system

Abstract

Provide a system. The system includes: a means for allowing a user to input or upload sales-related data; means for storing the sales-related data; a means for analyzing the stored sales-related data; A means for automatically generating sales procedures based on the analysis results; means for generating training materials based on the sales procedures; means for providing said sales procedures and training materials to users; A system including:

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] In order to improve the efficiency and results of sales activities, there is a need to create effective sales procedures and training materials. However, traditional methods require a lot of time and effort, and are heavily dependent on the experience and knowledge of the sales representative, which can lead to a lack of consistency. In addition, it takes time to train new sales representatives, and it takes time for them to become immediately effective. Furthermore, it is difficult to effectively utilize a wide range of customer information and past sales negotiation history, making it difficult to find the optimal sales method. [Means for solving the problem]

[0005] This invention provides a system including means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, and means for providing the sales procedures and training materials to users. This system can improve the efficiency and results of sales activities. Specifically, the system automatically generates effective sales procedures and training materials by analyzing sales-related data using natural language processing technology and applying machine learning algorithms to analyze the data. The system also provides the generated sales procedures and training materials to users so that they can immediately use them in sales activities. This system enables consistent and effective sales techniques to be achieved without relying on the experience or knowledge of sales representatives, helping new sales representatives become immediately effective.

[0006] "Sales-related data" refers to all data related to sales activities, such as customer information, sales history, and business negotiation details.

[0007] The "means for saving" refers to a function for storing sales-related data provided by a user in a storage device.

[0008] "Means of analysis" refers to the function of processing and analyzing collected sales-related data and extracting useful information and patterns.

[0009] A "sales procedure" is a set of step-by-step procedures or guidelines for conducting sales activities effectively.

[0010] "Automatic generation means" refers to the ability to create sales procedures and training materials based on the analysis results without human intervention.

[0011] "Training Materials" refers to educational and training materials for sales representatives to conduct effective sales activities.

[0012] "Means for providing" refers to the function for delivering or presenting the generated sales procedures and training materials to users.

[0013] "Natural language processing technology" is a technology that enables computers to understand, analyze, and process human language.

[0014] A "machine learning algorithm" is an artificial intelligence technology that learns patterns from data and makes predictions and classifications. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] MODE FOR CARRYING OUT THE INVENTION

[0037] The embodiments of the present invention will be described in detail below.

[0038] Overall overview

[0039] This system efficiently collects and analyzes sales-related data, automatically generating optimal sales procedures and training materials, and providing them to users. The server uses natural language processing technology and machine learning algorithms to analyze the data provided by users, and generates sales procedures and training materials based on the results.

[0040] Data collection

[0041] Data input / upload from users

[0042] Users use their devices to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format.

[0043] Data storage

[0044] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[0045] Data analysis

[0046] Data Preprocessing

[0047] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[0048] Text analysis using natural language processing

[0049] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[0050] Applying machine learning models

[0051] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[0052] Automatic generation of sales procedures

[0053] Creating a Procedure Template

[0054] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[0055] Individual optimization

[0056] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[0057] Creating training materials

[0058] Material content generation

[0059] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[0060] Aggregation of related information

[0061] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[0062] Provision to users

[0063] Sending data

[0064] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[0065] User Verification

[0066] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[0067] Specific examples

[0068] For example, a user uses the system in the following scenario.

[0069] 1. Data Collection

[0070] Users upload customer lists and past sales records to the system as CSV files.

[0071] The server receives this data and stores it in a database.

[0072] 2. Data analysis

[0073] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0074] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0075] 3. Automatic generation of sales procedures

[0076] The server generates an optimal sales procedure based on the identified patterns.

[0077] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0078] 4. Creating training materials

[0079] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0080] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0081] 5. Provision to Users

[0082] The server transmits these materials to the user's terminal.

[0083] The user checks the sent materials and prepares for the next business meeting.

[0084] This system allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, thereby improving sales results.

[0085] The processing flow will be explained below.

[0086] Step 1:

[0087] Users use their devices to input or upload sales-related data, such as customer information, sales history, and sales negotiation details, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and sales negotiation details.

[0088] Step 2:

[0089] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[0090] Step 3:

[0091] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[0092] Step 4:

[0093] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[0094] Step 5:

[0095] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[0096] Step 6:

[0097] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0098] Step 7:

[0099] The server generates training materials based on individually optimized sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[0100] Step 8:

[0101] The server sends the generated sales procedures and training materials to the user's device. The user can check these materials on the device and download or print them as needed. This allows the user to refer to them while proceeding with their sales activities.

[0102] Example 1

[0103] 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."

[0104] Conventional sales-related data collection and analysis systems require a lot of time and effort for manual data entry and analysis, and the generation of specific sales procedures and training materials based on analysis results is not automated, making it difficult to support efficient sales activities.Furthermore, it is difficult to optimize the systems to suit the specific circumstances of individual users and customers, resulting in a lack of versatility.

[0105] 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.

[0106] In this invention, the server includes means for allowing a user to input or upload information, means for saving the information, means for preprocessing the saved information, means for analyzing the preprocessed information using natural language processing technology, means for analyzing the analyzed information using a machine learning algorithm, means for automatically generating business procedures based on the analysis results, means for generating training materials based on the business procedures, and means for providing the business procedures and training materials to users. This enables efficient collection and analysis of sales-related data and automatic generation of optimized procedures and training materials.

[0107] A "user" is a person or entity that operates the system and inputs or uploads information.

[0108] "Information" refers to a wide range of data, including sales-related data such as customer information, past sales history, and business negotiation details.

[0109] "Server" means an integrated hardware and software system that stores, pre-processes, parses, and analyzes information sent by users, and generates and provides business procedures and training materials based on the results.

[0110] "Input or Upload Means" refers to the interface or protocol by which a user provides information to the system.

[0111] "Storage" refers to techniques and devices that record received information in a persistent storage medium, such as a database.

[0112] "Preprocessing means" refers to the process of converting stored information into a format suitable for analysis by completing missing values, removing duplicate data, normalizing data, etc.

[0113] "Means of analysis using natural language processing technology" refers to the process of analyzing text data using technologies such as tokenization, part-of-speech tagging, and contextual analysis.

[0114] "Methods of analysis using machine learning algorithms" refers to the process of statistically analyzing information to identify patterns and trends using various machine learning techniques, such as regression analysis and cluster analysis.

[0115] "Means for automatically generating business procedures" refers to the process by which the system automatically generates specific and optimal sales procedures based on the analysis results of natural language processing technology and machine learning algorithms.

[0116] "Means for generating educational materials" refers to the process of creating learning content such as sales negotiation simulations, FAQs, and success stories based on the generated business procedures.

[0117] "Means for providing" refers to the process of transmitting the generated business procedures and training materials to the user's terminal so that the user can view, download, and print them.

[0118] The present invention relates to a system for collecting and analyzing sales-related data and automatically generating optimal sales procedures and training materials. A specific embodiment of this system will be described below.

[0119] The server is equipped with an input means for receiving information provided by users. Users use their terminals to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files or JSON format.

[0120] The server has a storage means for securely storing the received information, which is then stored in a database (e.g., MySQL (registered trademark) or PostgreSQL) for subsequent analysis.

[0121] The server then uses Python's Pandas library to preprocess the stored information, which includes data cleaning (imputing missing values, removing duplicates), normalization, and other steps to convert the data into a format suitable for analysis.

[0122] The preprocessed information is then analyzed using natural language processing (NLP) techniques. This analysis involves tokenization, part-of-speech tagging, and contextual analysis using NLP libraries such as NLTK and Spacy. For example, a text such as "Describes the technical characteristics of a new product" is broken down into "New product / noun, technical / adjective, characteristics / noun, description / verb."

[0123] The server then applies machine learning algorithms (e.g., Scikit-learn or TENSORFLOW®) to analyze the information. This analysis includes regression analysis and cluster analysis, which can identify common factors in successful deals. For example, clusters can be generated based on past deal results to identify patterns of success.

[0124] Based on the analysis results, the server automatically generates business procedures. It uses a template engine such as Jinja2 to create a basic sales procedure template, and then individually optimizes the template according to the circumstances of the user and specific customer. For example, a procedure that provides a detailed technical overview of a new product for repeat customers could be included.

[0125] Based on the sales procedures, the server generates training materials, including sales negotiation simulations, FAQs, success stories, etc. For example, specific training content such as "frequently asked questions and answers about the technical specifications of a new product" is created.

[0126] The training materials also aggregate relevant supporting materials and reference links, including instructional videos and white papers, all centralized within one system.

[0127] Finally, the server sends the generated business procedures and training materials to the user's device, where the user can review, download, and print the received materials, allowing them to efficiently prepare for the next business meeting.

[0128] For example, consider a scenario in which a user uploads a customer list or past sales negotiation records to the system as a CSV file. The server then receives this data, stores it in a database, and performs analysis. As a specific example, it identifies a pattern that "explaining new products with emphasis on their technical details is effective for repeat customers," and incorporates a procedure that "explains the technical specifications of new products in detail when first contacted." It also generates training materials that include "frequently asked questions and answers about the technical specifications of new products," and provides them to users.

[0129] This allows users to conduct sales activities efficiently and quickly obtain optimal procedures and training materials.

[0130] Prompt Sentence Examples

[0131] "Upload a CSV file containing your customer list and generate the optimal sales procedures. Provide us with the generated procedures and training materials."

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Processing flow and each processing step

[0134] Step 1: Enter and collect data

[0135] User Action:

[0136] Users use their terminal to upload sales-related data such as customer information, past sales history, and sales negotiation details in CSV or JSON format.

[0137] input:

[0138] A CSV file containing data such as customer name, contact details, deal date, details, and results.

[0139] output:

[0140] The uploaded data file is sent to the server.

[0141] Specific behavior:

[0142] The user fills in the required fields in the data entry form on the web interface, selects the file, and clicks the upload button.

[0143] Step 2: Save your data

[0144] Server behavior:

[0145] The server securely stores the received data in a database (MySQL or PostgreSQL).

[0146] input:

[0147] CSV file or JSON data submitted by the user.

[0148] output:

[0149] Well-formed data stored in a database.

[0150] Specific behavior:

[0151] The server parses the contents of the file and stores it in a specific table in the database by executing an insert query.

[0152] Step 3: Preprocessing the data

[0153] Server behavior:

[0154] The server preprocesses the stored data using Python's Pandas library.

[0155] input:

[0156] Raw data stored in a database.

[0157] output:

[0158] Cleaned data with missing values ​​imputed and duplicates removed.

[0159] Specific behavior:

[0160] The server loads the data into a data frame, normalizes it by imputing missing values ​​with the mean and removing duplicates.

[0161] Step 4: Text analysis using natural language processing

[0162] Server behavior:

[0163] The server uses NLP libraries such as NLTK and Spacy to analyze the text data.

[0164] input:

[0165] Cleaned text data.

[0166] output:

[0167] Analysis results extracting important keywords and topics.

[0168] Specific behavior:

[0169] The server tokenizes the text data, tags it with parts of speech, and performs contextual analysis, breaking down, for example, "Describe the technical characteristics of a new product" into "New product / noun technical / adjective characteristics / noun description / verb."

[0170] Step 5: Analysis with machine learning models

[0171] Server behavior:

[0172] The server uses Scikit-learn and TensorFlow to analyze the data with machine learning algorithms.

[0173] input:

[0174] NLP text analysis results and cleaned numerical data.

[0175] output:

[0176] Analysis results that identify patterns and common factors in successful deals.

[0177] Specific behavior:

[0178] The server performs regression and cluster analysis to find successful patterns and generate clusters based on specific criteria.

[0179] Step 6: Automatic generation of business procedures

[0180] Server behavior:

[0181] The server uses a template engine such as Jinja2 to create templates for basic sales procedures and individually optimize them.

[0182] input:

[0183] Machine learning analysis results and templates.

[0184] output:

[0185] Sales playbooks optimized for users and specific customers.

[0186] Specific behavior:

[0187] The server embeds variables into the template and dynamically changes the content depending on the user's specific situation.

[0188] Step 7: Generate training material

[0189] Server behavior:

[0190] The server creates training materials based on the generated sales procedures.

[0191] input:

[0192] Customized sales procedures.

[0193] output:

[0194] Training materials including sales simulations, FAQs, success stories, and more.

[0195] Specific behavior:

[0196] The server formats the training material in Markdown or HTML and generates the specific content.

[0197] Step 8: Expanding training materials

[0198] Server behavior:

[0199] The server collects relevant supplementary material and reference links to add to the training materials.

[0200] input:

[0201] Generated training materials.

[0202] output:

[0203] Comprehensive training material with additional supplementary materials and reference links.

[0204] Specific behavior:

[0205] The server collects links to relevant videos and white papers and inserts them into the appropriate parts of the training materials.

[0206] Step 9: Send data and confirm with the user

[0207] Server behavior:

[0208] The server transmits the generated work procedure manual and training materials to the user's terminal.

[0209] input:

[0210] Final generated sales procedures and training materials.

[0211] output:

[0212] Materials sent to the user's device.

[0213] Specific behavior:

[0214] The server delivers the materials to users via email or a dedicated web portal.

[0215] Step 10: User validation and utilization

[0216] User Action:

[0217] The user checks the sent materials and downloads or prints them as necessary.

[0218] input:

[0219] Sales procedures and training materials sent from the server.

[0220] output:

[0221] Action items for users who are ready to close a deal.

[0222] Specific behavior:

[0223] Users can download materials, print them out for the next business meeting, and begin concrete preparations.

[0224] (Application example 1)

[0225] 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."

[0226] In sales activities, it is difficult to effectively use customer information and past sales history to determine the optimal sales procedure. In particular, in virtual stores, it is necessary to provide sales representatives with the optimal sales pitch and materials in real time and respond quickly. With traditional methods, these processes are highly manual, requiring time and effort, making it difficult to conduct efficient sales activities.

[0227] 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.

[0228] In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, and means for analyzing the sales data in real time and providing optimal sales pitches and materials to sales representatives of the virtual store in real time, thereby making it possible to improve the efficiency and accuracy of sales activities.

[0229] "User" refers to a person who uses the System to input or upload sales-related data.

[0230] "Sales-related data" refers to data related to sales activities, such as customer information, past sales history, and sales negotiation details.

[0231] "Storage Measures" means software or hardware for securely and efficiently storing collected business-related data.

[0232] "Analysis Tools" refers to software or hardware for analyzing collected and stored business-related data.

[0233] A "sales procedure" refers to a series of steps that indicate the optimal procedure for sales activities.

[0234] "Automatic generation means" refers to software or hardware for automatically generating sales procedures based on the results of data analysis.

[0235] "Training Materials" means the educational content and materials necessary to perform the Sales Procedures.

[0236] "Delivery means" refers to software or hardware for delivering the generated sales procedures and training materials to users.

[0237] "Real-time analysis" refers to the process of instantly analyzing collected data and providing the results in real time.

[0238] A "virtual store" refers to an online platform that conducts business over the Internet, rather than a physical store.

[0239] "Sales talk" refers to sales statements and explanations used during business negotiations with customers.

[0240] "Real-time delivery means" refers to software or hardware used to provide analysis results, sales pitches, and materials to sales representatives in real time.

[0241] MODE FOR CARRYING OUT THE INVENTION

[0242] Overall overview

[0243] This system efficiently stores and analyzes sales-related data collected from users, automatically generates optimal sales procedures and training materials, and also provides optimal sales pitches and materials to salespeople in real time in the virtual store.

[0244] Data collection

[0245] Data input / upload from users

[0246] Users use their terminals to input or upload sales-related data such as customer information, past sales history, and details of sales negotiations into the system. This data is generally provided in CSV or JSON format.

[0247] Data storage

[0248] The server receives the sales-related data sent by the user and stores it safely and efficiently. The stored data is recorded in a database and appropriately managed for later analysis.

[0249] Data analysis

[0250] Data Preprocessing

[0251] The server preprocesses the stored data, specifically by cleaning it by filling in missing values ​​and removing duplicate data, and converting it into a data format suitable for analysis.

[0252] Text analysis using natural language processing

[0253] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[0254] Applying machine learning models

[0255] The server analyzes the data using machine learning algorithms, specifically regression and cluster analysis, to identify which sales techniques were most effective.

[0256] Automatic generation of sales procedures

[0257] Creating a Procedure Template

[0258] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[0259] Individual optimization

[0260] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[0261] Creating training materials

[0262] Material content generation

[0263] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and their answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[0264] Aggregation of related information

[0265] The server aggregates supplemental materials and reference links related to the generated training materials, including instructional videos and white papers.

[0266] Real-time sales talk

[0267] Real-time analytics

[0268] Salespeople in the virtual store receive assistance from the system when negotiating with customers in real time. The server analyzes sales data in real time and provides optimal sales pitches and materials.

[0269] Real-time delivery method

[0270] The server sends the analysis results, sales pitches, and materials to the sales representative's device in real time, allowing the sales representative to respond quickly and appropriately.

[0271] Provision to users

[0272] Sending data

[0273] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[0274] User Verification

[0275] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[0276] Specific examples

[0277] For example, a user uses the system in the following scenario.

[0278] 1. Data Collection

[0279] Users upload customer lists and past sales records to the system as CSV files.

[0280] The server receives this data and stores it in a database.

[0281] 2. Data analysis

[0282] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0283] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0284] 3. Automatic generation of sales procedures

[0285] The server generates an optimal sales procedure based on the identified patterns.

[0286] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0287] 4. Creating training materials

[0288] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0289] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0290] 5. Real-time assistance

[0291] During sales negotiations in the virtual store, the server provides sales representatives with the most appropriate sales pitches and materials in real time based on the analysis results.

[0292] 6. Provision to Users

[0293] The server transmits these materials to the user's terminal.

[0294] The user checks the sent materials and prepares for the next business meeting.

[0295] Prompt Sentence Examples

[0296] Enter customer information and past sales history data. We will generate the optimal sales procedure based on this data. Upload the data in CSV format or enter it directly in the app.

[0297] This invention allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, and also enables the virtual store to provide optimal sales pitches and materials in real time.

[0298] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0299] Step 1: Data collection

[0300] Input: The user inputs customer information and past sales history data into the system using a terminal or uploads it as a CSV file.

[0301] Processing: The terminal receives the input data, converts it into an appropriate format, and sends it to the server.

[0302] Output: The server records the received data in a storage database.

[0303] Step 2: Save data

[0304] Input: Sales-related data received by the server.

[0305] Processing: The server securely stores the received data in a database, taking appropriate security measures when storing the data.

[0306] Output: The saved data is organized for later analysis.

[0307] Step 3: Data Preprocessing

[0308] Input: Sales-related data stored on the server.

[0309] Processing: The server cleans the data by imputing missing values, removing duplicates, etc. It also normalizes the data into a format that is easier to analyze.

[0310] Output: Preprocessed and formatted data suitable for analysis.

[0311] Step 4: Text analysis using natural language processing

[0312] Input: Preprocessed text data (e.g., business negotiation details).

[0313] Processing: The server analyzes the text data using natural language processing techniques (e.g., spaCy), performing tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics.

[0314] Output: Extracted keywords and topic information.

[0315] Step 5: Applying the machine learning model

[0316] Input: Preprocessed sales data and extracted keyword and topic information.

[0317] Processing: The server analyzes the data using machine learning algorithms (e.g., cluster analysis and regression analysis) to identify which sales techniques are most effective.

[0318] Output: A pattern of optimal sales techniques.

[0319] Step 6: Auto-generate sales procedures

[0320] Input: Optimal sales technique patterns.

[0321] Processing: The server generates a basic sales procedure template based on the analysis results and customizes it for specific customers and industries.

[0322] Output: Customized sales procedures.

[0323] Step 7: Create training materials

[0324] Input: Customized Sales Procedure.

[0325] Processing: The server generates training materials including sales negotiation simulations and FAQs based on sales procedures, and also aggregates related supplementary materials and reference links.

[0326] Output: The completed training material.

[0327] Step 8: Real-time analytics and sales pitches

[0328] Input: Real-time customer data and sales rep requests.

[0329] Processing: The server analyzes customer data collected in real time and provides optimal sales pitches and materials based on the latest sales techniques and materials.

[0330] Output: Sales pitches and materials provided in real time.

[0331] Step 9: Provide to users

[0332] Input: Generated sales procedures and training materials.

[0333] Processing: The server sends these materials to the user's terminal.

[0334] Output: The user checks the sent materials and downloads or prints them as needed.

[0335] This enables the system to improve the efficiency and accuracy of sales activities.

[0336] 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.

[0337] MODE FOR CARRYING OUT THE INVENTION

[0338] The embodiments of the present invention will be described in detail below.

[0339] Overall overview

[0340] This system efficiently collects and analyzes sales-related data, automatically generates optimal sales procedures and training materials, and provides them to users. In particular, by combining it with an emotion engine that recognizes the user's emotions, it realizes more advanced and personalized sales techniques.

[0341] Data collection

[0342] Data input / upload from users

[0343] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[0344] Data storage

[0345] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[0346] Data analysis

[0347] Data Preprocessing

[0348] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[0349] Text analysis using natural language processing

[0350] The server analyzes the text data using natural language processing (NLP) techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from, for example, a business meeting transcript.

[0351] Applying machine learning models

[0352] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[0353] Automatic generation of sales procedures

[0354] Creating a Procedure Template

[0355] The server creates a basic sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0356] Individual optimization

[0357] The server customizes the template to suit each user's or customer's specific circumstances, optimizing, for example, providing technical details first for customers in a particular industry.

[0358] Utilizing the Emotion Engine

[0359] emotion recognition

[0360] The emotion engine is designed to recognize user emotions. It uses natural language processing technology to determine emotions from text and voice data entered by the user. For example, it can identify user emotions such as "interested," "distrustful," or "satisfied" from text data during a business negotiation.

[0361] Sentiment Data Analysis

[0362] The server analyzes the emotional data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if the user has a "distrustful" feeling, it adds procedures to provide more detailed information or strengthen follow-up.

[0363] Creating training materials

[0364] Material content generation

[0365] The server generates training material content based on the sales process, including sales simulations, frequently asked questions and answers, and success stories, including stories of successful calls that highlight technical details.

[0366] Aggregation of related information

[0367] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[0368] Provision to users

[0369] Sending data

[0370] The server sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[0371] User Verification

[0372] The user can check the sent materials and prepare for the next business meeting. For example, the user can print out a procedure manual to use on-site in preparation for the next business meeting.

[0373] Specific examples

[0374] For example, a user uses the system in the following scenario.

[0375] 1. Data Collection

[0376] Users upload customer lists and past sales records to the system as CSV files.

[0377] The server receives this data and stores it in a database.

[0378] 2. Data analysis

[0379] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0380] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0381] 3. Automatic generation of sales procedures

[0382] The server generates an optimal sales procedure based on the identified patterns.

[0383] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0384] 4. Creating training materials

[0385] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0386] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0387] 5. Applying the Emotion Engine

[0388] The emotion engine analyzes the user's emotions in real time during a business negotiation.

[0389] For example, if a user is feeling unsure during a sales conversation, the system can detect this and generate instructions to strengthen follow-up procedures.

[0390] 6. Provision to Users

[0391] The server transmits these materials to the user's terminal.

[0392] The user checks the sent materials and prepares for the next business meeting.

[0393] This system allows users to quickly obtain procedures and training materials for efficient sales activities, thereby improving sales results. In addition, by utilizing an emotion engine, it is possible to realize more personalized sales methods and improve customer satisfaction.

[0394] The processing flow will be explained below.

[0395] Step 1:

[0396] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[0397] Step 2:

[0398] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[0399] Step 3:

[0400] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[0401] Step 4:

[0402] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[0403] Step 5:

[0404] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[0405] Step 6:

[0406] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0407] Step 7:

[0408] The server uses an emotion engine to analyze the user's emotions in real time. For example, it analyzes the user's text messages and voice data during a business meeting to determine whether the user is feeling "interested," "distrustful," or "satisfied."

[0409] Step 8:

[0410] The server analyzes the emotion data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if a user is feeling "distrustful," the server can detect this and generate instructions to strengthen follow-up procedures.

[0411] Step 9:

[0412] The server creates training materials based on the automatically generated sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[0413] Step 10:

[0414] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[0415] Step 11:

[0416] The user can check the sent materials and prepare for the next business meeting. For example, to prepare for the next business meeting, the user can print out a procedure manual and use it on-site. In this way, the user can conduct sales activities efficiently and effectively.

[0417] Example 2

[0418] 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."

[0419] There is a need for systems that can more effectively support sales activities by efficiently collecting, storing, and analyzing sales-related data, and automatically generating sales procedures and training materials. However, existing systems have not adequately performed data preprocessing and customization, or individual optimization based on user emotion recognition, which has led to problems in not improving sales efficiency and customer satisfaction.

[0420] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0421] In this invention, the server includes: means for allowing a user to input or upload sales-related data; means for saving the sales-related data; means for preprocessing the saved sales-related data; means for analyzing the saved data using natural language processing technology; means for analyzing the sales-related data by applying a machine learning algorithm; means for automatically generating sales procedures based on the analysis results; means for customizing the generated sales procedures according to the specific circumstances of each user and their customers; means for determining emotions from text data or voice data entered by the user; means for adjusting sales procedures and training materials based on the emotion data; means for generating training materials based on the sales procedures; means for aggregating supplementary materials and reference links related to the training materials; and means for providing the sales procedures and training materials to users. This centralizes the collection, storage, and analysis of sales-related data, making it possible to provide personalized sales methods utilizing emotion recognition.

[0422] "User" means any individual or legal entity that uses the System to input or upload business-related data.

[0423] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[0424] "Data preprocessing" refers to a series of processes to improve data quality, such as filling in missing values, correcting outliers, and removing duplicate data.

[0425] "Natural language processing technology" refers to technology for processing human language using computers, and includes tokenization, part-of-speech tagging, context analysis, etc.

[0426] A "machine learning algorithm" is an algorithm that finds patterns and relationships in data and makes predictions and classifications.

[0427] "Sales procedures" refer to the steps and processes for effectively carrying out sales activities, and include, for example, the flow of "initial contact → needs assessment → proposal → follow-up."

[0428] "Training materials" are educational materials created based on sales procedures, and include sales negotiation simulations, FAQs, success stories, etc.

[0429] "Emotion recognition" refers to the technology of determining emotions from a user's text data or voice data using natural language processing technology, etc.

[0430] "Related information aggregation" refers to the process of collecting supplementary materials and reference links related to training material and providing them as a single resource.

[0431] "Storage" means recording and securely storing entered or uploaded data in a database.

[0432] "Providing" refers to transmitting the generated sales procedures and training materials to the user and making them available to the user.

[0433] MODE FOR CARRYING OUT THE INVENTION

[0434] Overall overview

[0435] This system efficiently collects, stores, and analyzes sales-related data entered or uploaded by users, and automatically generates optimal sales procedures and training materials. Furthermore, it utilizes an emotion engine to recognize users' emotions and provide personalized sales techniques and training accordingly.

[0436] System configuration

[0437] This system consists of a user terminal, a server, a database, a natural language processing engine, a machine learning algorithm, an emotion recognition engine, and a user interface (UI).

[0438] Data collection

[0439] Users use their devices to input or upload sales-related data such as customer information, sales history, and details of business negotiations. The data is provided in standard CSV or JSON format. For example, it includes fields such as "customer name," "contact information," "sales negotiation date and time," and "sales negotiation details."

[0440] Data storage

[0441] The server receives sales-related data sent by users in real time and stores it securely in a database. The stored data is used for subsequent analysis and procedure generation, while also ensuring data integrity and security.

[0442] Data Preprocessing

[0443] The server preprocesses the sales-related data stored in the database, including cleaning tasks such as imputing missing values, correcting outliers, and removing duplicate data, as well as normalizing the data into a format suitable for analysis.

[0444] Text data analysis

[0445] The server uses a natural language processing engine to analyze the text data of the sales negotiation records. Specifically, it tokenizes the text, tags it for parts of speech, and performs context analysis. For example, it extracts "factors that lead to the success of a sales negotiation" from the sales negotiation records.

[0446] Applying machine learning algorithms

[0447] The server analyzes the data using machine learning algorithms, conducting regression analysis and cluster analysis to identify which sales techniques are most effective. For example, it can identify patterns in sales negotiations that resulted in high customer satisfaction.

[0448] Automatic generation of sales procedures

[0449] Based on the analysis results, the server generates a sales procedure template, which may include steps such as "initial contact," "needs assessment," "proposal," and "follow-up." This template is customized to fit the specific needs of the user.

[0450] Individual optimization

[0451] The server customizes the automatically generated sales procedure according to the specific circumstances of each user and their customer, for example, optimizing it to provide technical details to customers who are highly interested in technology at an early stage.

[0452] Utilizing the Emotion Engine

[0453] The server uses an emotion recognition engine to determine the user's emotions from the text and voice data they provide. For example, if the server determines that the user is distrustful, it will adjust the system to provide more detailed explanations and follow-up procedures.

[0454] Creating training materials

[0455] The server generates training materials based on the automatically generated sales procedures, including sales simulations, FAQs, and success stories, such as "Frequently Asked Questions and Answers about the Technical Specifications of a New Product."

[0456] Aggregation of information related to training materials

[0457] The server aggregates supplemental materials and reference links related to the generated training materials, for example, educational videos about the technical background of the product.

[0458] Sending data

[0459] The server then sends the generated sales procedure manual and training materials to the user's terminal, where the user can review these materials and prepare for the next business negotiation.

[0460] Specific examples

[0461] For example, a user can upload a "customer list" and "past sales negotiation records" to the system in CSV file format. The server receives this data, stores it in a database, and performs preprocessing. NLP technology is then used to analyze the text data and extract important keywords and patterns. A machine learning algorithm identifies the optimal sales method and generates a procedure, such as "explain the technical specifications of a new product in detail during the first contact."

[0462] Prompt Sentence Examples

[0463] The following prompts may be used:

[0464] "Analyze the data uploaded by users and generate the optimal sales method."

[0465] "Detect sentiment from text data entered by users during sales conversations and optimize procedures based on that."

[0466] In this way, the system efficiently and effectively supports sales activities and provides users with optimal sales procedures and training materials.

[0467] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0468] Step 1:

[0469] Users use their devices to input or upload sales-related data. Input includes customer information, sales history, and details of business negotiations, and is provided in CSV or JSON format. Specifically, users specify the data file through the device's user interface and click the upload button.

[0470] Input: Customer information, sales history, business details (CSV file or JSON format)

[0471] Output: Sales-related data sent from the user's device

[0472] Step 2:

[0473] The server receives sales-related data sent by users in real time and stores it in a database. The server first verifies the format and content of the data, and then securely records it in the database.

[0474] Input: Sales-related data sent from the user's terminal

[0475] Output: Sales-related data stored in a database

[0476] Step 3:

[0477] The server preprocesses the sales-related data stored in the database, specifically cleaning the data (e.g., filling in missing values, correcting outliers, removing duplicates), normalizing it, and converting it into a format suitable for analysis.

[0478] Input: Sales-related data stored in a database

[0479] Output: Preprocessed sales-related data

[0480] Step 4:

[0481] The server then analyzes the pre-processed data using natural language processing (NLP) techniques, such as text tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from the sales meeting notes.

[0482] Input: Pre-processed sales-related data

[0483] Output: Analysis results (extracted keywords, topics)

[0484] Step 5:

[0485] The server then applies machine learning algorithms to further analyze the stored sales-related data, for example, using regression analysis and cluster analysis to identify which sales techniques were most effective.

[0486] Input: Pre-processed sales-related data

[0487] Output: Machine learning analysis results (identification of effective sales methods)

[0488] Step 6:

[0489] The server automatically generates a sales procedure template based on the analysis results, for example, a template including general steps such as "initial contact → needs assessment → proposal → follow-up."

[0490] Input: Machine learning analysis results

[0491] Output: Sales Procedure Template

[0492] Step 7:

[0493] The server customizes the generated sales procedures to the specific circumstances of each user and their customer, for example, creating procedures tailored to customers in a particular industry by providing technical details upfront.

[0494] Input: Sales procedure template, customer information

[0495] Output: Customized sales procedures

[0496] Step 8:

[0497] The server uses an emotion recognition engine to determine emotions from the text and voice data entered by the user, identifying emotions such as "interested," "distrustful," and "satisfied," and adjusting sales procedures accordingly.

[0498] Input: Text data and voice data entered by the user

[0499] Output: Emotion recognition result

[0500] Step 9:

[0501] The server can then use the emotional data to adjust sales procedures and training materials, for example adding steps to strengthen follow-up if the user is "distrustful."

[0502] Input: Emotion recognition results, customized sales procedures

[0503] Output: Adjusted sales procedures

[0504] Step 10:

[0505] The server generates training materials based on the adjusted sales procedures, such as sales negotiation simulations, FAQs, and success stories.

[0506] Input: Adjusted Sales Procedures

[0507] Output: Generated training material

[0508] Step 11:

[0509] The server aggregates supplementary materials and reference links related to the generated training materials, for example, educational videos and white papers, and adds them to the training materials provided.

[0510] Input: Generated training material

[0511] Output: Training materials with supplementary materials and reference links

[0512] Step 12:

[0513] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can review the materials and prepare for the next sales meeting.

[0514] Input: Training materials with supplementary materials and reference links

[0515] Output: Data sent to the user's device

[0516] This is the specific process flow. This system allows users to receive the information and support they need to efficiently carry out their sales activities in a timely manner.

[0517] (Application example 2)

[0518] 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."

[0519] In sales activities, data collection and analysis are essential for quickly and efficiently understanding customer needs. However, conventional systems did not adequately analyze sales-related data or recognize emotions, making it difficult to provide appropriate sales techniques and training materials. Furthermore, they were unable to recognize customer emotions during the sales process in real time and adjust sales procedures accordingly, preventing improvements in sales efficiency and customer satisfaction.

[0520] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, an emotion engine that recognizes the user's emotions during the sales process in real time, and means for analyzing emotion data obtained by the emotion engine and adjusting the sales procedures. This makes it possible to efficiently analyze sales-related data and provide a personalized sales methodology based on the user's emotions.

[0521] "User" means any individual or legal entity that inputs or uploads business-related data.

[0522] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[0523] "Means for inputting or uploading" refers to a function that allows a user to input or upload sales-related data into the system.

[0524] "Means for storage" refers to the system's ability to securely store entered sales-related data.

[0525] "Means for analysis" refers to the function for analyzing stored sales-related data and extracting meaningful information.

[0526] "Means for automatic generation" refers to a function for automatically creating sales procedures based on the analysis results.

[0527] "Means for generating" refers to the function for creating training materials based on sales procedures.

[0528] "Means for providing" refers to a function for presenting the generated sales procedures and training materials to the user.

[0529] An "emotion engine" refers to a system that recognizes a user's emotions in real time and analyzes the data.

[0530] "Means for adjustment" refers to the function for appropriately adjusting sales procedures based on the emotional data obtained by the emotion engine.

[0531] Overall overview

[0532] This invention is a system that collects sales-related data from users and efficiently stores and analyzes it. Based on the analysis results, the system automatically generates optimal sales procedures and training materials and provides them to users. Furthermore, by combining it with an emotion engine, personalized sales techniques based on the user's emotions become possible.

[0533] Program structure and processing

[0534] 1. Data Collection

[0535] Users input or upload sales-related data such as customer information, sales history, and details of business negotiations through a smartphone application. This data is provided in JSON format and sent to the server.

[0536] 2. Data storage

[0537] The server securely stores the received sales-related data in a database such as MongoDB, where it is used for later analysis.

[0538] 3. Data analysis

[0539] The server uses the Google® Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques, including tokenization, part-of-speech tagging, and contextual analysis.

[0540] 4. Applying machine learning models

[0541] The server uses machine learning algorithms such as TensorFlow to analyze the data, specifically using clustering algorithms (e.g., KMeans) to identify which sales tactics were effective.

[0542] 5. Automatic generation of sales procedures

[0543] The server automatically generates optimal sales procedures based on the analysis results, for example, formulating a procedure such as "explaining the technical specifications of a new product in detail when first contacting the customer."

[0544] 6. Creating training materials

[0545] The server creates training materials based on the generated sales procedures, including sales negotiation simulations, FAQs, and success stories.

[0546] 7. Leveraging Emotional Engines

[0547] The emotion engine uses the IBM Watson® Emotion Analysis API to recognize user emotions in real time, for example, detecting disbelief during a sales meeting and adjusting follow-up procedures.

[0548] 8. Provision to Users

[0549] The server sends the generated sales procedure manual and training materials to the user's terminal, where the user can review the materials and prepare for the next business meeting.

[0550] Specific examples

[0551] 1. Data Collection

[0552] The user uploads a customer list and past sales records in JSON format from a smartphone application.

[0553] 2. Emotion recognition

[0554] Based on the text data during the business negotiation, the emotion engine determines the user's emotion as "interested."

[0555] 3. Sales procedure generation

[0556] The procedure "explain the technical specifications of a new product in detail" is automatically generated and provided to the user.

[0557] Prompt Sentence Examples

[0558] To prepare for the next sales meeting, propose a procedure to stimulate the customer's interest in a new product. Analyze customer information, sales history, and sales content data, and take into account emotion recognition to provide the optimal sales procedure. If the customer is determined to be interested, generate a procedure to provide technical details.

[0559] This system allows sales representatives to quickly access procedures and training materials to conduct sales activities efficiently, and the emotional engine enables personalized sales techniques, which is expected to improve customer satisfaction.

[0560] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0561] Step 1:

[0562] Users use a smartphone application to input or upload sales-related data such as customer information, sales history, and sales negotiation details in JSON format. Input includes customer name, contact information, sales negotiation date and time, sales negotiation details, etc. The output is JSON format data sent to the server.

[0563] Step 2:

[0564] The server receives sales-related data and stores it in a database such as MongoDB. The server keeps the data consistent and secure, and stores it for future analysis. The input is the JSON-formatted data sent by the user, and the output is the sales-related data securely stored in the database.

[0565] Step 3:

[0566] The server uses the Google Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and context analysis. The input is the text data stored in the database, and the output is the analysis result, tokenized and part-of-speech tagged text data.

[0567] Step 4:

[0568] The server applies machine learning algorithms such as TensorFlow to analyze the data. Specifically, it uses clustering algorithms (e.g., KMeans) to identify patterns of successful sales techniques. The input is tokenized and part-of-speech tagged text data, and the output is a list of clustered patterns.

[0569] Step 5:

[0570] The server automatically generates optimal sales procedures based on the analysis results. For example, it formulates a specific procedure such as "explaining the technical specifications of a new product in detail during the first contact." The input is a list of clustered patterns, and the output is an automatically generated sales procedure manual.

[0571] Step 6:

[0572] The server creates training materials based on the generated sales procedures. Specifically, it creates training materials that include sales negotiation simulations, FAQs, stories of success cases, etc. The input is the automatically generated sales procedures manual, and the output is the completed training materials.

[0573] Step 7:

[0574] The emotion engine uses the IBM Watson Emotion Analysis API to recognize user emotions in real time. The targets for emotion recognition include text and voice data from business negotiations. The input is text and voice data acquired in real time, and the output is analyzed emotion data (e.g., "interested" or "distrustful").

[0575] Step 8:

[0576] The server analyzes the emotion data obtained by the emotion engine and adjusts the sales procedure. For example, if "distrust" is determined to be high, it generates instructions to strengthen follow-up procedures. The input is emotion data from the emotion engine, and the output is an adjusted sales procedure.

[0577] Step 9:

[0578] The server sends the generated and adjusted sales procedures and training materials to the user's terminal. The user checks these materials and prepares for the next business meeting. The adjusted sales procedures and training materials are obtained as input, and the materials displayed on the user's terminal are obtained as output.

[0579] 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.

[0580] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0581] 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.

[0582] [Second embodiment]

[0583] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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.

[0592] 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.

[0593] In the smart glasses 214, 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.

[0594] 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."

[0595] MODE FOR CARRYING OUT THE INVENTION

[0596] The embodiments of the present invention will be described in detail below.

[0597] Overall overview

[0598] This system efficiently collects and analyzes sales-related data, automatically generating optimal sales procedures and training materials, and providing them to users. The server uses natural language processing technology and machine learning algorithms to analyze the data provided by users, and generates sales procedures and training materials based on the results.

[0599] Data collection

[0600] Data input / upload from users

[0601] Users use their devices to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format.

[0602] Data storage

[0603] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[0604] Data analysis

[0605] Data Preprocessing

[0606] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[0607] Text analysis using natural language processing

[0608] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[0609] Applying machine learning models

[0610] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[0611] Automatic generation of sales procedures

[0612] Creating a Procedure Template

[0613] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[0614] Individual optimization

[0615] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[0616] Creating training materials

[0617] Material content generation

[0618] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[0619] Aggregation of related information

[0620] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[0621] Provision to users

[0622] Sending data

[0623] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[0624] User Verification

[0625] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[0626] Specific examples

[0627] For example, a user uses the system in the following scenario.

[0628] 1. Data Collection

[0629] Users upload customer lists and past sales records to the system as CSV files.

[0630] The server receives this data and stores it in a database.

[0631] 2. Data analysis

[0632] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0633] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0634] 3. Automatic generation of sales procedures

[0635] The server generates an optimal sales procedure based on the identified patterns.

[0636] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0637] 4. Creating training materials

[0638] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0639] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0640] 5. Provision to Users

[0641] The server transmits these materials to the user's terminal.

[0642] The user checks the sent materials and prepares for the next business meeting.

[0643] This system allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, thereby improving sales results.

[0644] The processing flow will be explained below.

[0645] Step 1:

[0646] Users use their devices to input or upload sales-related data, such as customer information, sales history, and sales negotiation details, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and sales negotiation details.

[0647] Step 2:

[0648] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[0649] Step 3:

[0650] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[0651] Step 4:

[0652] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[0653] Step 5:

[0654] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[0655] Step 6:

[0656] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0657] Step 7:

[0658] The server generates training materials based on individually optimized sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[0659] Step 8:

[0660] The server sends the generated sales procedures and training materials to the user's device. The user can check these materials on the device and download or print them as needed. This allows the user to refer to them while proceeding with their sales activities.

[0661] Example 1

[0662] 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."

[0663] Conventional sales-related data collection and analysis systems require a lot of time and effort for manual data entry and analysis, and the generation of specific sales procedures and training materials based on analysis results is not automated, making it difficult to support efficient sales activities.Furthermore, it is difficult to optimize the systems to suit the specific circumstances of individual users and customers, resulting in a lack of versatility.

[0664] 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.

[0665] In this invention, the server includes means for allowing a user to input or upload information, means for saving the information, means for preprocessing the saved information, means for analyzing the preprocessed information using natural language processing technology, means for analyzing the analyzed information using a machine learning algorithm, means for automatically generating business procedures based on the analysis results, means for generating training materials based on the business procedures, and means for providing the business procedures and training materials to users. This enables efficient collection and analysis of sales-related data and automatic generation of optimized procedures and training materials.

[0666] A "user" is a person or entity that operates the system and inputs or uploads information.

[0667] "Information" refers to a wide range of data, including sales-related data such as customer information, past sales history, and business negotiation details.

[0668] "Server" means an integrated hardware and software system that stores, pre-processes, parses, and analyzes information sent by users, and generates and provides business procedures and training materials based on the results.

[0669] "Input or Upload Means" refers to the interface or protocol by which a user provides information to the system.

[0670] "Storage" refers to techniques and devices that record received information in a persistent storage medium, such as a database.

[0671] "Preprocessing means" refers to the process of converting stored information into a format suitable for analysis by completing missing values, removing duplicate data, normalizing data, etc.

[0672] "Means of analysis using natural language processing technology" refers to the process of analyzing text data using technologies such as tokenization, part-of-speech tagging, and contextual analysis.

[0673] "Methods of analysis using machine learning algorithms" refers to the process of statistically analyzing information to identify patterns and trends using various machine learning techniques, such as regression analysis and cluster analysis.

[0674] "Means for automatically generating business procedures" refers to the process by which a system automatically generates specific and optimal sales procedures based on the analysis results of natural language processing technology and machine learning algorithms.

[0675] "Means for generating educational materials" refers to the process of creating learning content such as sales negotiation simulations, FAQs, and success stories based on the generated business procedures.

[0676] "Means for providing" refers to the process of transmitting the generated business procedures and training materials to the user's terminal so that the user can check, download, and print them.

[0677] The present invention relates to a system for collecting and analyzing sales-related data and automatically generating optimal sales procedures and training materials. A specific embodiment of this system will be described.

[0678] The server is equipped with an input means for receiving information provided by users. Users use their terminals to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files or JSON format.

[0679] The server has a secure storage facility to store the received information, which is then stored in a database (e.g., MySQL or PostgreSQL) for further analysis.

[0680] The server then uses Python's Pandas library to preprocess the stored information, which includes data cleaning (imputing missing values, removing duplicates), normalization, and other steps to convert the data into a format suitable for analysis.

[0681] The preprocessed information is then analyzed using natural language processing (NLP) techniques. This analysis involves tokenization, part-of-speech tagging, and contextual analysis using NLP libraries such as NLTK and Spacy. For example, a text such as "Describes the technical characteristics of a new product" is broken down into "New product / noun, technical / adjective, characteristics / noun, description / verb."

[0682] The server then applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to analyze the information. This analysis includes regression analysis and cluster analysis, which can identify common factors behind successful deals. For example, clusters can be generated based on past deal results to identify patterns of success.

[0683] Based on the analysis results, the server automatically generates business procedures. It uses a template engine such as Jinja2 to create a basic sales procedure template, and then individually optimizes the template according to the circumstances of the user and specific customer. For example, a procedure that provides a detailed technical overview of a new product for repeat customers could be included.

[0684] Based on the sales procedures, the server generates training materials, including sales negotiation simulations, FAQs, success stories, etc. For example, specific training content such as "frequently asked questions and answers about the technical specifications of a new product" is created.

[0685] The training materials also aggregate relevant supporting materials and reference links, including instructional videos and white papers, all centralized within one system.

[0686] Finally, the server sends the generated business procedures and training materials to the user's device, where the user can review, download, and print the received materials, allowing them to efficiently prepare for the next business meeting.

[0687] For example, consider a scenario in which a user uploads a customer list or past sales negotiation records to the system as a CSV file. The server then receives this data, stores it in a database, and performs analysis. As a specific example, it identifies a pattern that "explaining new products with emphasis on their technical details is effective for repeat customers," and incorporates a procedure that "explains the technical specifications of new products in detail when first contacted." It also generates training materials that include "frequently asked questions and answers about the technical specifications of new products," and provides them to users.

[0688] This allows users to conduct sales activities efficiently and quickly obtain optimal procedures and training materials.

[0689] Prompt Sentence Examples

[0690] "Upload a CSV file containing your customer list and generate the optimal sales procedures. Provide us with the generated procedures and training materials."

[0691] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0692] Processing flow and each processing step

[0693] Step 1: Enter and collect data

[0694] User Action:

[0695] Users use their terminal to upload sales-related data such as customer information, past sales history, and sales negotiation details in CSV or JSON format.

[0696] input:

[0697] A CSV file containing data such as customer name, contact details, deal date, details, and results.

[0698] output:

[0699] The uploaded data file is sent to the server.

[0700] Specific behavior:

[0701] The user fills in the required fields in the data entry form on the web interface, selects the file, and clicks the upload button.

[0702] Step 2: Save your data

[0703] Server behavior:

[0704] The server securely stores the received data in a database (MySQL or PostgreSQL).

[0705] input:

[0706] CSV file or JSON data submitted by the user.

[0707] output:

[0708] Well-formed data stored in a database.

[0709] Specific behavior:

[0710] The server parses the contents of the file and stores it in a specific table in the database by executing an insert query.

[0711] Step 3: Preprocessing the data

[0712] Server behavior:

[0713] The server preprocesses the stored data using Python's Pandas library.

[0714] input:

[0715] Raw data stored in a database.

[0716] output:

[0717] Cleaned data with missing values ​​imputed and duplicates removed.

[0718] Specific behavior:

[0719] The server loads the data into a data frame, normalizes it by imputing missing values ​​with the mean and removing duplicates.

[0720] Step 4: Text analysis using natural language processing

[0721] Server behavior:

[0722] The server uses NLP libraries such as NLTK and Spacy to analyze the text data.

[0723] input:

[0724] Cleaned text data.

[0725] output:

[0726] Analysis results extracting important keywords and topics.

[0727] Specific behavior:

[0728] The server tokenizes the text data, tags it with parts of speech, and performs contextual analysis, breaking down, for example, "Describe the technical characteristics of a new product" into "New product / noun technical / adjective characteristics / noun description / verb."

[0729] Step 5: Analysis with machine learning models

[0730] Server behavior:

[0731] The server uses Scikit-learn and TensorFlow to analyze the data with machine learning algorithms.

[0732] input:

[0733] NLP text analysis results and cleaned numerical data.

[0734] output:

[0735] Analysis results that identify patterns and common factors in successful deals.

[0736] Specific behavior:

[0737] The server performs regression and cluster analysis to find successful patterns and generate clusters based on specific criteria.

[0738] Step 6: Automatic generation of business procedures

[0739] Server behavior:

[0740] The server uses a template engine such as Jinja2 to create templates for basic sales procedures and individually optimize them.

[0741] input:

[0742] Machine learning analysis results and templates.

[0743] output:

[0744] Sales playbooks optimized for users and specific customers.

[0745] Specific behavior:

[0746] The server embeds variables into the template and dynamically changes the content depending on the user's specific situation.

[0747] Step 7: Generate training material

[0748] Server behavior:

[0749] The server creates training materials based on the generated sales procedures.

[0750] input:

[0751] Customized sales procedures.

[0752] output:

[0753] Training materials including sales simulations, FAQs, success stories, and more.

[0754] Specific behavior:

[0755] The server formats the training material in Markdown or HTML and generates the specific content.

[0756] Step 8: Expanding training materials

[0757] Server behavior:

[0758] The server collects relevant supplementary material and reference links to add to the training materials.

[0759] input:

[0760] Generated training materials.

[0761] output:

[0762] Comprehensive training material with additional supplementary materials and reference links.

[0763] Specific behavior:

[0764] The server collects links to relevant videos and white papers and inserts them into the appropriate parts of the training materials.

[0765] Step 9: Send data and confirm with the user

[0766] Server behavior:

[0767] The server transmits the generated work procedure manual and training materials to the user's terminal.

[0768] input:

[0769] Final generated sales procedures and training materials.

[0770] output:

[0771] Materials sent to the user's device.

[0772] Specific behavior:

[0773] The server delivers the materials to users via email or a dedicated web portal.

[0774] Step 10: User verification and utilization

[0775] User Action:

[0776] The user checks the sent materials and downloads or prints them as necessary.

[0777] input:

[0778] Sales procedures and training materials sent from the server.

[0779] output:

[0780] Action items for users who are ready to close a deal.

[0781] Specific behavior:

[0782] Users can download materials, print them out for the next business meeting, and begin concrete preparations.

[0783] (Application example 1)

[0784] 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."

[0785] In sales activities, it is difficult to effectively use customer information and past sales history to determine the optimal sales procedure. In particular, in virtual stores, it is necessary to provide sales representatives with the optimal sales pitch and materials in real time and respond quickly. With traditional methods, these processes are highly manual, requiring time and effort, making it difficult to conduct efficient sales activities.

[0786] 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.

[0787] In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, and means for analyzing the sales data in real time and providing optimal sales pitches and materials to sales representatives of the virtual store in real time, thereby making it possible to improve the efficiency and accuracy of sales activities.

[0788] "User" refers to a person who uses the System to input or upload sales-related data.

[0789] "Sales-related data" refers to data related to sales activities, such as customer information, past sales history, and sales negotiation details.

[0790] "Storage Measures" means software or hardware for securely and efficiently storing collected business-related data.

[0791] "Analysis Tools" refers to software or hardware for analyzing collected and stored business-related data.

[0792] A "sales procedure" refers to a series of steps that indicate the optimal procedure for sales activities.

[0793] "Automatic generation means" refers to software or hardware for automatically generating sales procedures based on the results of data analysis.

[0794] "Training Materials" means the educational content and materials necessary to perform the Sales Procedures.

[0795] "Delivery means" refers to software or hardware for delivering the generated sales procedures and training materials to users.

[0796] "Real-time analysis" refers to the process of instantly analyzing collected data and providing the results in real time.

[0797] A "virtual store" refers to an online platform that conducts business over the Internet, rather than a physical store.

[0798] "Sales talk" refers to sales statements and explanations used during business negotiations with customers.

[0799] "Real-time delivery means" refers to software or hardware used to provide analysis results, sales pitches, and materials to sales representatives in real time.

[0800] MODE FOR CARRYING OUT THE INVENTION

[0801] Overall overview

[0802] This system efficiently stores and analyzes sales-related data collected from users, automatically generates optimal sales procedures and training materials, and also provides optimal sales pitches and materials to salespeople in real time in the virtual store.

[0803] Data collection

[0804] Data input / upload from users

[0805] Users use their terminals to input or upload sales-related data such as customer information, past sales history, and details of sales negotiations into the system. This data is generally provided in CSV or JSON format.

[0806] Data storage

[0807] The server receives the sales-related data sent by the user and stores it safely and efficiently. The stored data is recorded in a database and appropriately managed for later analysis.

[0808] Data analysis

[0809] Data Preprocessing

[0810] The server preprocesses the stored data, specifically by cleaning it by filling in missing values ​​and removing duplicate data, and converting it into a data format suitable for analysis.

[0811] Text analysis using natural language processing

[0812] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[0813] Applying machine learning models

[0814] The server analyzes the data using machine learning algorithms, specifically regression and cluster analysis, to identify which sales techniques were most effective.

[0815] Automatic generation of sales procedures

[0816] Creating a Procedure Template

[0817] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[0818] Individual optimization

[0819] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[0820] Creating training materials

[0821] Material content generation

[0822] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and their answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[0823] Aggregation of related information

[0824] The server aggregates supplemental materials and reference links related to the generated training materials, including instructional videos and white papers.

[0825] Real-time sales talk

[0826] Real-time analytics

[0827] Salespeople in the virtual store receive assistance from the system when negotiating with customers in real time. The server analyzes sales data in real time and provides optimal sales pitches and materials.

[0828] Real-time delivery method

[0829] The server sends the analysis results, sales pitches, and materials to the sales representative's device in real time, allowing the sales representative to respond quickly and appropriately.

[0830] Provision to users

[0831] Sending data

[0832] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[0833] User Verification

[0834] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[0835] Specific examples

[0836] For example, a user uses the system in the following scenario.

[0837] 1. Data Collection

[0838] Users upload customer lists and past sales records to the system as CSV files.

[0839] The server receives this data and stores it in a database.

[0840] 2. Data analysis

[0841] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0842] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0843] 3. Automatic generation of sales procedures

[0844] The server generates an optimal sales procedure based on the identified patterns.

[0845] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0846] 4. Creating training materials

[0847] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0848] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0849] 5. Real-time assistance

[0850] During sales negotiations in the virtual store, the server provides sales representatives with the most appropriate sales pitches and materials in real time based on the analysis results.

[0851] 6. Provision to Users

[0852] The server transmits these materials to the user's terminal.

[0853] The user checks the sent materials and prepares for the next business meeting.

[0854] Prompt Sentence Examples

[0855] Enter customer information and past sales history data. We will generate the optimal sales procedure based on this data. Upload the data in CSV format or enter it directly in the app.

[0856] This invention allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, and also enables the virtual store to provide optimal sales pitches and materials in real time.

[0857] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0858] Step 1: Data collection

[0859] Input: The user inputs customer information and past sales history data into the system using a terminal or uploads it as a CSV file.

[0860] Processing: The terminal receives the input data, converts it into an appropriate format, and sends it to the server.

[0861] Output: The server records the received data in a storage database.

[0862] Step 2: Save data

[0863] Input: Sales-related data received by the server.

[0864] Processing: The server securely stores the received data in a database, taking appropriate security measures when storing the data.

[0865] Output: The saved data is organized for later analysis.

[0866] Step 3: Data Preprocessing

[0867] Input: Sales-related data stored on the server.

[0868] Processing: The server cleans the data by imputing missing values, removing duplicates, etc. It also normalizes the data into a format that is easier to analyze.

[0869] Output: Preprocessed and formatted data suitable for analysis.

[0870] Step 4: Text analysis using natural language processing

[0871] Input: Preprocessed text data (e.g., business negotiation details).

[0872] Processing: The server analyzes the text data using natural language processing techniques (e.g., spaCy), performing tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics.

[0873] Output: Extracted keywords and topic information.

[0874] Step 5: Applying the machine learning model

[0875] Input: Preprocessed sales data and extracted keyword and topic information.

[0876] Processing: The server analyzes the data using machine learning algorithms (e.g., cluster analysis and regression analysis) to identify which sales techniques are most effective.

[0877] Output: A pattern of optimal sales techniques.

[0878] Step 6: Auto-generate sales procedures

[0879] Input: Optimal sales technique patterns.

[0880] Processing: The server generates a basic sales procedure template based on the analysis results and customizes it for specific customers and industries.

[0881] Output: Customized sales procedures.

[0882] Step 7: Create training materials

[0883] Input: Customized Sales Procedure.

[0884] Processing: The server generates training materials including sales negotiation simulations and FAQs based on sales procedures, and also aggregates related supplementary materials and reference links.

[0885] Output: The completed training material.

[0886] Step 8: Real-time analytics and sales pitches

[0887] Input: Real-time customer data and sales rep requests.

[0888] Processing: The server analyzes customer data collected in real time and provides optimal sales pitches and materials based on the latest sales techniques and materials.

[0889] Output: Sales pitches and materials provided in real time.

[0890] Step 9: Provide to users

[0891] Input: Generated sales procedures and training materials.

[0892] Processing: The server sends these materials to the user's terminal.

[0893] Output: The user checks the sent materials and downloads or prints them as needed.

[0894] This enables the system to improve the efficiency and accuracy of sales activities.

[0895] 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.

[0896] MODE FOR CARRYING OUT THE INVENTION

[0897] The embodiments of the present invention will be described in detail below.

[0898] Overall overview

[0899] This system efficiently collects and analyzes sales-related data, automatically generates optimal sales procedures and training materials, and provides them to users. In particular, by combining it with an emotion engine that recognizes the user's emotions, it realizes more advanced and personalized sales techniques.

[0900] Data collection

[0901] Data input / upload from users

[0902] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[0903] Data storage

[0904] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[0905] Data analysis

[0906] Data Preprocessing

[0907] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[0908] Text analysis using natural language processing

[0909] The server analyzes the text data using natural language processing (NLP) techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from, for example, a business meeting transcript.

[0910] Applying machine learning models

[0911] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[0912] Automatic generation of sales procedures

[0913] Creating a Procedure Template

[0914] The server creates a basic sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0915] Individual optimization

[0916] The server customizes the template to suit each user's or customer's specific circumstances, optimizing, for example, providing technical details first for customers in a particular industry.

[0917] Utilizing the Emotion Engine

[0918] emotion recognition

[0919] The emotion engine is designed to recognize user emotions. It uses natural language processing technology to determine emotions from text and voice data entered by the user. For example, it can identify user emotions such as "interested," "distrustful," or "satisfied" from text data during a business negotiation.

[0920] Sentiment Data Analysis

[0921] The server analyzes the emotional data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if the user has a "distrustful" feeling, it adds procedures to provide more detailed information or strengthen follow-up.

[0922] Creating training materials

[0923] Material content generation

[0924] The server generates training material content based on the sales process, including sales simulations, frequently asked questions and answers, and success stories, including stories of successful calls that highlight technical details.

[0925] Aggregation of related information

[0926] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[0927] Provision to users

[0928] Sending data

[0929] The server sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[0930] User Verification

[0931] The user can check the sent materials and prepare for the next business meeting. For example, the user can print out a procedure manual to use on-site in preparation for the next business meeting.

[0932] Specific examples

[0933] For example, a user uses the system in the following scenario.

[0934] 1. Data Collection

[0935] Users upload customer lists and past sales records to the system as CSV files.

[0936] The server receives this data and stores it in a database.

[0937] 2. Data analysis

[0938] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[0939] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[0940] 3. Automatic generation of sales procedures

[0941] The server generates an optimal sales procedure based on the identified patterns.

[0942] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[0943] 4. Creating training materials

[0944] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[0945] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[0946] 5. Applying the Emotion Engine

[0947] The emotion engine analyzes the user's emotions in real time during a business negotiation.

[0948] For example, if a user is feeling unsure during a sales conversation, the system can detect this and generate instructions to strengthen follow-up procedures.

[0949] 6. Provision to Users

[0950] The server transmits these materials to the user's terminal.

[0951] The user checks the sent materials and prepares for the next business meeting.

[0952] This system allows users to quickly obtain procedures and training materials for efficient sales activities, thereby improving sales results. In addition, by utilizing an emotion engine, it is possible to realize more personalized sales methods and improve customer satisfaction.

[0953] The processing flow will be explained below.

[0954] Step 1:

[0955] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[0956] Step 2:

[0957] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[0958] Step 3:

[0959] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[0960] Step 4:

[0961] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[0962] Step 5:

[0963] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[0964] Step 6:

[0965] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[0966] Step 7:

[0967] The server uses an emotion engine to analyze the user's emotions in real time. For example, it analyzes the user's text messages and voice data during a business meeting to determine whether the user is feeling "interested," "distrustful," or "satisfied."

[0968] Step 8:

[0969] The server analyzes the emotion data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if a user is feeling "distrustful," the server can detect this and generate instructions to strengthen follow-up procedures.

[0970] Step 9:

[0971] The server creates training materials based on the automatically generated sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[0972] Step 10:

[0973] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[0974] Step 11:

[0975] The user can check the sent materials and prepare for the next business meeting. For example, to prepare for the next business meeting, the user can print out a procedure manual and use it on-site. In this way, the user can conduct sales activities efficiently and effectively.

[0976] Example 2

[0977] 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."

[0978] There is a need for systems that can more effectively support sales activities by efficiently collecting, storing, and analyzing sales-related data, and automatically generating sales procedures and training materials. However, existing systems have not adequately performed data preprocessing and customization, or individual optimization based on user emotion recognition, which has led to problems in not improving sales efficiency and customer satisfaction.

[0979] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0980] In this invention, the server includes: means for allowing a user to input or upload sales-related data; means for saving the sales-related data; means for preprocessing the saved sales-related data; means for analyzing the saved data using natural language processing technology; means for analyzing the sales-related data by applying a machine learning algorithm; means for automatically generating sales procedures based on the analysis results; means for customizing the generated sales procedures according to the specific circumstances of each user and their customers; means for determining emotions from text data or voice data entered by the user; means for adjusting sales procedures and training materials based on the emotion data; means for generating training materials based on the sales procedures; means for aggregating supplementary materials and reference links related to the training materials; and means for providing the sales procedures and training materials to users. This centralizes the collection, storage, and analysis of sales-related data, making it possible to provide personalized sales methods utilizing emotion recognition.

[0981] "User" means any individual or legal entity that uses the System to input or upload business-related data.

[0982] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[0983] "Data preprocessing" refers to a series of processes to improve data quality, such as filling in missing values, correcting outliers, and removing duplicate data.

[0984] "Natural language processing technology" refers to technology for processing human language using computers, and includes tokenization, part-of-speech tagging, context analysis, etc.

[0985] A "machine learning algorithm" is an algorithm that finds patterns and relationships in data and makes predictions and classifications.

[0986] "Sales procedures" refer to the steps and processes for effectively carrying out sales activities, and include, for example, the flow of "initial contact → needs assessment → proposal → follow-up."

[0987] "Training materials" are educational materials created based on sales procedures, and include sales negotiation simulations, FAQs, success stories, etc.

[0988] "Emotion recognition" refers to the technology of determining emotions from a user's text data or voice data using natural language processing technology, etc.

[0989] "Related information aggregation" refers to the process of collecting supplementary materials and reference links related to training material and providing them as a single resource.

[0990] "Storage" means recording and securely storing entered or uploaded data in a database.

[0991] "Providing" refers to transmitting the generated sales procedures and training materials to the user and making them available to the user.

[0992] MODE FOR CARRYING OUT THE INVENTION

[0993] Overall overview

[0994] This system efficiently collects, stores, and analyzes sales-related data entered or uploaded by users, and automatically generates optimal sales procedures and training materials. Furthermore, it utilizes an emotion engine to recognize users' emotions and provide personalized sales techniques and training accordingly.

[0995] System configuration

[0996] This system consists of a user terminal, a server, a database, a natural language processing engine, a machine learning algorithm, an emotion recognition engine, and a user interface (UI).

[0997] Data collection

[0998] Users use their devices to input or upload sales-related data such as customer information, sales history, and details of business negotiations. The data is provided in standard CSV or JSON format. For example, it includes fields such as "customer name," "contact information," "sales negotiation date and time," and "sales negotiation details."

[0999] Data storage

[1000] The server receives sales-related data sent by users in real time and stores it securely in a database. The stored data is used for subsequent analysis and procedure generation, while also ensuring data integrity and security.

[1001] Data Preprocessing

[1002] The server preprocesses the sales-related data stored in the database, including cleaning tasks such as imputing missing values, correcting outliers, and removing duplicate data, as well as normalizing the data into a format suitable for analysis.

[1003] Text data analysis

[1004] The server uses a natural language processing engine to analyze the text data of the sales negotiation records. Specifically, it tokenizes the text, tags it for parts of speech, and performs context analysis. For example, it extracts "factors that lead to the success of a sales negotiation" from the sales negotiation records.

[1005] Applying machine learning algorithms

[1006] The server analyzes the data using machine learning algorithms, conducting regression analysis and cluster analysis to identify which sales techniques are most effective. For example, it can identify patterns in sales negotiations that resulted in high customer satisfaction.

[1007] Automatic generation of sales procedures

[1008] Based on the analysis results, the server generates a sales procedure template, which may include steps such as "initial contact," "needs assessment," "proposal," and "follow-up." This template is customized to fit the specific needs of the user.

[1009] Individual optimization

[1010] The server customizes the automatically generated sales procedure according to the specific circumstances of each user and their customer, for example, optimizing it to provide technical details to customers who are highly interested in technology at an early stage.

[1011] Utilizing the Emotion Engine

[1012] The server uses an emotion recognition engine to determine the user's emotions from the text and voice data they provide. For example, if the server determines that the user is distrustful, it will adjust the system to provide more detailed explanations and follow-up procedures.

[1013] Creating training materials

[1014] The server generates training materials based on the automatically generated sales procedures, including sales simulations, FAQs, and success stories, such as "Frequently Asked Questions and Answers about the Technical Specifications of a New Product."

[1015] Aggregation of information related to training materials

[1016] The server aggregates supplemental materials and reference links related to the generated training materials, for example, educational videos about the technical background of the product.

[1017] Sending data

[1018] The server then sends the generated sales procedure manual and training materials to the user's terminal, where the user can review these materials and prepare for the next business negotiation.

[1019] Specific examples

[1020] For example, a user can upload a "customer list" and "past sales negotiation records" to the system in CSV file format. The server receives this data, stores it in a database, and performs preprocessing. NLP technology is then used to analyze the text data and extract important keywords and patterns. A machine learning algorithm identifies the optimal sales method and generates a procedure, such as "explain the technical specifications of a new product in detail during the first contact."

[1021] Prompt Sentence Examples

[1022] The following prompts may be used:

[1023] "Analyze the data uploaded by users and generate the optimal sales method."

[1024] "Detect sentiment from text data entered by users during sales conversations and optimize procedures based on that."

[1025] In this way, the system efficiently and effectively supports sales activities and provides users with optimal sales procedures and training materials.

[1026] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1027] Step 1:

[1028] Users use their devices to input or upload sales-related data. Input includes customer information, sales history, and details of business negotiations, and is provided in CSV or JSON format. Specifically, users specify the data file through the device's user interface and click the upload button.

[1029] Input: Customer information, sales history, business details (CSV file or JSON format)

[1030] Output: Sales-related data sent from the user's device

[1031] Step 2:

[1032] The server receives sales-related data sent by users in real time and stores it in a database. The server first verifies the format and content of the data, and then securely records it in the database.

[1033] Input: Sales-related data sent from the user's terminal

[1034] Output: Sales-related data stored in a database

[1035] Step 3:

[1036] The server preprocesses the sales-related data stored in the database, specifically cleaning the data (e.g., filling in missing values, correcting outliers, removing duplicates), normalizing it, and converting it into a format suitable for analysis.

[1037] Input: Sales-related data stored in a database

[1038] Output: Preprocessed sales-related data

[1039] Step 4:

[1040] The server then analyzes the pre-processed data using natural language processing (NLP) techniques, such as text tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from the sales meeting notes.

[1041] Input: Pre-processed sales-related data

[1042] Output: Analysis results (extracted keywords, topics)

[1043] Step 5:

[1044] The server then applies machine learning algorithms to further analyze the stored sales-related data, for example, using regression analysis and cluster analysis to identify which sales techniques were most effective.

[1045] Input: Pre-processed sales-related data

[1046] Output: Machine learning analysis results (identification of effective sales methods)

[1047] Step 6:

[1048] The server automatically generates a sales procedure template based on the analysis results, for example, a template including general steps such as "initial contact → needs assessment → proposal → follow-up."

[1049] Input: Machine learning analysis results

[1050] Output: Sales Procedure Template

[1051] Step 7:

[1052] The server customizes the generated sales procedures to the specific circumstances of each user and their customer, for example, creating procedures tailored to customers in a particular industry by providing technical details upfront.

[1053] Input: Sales procedure template, customer information

[1054] Output: Customized sales procedures

[1055] Step 8:

[1056] The server uses an emotion recognition engine to determine emotions from the text and voice data entered by the user, identifying emotions such as "interested," "distrustful," and "satisfied," and adjusting sales procedures accordingly.

[1057] Input: Text data and voice data entered by the user

[1058] Output: Emotion recognition result

[1059] Step 9:

[1060] The server can then use the emotional data to adjust sales procedures and training materials, for example adding steps to strengthen follow-up if the user is "distrustful."

[1061] Input: Emotion recognition results, customized sales procedures

[1062] Output: Adjusted sales procedures

[1063] Step 10:

[1064] The server generates training materials based on the adjusted sales procedures, such as sales negotiation simulations, FAQs, and success stories.

[1065] Input: Adjusted Sales Procedures

[1066] Output: Generated training material

[1067] Step 11:

[1068] The server aggregates supplementary materials and reference links related to the generated training materials, for example, educational videos and white papers, and adds them to the training materials provided.

[1069] Input: Generated training material

[1070] Output: Training materials with supplementary materials and reference links

[1071] Step 12:

[1072] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can review the materials and prepare for the next sales meeting.

[1073] Input: Training materials with supplementary materials and reference links

[1074] Output: Data sent to the user's device

[1075] This is the specific process flow. This system allows users to receive the information and support they need to efficiently carry out their sales activities in a timely manner.

[1076] (Application example 2)

[1077] 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."

[1078] In sales activities, data collection and analysis are essential for quickly and efficiently understanding customer needs. However, conventional systems did not adequately analyze sales-related data or recognize emotions, making it difficult to provide appropriate sales techniques and training materials. Furthermore, they were unable to recognize customer emotions during the sales process in real time and adjust sales procedures accordingly, preventing improvements in sales efficiency and customer satisfaction.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, an emotion engine that recognizes the user's emotions during the sales process in real time, and means for analyzing emotion data obtained by the emotion engine and adjusting the sales procedures. This makes it possible to efficiently analyze sales-related data and provide a personalized sales methodology based on the user's emotions.

[1080] "User" means any individual or legal entity that inputs or uploads business-related data.

[1081] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[1082] "Means for inputting or uploading" refers to a function that allows a user to input or upload sales-related data into the system.

[1083] "Means for storage" refers to the system's ability to securely store entered sales-related data.

[1084] "Means for analysis" refers to the function for analyzing stored sales-related data and extracting meaningful information.

[1085] "Means for automatic generation" refers to a function for automatically creating sales procedures based on the analysis results.

[1086] "Means for generating" refers to the function for creating training materials based on sales procedures.

[1087] "Means for providing" refers to a function for presenting the generated sales procedures and training materials to the user.

[1088] An "emotion engine" refers to a system that recognizes a user's emotions in real time and analyzes the data.

[1089] "Means for adjustment" refers to the function for appropriately adjusting sales procedures based on the emotional data obtained by the emotion engine.

[1090] Overall overview

[1091] This invention is a system that collects sales-related data from users and efficiently stores and analyzes it. Based on the analysis results, the system automatically generates optimal sales procedures and training materials and provides them to users. Furthermore, by combining it with an emotion engine, personalized sales techniques based on the user's emotions become possible.

[1092] Program structure and processing

[1093] 1. Data Collection

[1094] Users input or upload sales-related data such as customer information, sales history, and details of business negotiations through a smartphone application. This data is provided in JSON format and sent to the server.

[1095] 2. Data storage

[1096] The server securely stores the received sales-related data in a database such as MongoDB, where it is used for later analysis.

[1097] 3. Data analysis

[1098] The server uses the Google Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques, including tokenization, part-of-speech tagging, and contextual analysis.

[1099] 4. Applying machine learning models

[1100] The server uses machine learning algorithms such as TensorFlow to analyze the data, specifically using clustering algorithms (e.g., KMeans) to identify which sales tactics were effective.

[1101] 5. Automatic generation of sales procedures

[1102] The server automatically generates optimal sales procedures based on the analysis results, for example, formulating a procedure such as "explaining the technical specifications of a new product in detail when first contacting the customer."

[1103] 6. Creating training materials

[1104] The server creates training materials based on the generated sales procedures, including sales negotiation simulations, FAQs, and success stories.

[1105] 7. Leveraging Emotional Engines

[1106] The emotion engine uses the IBM Watson Emotion Analysis API to recognize user emotions in real time, for example, if a user feels distrust during a sales meeting, it can sense this and adjust follow-up procedures.

[1107] 8. Provision to Users

[1108] The server sends the generated sales procedure manual and training materials to the user's terminal, where the user can review the materials and prepare for the next business meeting.

[1109] Specific examples

[1110] 1. Data Collection

[1111] The user uploads a customer list and past sales records in JSON format from a smartphone application.

[1112] 2. Emotion recognition

[1113] Based on the text data during the business negotiation, the emotion engine determines the user's emotion as "interested."

[1114] 3. Sales procedure generation

[1115] The procedure "explain the technical specifications of a new product in detail" is automatically generated and provided to the user.

[1116] Prompt Sentence Examples

[1117] To prepare for the next sales meeting, propose a procedure to stimulate the customer's interest in a new product. Analyze customer information, sales history, and sales content data, and take into account emotion recognition to provide the optimal sales procedure. If the customer is determined to be interested, generate a procedure to provide technical details.

[1118] This system allows sales representatives to quickly access procedures and training materials to conduct sales activities efficiently, and the emotional engine enables personalized sales techniques, which is expected to improve customer satisfaction.

[1119] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1120] Step 1:

[1121] Users use a smartphone application to input or upload sales-related data such as customer information, sales history, and sales negotiation details in JSON format. Input includes customer name, contact information, sales negotiation date and time, sales negotiation details, etc. The output is JSON format data sent to the server.

[1122] Step 2:

[1123] The server receives sales-related data and stores it in a database such as MongoDB. The server keeps the data consistent and secure, and stores it for future analysis. The input is the JSON-formatted data sent by the user, and the output is the sales-related data securely stored in the database.

[1124] Step 3:

[1125] The server uses the Google Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and context analysis. The input is the text data stored in the database, and the output is the analysis result, tokenized and part-of-speech tagged text data.

[1126] Step 4:

[1127] The server applies machine learning algorithms such as TensorFlow to analyze the data. Specifically, it uses clustering algorithms (e.g., KMeans) to identify patterns of successful sales techniques. The input is tokenized and part-of-speech tagged text data, and the output is a list of clustered patterns.

[1128] Step 5:

[1129] The server automatically generates optimal sales procedures based on the analysis results. For example, it formulates a specific procedure such as "explaining the technical specifications of a new product in detail during the first contact." The input is a list of clustered patterns, and the output is an automatically generated sales procedure manual.

[1130] Step 6:

[1131] The server creates training materials based on the generated sales procedures. Specifically, it creates training materials that include sales negotiation simulations, FAQs, stories of success cases, etc. The input is the automatically generated sales procedures manual, and the output is the completed training materials.

[1132] Step 7:

[1133] The emotion engine uses the IBM Watson Emotion Analysis API to recognize user emotions in real time. The targets for emotion recognition include text and voice data from business negotiations. The input is text and voice data acquired in real time, and the output is analyzed emotion data (e.g., "interested" or "distrustful").

[1134] Step 8:

[1135] The server analyzes the emotion data obtained by the emotion engine and adjusts the sales procedure. For example, if "distrust" is determined to be high, it generates instructions to strengthen follow-up procedures. The input is emotion data from the emotion engine, and the output is an adjusted sales procedure.

[1136] Step 9:

[1137] The server sends the generated and adjusted sales procedures and training materials to the user's terminal. The user checks these materials and prepares for the next business meeting. The adjusted sales procedures and training materials are obtained as input, and the materials displayed on the user's terminal are obtained as output.

[1138] 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.

[1139] 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.

[1140] 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.

[1141] [Third embodiment]

[1142] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1144] 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).

[1145] 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.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] 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.

[1153] 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."

[1154] MODE FOR CARRYING OUT THE INVENTION

[1155] The embodiments of the present invention will be described in detail below.

[1156] Overall overview

[1157] This system efficiently collects and analyzes sales-related data, automatically generating optimal sales procedures and training materials, and providing them to users. The server uses natural language processing technology and machine learning algorithms to analyze the data provided by users, and generates sales procedures and training materials based on the results.

[1158] Data collection

[1159] Data input / upload from users

[1160] Users use their devices to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format.

[1161] Data storage

[1162] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[1163] Data analysis

[1164] Data Preprocessing

[1165] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[1166] Text analysis using natural language processing

[1167] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[1168] Applying machine learning models

[1169] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[1170] Automatic generation of sales procedures

[1171] Creating a Procedure Template

[1172] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[1173] Individual optimization

[1174] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[1175] Creating training materials

[1176] Material content generation

[1177] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[1178] Aggregation of related information

[1179] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[1180] Provision to users

[1181] Sending data

[1182] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[1183] User Verification

[1184] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[1185] Specific examples

[1186] For example, a user uses the system in the following scenario.

[1187] 1. Data Collection

[1188] Users upload customer lists and past sales records to the system as CSV files.

[1189] The server receives this data and stores it in a database.

[1190] 2. Data analysis

[1191] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[1192] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[1193] 3. Automatic generation of sales procedures

[1194] The server generates an optimal sales procedure based on the identified patterns.

[1195] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[1196] 4. Creating training materials

[1197] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[1198] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[1199] 5. Provision to Users

[1200] The server transmits these materials to the user's terminal.

[1201] The user checks the sent materials and prepares for the next business meeting.

[1202] This system allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, thereby improving sales results.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] Users use their devices to input or upload sales-related data, such as customer information, sales history, and sales negotiation details, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and sales negotiation details.

[1206] Step 2:

[1207] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[1208] Step 3:

[1209] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[1210] Step 4:

[1211] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[1212] Step 5:

[1213] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[1214] Step 6:

[1215] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[1216] Step 7:

[1217] The server generates training materials based on individually optimized sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[1218] Step 8:

[1219] The server sends the generated sales procedures and training materials to the user's device. The user can check these materials on the device and download or print them as needed. This allows the user to refer to them while proceeding with their sales activities.

[1220] Example 1

[1221] 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."

[1222] Conventional sales-related data collection and analysis systems require a lot of time and effort for manual data entry and analysis, and the generation of specific sales procedures and training materials based on analysis results is not automated, making it difficult to support efficient sales activities.Furthermore, it is difficult to optimize the systems to suit the specific circumstances of individual users and customers, resulting in a lack of versatility.

[1223] 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.

[1224] In this invention, the server includes means for allowing a user to input or upload information, means for saving the information, means for preprocessing the saved information, means for analyzing the preprocessed information using natural language processing technology, means for analyzing the analyzed information using a machine learning algorithm, means for automatically generating business procedures based on the analysis results, means for generating training materials based on the business procedures, and means for providing the business procedures and training materials to users. This enables efficient collection and analysis of sales-related data and automatic generation of optimized procedures and training materials.

[1225] A "user" is a person or entity that operates the system and inputs or uploads information.

[1226] "Information" refers to a wide range of data, including sales-related data such as customer information, past sales history, and business negotiation details.

[1227] "Server" means an integrated hardware and software system that stores, pre-processes, parses, and analyzes information sent by users, and generates and provides business procedures and training materials based on the results.

[1228] "Input or Upload Means" refers to the interface or protocol by which a user provides information to the system.

[1229] "Storage" refers to techniques and devices that record received information in a persistent storage medium, such as a database.

[1230] "Preprocessing means" refers to the process of converting stored information into a format suitable for analysis by completing missing values, removing duplicate data, normalizing data, etc.

[1231] "Means of analysis using natural language processing technology" refers to the process of analyzing text data using technologies such as tokenization, part-of-speech tagging, and contextual analysis.

[1232] "Methods of analysis using machine learning algorithms" refers to the process of statistically analyzing information to identify patterns and trends using various machine learning techniques, such as regression analysis and cluster analysis.

[1233] "Means for automatically generating business procedures" refers to the process by which the system automatically generates specific and optimal sales procedures based on the analysis results of natural language processing technology and machine learning algorithms.

[1234] "Means for generating educational materials" refers to the process of creating learning content such as sales negotiation simulations, FAQs, and success stories based on the generated business procedures.

[1235] "Means for providing" refers to the process of transmitting the generated business procedures and training materials to the user's terminal so that the user can view, download, and print them.

[1236] The present invention relates to a system for collecting and analyzing sales-related data and automatically generating optimal sales procedures and training materials. A specific embodiment of this system will be described below.

[1237] The server is equipped with an input means for receiving information provided by users. Users use their terminals to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files or JSON format.

[1238] The server has a secure storage facility to store the received information, which is then stored in a database (e.g., MySQL or PostgreSQL) for further analysis.

[1239] The server then uses Python's Pandas library to preprocess the stored information, which includes data cleaning (imputing missing values, removing duplicates), normalization, and other steps to convert the data into a format suitable for analysis.

[1240] The preprocessed information is then analyzed using natural language processing (NLP) techniques. This analysis involves tokenization, part-of-speech tagging, and contextual analysis using NLP libraries such as NLTK and Spacy. For example, a text such as "Describes the technical characteristics of a new product" is broken down into "New product / noun, technical / adjective, characteristics / noun, description / verb."

[1241] The server then applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to analyze the information. This analysis includes regression analysis and cluster analysis, which can identify common factors behind successful deals. For example, clusters can be generated based on past deal results to identify patterns of success.

[1242] Based on the analysis results, the server automatically generates business procedures. It uses a template engine such as Jinja2 to create a basic sales procedure template, and then individually optimizes the template according to the circumstances of the user and specific customer. For example, a procedure that provides a detailed technical overview of a new product for repeat customers could be included.

[1243] Based on the sales procedures, the server generates training materials, including sales negotiation simulations, FAQs, success stories, etc. For example, specific training content such as "frequently asked questions and answers about the technical specifications of a new product" is created.

[1244] The training materials also aggregate relevant supporting materials and reference links, including instructional videos and white papers, all centralized within one system.

[1245] Finally, the server sends the generated business procedures and training materials to the user's device, where the user can review, download, and print the received materials, allowing them to efficiently prepare for the next business meeting.

[1246] For example, consider a scenario in which a user uploads a customer list or past sales negotiation records to the system as a CSV file. The server then receives this data, stores it in a database, and performs analysis. As a specific example, it identifies a pattern that "explaining new products with emphasis on their technical details is effective for repeat customers," and incorporates a procedure that "explains the technical specifications of new products in detail when first contacted." It also generates training materials that include "frequently asked questions and answers about the technical specifications of new products," and provides them to users.

[1247] This allows users to conduct sales activities efficiently and quickly obtain optimal procedures and training materials.

[1248] Prompt Sentence Examples

[1249] "Upload a CSV file containing your customer list and generate the optimal sales procedures. Provide us with the generated procedures and training materials."

[1250] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1251] Processing flow and each processing step

[1252] Step 1: Enter and collect data

[1253] User Action:

[1254] Users use their terminal to upload sales-related data such as customer information, past sales history, and sales negotiation details in CSV or JSON format.

[1255] input:

[1256] A CSV file containing data such as customer name, contact details, deal date, details, and results.

[1257] output:

[1258] The uploaded data file is sent to the server.

[1259] Specific behavior:

[1260] The user fills in the required fields in the data entry form on the web interface, selects the file, and clicks the upload button.

[1261] Step 2: Save your data

[1262] Server behavior:

[1263] The server securely stores the received data in a database (MySQL or PostgreSQL).

[1264] input:

[1265] CSV file or JSON data submitted by the user.

[1266] output:

[1267] Well-formed data stored in a database.

[1268] Specific behavior:

[1269] The server parses the contents of the file and stores it in a specific table in the database by executing an insert query.

[1270] Step 3: Preprocessing the data

[1271] Server behavior:

[1272] The server preprocesses the stored data using Python's Pandas library.

[1273] input:

[1274] Raw data stored in a database.

[1275] output:

[1276] Cleaned data with missing values ​​imputed and duplicates removed.

[1277] Specific behavior:

[1278] The server loads the data into a data frame, normalizes it by imputing missing values ​​with the mean and removing duplicates.

[1279] Step 4: Text analysis using natural language processing

[1280] Server behavior:

[1281] The server uses NLP libraries such as NLTK and Spacy to analyze the text data.

[1282] input:

[1283] Cleaned text data.

[1284] output:

[1285] Analysis results extracting important keywords and topics.

[1286] Specific behavior:

[1287] The server tokenizes the text data, tags it with parts of speech, and performs contextual analysis, breaking down, for example, "Describe the technical characteristics of a new product" into "New product / noun technical / adjective characteristics / noun description / verb."

[1288] Step 5: Analysis with machine learning models

[1289] Server behavior:

[1290] The server uses Scikit-learn and TensorFlow to analyze the data with machine learning algorithms.

[1291] input:

[1292] NLP text analysis results and cleaned numerical data.

[1293] output:

[1294] Analysis results that identify patterns and common factors in successful deals.

[1295] Specific behavior:

[1296] The server performs regression and cluster analysis to find successful patterns and generate clusters based on specific criteria.

[1297] Step 6: Automatic generation of business procedures

[1298] Server behavior:

[1299] The server uses a template engine such as Jinja2 to create templates for basic sales procedures and individually optimize them.

[1300] input:

[1301] Machine learning analysis results and templates.

[1302] output:

[1303] Sales playbooks optimized for users and specific customers.

[1304] Specific behavior:

[1305] The server embeds variables into the template and dynamically changes the content depending on the user's specific situation.

[1306] Step 7: Generate training material

[1307] Server behavior:

[1308] The server creates training materials based on the generated sales procedures.

[1309] input:

[1310] Customized sales procedures.

[1311] output:

[1312] Training materials including sales simulations, FAQs, success stories, and more.

[1313] Specific behavior:

[1314] The server formats the training material in Markdown or HTML and generates the specific content.

[1315] Step 8: Expanding training materials

[1316] Server behavior:

[1317] The server collects relevant supplementary material and reference links to add to the training materials.

[1318] input:

[1319] Generated training materials.

[1320] output:

[1321] Comprehensive training material with additional supplementary materials and reference links.

[1322] Specific behavior:

[1323] The server collects links to relevant videos and white papers and inserts them into the appropriate parts of the training materials.

[1324] Step 9: Send data and confirm with the user

[1325] Server behavior:

[1326] The server transmits the generated work procedure manual and training materials to the user's terminal.

[1327] input:

[1328] Final generated sales procedures and training materials.

[1329] output:

[1330] Materials sent to the user's device.

[1331] Specific behavior:

[1332] The server delivers the materials to users via email or a dedicated web portal.

[1333] Step 10: User verification and utilization

[1334] User Action:

[1335] The user checks the sent materials and downloads or prints them as necessary.

[1336] input:

[1337] Sales procedures and training materials sent from the server.

[1338] output:

[1339] Action items for users who are ready to close a deal.

[1340] Specific behavior:

[1341] Users can download materials, print them out for the next business meeting, and begin concrete preparations.

[1342] (Application example 1)

[1343] 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."

[1344] In sales activities, it is difficult to effectively use customer information and past sales history to determine the optimal sales procedure. In particular, in virtual stores, it is necessary to provide sales representatives with the optimal sales pitch and materials in real time and respond quickly. With traditional methods, these processes are highly manual, requiring time and effort, making it difficult to conduct efficient sales activities.

[1345] 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.

[1346] In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, and means for analyzing the sales data in real time and providing optimal sales pitches and materials to sales representatives of the virtual store in real time, thereby making it possible to improve the efficiency and accuracy of sales activities.

[1347] "User" refers to a person who uses the System to input or upload sales-related data.

[1348] "Sales-related data" refers to data related to sales activities, such as customer information, past sales history, and sales negotiation details.

[1349] "Storage Measures" means software or hardware for securely and efficiently storing collected business-related data.

[1350] "Analysis Tools" refers to software or hardware for analyzing collected and stored business-related data.

[1351] A "sales procedure" refers to a series of steps that indicate the optimal procedure for sales activities.

[1352] "Automatic generation means" refers to software or hardware for automatically generating sales procedures based on the results of data analysis.

[1353] "Training Materials" means the educational content and materials necessary to perform the Sales Procedures.

[1354] "Delivery means" refers to software or hardware for delivering the generated sales procedures and training materials to users.

[1355] "Real-time analysis" refers to the process of instantly analyzing collected data and providing the results in real time.

[1356] A "virtual store" refers to an online platform that conducts business over the Internet, rather than a physical store.

[1357] "Sales talk" refers to sales statements and explanations used during business negotiations with customers.

[1358] "Real-time delivery means" refers to software or hardware used to provide analysis results, sales pitches, and materials to sales representatives in real time.

[1359] MODE FOR CARRYING OUT THE INVENTION

[1360] Overall overview

[1361] This system efficiently stores and analyzes sales-related data collected from users, automatically generates optimal sales procedures and training materials, and also provides optimal sales pitches and materials to salespeople in real time in the virtual store.

[1362] Data collection

[1363] Data input / upload from users

[1364] Users use their terminals to input or upload sales-related data such as customer information, past sales history, and details of sales negotiations into the system. This data is generally provided in CSV or JSON format.

[1365] Data storage

[1366] The server receives the sales-related data sent by the user and stores it safely and efficiently. The stored data is recorded in a database and appropriately managed for later analysis.

[1367] Data analysis

[1368] Data Preprocessing

[1369] The server preprocesses the stored data, specifically by cleaning it by filling in missing values ​​and removing duplicate data, and converting it into a data format suitable for analysis.

[1370] Text analysis using natural language processing

[1371] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[1372] Applying machine learning models

[1373] The server analyzes the data using machine learning algorithms, specifically regression and cluster analysis, to identify which sales techniques were most effective.

[1374] Automatic generation of sales procedures

[1375] Creating a Procedure Template

[1376] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[1377] Individual optimization

[1378] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[1379] Creating training materials

[1380] Material content generation

[1381] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and their answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[1382] Aggregation of related information

[1383] The server aggregates supplemental materials and reference links related to the generated training materials, including instructional videos and white papers.

[1384] Real-time sales talk

[1385] Real-time analytics

[1386] Salespeople in the virtual store receive assistance from the system when negotiating with customers in real time. The server analyzes sales data in real time and provides optimal sales pitches and materials.

[1387] Real-time delivery method

[1388] The server sends the analysis results, sales pitches, and materials to the sales representative's device in real time, allowing the sales representative to respond quickly and appropriately.

[1389] Provision to users

[1390] Sending data

[1391] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[1392] User Verification

[1393] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[1394] Specific examples

[1395] For example, a user uses the system in the following scenario.

[1396] 1. Data Collection

[1397] Users upload customer lists and past sales records to the system as CSV files.

[1398] The server receives this data and stores it in a database.

[1399] 2. Data analysis

[1400] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[1401] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[1402] 3. Automatic generation of sales procedures

[1403] The server generates an optimal sales procedure based on the identified patterns.

[1404] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[1405] 4. Creating training materials

[1406] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[1407] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[1408] 5. Real-time assistance

[1409] During sales negotiations in the virtual store, the server provides sales representatives with the most appropriate sales pitches and materials in real time based on the analysis results.

[1410] 6. Provision to Users

[1411] The server transmits these materials to the user's terminal.

[1412] The user checks the sent materials and prepares for the next business meeting.

[1413] Prompt Sentence Examples

[1414] Enter customer information and past sales history data. We will generate the optimal sales procedure based on this data. Upload the data in CSV format or enter it directly in the app.

[1415] This invention allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, and also enables the virtual store to provide optimal sales pitches and materials in real time.

[1416] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1417] Step 1: Data collection

[1418] Input: The user inputs customer information and past sales history data into the system using a terminal or uploads it as a CSV file.

[1419] Processing: The terminal receives the input data, converts it into an appropriate format, and sends it to the server.

[1420] Output: The server records the received data in a storage database.

[1421] Step 2: Save data

[1422] Input: Sales-related data received by the server.

[1423] Processing: The server securely stores the received data in a database, taking appropriate security measures when storing the data.

[1424] Output: The saved data is organized for later analysis.

[1425] Step 3: Data Preprocessing

[1426] Input: Sales-related data stored on the server.

[1427] Processing: The server cleans the data by imputing missing values, removing duplicates, etc. It also normalizes the data into a format that is easier to analyze.

[1428] Output: Preprocessed and formatted data suitable for analysis.

[1429] Step 4: Text analysis using natural language processing

[1430] Input: Preprocessed text data (e.g., business negotiation details).

[1431] Processing: The server analyzes the text data using natural language processing techniques (e.g., spaCy), performing tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics.

[1432] Output: Extracted keywords and topic information.

[1433] Step 5: Applying the machine learning model

[1434] Input: Preprocessed sales data and extracted keyword and topic information.

[1435] Processing: The server analyzes the data using machine learning algorithms (e.g., cluster analysis and regression analysis) to identify which sales techniques are most effective.

[1436] Output: A pattern of optimal sales techniques.

[1437] Step 6: Auto-generate sales procedures

[1438] Input: Optimal sales technique patterns.

[1439] Processing: The server generates a basic sales procedure template based on the analysis results and customizes it for specific customers and industries.

[1440] Output: Customized sales procedures.

[1441] Step 7: Create training materials

[1442] Input: Customized Sales Procedure.

[1443] Processing: The server generates training materials including sales negotiation simulations and FAQs based on sales procedures, and also aggregates related supplementary materials and reference links.

[1444] Output: The completed training material.

[1445] Step 8: Real-time analytics and sales pitches

[1446] Input: Real-time customer data and sales rep requests.

[1447] Processing: The server analyzes customer data collected in real time and provides optimal sales pitches and materials based on the latest sales techniques and materials.

[1448] Output: Sales pitches and materials provided in real time.

[1449] Step 9: Provide to users

[1450] Input: Generated sales procedures and training materials.

[1451] Processing: The server sends these materials to the user's terminal.

[1452] Output: The user checks the sent materials and downloads or prints them as needed.

[1453] This enables the system to improve the efficiency and accuracy of sales activities.

[1454] 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.

[1455] MODE FOR CARRYING OUT THE INVENTION

[1456] The embodiments of the present invention will be described in detail below.

[1457] Overall overview

[1458] This system efficiently collects and analyzes sales-related data, automatically generates optimal sales procedures and training materials, and provides them to users. In particular, by combining it with an emotion engine that recognizes the user's emotions, it realizes more advanced and personalized sales techniques.

[1459] Data collection

[1460] Data input / upload from users

[1461] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[1462] Data storage

[1463] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[1464] Data analysis

[1465] Data Preprocessing

[1466] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[1467] Text analysis using natural language processing

[1468] The server analyzes the text data using natural language processing (NLP) techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from, for example, a business meeting transcript.

[1469] Applying machine learning models

[1470] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[1471] Automatic generation of sales procedures

[1472] Creating a Procedure Template

[1473] The server creates a basic sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[1474] Individual optimization

[1475] The server customizes the template to suit each user's or customer's specific circumstances, optimizing, for example, providing technical details first for customers in a particular industry.

[1476] Utilizing the Emotion Engine

[1477] emotion recognition

[1478] The emotion engine is designed to recognize user emotions. It uses natural language processing technology to determine emotions from text and voice data entered by the user. For example, it can identify user emotions such as "interested," "distrustful," or "satisfied" from text data during a business negotiation.

[1479] Sentiment Data Analysis

[1480] The server analyzes the emotional data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if the user has a "distrustful" feeling, it adds procedures to provide more detailed information or strengthen follow-up.

[1481] Creating training materials

[1482] Material content generation

[1483] The server generates training material content based on the sales process, including sales simulations, frequently asked questions and answers, and success stories, including stories of successful calls that highlight technical details.

[1484] Aggregation of related information

[1485] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[1486] Provision to users

[1487] Sending data

[1488] The server sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[1489] User Verification

[1490] The user can check the sent materials and prepare for the next business meeting. For example, the user can print out a procedure manual to use on-site in preparation for the next business meeting.

[1491] Specific examples

[1492] For example, a user uses the system in the following scenario.

[1493] 1. Data Collection

[1494] Users upload customer lists and past sales records to the system as CSV files.

[1495] The server receives this data and stores it in a database.

[1496] 2. Data analysis

[1497] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[1498] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[1499] 3. Automatic generation of sales procedures

[1500] The server generates an optimal sales procedure based on the identified patterns.

[1501] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[1502] 4. Creating training materials

[1503] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[1504] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[1505] 5. Applying the Emotion Engine

[1506] The emotion engine analyzes the user's emotions in real time during a business negotiation.

[1507] For example, if a user is feeling unsure during a sales conversation, the system can detect this and generate instructions to strengthen follow-up procedures.

[1508] 6. Provision to Users

[1509] The server transmits these materials to the user's terminal.

[1510] The user checks the sent materials and prepares for the next business meeting.

[1511] This system allows users to quickly obtain procedures and training materials for efficient sales activities, thereby improving sales results. In addition, by utilizing an emotion engine, it is possible to realize more personalized sales methods and improve customer satisfaction.

[1512] The processing flow will be explained below.

[1513] Step 1:

[1514] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[1515] Step 2:

[1516] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[1517] Step 3:

[1518] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[1519] Step 4:

[1520] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[1521] Step 5:

[1522] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[1523] Step 6:

[1524] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[1525] Step 7:

[1526] The server uses an emotion engine to analyze the user's emotions in real time. For example, it analyzes the user's text messages and voice data during a business meeting to determine whether the user is feeling "interested," "distrustful," or "satisfied."

[1527] Step 8:

[1528] The server analyzes the emotion data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if a user is feeling "distrustful," the server can detect this and generate instructions to strengthen follow-up procedures.

[1529] Step 9:

[1530] The server creates training materials based on the automatically generated sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[1531] Step 10:

[1532] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[1533] Step 11:

[1534] The user can check the sent materials and prepare for the next business meeting. For example, to prepare for the next business meeting, the user can print out a procedure manual and use it on-site. In this way, the user can conduct sales activities efficiently and effectively.

[1535] Example 2

[1536] 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."

[1537] There is a need for systems that can more effectively support sales activities by efficiently collecting, storing, and analyzing sales-related data, and automatically generating sales procedures and training materials. However, existing systems have not adequately performed data preprocessing and customization, or individual optimization based on user emotion recognition, which has led to problems in not improving sales efficiency and customer satisfaction.

[1538] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1539] In this invention, the server includes: means for allowing a user to input or upload sales-related data; means for saving the sales-related data; means for preprocessing the saved sales-related data; means for analyzing the saved data using natural language processing technology; means for analyzing the sales-related data by applying a machine learning algorithm; means for automatically generating sales procedures based on the analysis results; means for customizing the generated sales procedures according to the specific circumstances of each user and their customers; means for determining emotions from text data or voice data entered by the user; means for adjusting sales procedures and training materials based on the emotion data; means for generating training materials based on the sales procedures; means for aggregating supplementary materials and reference links related to the training materials; and means for providing the sales procedures and training materials to users. This centralizes the collection, storage, and analysis of sales-related data, making it possible to provide personalized sales methods utilizing emotion recognition.

[1540] "User" means any individual or legal entity that uses the System to input or upload business-related data.

[1541] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[1542] "Data preprocessing" refers to a series of processes to improve data quality, such as filling in missing values, correcting outliers, and removing duplicate data.

[1543] "Natural language processing technology" refers to technology for processing human language using computers, and includes tokenization, part-of-speech tagging, context analysis, etc.

[1544] A "machine learning algorithm" is an algorithm that finds patterns and relationships in data and makes predictions and classifications.

[1545] "Sales procedures" refer to the steps and processes for effectively carrying out sales activities, and include, for example, the flow of "initial contact → needs assessment → proposal → follow-up."

[1546] "Training materials" are educational materials created based on sales procedures, and include sales negotiation simulations, FAQs, success stories, etc.

[1547] "Emotion recognition" refers to the technology of determining emotions from a user's text data or voice data using natural language processing technology, etc.

[1548] "Related information aggregation" refers to the process of collecting supplementary materials and reference links related to training material and providing them as a single resource.

[1549] "Storage" means recording and securely storing entered or uploaded data in a database.

[1550] "Providing" refers to transmitting the generated sales procedures and training materials to the user and making them available to the user.

[1551] MODE FOR CARRYING OUT THE INVENTION

[1552] Overall overview

[1553] This system efficiently collects, stores, and analyzes sales-related data entered or uploaded by users, and automatically generates optimal sales procedures and training materials. Furthermore, it utilizes an emotion engine to recognize users' emotions and provide personalized sales techniques and training accordingly.

[1554] System configuration

[1555] This system consists of a user terminal, a server, a database, a natural language processing engine, a machine learning algorithm, an emotion recognition engine, and a user interface (UI).

[1556] Data collection

[1557] Users use their devices to input or upload sales-related data such as customer information, sales history, and details of business negotiations. The data is provided in standard CSV or JSON format. For example, it includes fields such as "customer name," "contact information," "sales negotiation date and time," and "sales negotiation details."

[1558] Data storage

[1559] The server receives sales-related data sent by users in real time and stores it securely in a database. The stored data is used for subsequent analysis and procedure generation, while also ensuring data integrity and security.

[1560] Data Preprocessing

[1561] The server preprocesses the sales-related data stored in the database, including cleaning tasks such as imputing missing values, correcting outliers, and removing duplicate data, as well as normalizing the data into a format suitable for analysis.

[1562] Text data analysis

[1563] The server uses a natural language processing engine to analyze the text data of the sales negotiation records. Specifically, it tokenizes the text, tags it for parts of speech, and performs context analysis. For example, it extracts "factors that lead to the success of a sales negotiation" from the sales negotiation records.

[1564] Applying machine learning algorithms

[1565] The server analyzes the data using machine learning algorithms, conducting regression analysis and cluster analysis to identify which sales techniques are most effective. For example, it can identify patterns in sales negotiations that resulted in high customer satisfaction.

[1566] Automatic generation of sales procedures

[1567] Based on the analysis results, the server generates a sales procedure template, which may include steps such as "initial contact," "needs assessment," "proposal," and "follow-up." This template is customized to fit the specific needs of the user.

[1568] Individual optimization

[1569] The server customizes the automatically generated sales procedure according to the specific circumstances of each user and their customer, for example, optimizing it to provide technical details to customers who are highly interested in technology at an early stage.

[1570] Utilizing the Emotion Engine

[1571] The server uses an emotion recognition engine to determine the user's emotions from the text and voice data they provide. For example, if the server determines that the user is distrustful, it will adjust the system to provide more detailed explanations and follow-up procedures.

[1572] Creating training materials

[1573] The server generates training materials based on the automatically generated sales procedures, including sales simulations, FAQs, and success stories, such as "Frequently Asked Questions and Answers about the Technical Specifications of a New Product."

[1574] Aggregation of information related to training materials

[1575] The server aggregates supplemental materials and reference links related to the generated training materials, for example, educational videos about the technical background of the product.

[1576] Sending data

[1577] The server then sends the generated sales procedure manual and training materials to the user's terminal, where the user can review these materials and prepare for the next business negotiation.

[1578] Specific examples

[1579] For example, a user can upload a "customer list" and "past sales negotiation records" to the system in CSV file format. The server receives this data, stores it in a database, and performs preprocessing. NLP technology is then used to analyze the text data and extract important keywords and patterns. A machine learning algorithm identifies the optimal sales method and generates a procedure, such as "explain the technical specifications of a new product in detail during the first contact."

[1580] Prompt Sentence Examples

[1581] The following prompts may be used:

[1582] "Analyze the data uploaded by users and generate the optimal sales method."

[1583] "Detect sentiment from text data entered by users during sales conversations and optimize procedures based on that."

[1584] In this way, the system efficiently and effectively supports sales activities and provides users with optimal sales procedures and training materials.

[1585] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1586] Step 1:

[1587] Users use their devices to input or upload sales-related data. Input includes customer information, sales history, and details of business negotiations, and is provided in CSV or JSON format. Specifically, users specify the data file through the device's user interface and click the upload button.

[1588] Input: Customer information, sales history, business details (CSV file or JSON format)

[1589] Output: Sales-related data sent from the user's device

[1590] Step 2:

[1591] The server receives sales-related data sent by users in real time and stores it in a database. The server first verifies the format and content of the data, and then securely records it in the database.

[1592] Input: Sales-related data sent from the user's terminal

[1593] Output: Sales-related data stored in a database

[1594] Step 3:

[1595] The server preprocesses the sales-related data stored in the database, specifically cleaning the data (e.g., filling in missing values, correcting outliers, removing duplicates), normalizing it, and converting it into a format suitable for analysis.

[1596] Input: Sales-related data stored in a database

[1597] Output: Preprocessed sales-related data

[1598] Step 4:

[1599] The server then analyzes the pre-processed data using natural language processing (NLP) techniques, such as text tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from the sales meeting notes.

[1600] Input: Pre-processed sales-related data

[1601] Output: Analysis results (extracted keywords, topics)

[1602] Step 5:

[1603] The server then applies machine learning algorithms to further analyze the stored sales-related data, for example, using regression analysis and cluster analysis to identify which sales techniques were most effective.

[1604] Input: Pre-processed sales-related data

[1605] Output: Machine learning analysis results (identification of effective sales methods)

[1606] Step 6:

[1607] The server automatically generates a sales procedure template based on the analysis results, for example, a template including general steps such as "initial contact → needs assessment → proposal → follow-up."

[1608] Input: Machine learning analysis results

[1609] Output: Sales Procedure Template

[1610] Step 7:

[1611] The server customizes the generated sales procedures to the specific circumstances of each user and their customer, for example, creating procedures tailored to customers in a particular industry by providing technical details upfront.

[1612] Input: Sales procedure template, customer information

[1613] Output: Customized sales procedures

[1614] Step 8:

[1615] The server uses an emotion recognition engine to determine emotions from the text and voice data entered by the user, identifying emotions such as "interested," "distrustful," and "satisfied," and adjusting sales procedures accordingly.

[1616] Input: Text data and voice data entered by the user

[1617] Output: Emotion recognition result

[1618] Step 9:

[1619] The server can then use the emotional data to adjust sales procedures and training materials, for example adding steps to strengthen follow-up if the user is "distrustful."

[1620] Input: Emotion recognition results, customized sales procedures

[1621] Output: Adjusted sales procedures

[1622] Step 10:

[1623] The server generates training materials based on the adjusted sales procedures, such as sales negotiation simulations, FAQs, and success stories.

[1624] Input: Adjusted Sales Procedures

[1625] Output: Generated training material

[1626] Step 11:

[1627] The server aggregates supplementary materials and reference links related to the generated training materials, for example, educational videos and white papers, and adds them to the training materials provided.

[1628] Input: Generated training material

[1629] Output: Training materials with supplementary materials and reference links

[1630] Step 12:

[1631] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can review the materials and prepare for the next sales meeting.

[1632] Input: Training materials with supplementary materials and reference links

[1633] Output: Data sent to the user's device

[1634] This is the specific process flow. This system allows users to receive the information and support they need to efficiently carry out their sales activities in a timely manner.

[1635] (Application example 2)

[1636] 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."

[1637] In sales activities, data collection and analysis are essential for quickly and efficiently understanding customer needs. However, conventional systems did not adequately analyze sales-related data or recognize emotions, making it difficult to provide appropriate sales techniques and training materials. Furthermore, they were unable to recognize customer emotions during the sales process in real time and adjust sales procedures accordingly, preventing improvements in sales efficiency and customer satisfaction.

[1638] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, an emotion engine that recognizes the user's emotions during the sales process in real time, and means for analyzing emotion data obtained by the emotion engine and adjusting the sales procedures. This makes it possible to efficiently analyze sales-related data and provide a personalized sales methodology based on the user's emotions.

[1639] "User" means any individual or legal entity that inputs or uploads business-related data.

[1640] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[1641] "Means for inputting or uploading" refers to a function that allows a user to input or upload sales-related data into the system.

[1642] "Means for storage" refers to the system's ability to securely store entered sales-related data.

[1643] "Means for analysis" refers to the function for analyzing stored sales-related data and extracting meaningful information.

[1644] "Means for automatic generation" refers to a function for automatically creating sales procedures based on the analysis results.

[1645] "Means for generating" refers to the function for creating training materials based on sales procedures.

[1646] "Means for providing" refers to a function for presenting the generated sales procedures and training materials to the user.

[1647] An "emotion engine" refers to a system that recognizes a user's emotions in real time and analyzes the data.

[1648] "Means for adjustment" refers to the function for appropriately adjusting sales procedures based on the emotional data obtained by the emotion engine.

[1649] Overall overview

[1650] This invention is a system that collects sales-related data from users and efficiently stores and analyzes it. Based on the analysis results, the system automatically generates optimal sales procedures and training materials and provides them to users. Furthermore, by combining it with an emotion engine, personalized sales techniques based on the user's emotions become possible.

[1651] Program structure and processing

[1652] 1. Data Collection

[1653] Users input or upload sales-related data such as customer information, sales history, and details of business negotiations through a smartphone application. This data is provided in JSON format and sent to the server.

[1654] 2. Data storage

[1655] The server securely stores the received sales-related data in a database such as MongoDB, where it is used for later analysis.

[1656] 3. Data analysis

[1657] The server uses the Google Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques, including tokenization, part-of-speech tagging, and contextual analysis.

[1658] 4. Applying machine learning models

[1659] The server uses machine learning algorithms such as TensorFlow to analyze the data, specifically using clustering algorithms (e.g., KMeans) to identify which sales tactics were effective.

[1660] 5. Automatic generation of sales procedures

[1661] The server automatically generates optimal sales procedures based on the analysis results, for example, formulating a procedure such as "explaining the technical specifications of a new product in detail when first contacting the customer."

[1662] 6. Creating training materials

[1663] The server creates training materials based on the generated sales procedures, including sales negotiation simulations, FAQs, and success stories.

[1664] 7. Leveraging Emotional Engines

[1665] The emotion engine uses the IBM Watson Emotion Analysis API to recognize user emotions in real time, for example, if a user feels distrust during a sales meeting, it can sense this and adjust follow-up procedures.

[1666] 8. Provision to Users

[1667] The server sends the generated sales procedure manual and training materials to the user's terminal, where the user can review the materials and prepare for the next business meeting.

[1668] Specific examples

[1669] 1. Data Collection

[1670] The user uploads a customer list and past sales records in JSON format from a smartphone application.

[1671] 2. Emotion recognition

[1672] Based on the text data during the business negotiation, the emotion engine determines the user's emotion as "interested."

[1673] 3. Sales procedure generation

[1674] The procedure "explain the technical specifications of a new product in detail" is automatically generated and provided to the user.

[1675] Prompt Sentence Examples

[1676] To prepare for the next sales meeting, propose a procedure to stimulate the customer's interest in a new product. Analyze customer information, sales history, and sales content data, and take into account emotion recognition to provide the optimal sales procedure. If the customer is determined to be interested, generate a procedure to provide technical details.

[1677] This system allows sales representatives to quickly access procedures and training materials to conduct sales activities efficiently, and the emotional engine enables personalized sales techniques, which is expected to improve customer satisfaction.

[1678] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1679] Step 1:

[1680] Users use a smartphone application to input or upload sales-related data such as customer information, sales history, and sales negotiation details in JSON format. Input includes customer name, contact information, sales negotiation date and time, sales negotiation details, etc. The output is JSON format data sent to the server.

[1681] Step 2:

[1682] The server receives sales-related data and stores it in a database such as MongoDB. The server keeps the data consistent and secure, and stores it for future analysis. The input is the JSON-formatted data sent by the user, and the output is the sales-related data securely stored in the database.

[1683] Step 3:

[1684] The server uses the Google Cloud Natural Language API to analyze the stored data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and context analysis. The input is the text data stored in the database, and the output is the analysis result, tokenized and part-of-speech tagged text data.

[1685] Step 4:

[1686] The server applies machine learning algorithms such as TensorFlow to analyze the data. Specifically, it uses clustering algorithms (e.g., KMeans) to identify patterns of successful sales techniques. The input is tokenized and part-of-speech tagged text data, and the output is a list of clustered patterns.

[1687] Step 5:

[1688] The server automatically generates optimal sales procedures based on the analysis results. For example, it formulates a specific procedure such as "explaining the technical specifications of a new product in detail during the first contact." The input is a list of clustered patterns, and the output is an automatically generated sales procedure manual.

[1689] Step 6:

[1690] The server creates training materials based on the generated sales procedures. Specifically, it creates training materials that include sales negotiation simulations, FAQs, stories of success cases, etc. The input is the automatically generated sales procedures manual, and the output is the completed training materials.

[1691] Step 7:

[1692] The emotion engine uses the IBM Watson Emotion Analysis API to recognize user emotions in real time. The targets for emotion recognition include text and voice data from business negotiations. The input is text and voice data acquired in real time, and the output is analyzed emotion data (e.g., "interested" or "distrustful").

[1693] Step 8:

[1694] The server analyzes the emotion data obtained by the emotion engine and adjusts the sales procedure. For example, if "distrust" is determined to be high, it generates instructions to strengthen follow-up procedures. The input is emotion data from the emotion engine, and the output is an adjusted sales procedure.

[1695] Step 9:

[1696] The server sends the generated and adjusted sales procedures and training materials to the user's terminal. The user checks these materials and prepares for the next business meeting. The adjusted sales procedures and training materials are obtained as input, and the materials displayed on the user's terminal are obtained as output.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] [Fourth embodiment]

[1701] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1702] 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.

[1703] 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).

[1704] 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.

[1705] 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.

[1706] 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).

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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.

[1711] 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.

[1712] 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.

[1713] 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."

[1714] MODE FOR CARRYING OUT THE INVENTION

[1715] The embodiments of the present invention will be described in detail below.

[1716] Overall overview

[1717] This system efficiently collects and analyzes sales-related data, automatically generating optimal sales procedures and training materials, and providing them to users. The server uses natural language processing technology and machine learning algorithms to analyze the data provided by users, and generates sales procedures and training materials based on the results.

[1718] Data collection

[1719] Data input / upload from users

[1720] Users use their devices to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format.

[1721] Data storage

[1722] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[1723] Data analysis

[1724] Data Preprocessing

[1725] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[1726] Text analysis using natural language processing

[1727] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[1728] Applying machine learning models

[1729] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[1730] Automatic generation of sales procedures

[1731] Creating a Procedure Template

[1732] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[1733] Individual optimization

[1734] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[1735] Creating training materials

[1736] Material content generation

[1737] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[1738] Aggregation of related information

[1739] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[1740] Provision to users

[1741] Sending data

[1742] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[1743] User Verification

[1744] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[1745] Specific examples

[1746] For example, a user uses the system in the following scenario.

[1747] 1. Data Collection

[1748] Users upload customer lists and past sales records to the system as CSV files.

[1749] The server receives this data and stores it in a database.

[1750] 2. Data analysis

[1751] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[1752] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[1753] 3. Automatic generation of sales procedures

[1754] The server generates an optimal sales procedure based on the identified patterns.

[1755] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[1756] 4. Creating training materials

[1757] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[1758] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[1759] 5. Provision to Users

[1760] The server transmits these materials to the user's terminal.

[1761] The user checks the sent materials and prepares for the next business meeting.

[1762] This system allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, thereby improving sales results.

[1763] The processing flow will be explained below.

[1764] Step 1:

[1765] Users use their devices to input or upload sales-related data, such as customer information, sales history, and sales negotiation details, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and sales negotiation details.

[1766] Step 2:

[1767] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[1768] Step 3:

[1769] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[1770] Step 4:

[1771] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[1772] Step 5:

[1773] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[1774] Step 6:

[1775] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[1776] Step 7:

[1777] The server generates training materials based on individually optimized sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[1778] Step 8:

[1779] The server sends the generated sales procedures and training materials to the user's device. The user can check these materials on the device and download or print them as needed. This allows the user to refer to them while proceeding with their sales activities.

[1780] Example 1

[1781] 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."

[1782] Conventional sales-related data collection and analysis systems require a lot of time and effort for manual data entry and analysis, and the generation of specific sales procedures and training materials based on analysis results is not automated, making it difficult to support efficient sales activities.Furthermore, it is difficult to optimize the systems to suit the specific circumstances of individual users and customers, resulting in a lack of versatility.

[1783] 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.

[1784] In this invention, the server includes means for allowing a user to input or upload information, means for saving the information, means for preprocessing the saved information, means for analyzing the preprocessed information using natural language processing technology, means for analyzing the analyzed information using a machine learning algorithm, means for automatically generating business procedures based on the analysis results, means for generating training materials based on the business procedures, and means for providing the business procedures and training materials to users. This enables efficient collection and analysis of sales-related data and automatic generation of optimized procedures and training materials.

[1785] A "user" is a person or entity that operates the system and inputs or uploads information.

[1786] "Information" refers to a wide range of data, including sales-related data such as customer information, past sales history, and business negotiation details.

[1787] "Server" means an integrated hardware and software system that stores, pre-processes, parses, and analyzes information sent by users, and generates and provides business procedures and training materials based on the results.

[1788] "Input or Upload Means" refers to the interface or protocol by which a user provides information to the system.

[1789] "Storage" refers to techniques and devices that record received information in a persistent storage medium, such as a database.

[1790] "Preprocessing means" refers to the process of converting stored information into a format suitable for analysis by completing missing values, removing duplicate data, normalizing data, etc.

[1791] "Means of analysis using natural language processing technology" refers to the process of analyzing text data using technologies such as tokenization, part-of-speech tagging, and contextual analysis.

[1792] "Methods of analysis using machine learning algorithms" refers to the process of statistically analyzing information to identify patterns and trends using various machine learning techniques, such as regression analysis and cluster analysis.

[1793] "Means for automatically generating business procedures" refers to the process by which the system automatically generates specific and optimal sales procedures based on the analysis results of natural language processing technology and machine learning algorithms.

[1794] "Means for generating educational materials" refers to the process of creating learning content such as sales negotiation simulations, FAQs, and success stories based on the generated business procedures.

[1795] "Means for providing" refers to the process of transmitting the generated business procedures and training materials to the user's terminal so that the user can view, download, and print them.

[1796] The present invention relates to a system for collecting and analyzing sales-related data and automatically generating optimal sales procedures and training materials. A specific embodiment of this system will be described below.

[1797] The server is equipped with an input means for receiving information provided by users. Users use their terminals to input or upload sales-related data, such as customer information, past sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files or JSON format.

[1798] The server has a secure storage facility to store the received information, which is then stored in a database (e.g., MySQL or PostgreSQL) for further analysis.

[1799] The server then uses Python's Pandas library to preprocess the stored information, which includes data cleaning (imputing missing values, removing duplicates), normalization, and other steps to convert the data into a format suitable for analysis.

[1800] The preprocessed information is then analyzed using natural language processing (NLP) techniques. This analysis involves tokenization, part-of-speech tagging, and contextual analysis using NLP libraries such as NLTK and Spacy. For example, a text such as "Describes the technical characteristics of a new product" is broken down into "New product / noun, technical / adjective, characteristics / noun, description / verb."

[1801] The server then applies machine learning algorithms (e.g., Scikit-learn or TensorFlow) to analyze the information. This analysis includes regression analysis and cluster analysis, which can identify common factors behind successful deals. For example, clusters can be generated based on past deal results to identify patterns of success.

[1802] Based on the analysis results, the server automatically generates business procedures. It uses a template engine such as Jinja2 to create a basic sales procedure template, and then individually optimizes the template according to the circumstances of the user and specific customer. For example, a procedure that provides a detailed technical overview of a new product for repeat customers could be included.

[1803] Based on the sales procedures, the server generates training materials, including sales negotiation simulations, FAQs, success stories, etc. For example, specific training content such as "frequently asked questions and answers about the technical specifications of a new product" is created.

[1804] The training materials also aggregate relevant supporting materials and reference links, including instructional videos and white papers, all centralized within one system.

[1805] Finally, the server sends the generated business procedures and training materials to the user's device, where the user can review, download, and print the received materials, allowing them to efficiently prepare for the next business meeting.

[1806] For example, consider a scenario in which a user uploads a customer list or past sales negotiation records to the system as a CSV file. The server then receives this data, stores it in a database, and performs analysis. As a specific example, it identifies a pattern that "explaining new products with emphasis on their technical details is effective for repeat customers," and incorporates a procedure that "explains the technical specifications of new products in detail when first contacted." It also generates training materials that include "frequently asked questions and answers about the technical specifications of new products," and provides them to users.

[1807] This allows users to conduct sales activities efficiently and quickly obtain optimal procedures and training materials.

[1808] Prompt Sentence Examples

[1809] "Upload a CSV file containing your customer list and generate the optimal sales procedures. Provide us with the generated procedures and training materials."

[1810] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1811] Processing flow and each processing step

[1812] Step 1: Enter and collect data

[1813] User Action:

[1814] Users use their terminal to upload sales-related data such as customer information, past sales history, and sales negotiation details in CSV or JSON format.

[1815] input:

[1816] A CSV file containing data such as customer name, contact details, deal date, details, and results.

[1817] output:

[1818] The uploaded data file is sent to the server.

[1819] Specific behavior:

[1820] The user fills in the required fields in the data entry form on the web interface, selects the file, and clicks the upload button.

[1821] Step 2: Save your data

[1822] Server behavior:

[1823] The server securely stores the received data in a database (MySQL or PostgreSQL).

[1824] input:

[1825] CSV file or JSON data submitted by the user.

[1826] output:

[1827] Well-formed data stored in a database.

[1828] Specific behavior:

[1829] The server parses the contents of the file and stores it in a specific table in the database by executing an insert query.

[1830] Step 3: Preprocessing the data

[1831] Server behavior:

[1832] The server preprocesses the stored data using Python's Pandas library.

[1833] input:

[1834] Raw data stored in a database.

[1835] output:

[1836] Cleaned data with missing values ​​imputed and duplicates removed.

[1837] Specific behavior:

[1838] The server loads the data into a data frame, normalizes it by imputing missing values ​​with the mean and removing duplicates.

[1839] Step 4: Text analysis using natural language processing

[1840] Server behavior:

[1841] The server uses NLP libraries such as NLTK and Spacy to analyze the text data.

[1842] input:

[1843] Cleaned text data.

[1844] output:

[1845] Analysis results extracting important keywords and topics.

[1846] Specific behavior:

[1847] The server tokenizes the text data, tags it with parts of speech, and performs contextual analysis, breaking down, for example, "Describe the technical characteristics of a new product" into "New product / noun technical / adjective characteristics / noun description / verb."

[1848] Step 5: Analysis with machine learning models

[1849] Server behavior:

[1850] The server uses Scikit-learn and TensorFlow to analyze the data with machine learning algorithms.

[1851] input:

[1852] NLP text analysis results and cleaned numerical data.

[1853] output:

[1854] Analysis results that identify patterns and common factors in successful deals.

[1855] Specific behavior:

[1856] The server performs regression and cluster analysis to find successful patterns and generate clusters based on specific criteria.

[1857] Step 6: Automatic generation of business procedures

[1858] Server behavior:

[1859] The server uses a template engine such as Jinja2 to create templates for basic sales procedures and individually optimize them.

[1860] input:

[1861] Machine learning analysis results and templates.

[1862] output:

[1863] Sales playbooks optimized for users and specific customers.

[1864] Specific behavior:

[1865] The server embeds variables into the template and dynamically changes the content depending on the user's specific situation.

[1866] Step 7: Generate training material

[1867] Server behavior:

[1868] The server creates training materials based on the generated sales procedures.

[1869] input:

[1870] Customized sales procedures.

[1871] output:

[1872] Training materials including sales simulations, FAQs, success stories, and more.

[1873] Specific behavior:

[1874] The server formats the training material in Markdown or HTML and generates the specific content.

[1875] Step 8: Expanding training materials

[1876] Server behavior:

[1877] The server collects relevant supplementary material and reference links to add to the training materials.

[1878] input:

[1879] Generated training materials.

[1880] output:

[1881] Comprehensive training material with additional supplementary materials and reference links.

[1882] Specific behavior:

[1883] The server collects links to relevant videos and white papers and inserts them into the appropriate parts of the training materials.

[1884] Step 9: Send data and confirm with the user

[1885] Server behavior:

[1886] The server transmits the generated work procedure manual and training materials to the user's terminal.

[1887] input:

[1888] Final generated sales procedures and training materials.

[1889] output:

[1890] Materials sent to the user's device.

[1891] Specific behavior:

[1892] The server delivers the materials to users via email or a dedicated web portal.

[1893] Step 10: User verification and utilization

[1894] User Action:

[1895] The user checks the sent materials and downloads or prints them as necessary.

[1896] input:

[1897] Sales procedures and training materials sent from the server.

[1898] output:

[1899] Action items for users who are ready to close a deal.

[1900] Specific behavior:

[1901] Users can download materials, print them out for the next business meeting, and begin concrete preparations.

[1902] (Application example 1)

[1903] 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."

[1904] In sales activities, it is difficult to effectively use customer information and past sales history to determine the optimal sales procedure. In particular, in virtual stores, it is necessary to provide sales representatives with the optimal sales pitch and materials in real time and respond quickly. With traditional methods, these processes are highly manual, requiring time and effort, making it difficult to conduct efficient sales activities.

[1905] 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.

[1906] In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, and means for analyzing the sales data in real time and providing optimal sales pitches and materials to sales representatives of the virtual store in real time, thereby making it possible to improve the efficiency and accuracy of sales activities.

[1907] "User" refers to a person who uses the System to input or upload sales-related data.

[1908] "Sales-related data" refers to data related to sales activities, such as customer information, past sales history, and sales negotiation details.

[1909] "Storage Measures" means software or hardware for securely and efficiently storing collected business-related data.

[1910] "Analysis Tools" refers to software or hardware for analyzing collected and stored business-related data.

[1911] A "sales procedure" refers to a series of steps that indicate the optimal procedure for sales activities.

[1912] "Automatic generation means" refers to software or hardware for automatically generating sales procedures based on the results of data analysis.

[1913] "Training Materials" means the educational content and materials necessary to perform the Sales Procedures.

[1914] "Delivery means" refers to software or hardware for delivering the generated sales procedures and training materials to users.

[1915] "Real-time analysis" refers to the process of instantly analyzing collected data and providing the results in real time.

[1916] A "virtual store" refers to an online platform that conducts business over the Internet, rather than a physical store.

[1917] "Sales talk" refers to sales statements and explanations used during business negotiations with customers.

[1918] "Real-time delivery means" refers to software or hardware used to provide analysis results, sales pitches, and materials to sales representatives in real time.

[1919] MODE FOR CARRYING OUT THE INVENTION

[1920] Overall overview

[1921] This system efficiently stores and analyzes sales-related data collected from users, automatically generates optimal sales procedures and training materials, and also provides optimal sales pitches and materials to salespeople in real time in the virtual store.

[1922] Data collection

[1923] Data input / upload from users

[1924] Users use their terminals to input or upload sales-related data such as customer information, past sales history, and details of sales negotiations into the system. This data is generally provided in CSV or JSON format.

[1925] Data storage

[1926] The server receives the sales-related data sent by the user and stores it safely and efficiently. The stored data is recorded in a database and appropriately managed for later analysis.

[1927] Data analysis

[1928] Data Preprocessing

[1929] The server preprocesses the stored data, specifically by cleaning it by filling in missing values ​​and removing duplicate data, and converting it into a data format suitable for analysis.

[1930] Text analysis using natural language processing

[1931] The server analyzes the text data using natural language processing techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from past sales negotiation data, for example.

[1932] Applying machine learning models

[1933] The server analyzes the data using machine learning algorithms, specifically regression and cluster analysis, to identify which sales techniques were most effective.

[1934] Automatic generation of sales procedures

[1935] Creating a Procedure Template

[1936] The server creates a template for a basic sales procedure based on the analysis results, such as a typical sales procedure such as "initial contact → needs assessment → proposal → follow-up."

[1937] Individual optimization

[1938] The server customizes the procedure template to suit the specific circumstances of each user or customer, optimizing, for example, providing technical details first for customers in certain industries.

[1939] Creating training materials

[1940] Material content generation

[1941] The server generates training material content based on sales procedures, including sales negotiation simulations, frequently asked questions and their answers, success stories, etc. For example, it creates training content that simulates the explanation of a new product and customer reactions to it.

[1942] Aggregation of related information

[1943] The server aggregates supplemental materials and reference links related to the generated training materials, including instructional videos and white papers.

[1944] Real-time sales talk

[1945] Real-time analytics

[1946] Salespeople in the virtual store receive assistance from the system when negotiating with customers in real time. The server analyzes sales data in real time and provides optimal sales pitches and materials.

[1947] Real-time delivery method

[1948] The server sends the analysis results, sales pitches, and materials to the sales representative's device in real time, allowing the sales representative to respond quickly and appropriately.

[1949] Provision to users

[1950] Sending data

[1951] The server sends the generated sales procedures and training materials to the user's terminal, allowing the user to refer to these materials at any time.

[1952] User Verification

[1953] The user can check the sent materials and download or print them as needed. For example, a procedure manual can be printed to prepare for the next business meeting and used on-site.

[1954] Specific examples

[1955] For example, a user uses the system in the following scenario.

[1956] 1. Data Collection

[1957] Users upload customer lists and past sales records to the system as CSV files.

[1958] The server receives this data and stores it in a database.

[1959] 2. Data analysis

[1960] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[1961] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[1962] 3. Automatic generation of sales procedures

[1963] The server generates an optimal sales procedure based on the identified patterns.

[1964] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[1965] 4. Creating training materials

[1966] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[1967] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[1968] 5. Real-time assistance

[1969] During sales negotiations in the virtual store, the server provides sales representatives with the most appropriate sales pitches and materials in real time based on the analysis results.

[1970] 6. Provision to Users

[1971] The server transmits these materials to the user's terminal.

[1972] The user checks the sent materials and prepares for the next business meeting.

[1973] Prompt Sentence Examples

[1974] Enter customer information and past sales history data. We will generate the optimal sales procedure based on this data. Upload the data in CSV format or enter it directly in the app.

[1975] This invention allows users to quickly obtain procedures and training materials for conducting sales activities efficiently, and also enables the virtual store to provide optimal sales pitches and materials in real time.

[1976] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1977] Step 1: Data collection

[1978] Input: The user inputs customer information and past sales history data into the system using a terminal or uploads it as a CSV file.

[1979] Processing: The terminal receives the input data, converts it into an appropriate format, and sends it to the server.

[1980] Output: The server records the received data in a storage database.

[1981] Step 2: Save data

[1982] Input: Sales-related data received by the server.

[1983] Processing: The server securely stores the received data in a database, taking appropriate security measures when storing the data.

[1984] Output: The saved data is organized for later analysis.

[1985] Step 3: Data Preprocessing

[1986] Input: Sales-related data stored on the server.

[1987] Processing: The server cleans the data by imputing missing values, removing duplicates, etc. It also normalizes the data into a format that is easier to analyze.

[1988] Output: Preprocessed and formatted data suitable for analysis.

[1989] Step 4: Text analysis using natural language processing

[1990] Input: Preprocessed text data (e.g., business negotiation details).

[1991] Processing: The server analyzes the text data using natural language processing techniques (e.g., spaCy), performing tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics.

[1992] Output: Extracted keywords and topic information.

[1993] Step 5: Applying the machine learning model

[1994] Input: Preprocessed sales data and extracted keyword and topic information.

[1995] Processing: The server analyzes the data using machine learning algorithms (e.g., cluster analysis and regression analysis) to identify which sales techniques are most effective.

[1996] Output: A pattern of optimal sales techniques.

[1997] Step 6: Auto-generate sales procedures

[1998] Input: Optimal sales technique patterns.

[1999] Processing: The server generates a basic sales procedure template based on the analysis results and customizes it for specific customers and industries.

[2000] Output: Customized sales procedures.

[2001] Step 7: Create training materials

[2002] Input: Customized Sales Procedure.

[2003] Processing: The server generates training materials including sales negotiation simulations and FAQs based on sales procedures, and also aggregates related supplementary materials and reference links.

[2004] Output: The completed training material.

[2005] Step 8: Real-time analytics and sales pitches

[2006] Input: Real-time customer data and sales rep requests.

[2007] Processing: The server analyzes customer data collected in real time and provides optimal sales pitches and materials based on the latest sales techniques and materials.

[2008] Output: Sales pitches and materials provided in real time.

[2009] Step 9: Provide to users

[2010] Input: Generated sales procedures and training materials.

[2011] Processing: The server sends these materials to the user's terminal.

[2012] Output: The user checks the sent materials and downloads or prints them as needed.

[2013] This enables the system to improve the efficiency and accuracy of sales activities.

[2014] 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.

[2015] MODE FOR CARRYING OUT THE INVENTION

[2016] The embodiments of the present invention will be described in detail below.

[2017] Overall overview

[2018] This system efficiently collects and analyzes sales-related data, automatically generates optimal sales procedures and training materials, and provides them to users. In particular, by combining it with an emotion engine that recognizes the user's emotions, it realizes more advanced and personalized sales techniques.

[2019] Data collection

[2020] Data input / upload from users

[2021] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. This data is provided in standard formats such as CSV files and JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[2022] Data storage

[2023] The server receives and securely stores the sales-related data sent by the user, which is then recorded in a database for later analysis.

[2024] Data analysis

[2025] Data Preprocessing

[2026] The server preprocesses the stored data, specifically cleaning the data (filling in missing values, removing duplicate data, etc.) and normalizing it, and converting it into a data format suitable for analysis.

[2027] Text analysis using natural language processing

[2028] The server analyzes the text data using natural language processing (NLP) techniques, which include steps such as tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from, for example, a business meeting transcript.

[2029] Applying machine learning models

[2030] The server uses machine learning algorithms to analyze the data. Specifically, it uses regression analysis and cluster analysis to identify which sales techniques were most effective. For example, it clusters the patterns of successful sales negotiations and finds common factors.

[2031] Automatic generation of sales procedures

[2032] Creating a Procedure Template

[2033] The server creates a basic sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[2034] Individual optimization

[2035] The server customizes the template to suit each user's or customer's specific circumstances, optimizing, for example, providing technical details first for customers in a particular industry.

[2036] Utilizing the Emotion Engine

[2037] emotion recognition

[2038] The emotion engine is designed to recognize user emotions. It uses natural language processing technology to determine emotions from text and voice data entered by the user. For example, it can identify user emotions such as "interested," "distrustful," or "satisfied" from text data during a business negotiation.

[2039] Sentiment Data Analysis

[2040] The server analyzes the emotional data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if the user has a "distrustful" feeling, it adds procedures to provide more detailed information or strengthen follow-up.

[2041] Creating training materials

[2042] Material content generation

[2043] The server generates training material content based on the sales process, including sales simulations, frequently asked questions and answers, and success stories, including stories of successful calls that highlight technical details.

[2044] Aggregation of related information

[2045] The server aggregates supplemental materials and reference links related to the generated training material, including instructional videos and white papers, for example, providing in-depth videos on the technical background of the product.

[2046] Provision to users

[2047] Sending data

[2048] The server sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[2049] User Verification

[2050] The user can check the sent materials and prepare for the next business meeting. For example, the user can print out a procedure manual to use on-site in preparation for the next business meeting.

[2051] Specific examples

[2052] For example, a user uses the system in the following scenario.

[2053] 1. Data Collection

[2054] Users upload customer lists and past sales records to the system as CSV files.

[2055] The server receives this data and stores it in a database.

[2056] 2. Data analysis

[2057] The server preprocesses the stored data and analyzes the text data using NLP techniques.

[2058] For example, identify a pattern that "explanations that emphasize the technical details of new products are effective for repeat customers."

[2059] 3. Automatic generation of sales procedures

[2060] The server generates an optimal sales procedure based on the identified patterns.

[2061] Specifically, we will incorporate a procedure that involves providing a detailed explanation of the technical specifications of new products when first contacted.

[2062] 4. Creating training materials

[2063] The server creates a sales negotiation simulation and FAQs based on the generated sales procedures.

[2064] For example, create training materials that include frequently asked questions and answers about the technical specifications of a new product.

[2065] 5. Applying the Emotion Engine

[2066] The emotion engine analyzes the user's emotions in real time during a business negotiation.

[2067] For example, if a user is feeling unsure during a sales conversation, the system can detect this and generate instructions to strengthen follow-up procedures.

[2068] 6. Provision to Users

[2069] The server transmits these materials to the user's terminal.

[2070] The user checks the sent materials and prepares for the next business meeting.

[2071] This system allows users to quickly obtain procedures and training materials for efficient sales activities, thereby improving sales results. In addition, by utilizing an emotion engine, it is possible to realize more personalized sales methods and improve customer satisfaction.

[2072] The processing flow will be explained below.

[2073] Step 1:

[2074] Users use their devices to input or upload sales-related data, such as customer information, sales history, and details of sales negotiations, into the system. Specifically, they provide data in standard formats such as CSV files or JSON format. This data includes customer names, contact information, sales negotiation dates and times, and details of sales negotiations.

[2075] Step 2:

[2076] The server receives sales-related data sent by the user and stores it in a database. The server validates the format of the data and returns an error message to the user if it is not correct. Correct data is stored in the database and used for subsequent processing.

[2077] Step 3:

[2078] The server preprocesses the stored data, cleaning it, filling in missing values, removing duplicates, and normalizing it, converting it into a data format suitable for analysis.

[2079] Step 4:

[2080] The server analyzes the text data using natural language processing (NLP) techniques. Specifically, it performs tokenization, part-of-speech tagging, and contextual analysis to extract important keywords and topics from the text data. For example, it identifies important topics such as "price negotiation" and "technical support" from a sales negotiation record.

[2081] Step 5:

[2082] The server analyzes the data using machine learning algorithms, using regression and cluster analysis to identify which sales techniques were most effective, for example by clustering patterns of successful deals and finding common factors.

[2083] Step 6:

[2084] The server creates a sales procedure template based on the analysis results. The server bases the template on a general sales procedure such as "initial contact → needs assessment → proposal → follow-up." This template is customized according to the specific circumstances of each user or customer.

[2085] Step 7:

[2086] The server uses an emotion engine to analyze the user's emotions in real time. For example, it analyzes the user's text messages and voice data during a business meeting to determine whether the user is feeling "interested," "distrustful," or "satisfied."

[2087] Step 8:

[2088] The server analyzes the emotion data detected by the emotion engine and reflects it in the generation of sales procedures and training materials. For example, if a user is feeling "distrustful," the server can detect this and generate instructions to strengthen follow-up procedures.

[2089] Step 9:

[2090] The server creates training materials based on the automatically generated sales procedures, including content such as sales negotiation simulations, frequently asked questions and answers, and success stories. As success stories, it adds stories of successful visits that highlight technical details.

[2091] Step 10:

[2092] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can check the materials and download or print them as needed.

[2093] Step 11:

[2094] The user can check the sent materials and prepare for the next business meeting. For example, to prepare for the next business meeting, the user can print out a procedure manual and use it on-site. In this way, the user can conduct sales activities efficiently and effectively.

[2095] Example 2

[2096] 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."

[2097] There is a need for systems that can more effectively support sales activities by efficiently collecting, storing, and analyzing sales-related data, and automatically generating sales procedures and training materials. However, existing systems have not adequately performed data preprocessing and customization, or individual optimization based on user emotion recognition, which has led to problems in not improving sales efficiency and customer satisfaction.

[2098] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2099] In this invention, the server includes: means for allowing a user to input or upload sales-related data; means for saving the sales-related data; means for preprocessing the saved sales-related data; means for analyzing the saved data using natural language processing technology; means for analyzing the sales-related data by applying a machine learning algorithm; means for automatically generating sales procedures based on the analysis results; means for customizing the generated sales procedures according to the specific circumstances of each user and their customers; means for determining emotions from text data or voice data entered by the user; means for adjusting sales procedures and training materials based on the emotion data; means for generating training materials based on the sales procedures; means for aggregating supplementary materials and reference links related to the training materials; and means for providing the sales procedures and training materials to users. This centralizes the collection, storage, and analysis of sales-related data, making it possible to provide personalized sales methods utilizing emotion recognition.

[2100] "User" means any individual or legal entity that uses the System to input or upload business-related data.

[2101] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[2102] "Data preprocessing" refers to a series of processes to improve data quality, such as filling in missing values, correcting outliers, and removing duplicate data.

[2103] "Natural language processing technology" refers to technology for processing human language using computers, and includes tokenization, part-of-speech tagging, context analysis, etc.

[2104] A "machine learning algorithm" is an algorithm that finds patterns and relationships in data and makes predictions and classifications.

[2105] "Sales procedures" refer to the steps and processes for effectively carrying out sales activities, and include, for example, the flow of "initial contact → needs assessment → proposal → follow-up."

[2106] "Training materials" are educational materials created based on sales procedures, and include sales negotiation simulations, FAQs, success stories, etc.

[2107] "Emotion recognition" refers to the technology of determining emotions from a user's text data or voice data using natural language processing technology, etc.

[2108] "Related information aggregation" refers to the process of collecting supplementary materials and reference links related to training material and providing them as a single resource.

[2109] "Storage" means recording and securely storing entered or uploaded data in a database.

[2110] "Providing" refers to transmitting the generated sales procedures and training materials to the user and making them available to the user.

[2111] MODE FOR CARRYING OUT THE INVENTION

[2112] Overall overview

[2113] This system efficiently collects, stores, and analyzes sales-related data entered or uploaded by users, and automatically generates optimal sales procedures and training materials. Furthermore, it utilizes an emotion engine to recognize users' emotions and provide personalized sales techniques and training accordingly.

[2114] System configuration

[2115] This system consists of a user terminal, a server, a database, a natural language processing engine, a machine learning algorithm, an emotion recognition engine, and a user interface (UI).

[2116] Data collection

[2117] Users use their devices to input or upload sales-related data such as customer information, sales history, and details of business negotiations. The data is provided in standard CSV or JSON format. For example, it includes fields such as "customer name," "contact information," "sales negotiation date and time," and "sales negotiation details."

[2118] Data storage

[2119] The server receives sales-related data sent by users in real time and stores it securely in a database. The stored data is used for subsequent analysis and procedure generation, while also ensuring data integrity and security.

[2120] Data Preprocessing

[2121] The server preprocesses the sales-related data stored in the database, including cleaning tasks such as imputing missing values, correcting outliers, and removing duplicate data, as well as normalizing the data into a format suitable for analysis.

[2122] Text data analysis

[2123] The server uses a natural language processing engine to analyze the text data of the sales negotiation records. Specifically, it tokenizes the text, tags it for parts of speech, and performs context analysis. For example, it extracts "factors that lead to the success of a sales negotiation" from the sales negotiation records.

[2124] Applying machine learning algorithms

[2125] The server analyzes the data using machine learning algorithms, conducting regression analysis and cluster analysis to identify which sales techniques are most effective. For example, it can identify patterns in sales negotiations that resulted in high customer satisfaction.

[2126] Automatic generation of sales procedures

[2127] Based on the analysis results, the server generates a sales procedure template, which may include steps such as "initial contact," "needs assessment," "proposal," and "follow-up." This template is customized to fit the specific needs of the user.

[2128] Individual optimization

[2129] The server customizes the automatically generated sales procedure according to the specific circumstances of each user and their customer, for example, optimizing it to provide technical details to customers who are highly interested in technology at an early stage.

[2130] Utilizing the Emotion Engine

[2131] The server uses an emotion recognition engine to determine the user's emotions from the text and voice data they provide. For example, if the server determines that the user is distrustful, it will adjust the system to provide more detailed explanations and follow-up procedures.

[2132] Creating training materials

[2133] The server generates training materials based on the automatically generated sales procedures, including sales simulations, FAQs, and success stories, such as "Frequently Asked Questions and Answers about the Technical Specifications of a New Product."

[2134] Aggregation of information related to training materials

[2135] The server aggregates supplemental materials and reference links related to the generated training materials, for example, educational videos about the technical background of the product.

[2136] Sending data

[2137] The server then sends the generated sales procedure manual and training materials to the user's terminal, where the user can review these materials and prepare for the next business negotiation.

[2138] Specific examples

[2139] For example, a user can upload a "customer list" and "past sales negotiation records" to the system in CSV file format. The server receives this data, stores it in a database, and performs preprocessing. NLP technology is then used to analyze the text data and extract important keywords and patterns. A machine learning algorithm identifies the optimal sales method and generates a procedure, such as "explain the technical specifications of a new product in detail during the first contact."

[2140] Prompt Sentence Examples

[2141] The following prompts may be used:

[2142] "Analyze the data uploaded by users and generate the optimal sales method."

[2143] "Detect sentiment from text data entered by users during sales conversations and optimize procedures based on that."

[2144] In this way, the system efficiently and effectively supports sales activities and provides users with optimal sales procedures and training materials.

[2145] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2146] Step 1:

[2147] Users use their devices to input or upload sales-related data. Input includes customer information, sales history, and details of business negotiations, and is provided in CSV or JSON format. Specifically, users specify the data file through the device's user interface and click the upload button.

[2148] Input: Customer information, sales history, business details (CSV file or JSON format)

[2149] Output: Sales-related data sent from the user's device

[2150] Step 2:

[2151] The server receives sales-related data sent by users in real time and stores it in a database. The server first verifies the format and content of the data, and then securely records it in the database.

[2152] Input: Sales-related data sent from the user's terminal

[2153] Output: Sales-related data stored in a database

[2154] Step 3:

[2155] The server preprocesses the sales-related data stored in the database, specifically cleaning the data (e.g., filling in missing values, correcting outliers, removing duplicates), normalizing it, and converting it into a format suitable for analysis.

[2156] Input: Sales-related data stored in a database

[2157] Output: Preprocessed sales-related data

[2158] Step 4:

[2159] The server then analyzes the pre-processed data using natural language processing (NLP) techniques, such as text tokenization, part-of-speech tagging, and contextual analysis, to extract important keywords and topics from the sales meeting notes.

[2160] Input: Pre-processed sales-related data

[2161] Output: Analysis results (extracted keywords, topics)

[2162] Step 5:

[2163] The server then applies machine learning algorithms to further analyze the stored sales-related data, for example, using regression analysis and cluster analysis to identify which sales techniques were most effective.

[2164] Input: Pre-processed sales-related data

[2165] Output: Machine learning analysis results (identification of effective sales methods)

[2166] Step 6:

[2167] The server automatically generates a sales procedure template based on the analysis results, for example, a template including general steps such as "initial contact → needs assessment → proposal → follow-up."

[2168] Input: Machine learning analysis results

[2169] Output: Sales Procedure Template

[2170] Step 7:

[2171] The server customizes the generated sales procedures to the specific circumstances of each user and their customer, for example, creating procedures tailored to customers in a particular industry by providing technical details upfront.

[2172] Input: Sales procedure template, customer information

[2173] Output: Customized sales procedures

[2174] Step 8:

[2175] The server uses an emotion recognition engine to determine emotions from the text and voice data entered by the user, identifying emotions such as "interested," "distrustful," and "satisfied," and adjusting sales procedures accordingly.

[2176] Input: Text data and voice data entered by the user

[2177] Output: Emotion recognition result

[2178] Step 9:

[2179] The server can then use the emotional data to adjust sales procedures and training materials, for example adding steps to strengthen follow-up if the user is "distrustful."

[2180] Input: Emotion recognition results, customized sales procedures

[2181] Output: Adjusted sales procedures

[2182] Step 10:

[2183] The server generates training materials based on the adjusted sales procedures, such as sales negotiation simulations, FAQs, and success stories.

[2184] Input: Adjusted Sales Procedures

[2185] Output: Generated training material

[2186] Step 11:

[2187] The server aggregates supplementary materials and reference links related to the generated training materials, for example, educational videos and white papers, and adds them to the training materials provided.

[2188] Input: Generated training material

[2189] Output: Training materials with supplementary materials and reference links

[2190] Step 12:

[2191] The server then sends the generated sales procedures and training materials to the user's terminal, where the user can review the materials and prepare for the next sales meeting.

[2192] Input: Training materials with supplementary materials and reference links

[2193] Output: Data sent to the user's device

[2194] This is the specific process flow. This system allows users to receive the information and support they need to efficiently carry out their sales activities in a timely manner.

[2195] (Application example 2)

[2196] 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."

[2197] In sales activities, data collection and analysis are essential for quickly and efficiently understanding customer needs. However, conventional systems did not adequately analyze sales-related data or recognize emotions, making it difficult to provide appropriate sales techniques and training materials. Furthermore, they were unable to recognize customer emotions during the sales process in real time and adjust sales procedures accordingly, preventing improvements in sales efficiency and customer satisfaction.

[2198] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for allowing a user to input or upload sales-related data, means for saving the sales-related data, means for analyzing the saved sales-related data, means for automatically generating sales procedures based on the analysis results, means for generating training materials based on the sales procedures, means for providing the sales procedures and training materials to the user, an emotion engine that recognizes the user's emotions during the sales process in real time, and means for analyzing emotion data obtained by the emotion engine and adjusting the sales procedures. This makes it possible to efficiently analyze sales-related data and provide a personalized sales methodology based on the user's emotions.

[2199] "User" means any individual or legal entity that inputs or uploads business-related data.

[2200] "Sales-related data" refers to information related to sales activities, such as customer information, sales history, and business negotiation details.

[2201] "Means for inputting or uploading" refers to a function that allows a user to input or upload sales-related data into the system.

[2202] "Means for storage" refers to the system's ability to securely store entered sales-related data.

[2203] "Means for analysis" refers to the function for analyzing stored sales-related data and extracting meaningful information.

[2204] "Means for automatic generation" refers to a function for automatically creating sales procedures based on the analysis results.

[2205] "Means for generating" refers to the function for creating training materials based on sales procedures.

[2206] "Means for providing" refers to a function for presenting the generated sales procedures and training materials to the user.

[2207] An "emotion engine" refers to a system that recognizes a user's emotions in real time and analyzes the data.

[2208] "Means for adjustment" refers to the function for appropriately adjusting sales procedures based on the emotional data obtained by the emotion engine.

[2209] Overall overview

[2210] This invention is a system that collects sales-related data from users and efficiently stores and analyzes it. Based on the analysis results, the system automatically generates optimal sale...

Claims

1. means for allowing users to input or upload sales-related data; means for storing the sales-related data; a means for analyzing the stored sales-related data; A means for automatically generating sales procedures based on the analysis results; means for generating training materials based on the sales procedures; means for providing said sales procedures and training materials to users; A system including:

2. 2. The system of claim 1, wherein the analysis means analyzes the sales-related data using natural language processing techniques.

3. The system of claim 1 , wherein the analysis means applies a machine learning algorithm to analyze the sales-related data.

Images