include specific products and purchasing steps for "ideal wedding gift items."

[0403] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0404] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0405] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0406] [Second embodiment]

[0407] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0408] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0409] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0410] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0411] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0413] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0414] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0415] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0416] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0417] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0418] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0419] The present invention is a system that includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user.

[0420] Specific explanation of the system's operation

[0421] User Input

[0422] A user uses a web form or application to input the details of a consulting request. For example, the user inputs a request such as "I would like to improve my marketing strategy through the analysis of customer data."

[0423] Data collection and preprocessing

[0424] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0425] Proposal generation by generative AI

[0426] The server inputs the stored preprocessed data into a generative AI engine to generate proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific proposals that meet the user's requests. For example, it generates a proposal such as "Identify target segments and conduct social media campaigns."

[0427] Consultant review and follow-up

[0428] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0429] Specific examples

[0430] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[0431] 1. User Input: A user fills out a web form with "Improve marketing strategies through customer data analysis."

[0432] 2. Data collection: The server collects relevant data from internal databases and external APIs.

[0433] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0434] 4. Proposal Generation: The generative AI engine analyzes the data and proposes "identifying target segments and implementing social media campaigns."

[0435] 5. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0436] 6. Feedback: Send the final proposal to the user and provide implementation instructions or recommended actions.

[0437] This invention enables generative AI to automate many consulting tasks, providing efficient and cost-effective services. Users can receive high-quality consulting services quickly, and can meet a variety of needs, such as promoting digital transformation and strengthening risk management.

[0438] The processing flow will be explained below.

[0439] Step 1:

[0440] The user enters the project outline and required consulting details into the input form. The entered information is sent to the server by the terminal.

[0441] Step 2:

[0442] The server processes the input information received from the user and initiates data collection methods to collect relevant data, which may include retrieving the required data from internal databases or external APIs.

[0443] Step 3:

[0444] The server preprocesses the collected data. Preprocessing includes data cleaning (for example, filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[0445] Step 4:

[0446] The server stores the preprocessed data in a data storage means, and the stored data is used for analysis by the generative AI engine.

[0447] Step 5:

[0448] The server launches a generative AI engine, which provides the stored preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate suggestions based on the user's requests.

[0449] Step 6:

[0450] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[0451] Step 7:

[0452] The terminal displays the proposal to the consultant, who reviews it and makes any necessary revisions.

[0453] Step 8:

[0454] The terminal sends the final proposal to the server, which then sends the revised final proposal to the user as feedback.

[0455] Step 9:

[0456] The user receives the final proposal and implements any actionable advice or instructions. If there is additional feedback from the user, the cycle begins again.

[0457] Example 1

[0458] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0459] In traditional consulting work, users manually input the details of requests, and the subsequent data collection, proposal generation, review, and feedback required a great deal of time and cost. In addition, due to a lack of automated processes, many aspects of the work depended on specific know-how and experience, and there was a need to improve efficiency.

[0460] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0461] In this invention, the server includes input means for a user to input a consulting request, data collection means for collecting related data based on the input information, preprocessing means for preprocessing the collected data, data storage means for storing the preprocessed data, generation means for a generative AI model to generate a proposal based on the preprocessed data, transmission means for transmitting the generated proposal to a consultant terminal, review means for the consultant to review and modify the proposal content, feedback means for feeding back the final proposal to the user, input means for inputting data to the generative AI model using a prompt sentence, and display means for the consultant to check and modify the proposal content on his terminal. This automates and streamlines the entire process in consulting work, from data collection to proposal generation, review, and feedback, enabling significant reductions in time and cost.

[0462] "User" refers to an individual or company that uses the system to input a consulting request.

[0463] "Input means" refers to an interface or device that allows a user to input the content of a consulting request.

[0464] "Data Collection Measures" refers to software or systems for collecting relevant data based on input information.

[0465] "Preprocessing means" refers to software or a system for processing collected data to convert it into a format suitable for analysis and for removing noise data.

[0466] "Data storage means" refers to a database or cloud storage for storing preprocessed data.

[0467] "Generator" means a generative artificial intelligence model and associated software for generating recommendations using the pre-processed data.

[0468] "Transmission means" refers to communication means for transmitting the generated proposal to the consultant terminal.

[0469] "Review Tool" means a specialized interface or software that allows a Consultant to review and modify the Proposal.

[0470] "Feedback means" refers to a means for providing feedback on the final proposal to the user.

[0471] A "generative artificial intelligence model" refers to a system that uses machine learning algorithms and natural language processing technology to automatically generate suggestions based on input data.

[0472] A "prompt" refers to a text-based instruction or question that is input to a generative artificial intelligence model.

[0473] "Terminal" refers to the device used by the consultant to review and revise the proposal.

[0474] "Display means" refers to the display or user interface that allows the consultant to check and modify the proposal content on a terminal.

[0475] A specific embodiment of the present invention will be described below. This system automates a series of processes: a user inputs a consulting request, collects and preprocesses data based on the request, generates a proposal using a generative AI model, and then a consultant reviews and modifies the final proposal, providing the final proposal as feedback to the user.

[0476] Specific configuration and operation

[0477] User Input

[0478] The user enters the details of the consulting request through a web form or application. This input method is provided, for example, as a form that runs on a web browser or a mobile application. The user enters specific details of the request into the form, such as "I would like to improve my marketing strategy through the analysis of customer data," and clicks the submit button.

[0479] Data collection and preprocessing

[0480] The server receives input from the user and collects relevant data based on that input, either from an internal database (MySQL or PostgreSQL) or an external API (Google Analytics API, Twitter API, etc.) The server communicates with these databases and APIs to retrieve data relevant to the user's request.

[0481] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes unnecessary noise data, and converts the data format (for example, converting it to a CSV file or data frame). This prepares the data in a format suitable for analysis. The preprocessed data is then stored in a database or cloud storage, which is used as a data storage method.

[0482] Proposal generation

[0483] The server inputs the preprocessed data into a generative AI engine, which uses OpenAI GPT-3 or similar natural language processing technology. This AI engine uses machine learning algorithms to generate specific suggestions that address the user's request. For example, a suggestion might be, "Identify target segments and run social media campaigns."

[0484] Examples of prompts used to generate suggestions are:

[0485] "The user wants to improve their marketing strategy by analyzing customer data. The relevant data has been collected and preprocessed. Based on this, you would like to generate specific recommendations for the user."

[0486] Consultant review and feedback

[0487] The generated proposal is sent from the server to the consultant's terminal. The consultant can check the proposal contents by displaying them on a dedicated interface and make corrections if necessary. This display means is designed to make it easy for the consultant to check the proposal contents.

[0488] After the consultant makes any necessary corrections, the final proposal is finalized. This final proposal is then sent back to the user via the server as a means of feedback. The user can then receive the feedback and confirm specific implementation steps and recommended action plans.

[0489] This system enables faster, higher-quality consulting services than traditional manual processes. By combining generative AI with data pre-processing and consultant review, we can deliver efficient and cost-effective services.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Step 1:

[0492] User Input

[0493] The user enters the details of the consulting request through a web form or application. Specifically, the user enters a request such as "I would like to improve my marketing strategy through the analysis of customer data" and clicks the "Submit" button. This input is sent to the server and used to collect data for the next step.

[0494] Input: User's request (e.g., "I want to improve my marketing strategy through customer data analysis.")

[0495] Output: The request sent to the server

[0496] Step 2:

[0497] Data collection

[0498] The server collects relevant data based on the request received from the user. Specifically, it obtains the necessary data using an internal database (e.g., MySQL, PostgreSQL) or an external API (e.g., Google Analytics API, Twitter API). The server temporarily stores the obtained data and passes it to the next preprocessing step.

[0499] Input: User's request

[0500] Output: Relevant data collected

[0501] Step 3:

[0502] Data Preprocessing

[0503] The server performs preprocessing on the collected data. Specifically, it performs data cleaning, including filling in missing values ​​and removing noise data, and converts the data into a format suitable for analysis (e.g., CSV file, data frame). After preprocessing, the data is stored in a database.

[0504] Input: Relevant data collected

[0505] Output: Preprocessed data

[0506] Step 4:

[0507] Proposal generation

[0508] The server inputs the preprocessed data into a generative AI engine (e.g., OpenAI GPT-3), which uses the prompt to generate specific suggestions based on the user's request. For example, a suggestion might be "Identify target segments and conduct social media campaigns."

[0509] Input: Preprocessed data, prompt (e.g., "The user requests that we improve our marketing strategy through the analysis of customer data. The relevant data has been collected and preprocessed. Based on this, please generate specific suggestions for the user.")

[0510] Output: Generated proposals

[0511] Step 5:

[0512] Proposal Review

[0513] The generated proposal is sent from the server to the terminal (consultant device). The consultant reviews the content and makes any necessary corrections. The reviewed proposal is then sent to the server as the final proposal.

[0514] Input: Generated proposals

[0515] Output: Reviewed final proposal

[0516] Step 6:

[0517] feedback

[0518] The server then sends the final proposal, reviewed and revised by the consultant, back to the user. Specifically, it sends the final proposal to the user's email address or a dedicated user interface. The user receives the feedback and checks specific implementation steps and recommended action plans.

[0519] Input: Reviewed final proposal

[0520] Output: Final proposals fed back to the user

[0521] (Application example 1)

[0522] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0523] Conventional consulting systems have difficulty efficiently processing consulting requests from users, and in particular, they have not adequately proposed personalized marketing strategies that utilize customer behavior data and sales data in virtual stores. This poses a challenge, making it difficult to maximize customer engagement and sales opportunities.

[0524] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0525] In this invention, the server includes an input means for users to input consulting requests, a data collection means for collecting related data based on the input information, and a preprocessing means for preprocessing the collected data. This allows for efficient collection and processing of data based on user requests, automatic proposal of personalized marketing strategies using a generative AI model, and the proposals can be reviewed and revised by consultants to reflect them in the final proposal. Furthermore, by adding functions for collecting and preprocessing customer behavior data and sales data within the virtual store, it is possible to provide users with more accurate personalized marketing strategies.

[0526] "User" refers to an individual or organization that submits a consulting request.

[0527] "Input means" refers to a mechanism or device that provides an interface for users to input consulting requests into the system.

[0528] "Data collection means" refers to a mechanism for collecting related data based on information input by a user.

[0529] "Pre-processing means" refers to a mechanism that processes collected data to convert it into a format suitable for analysis and generation of proposals by a generative AI model.

[0530] "Data storage means" refers to a mechanism for storing preprocessed data.

[0531] "Generative means" refers to the generative AI model or algorithm that uses pre-processed data to generate recommendations.

[0532] The "transmission means" refers to a mechanism for transmitting the generated proposal to the consultant terminal.

[0533] "Review procedures" refer to the mechanisms by which consultants review proposals and make corrections as necessary.

[0534] "Feedback means" refers to a mechanism for feeding back the final proposal to the user.

[0535] "Additional data collection means" refers to a mechanism for collecting customer behavior data and sales data within the virtual store.

[0536] "Additional pre-processing means" refers to a mechanism for pre-processing customer behavior data and sales data and converting them into a format for use in analysis.

[0537] "Generative AI model" refers to a model that uses machine learning algorithms and natural language processing techniques to generate suggestions.

[0538] "Strategy generation means" refers to a mechanism that uses a generative AI model to generate personalized marketing strategies for virtual stores.

[0539] The "strategy feedback means" refers to a mechanism for providing the generated marketing strategy to the user and providing feedback including implementation procedures and recommended actions.

[0540] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the proposal content, and a feedback means for feeding back the final proposal to the user.The system also includes an additional data collection means for collecting customer behavior data and sales data in a virtual store, an additional preprocessing means for preprocessing the customer behavior data and sales data and using it for analysis, a strategy generation means for generating a personalized marketing strategy using a generative AI model, and a strategy feedback means for providing the generated strategy to the user.

[0541] Program operation explanation

[0542] 1. User Input: A user enters a consulting request within a virtual store through a web form or mobile application. For example, a user might say, "Please tell me when there will be sales this month."

[0543] 2. Data collection: The server receives the input information and collects relevant data. The main data sources are customer behavior data (e.g., clickstream data) and sales data within the virtual store. These are obtained from internal databases and external APIs.

[0544] 3. Preprocessing: The server performs preprocessing on the collected data, such as filling in missing data and removing noise data, to generate preprocessed data.

[0545] 4. Proposal generation using generative AI: Using the preprocessed data, a generative AI model (e.g., GPT-3) is used to generate proposals. For example, a specific proposal such as "Hold a sale in the third week of this month" is generated.

[0546] 5. Review and follow-up by consultant: The proposal will be sent to the consultant's terminal, where the consultant will review the proposal and make any necessary corrections.

[0547] 6. Feedback: A final suggestion is given to the user, for example, "We'll have a sale in the third week of this month, and we'll focus on specific products."

[0548] Hardware and software used

[0549] Hardware: Servers, user devices (PCs, smartphones, etc.), consultant devices

[0550] Software: Databases (e.g., MySQL), external APIs, data preprocessing libraries (e.g., Pandas, SciPy), generative AI models (e.g., GPT-3), cloud storage (e.g., AWS, Google Cloud)

[0551] Specific examples

[0552] For example, if a company sends a request to "suggest the timing of the next sale based on customer behavior data and sales data," the process would go something like this:

[0553] 1. User Input: The user enters their "next sale timing suggestion" into a web form.

[0554] 2. Data collection: The server collects customer behavior data and sales data from the virtual store's database and external APIs.

[0555] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0556] 4. Proposal Generation: The generative AI model analyzes the data and generates a suggestion such as "the next sale should be held in the third week."

[0557] 5. Review: The consultant reviews the proposal and makes any necessary revisions.

[0558] 6. Feedback: Send the final proposal to the user, providing specific implementation steps and recommended actions.

[0559] Example prompt sentence:

[0560] "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0561] This allows users to receive personalized marketing strategy suggestions quickly and accurately.

[0562] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0563] Step 1: User Input

[0564] A user inputs a consulting request through a web form or mobile application. For example, they might input, "Please let me know when the sale will be this month." This input triggers the system. The input information is sent to the server, and the system proceeds to the next processing step.

[0565] Input: A consulting request entered by the user (e.g., "Please let me know when the sale will be this month.")

[0566] Output: The request sent to the server

[0567] Specific behavior:

[0568] The user enters the request details into the form and presses the send button.

[0569] This information is sent to the server via the HTTPS protocol.

[0570] Step 2: Data collection

[0571] The server collects relevant data based on the request received from the user. Specifically, it retrieves customer behavior data (e.g., clickstream data) and sales data within the virtual store from an internal database or external API. This data is then passed on to the next pre-processing step.

[0572] Input: User requests, access to internal databases and external APIs

[0573] Output: Collected customer behavior and sales data

[0574] Specific behavior:

[0575] The server executes database queries to obtain internal customer behavior and sales data.

[0576] Call an external API to retrieve additional data.

[0577] Step 3: Preprocessing

[0578] The server performs preprocessing on the collected data, such as filling in missing data, removing noise, and normalizing the data to generate preprocessed data, which is then converted into a format that is easier to analyze.

[0579] Input: Collected raw data (customer behavior data and sales data)

[0580] Output: Preprocessed data

[0581] Specific behavior:

[0582] The server cleans the data using Python libraries such as Pandas and SciPy.

[0583] Impute missing values ​​and remove outliers.

[0584] Normalize the data and convert it into a suitable format for analysis.

[0585] Step 4: Proposal generation by generative AI

[0586] Using the preprocessed data, the server uses a generative AI model (e.g., GPT-3) to generate suggestions, which may include specific details such as "Hold a sale in the third week of this month."

[0587] Input: Preprocessed data

[0588] Output: Generated proposals

[0589] Specific behavior:

[0590] The server inputs a prompt sentence into the generative AI model and generates a suggestion.

[0591] Example prompt: "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0592] Step 5: Consultant review and follow-up

[0593] The generated proposal is sent to the consultant's terminal, where the consultant reviews the proposal and makes any necessary corrections. After the consultant has confirmed and corrected the proposal, the final proposal is decided.

[0594] Input: Generated proposals

[0595] Output: Reviewed and revised final proposal

[0596] Specific behavior:

[0597] The server transmits the generated proposal to the consultant terminal.

[0598] The consultant reviews the proposal and enters any corrections into the system.

[0599] Step 6: Feedback

[0600] A final recommendation is provided to the user, such as "We're running a sale in the third week of this month, focusing on specific products."

[0601] Input: Reviewed and revised final proposal

[0602] Output: Feedback to the user

[0603] Specific behavior:

[0604] The server sends the final proposal to the user's terminal.

[0605] The user reviews the suggestions and decides on their next action.

[0606] The above processing flow enables the user to receive personalized marketing strategy proposals quickly and accurately.

[0607] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0608] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user, and further includes an emotion engine that recognizes the user's emotions.

[0609] Specific explanation of the system's operation

[0610] User Input

[0611] A user uses a web form or application to input the details of a consulting request. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[0612] emotion recognition

[0613] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[0614] Data collection and preprocessing

[0615] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0616] Proposal generation by generative AI

[0617] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[0618] Consultant review and follow-up

[0619] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0620] Specific examples

[0621] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[0622] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[0623] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[0624] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[0625] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0626] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[0627] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0628] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[0629] This invention enables generative AI to automate much of the consulting work, providing efficient and cost-effective services. Furthermore, the introduction of an emotion engine enables flexible responses according to the user's emotional state, which is expected to improve user satisfaction.

[0630] The processing flow will be explained below.

[0631] Step 1:

[0632] The user inputs a consulting request. The user uses a web form or application to input information such as "I would like to improve my marketing strategy through customer data analysis." The input information is sent to the server by the terminal.

[0633] Step 2:

[0634] The server processes the input received from the user. The server then launches the data collection mechanism and executes scripts to collect relevant data based on the user input. The data source can be an internal database or an external API.

[0635] Step 3:

[0636] The server launches an emotion engine to analyze the user's input. The emotion engine uses text and voice analysis techniques to determine the user's emotional state (e.g., stress, anxiety, satisfaction, etc.).

[0637] Step 4:

[0638] The server preprocesses the collected data. Preprocessing includes data cleaning (filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[0639] Step 5:

[0640] The server stores the preprocessed data in the data storage means, and the stored data is used for analysis by the generating means.

[0641] Step 6:

[0642] The server launches the generative AI engine and provides the saved preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate specific suggestions that meet the user's needs. At this time, the user's emotional state, obtained from the emotion engine, is also reflected in the suggestion content and tone.

[0643] Step 7:

[0644] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[0645] Step 8:

[0646] The terminal displays the proposal to the consultant, who reviews it and makes any necessary corrections. The revised proposal is then sent back to the server.

[0647] Step 9:

[0648] The server then provides the user with a final, revised proposal, which includes specific steps to implement and a recommended action plan, taking into account the user's emotional state.

[0649] Step 10:

[0650] The user receives the final proposal and implements any actionable advice or instructions. If the user provides additional feedback, the cycle begins again, continually improving the quality of the consulting service.

[0651] Example 2

[0652] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0653] Conventional consulting systems have had difficulty generating proposals that take users' emotions into account, making it difficult to provide effective support that increases user satisfaction. Additionally, data preprocessing takes time, making it difficult to respond in real time.

[0654] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for the user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to the consultant terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, and an emotion engine means for recognizing the user's emotions. This makes it possible to quickly generate a proposal that takes the user's emotions into consideration and provide effective support to improve user satisfaction.

[0655] "User" means an individual or corporation that utilizes the system to input a consulting request and seek a solution.

[0656] The "input means" is an interface used by a user to input a consulting request, and may take the form of a web form, an application, or the like.

[0657] "Data collection means" has the function of collecting necessary data from an internal database or external API based on the input information.

[0658] The "preprocessing means" has the function of complementing missing values ​​and removing noise from the collected data, and shaping it into a format suitable for analysis.

[0659] "Data storage means" means a means that has a storage function for efficiently storing and managing preprocessed data, and includes cloud storage.

[0660] The "generation means" has a function of generating specific proposals based on the preprocessed data in accordance with the user's needs.

[0661] The "transmitting means" has a communication function for transmitting the generated proposal to the consultant terminal.

[0662] "Review tools" are functions that allow consultants to check the content of proposals and make necessary corrections, and may use artificial intelligence technology.

[0663] The "feedback means" has the function of returning the final proposal to the user and providing implementation procedures and recommended actions.

[0664] The "emotion engine means" has a function for analyzing emotions from the user's input data and generating a response according to the user's emotional state.

[0665] The present invention is a system that allows users to input a consulting request and generates optimal proposals based on the request. This system also includes an emotion engine that recognizes the user's emotions in real time, improving the user experience.

[0666] Hardware and software used

[0667] The main components of this system are the server, the terminal, and the user, and have the following specific functions:

[0668] Server: Performs data collection, pre-processing, proposal generation, emotion recognition, and proposal transmission. Software used includes natural language processing technology, voice analysis technology, machine learning algorithms, cloud storage, etc.

[0669] Terminal: A review terminal for the consultant, which serves as an interface for the consultant to review and modify the proposal.

[0670] User: A person requesting a consulting business and entering the details of their request via a web form or application.

[0671] Specific circumstances of data processing and calculation

[0672] User Input

[0673] A user enters a consulting request using a web form or application. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[0674] emotion recognition

[0675] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[0676] Data collection and preprocessing

[0677] The server receives user input and collects the necessary data based on it. The data source is mainly an internal database or an external API. The collected data undergoes preprocessing, such as processing missing values ​​and removing noise data, and is then stored in a database. This allows the data to be formatted so that it can be easily analyzed by the generating means.

[0678] Proposal generation by generative AI

[0679] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[0680] Consultant review and follow-up

[0681] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0682] Specific examples

[0683] For example, if a company submits a request to "improve marketing strategies through analysis of customer data," the system operates as follows:

[0684] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[0685] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[0686] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[0687] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0688] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[0689] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0690] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[0691] Prompt Sentence Examples

[0692] An example of a prompt to use for system input is:

[0693] 1. "The user requests improvement of their marketing strategy through analysis of customer data. Generate suggestions based on the collected data and the user's emotional state."

[0694] 2. "The user is feeling anxious. Generate support-focused marketing strategy suggestions that take this emotional state into account."

[0695] By combining generative AI technology with an emotion engine, the system of the present invention makes it possible to provide users with advanced and detailed consulting services.

[0696] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0697] Step 1:

[0698] User Input

[0699] A user enters a specific consulting request using a web form or application. For example, the user enters a request such as "I would like to improve my marketing strategy through customer data analysis," and presses the submit button. At this time, the entered text data is sent to the server along with voice data and other contextual information.

[0700] Input: Text data: "I want to improve my marketing strategy through customer data analysis."

[0701] Output: User's consulting request data

[0702] Step 2:

[0703] emotion recognition

[0704] The server analyzes the received user input data and activates an emotion engine. The emotion engine uses natural language processing and speech analysis technologies to evaluate the input text data and voice data and determine the user's emotional state. For example, it can extract an emotional state such as "the user is feeling anxious" from the input text.

[0705] Input: User's consulting request text and voice data

[0706] Output: User's emotional state (e.g., anxiety)

[0707] Step 3:

[0708] Data collection

[0709] The server collects relevant data based on the user's input data and emotional state. This data is mainly obtained from internal databases and external APIs and is included in the required dataset. The data collection takes into account the user's consultation request.

[0710] Input: User's consulting request data and emotional state

[0711] Output: Collected related dataset

[0712] Step 4:

[0713] Data Preprocessing

[0714] The server performs preprocessing on the collected data, including missing value imputation, noise removal, and data shaping and normalization. The preprocessed data is stored in a database and prepared for the generative AI engine to generate suggestions.

[0715] Input: Collected relevant datasets

[0716] Output: Preprocessed data

[0717] Step 5:

[0718] Proposal generation by generative AI

[0719] The server inputs the preprocessed data into a generative AI engine, which generates proposals based on the user's request. The generative AI engine uses machine learning algorithms and natural language processing technology to create specific proposals. At this time, the user's emotional state obtained from the emotion engine is also reflected, resulting in more personalized proposals.

[0720] Input: Preprocessed data and user's emotional state

[0721] Output: Generated concrete consulting proposals

[0722] Step 6:

[0723] Submit a proposal

[0724] The server sends the proposal created by the generative AI engine to the consultant's device, where the proposal is encoded and sent via HTTP or other communication protocol.

[0725] Input: Generated specific consulting proposal

[0726] Output: Proposal data to consultant's terminal

[0727] Step 7:

[0728] Consultant Review

[0729] The terminal (consultant) checks the received proposal and makes corrections as necessary. The consultant checks the appropriateness and details of the proposal and improves the quality of the proposal by correcting any insufficiencies or errors. The corrected proposal is then sent back to the server.

[0730] Input: Proposal data displayed on the consultant's terminal

[0731] Output: Final revised proposal data

[0732] Step 8:

[0733] feedback

[0734] The server receives revised proposals from the consultant and provides the final proposal as feedback to the user, typically via the user's email address or application notification. The proposal includes specific implementation steps and a recommended action plan.

[0735] Input: Revised final proposal data

[0736] Output: Final proposal feedback to the user

[0737] (Application example 2)

[0738] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0739] Conventional consulting systems were unable to automatically generate proposals based on user-entered requests, and also had difficulty responding to requests that took the user's emotional state into account. Furthermore, while it is important for brick-and-mortar stores to recognize customers' emotions in real time and adjust proposals based on that information, there was a lack of efficient ways to do this. This resulted in lower customer satisfaction and the inability to provide effective proposals.

[0740] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0741] In this invention, the server includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a review terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, an emotion analysis means for recognizing the user's emotion, a proposal adjustment means for adjusting the proposal content based on the emotion analysis means, and an input assistance means for inputting the user's request into smart glasses or a smartphone. This enables flexible responses according to the user's emotional state and real-time customer service in a physical store.

[0742] The "input means for a user to input a consulting request" refers to a means for a user to input a consulting request using a device such as smart glasses or a smartphone.

[0743] The "data collection means for collecting related data based on input information" is a means for automatically collecting necessary related data based on information input by the user.

[0744] The "preprocessing means for preprocessing collected data" refers to a means for removing noise data from collected data, complementing missing values, and converting the data into a format suitable for analysis.

[0745] The "data storage means for storing the preprocessed data" refers to a means for safely and efficiently storing the preprocessed data, and cloud storage may be used.

[0746] The "means for generating a proposal using preprocessed data" refers to a means for generating a proposal suited to a user request based on the preprocessed data.

[0747] The "transmission means for transmitting the generated proposal to the review terminal" is a means for transmitting the generated proposal to a terminal where the consultant can review it.

[0748] The "review means for the consultant to review and modify the proposal content" refers to a means for the consultant to evaluate the generated proposal and modify it as necessary.

[0749] The "feedback means for feeding back the final proposal to the user" is a means for feeding back the final proposal after correction to the user.

[0750] The "emotion analysis means for recognizing the user's emotions" is a means for analyzing emotions from the user's voice or text input and recognizing the user's emotional state, such as stress or satisfaction.

[0751] The "proposal adjustment means for adjusting the proposal content based on the emotion analysis means" is a means for adjusting the proposal content and its tone based on the emotion information obtained from the emotion analysis means.

[0752] The "input assistance means for inputting a user's request into smart glasses or a smartphone" is a means for a user to input a request in real time using smart glasses or a smartphone.

[0753] The present invention is a system for improving the efficiency of customer service in brick-and-mortar stores and enhancing customer satisfaction. This system involves a series of processes in which a user inputs a consulting request using smart glasses or a smartphone, automatically generates a proposal based on the request, and finally provides feedback. The components of the system are as follows:

[0754] Program processing and the hardware and software used

[0755] 1. Input method: The user inputs a consulting request using smart glasses or a smartphone. For example, a customer in a physical store inputs a request such as "I'm looking for a suitable gift item for a wedding." This is done using the touch input or voice input functions of the smart glasses or smartphone.

[0756] 2. Emotion analysis: The server analyzes emotions from user input and voice data. Using the Emotion Engine, it recognizes the customer's emotional state in real time. The results of this analysis are used to determine whether or not support is required.

[0757] 3. Data collection method: The server automatically collects relevant data based on the user's input. The data source is mainly internal databases and external APIs. The data collection here uses the Python requests library.

[0758] 4. Preprocessing: The collected data is not suitable for analysis as it is, so it is preprocessed. This preprocessing includes filling in missing values ​​and removing noise data. For example, data cleaning and standardization of format are performed.

[0759] 5. Proposal generation method: Using the preprocessed data, the generative AI model creates specific proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate proposals that best fit the user's request. The proposal content is also adjusted taking into account the results of sentiment analysis.

[0760] 6. Transmission method: The generated proposal is sent to a device (smart glasses or smartphone) where the consultant can review it. This allows the consultant to check and modify the proposal in real time.

[0761] 7. Review method: The consultant's terminal reviews the proposal and makes any necessary corrections. The proposal may also be evaluated using artificial intelligence technology. At this stage, unnecessary information is removed and important information is added.

[0762] 8. Feedback: The final revised proposal is fed back to the user. This feedback includes implementation procedures and recommended action plans. For example, specific product names and purchasing instructions for "gift items the customer is looking for" are provided.

[0763] Examples of specific examples and prompts

[0764] For example, if a customer requests "I'm looking for a gift item suitable for a wedding" in a physical store and is a little nervous,

[0765] Example prompt sentence:

[0766] The request states, "I'm looking for a gift item suitable for a wedding." At this point, the customer is a little nervous.

[0767] Prompt for generative AI model:

[0768] A request is received saying, "I'm looking for a suitable gift item for a wedding." The customer is in a tense emotional state and is seeking suggestions that emphasize reassuring support.

[0769] This system enables flexible responses based on the user's emotional state and real-time customer support in physical stores, which is expected to improve customer satisfaction.

[0770] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0771] Step 1:

[0772] The user inputs a consulting request using smart glasses or a smartphone. The user enters the request details into an input form within the application, and can also input by voice. For example, the user might input, "I'm looking for a suitable gift item for a wedding." The input data is sent to the server.

[0773] Step 2:

[0774] The server analyzes the received user input data. Using the Emotion Engine, it recognizes the user's emotional state from the input text and voice data. The user's request data is used as input, and the user's emotional state is obtained as output. Specifically, it determines in real time whether the user is nervous or satisfied.

[0775] Step 3:

[0776] The server collects relevant data based on the sentiment analysis results and input data. It uses the Python requests library to automatically retrieve the necessary data from an internal database or external API. The input is the user's request and emotional state, and the output is the retrieved relevant data. For example, it can collect gift item candidates and rating data.

[0777] Step 4:

[0778] The collected data is preprocessed by the server. The preprocessing means complements missing values ​​and removes noise data from the collected data, and converts it into a format suitable for analysis. The collected data is used as input, and preprocessed data is obtained as output. Specific examples include removing duplicate data and standardizing formats.

[0779] Step 5:

[0780] The server uses the preprocessed data to generate a generative AI model to generate suggestions based on the user's request. The suggestion generator uses machine learning algorithms and natural language processing techniques to create appropriate suggestions. The preprocessed data and the results of the sentiment analysis are used as input, and the suggestion content is obtained as output. For example, a list of recommended gift items for a specific gift is generated. The prompt includes the request "I'm looking for gift items suitable for a wedding" and the user's emotional state.

[0781] Step 6:

[0782] The generated proposal is sent by the server to the review device. The consultant checks the proposal using smart glasses or a smartphone, and reviews and modifies it as necessary. The generated proposal is used as input, and a modified proposal is obtained as output. Specifically, the consultant checks the content of the proposal and adds points to be emphasized or supplementary information.

[0783] Step 7:

[0784] The final proposal is fed back to the user by the server. A feedback means provides the user with a revised proposal, including implementation steps and a recommended action plan. The revised proposal is used as input, and feedback is provided to the user as output. Specific feedback may include specific products and purchasing steps for "ideal wedding gift items."

[0785] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0786] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0787] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0788] [Third embodiment]

[0789] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0790] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0791] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0792] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0793] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0794] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0795] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0796] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0797] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0798] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0799] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0800] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0801] The present invention is a system that includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user.

[0802] Specific explanation of the system's operation

[0803] User Input

[0804] A user uses a web form or application to input the details of a consulting request. For example, the user inputs a request such as "I would like to improve my marketing strategy through the analysis of customer data."

[0805] Data collection and preprocessing

[0806] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0807] Proposal generation by generative AI

[0808] The server inputs the stored preprocessed data into a generative AI engine to generate proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific proposals that meet the user's requests. For example, it generates a proposal such as "Identify target segments and conduct social media campaigns."

[0809] Consultant review and follow-up

[0810] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[0811] Specific examples

[0812] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[0813] 1. User Input: A user fills out a web form with "Improve marketing strategies through customer data analysis."

[0814] 2. Data collection: The server collects relevant data from internal databases and external APIs.

[0815] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0816] 4. Proposal Generation: The generative AI engine analyzes the data and proposes "identifying target segments and implementing social media campaigns."

[0817] 5. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[0818] 6. Feedback: Send the final proposal to the user and provide implementation instructions or recommended actions.

[0819] This invention enables generative AI to automate many consulting tasks, providing efficient and cost-effective services. Users can receive high-quality consulting services quickly, and can meet a variety of needs, such as promoting digital transformation and strengthening risk management.

[0820] The processing flow will be explained below.

[0821] Step 1:

[0822] The user enters the project outline and required consulting details into the input form. The entered information is sent to the server by the terminal.

[0823] Step 2:

[0824] The server processes the input information received from the user and initiates data collection methods to collect relevant data, which may include retrieving the required data from internal databases or external APIs.

[0825] Step 3:

[0826] The server preprocesses the collected data. Preprocessing includes data cleaning (for example, filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[0827] Step 4:

[0828] The server stores the preprocessed data in a data storage means, and the stored data is used for analysis by the generative AI engine.

[0829] Step 5:

[0830] The server launches a generative AI engine, which provides the stored preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate suggestions based on the user's requests.

[0831] Step 6:

[0832] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[0833] Step 7:

[0834] The terminal displays the proposal to the consultant, who reviews it and makes any necessary revisions.

[0835] Step 8:

[0836] The terminal sends the final proposal to the server, which then sends the revised final proposal to the user as feedback.

[0837] Step 9:

[0838] The user receives the final proposal and implements any actionable advice or instructions. If there is additional feedback from the user, the cycle begins again.

[0839] Example 1

[0840] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0841] In traditional consulting work, users manually input the details of requests, and the subsequent data collection, proposal generation, review, and feedback required a great deal of time and cost. In addition, due to a lack of automated processes, many aspects of the work depended on specific know-how and experience, and there was a need to improve efficiency.

[0842] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0843] In this invention, the server includes input means for a user to input a consulting request, data collection means for collecting related data based on the input information, preprocessing means for preprocessing the collected data, data storage means for storing the preprocessed data, generation means for a generative AI model to generate a proposal based on the preprocessed data, transmission means for transmitting the generated proposal to a consultant terminal, review means for the consultant to review and modify the proposal content, feedback means for feeding back the final proposal to the user, input means for inputting data to the generative AI model using a prompt sentence, and display means for the consultant to check and modify the proposal content on his terminal. This automates and streamlines the entire process in consulting work, from data collection to proposal generation, review, and feedback, enabling significant reductions in time and cost.

[0844] "User" refers to an individual or company that uses the system to input a consulting request.

[0845] "Input means" refers to an interface or device that allows a user to input the content of a consulting request.

[0846] "Data Collection Measures" refers to software or systems for collecting relevant data based on input information.

[0847] "Preprocessing means" refers to software or a system for processing collected data to convert it into a format suitable for analysis and for removing noise data.

[0848] "Data storage means" refers to a database or cloud storage for storing preprocessed data.

[0849] "Generator" means a generative artificial intelligence model and associated software for generating recommendations using the pre-processed data.

[0850] "Transmission means" refers to communication means for transmitting the generated proposal to the consultant terminal.

[0851] "Review Tool" means a specialized interface or software that allows a Consultant to review and modify the Proposal.

[0852] "Feedback means" refers to a means for providing feedback on the final proposal to the user.

[0853] A "generative artificial intelligence model" refers to a system that uses machine learning algorithms and natural language processing technology to automatically generate suggestions based on input data.

[0854] A "prompt" refers to a text-based instruction or question that is input to a generative artificial intelligence model.

[0855] "Terminal" refers to the device used by the consultant to review and revise the proposal.

[0856] "Display means" refers to the display or user interface that allows the consultant to check and modify the proposal content on a terminal.

[0857] A specific embodiment of the present invention will be described below. This system automates a series of processes: a user inputs a consulting request, collects and preprocesses data based on the request, generates a proposal using a generative AI model, and then a consultant reviews and modifies the final proposal, providing the final proposal as feedback to the user.

[0858] Specific configuration and operation

[0859] User Input

[0860] The user enters the details of the consulting request through a web form or application. This input method is provided, for example, as a form that runs on a web browser or a mobile application. The user enters specific details of the request into the form, such as "I would like to improve my marketing strategy through the analysis of customer data," and clicks the submit button.

[0861] Data collection and preprocessing

[0862] The server receives input from the user and collects relevant data based on that input, either from an internal database (MySQL or PostgreSQL) or an external API (Google Analytics API, Twitter API, etc.) The server communicates with these databases and APIs to retrieve data relevant to the user's request.

[0863] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes unnecessary noise data, and converts the data format (for example, converting it to a CSV file or data frame). This prepares the data in a format suitable for analysis. The preprocessed data is then stored in a database or cloud storage, which is used as a data storage method.

[0864] Proposal generation

[0865] The server inputs the preprocessed data into a generative AI engine, which uses OpenAI GPT-3 or similar natural language processing technology. This AI engine uses machine learning algorithms to generate specific suggestions that address the user's request. For example, a suggestion might be, "Identify target segments and run social media campaigns."

[0866] Examples of prompts used to generate suggestions are:

[0867] "The user wants to improve their marketing strategy by analyzing customer data. The relevant data has been collected and preprocessed. Based on this, you would like to generate specific recommendations for the user."

[0868] Consultant review and feedback

[0869] The generated proposal is sent from the server to the consultant's terminal. The consultant can check the proposal contents by displaying them on a dedicated interface and make corrections if necessary. This display means is designed to make it easy for the consultant to check the proposal contents.

[0870] After the consultant makes any necessary corrections, the final proposal is finalized. This final proposal is then sent back to the user via the server as a means of feedback. The user can then receive the feedback and confirm specific implementation steps and recommended action plans.

[0871] This system enables faster, higher-quality consulting services than traditional manual processes. By combining generative AI with data pre-processing and consultant review, we can deliver efficient and cost-effective services.

[0872] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0873] Step 1:

[0874] User Input

[0875] The user enters the details of the consulting request through a web form or application. Specifically, the user enters a request such as "I would like to improve my marketing strategy through the analysis of customer data" and clicks the "Submit" button. This input is sent to the server and used to collect data for the next step.

[0876] Input: User's request (e.g., "I want to improve my marketing strategy through customer data analysis.")

[0877] Output: The request sent to the server

[0878] Step 2:

[0879] Data collection

[0880] The server collects relevant data based on the request received from the user. Specifically, it obtains the necessary data using an internal database (e.g., MySQL, PostgreSQL) or an external API (e.g., Google Analytics API, Twitter API). The server temporarily stores the obtained data and passes it to the next preprocessing step.

[0881] Input: User's request

[0882] Output: Relevant data collected

[0883] Step 3:

[0884] Data Preprocessing

[0885] The server performs preprocessing on the collected data. Specifically, it performs data cleaning, including filling in missing values ​​and removing noise data, and converts the data into a format suitable for analysis (e.g., CSV file, data frame). After preprocessing, the data is stored in a database.

[0886] Input: Relevant data collected

[0887] Output: Preprocessed data

[0888] Step 4:

[0889] Proposal generation

[0890] The server inputs the preprocessed data into a generative AI engine (e.g., OpenAI GPT-3), which uses the prompt to generate specific suggestions based on the user's request. For example, a suggestion might be "Identify target segments and conduct social media campaigns."

[0891] Input: Preprocessed data, prompt (e.g., "The user requests that we improve our marketing strategy through the analysis of customer data. The relevant data has been collected and preprocessed. Based on this, please generate specific suggestions for the user.")

[0892] Output: Generated proposals

[0893] Step 5:

[0894] Proposal Review

[0895] The generated proposal is sent from the server to the terminal (consultant device). The consultant reviews the content and makes any necessary corrections. The reviewed proposal is then sent to the server as the final proposal.

[0896] Input: Generated proposals

[0897] Output: Reviewed final proposal

[0898] Step 6:

[0899] feedback

[0900] The server then sends the final proposal, reviewed and revised by the consultant, back to the user. Specifically, it sends the final proposal to the user's email address or a dedicated user interface. The user receives the feedback and checks specific implementation steps and recommended action plans.

[0901] Input: Reviewed final proposal

[0902] Output: Final proposals fed back to the user

[0903] (Application example 1)

[0904] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0905] Conventional consulting systems have difficulty efficiently processing consulting requests from users, and in particular, they have not adequately proposed personalized marketing strategies that utilize customer behavior data and sales data in virtual stores. This poses a challenge, making it difficult to maximize customer engagement and sales opportunities.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0907] In this invention, the server includes an input means for users to input consulting requests, a data collection means for collecting related data based on the input information, and a preprocessing means for preprocessing the collected data. This allows for efficient collection and processing of data based on user requests, automatic proposal of personalized marketing strategies using a generative AI model, and the proposals can be reviewed and revised by consultants to reflect them in the final proposal. Furthermore, by adding functions for collecting and preprocessing customer behavior data and sales data within the virtual store, it is possible to provide users with more accurate personalized marketing strategies.

[0908] "User" refers to an individual or organization that submits a consulting request.

[0909] "Input means" refers to a mechanism or device that provides an interface for users to input consulting requests into the system.

[0910] "Data collection means" refers to a mechanism for collecting related data based on information input by a user.

[0911] "Pre-processing means" refers to a mechanism that processes collected data to convert it into a format suitable for analysis and generation of proposals by a generative AI model.

[0912] "Data storage means" refers to a mechanism for storing preprocessed data.

[0913] "Generative means" refers to the generative AI model or algorithm that uses pre-processed data to generate recommendations.

[0914] The "transmission means" refers to a mechanism for transmitting the generated proposal to the consultant terminal.

[0915] "Review procedures" refer to the mechanisms by which consultants review proposals and make corrections as necessary.

[0916] "Feedback means" refers to a mechanism for feeding back the final proposal to the user.

[0917] "Additional data collection means" refers to a mechanism for collecting customer behavior data and sales data within the virtual store.

[0918] "Additional pre-processing means" refers to a mechanism for pre-processing customer behavior data and sales data and converting them into a format for use in analysis.

[0919] "Generative AI model" refers to a model that uses machine learning algorithms and natural language processing techniques to generate suggestions.

[0920] "Strategy generation means" refers to a mechanism that uses a generative AI model to generate personalized marketing strategies for virtual stores.

[0921] The "strategy feedback means" refers to a mechanism for providing the generated marketing strategy to the user and providing feedback including implementation procedures and recommended actions.

[0922] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the proposal content, and a feedback means for feeding back the final proposal to the user.The system also includes an additional data collection means for collecting customer behavior data and sales data in a virtual store, an additional preprocessing means for preprocessing the customer behavior data and sales data and using it for analysis, a strategy generation means for generating a personalized marketing strategy using a generative AI model, and a strategy feedback means for providing the generated strategy to the user.

[0923] Program operation explanation

[0924] 1. User Input: A user enters a consulting request within a virtual store through a web form or mobile application. For example, a user might say, "Please tell me when there will be sales this month."

[0925] 2. Data collection: The server receives the input information and collects relevant data. The main data sources are customer behavior data (e.g., clickstream data) and sales data within the virtual store. These are obtained from internal databases and external APIs.

[0926] 3. Preprocessing: The server performs preprocessing on the collected data, such as filling in missing data and removing noise data, to generate preprocessed data.

[0927] 4. Proposal generation using generative AI: Using the preprocessed data, a generative AI model (e.g., GPT-3) is used to generate proposals. For example, a specific proposal such as "Hold a sale in the third week of this month" is generated.

[0928] 5. Review and follow-up by consultant: The proposal will be sent to the consultant's terminal, where the consultant will review the proposal and make any necessary corrections.

[0929] 6. Feedback: A final suggestion is given to the user, for example, "We'll have a sale in the third week of this month, and we'll focus on specific products."

[0930] Hardware and software used

[0931] Hardware: Servers, user devices (PCs, smartphones, etc.), consultant devices

[0932] Software: Databases (e.g., MySQL), external APIs, data preprocessing libraries (e.g., Pandas, SciPy), generative AI models (e.g., GPT-3), cloud storage (e.g., AWS, Google Cloud)

[0933] Specific examples

[0934] For example, if a company sends a request to "suggest the timing of the next sale based on customer behavior data and sales data," the process would go something like this:

[0935] 1. User Input: The user enters their "next sale timing suggestion" into a web form.

[0936] 2. Data collection: The server collects customer behavior data and sales data from the virtual store's database and external APIs.

[0937] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[0938] 4. Proposal Generation: The generative AI model analyzes the data and generates a suggestion such as "the next sale should be held in the third week."

[0939] 5. Review: The consultant reviews the proposal and makes any necessary revisions.

[0940] 6. Feedback: Send the final proposal to the user, providing specific implementation steps and recommended actions.

[0941] Example prompt sentence:

[0942] "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0943] This allows users to receive personalized marketing strategy suggestions quickly and accurately.

[0944] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0945] Step 1: User Input

[0946] A user inputs a consulting request through a web form or mobile application. For example, they might input, "Please let me know when the sale will be this month." This input triggers the system. The input information is sent to the server, and the system proceeds to the next processing step.

[0947] Input: A consulting request entered by the user (e.g., "Please let me know when the sale will be this month.")

[0948] Output: The request sent to the server

[0949] Specific behavior:

[0950] The user enters the request details into the form and presses the send button.

[0951] This information is sent to the server via the HTTPS protocol.

[0952] Step 2: Data collection

[0953] The server collects relevant data based on the request received from the user. Specifically, it retrieves customer behavior data (e.g., clickstream data) and sales data within the virtual store from an internal database or external API. This data is then passed on to the next pre-processing step.

[0954] Input: User requests, access to internal databases and external APIs

[0955] Output: Collected customer behavior and sales data

[0956] Specific behavior:

[0957] The server executes database queries to obtain internal customer behavior and sales data.

[0958] Call an external API to retrieve additional data.

[0959] Step 3: Preprocessing

[0960] The server performs preprocessing on the collected data, such as filling in missing data, removing noise, and normalizing the data to generate preprocessed data, which is then converted into a format that is easier to analyze.

[0961] Input: Collected raw data (customer behavior data and sales data)

[0962] Output: Preprocessed data

[0963] Specific behavior:

[0964] The server cleans the data using Python libraries such as Pandas and SciPy.

[0965] Impute missing values ​​and remove outliers.

[0966] Normalize the data and convert it into a suitable format for analysis.

[0967] Step 4: Proposal generation by generative AI

[0968] Using the preprocessed data, the server uses a generative AI model (e.g., GPT-3) to generate suggestions, which may include specific details such as "Hold a sale in the third week of this month."

[0969] Input: Preprocessed data

[0970] Output: Generated proposals

[0971] Specific behavior:

[0972] The server inputs a prompt sentence into the generative AI model and generates a suggestion.

[0973] Example prompt: "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[0974] Step 5: Consultant review and follow-up

[0975] The generated proposal is sent to the consultant's terminal, where the consultant reviews the proposal and makes any necessary corrections. After the consultant has confirmed and corrected the proposal, the final proposal is decided.

[0976] Input: Generated proposals

[0977] Output: Reviewed and revised final proposal

[0978] Specific behavior:

[0979] The server transmits the generated proposal to the consultant terminal.

[0980] The consultant reviews the proposal and enters any corrections into the system.

[0981] Step 6: Feedback

[0982] A final recommendation is provided to the user, such as "We're running a sale in the third week of this month, focusing on specific products."

[0983] Input: Reviewed and revised final proposal

[0984] Output: Feedback to the user

[0985] Specific behavior:

[0986] The server sends the final proposal to the user's terminal.

[0987] The user reviews the suggestions and decides on their next action.

[0988] The above processing flow enables the user to receive personalized marketing strategy proposals quickly and accurately.

[0989] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0990] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user, and further includes an emotion engine that recognizes the user's emotions.

[0991] Specific explanation of the system's operation

[0992] User Input

[0993] A user uses a web form or application to input the details of a consulting request. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[0994] emotion recognition

[0995] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[0996] Data collection and preprocessing

[0997] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[0998] Proposal generation by generative AI

[0999] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[1000] Consultant review and follow-up

[1001] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[1002] Specific examples

[1003] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[1004] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[1005] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[1006] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[1007] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1008] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[1009] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[1010] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[1011] This invention enables generative AI to automate much of the consulting work, providing efficient and cost-effective services. Furthermore, the introduction of an emotion engine enables flexible responses according to the user's emotional state, which is expected to improve user satisfaction.

[1012] The processing flow will be explained below.

[1013] Step 1:

[1014] The user inputs a consulting request. The user uses a web form or application to input information such as "I would like to improve my marketing strategy through customer data analysis." The input information is sent to the server by the terminal.

[1015] Step 2:

[1016] The server processes the input received from the user. The server then launches the data collection mechanism and executes scripts to collect relevant data based on the user input. The data source can be an internal database or an external API.

[1017] Step 3:

[1018] The server launches an emotion engine to analyze the user's input. The emotion engine uses text and voice analysis techniques to determine the user's emotional state (e.g., stress, anxiety, satisfaction, etc.).

[1019] Step 4:

[1020] The server preprocesses the collected data. Preprocessing includes data cleaning (filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[1021] Step 5:

[1022] The server stores the preprocessed data in the data storage means, and the stored data is used for analysis by the generating means.

[1023] Step 6:

[1024] The server launches the generative AI engine and provides the saved preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate specific suggestions that meet the user's needs. At this time, the user's emotional state, obtained from the emotion engine, is also reflected in the suggestion content and tone.

[1025] Step 7:

[1026] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[1027] Step 8:

[1028] The terminal displays the proposal to the consultant, who reviews it and makes any necessary corrections. The revised proposal is then sent back to the server.

[1029] Step 9:

[1030] The server then provides the user with a final, revised proposal, which includes specific steps to implement and a recommended action plan, taking into account the user's emotional state.

[1031] Step 10:

[1032] The user receives the final proposal and implements any actionable advice or instructions. If the user provides additional feedback, the cycle begins again, continually improving the quality of the consulting service.

[1033] Example 2

[1034] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1035] Conventional consulting systems have had difficulty generating proposals that take users' emotions into account, making it difficult to provide effective support that increases user satisfaction. Additionally, data preprocessing takes time, making it difficult to respond in real time.

[1036] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for the user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to the consultant terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, and an emotion engine means for recognizing the user's emotions. This makes it possible to quickly generate a proposal that takes the user's emotions into consideration and provide effective support to improve user satisfaction.

[1037] "User" means an individual or corporation that utilizes the system to input a consulting request and seek a solution.

[1038] The "input means" is an interface used by a user to input a consulting request, and may take the form of a web form, an application, or the like.

[1039] "Data collection means" has the function of collecting necessary data from an internal database or external API based on the input information.

[1040] The "preprocessing means" has the function of complementing missing values ​​and removing noise from the collected data, and shaping it into a format suitable for analysis.

[1041] "Data storage means" means a means that has a storage function for efficiently storing and managing preprocessed data, and includes cloud storage.

[1042] The "generation means" has a function of generating specific proposals based on the preprocessed data in accordance with the user's needs.

[1043] The "transmitting means" has a communication function for transmitting the generated proposal to the consultant terminal.

[1044] "Review tools" are functions that allow consultants to check the content of proposals and make necessary corrections, and may use artificial intelligence technology.

[1045] The "feedback means" has the function of returning the final proposal to the user and providing implementation procedures and recommended actions.

[1046] The "emotion engine means" has a function for analyzing emotions from the user's input data and generating a response according to the user's emotional state.

[1047] The present invention is a system that allows users to input a consulting request and generates optimal proposals based on the request. This system also includes an emotion engine that recognizes the user's emotions in real time, improving the user experience.

[1048] Hardware and software used

[1049] The main components of this system are the server, the terminal, and the user, and have the following specific functions:

[1050] Server: Performs data collection, pre-processing, proposal generation, emotion recognition, and proposal transmission. Software used includes natural language processing technology, voice analysis technology, machine learning algorithms, cloud storage, etc.

[1051] Terminal: A review terminal for the consultant, which serves as an interface for the consultant to review and modify the proposal.

[1052] User: A person requesting a consulting business and entering the details of their request via a web form or application.

[1053] Specific circumstances of data processing and calculation

[1054] User Input

[1055] A user enters a consulting request using a web form or application. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[1056] emotion recognition

[1057] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[1058] Data collection and preprocessing

[1059] The server receives user input and collects the necessary data based on it. The data source is mainly an internal database or an external API. The collected data undergoes preprocessing, such as processing missing values ​​and removing noise data, and is then stored in a database. This allows the data to be formatted so that it can be easily analyzed by the generating means.

[1060] Proposal generation by generative AI

[1061] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[1062] Consultant review and follow-up

[1063] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[1064] Specific examples

[1065] For example, if a company submits a request to "improve marketing strategies through analysis of customer data," the system operates as follows:

[1066] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[1067] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[1068] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[1069] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1070] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[1071] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[1072] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[1073] Prompt Sentence Examples

[1074] An example of a prompt to use for system input is:

[1075] 1. "The user requests improvement of their marketing strategy through analysis of customer data. Generate suggestions based on the collected data and the user's emotional state."

[1076] 2. "The user is feeling anxious. Generate support-focused marketing strategy suggestions that take this emotional state into account."

[1077] By combining generative AI technology with an emotion engine, the system of the present invention makes it possible to provide users with advanced and detailed consulting services.

[1078] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1079] Step 1:

[1080] User Input

[1081] A user enters a specific consulting request using a web form or application. For example, the user enters a request such as "I would like to improve my marketing strategy through customer data analysis," and presses the submit button. At this time, the entered text data is sent to the server along with voice data and other contextual information.

[1082] Input: Text data: "I want to improve my marketing strategy through customer data analysis."

[1083] Output: User's consulting request data

[1084] Step 2:

[1085] emotion recognition

[1086] The server analyzes the received user input data and activates an emotion engine. The emotion engine uses natural language processing and speech analysis technologies to evaluate the input text data and voice data and determine the user's emotional state. For example, it can extract an emotional state such as "the user is feeling anxious" from the input text.

[1087] Input: User's consulting request text and voice data

[1088] Output: User's emotional state (e.g., anxiety)

[1089] Step 3:

[1090] Data collection

[1091] The server collects relevant data based on the user's input data and emotional state. This data is mainly obtained from internal databases and external APIs and is included in the required dataset. The data collection takes into account the user's consultation request.

[1092] Input: User's consulting request data and emotional state

[1093] Output: Collected related dataset

[1094] Step 4:

[1095] Data Preprocessing

[1096] The server performs preprocessing on the collected data, including missing value imputation, noise removal, and data shaping and normalization. The preprocessed data is stored in a database and prepared for the generative AI engine to generate suggestions.

[1097] Input: Collected relevant datasets

[1098] Output: Preprocessed data

[1099] Step 5:

[1100] Proposal generation by generative AI

[1101] The server inputs the preprocessed data into a generative AI engine, which generates proposals based on the user's request. The generative AI engine uses machine learning algorithms and natural language processing technology to create specific proposals. At this time, the user's emotional state obtained from the emotion engine is also reflected, resulting in more personalized proposals.

[1102] Input: Preprocessed data and user's emotional state

[1103] Output: Generated concrete consulting proposals

[1104] Step 6:

[1105] Submit a proposal

[1106] The server sends the proposal created by the generative AI engine to the consultant's device, where the proposal is encoded and sent via HTTP or other communication protocol.

[1107] Input: Generated specific consulting proposal

[1108] Output: Proposal data to consultant's terminal

[1109] Step 7:

[1110] Consultant Review

[1111] The terminal (consultant) checks the received proposal and makes corrections as necessary. The consultant checks the appropriateness and details of the proposal and improves the quality of the proposal by correcting any insufficiencies or errors. The corrected proposal is then sent back to the server.

[1112] Input: Proposal data displayed on the consultant's terminal

[1113] Output: Final revised proposal data

[1114] Step 8:

[1115] feedback

[1116] The server receives revised proposals from the consultant and provides the final proposal as feedback to the user, typically via the user's email address or application notification. The proposal includes specific implementation steps and a recommended action plan.

[1117] Input: Revised final proposal data

[1118] Output: Final proposal feedback to the user

[1119] (Application example 2)

[1120] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1121] Conventional consulting systems were unable to automatically generate proposals based on user-entered requests, and also had difficulty responding to requests that took the user's emotional state into account. Furthermore, while it is important for brick-and-mortar stores to recognize customers' emotions in real time and adjust proposals based on that information, there was a lack of efficient ways to do this. This resulted in lower customer satisfaction and the inability to provide effective proposals.

[1122] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1123] In this invention, the server includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a review terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, an emotion analysis means for recognizing the user's emotion, a proposal adjustment means for adjusting the proposal content based on the emotion analysis means, and an input assistance means for inputting the user's request into smart glasses or a smartphone. This enables flexible responses according to the user's emotional state and real-time customer service in a physical store.

[1124] The "input means for a user to input a consulting request" refers to a means for a user to input a consulting request using a device such as smart glasses or a smartphone.

[1125] The "data collection means for collecting related data based on input information" is a means for automatically collecting necessary related data based on information input by the user.

[1126] The "preprocessing means for preprocessing collected data" refers to a means for removing noise data from collected data, complementing missing values, and converting the data into a format suitable for analysis.

[1127] The "data storage means for storing the preprocessed data" refers to a means for safely and efficiently storing the preprocessed data, and cloud storage may be used.

[1128] The "means for generating a proposal using preprocessed data" refers to a means for generating a proposal suited to a user request based on the preprocessed data.

[1129] The "transmission means for transmitting the generated proposal to the review terminal" is a means for transmitting the generated proposal to a terminal where the consultant can review it.

[1130] The "review means for the consultant to review and modify the proposal content" refers to a means for the consultant to evaluate the generated proposal and modify it as necessary.

[1131] The "feedback means for feeding back the final proposal to the user" is a means for feeding back the final proposal after correction to the user.

[1132] The "emotion analysis means for recognizing the user's emotions" is a means for analyzing emotions from the user's voice or text input and recognizing the user's emotional state, such as stress or satisfaction.

[1133] The "proposal adjustment means for adjusting the proposal content based on the emotion analysis means" is a means for adjusting the proposal content and its tone based on the emotion information obtained from the emotion analysis means.

[1134] The "input assistance means for inputting a user's request into smart glasses or a smartphone" is a means for a user to input a request in real time using smart glasses or a smartphone.

[1135] The present invention is a system for improving the efficiency of customer service in brick-and-mortar stores and enhancing customer satisfaction. This system involves a series of processes in which a user inputs a consulting request using smart glasses or a smartphone, automatically generates a proposal based on the request, and finally provides feedback. The components of the system are as follows:

[1136] Program processing and the hardware and software used

[1137] 1. Input method: The user inputs a consulting request using smart glasses or a smartphone. For example, a customer in a physical store inputs a request such as "I'm looking for a suitable gift item for a wedding." This is done using the touch input or voice input functions of the smart glasses or smartphone.

[1138] 2. Emotion analysis: The server analyzes emotions from user input and voice data. Using the Emotion Engine, it recognizes the customer's emotional state in real time. The results of this analysis are used to determine whether or not support is required.

[1139] 3. Data collection method: The server automatically collects relevant data based on the user's input. The data source is mainly internal databases and external APIs. The data collection here uses the Python requests library.

[1140] 4. Preprocessing: The collected data is not suitable for analysis as it is, so it is preprocessed. This preprocessing includes filling in missing values ​​and removing noise data. For example, data cleaning and standardization of format are performed.

[1141] 5. Proposal generation method: Using the preprocessed data, the generative AI model creates specific proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate proposals that best fit the user's request. The proposal content is also adjusted taking into account the results of sentiment analysis.

[1142] 6. Transmission method: The generated proposal is sent to a device (smart glasses or smartphone) where the consultant can review it. This allows the consultant to check and modify the proposal in real time.

[1143] 7. Review method: The consultant's terminal reviews the proposal and makes any necessary corrections. The proposal may also be evaluated using artificial intelligence technology. At this stage, unnecessary information is removed and important information is added.

[1144] 8. Feedback: The final revised proposal is fed back to the user. This feedback includes implementation procedures and recommended action plans. For example, specific product names and purchasing instructions for "gift items the customer is looking for" are provided.

[1145] Examples of specific examples and prompts

[1146] For example, if a customer requests "I'm looking for a gift item suitable for a wedding" in a physical store and is a little nervous,

[1147] Example prompt sentence:

[1148] The request states, "I'm looking for a gift item suitable for a wedding." At this point, the customer is a little nervous.

[1149] Prompt for generative AI model:

[1150] A request is received saying, "I'm looking for a suitable gift item for a wedding." The customer is in a tense emotional state and is seeking suggestions that emphasize reassuring support.

[1151] This system enables flexible responses based on the user's emotional state and real-time customer support in physical stores, which is expected to improve customer satisfaction.

[1152] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1153] Step 1:

[1154] The user inputs a consulting request using smart glasses or a smartphone. The user enters the request details into an input form within the application, and can also input by voice. For example, the user might input, "I'm looking for a suitable gift item for a wedding." The input data is sent to the server.

[1155] Step 2:

[1156] The server analyzes the received user input data. Using the Emotion Engine, it recognizes the user's emotional state from the input text and voice data. The user's request data is used as input, and the user's emotional state is obtained as output. Specifically, it determines in real time whether the user is nervous or satisfied.

[1157] Step 3:

[1158] The server collects relevant data based on the sentiment analysis results and input data. It uses the Python requests library to automatically retrieve the necessary data from an internal database or external API. The input is the user's request and emotional state, and the output is the retrieved relevant data. For example, it can collect gift item candidates and rating data.

[1159] Step 4:

[1160] The collected data is preprocessed by the server. The preprocessing means complements missing values ​​and removes noise data from the collected data, and converts it into a format suitable for analysis. The collected data is used as input, and preprocessed data is obtained as output. Specific examples include removing duplicate data and standardizing formats.

[1161] Step 5:

[1162] The server uses the preprocessed data to generate a generative AI model to generate suggestions based on the user's request. The suggestion generator uses machine learning algorithms and natural language processing techniques to create appropriate suggestions. The preprocessed data and the results of the sentiment analysis are used as input, and the suggestion content is obtained as output. For example, a list of recommended gift items for a specific gift is generated. The prompt includes the request "I'm looking for gift items suitable for a wedding" and the user's emotional state.

[1163] Step 6:

[1164] The generated proposal is sent by the server to the review device. The consultant checks the proposal using smart glasses or a smartphone, and reviews and modifies it as necessary. The generated proposal is used as input, and a modified proposal is obtained as output. Specifically, the consultant checks the content of the proposal and adds points to be emphasized or supplementary information.

[1165] Step 7:

[1166] The final proposal is fed back to the user by the server. A feedback means provides the user with a revised proposal, including implementation steps and a recommended action plan. The revised proposal is used as input, and feedback is provided to the user as output. Specific feedback may include specific products and purchasing steps for "ideal wedding gift items."

[1167] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1168] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1169] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1170] [Fourth embodiment]

[1171] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1172] 7, a 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.

[1173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1174] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1175] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1178] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1179] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1180] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1181] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1182] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1183] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1184] The present invention is a system that includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user.

[1185] Specific explanation of the system's operation

[1186] User Input

[1187] A user uses a web form or application to input the details of a consulting request. For example, the user inputs a request such as "I would like to improve my marketing strategy through the analysis of customer data."

[1188] Data collection and preprocessing

[1189] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[1190] Proposal generation by generative AI

[1191] The server inputs the stored preprocessed data into a generative AI engine to generate proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific proposals that meet the user's requests. For example, it generates a proposal such as "Identify target segments and conduct social media campaigns."

[1192] Consultant review and follow-up

[1193] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[1194] Specific examples

[1195] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[1196] 1. User Input: A user fills out a web form with "Improve marketing strategies through customer data analysis."

[1197] 2. Data collection: The server collects relevant data from internal databases and external APIs.

[1198] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1199] 4. Proposal Generation: The generative AI engine analyzes the data and proposes "identifying target segments and implementing social media campaigns."

[1200] 5. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[1201] 6. Feedback: Send the final proposal to the user and provide implementation instructions or recommended actions.

[1202] This invention enables generative AI to automate many consulting tasks, providing efficient and cost-effective services. Users can receive high-quality consulting services quickly, and can meet a variety of needs, such as promoting digital transformation and strengthening risk management.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] The user enters the project outline and required consulting details into the input form. The entered information is sent to the server by the terminal.

[1206] Step 2:

[1207] The server processes the input information received from the user and initiates data collection methods to collect relevant data, which may include retrieving the required data from internal databases or external APIs.

[1208] Step 3:

[1209] The server preprocesses the collected data. Preprocessing includes data cleaning (for example, filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[1210] Step 4:

[1211] The server stores the preprocessed data in a data storage means, and the stored data is used for analysis by the generative AI engine.

[1212] Step 5:

[1213] The server launches a generative AI engine, which provides the stored preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate suggestions based on the user's requests.

[1214] Step 6:

[1215] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[1216] Step 7:

[1217] The terminal displays the proposal to the consultant, who reviews it and makes any necessary revisions.

[1218] Step 8:

[1219] The terminal sends the final proposal to the server, which then sends the revised final proposal to the user as feedback.

[1220] Step 9:

[1221] The user receives the final proposal and implements any actionable advice or instructions. If there is additional feedback from the user, the cycle begins again.

[1222] Example 1

[1223] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] In traditional consulting work, users manually input the details of requests, and the subsequent data collection, proposal generation, review, and feedback required a great deal of time and cost. In addition, due to a lack of automated processes, many aspects of the work depended on specific know-how and experience, and there was a need to improve efficiency.

[1225] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1226] In this invention, the server includes input means for a user to input a consulting request, data collection means for collecting related data based on the input information, preprocessing means for preprocessing the collected data, data storage means for storing the preprocessed data, generation means for a generative AI model to generate a proposal based on the preprocessed data, transmission means for transmitting the generated proposal to a consultant terminal, review means for the consultant to review and modify the proposal content, feedback means for feeding back the final proposal to the user, input means for inputting data to the generative AI model using a prompt sentence, and display means for the consultant to check and modify the proposal content on his terminal. This automates and streamlines the entire process in consulting work, from data collection to proposal generation, review, and feedback, enabling significant reductions in time and cost.

[1227] "User" refers to an individual or company that uses the system to input a consulting request.

[1228] "Input means" refers to an interface or device that allows a user to input the content of a consulting request.

[1229] "Data Collection Measures" refers to software or systems for collecting relevant data based on input information.

[1230] "Preprocessing means" refers to software or a system for processing collected data to convert it into a format suitable for analysis and for removing noise data.

[1231] "Data storage means" refers to a database or cloud storage for storing preprocessed data.

[1232] "Generator" means a generative artificial intelligence model and associated software for generating recommendations using the pre-processed data.

[1233] "Transmission means" refers to communication means for transmitting the generated proposal to the consultant terminal.

[1234] "Review Tool" means a specialized interface or software that allows a Consultant to review and modify the Proposal.

[1235] "Feedback means" refers to a means for providing feedback on the final proposal to the user.

[1236] A "generative artificial intelligence model" refers to a system that uses machine learning algorithms and natural language processing technology to automatically generate suggestions based on input data.

[1237] A "prompt" refers to a text-based instruction or question that is input to a generative artificial intelligence model.

[1238] "Terminal" refers to the device used by the consultant to review and revise the proposal.

[1239] "Display means" refers to the display or user interface that allows the consultant to check and modify the proposal content on a terminal.

[1240] A specific embodiment of the present invention will be described below. This system automates a series of processes: a user inputs a consulting request, collects and preprocesses data based on the request, generates a proposal using a generative AI model, and then a consultant reviews and modifies the final proposal, providing the final proposal as feedback to the user.

[1241] Specific configuration and operation

[1242] User Input

[1243] The user enters the details of the consulting request through a web form or application. This input method is provided, for example, as a form that runs on a web browser or a mobile application. The user enters specific details of the request into the form, such as "I would like to improve my marketing strategy through the analysis of customer data," and clicks the submit button.

[1244] Data collection and preprocessing

[1245] The server receives input from the user and collects relevant data based on that input, either from an internal database (MySQL or PostgreSQL) or an external API (Google Analytics API, Twitter API, etc.) The server communicates with these databases and APIs to retrieve data relevant to the user's request.

[1246] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes unnecessary noise data, and converts the data format (for example, converting it to a CSV file or data frame). This prepares the data in a format suitable for analysis. The preprocessed data is then stored in a database or cloud storage, which is used as a data storage method.

[1247] Proposal generation

[1248] The server inputs the preprocessed data into a generative AI engine, which uses OpenAI GPT-3 or similar natural language processing technology. This AI engine uses machine learning algorithms to generate specific suggestions that address the user's request. For example, a suggestion might be, "Identify target segments and run social media campaigns."

[1249] Examples of prompts used to generate suggestions are:

[1250] "The user wants to improve their marketing strategy by analyzing customer data. The relevant data has been collected and preprocessed. Based on this, you would like to generate specific recommendations for the user."

[1251] Consultant review and feedback

[1252] The generated proposal is sent from the server to the consultant's terminal. The consultant can check the proposal contents by displaying them on a dedicated interface and make corrections if necessary. This display means is designed to make it easy for the consultant to check the proposal contents.

[1253] After the consultant makes any necessary corrections, the final proposal is finalized. This final proposal is then sent back to the user via the server as a means of feedback. The user can then receive the feedback and confirm specific implementation steps and recommended action plans.

[1254] This system enables faster, higher-quality consulting services than traditional manual processes. By combining generative AI with data pre-processing and consultant review, we can deliver efficient and cost-effective services.

[1255] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1256] Step 1:

[1257] User Input

[1258] The user enters the details of the consulting request through a web form or application. Specifically, the user enters a request such as "I would like to improve my marketing strategy through the analysis of customer data" and clicks the "Submit" button. This input is sent to the server and used to collect data for the next step.

[1259] Input: User's request (e.g., "I want to improve my marketing strategy through customer data analysis.")

[1260] Output: The request sent to the server

[1261] Step 2:

[1262] Data collection

[1263] The server collects relevant data based on the request received from the user. Specifically, it obtains the necessary data using an internal database (e.g., MySQL, PostgreSQL) or an external API (e.g., Google Analytics API, Twitter API). The server temporarily stores the obtained data and passes it to the next preprocessing step.

[1264] Input: User's request

[1265] Output: Relevant data collected

[1266] Step 3:

[1267] Data Preprocessing

[1268] The server performs preprocessing on the collected data. Specifically, it performs data cleaning, including filling in missing values ​​and removing noise data, and converts the data into a format suitable for analysis (e.g., CSV file, data frame). After preprocessing, the data is stored in a database.

[1269] Input: Relevant data collected

[1270] Output: Preprocessed data

[1271] Step 4:

[1272] Proposal generation

[1273] The server inputs the preprocessed data into a generative AI engine (e.g., OpenAI GPT-3), which uses the prompt to generate specific suggestions based on the user's request. For example, a suggestion might be "Identify target segments and conduct social media campaigns."

[1274] Input: Preprocessed data, prompt (e.g., "The user requests that we improve our marketing strategy through the analysis of customer data. The relevant data has been collected and preprocessed. Based on this, please generate specific suggestions for the user.")

[1275] Output: Generated proposals

[1276] Step 5:

[1277] Proposal Review

[1278] The generated proposal is sent from the server to the terminal (consultant device). The consultant reviews the content and makes any necessary corrections. The reviewed proposal is then sent to the server as the final proposal.

[1279] Input: Generated proposals

[1280] Output: Reviewed final proposal

[1281] Step 6:

[1282] feedback

[1283] The server then sends the final proposal, reviewed and revised by the consultant, back to the user. Specifically, it sends the final proposal to the user's email address or a dedicated user interface. The user receives the feedback and checks specific implementation steps and recommended action plans.

[1284] Input: Reviewed final proposal

[1285] Output: Final proposals fed back to the user

[1286] (Application example 1)

[1287] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1288] Conventional consulting systems have difficulty efficiently processing consulting requests from users, and in particular, they have not adequately proposed personalized marketing strategies that utilize customer behavior data and sales data in virtual stores. This poses a challenge, making it difficult to maximize customer engagement and sales opportunities.

[1289] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1290] In this invention, the server includes an input means for users to input consulting requests, a data collection means for collecting related data based on the input information, and a preprocessing means for preprocessing the collected data. This allows for efficient collection and processing of data based on user requests, automatic proposal of personalized marketing strategies using a generative AI model, and the proposals can be reviewed and revised by consultants to reflect them in the final proposal. Furthermore, by adding functions for collecting and preprocessing customer behavior data and sales data within the virtual store, it is possible to provide users with more accurate personalized marketing strategies.

[1291] "User" refers to an individual or organization that submits a consulting request.

[1292] "Input means" refers to a mechanism or device that provides an interface for users to input consulting requests into the system.

[1293] "Data collection means" refers to a mechanism for collecting related data based on information input by a user.

[1294] "Pre-processing means" refers to a mechanism that processes collected data to convert it into a format suitable for analysis and generation of proposals by a generative AI model.

[1295] "Data storage means" refers to a mechanism for storing preprocessed data.

[1296] "Generative means" refers to the generative AI model or algorithm that uses pre-processed data to generate recommendations.

[1297] The "transmission means" refers to a mechanism for transmitting the generated proposal to the consultant terminal.

[1298] "Review procedures" refer to the mechanisms by which consultants review proposals and make corrections as necessary.

[1299] "Feedback means" refers to a mechanism for feeding back the final proposal to the user.

[1300] "Additional data collection means" refers to a mechanism for collecting customer behavior data and sales data within the virtual store.

[1301] "Additional pre-processing means" refers to a mechanism for pre-processing customer behavior data and sales data and converting them into a format for use in analysis.

[1302] "Generative AI model" refers to a model that uses machine learning algorithms and natural language processing techniques to generate suggestions.

[1303] "Strategy generation means" refers to a mechanism that uses a generative AI model to generate personalized marketing strategies for virtual stores.

[1304] The "strategy feedback means" refers to a mechanism for providing the generated marketing strategy to the user and providing feedback including implementation procedures and recommended actions.

[1305] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the proposal content, and a feedback means for feeding back the final proposal to the user.The system also includes an additional data collection means for collecting customer behavior data and sales data in a virtual store, an additional preprocessing means for preprocessing the customer behavior data and sales data and using it for analysis, a strategy generation means for generating a personalized marketing strategy using a generative AI model, and a strategy feedback means for providing the generated strategy to the user.

[1306] Program operation explanation

[1307] 1. User Input: A user enters a consulting request within a virtual store through a web form or mobile application. For example, a user might say, "Please tell me when there will be sales this month."

[1308] 2. Data collection: The server receives the input information and collects relevant data. The main data sources are customer behavior data (e.g., clickstream data) and sales data within the virtual store. These are obtained from internal databases and external APIs.

[1309] 3. Preprocessing: The server performs preprocessing on the collected data, such as filling in missing data and removing noise data, to generate preprocessed data.

[1310] 4. Proposal generation using generative AI: Using the preprocessed data, a generative AI model (e.g., GPT-3) is used to generate proposals. For example, a specific proposal such as "Hold a sale in the third week of this month" is generated.

[1311] 5. Review and follow-up by consultant: The proposal will be sent to the consultant's terminal, where the consultant will review the proposal and make any necessary corrections.

[1312] 6. Feedback: A final suggestion is given to the user, for example, "We'll have a sale in the third week of this month, and we'll focus on specific products."

[1313] Hardware and software used

[1314] Hardware: Servers, user devices (PCs, smartphones, etc.), consultant devices

[1315] Software: Databases (e.g., MySQL), external APIs, data preprocessing libraries (e.g., Pandas, SciPy), generative AI models (e.g., GPT-3), cloud storage (e.g., AWS, Google Cloud)

[1316] Specific examples

[1317] For example, if a company sends a request to "suggest the timing of the next sale based on customer behavior data and sales data," the process would go something like this:

[1318] 1. User Input: The user enters their "next sale timing suggestion" into a web form.

[1319] 2. Data collection: The server collects customer behavior data and sales data from the virtual store's database and external APIs.

[1320] 3. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1321] 4. Proposal Generation: The generative AI model analyzes the data and generates a suggestion such as "the next sale should be held in the third week."

[1322] 5. Review: The consultant reviews the proposal and makes any necessary revisions.

[1323] 6. Feedback: Send the final proposal to the user, providing specific implementation steps and recommended actions.

[1324] Example prompt sentence:

[1325] "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[1326] This allows users to receive personalized marketing strategy suggestions quickly and accurately.

[1327] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1328] Step 1: User Input

[1329] A user inputs a consulting request through a web form or mobile application. For example, they might input, "Please let me know when the sale will be this month." This input triggers the system. The input information is sent to the server, and the system proceeds to the next processing step.

[1330] Input: A consulting request entered by the user (e.g., "Please let me know when the sale will be this month.")

[1331] Output: The request sent to the server

[1332] Specific behavior:

[1333] The user enters the request details into the form and presses the send button.

[1334] This information is sent to the server via the HTTPS protocol.

[1335] Step 2: Data collection

[1336] The server collects relevant data based on the request received from the user. Specifically, it retrieves customer behavior data (e.g., clickstream data) and sales data within the virtual store from an internal database or external API. This data is then passed on to the next pre-processing step.

[1337] Input: User requests, access to internal databases and external APIs

[1338] Output: Collected customer behavior and sales data

[1339] Specific behavior:

[1340] The server executes database queries to obtain internal customer behavior and sales data.

[1341] Call an external API to retrieve additional data.

[1342] Step 3: Preprocessing

[1343] The server performs preprocessing on the collected data, such as filling in missing data, removing noise, and normalizing the data to generate preprocessed data, which is then converted into a format that is easier to analyze.

[1344] Input: Collected raw data (customer behavior data and sales data)

[1345] Output: Preprocessed data

[1346] Specific behavior:

[1347] The server cleans the data using Python libraries such as Pandas and SciPy.

[1348] Impute missing values ​​and remove outliers.

[1349] Normalize the data and convert it into a suitable format for analysis.

[1350] Step 4: Proposal generation by generative AI

[1351] Using the preprocessed data, the server uses a generative AI model (e.g., GPT-3) to generate suggestions, which may include specific details such as "Hold a sale in the third week of this month."

[1352] Input: Preprocessed data

[1353] Output: Generated proposals

[1354] Specific behavior:

[1355] The server inputs a prompt sentence into the generative AI model and generates a suggestion.

[1356] Example prompt: "Given the following data: [preprocessed data], generate a marketing strategy proposal for the next sales event."

[1357] Step 5: Consultant review and follow-up

[1358] The generated proposal is sent to the consultant's terminal, where the consultant reviews the proposal and makes any necessary corrections. After the consultant has confirmed and corrected the proposal, the final proposal is decided.

[1359] Input: Generated proposals

[1360] Output: Reviewed and revised final proposal

[1361] Specific behavior:

[1362] The server transmits the generated proposal to the consultant terminal.

[1363] The consultant reviews the proposal and enters any corrections into the system.

[1364] Step 6: Feedback

[1365] A final recommendation is provided to the user, such as "We're running a sale in the third week of this month, focusing on specific products."

[1366] Input: Reviewed and revised final proposal

[1367] Output: Feedback to the user

[1368] Specific behavior:

[1369] The server sends the final proposal to the user's terminal.

[1370] The user reviews the suggestions and decides on their next action.

[1371] The above processing flow enables the user to receive personalized marketing strategy proposals quickly and accurately.

[1372] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1373] The present invention is a system including an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a consultant terminal, a review means for the consultant to review and modify the content of the proposal, and a feedback means for feeding back the final proposal to the user, and further includes an emotion engine that recognizes the user's emotions.

[1374] Specific explanation of the system's operation

[1375] User Input

[1376] A user uses a web form or application to input the details of a consulting request. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[1377] emotion recognition

[1378] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[1379] Data collection and preprocessing

[1380] The server receives user input and collects the necessary data based on it. The data source is mainly internal databases or external APIs. The collected data undergoes preprocessing, such as handling missing values ​​and removing noise data. The preprocessed data is stored in a database and later used for analysis by the generation means.

[1381] Proposal generation by generative AI

[1382] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[1383] Consultant review and follow-up

[1384] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[1385] Specific examples

[1386] For example, if a company sends a request to "improve its marketing strategies through analysis of customer data," the process would go something like this:

[1387] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[1388] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[1389] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[1390] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1391] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[1392] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[1393] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[1394] This invention enables generative AI to automate much of the consulting work, providing efficient and cost-effective services. Furthermore, the introduction of an emotion engine enables flexible responses according to the user's emotional state, which is expected to improve user satisfaction.

[1395] The processing flow will be explained below.

[1396] Step 1:

[1397] The user inputs a consulting request. The user uses a web form or application to input information such as "I would like to improve my marketing strategy through customer data analysis." The input information is sent to the server by the terminal.

[1398] Step 2:

[1399] The server processes the input received from the user. The server then launches the data collection mechanism and executes scripts to collect relevant data based on the user input. The data source can be an internal database or an external API.

[1400] Step 3:

[1401] The server launches an emotion engine to analyze the user's input. The emotion engine uses text and voice analysis techniques to determine the user's emotional state (e.g., stress, anxiety, satisfaction, etc.).

[1402] Step 4:

[1403] The server preprocesses the collected data. Preprocessing includes data cleaning (filling in missing values ​​and removing noise data), extracting necessary features, and converting the data format.

[1404] Step 5:

[1405] The server stores the preprocessed data in the data storage means, and the stored data is used for analysis by the generating means.

[1406] Step 6:

[1407] The server launches the generative AI engine and provides the saved preprocessed data as input. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate specific suggestions that meet the user's needs. At this time, the user's emotional state, obtained from the emotion engine, is also reflected in the suggestion content and tone.

[1408] Step 7:

[1409] The server sends the generated proposal to the consultant's terminal. The proposal is sent in a structured format (e.g., JSON format).

[1410] Step 8:

[1411] The terminal displays the proposal to the consultant, who reviews it and makes any necessary corrections. The revised proposal is then sent back to the server.

[1412] Step 9:

[1413] The server then provides the user with a final, revised proposal, which includes specific steps to implement and a recommended action plan, taking into account the user's emotional state.

[1414] Step 10:

[1415] The user receives the final proposal and implements any actionable advice or instructions. If the user provides additional feedback, the cycle begins again, continually improving the quality of the consulting service.

[1416] Example 2

[1417] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1418] Conventional consulting systems have had difficulty generating proposals that take users' emotions into account, making it difficult to provide effective support that increases user satisfaction. Additionally, data preprocessing takes time, making it difficult to respond in real time.

[1419] The specification processing by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for the user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to the consultant terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, and an emotion engine means for recognizing the user's emotions. This makes it possible to quickly generate a proposal that takes the user's emotions into consideration and provide effective support to improve user satisfaction.

[1420] "User" means an individual or corporation that utilizes the system to input a consulting request and seek a solution.

[1421] The "input means" is an interface used by a user to input a consulting request, and may take the form of a web form, an application, or the like.

[1422] "Data collection means" has the function of collecting necessary data from an internal database or external API based on the input information.

[1423] The "preprocessing means" has the function of complementing missing values ​​and removing noise from the collected data, and shaping it into a format suitable for analysis.

[1424] "Data storage means" means a means that has a storage function for efficiently storing and managing preprocessed data, and includes cloud storage.

[1425] The "generation means" has a function of generating specific proposals based on the preprocessed data in accordance with the user's needs.

[1426] The "transmitting means" has a communication function for transmitting the generated proposal to the consultant terminal.

[1427] "Review tools" are functions that allow consultants to check the content of proposals and make necessary corrections, and may use artificial intelligence technology.

[1428] The "feedback means" has the function of returning the final proposal to the user and providing implementation procedures and recommended actions.

[1429] The "emotion engine means" has a function for analyzing emotions from the user's input data and generating a response according to the user's emotional state.

[1430] The present invention is a system that allows users to input a consulting request and generates optimal proposals based on the request. This system also includes an emotion engine that recognizes the user's emotions in real time, improving the user experience.

[1431] Hardware and software used

[1432] The main components of this system are the server, the terminal, and the user, and have the following specific functions:

[1433] Server: Performs data collection, pre-processing, proposal generation, emotion recognition, and proposal transmission. Software used includes natural language processing technology, voice analysis technology, machine learning algorithms, cloud storage, etc.

[1434] Terminal: A review terminal for the consultant, which serves as an interface for the consultant to review and modify the proposal.

[1435] User: A person requesting a consulting business and entering the details of their request via a web form or application.

[1436] Specific circumstances of data processing and calculation

[1437] User Input

[1438] A user enters a consulting request using a web form or application. For example, a request to "improve marketing strategies through customer data analysis" is entered. At this time, an emotion engine is also used to recognize the user's emotional state in real time.

[1439] emotion recognition

[1440] The server starts an emotion engine upon receiving input from the user and analyzes emotions from the user's text input and voice data. The emotion engine uses natural language processing and voice analysis techniques to determine whether the user is feeling stressed, satisfied, or in other emotional states.

[1441] Data collection and preprocessing

[1442] The server receives user input and collects the necessary data based on it. The data source is mainly an internal database or an external API. The collected data undergoes preprocessing, such as processing missing values ​​and removing noise data, and is then stored in a database. This allows the data to be formatted so that it can be easily analyzed by the generating means.

[1443] Proposal generation by generative AI

[1444] The server inputs the stored preprocessed data into a generative AI engine to generate suggestions. The generative AI engine uses machine learning algorithms and natural language processing techniques to create specific suggestions that address the user's needs. The user's emotional state, as determined by the emotion engine, is also reflected in the suggestion's content and tone. For example, if the user is feeling stressed, the suggestion will take on a more supportive tone.

[1445] Consultant review and follow-up

[1446] The proposal sent from the server is displayed on the terminal (consultant device). The consultant reviews the proposal and makes any necessary corrections. After review, the final proposal is fed back to the user. The feedback includes specific implementation steps and a recommended action plan.

[1447] Specific examples

[1448] For example, if a company submits a request to "improve marketing strategies through analysis of customer data," the system operates as follows:

[1449] 1. User Input: A user fills out a web form about "improving marketing strategies through customer data analysis." If the user is feeling anxious, the emotion engine will recognize this.

[1450] 2. Emotion recognition: The server analyzes the user's emotions based on the input and recognizes that the user is feeling anxious.

[1451] 3. Data collection: The server collects relevant data from internal databases and external APIs.

[1452] 4. Preprocessing: The server cleans the collected data and converts it into a format suitable for analysis.

[1453] 5. Recommendation Generation: The generative AI engine analyzes the data and suggests identifying target segments and implementing social media campaigns. This recommendation is written in a supportive tone, taking into consideration the user's concerns.

[1454] 6. Review: The consultant checks the proposal on the terminal and makes any necessary corrections.

[1455] 7. Feedback: Send the final proposal to the user with implementation instructions and recommended actions. Include a specific support plan, as the user is concerned.

[1456] Prompt Sentence Examples

[1457] An example of a prompt to use for system input is:

[1458] 1. "The user requests improvement of their marketing strategy through analysis of customer data. Generate suggestions based on the collected data and the user's emotional state."

[1459] 2. "The user is feeling anxious. Generate support-focused marketing strategy suggestions that take this emotional state into account."

[1460] By combining generative AI technology with an emotion engine, the system of the present invention makes it possible to provide users with advanced and detailed consulting services.

[1461] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1462] Step 1:

[1463] User Input

[1464] A user enters a specific consulting request using a web form or application. For example, the user enters a request such as "I would like to improve my marketing strategy through customer data analysis," and presses the submit button. At this time, the entered text data is sent to the server along with voice data and other contextual information.

[1465] Input: Text data: "I want to improve my marketing strategy through customer data analysis."

[1466] Output: User's consulting request data

[1467] Step 2:

[1468] emotion recognition

[1469] The server analyzes the received user input data and activates an emotion engine. The emotion engine uses natural language processing and speech analysis technologies to evaluate the input text data and voice data and determine the user's emotional state. For example, it can extract an emotional state such as "the user is feeling anxious" from the input text.

[1470] Input: User's consulting request text and voice data

[1471] Output: User's emotional state (e.g., anxiety)

[1472] Step 3:

[1473] Data collection

[1474] The server collects relevant data based on the user's input data and emotional state. This data is mainly obtained from internal databases and external APIs and is included in the required dataset. The data collection takes into account the user's consultation request.

[1475] Input: User's consulting request data and emotional state

[1476] Output: Collected related dataset

[1477] Step 4:

[1478] Data Preprocessing

[1479] The server performs preprocessing on the collected data, including missing value imputation, noise removal, and data shaping and normalization. The preprocessed data is stored in a database and prepared for the generative AI engine to generate suggestions.

[1480] Input: Collected relevant datasets

[1481] Output: Preprocessed data

[1482] Step 5:

[1483] Proposal generation by generative AI

[1484] The server inputs the preprocessed data into a generative AI engine, which generates proposals based on the user's request. The generative AI engine uses machine learning algorithms and natural language processing technology to create specific proposals. At this time, the user's emotional state obtained from the emotion engine is also reflected, resulting in more personalized proposals.

[1485] Input: Preprocessed data and user's emotional state

[1486] Output: Generated concrete consulting proposals

[1487] Step 6:

[1488] Submit a proposal

[1489] The server sends the proposal created by the generative AI engine to the consultant's device, where the proposal is encoded and sent via HTTP or other communication protocol.

[1490] Input: Generated specific consulting proposal

[1491] Output: Proposal data to consultant's terminal

[1492] Step 7:

[1493] Consultant Review

[1494] The terminal (consultant) checks the received proposal and makes corrections as necessary. The consultant checks the appropriateness and details of the proposal and improves the quality of the proposal by correcting any insufficiencies or errors. The corrected proposal is then sent back to the server.

[1495] Input: Proposal data displayed on the consultant's terminal

[1496] Output: Final revised proposal data

[1497] Step 8:

[1498] feedback

[1499] The server receives revised proposals from the consultant and provides the final proposal as feedback to the user, typically via the user's email address or application notification. The proposal includes specific implementation steps and a recommended action plan.

[1500] Input: Revised final proposal data

[1501] Output: Final proposal feedback to the user

[1502] (Application example 2)

[1503] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] Conventional consulting systems were unable to automatically generate proposals based on user-entered requests, and also had difficulty responding to requests that took the user's emotional state into account. Furthermore, while it is important for brick-and-mortar stores to recognize customers' emotions in real time and adjust proposals based on that information, there was a lack of efficient ways to do this. This resulted in lower customer satisfaction and the inability to provide effective proposals.

[1505] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1506] In this invention, the server includes an input means for a user to input a consulting request, a data collection means for collecting related data based on the input information, a preprocessing means for preprocessing the collected data, a data storage means for storing the preprocessed data, a generation means for generating a proposal using the preprocessed data, a transmission means for transmitting the generated proposal to a review terminal, a review means for the consultant to review and modify the proposal content, a feedback means for feeding back the final proposal to the user, an emotion analysis means for recognizing the user's emotion, a proposal adjustment means for adjusting the proposal content based on the emotion analysis means, and an input assistance means for inputting the user's request into smart glasses or a smartphone. This enables flexible responses according to the user's emotional state and real-time customer service in a physical store.

[1507] The "input means for a user to input a consulting request" refers to a means for a user to input a consulting request using a device such as smart glasses or a smartphone.

[1508] The "data collection means for collecting related data based on input information" is a means for automatically collecting necessary related data based on information input by the user.

[1509] The "preprocessing means for preprocessing collected data" refers to a means for removing noise data from collected data, complementing missing values, and converting the data into a format suitable for analysis.

[1510] The "data storage means for storing the preprocessed data" refers to a means for safely and efficiently storing the preprocessed data, and cloud storage may be used.

[1511] The "means for generating a proposal using preprocessed data" refers to a means for generating a proposal suited to a user request based on the preprocessed data.

[1512] The "transmission means for transmitting the generated proposal to the review terminal" is a means for transmitting the generated proposal to a terminal where the consultant can review it.

[1513] The "review means for the consultant to review and modify the proposal content" refers to a means for the consultant to evaluate the generated proposal and modify it as necessary.

[1514] The "feedback means for feeding back the final proposal to the user" is a means for feeding back the final proposal after correction to the user.

[1515] The "emotion analysis means for recognizing the user's emotions" is a means for analyzing emotions from the user's voice or text input and recognizing the user's emotional state, such as stress or satisfaction.

[1516] The "proposal adjustment means for adjusting the proposal content based on the emotion analysis means" is a means for adjusting the proposal content and its tone based on the emotion information obtained from the emotion analysis means.

[1517] The "input assistance means for inputting a user's request into smart glasses or a smartphone" is a means for a user to input a request in real time using smart glasses or a smartphone.

[1518] The present invention is a system for improving the efficiency of customer service in brick-and-mortar stores and enhancing customer satisfaction. This system involves a series of processes in which a user inputs a consulting request using smart glasses or a smartphone, automatically generates a proposal based on the request, and finally provides feedback. The components of the system are as follows:

[1519] Program processing and the hardware and software used

[1520] 1. Input method: The user inputs a consulting request using smart glasses or a smartphone. For example, a customer in a physical store inputs a request such as "I'm looking for a suitable gift item for a wedding." This is done using the touch input or voice input functions of the smart glasses or smartphone.

[1521] 2. Emotion analysis: The server analyzes emotions from user input and voice data. Using the Emotion Engine, it recognizes the customer's emotional state in real time. The results of this analysis are used to determine whether or not support is required.

[1522] 3. Data collection method: The server automatically collects relevant data based on the user's input. The data source is mainly internal databases and external APIs. The data collection here uses the Python requests library.

[1523] 4. Preprocessing: The collected data is not suitable for analysis as it is, so it is preprocessed. This preprocessing includes filling in missing values ​​and removing noise data. For example, data cleaning and standardization of format are performed.

[1524] 5. Proposal generation method: Using the preprocessed data, the generative AI model creates specific proposals. The generative AI engine uses machine learning algorithms and natural language processing techniques to generate proposals that best fit the user's request. The proposal content is also adjusted taking into account the results of sentiment analysis.

[1525] 6. Transmission method: The generated proposal is sent to a device (smart glasses or smartphone) where the consultant can review it. This allows the consultant to check and modify the proposal in real time.

[1526] 7. Review method: The consultant's terminal reviews the proposal and makes any necessary corrections. The proposal may also be evaluated using artificial intelligence technology. At this stage, unnecessary information is removed and important information is added.

[1527] 8. Feedback: The final revised proposal is fed back to the user. This feedback includes implementation procedures and recommended action plans. For example, specific product names and purchasing instructions for "gift items the customer is looking for" are provided.

[1528] Examples of specific examples and prompts

[1529] For example, if a customer requests "I'm looking for a gift item suitable for a wedding" in a physical store and is a little nervous,

[1530] Example prompt sentence:

[1531] The request states, "I'm looking for a gift item suitable for a wedding." At this point, the customer is a little nervous.

[1532] Prompt for generative AI model:

[1533] A request is received saying, "I'm looking for a suitable gift item for a wedding." The customer is in a tense emotional state and is seeking suggestions that emphasize reassuring support.

[1534] This system enables flexible responses based on the user's emotional state and real-time customer support in physical stores, which is expected to improve customer satisfaction.

[1535] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1536] Step 1:

[1537] The user inputs a consulting request using smart glasses or a smartphone. The user enters the request details into an input form within the application, and can also input by voice. For example, the user might input, "I'm looking for a suitable gift item for a wedding." The input data is sent to the server.

[1538] Step 2:

[1539] The server analyzes the received user input data. Using the Emotion Engine, it recognizes the user's emotional state from the input text and voice data. The user's request data is used as input, and the user's emotional state is obtained as output. Specifically, it determines in real time whether the user is nervous or satisfied.

[1540] Step 3:

[1541] The server collects relevant data based on the sentiment analysis results and input data. It uses the Python requests library to automatically retrieve the necessary data from an internal database or external API. The input is the user's request and emotional state, and the output is the retrieved relevant data. For example, it can collect gift item candidates and rating data.

[1542] Step 4:

[1543] The collected data is preprocessed by the server. The preprocessing means complements missing values ​​and removes noise data from the collected data, and converts it into a format suitable for analysis. The collected data is used as input, and preprocessed data is obtained as output. Specific examples include removing duplicate data and standardizing formats.

[1544] Step 5:

[1545] The server uses the preprocessed data to generate a generative AI model to generate suggestions based on the user's request. The suggestion generator uses machine learning algorithms and natural language processing techniques to create appropriate suggestions. The preprocessed data and the results of the sentiment analysis are used as input, and the suggestion content is obtained as output. For example, a list of recommended gift items for a specific gift is generated. The prompt includes the request "I'm looking for gift items suitable for a wedding" and the user's emotional state.

[1546] Step 6:

[1547] The generated proposal is sent by the server to the review device. The consultant checks the proposal using smart glasses or a smartphone, and reviews and modifies it as necessary. The generated proposal is used as input, and a modified proposal is obtained as output. Specifically, the consultant checks the content of the proposal and adds points to be emphasized or supplementary information.

[1548] Step 7:

[1549] The final proposal is fed back to the user by the server. A feedback means provides the user with a revised proposal, including implementation steps and a recommended action plan. The revised proposal is used as input, and feedback is provided to the user as output. Specific feedback may include specific products and purchasing steps for "ideal wedding gift items."

[1550] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1551] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1552] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1553] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1554] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1555] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1556] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1557] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1558] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1559] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1560] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1561] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1562] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1563] 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.

[1564] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1565] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1566] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1567] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1568] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1569] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1570] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1571] The following is further disclosed regarding the above embodiment.

[1572] (Claim 1)

[1573] an input means for a user to input a consulting request;

[1574] a data collection means for collecting related data based on input information;

[1575] a preprocessing means for preprocessing the collected data;

[1576] a data storage means for storing the preprocessed data;

[1577] a generating means for generating suggestions using the preprocessed data;

[1578] a transmitting means for transmitting the generated proposal to the consultant terminal;

[1579] A review mechanism for consultants to review and revise their proposals;

[1580] The system includes a feedback means for feeding back the final proposal to the user.

[1581] (Claim 2)

[1582] The system of claim 1, wherein the data storage means uses cloud storage.

[1583] (Claim 3)

[1584] 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques.

[1585] "Example 1"

[1586] (Claim 1)

[1587] an input means for a user to input a consulting request;

[1588] a data collection means for collecting related data based on input information;

[1589] a preprocessing means for preprocessing the collected data;

[1590] a data storage means for storing the preprocessed data;

[1591] a generating means for generating suggestions using the preprocessed data;

[1592] a transmitting means for transmitting the generated proposal to the consultant terminal;

[1593] A review mechanism for consultants to review and revise their proposals;

[1594] a feedback means for feeding back the final proposal to the user;

[1595] generating means for generating suggestions based on the preprocessed data using a generative artificial intelligence model;

[1596] an input means for inputting data into the generative artificial intelligence model using a prompt sentence;

[1597] A display means for consultants to check and correct the proposals on their terminals,

[1598] A system including:

[1599] (Claim 2)

[1600] The system of claim 1, wherein the data storage means uses cloud storage.

[1601] (Claim 3)

[1602] 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques.

[1603] "Application Example 1"

[1604] (Claim 1)

[1605] an input means for a user to input a consulting request;

[1606] a data collection means for collecting related data based on input information;

[1607] a preprocessing means for preprocessing the collected data;

[1608] a data storage means for storing the preprocessed data;

[1609] a generating means for generating suggestions using the preprocessed data;

[1610] a transmitting means for transmitting the generated proposal to the consultant terminal;

[1611] A review mechanism for consultants to review and revise their proposals;

[1612] a feedback means for feeding back the final proposal to the user;

[1613] additional data collection means for collecting customer behavior data and sales data within the virtual store;

[1614] additional pre-processing means for pre-processing customer behavior data and sales data for use in analysis;

[1615] a strategy generation means for generating a personalized marketing strategy using a generative AI model;

[1616] The system includes a strategy feedback means for providing the generated strategy to the user as a final proposal.

[1617] (Claim 2)

[1618] The system of claim 1, wherein the data storage means uses cloud storage.

[1619] (Claim 3)

[1620] 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques.

[1621] "Example 2: Combining Emotion Engines"

[1622] (Claim 1)

[1623] an input means for a user to input a consulting request;

[1624] a data collection means for collecting related data based on input information;

[1625] a preprocessing means for preprocessing the collected data;

[1626] a data storage means for storing the preprocessed data;

[1627] a generating means for generating suggestions using the preprocessed data;

[1628] a transmitting means for transmitting the generated proposal to the consultant terminal;

[1629] A review mechanism for consultants to review and revise their proposals;

[1630] a feedback means for feeding back the final proposal to the user;

[1631] A system including an emotion engine means for recognizing an emotion of a user.

[1632] (Claim 2)

[1633] The system of claim 1, wherein the data storage means uses cloud storage.

[1634] (Claim 3)

[1635] 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques.

[1636] "Application example 2 when combining emotion engines"

[1637] (Claim 1)

[1638] an input means for a user to input a consulting request;

[1639] a data collection means for collecting related data based on input information;

[1640] a preprocessing means for preprocessing the collected data;

[1641] a data storage means for storing the preprocessed data;

[1642] a generating means for generating suggestions using the preprocessed data;

[1643] a transmitting means for transmitting the generated proposal to the review terminal;

[1644] A review mechanism for consultants to review and revise their proposals;

[1645] a feedback means for feeding back the final proposal to the user;

[1646] emotion analysis means for recognizing the emotion of a user;

[1647] a proposal adjustment means for adjusting the proposal content based on the sentiment analysis means;

[1648] A system including an input assistant for inputting user requests into smart glasses or a smartphone.

[1649] (Claim 2)

[1650] The system of claim 1, wherein the data storage means uses cloud storage.

[1651] (Claim 3)

[1652] 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques. [Explanation of symbols]

[1653] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for a user to input a consulting request; a data collection means for collecting related data based on input information; a preprocessing means for preprocessing the collected data; a data storage means for storing the preprocessed data; a generating means for generating suggestions using the preprocessed data; a transmitting means for transmitting the generated proposal to the consultant terminal; A review mechanism for consultants to review and revise their proposals; The system includes a feedback means for feeding back the final proposal to the user.

2. The system according to claim 1 , wherein the data storage means uses cloud storage.

3. 10. The system of claim 1, wherein the reviewing means evaluates the suggestions from the generating means using artificial intelligence techniques.

Images