system

Abstract

We provide the system. [Solution] A means of automatically collecting data from a vast number of information sources, A means for denoising and standardizing the collected data, A method for calculating the likelihood of a lead converting using a machine learning algorithm, A means of generating the optimal sales strategy based on the calculated probability of closing a deal, A means of continuously monitoring lead information and notifying when there are changes, A means for sales representatives to check information through a user interface, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional business lead acquisition process, it is a problem that a great deal of time and cost are required for the collection and analysis of lead information. It is difficult for salespersons to quickly obtain information for effectively approaching new customers, and there is a need for a method of efficiently identifying and approaching leads that have a high probability of resulting in a contract.

Means for Solving the Problems

[0005] This invention enables accurate data analysis by providing a means for automatically collecting, cleansing, and standardizing data from a vast number of information sources. It also includes a means for calculating the likelihood of a lead closing using machine learning algorithms and generating an optimal sales strategy based on the results. Furthermore, it provides a system that supports rapid and efficient sales activities by including a means for monitoring new and changing information in real time and notifying sales representatives.

[0006] "Information sources" refer to online resources such as websites, social networking platforms, and news sites from which data is collected.

[0007] "Data collection means" refers to programs or technologies that automatically acquire data from information sources.

[0008] "Noise reduction" is the process of removing unnecessary data in the preliminary stages of data analysis.

[0009] "Standardization" is the process of organizing collected data into a consistent format.

[0010] A "machine learning algorithm" is a mathematical model used to learn patterns and make predictions.

[0011] "Closing probability" is a numerical value or indicator that shows the likelihood of a particular lead reaching a sales negotiation.

[0012] A "sales strategy" is a detailed plan outlining how to approach leads.

[0013] "Monitoring" is the act of continuously observing specific lead information and detecting changes.

[0014] "User interface" is a general term for the screen display and operation methods that allow users to access and manipulate information. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] An example of an embodiment of the 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 numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] One possible embodiment of this invention is to construct the following system.

[0037] First, the server runs a program to collect data from internet sources. This program is configured to periodically retrieve the latest information from multiple sources, such as the websites and social media accounts of specified companies.

[0038] Next, the server preprocesses the collected data in order to analyze it. This process automatically removes noise and standardizes the data format to improve the accuracy and reliability of the analysis.

[0039] The server then uses a machine learning algorithm to evaluate the lead's likelihood of conversion. Based on past conversion data, the model is trained using the lead's current attributes and behavioral patterns as input, and the likelihood of conversion is output as a score.

[0040] Furthermore, the server develops the optimal sales strategy based on the scoring results. This strategy is customized according to the industry and size of the lead. For example, if it is determined that a social media campaign would be effective in a particular industry, the server will propose that method.

[0041] The server also monitors lead information in real time and immediately notifies sales representatives of any significant changes. These notifications are issued when a lead makes a major business announcement or when other market fluctuations are detected.

[0042] Once the information is ready, the terminal provides a user interface for sales representatives. This interface visually displays each lead's closing score and proposed sales strategy, providing information directly relevant to planning sales activities.

[0043] For example, if a user is targeting lead companies with new product lines, the server will continuously analyze those leads' social media activity and suggest sales strategies such as launching large-scale online campaigns at the right moments.

[0044] Thus, the present invention is a system that automates a series of processes from data collection and analysis to proposal, monitoring, and notification, dramatically improving the efficiency of the sales team.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server uses web scraping to collect data from information sources on the internet. This targets information from corporate websites, social networking platforms, news sites, etc., and is performed periodically according to a pre-set schedule. The collected data is temporarily stored in a database.

[0048] Step 2:

[0049] The server preprocesses the collected data. This step involves filtering out noisy data, removing duplicate data, and standardizing the format (e.g., formatting dates). This prepares the data for use in the next analysis step.

[0050] Step 3:

[0051] The server uses pre-processed data to apply a machine learning algorithm to score the likelihood of each lead closing. Here, the current lead data is input into a model trained using past transaction data and lead characteristic data, and the probability of each lead closing is calculated.

[0052] Step 4:

[0053] The server generates the optimal sales strategy for each lead based on the scoring results. In this step, the strategy is selected considering the lead's industry, size, geographical factors, and past success stories. For example, it determines whether an email campaign or a direct visit is appropriate.

[0054] Step 5:

[0055] The server monitors lead information in real time and detects important changes. This monitoring is done to catch changes in lead behavior, such as new product announcements or company news. When a change is detected, a notification is quickly sent to the sales team.

[0056] Step 6:

[0057] The device provides a dashboard for sales representatives to access, allowing them to view lead conversion scores, proposed strategies, and updates. The display interface is designed to be directly relevant to sales activities, enabling users to develop effective sales plans based on this information.

[0058] Step 7:

[0059] Based on the information provided through the device, users initiate sales actions towards target leads. These actions include specific activities such as creating proposals, contacting customers, and scheduling meetings. These actions are not limited to following the proposed strategy; users can also adjust them based on their own judgment.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In today's business environment, companies need to quickly collect and analyze valuable data from vast amounts of information to formulate appropriate sales strategies in order to maintain their competitiveness. However, doing this manually is extremely labor-intensive, and real-time monitoring and rapid response are difficult. To solve this problem, there is a need to develop a system that can handle everything from automated information collection to real-time notifications.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for calculating the likelihood of a lead closing using a machine learning algorithm. This enables companies to efficiently process large amounts of information, quickly generate optimal sales strategies, and immediately implement them.

[0065] "Information sources" refer to all digital media, such as websites, social media, and news sites, that are referenced to collect data.

[0066] "Automated data collection" refers to the process of periodically acquiring data through a program without manual intervention.

[0067] "Noise reduction" refers to the process of removing irrelevant or meaningless information from data to increase its purity.

[0068] "Standardization" refers to the process of unifying data formats and structures into a consistent form.

[0069] "Closing probability" refers to a numerical value or score that indicates the degree to which a lead is likely to actually result in a transaction.

[0070] A "machine learning algorithm" refers to a mathematical model used to analyze large amounts of data and make predictions or classifications related to a specific task.

[0071] "Sales strategy" refers to the approach and plan a company uses to conduct its commercial activities.

[0072] "Real-time monitoring" refers to the instantaneous tracking of data and situations, ensuring that the latest information is always available.

[0073] "Notification" refers to sending a message to inform a user when a specific event or change occurs.

[0074] "User interface" refers to the screen layout and operating environment that users use to view and manipulate information.

[0075] A "data feed" refers to a system that provides a continuously updated stream of data.

[0076] To implement the present invention, it is conceivable to construct a system as follows. First, the server functions as the core of the whole system and performs automated information gathering processing. Here, various information sources on the internet are utilized for data collection. Specifically, it connects with official company websites, social media, news media, etc., and acquires data using web scraping tools and APIs (for example, general web scraping libraries and social media APIs).

[0077] Next, the server performs preprocessing on the collected data. At this stage, data cleansing is performed, including noise reduction and formatting standardization, using libraries such as Python's Pandas and Beautiful Soup to improve data quality.

[0078] Furthermore, the server evaluates the likelihood of a lead being converted through a machine learning algorithm. Here, the server uses a model that has been trained based on historical data. Specifically, it uses a logistic regression model provided by Scikit-learn to calculate the likelihood of conversion as a score by inputting the collected lead attribute data.

[0079] The server then uses the obtained score results to build the optimal sales strategy. It has the capability to provide different approaches depending on the characteristics of each lead. For example, in certain markets, it may be determined that a social media campaign is effective.

[0080] Furthermore, the server tracks changes in real time through its monitoring function and quickly notifies sales representatives when important events or market fluctuations are detected. These notifications are delivered via email or the company's internal communication platform.

[0081] Ultimately, the device provides an intuitive user interface for sales representatives. Here, users can easily and clearly see each lead's closing score and proposed sales strategy. The UI is built with a front-end framework such as React, creating an environment where the sales team can work efficiently.

[0082] For example, if a user targets a company offering a new product, the server will continuously analyze the company's social media activity and develop a sales strategy to implement campaigns at the appropriate time. Furthermore, it can utilize generative AI models to make predictions and suggestions based on specific conditions.

[0083] Examples of prompts to input into a generative AI model:

[0084] "Gather the latest information on the specified companies and evaluate their likelihood of closing a deal. This information consists of data obtained through websites and social media."

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server collects data from information sources on the internet. Input includes pre-specified company names and related keywords, and output is the collected raw data. This process uses web scraping tools and APIs to retrieve websites, social media posts, and news articles. For example, it may involve extracting text data from a specified site using a common web scraping library.

[0088] Step 2:

[0089] The server preprocesses the collected data. The input is the raw data obtained in step 1, and the output is clean, standardized data. This process utilizes Python's Pandas and Beautiful Soup to remove noise and standardize the format. For example, this includes specific actions such as removing HTML tags and formatting special characters.

[0090] Step 3:

[0091] The server inputs the preprocessed data into a machine learning model to evaluate the likelihood of each lead being converted. The input is the clean data from step 2, and the output is the conversion likelihood score. Here, the server uses the Scikit-learn algorithm to analyze the attribute data using a logistic regression model. For example, the characteristics of each lead are converted into numerical vectors as input to the model, and a score is calculated.

[0092] Step 4:

[0093] The server develops sales strategies based on the scoring results. The input is the closing score from Step 3, and the output is a customized sales strategy. The server uses a pre-configured rule-based system to select the optimal approach based on industry and scale. For example, it may recommend social media campaigns in certain markets.

[0094] Step 5:

[0095] The server monitors lead information in real time and sends notifications when significant changes are detected. Input is a real-time data feed, and output is notification messages to the responsible party. The server sets thresholds and sends alerts via email or communication platforms when fluctuations are detected. Specifically, continuous data monitoring is performed to collect market changes.

[0096] Step 6:

[0097] The terminal provides a user interface that allows sales representatives to view information. Input is the final sales data obtained from the server, and output is a visualized interface display. The terminal uses a web frontend framework such as React to build dynamic dashboards and provide information to the user visually. This includes actions such as graphing closing scores and displaying strategic proposals as cards.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] A challenge in applying current sales and advertising strategies is the inefficient collection of data from a vast number of sources and the inability to efficiently assess the likelihood of transactions. Furthermore, the optimization of advertising strategies and the ability to respond immediately to changes in transactions are insufficient, limiting the effectiveness of sales activities. In addition, the lack of a system to grasp market changes in the customer base in real time and respond immediately makes it easy to miss opportunities.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes means for automatically collecting information from a vast data source, means for removing unnecessary data and standardizing the collected information, and means for evaluating the potential of a transaction using a machine learning algorithm. This enables efficient data processing and optimization of sales strategies, thereby maximizing the effectiveness of advertising strategies and enabling rapid responses to market fluctuations.

[0103] A "vast data source" refers to a wide range of information sources, such as company websites and social media, which are the targets of information collection.

[0104] "Automatically collecting information" means that the system acquires information according to its programmed instructions, without requiring human intervention.

[0105] "Removing unnecessary data" is the process of removing noise that is not needed for analysis or evaluation, leaving only the necessary data.

[0106] "Standardization" refers to unifying data in different formats and types to create a state that allows for efficient subsequent processing.

[0107] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that information to make future predictions and classifications.

[0108] "Assessing the likelihood of a transaction" means quantifying or classifying the probability that a potential trading partner or inventory source will actually complete a business transaction.

[0109] "Creating a sales policy" means planning and proposing the optimal approach and strategy for dealing with clients.

[0110] "To be able to view information" means to make information presented as digital data through a user interface visually verifiable by humans.

[0111] "Communicating an advertising strategy" means putting a proposed advertising policy into action and communicating its contents to a wide audience.

[0112] "Sending a warning" means that when the system determines that certain conditions have been met, it immediately sends out a notification to provide an alert or information.

[0113] To implement this invention, the first role of the server is to automatically collect information from a vast data source using web crawlers and APIs. The server then uses Python libraries such as Pandas and NumPy to remove unnecessary data and standardize the collected data. This organizes the data, allowing it to proceed to the next evaluation step.

[0114] During the evaluation phase, the server uses machine learning algorithms such as Scikit-learn to train a model on historical data and perform scoring to predict the likelihood of a transaction. This score is used as an important data point for formulating sales strategies. The server automatically generates the optimal sales strategy based on the scoring results and compiles it into a proposal for an advertising strategy for the user.

[0115] The device provides a user interface that visualizes this information. Built with React Native and other technologies, the user interface is designed to allow sales representatives to easily access and immediately utilize the information in their sales activities. This enables rapid responses to changing market conditions.

[0116] For example, users can observe information about business partners launching new products and apply advertising campaigns based on that information in a timely manner to effectively reach potential customers.

[0117] Examples of prompts for the generating AI model include: "Based on the latest social media data, suggest ways to optimize our clients' advertising strategies," or "Use real-time analysis to understand competitor trends and plan effective advertising campaigns."

[0118] This invention enables real-time data monitoring and immediate strategic implementation, dramatically improving the efficiency of a company's sales activities.

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server automatically collects data from a vast number of sources on the internet using web crawlers and APIs. The input is a specified list of URLs or API endpoints, and the output is the collected raw data. This data forms the basis for subsequent data processing.

[0122] Step 2:

[0123] The server uses Pandas and NumPy to preprocess the collected raw data. Specifically, it filters out noisy data and standardizes the data format. The input is the raw data obtained in step 1, and the output is cleansed and standardized data. This ensures that the data is in a state suitable for analysis.

[0124] Step 3:

[0125] The server uses Scikit-learn to input standardized data into a machine learning model and calculate a transaction probability score. The input is the standardized data obtained in step 2, and the output is the evaluated score. This score indicates the likelihood of a transaction being completed with the trading partner.

[0126] Step 4:

[0127] The server generates optimal sales strategies and develops advertising strategies based on the transaction potential score. This may utilize a generative AI model. The input is the score obtained in step 3, and the output is the generated sales strategy and advertising strategy. Prompt statements are applied as needed to reflect the results of the AI ​​model.

[0128] Step 5:

[0129] The terminal visualizes and presents the generated sales policies and advertising strategies to sales representatives through a user interface. The input is the policies and strategies obtained in step 4, and the output is the visually displayed information. This enables sales representatives to respond quickly and appropriately.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] To implement this invention, a configuration is adopted in which an emotion engine is integrated into the lead management system. The emotion engine can grasp the emotional state of sales representatives in real time by analyzing speech recognition, facial recognition technology, and text data entered by users.

[0132] First, the server is responsible for collecting and analyzing lead data. At the same time, the server also receives and centrally manages emotional data obtained from the emotion engine. The collected emotional data is used as an indicator of the sales representative's psychological state.

[0133] Next, the terminal provides an interface for the sales representative. This interface displays lead information along with the emotional state analyzed by the emotion engine. For example, if the sales representative is feeling stressed, the proposed sales strategy will be automatically adjusted based on that information. Specifically, a flexible approach may be suggested to ensure that communication does not become overly stressful.

[0134] Furthermore, the server combines and analyzes lead data and sentiment data to generate feedback for sales representatives. This feedback helps them approach high-potential leads at the most effective time. For example, it provides strategies for sales representatives to interact with leads in a relaxed state and guidelines to reduce stress.

[0135] For example, suppose a user attempts to approach a particular lead, and data from their emotion engine indicates a state of tension. The server, upon receiving this information, automatically revises the approach and suggests a script that facilitates a more pleasant conversation. It also provides regular alerts to encourage breaks, helping sales representatives maintain optimal psychological well-being while continuing their work.

[0136] Thus, the present invention is a system that incorporates an emotion engine to realize comprehensive sales support that takes into account the psychological aspects of sales representatives.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server uses web scraping techniques to collect lead-related data from the internet. This data includes information from company websites, social media posts, industry news, and other sources, and is stored in a database.

[0140] Step 2:

[0141] The server collects user (sales representative) emotional data in real time through an emotion engine. This data collection utilizes technologies such as voice input, text analysis, and facial recognition. The emotional data is recorded as a psychological indicator for sales activities.

[0142] Step 3:

[0143] The server performs data cleansing on the collected read data, including noise reduction, duplicate removal, and format standardization. Simultaneously, data from the sentiment engine is preprocessed for analysis and converted into an analyzable format.

[0144] Step 4:

[0145] The server uses a machine learning model to score the likelihood of a lead closing. It applies an algorithm that reflects past transaction history and current market conditions to quantify the probability of each lead closing.

[0146] Step 5:

[0147] The server generates the optimal sales strategy for each lead based on the scoring results and sentiment data. If the sentiment engine determines that the salesperson's emotional state is sensitive, a gentler approach is selected, and the strategy is customized accordingly.

[0148] Step 6:

[0149] The device provides a dashboard for sales representatives, displaying lead information, closing scores, sentiment feedback, and recommended sales strategies. Sales representatives use this information to develop action plans.

[0150] Step 7:

[0151] Users leverage information provided by their devices to approach leads. They use emotional feedback to communicate at the appropriate time and adjust proposed sales strategies as needed.

[0152] Step 8:

[0153] The server continues to monitor emotional data during sales activities, and if it detects signs of stress or fatigue, it sends messages to the user via their device encouraging relaxation or suggesting breaks. This helps ensure that sales representatives maintain optimal condition.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] Traditional sales support systems focus on managing lead data and calculating the likelihood of closing deals, but they do not adequately address strategic adjustments that take into account the psychological state of sales representatives. As a result, they fail to effectively utilize the impact of sales representatives' emotional states on closing deals, leading to a problem where their performance is not optimized.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for analyzing the psychological state of sales representatives using sentiment analysis technology. This enables dynamic adjustment of sales strategies in accordance with the psychological state of sales representatives.

[0159] "Information source" refers to the place or system from which data is collected, including databases and the internet.

[0160] "Noise reduction" is the process of removing unnecessary or inaccurate information from data, and is performed to improve the accuracy of the data.

[0161] Standardization is the process of converting collected data into a consistent format and units to maintain data consistency and make it comparable.

[0162] A "machine learning algorithm" is a program or process that allows a machine to automatically learn patterns and rules from large amounts of data.

[0163] "Closing probability" is an indicator that shows the degree to which a lead is likely to close a deal during the sales process.

[0164] "Sales strategy" refers to the planned approach and methods for effectively selling products or services to customers.

[0165] "Emotional analysis technology" is a technique that analyzes a person's emotional state from sources such as voice, facial expressions, and text.

[0166] "Psychological state" refers to the emotional and mental state an individual is experiencing at a particular moment.

[0167] A "user interface" refers to the screens and operating devices used by a system and its users to exchange information, enabling intuitive operation.

[0168] To implement this invention, it is necessary to integrate sentiment analysis technology into the lead management system. Specifically, a system consisting of a server, terminals, and users is configured, and various hardware and software are used.

[0169] The server collects lead data from a vast number of sources and stores it in a database. The server then performs noise reduction and standardization on the collected data to ensure accuracy and consistency. Next, machine learning algorithms are used to calculate the likelihood of each lead converting. Furthermore, sentiment analysis technology is used to analyze the emotional state of sales representatives from their voice, facial expressions, and input text, and this information is then used to inform strategies.

[0170] The terminal provides an interface for sales representatives. This interface has the functionality to display lead information and sentiment analysis results in real time, specifically including a graphical dashboard and notification system. Based on this information, sales representatives can make decisions and dynamically adjust their sales strategies.

[0171] The sales representative, acting as the user, approaches leads based on the information provided. For example, if the user's emotional state indicates stress when approaching a particular lead, the server uses this information to automatically adjust the proposal and approach. Furthermore, by following the system's feedback, the user can reduce stress while conducting effective sales activities.

[0172] An example of a prompt might be, "Generate a friendly conversation script for when the sales representative is nervous." This would enable the AI ​​model to propose appropriate and flexible sales strategies.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server automatically collects lead data from various sources. This data includes customer contact information and transaction history. It uses information from databases and web services as input and generates structured lead data as output, which is then stored in the database. Specifically, it uses scripts to retrieve information via APIs, automatically formatting and storing it.

[0176] Step 2:

[0177] The server performs denoising and standardization on the collected read data. This process removes unnecessary information and inconsistent data, improving data quality. Using the collected data as input, the output is a clean and unified dataset. Specifically, it filters out redundant data and imputes missing values, then stores the results back into the database.

[0178] Step 3:

[0179] The server uses emotion analysis technology to analyze the psychological state of sales representatives. It processes voice and facial expression data as input and generates an index indicating the sales representative's emotional state as output. This process requires acquiring data in real time from microphones and cameras and applying an emotion analysis algorithm to calculate an emotion score.

[0180] Step 4:

[0181] The server uses machine learning algorithms to calculate the likelihood of a lead closing. It utilizes lead data and the emotional state of sales representatives as input and outputs a score indicating the probability of closing. Specifically, it builds a predictive model based on past closing data and performs predictions by analyzing real-time data.

[0182] Step 5:

[0183] The terminal displays information to sales representatives through a user interface. This interface is in a dashboard format, visualizing lead data, sentiment status, and conversion probability. It retrieves information from the server as input and provides it to sales representatives in an easy-to-understand format as output. Specifically, it generates an intuitive interface by graphically arranging the data.

[0184] Step 6:

[0185] The user approaches leads based on the information displayed in the interface. It generates prompts as needed and dynamically adjusts the sales strategy. Based on the data received from the interface as input, it executes an improved sales script as output. Specific actions include reading out appropriate conversation scripts to ease tension and executing flexible sales approaches.

[0186] (Application Example 2)

[0187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0188] Existing sales support systems struggle to provide flexible responses that take into account the feelings and psychological state of sales representatives, limiting improvements in closing rates. Furthermore, because home-use devices cannot provide appropriate support that responds to residents' emotions, new needs are arising to enhance their quality of life.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0190] In this invention, the server includes means for analyzing the emotional state of a salesperson using emotion recognition technology, means for generating an optimal sales strategy based on the calculated probability of closing a deal and the salesperson's emotional state, and means for a home device to perform the optimal action based on the emotional state of the family. This makes it possible to support sales activities in accordance with the psychological state of the salesperson, and improve the quality of life by having the home device provide appropriate actions in accordance with people's emotions.

[0191] "Automated data collection" is the process of automatically extracting necessary information from a vast amount of data sources using a program.

[0192] "Denoising and standardization" is the process of removing unnecessary information from collected data and organizing the data into a consistent format.

[0193] A "machine learning algorithm" is an algorithm used to analyze data and make predictions or classifications based on specific patterns or rules.

[0194] "Closing probability" refers to the degree of likelihood that a particular lead will result in a sale as a result of sales activities.

[0195] "Emotion recognition technology" is a technology that objectively determines a person's emotions by analyzing their voice, facial expressions, and body movements.

[0196] "Sales strategy generation" is the act of formulating a plan for the most effective sales activities based on analyzed data.

[0197] "User interface" refers to the screens and operating systems that facilitate the smooth exchange of information between a system and a user.

[0198] "Optimal action" refers to the actions or choices that best match the situation and conditions and produce the desired outcome.

[0199] In this system, the server plays a central role. The server automatically collects data from a vast number of sources, performing noise reduction and standardization in the process. A high-performance database management system is used for data collection. The collected data is then used to calculate the likelihood of each lead being converted using machine learning algorithms. For example, the scikit-learn library in Python is used for this purpose.

[0200] In addition, the server utilizes emotion recognition technology to analyze audio and video data in real time, for example. This allows it to understand the emotional state of sales representatives and family members. This process applies a deep learning-based TENSORFLOW® model.

[0201] Sales representatives can access information provided by the server through the user interface of their smartphones or home devices. This interface, implemented using web and mobile app technologies, displays optimal sales strategies and in-home action suggestions tailored to individual emotions.

[0202] For example, if a salesperson is detected as being stressed, the server will suggest a gentler sales script based on emotional data. Similarly, if a home device detects a child's depression, it will suggest playing uplifting music.

[0203] Examples of prompts for a generative AI model include:

[0204] "What kind of encouraging words should you offer when a child is feeling down?"

[0205] "What kind of conversation should sales representatives keep in mind when visiting clients?"

[0206] This invention proposes flexible behaviors that respond to emotional states, and is expected to improve the quality of business activities and family life.

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

[0208] Step 1:

[0209] The server automatically collects data from a vast number of sources. It receives raw data from each data source as input and stores it in a collection database as output. Specifically, it accesses online databases via APIs to retrieve sales-related information.

[0210] Step 2:

[0211] The server performs denoising and standardization on the collected data. The input is the collected raw data, and the output is a clean dataset. In this process, outliers are removed using the numpy library and the data is converted to CSV format.

[0212] Step 3:

[0213] The server calculates the conversion probability of a lead using a machine learning algorithm. The input is a clean dataset, and the output is a conversion probability score. Specifically, it uses scikit-learn to execute a random forest algorithm and makes predictions based on the lead's features.

[0214] Step 4:

[0215] The server uses emotion recognition technology to analyze the voice and video data of sales representatives. It receives real-time collected voice and facial image data as input, and outputs emotional state labels. Specifically, it uses a TensorFlow emotion recognition model to evaluate the voice spectrum and facial expressions.

[0216] Step 5:

[0217] The server generates the optimal sales strategy based on the obtained conversion probability score and emotional state. The input is the conversion score and emotional label, and the output is a customized sales script. A generative AI model is used to generate emotionally sensitive, contextually appropriate prompts.

[0218] Step 6:

[0219] The user terminal presents the generated sales strategies and action proposals to the sales representative. The input consists of customized scripts and proposals received from the server, while the output is visual feedback to the user. Specifically, the strategy is displayed to the representative using the notification function of a smartphone app.

[0220] Step 7:

[0221] Users initiate actions based on suggestions from the application. The input is the presented suggestion, and the output is actual sales activities or actions within the home. Specifically, they might start a conversation with a client or take appropriate action with family members based on a suggested script.

[0222] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0223] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0225] [Second Embodiment]

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

[0227] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0229] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0232] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0233] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0234] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0235] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0236] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0237] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0238] One possible embodiment of this invention is to construct the following system.

[0239] First, the server runs a program to collect data from internet sources. This program is configured to periodically retrieve the latest information from multiple sources, such as the websites and social media accounts of specified companies.

[0240] Next, the server preprocesses the collected data in order to analyze it. This process automatically removes noise and standardizes the data format to improve the accuracy and reliability of the analysis.

[0241] The server then uses a machine learning algorithm to evaluate the lead's likelihood of conversion. Based on past conversion data, the model is trained using the lead's current attributes and behavioral patterns as input, and the likelihood of conversion is output as a score.

[0242] Furthermore, the server develops the optimal sales strategy based on the scoring results. This strategy is customized according to the industry and size of the lead. For example, if it is determined that a social media campaign would be effective in a particular industry, the server will propose that method.

[0243] The server also monitors lead information in real time and immediately notifies sales representatives of any significant changes. These notifications are issued when a lead makes a major business announcement or when other market fluctuations are detected.

[0244] Once the information is ready, the terminal provides a user interface for sales representatives. This interface visually displays each lead's closing score and proposed sales strategy, providing information directly relevant to planning sales activities.

[0245] For example, if a user is targeting lead companies with new product lines, the server will continuously analyze those leads' social media activity and suggest sales strategies such as launching large-scale online campaigns at the right moments.

[0246] Thus, the present invention is a system that automates a series of processes from data collection and analysis to proposal, monitoring, and notification, dramatically improving the efficiency of the sales team.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The server uses web scraping to collect data from information sources on the internet. This targets information from corporate websites, social networking platforms, news sites, etc., and is performed periodically according to a pre-set schedule. The collected data is temporarily stored in a database.

[0250] Step 2:

[0251] The server preprocesses the collected data. This step involves filtering out noisy data, removing duplicate data, and standardizing the format (e.g., formatting dates). This prepares the data for use in the next analysis step.

[0252] Step 3:

[0253] The server uses pre-processed data to apply a machine learning algorithm to score the likelihood of each lead closing. Here, the current lead data is input into a model trained using past transaction data and lead characteristic data, and the probability of each lead closing is calculated.

[0254] Step 4:

[0255] The server generates the optimal sales strategy for each lead based on the scoring results. In this step, the strategy is selected considering the lead's industry, size, geographical factors, and past success stories. For example, it determines whether an email campaign or a direct visit is appropriate.

[0256] Step 5:

[0257] The server monitors lead information in real time and detects important changes. This monitoring is done to catch changes in lead behavior, such as new product announcements or company news. When a change is detected, a notification is quickly sent to the sales team.

[0258] Step 6:

[0259] The device provides a dashboard for sales representatives to access, allowing them to view lead conversion scores, proposed strategies, and updates. The display interface is designed to be directly relevant to sales activities, enabling users to develop effective sales plans based on this information.

[0260] Step 7:

[0261] Based on the information provided through the device, users initiate sales actions towards target leads. These actions include specific activities such as creating proposals, contacting customers, and scheduling meetings. These actions are not limited to following the proposed strategy; users can also adjust them based on their own judgment.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In today's business environment, companies need to quickly collect and analyze valuable data from vast amounts of information to formulate appropriate sales strategies in order to maintain their competitiveness. However, doing this manually is extremely labor-intensive, and real-time monitoring and rapid response are difficult. To solve this problem, there is a need to develop a system that can handle everything from automated information collection to real-time notifications.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for calculating the likelihood of a lead closing using a machine learning algorithm. This enables companies to efficiently process large amounts of information, quickly generate optimal sales strategies, and immediately implement them.

[0267] "Information sources" refer to all digital media, such as websites, social media, and news sites, that are referenced to collect data.

[0268] "Automated data collection" refers to the process of periodically acquiring data through a program without manual intervention.

[0269] "Noise reduction" refers to the process of removing irrelevant or meaningless information from data to increase its purity.

[0270] "Standardization" refers to the process of unifying data formats and structures into a consistent form.

[0271] "Closing probability" refers to a numerical value or score that indicates the degree to which a lead is likely to actually result in a transaction.

[0272] A "machine learning algorithm" refers to a mathematical model used to analyze large amounts of data and make predictions or classifications related to a specific task.

[0273] "Sales strategy" refers to the approach and plan a company uses to conduct its commercial activities.

[0274] "Real-time monitoring" refers to the instantaneous tracking of data and situations, ensuring that the latest information is always available.

[0275] "Notification" refers to sending a message to inform a user when a specific event or change occurs.

[0276] "User interface" refers to the screen layout and operating environment that users use to view and manipulate information.

[0277] A "data feed" refers to a system that provides a continuously updated stream of data.

[0278] To implement the present invention, it is conceivable to construct a system as follows. First, the server functions as the core of the whole system and performs automated information gathering processing. Here, various information sources on the internet are utilized for data collection. Specifically, it connects with official company websites, social media, news media, etc., and acquires data using web scraping tools and APIs (for example, general web scraping libraries and social media APIs).

[0279] Next, the server performs preprocessing on the collected data. At this stage, data cleansing is performed, including noise reduction and formatting standardization, using libraries such as Python's Pandas and Beautiful Soup to improve data quality.

[0280] Furthermore, the server evaluates the likelihood of a lead being converted through a machine learning algorithm. Here, the server uses a model that has been trained based on historical data. Specifically, it uses a logistic regression model provided by Scikit-learn to calculate the likelihood of conversion as a score by inputting the collected lead attribute data.

[0281] The server then uses the obtained score results to build the optimal sales strategy. It has the capability to provide different approaches depending on the characteristics of each lead. For example, in certain markets, it may be determined that a social media campaign is effective.

[0282] In addition, the server tracks changes in real time through its monitoring function and promptly notifies sales staff when important events or market fluctuations are detected. This notification is provided using email or the company's internal communication platform.

[0283] Finally, the terminal provides an intuitive user interface for sales staff. Here, users can easily visually confirm and visualize the conversion scores of each lead and the proposed sales strategies. The UI is built with a front-end framework such as React, creating an environment in which the sales team can operate efficiently.

[0284] As a specific example, when a user targets a company that offers new products, the server sequentially analyzes the company's SNS activities and constructs a sales strategy to implement a campaign at an appropriate timing. Additionally, it is also possible to make predictions and proposals based on specific conditions by leveraging a generative AI model.

[0285] Example of a prompt sentence to be input into the generative AI model:

[0286] "Collect the latest information on the specified company and evaluate the likelihood of closing a deal. This information consists of data obtained through websites and SNS."

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The server collects data from information sources on the Internet. The input includes a pre-specified company name and related keywords, and the output is the raw data collected. In this process, web scraping tools or APIs are used to obtain websites, SNS posts, and news articles. For example, it includes the operation of extracting text data from a specified site using a general web scraping library.

[0290] Step 2:

[0291] The server preprocesses the collected data. The input is the raw data obtained in step 1, and the output is clean, standardized data. This process utilizes Python's Pandas and Beautiful Soup to remove noise and standardize the format. For example, this includes specific actions such as removing HTML tags and formatting special characters.

[0292] Step 3:

[0293] The server inputs the preprocessed data into a machine learning model to evaluate the likelihood of each lead being converted. The input is the clean data from step 2, and the output is the conversion likelihood score. Here, the server uses the Scikit-learn algorithm to analyze the attribute data using a logistic regression model. For example, the characteristics of each lead are converted into numerical vectors as input to the model, and a score is calculated.

[0294] Step 4:

[0295] The server develops sales strategies based on the scoring results. The input is the closing score from Step 3, and the output is a customized sales strategy. The server uses a pre-configured rule-based system to select the optimal approach based on industry and scale. For example, it may recommend social media campaigns in certain markets.

[0296] Step 5:

[0297] The server monitors lead information in real time and sends notifications when significant changes are detected. Input is a real-time data feed, and output is notification messages to the responsible party. The server sets thresholds and sends alerts via email or communication platforms when fluctuations are detected. Specifically, continuous data monitoring is performed to collect market changes.

[0298] Step 6:

[0299] The terminal provides a user interface that allows sales representatives to view information. Input is the final sales data obtained from the server, and output is a visualized interface display. The terminal uses a web frontend framework such as React to build dynamic dashboards and provide information to the user visually. This includes actions such as graphing closing scores and displaying strategic proposals as cards.

[0300] (Application Example 1)

[0301] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0302] A challenge in applying current sales and advertising strategies is the inefficient collection of data from a vast number of sources and the inability to efficiently assess the likelihood of transactions. Furthermore, the optimization of advertising strategies and the ability to respond immediately to changes in transactions are insufficient, limiting the effectiveness of sales activities. In addition, the lack of a system to grasp market changes in the customer base in real time and respond immediately makes it easy to miss opportunities.

[0303] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0304] In this invention, the server includes means for automatically collecting information from a vast data source, means for removing unnecessary data and standardizing the collected information, and means for evaluating the potential of a transaction using a machine learning algorithm. This enables efficient data processing and optimization of sales strategies, thereby maximizing the effectiveness of advertising strategies and enabling rapid responses to market fluctuations.

[0305] A "vast data source" refers to a wide range of information sources, such as company websites and social media, which are the targets of information collection.

[0306] "Automatically collect" means that without the need for human intervention, the system acquires information as programmed.

[0307] "Removing unnecessary data" is a process of removing noise that is unnecessary for analysis or evaluation and leaving only the necessary data.

[0308] "Standardization" means to unify data in different formats or forms so as to prepare it for efficient subsequent processing.

[0309] "Machine learning algorithm" is a technology that learns patterns based on past data and performs future predictions or classifications.

[0310] "Evaluating the potential in transactions" means quantifying or classifying the possibility that potential business partners or inventory holders will actually establish a business.

[0311] "Formulating business policies" means planning and proposing the optimal approach and strategy for business partners.

[0312] "Enabling information viewing" means making the information presented as digital data visually confirmable by humans through the user interface.

[0313] "Implementing an advertising strategy" means putting the proposed advertising policy into practice and communicating its content to many people.

[0314] "Sending a warning" means that when the system determines that a specific condition is met, it immediately sends a notification to raise awareness or provide information.

[0315] To implement this invention, the first role of the server is to automatically collect information from a vast data source using web crawlers and APIs. The server then uses Python libraries such as Pandas and NumPy to remove unnecessary data and standardize the collected data. This organizes the data, allowing it to proceed to the next evaluation step.

[0316] During the evaluation phase, the server uses machine learning algorithms such as Scikit-learn to train a model on historical data and perform scoring to predict the likelihood of a transaction. This score is used as an important data point for formulating sales strategies. The server automatically generates the optimal sales strategy based on the scoring results and compiles it into a proposal for an advertising strategy for the user.

[0317] The device provides a user interface that visualizes this information. Built with React Native and other technologies, the user interface is designed to allow sales representatives to easily access and immediately utilize the information in their sales activities. This enables rapid responses to changing market conditions.

[0318] For example, users can observe information about business partners launching new products and apply advertising campaigns based on that information in a timely manner to effectively reach potential customers.

[0319] Examples of prompts for the generating AI model include: "Based on the latest social media data, suggest ways to optimize our clients' advertising strategies," or "Use real-time analysis to understand competitor trends and plan effective advertising campaigns."

[0320] This invention enables real-time data monitoring and immediate strategic implementation, dramatically improving the efficiency of a company's sales activities.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server automatically collects data from a vast number of sources on the internet using web crawlers and APIs. The input is a specified list of URLs or API endpoints, and the output is the collected raw data. This data forms the basis for subsequent data processing.

[0324] Step 2:

[0325] The server uses Pandas and NumPy to preprocess the collected raw data. Specifically, it filters out noisy data and standardizes the data format. The input is the raw data obtained in step 1, and the output is cleansed and standardized data. This ensures that the data is in a state suitable for analysis.

[0326] Step 3:

[0327] The server uses Scikit-learn to input standardized data into a machine learning model and calculate a transaction probability score. The input is the standardized data obtained in step 2, and the output is the evaluated score. This score indicates the likelihood of a transaction being completed with the trading partner.

[0328] Step 4:

[0329] The server generates optimal sales strategies and develops advertising strategies based on the transaction potential score. This may utilize a generative AI model. The input is the score obtained in step 3, and the output is the generated sales strategy and advertising strategy. Prompt statements are applied as needed to reflect the results of the AI ​​model.

[0330] Step 5:

[0331] The terminal visualizes and presents the generated sales policies and advertising strategies to sales representatives through a user interface. The input is the policies and strategies obtained in step 4, and the output is the visually displayed information. This enables sales representatives to respond quickly and appropriately.

[0332] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0333] To implement this invention, a configuration is adopted in which an emotion engine is integrated into the lead management system. The emotion engine can grasp the emotional state of sales representatives in real time by analyzing speech recognition, facial recognition technology, and text data entered by users.

[0334] First, the server is responsible for collecting and analyzing lead data. At the same time, the server also receives and centrally manages emotional data obtained from the emotion engine. The collected emotional data is used as an indicator of the sales representative's psychological state.

[0335] Next, the terminal provides an interface for the sales representative. This interface displays lead information along with the emotional state analyzed by the emotion engine. For example, if the sales representative is feeling stressed, the proposed sales strategy will be automatically adjusted based on that information. Specifically, a flexible approach may be suggested to ensure that communication does not become overly stressful.

[0336] Furthermore, the server combines and analyzes lead data and sentiment data to generate feedback for sales representatives. This feedback helps them approach high-potential leads at the most effective time. For example, it provides strategies for sales representatives to interact with leads in a relaxed state and guidelines to reduce stress.

[0337] For example, suppose a user attempts to approach a particular lead, and data from their emotion engine indicates a state of tension. The server, upon receiving this information, automatically revises the approach and suggests a script that facilitates a more pleasant conversation. It also provides regular alerts to encourage breaks, helping sales representatives maintain optimal psychological well-being while continuing their work.

[0338] Thus, the present invention is a system that incorporates an emotion engine to realize comprehensive sales support that takes into account the psychological aspects of sales representatives.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The server uses web scraping techniques to collect lead-related data from the internet. This data includes information from company websites, social media posts, industry news, and other sources, and is stored in a database.

[0342] Step 2:

[0343] The server collects user (sales representative) emotional data in real time through an emotion engine. This data collection utilizes technologies such as voice input, text analysis, and facial recognition. The emotional data is recorded as a psychological indicator for sales activities.

[0344] Step 3:

[0345] The server performs data cleansing on the collected read data, including noise reduction, duplicate removal, and format standardization. Simultaneously, data from the sentiment engine is preprocessed for analysis and converted into an analyzable format.

[0346] Step 4:

[0347] The server uses a machine learning model to score the likelihood of a lead closing. It applies an algorithm that reflects past transaction history and current market conditions to quantify the probability of each lead closing.

[0348] Step 5:

[0349] The server generates the optimal sales strategy for each lead based on the scoring results and sentiment data. If the sentiment engine determines that the salesperson's emotional state is sensitive, a gentler approach is selected, and the strategy is customized accordingly.

[0350] Step 6:

[0351] The device provides a dashboard for sales representatives, displaying lead information, closing scores, sentiment feedback, and recommended sales strategies. Sales representatives use this information to develop action plans.

[0352] Step 7:

[0353] Users leverage information provided by their devices to approach leads. They use emotional feedback to communicate at the appropriate time and adjust proposed sales strategies as needed.

[0354] Step 8:

[0355] The server continues to monitor emotional data during sales activities, and if it detects signs of stress or fatigue, it sends messages to the user via their device encouraging relaxation or suggesting breaks. This helps ensure that sales representatives maintain optimal condition.

[0356] (Example 2)

[0357] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0358] Traditional sales support systems focus on managing lead data and calculating the likelihood of closing deals, but they do not adequately address strategic adjustments that take into account the psychological state of sales representatives. As a result, they fail to effectively utilize the impact of sales representatives' emotional states on closing deals, leading to a problem where their performance is not optimized.

[0359] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0360] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for analyzing the psychological state of sales representatives using sentiment analysis technology. This enables dynamic adjustment of sales strategies in accordance with the psychological state of sales representatives.

[0361] "Information source" refers to the place or system from which data is collected, including databases and the internet.

[0362] "Noise reduction" is the process of removing unnecessary or inaccurate information from data, and is performed to improve the accuracy of the data.

[0363] Standardization is the process of converting collected data into a consistent format and units to maintain data consistency and make it comparable.

[0364] A "machine learning algorithm" is a program or process that allows a machine to automatically learn patterns and rules from large amounts of data.

[0365] "Closing probability" is an indicator that shows the degree to which a lead is likely to close a deal during the sales process.

[0366] "Sales strategy" refers to the planned approach and methods for effectively selling products or services to customers.

[0367] "Emotional analysis technology" is a technique that analyzes a person's emotional state from sources such as voice, facial expressions, and text.

[0368] "Psychological state" refers to the emotional and mental state an individual is experiencing at a particular moment.

[0369] A "user interface" refers to the screens and operating devices used by a system and its users to exchange information, enabling intuitive operation.

[0370] To implement this invention, it is necessary to integrate sentiment analysis technology into the lead management system. Specifically, a system consisting of a server, terminals, and users is configured, and various hardware and software are used.

[0371] The server collects lead data from a vast number of sources and stores it in a database. The server then performs noise reduction and standardization on the collected data to ensure accuracy and consistency. Next, machine learning algorithms are used to calculate the likelihood of each lead converting. Furthermore, sentiment analysis technology is used to analyze the emotional state of sales representatives from their voice, facial expressions, and input text, and this information is then used to inform strategies.

[0372] The terminal provides an interface for sales representatives. This interface has the functionality to display lead information and sentiment analysis results in real time, specifically including a graphical dashboard and notification system. Based on this information, sales representatives can make decisions and dynamically adjust their sales strategies.

[0373] The sales representative, acting as the user, approaches leads based on the information provided. For example, if the user's emotional state indicates stress when approaching a particular lead, the server uses this information to automatically adjust the proposal and approach. Furthermore, by following the system's feedback, the user can reduce stress while conducting effective sales activities.

[0374] An example of a prompt might be, "Generate a friendly conversation script for when the sales representative is nervous." This would enable the AI ​​model to propose appropriate and flexible sales strategies.

[0375] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0376] Step 1:

[0377] The server automatically collects lead data from various sources. This data includes customer contact information and transaction history. It uses information from databases and web services as input and generates structured lead data as output, which is then stored in the database. Specifically, it uses scripts to retrieve information via APIs, automatically formatting and storing it.

[0378] Step 2:

[0379] The server performs denoising and standardization on the collected read data. This process removes unnecessary information and inconsistent data, improving data quality. Using the collected data as input, the output is a clean and unified dataset. Specifically, it filters out redundant data and imputes missing values, then stores the results back into the database.

[0380] Step 3:

[0381] The server uses emotion analysis technology to analyze the psychological state of sales representatives. It processes voice and facial expression data as input and generates an index indicating the sales representative's emotional state as output. This process requires acquiring data in real time from microphones and cameras and applying an emotion analysis algorithm to calculate an emotion score.

[0382] Step 4:

[0383] The server uses machine learning algorithms to calculate the likelihood of a lead closing. It utilizes lead data and the emotional state of sales representatives as input and outputs a score indicating the probability of closing. Specifically, it builds a predictive model based on past closing data and performs predictions by analyzing real-time data.

[0384] Step 5:

[0385] The terminal displays information to sales representatives through a user interface. This interface is in a dashboard format, visualizing lead data, sentiment status, and conversion probability. It retrieves information from the server as input and provides it to sales representatives in an easy-to-understand format as output. Specifically, it generates an intuitive interface by graphically arranging the data.

[0386] Step 6:

[0387] The user approaches leads based on the information displayed in the interface. It generates prompts as needed and dynamically adjusts the sales strategy. Based on the data received from the interface as input, it executes an improved sales script as output. Specific actions include reading out appropriate conversation scripts to ease tension and executing flexible sales approaches.

[0388] (Application Example 2)

[0389] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0390] Existing sales support systems struggle to provide flexible responses that take into account the feelings and psychological state of sales representatives, limiting improvements in closing rates. Furthermore, because home-use devices cannot provide appropriate support that responds to residents' emotions, new needs are arising to enhance their quality of life.

[0391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0392] In this invention, the server includes means for analyzing the emotional state of a salesperson using emotion recognition technology, means for generating an optimal sales strategy based on the calculated probability of closing a deal and the salesperson's emotional state, and means for a home device to perform the optimal action based on the emotional state of the family. This makes it possible to support sales activities in accordance with the psychological state of the salesperson, and improve the quality of life by having the home device provide appropriate actions in accordance with people's emotions.

[0393] "Automated data collection" is the process of automatically extracting necessary information from a vast amount of data sources using a program.

[0394] "Denoising and standardization" is the process of removing unnecessary information from collected data and organizing the data into a consistent format.

[0395] A "machine learning algorithm" is an algorithm used to analyze data and make predictions or classifications based on specific patterns or rules.

[0396] "Closing probability" refers to the degree of likelihood that a particular lead will result in a sale as a result of sales activities.

[0397] "Emotion recognition technology" is a technology that objectively determines a person's emotions by analyzing their voice, facial expressions, and body movements.

[0398] "Sales strategy generation" is the act of formulating a plan for the most effective sales activities based on analyzed data.

[0399] "User interface" refers to the screens and operating systems that facilitate the smooth exchange of information between a system and a user.

[0400] "Optimal action" refers to the actions or choices that best match the situation and conditions and produce the desired outcome.

[0401] In this system, the server plays a central role. The server automatically collects data from a vast number of sources, performing noise reduction and standardization in the process. A high-performance database management system is used for data collection. The collected data is then used to calculate the likelihood of each lead being converted using machine learning algorithms. For example, the scikit-learn library in Python is used for this purpose.

[0402] In addition, the server utilizes emotion recognition technology to analyze audio and video data in real time, for example. This allows it to understand the emotional state of sales representatives and family members. This process employs a TensorFlow model that utilizes deep learning.

[0403] Sales representatives can access information provided by the server through the user interface of their smartphones or home devices. This interface, implemented using web and mobile app technologies, displays optimal sales strategies and in-home action suggestions tailored to individual emotions.

[0404] For example, if a salesperson is detected as being stressed, the server will suggest a gentler sales script based on emotional data. Similarly, if a home device detects a child's depression, it will suggest playing uplifting music.

[0405] Examples of prompts for a generative AI model include:

[0406] "What kind of encouraging words should you offer when a child is feeling down?"

[0407] "What kind of conversation should sales representatives keep in mind when visiting clients?"

[0408] This invention proposes flexible behaviors that respond to emotional states, and is expected to improve the quality of business activities and family life.

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

[0410] Step 1:

[0411] The server automatically collects data from a vast number of sources. It receives raw data from each data source as input and stores it in a collection database as output. Specifically, it accesses online databases via APIs to retrieve sales-related information.

[0412] Step 2:

[0413] The server performs denoising and standardization on the collected data. The input is the collected raw data, and the output is a clean dataset. In this process, outliers are removed using the numpy library and the data is converted to CSV format.

[0414] Step 3:

[0415] The server calculates the conversion probability of a lead using a machine learning algorithm. The input is a clean dataset, and the output is a conversion probability score. Specifically, it uses scikit-learn to execute a random forest algorithm and makes predictions based on the lead's features.

[0416] Step 4:

[0417] The server uses emotion recognition technology to analyze the voice and video data of sales representatives. It receives real-time collected voice and facial image data as input, and outputs emotional state labels. Specifically, it uses a TensorFlow emotion recognition model to evaluate the voice spectrum and facial expressions.

[0418] Step 5:

[0419] The server generates the optimal sales strategy based on the obtained conversion probability score and emotional state. The input is the conversion score and emotional label, and the output is a customized sales script. A generative AI model is used to generate emotionally sensitive, contextually appropriate prompts.

[0420] Step 6:

[0421] The user terminal presents the generated sales strategies and action proposals to the sales representative. The input consists of customized scripts and proposals received from the server, while the output is visual feedback to the user. Specifically, the strategy is displayed to the representative using the notification function of a smartphone app.

[0422] Step 7:

[0423] Users initiate actions based on suggestions from the application. The input is the presented suggestion, and the output is actual sales activities or actions within the home. Specifically, they might start a conversation with a client or take appropriate action with family members based on a suggested script.

[0424] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0425] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0426] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0427] [Third Embodiment]

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

[0429] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0430] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0431] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0432] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0433] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0434] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0435] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0436] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0437] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0438] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0439] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0440] One possible embodiment of this invention is to construct the following system.

[0441] First, the server runs a program to collect data from internet sources. This program is configured to periodically retrieve the latest information from multiple sources, such as the websites and social media accounts of specified companies.

[0442] Next, the server preprocesses the collected data in order to analyze it. This process automatically removes noise and standardizes the data format to improve the accuracy and reliability of the analysis.

[0443] The server then uses a machine learning algorithm to evaluate the lead's likelihood of conversion. Based on past conversion data, the model is trained using the lead's current attributes and behavioral patterns as input, and the likelihood of conversion is output as a score.

[0444] Furthermore, the server develops the optimal sales strategy based on the scoring results. This strategy is customized according to the industry and size of the lead. For example, if it is determined that a social media campaign would be effective in a particular industry, the server will propose that method.

[0445] The server also monitors lead information in real time and immediately notifies sales representatives of any significant changes. These notifications are issued when a lead makes a major business announcement or when other market fluctuations are detected.

[0446] Once the information is ready, the terminal provides a user interface for sales representatives. This interface visually displays each lead's closing score and proposed sales strategy, providing information directly relevant to planning sales activities.

[0447] For example, if a user is targeting lead companies with new product lines, the server will continuously analyze those leads' social media activity and suggest sales strategies such as launching large-scale online campaigns at the right moments.

[0448] Thus, the present invention is a system that automates a series of processes from data collection and analysis to proposal, monitoring, and notification, dramatically improving the efficiency of the sales team.

[0449] The following describes the processing flow.

[0450] Step 1:

[0451] The server uses web scraping to collect data from information sources on the internet. This targets information from corporate websites, social networking platforms, news sites, etc., and is performed periodically according to a pre-set schedule. The collected data is temporarily stored in a database.

[0452] Step 2:

[0453] The server preprocesses the collected data. This step involves filtering out noisy data, removing duplicate data, and standardizing the format (e.g., formatting dates). This prepares the data for use in the next analysis step.

[0454] Step 3:

[0455] The server uses pre-processed data to apply a machine learning algorithm to score the likelihood of each lead closing. Here, the current lead data is input into a model trained using past transaction data and lead characteristic data, and the probability of each lead closing is calculated.

[0456] Step 4:

[0457] The server generates the optimal sales strategy for each lead based on the scoring results. In this step, the strategy is selected considering the lead's industry, size, geographical factors, and past success stories. For example, it determines whether an email campaign or a direct visit is appropriate.

[0458] Step 5:

[0459] The server monitors lead information in real time and detects important changes. This monitoring is done to catch changes in lead behavior, such as new product announcements or company news. When a change is detected, a notification is quickly sent to the sales team.

[0460] Step 6:

[0461] The device provides a dashboard for sales representatives to access, allowing them to view lead conversion scores, proposed strategies, and updates. The display interface is designed to be directly relevant to sales activities, enabling users to develop effective sales plans based on this information.

[0462] Step 7:

[0463] Based on the information provided through the device, users initiate sales actions towards target leads. These actions include specific activities such as creating proposals, contacting customers, and scheduling meetings. These actions are not limited to following the proposed strategy; users can also adjust them based on their own judgment.

[0464] (Example 1)

[0465] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] In today's business environment, companies need to quickly collect and analyze valuable data from vast amounts of information to formulate appropriate sales strategies in order to maintain their competitiveness. However, doing this manually is extremely labor-intensive, and real-time monitoring and rapid response are difficult. To solve this problem, there is a need to develop a system that can handle everything from automated information collection to real-time notifications.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0468] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for calculating the likelihood of a lead closing using a machine learning algorithm. This enables companies to efficiently process large amounts of information, quickly generate optimal sales strategies, and immediately implement them.

[0469] "Information sources" refer to all digital media, such as websites, social media, and news sites, that are referenced to collect data.

[0470] "Automated data collection" refers to the process of periodically acquiring data through a program without manual intervention.

[0471] "Noise reduction" refers to the process of removing irrelevant or meaningless information from data to increase its purity.

[0472] "Standardization" refers to the process of unifying data formats and structures into a consistent form.

[0473] "Closing probability" refers to a numerical value or score that indicates the degree to which a lead is likely to actually result in a transaction.

[0474] A "machine learning algorithm" refers to a mathematical model used to analyze large amounts of data and make predictions or classifications related to a specific task.

[0475] "Sales strategy" refers to the approach and plan a company uses to conduct its commercial activities.

[0476] "Real-time monitoring" refers to the instantaneous tracking of data and situations, ensuring that the latest information is always available.

[0477] "Notification" refers to sending a message to inform a user when a specific event or change occurs.

[0478] "User interface" refers to the screen layout and operating environment that users use to view and manipulate information.

[0479] A "data feed" refers to a system that provides a continuously updated stream of data.

[0480] To implement the present invention, it is conceivable to construct a system as follows. First, the server functions as the core of the whole system and performs automated information gathering processing. Here, various information sources on the internet are utilized for data collection. Specifically, it connects with official company websites, social media, news media, etc., and acquires data using web scraping tools and APIs (for example, general web scraping libraries and social media APIs).

[0481] Next, the server performs preprocessing on the collected data. At this stage, data cleansing is performed, including noise reduction and formatting standardization, using libraries such as Python's Pandas and Beautiful Soup to improve data quality.

[0482] Furthermore, the server evaluates the likelihood of a lead being converted through a machine learning algorithm. Here, the server uses a model that has been trained based on historical data. Specifically, it uses a logistic regression model provided by Scikit-learn to calculate the likelihood of conversion as a score by inputting the collected lead attribute data.

[0483] The server then uses the obtained score results to build the optimal sales strategy. It has the capability to provide different approaches depending on the characteristics of each lead. For example, in certain markets, it may be determined that a social media campaign is effective.

[0484] Furthermore, the server tracks changes in real time through its monitoring function and quickly notifies sales representatives when important events or market fluctuations are detected. These notifications are delivered via email or the company's internal communication platform.

[0485] Ultimately, the device provides an intuitive user interface for sales representatives. Here, users can easily and clearly see each lead's closing score and proposed sales strategy. The UI is built with a front-end framework such as React, creating an environment where the sales team can work efficiently.

[0486] For example, if a user targets a company offering a new product, the server will continuously analyze the company's social media activity and develop a sales strategy to implement campaigns at the appropriate time. Furthermore, it can utilize generative AI models to make predictions and suggestions based on specific conditions.

[0487] Examples of prompts to input into a generative AI model:

[0488] "Gather the latest information on the specified companies and evaluate their likelihood of closing a deal. This information consists of data obtained through websites and social media."

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] The server collects data from information sources on the internet. Input includes pre-specified company names and related keywords, and output is the collected raw data. This process uses web scraping tools and APIs to retrieve websites, social media posts, and news articles. For example, it may involve extracting text data from a specified site using a common web scraping library.

[0492] Step 2:

[0493] The server preprocesses the collected data. The input is the raw data obtained in step 1, and the output is clean, standardized data. This process utilizes Python's Pandas and Beautiful Soup to remove noise and standardize the format. For example, this includes specific actions such as removing HTML tags and formatting special characters.

[0494] Step 3:

[0495] The server inputs the preprocessed data into a machine learning model to evaluate the likelihood of each lead being converted. The input is the clean data from step 2, and the output is the conversion likelihood score. Here, the server uses the Scikit-learn algorithm to analyze the attribute data using a logistic regression model. For example, the characteristics of each lead are converted into numerical vectors as input to the model, and a score is calculated.

[0496] Step 4:

[0497] The server develops sales strategies based on the scoring results. The input is the closing score from Step 3, and the output is a customized sales strategy. The server uses a pre-configured rule-based system to select the optimal approach based on industry and scale. For example, it may recommend social media campaigns in certain markets.

[0498] Step 5:

[0499] The server monitors lead information in real time and sends notifications when significant changes are detected. Input is a real-time data feed, and output is notification messages to the responsible party. The server sets thresholds and sends alerts via email or communication platforms when fluctuations are detected. Specifically, continuous data monitoring is performed to collect market changes.

[0500] Step 6:

[0501] The terminal provides a user interface that allows sales representatives to view information. Input is the final sales data obtained from the server, and output is a visualized interface display. The terminal uses a web frontend framework such as React to build dynamic dashboards and provide information to the user visually. This includes actions such as graphing closing scores and displaying strategic proposals as cards.

[0502] (Application Example 1)

[0503] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0504] A challenge in applying current sales and advertising strategies is the inefficient collection of data from a vast number of sources and the inability to efficiently assess the likelihood of transactions. Furthermore, the optimization of advertising strategies and the ability to respond immediately to changes in transactions are insufficient, limiting the effectiveness of sales activities. In addition, the lack of a system to grasp market changes in the customer base in real time and respond immediately makes it easy to miss opportunities.

[0505] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0506] In this invention, the server includes means for automatically collecting information from a vast data source, means for removing unnecessary data and standardizing the collected information, and means for evaluating the potential of a transaction using a machine learning algorithm. This enables efficient data processing and optimization of sales strategies, thereby maximizing the effectiveness of advertising strategies and enabling rapid responses to market fluctuations.

[0507] A "vast data source" refers to a wide range of information sources, such as company websites and social media, which are the targets of information collection.

[0508] "Automatically collecting information" means that the system acquires information according to its programmed instructions, without requiring human intervention.

[0509] "Removing unnecessary data" is the process of removing noise that is not needed for analysis or evaluation, leaving only the necessary data.

[0510] "Standardization" refers to unifying data in different formats and types to create a state that allows for efficient subsequent processing.

[0511] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that information to make future predictions and classifications.

[0512] "Assessing the likelihood of a transaction" means quantifying or classifying the probability that a potential trading partner or inventory source will actually complete a business transaction.

[0513] "Creating a sales policy" means planning and proposing the optimal approach and strategy for dealing with clients.

[0514] "To be able to view information" means to make information presented as digital data through a user interface visually verifiable by humans.

[0515] "Communicating an advertising strategy" means putting a proposed advertising policy into action and communicating its contents to a wide audience.

[0516] "Sending a warning" means that when the system determines that certain conditions have been met, it immediately sends out a notification to provide an alert or information.

[0517] To implement this invention, the first role of the server is to automatically collect information from a vast data source using web crawlers and APIs. The server then uses Python libraries such as Pandas and NumPy to remove unnecessary data and standardize the collected data. This organizes the data, allowing it to proceed to the next evaluation step.

[0518] During the evaluation phase, the server uses machine learning algorithms such as Scikit-learn to train a model on historical data and perform scoring to predict the likelihood of a transaction. This score is used as an important data point for formulating sales strategies. The server automatically generates the optimal sales strategy based on the scoring results and compiles it into a proposal for an advertising strategy for the user.

[0519] The device provides a user interface that visualizes this information. Built with React Native and other technologies, the user interface is designed to allow sales representatives to easily access and immediately utilize the information in their sales activities. This enables rapid responses to changing market conditions.

[0520] For example, users can observe information about business partners launching new products and apply advertising campaigns based on that information in a timely manner to effectively reach potential customers.

[0521] Examples of prompts for the generating AI model include: "Based on the latest social media data, suggest ways to optimize our clients' advertising strategies," or "Use real-time analysis to understand competitor trends and plan effective advertising campaigns."

[0522] This invention enables real-time data monitoring and immediate strategic implementation, dramatically improving the efficiency of a company's sales activities.

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server automatically collects data from a vast number of sources on the internet using web crawlers and APIs. The input is a specified list of URLs or API endpoints, and the output is the collected raw data. This data forms the basis for subsequent data processing.

[0526] Step 2:

[0527] The server uses Pandas and NumPy to preprocess the collected raw data. Specifically, it filters out noisy data and standardizes the data format. The input is the raw data obtained in step 1, and the output is cleansed and standardized data. This ensures that the data is in a state suitable for analysis.

[0528] Step 3:

[0529] The server uses Scikit-learn to input standardized data into a machine learning model and calculate a transaction probability score. The input is the standardized data obtained in step 2, and the output is the evaluated score. This score indicates the likelihood of a transaction being completed with the trading partner.

[0530] Step 4:

[0531] The server generates optimal sales strategies and develops advertising strategies based on the transaction potential score. This may utilize a generative AI model. The input is the score obtained in step 3, and the output is the generated sales strategy and advertising strategy. Prompt statements are applied as needed to reflect the results of the AI ​​model.

[0532] Step 5:

[0533] The terminal visualizes and presents the generated sales policies and advertising strategies to sales representatives through a user interface. The input is the policies and strategies obtained in step 4, and the output is the visually displayed information. This enables sales representatives to respond quickly and appropriately.

[0534] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0535] To implement this invention, a configuration is adopted in which an emotion engine is integrated into the lead management system. The emotion engine can grasp the emotional state of sales representatives in real time by analyzing speech recognition, facial recognition technology, and text data entered by users.

[0536] First, the server is responsible for collecting and analyzing lead data. At the same time, the server also receives and centrally manages emotional data obtained from the emotion engine. The collected emotional data is used as an indicator of the sales representative's psychological state.

[0537] Next, the terminal provides an interface for the sales representative. This interface displays lead information along with the emotional state analyzed by the emotion engine. For example, if the sales representative is feeling stressed, the proposed sales strategy will be automatically adjusted based on that information. Specifically, a flexible approach may be suggested to ensure that communication does not become overly stressful.

[0538] Furthermore, the server combines and analyzes lead data and sentiment data to generate feedback for sales representatives. This feedback helps them approach high-potential leads at the most effective time. For example, it provides strategies for sales representatives to interact with leads in a relaxed state and guidelines to reduce stress.

[0539] For example, suppose a user attempts to approach a particular lead, and data from their emotion engine indicates a state of tension. The server, upon receiving this information, automatically revises the approach and suggests a script that facilitates a more pleasant conversation. It also provides regular alerts to encourage breaks, helping sales representatives maintain optimal psychological well-being while continuing their work.

[0540] Thus, the present invention is a system that incorporates an emotion engine to realize comprehensive sales support that takes into account the psychological aspects of sales representatives.

[0541] The following describes the processing flow.

[0542] Step 1:

[0543] The server uses web scraping techniques to collect lead-related data from the internet. This data includes information from company websites, social media posts, industry news, and other sources, and is stored in a database.

[0544] Step 2:

[0545] The server collects user (sales representative) emotional data in real time through an emotion engine. This data collection utilizes technologies such as voice input, text analysis, and facial recognition. The emotional data is recorded as a psychological indicator for sales activities.

[0546] Step 3:

[0547] The server performs data cleansing on the collected read data, including noise reduction, duplicate removal, and format standardization. Simultaneously, data from the sentiment engine is preprocessed for analysis and converted into an analyzable format.

[0548] Step 4:

[0549] The server uses a machine learning model to score the likelihood of a lead closing. It applies an algorithm that reflects past transaction history and current market conditions to quantify the probability of each lead closing.

[0550] Step 5:

[0551] The server generates the optimal sales strategy for each lead based on the scoring results and sentiment data. If the sentiment engine determines that the salesperson's emotional state is sensitive, a gentler approach is selected, and the strategy is customized accordingly.

[0552] Step 6:

[0553] The device provides a dashboard for sales representatives, displaying lead information, closing scores, sentiment feedback, and recommended sales strategies. Sales representatives use this information to develop action plans.

[0554] Step 7:

[0555] Users leverage information provided by their devices to approach leads. They use emotional feedback to communicate at the appropriate time and adjust proposed sales strategies as needed.

[0556] Step 8:

[0557] The server continues to monitor emotional data during sales activities, and if it detects signs of stress or fatigue, it sends messages to the user via their device encouraging relaxation or suggesting breaks. This helps ensure that sales representatives maintain optimal condition.

[0558] (Example 2)

[0559] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0560] Traditional sales support systems focus on managing lead data and calculating the likelihood of closing deals, but they do not adequately address strategic adjustments that take into account the psychological state of sales representatives. As a result, they fail to effectively utilize the impact of sales representatives' emotional states on closing deals, leading to a problem where their performance is not optimized.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0562] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for analyzing the psychological state of sales representatives using sentiment analysis technology. This enables dynamic adjustment of sales strategies in accordance with the psychological state of sales representatives.

[0563] "Information source" refers to the place or system from which data is collected, including databases and the internet.

[0564] "Noise reduction" is the process of removing unnecessary or inaccurate information from data, and is performed to improve the accuracy of the data.

[0565] Standardization is the process of converting collected data into a consistent format and units to maintain data consistency and make it comparable.

[0566] A "machine learning algorithm" is a program or process that allows a machine to automatically learn patterns and rules from large amounts of data.

[0567] "Closing probability" is an indicator that shows the degree to which a lead is likely to close a deal during the sales process.

[0568] "Sales strategy" refers to the planned approach and methods for effectively selling products or services to customers.

[0569] "Emotional analysis technology" is a technique that analyzes a person's emotional state from sources such as voice, facial expressions, and text.

[0570] "Psychological state" refers to the emotional and mental state an individual is experiencing at a particular moment.

[0571] A "user interface" refers to the screens and operating devices used by a system and its users to exchange information, enabling intuitive operation.

[0572] To implement this invention, it is necessary to integrate sentiment analysis technology into the lead management system. Specifically, a system consisting of a server, terminals, and users is configured, and various hardware and software are used.

[0573] The server collects lead data from a vast number of sources and stores it in a database. The server then performs noise reduction and standardization on the collected data to ensure accuracy and consistency. Next, machine learning algorithms are used to calculate the likelihood of each lead converting. Furthermore, sentiment analysis technology is used to analyze the emotional state of sales representatives from their voice, facial expressions, and input text, and this information is then used to inform strategies.

[0574] The terminal provides an interface for sales representatives. This interface has the functionality to display lead information and sentiment analysis results in real time, specifically including a graphical dashboard and notification system. Based on this information, sales representatives can make decisions and dynamically adjust their sales strategies.

[0575] The sales representative, acting as the user, approaches leads based on the information provided. For example, if the user's emotional state indicates stress when approaching a particular lead, the server uses this information to automatically adjust the proposal and approach. Furthermore, by following the system's feedback, the user can reduce stress while conducting effective sales activities.

[0576] An example of a prompt might be, "Generate a friendly conversation script for when the sales representative is nervous." This would enable the AI ​​model to propose appropriate and flexible sales strategies.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The server automatically collects lead data from various sources. This data includes customer contact information and transaction history. It uses information from databases and web services as input and generates structured lead data as output, which is then stored in the database. Specifically, it uses scripts to retrieve information via APIs, automatically formatting and storing it.

[0580] Step 2:

[0581] The server performs denoising and standardization on the collected read data. This process removes unnecessary information and inconsistent data, improving data quality. Using the collected data as input, the output is a clean and unified dataset. Specifically, it filters out redundant data and imputes missing values, then stores the results back into the database.

[0582] Step 3:

[0583] The server uses emotion analysis technology to analyze the psychological state of sales representatives. It processes voice and facial expression data as input and generates an index indicating the sales representative's emotional state as output. This process requires acquiring data in real time from microphones and cameras and applying an emotion analysis algorithm to calculate an emotion score.

[0584] Step 4:

[0585] The server uses machine learning algorithms to calculate the likelihood of a lead closing. It utilizes lead data and the emotional state of sales representatives as input and outputs a score indicating the probability of closing. Specifically, it builds a predictive model based on past closing data and performs predictions by analyzing real-time data.

[0586] Step 5:

[0587] The terminal displays information to sales representatives through a user interface. This interface is in a dashboard format, visualizing lead data, sentiment status, and conversion probability. It retrieves information from the server as input and provides it to sales representatives in an easy-to-understand format as output. Specifically, it generates an intuitive interface by graphically arranging the data.

[0588] Step 6:

[0589] The user approaches leads based on the information displayed in the interface. It generates prompts as needed and dynamically adjusts the sales strategy. Based on the data received from the interface as input, it executes an improved sales script as output. Specific actions include reading out appropriate conversation scripts to ease tension and executing flexible sales approaches.

[0590] (Application Example 2)

[0591] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0592] Existing sales support systems struggle to provide flexible responses that take into account the feelings and psychological state of sales representatives, limiting improvements in closing rates. Furthermore, because home-use devices cannot provide appropriate support that responds to residents' emotions, new needs are arising to enhance their quality of life.

[0593] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0594] In this invention, the server includes means for analyzing the emotional state of a salesperson using emotion recognition technology, means for generating an optimal sales strategy based on the calculated probability of closing a deal and the salesperson's emotional state, and means for a home device to perform the optimal action based on the emotional state of the family. This makes it possible to support sales activities in accordance with the psychological state of the salesperson, and improve the quality of life by having the home device provide appropriate actions in accordance with people's emotions.

[0595] "Automated data collection" is the process of automatically extracting necessary information from a vast amount of data sources using a program.

[0596] "Denoising and standardization" is the process of removing unnecessary information from collected data and organizing the data into a consistent format.

[0597] A "machine learning algorithm" is an algorithm used to analyze data and make predictions or classifications based on specific patterns or rules.

[0598] "Closing probability" refers to the degree of likelihood that a particular lead will result in a sale as a result of sales activities.

[0599] "Emotion recognition technology" is a technology that objectively determines a person's emotions by analyzing their voice, facial expressions, and body movements.

[0600] "Sales strategy generation" is the act of formulating a plan for the most effective sales activities based on analyzed data.

[0601] "User interface" refers to the screens and operating systems that facilitate the smooth exchange of information between a system and a user.

[0602] "Optimal action" refers to the actions or choices that best match the situation and conditions and produce the desired outcome.

[0603] In this system, the server plays a central role. The server automatically collects data from a vast number of sources, performing noise reduction and standardization in the process. A high-performance database management system is used for data collection. The collected data is then used to calculate the likelihood of each lead being converted using machine learning algorithms. For example, the scikit-learn library in Python is used for this purpose.

[0604] In addition, the server utilizes emotion recognition technology to analyze audio and video data in real time, for example. This allows it to understand the emotional state of sales representatives and family members. This process employs a TensorFlow model that utilizes deep learning.

[0605] Sales representatives can access information provided by the server through the user interface of their smartphones or home devices. This interface, implemented using web and mobile app technologies, displays optimal sales strategies and in-home action suggestions tailored to individual emotions.

[0606] For example, if a salesperson is detected as being stressed, the server will suggest a gentler sales script based on emotional data. Similarly, if a home device detects a child's depression, it will suggest playing uplifting music.

[0607] Examples of prompts for a generative AI model include:

[0608] "What kind of encouraging words should you offer when a child is feeling down?"

[0609] "What kind of conversation should sales representatives keep in mind when visiting clients?"

[0610] This invention proposes flexible behaviors that respond to emotional states, and is expected to improve the quality of business activities and family life.

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

[0612] Step 1:

[0613] The server automatically collects data from a vast number of sources. It receives raw data from each data source as input and stores it in a collection database as output. Specifically, it accesses online databases via APIs to retrieve sales-related information.

[0614] Step 2:

[0615] The server performs denoising and standardization on the collected data. The input is the collected raw data, and the output is a clean dataset. In this process, outliers are removed using the numpy library and the data is converted to CSV format.

[0616] Step 3:

[0617] The server calculates the conversion probability of a lead using a machine learning algorithm. The input is a clean dataset, and the output is a conversion probability score. Specifically, it uses scikit-learn to execute a random forest algorithm and makes predictions based on the lead's features.

[0618] Step 4:

[0619] The server uses emotion recognition technology to analyze the voice and video data of sales representatives. It receives real-time collected voice and facial image data as input, and outputs emotional state labels. Specifically, it uses a TensorFlow emotion recognition model to evaluate the voice spectrum and facial expressions.

[0620] Step 5:

[0621] The server generates the optimal sales strategy based on the obtained conversion probability score and emotional state. The input is the conversion score and emotional label, and the output is a customized sales script. A generative AI model is used to generate emotionally sensitive, contextually appropriate prompts.

[0622] Step 6:

[0623] The user terminal presents the generated sales strategies and action proposals to the sales representative. The input consists of customized scripts and proposals received from the server, while the output is visual feedback to the user. Specifically, the strategy is displayed to the representative using the notification function of a smartphone app.

[0624] Step 7:

[0625] Users initiate actions based on suggestions from the application. The input is the presented suggestion, and the output is actual sales activities or actions within the home. Specifically, they might start a conversation with a client or take appropriate action with family members based on a suggested script.

[0626] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0627] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0628] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0629] [Fourth Embodiment]

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

[0631] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0632] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0633] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0634] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0635] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0636] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0637] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0638] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] One possible embodiment of this invention is to construct the following system.

[0644] First, the server runs a program to collect data from internet sources. This program is configured to periodically retrieve the latest information from multiple sources, such as the websites and social media accounts of specified companies.

[0645] Next, the server preprocesses the collected data in order to analyze it. This process automatically removes noise and standardizes the data format to improve the accuracy and reliability of the analysis.

[0646] The server then uses a machine learning algorithm to evaluate the lead's likelihood of conversion. Based on past conversion data, the model is trained using the lead's current attributes and behavioral patterns as input, and the likelihood of conversion is output as a score.

[0647] Furthermore, the server develops the optimal sales strategy based on the scoring results. This strategy is customized according to the industry and size of the lead. For example, if it is determined that a social media campaign would be effective in a particular industry, the server will propose that method.

[0648] The server also monitors lead information in real time and immediately notifies sales representatives of any significant changes. These notifications are issued when a lead makes a major business announcement or when other market fluctuations are detected.

[0649] Once the information is ready, the terminal provides a user interface for sales representatives. This interface visually displays each lead's closing score and proposed sales strategy, providing information directly relevant to planning sales activities.

[0650] For example, if a user is targeting lead companies with new product lines, the server will continuously analyze those leads' social media activity and suggest sales strategies such as launching large-scale online campaigns at the right moments.

[0651] Thus, the present invention is a system that automates a series of processes from data collection and analysis to proposal, monitoring, and notification, dramatically improving the efficiency of the sales team.

[0652] The following describes the processing flow.

[0653] Step 1:

[0654] The server uses web scraping to collect data from information sources on the internet. This targets information from corporate websites, social networking platforms, news sites, etc., and is performed periodically according to a pre-set schedule. The collected data is temporarily stored in a database.

[0655] Step 2:

[0656] The server preprocesses the collected data. This step involves filtering out noisy data, removing duplicate data, and standardizing the format (e.g., formatting dates). This prepares the data for use in the next analysis step.

[0657] Step 3:

[0658] The server uses pre-processed data to apply a machine learning algorithm to score the likelihood of each lead closing. Here, the current lead data is input into a model trained using past transaction data and lead characteristic data, and the probability of each lead closing is calculated.

[0659] Step 4:

[0660] The server generates the optimal sales strategy for each lead based on the scoring results. In this step, the strategy is selected considering the lead's industry, size, geographical factors, and past success stories. For example, it determines whether an email campaign or a direct visit is appropriate.

[0661] Step 5:

[0662] The server monitors lead information in real time and detects important changes. This monitoring is done to catch changes in lead behavior, such as new product announcements or company news. When a change is detected, a notification is quickly sent to the sales team.

[0663] Step 6:

[0664] The device provides a dashboard for sales representatives to access, allowing them to view lead conversion scores, proposed strategies, and updates. The display interface is designed to be directly relevant to sales activities, enabling users to develop effective sales plans based on this information.

[0665] Step 7:

[0666] Based on the information provided through the device, users initiate sales actions towards target leads. These actions include specific activities such as creating proposals, contacting customers, and scheduling meetings. These actions are not limited to following the proposed strategy; users can also adjust them based on their own judgment.

[0667] (Example 1)

[0668] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] In today's business environment, companies need to quickly collect and analyze valuable data from vast amounts of information to formulate appropriate sales strategies in order to maintain their competitiveness. However, doing this manually is extremely labor-intensive, and real-time monitoring and rapid response are difficult. To solve this problem, there is a need to develop a system that can handle everything from automated information collection to real-time notifications.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0671] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for calculating the likelihood of a lead closing using a machine learning algorithm. This enables companies to efficiently process large amounts of information, quickly generate optimal sales strategies, and immediately implement them.

[0672] "Information sources" refer to all digital media, such as websites, social media, and news sites, that are referenced to collect data.

[0673] "Automated data collection" refers to the process of periodically acquiring data through a program without manual intervention.

[0674] "Noise reduction" refers to the process of removing irrelevant or meaningless information from data to increase its purity.

[0675] "Standardization" refers to the process of unifying data formats and structures into a consistent form.

[0676] "Closing probability" refers to a numerical value or score that indicates the degree to which a lead is likely to actually result in a transaction.

[0677] A "machine learning algorithm" refers to a mathematical model used to analyze large amounts of data and make predictions or classifications related to a specific task.

[0678] "Sales strategy" refers to the approach and plan a company uses to conduct its commercial activities.

[0679] "Real-time monitoring" refers to the instantaneous tracking of data and situations, ensuring that the latest information is always available.

[0680] "Notification" refers to sending a message to inform a user when a specific event or change occurs.

[0681] "User interface" refers to the screen layout and operating environment that users use to view and manipulate information.

[0682] A "data feed" refers to a system that provides a continuously updated stream of data.

[0683] To implement the present invention, it is conceivable to construct a system as follows. First, the server functions as the core of the whole system and performs automated information gathering processing. Here, various information sources on the internet are utilized for data collection. Specifically, it connects with official company websites, social media, news media, etc., and acquires data using web scraping tools and APIs (for example, general web scraping libraries and social media APIs).

[0684] Next, the server performs preprocessing on the collected data. At this stage, data cleansing is performed, including noise reduction and formatting standardization, using libraries such as Python's Pandas and Beautiful Soup to improve data quality.

[0685] Furthermore, the server evaluates the likelihood of a lead being converted through a machine learning algorithm. Here, the server uses a model that has been trained based on historical data. Specifically, it uses a logistic regression model provided by Scikit-learn to calculate the likelihood of conversion as a score by inputting the collected lead attribute data.

[0686] The server then uses the obtained score results to build the optimal sales strategy. It has the capability to provide different approaches depending on the characteristics of each lead. For example, in certain markets, it may be determined that a social media campaign is effective.

[0687] Furthermore, the server tracks changes in real time through its monitoring function and quickly notifies sales representatives when important events or market fluctuations are detected. These notifications are delivered via email or the company's internal communication platform.

[0688] Ultimately, the device provides an intuitive user interface for sales representatives. Here, users can easily and clearly see each lead's closing score and proposed sales strategy. The UI is built with a front-end framework such as React, creating an environment where the sales team can work efficiently.

[0689] For example, if a user targets a company offering a new product, the server will continuously analyze the company's social media activity and develop a sales strategy to implement campaigns at the appropriate time. Furthermore, it can utilize generative AI models to make predictions and suggestions based on specific conditions.

[0690] Examples of prompts to input into a generative AI model:

[0691] "Gather the latest information on the specified companies and evaluate their likelihood of closing a deal. This information consists of data obtained through websites and social media."

[0692] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0693] Step 1:

[0694] The server collects data from information sources on the internet. Input includes pre-specified company names and related keywords, and output is the collected raw data. This process uses web scraping tools and APIs to retrieve websites, social media posts, and news articles. For example, it may involve extracting text data from a specified site using a common web scraping library.

[0695] Step 2:

[0696] The server preprocesses the collected data. The input is the raw data obtained in step 1, and the output is clean, standardized data. This process utilizes Python's Pandas and Beautiful Soup to remove noise and standardize the format. For example, this includes specific actions such as removing HTML tags and formatting special characters.

[0697] Step 3:

[0698] The server inputs the preprocessed data into a machine learning model to evaluate the likelihood of each lead being converted. The input is the clean data from step 2, and the output is the conversion likelihood score. Here, the server uses the Scikit-learn algorithm to analyze the attribute data using a logistic regression model. For example, the characteristics of each lead are converted into numerical vectors as input to the model, and a score is calculated.

[0699] Step 4:

[0700] The server develops sales strategies based on the scoring results. The input is the closing score from Step 3, and the output is a customized sales strategy. The server uses a pre-configured rule-based system to select the optimal approach based on industry and scale. For example, it may recommend social media campaigns in certain markets.

[0701] Step 5:

[0702] The server monitors lead information in real time and sends notifications when significant changes are detected. Input is a real-time data feed, and output is notification messages to the responsible party. The server sets thresholds and sends alerts via email or communication platforms when fluctuations are detected. Specifically, continuous data monitoring is performed to collect market changes.

[0703] Step 6:

[0704] The terminal provides a user interface that allows sales representatives to view information. Input is the final sales data obtained from the server, and output is a visualized interface display. The terminal uses a web frontend framework such as React to build dynamic dashboards and provide information to the user visually. This includes actions such as graphing closing scores and displaying strategic proposals as cards.

[0705] (Application Example 1)

[0706] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0707] A challenge in applying current sales and advertising strategies is the inefficient collection of data from a vast number of sources and the inability to efficiently assess the likelihood of transactions. Furthermore, the optimization of advertising strategies and the ability to respond immediately to changes in transactions are insufficient, limiting the effectiveness of sales activities. In addition, the lack of a system to grasp market changes in the customer base in real time and respond immediately makes it easy to miss opportunities.

[0708] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0709] In this invention, the server includes means for automatically collecting information from a vast data source, means for removing unnecessary data and standardizing the collected information, and means for evaluating the potential of a transaction using a machine learning algorithm. This enables efficient data processing and optimization of sales strategies, thereby maximizing the effectiveness of advertising strategies and enabling rapid responses to market fluctuations.

[0710] A "vast data source" refers to a wide range of information sources, such as company websites and social media, which are the targets of information collection.

[0711] "Automatically collecting information" means that the system acquires information according to its programmed instructions, without requiring human intervention.

[0712] "Removing unnecessary data" is the process of removing noise that is not needed for analysis or evaluation, leaving only the necessary data.

[0713] "Standardization" refers to unifying data in different formats and types to create a state that allows for efficient subsequent processing.

[0714] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that information to make future predictions and classifications.

[0715] "Assessing the likelihood of a transaction" means quantifying or classifying the probability that a potential trading partner or inventory source will actually complete a business transaction.

[0716] "Creating a sales policy" means planning and proposing the optimal approach and strategy for dealing with clients.

[0717] "To be able to view information" means to make information presented as digital data through a user interface visually verifiable by humans.

[0718] "Communicating an advertising strategy" means putting a proposed advertising policy into action and communicating its contents to a wide audience.

[0719] "Sending a warning" means that when the system determines that certain conditions have been met, it immediately sends out a notification to provide an alert or information.

[0720] To implement this invention, the first role of the server is to automatically collect information from a vast data source using web crawlers and APIs. The server then uses Python libraries such as Pandas and NumPy to remove unnecessary data and standardize the collected data. This organizes the data, allowing it to proceed to the next evaluation step.

[0721] During the evaluation phase, the server uses machine learning algorithms such as Scikit-learn to train a model on historical data and perform scoring to predict the likelihood of a transaction. This score is used as an important data point for formulating sales strategies. The server automatically generates the optimal sales strategy based on the scoring results and compiles it into a proposal for an advertising strategy for the user.

[0722] The device provides a user interface that visualizes this information. Built with React Native and other technologies, the user interface is designed to allow sales representatives to easily access and immediately utilize the information in their sales activities. This enables rapid responses to changing market conditions.

[0723] For example, users can observe information about business partners launching new products and apply advertising campaigns based on that information in a timely manner to effectively reach potential customers.

[0724] Examples of prompts for the generating AI model include: "Based on the latest social media data, suggest ways to optimize our clients' advertising strategies," or "Use real-time analysis to understand competitor trends and plan effective advertising campaigns."

[0725] This invention enables real-time data monitoring and immediate strategic implementation, dramatically improving the efficiency of a company's sales activities.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server automatically collects data from a vast number of sources on the internet using web crawlers and APIs. The input is a specified list of URLs or API endpoints, and the output is the collected raw data. This data forms the basis for subsequent data processing.

[0729] Step 2:

[0730] The server uses Pandas and NumPy to preprocess the collected raw data. Specifically, it filters out noisy data and standardizes the data format. The input is the raw data obtained in step 1, and the output is cleansed and standardized data. This ensures that the data is in a state suitable for analysis.

[0731] Step 3:

[0732] The server uses Scikit-learn to input standardized data into a machine learning model and calculate a transaction probability score. The input is the standardized data obtained in step 2, and the output is the evaluated score. This score indicates the likelihood of a transaction being completed with the trading partner.

[0733] Step 4:

[0734] The server generates optimal sales strategies and develops advertising strategies based on the transaction potential score. This may utilize a generative AI model. The input is the score obtained in step 3, and the output is the generated sales strategy and advertising strategy. Prompt statements are applied as needed to reflect the results of the AI ​​model.

[0735] Step 5:

[0736] The terminal visualizes and presents the generated sales policies and advertising strategies to sales representatives through a user interface. The input is the policies and strategies obtained in step 4, and the output is the visually displayed information. This enables sales representatives to respond quickly and appropriately.

[0737] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0738] To implement this invention, a configuration is adopted in which an emotion engine is integrated into the lead management system. The emotion engine can grasp the emotional state of sales representatives in real time by analyzing speech recognition, facial recognition technology, and text data entered by users.

[0739] First, the server is responsible for collecting and analyzing lead data. At the same time, the server also receives and centrally manages emotional data obtained from the emotion engine. The collected emotional data is used as an indicator of the sales representative's psychological state.

[0740] Next, the terminal provides an interface for the sales representative. This interface displays lead information along with the emotional state analyzed by the emotion engine. For example, if the sales representative is feeling stressed, the proposed sales strategy will be automatically adjusted based on that information. Specifically, a flexible approach may be suggested to ensure that communication does not become overly stressful.

[0741] Furthermore, the server combines and analyzes lead data and sentiment data to generate feedback for sales representatives. This feedback helps them approach high-potential leads at the most effective time. For example, it provides strategies for sales representatives to interact with leads in a relaxed state and guidelines to reduce stress.

[0742] For example, suppose a user attempts to approach a particular lead, and data from their emotion engine indicates a state of tension. The server, upon receiving this information, automatically revises the approach and suggests a script that facilitates a more pleasant conversation. It also provides regular alerts to encourage breaks, helping sales representatives maintain optimal psychological well-being while continuing their work.

[0743] Thus, the present invention is a system that incorporates an emotion engine to realize comprehensive sales support that takes into account the psychological aspects of sales representatives.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The server uses web scraping techniques to collect lead-related data from the internet. This data includes information from company websites, social media posts, industry news, and other sources, and is stored in a database.

[0747] Step 2:

[0748] The server collects user (sales representative) emotional data in real time through an emotion engine. This data collection utilizes technologies such as voice input, text analysis, and facial recognition. The emotional data is recorded as a psychological indicator for sales activities.

[0749] Step 3:

[0750] The server performs data cleansing on the collected read data, including noise reduction, duplicate removal, and format standardization. Simultaneously, data from the sentiment engine is preprocessed for analysis and converted into an analyzable format.

[0751] Step 4:

[0752] The server uses a machine learning model to score the likelihood of a lead closing. It applies an algorithm that reflects past transaction history and current market conditions to quantify the probability of each lead closing.

[0753] Step 5:

[0754] The server generates the optimal sales strategy for each lead based on the scoring results and sentiment data. If the sentiment engine determines that the salesperson's emotional state is sensitive, a gentler approach is selected, and the strategy is customized accordingly.

[0755] Step 6:

[0756] The device provides a dashboard for sales representatives, displaying lead information, closing scores, sentiment feedback, and recommended sales strategies. Sales representatives use this information to develop action plans.

[0757] Step 7:

[0758] Users leverage information provided by their devices to approach leads. They use emotional feedback to communicate at the appropriate time and adjust proposed sales strategies as needed.

[0759] Step 8:

[0760] The server continues to monitor emotional data during sales activities, and if it detects signs of stress or fatigue, it sends messages to the user via their device encouraging relaxation or suggesting breaks. This helps ensure that sales representatives maintain optimal condition.

[0761] (Example 2)

[0762] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0763] Traditional sales support systems focus on managing lead data and calculating the likelihood of closing deals, but they do not adequately address strategic adjustments that take into account the psychological state of sales representatives. As a result, they fail to effectively utilize the impact of sales representatives' emotional states on closing deals, leading to a problem where their performance is not optimized.

[0764] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0765] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for denoising and standardizing the collected data, and means for analyzing the psychological state of sales representatives using sentiment analysis technology. This enables dynamic adjustment of sales strategies in accordance with the psychological state of sales representatives.

[0766] "Information source" refers to the place or system from which data is collected, including databases and the internet.

[0767] "Noise reduction" is the process of removing unnecessary or inaccurate information from data, and is performed to improve the accuracy of the data.

[0768] Standardization is the process of converting collected data into a consistent format and units to maintain data consistency and make it comparable.

[0769] A "machine learning algorithm" is a program or process that allows a machine to automatically learn patterns and rules from large amounts of data.

[0770] "Closing probability" is an indicator that shows the degree to which a lead is likely to close a deal during the sales process.

[0771] "Sales strategy" refers to the planned approach and methods for effectively selling products or services to customers.

[0772] "Emotional analysis technology" is a technique that analyzes a person's emotional state from sources such as voice, facial expressions, and text.

[0773] "Psychological state" refers to the emotional and mental state an individual is experiencing at a particular moment.

[0774] A "user interface" refers to the screens and operating devices used by a system and its users to exchange information, enabling intuitive operation.

[0775] To implement this invention, it is necessary to integrate sentiment analysis technology into the lead management system. Specifically, a system consisting of a server, terminals, and users is configured, and various hardware and software are used.

[0776] The server collects lead data from a vast number of sources and stores it in a database. The server then performs noise reduction and standardization on the collected data to ensure accuracy and consistency. Next, machine learning algorithms are used to calculate the likelihood of each lead converting. Furthermore, sentiment analysis technology is used to analyze the emotional state of sales representatives from their voice, facial expressions, and input text, and this information is then used to inform strategies.

[0777] The terminal provides an interface for sales representatives. This interface has the functionality to display lead information and sentiment analysis results in real time, specifically including a graphical dashboard and notification system. Based on this information, sales representatives can make decisions and dynamically adjust their sales strategies.

[0778] The sales representative, acting as the user, approaches leads based on the information provided. For example, if the user's emotional state indicates stress when approaching a particular lead, the server uses this information to automatically adjust the proposal and approach. Furthermore, by following the system's feedback, the user can reduce stress while conducting effective sales activities.

[0779] An example of a prompt might be, "Generate a friendly conversation script for when the sales representative is nervous." This would enable the AI ​​model to propose appropriate and flexible sales strategies.

[0780] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0781] Step 1:

[0782] The server automatically collects lead data from various sources. This data includes customer contact information and transaction history. It uses information from databases and web services as input and generates structured lead data as output, which is then stored in the database. Specifically, it uses scripts to retrieve information via APIs, automatically formatting and storing it.

[0783] Step 2:

[0784] The server performs denoising and standardization on the collected read data. This process removes unnecessary information and inconsistent data, improving data quality. Using the collected data as input, the output is a clean and unified dataset. Specifically, it filters out redundant data and imputes missing values, then stores the results back into the database.

[0785] Step 3:

[0786] The server uses emotion analysis technology to analyze the psychological state of sales representatives. It processes voice and facial expression data as input and generates an index indicating the sales representative's emotional state as output. This process requires acquiring data in real time from microphones and cameras and applying an emotion analysis algorithm to calculate an emotion score.

[0787] Step 4:

[0788] The server uses machine learning algorithms to calculate the likelihood of a lead closing. It utilizes lead data and the emotional state of sales representatives as input and outputs a score indicating the probability of closing. Specifically, it builds a predictive model based on past closing data and performs predictions by analyzing real-time data.

[0789] Step 5:

[0790] The terminal displays information to sales representatives through a user interface. This interface is in a dashboard format, visualizing lead data, sentiment status, and conversion probability. It retrieves information from the server as input and provides it to sales representatives in an easy-to-understand format as output. Specifically, it generates an intuitive interface by graphically arranging the data.

[0791] Step 6:

[0792] The user approaches leads based on the information displayed in the interface. It generates prompts as needed and dynamically adjusts the sales strategy. Based on the data received from the interface as input, it executes an improved sales script as output. Specific actions include reading out appropriate conversation scripts to ease tension and executing flexible sales approaches.

[0793] (Application Example 2)

[0794] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0795] Existing sales support systems struggle to provide flexible responses that take into account the feelings and psychological state of sales representatives, limiting improvements in closing rates. Furthermore, because home-use devices cannot provide appropriate support that responds to residents' emotions, new needs are arising to enhance their quality of life.

[0796] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0797] In this invention, the server includes means for analyzing the emotional state of a salesperson using emotion recognition technology, means for generating an optimal sales strategy based on the calculated probability of closing a deal and the salesperson's emotional state, and means for a home device to perform the optimal action based on the emotional state of the family. This makes it possible to support sales activities in accordance with the psychological state of the salesperson, and improve the quality of life by having the home device provide appropriate actions in accordance with people's emotions.

[0798] "Automated data collection" is the process of automatically extracting necessary information from a vast amount of data sources using a program.

[0799] "Denoising and standardization" is the process of removing unnecessary information from collected data and organizing the data into a consistent format.

[0800] A "machine learning algorithm" is an algorithm used to analyze data and make predictions or classifications based on specific patterns or rules.

[0801] "Closing probability" refers to the degree of likelihood that a particular lead will result in a sale as a result of sales activities.

[0802] "Emotion recognition technology" is a technology that objectively determines a person's emotions by analyzing their voice, facial expressions, and body movements.

[0803] "Sales strategy generation" is the act of formulating a plan for the most effective sales activities based on analyzed data.

[0804] "User interface" refers to the screens and operating systems that facilitate the smooth exchange of information between a system and a user.

[0805] "Optimal action" refers to the actions or choices that best match the situation and conditions and produce the desired outcome.

[0806] In this system, the server plays a central role. The server automatically collects data from a vast number of sources, performing noise reduction and standardization in the process. A high-performance database management system is used for data collection. The collected data is then used to calculate the likelihood of each lead being converted using machine learning algorithms. For example, the scikit-learn library in Python is used for this purpose.

[0807] In addition, the server utilizes emotion recognition technology to analyze audio and video data in real time, for example. This allows it to understand the emotional state of sales representatives and family members. This process employs a TensorFlow model that utilizes deep learning.

[0808] Sales representatives can access information provided by the server through the user interface of their smartphones or home devices. This interface, implemented using web and mobile app technologies, displays optimal sales strategies and in-home action suggestions tailored to individual emotions.

[0809] For example, if a salesperson is detected as being stressed, the server will suggest a gentler sales script based on emotional data. Similarly, if a home device detects a child's depression, it will suggest playing uplifting music.

[0810] Examples of prompts for a generative AI model include:

[0811] "What kind of encouraging words should you offer when a child is feeling down?"

[0812] "What kind of conversation should sales representatives keep in mind when visiting clients?"

[0813] This invention proposes flexible behaviors that respond to emotional states, and is expected to improve the quality of business activities and family life.

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

[0815] Step 1:

[0816] The server automatically collects data from a vast number of sources. It receives raw data from each data source as input and stores it in a collection database as output. Specifically, it accesses online databases via APIs to retrieve sales-related information.

[0817] Step 2:

[0818] The server performs denoising and standardization on the collected data. The input is the collected raw data, and the output is a clean dataset. In this process, outliers are removed using the numpy library and the data is converted to CSV format.

[0819] Step 3:

[0820] The server calculates the conversion probability of a lead using a machine learning algorithm. The input is a clean dataset, and the output is a conversion probability score. Specifically, it uses scikit-learn to execute a random forest algorithm and makes predictions based on the lead's features.

[0821] Step 4:

[0822] The server uses emotion recognition technology to analyze the voice and video data of sales representatives. It receives real-time collected voice and facial image data as input, and outputs emotional state labels. Specifically, it uses a TensorFlow emotion recognition model to evaluate the voice spectrum and facial expressions.

[0823] Step 5:

[0824] The server generates the optimal sales strategy based on the obtained conversion probability score and emotional state. The input is the conversion score and emotional label, and the output is a customized sales script. A generative AI model is used to generate emotionally sensitive, contextually appropriate prompts.

[0825] Step 6:

[0826] The user terminal presents the generated sales strategies and action proposals to the sales representative. The input consists of customized scripts and proposals received from the server, while the output is visual feedback to the user. Specifically, the strategy is displayed to the representative using the notification function of a smartphone app.

[0827] Step 7:

[0828] Users initiate actions based on suggestions from the application. The input is the presented suggestion, and the output is actual sales activities or actions within the home. Specifically, they might start a conversation with a client or take appropriate action with family members based on a suggested script.

[0829] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0830] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

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

[0832] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0833] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0834] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0835] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0836] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0837] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0838] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0839] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0840] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0841] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0842] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0843] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0844] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0845] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0846] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0847] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0848] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0849] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

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

[0851] (Claim 1)

[0852] A means of automatically collecting data from a vast number of information sources,

[0853] A means for denoising and standardizing the collected data,

[0854] A method for calculating the likelihood of a lead converting using a machine learning algorithm,

[0855] A means of generating the optimal sales strategy based on the calculated probability of closing a deal,

[0856] A means of continuously monitoring lead information and notifying when there are changes,

[0857] A means for sales representatives to check information through a user interface,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, comprising means for customizing sales strategies according to the industry, size, and region of leads.

[0861] (Claim 3)

[0862] The system according to claim 1, further comprising means for sending an alert to a sales representative in real time when a new lead is discovered.

[0863] "Example 1"

[0864] (Claim 1)

[0865] A means of automatically collecting data from a vast number of information sources,

[0866] A means for denoising and standardizing the collected data,

[0867] A method for calculating the likelihood of a lead converting using a machine learning algorithm,

[0868] A means of generating the optimal sales strategy based on the calculated probability of closing a deal,

[0869] A means of monitoring lead information in real time and notifying when important changes are detected,

[0870] A means for sales representatives to visually confirm information through a user interface,

[0871] A means of receiving data feeds in real time based on specific information sources,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, comprising means for customizing sales strategies according to the industry, market trends, and size of leads.

[0875] (Claim 3)

[0876] The system according to claim 1, comprising means for sending notifications to sales representatives in real time when new leads are discovered and when there are market fluctuations.

[0877] "Application Example 1"

[0878] (Claim 1)

[0879] A means that has the function of automatically collecting information from a vast data source,

[0880] A means having the function of removing unnecessary data and standardizing the collected information,

[0881] A means that has the function of evaluating the probability of a transaction using a machine learning algorithm,

[0882] A means that has the function of creating the optimal sales policy based on the evaluated potential,

[0883] A means that has the function of continuously monitoring changes in information and notifying when a change is detected,

[0884] A means that has the function of allowing sales representatives to view information via a user interface,

[0885] A means of disseminating the proposed advertising strategy,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, which has a function to adjust sales policies according to industry, scale, and region.

[0889] (Claim 3)

[0890] The system according to claim 1, further comprising a function to immediately send a warning to a sales representative when a new business partner is discovered.

[0891] "Example 2 of combining an emotion engine"

[0892] (Claim 1)

[0893] A means of automatically collecting data from a vast number of information sources,

[0894] A means for denoising and standardizing the collected data,

[0895] A method for calculating the likelihood of a lead converting using a machine learning algorithm,

[0896] A means of generating the optimal sales strategy based on the calculated probability of closing a deal,

[0897] A method for analyzing the psychological state of sales representatives using emotion analysis technology,

[0898] A means of dynamically adjusting sales strategies according to the psychological state of sales representatives,

[0899] A means of continuously monitoring lead information and notifying when there are changes,

[0900] A means for sales representatives to check information through a user interface,

[0901] A system that includes this.

[0902] (Claim 2)

[0903] The system according to claim 1, comprising means for customizing sales strategies according to the industry, size, and region of leads.

[0904] (Claim 3)

[0905] The system according to claim 1, further comprising means for sending an alert to a sales representative in real time when a new lead is discovered.

[0906] "Application example 2 when combining with an emotional engine"

[0907] (Claim 1)

[0908] A means of automatically collecting data from a vast number of information sources,

[0909] A means for denoising and standardizing the collected data,

[0910] A method for calculating the likelihood of a lead converting using a machine learning algorithm,

[0911] A method for analyzing the emotional state of sales representatives using emotion recognition technology,

[0912] A means of generating the optimal sales strategy based on the calculated probability of closing a deal and the emotional state of the sales representative,

[0913] A means of continuously monitoring lead information and notifying when there are changes,

[0914] A means for sales representatives to check information through a user interface,

[0915] A means of providing suggestions to adjust actions according to the emotional state of sales representatives,

[0916] A means by which a home device performs the optimal action based on the emotional state of the family,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, comprising means for customizing sales strategies according to the industry, size, and region of leads.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for sending an alert to a sales representative in real time when a new lead is discovered. [Explanation of symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically collecting data from a vast number of information sources, A means for denoising and standardizing the collected data, A method for calculating the likelihood of a lead converting using a machine learning algorithm, A means of generating the optimal sales strategy based on the calculated probability of closing a deal, A means of continuously monitoring lead information and notifying when there are changes, A means for sales representatives to check information through a user interface, A system that includes this.

2. The system according to claim 1, comprising means for customizing sales strategies according to the industry, size, and region of leads.

3. The system according to claim 1, further comprising means for sending an alert to a sales representative in real time when a new lead is discovered.

Images