system

Abstract

We provide the system. [Solution] Means for collecting user relationship data, A means for analyzing the aforementioned related data and extracting features, A method for predicting the optimal connection for a user using a generative model, A means for proposing the aforementioned predicted connection to the user, A means of collecting user feedback and updating the generative model, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern business professionals and freelancers find that building new business connections is the key to success. However, it is not easy to build these relationships effectively and efficiently. In many cases, it is done through networking events or online platforms, but it is difficult to find appropriate connections buried in a vast amount of information. As a result, there is a problem of wasting time and labor.

Means for Solving the Problems

[0005] This invention provides a system for effectively expanding a user's business network. Specifically, it includes means for collecting user relationship data, analyzing it, and extracting features. Furthermore, it includes means for predicting the optimal connections for the user using a generative model and making suggestions to the user. This allows for the efficient construction of new business relationships based on the suggested connections. It is possible to update the generative model by utilizing the collected feedback, thereby continuously improving the accuracy of the suggestions.

[0006] "User" refers to an individual or legal entity that intends to use this system to build a business network.

[0007] "Relationship data" refers to information about business contacts held by the user, including, for example, email history, social media contact history, and business card exchange information.

[0008] "Analysis" refers to the act of classifying and interpreting collected relational data based on certain criteria and extracting useful features.

[0009] "Features" refer to patterns and trends extracted from the data obtained through analysis, and serve as a basis for users to identify meaningful business connections.

[0010] A "generative model" is a predictive tool built using machine learning methods, and is used to suggest business connections that are suitable for the user.

[0011] "Connection" is a term that refers to someone with whom a user has the potential to build a business relationship.

[0012] "Proposal" refers to the act of providing users with information about optimal business connections based on analysis results.

[0013] "Feedback" refers to the act of a user recording their experiences and opinions regarding a suggested connection and providing them to the system. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] 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), etc.

[0018] 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.

[0019] 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.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The present invention aims to provide a system that effectively expands a user's business network and proposes new business connections. The following describes specific embodiments for carrying out the present invention.

[0036] First, the user accesses the connection recommendation system through the application. The user grants permission to access their business relationship data. Based on this, the server collects business-related data such as the user's email history, social media contact history, and business card exchange information.

[0037] Next, the server organizes and preprocesses the data. This means removing unnecessary information from the data and preparing it for analysis. The server then uses natural language processing techniques to extract features from the organized data. For example, it might identify specific characteristics and industries of successful business relationships the user has had in the past.

[0038] Once feature extraction is complete, the server uses a generative AI model to predict suitable business connections for the user. This prediction is made by listing new business partners in the same industry and role, based on the analysis results.

[0039] The server then sends connection suggestions to the user's terminal based on the prediction results. The terminal displays this information to the user. The suggestions include the reasons why each connection is considered appropriate, as well as relevant background information.

[0040] For example, if a user works in sales, past successful business approaches might lead to suggestions for connections involving specific roles in the manufacturing industry. Based on this, the user can effectively expand their network.

[0041] Finally, the user contacts the suggested connections and provides feedback on the results and any newly acquired information. Based on this feedback, the server updates the generating AI model, and a mechanism is activated to improve the accuracy of the suggestions. This allows for the efficient provision of increasingly beneficial business connections to the user.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user logs into the application and grants the server permission to access business-related data. This prepares the server to begin collecting data.

[0045] Step 2:

[0046] The server securely collects users' email history, social media contact history, and business card exchange information. It also retrieves relevant information from external business databases as needed.

[0047] Step 3:

[0048] The server preprocesses the collected data, removing unnecessary information and duplicates. Furthermore, it structures the text data using natural language processing techniques, converting it into a parseable format.

[0049] Step 4:

[0050] The server analyzes the data to identify patterns of the user's past business success and extract key features. These features may include industry, job title, and relationship depth.

[0051] Step 5:

[0052] The server uses a generated AI model to predict the best business connections for the user based on extracted features. The model is trained on similar successful cases.

[0053] Step 6:

[0054] The server lists the predicted connections and sends them to the terminal, along with suggestions. This includes the reasons and background information for the predictions.

[0055] Step 7:

[0056] The device notifies the user of suggestions and displays the information visually. The user can then use this information to consider new business connections.

[0057] Step 8:

[0058] Users receive a proposal, attempt to make contact, and provide feedback on the results and their impressions. This helps improve future proposals.

[0059] Step 9:

[0060] The server collects user feedback and updates the generated AI model, improving the accuracy of future suggestions. This cycle continuously enhances the system's effectiveness.

[0061] (Example 1)

[0062] 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."

[0063] In today's business environment, individuals are required to expand their business networks efficiently and effectively. However, manually finding, organizing, and managing valuable business connections is time-consuming and laborious. Therefore, there is a need for a system that automatically suggests suitable business connections for individuals and enables them to effectively capitalize on new opportunities.

[0064] 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.

[0065] In this invention, the server includes means for collecting personal relationship information, means for analyzing the relationship information and extracting characteristics, and means for predicting the optimal connection for the individual using a machine learning model. This makes it possible to efficiently propose business connections optimized for the individual.

[0066] "Personal relationship information" refers to data such as contact information, interaction history, and business card information that individuals use when forming business or social networks.

[0067] "Extracting characteristics" refers to the process of identifying useful patterns and features from collected data and extracting them as concrete information.

[0068] A "machine learning model" refers to an algorithm or statistical model that learns patterns based on provided data and can automatically make predictions and classifications on new data.

[0069] "Predicting connections" refers to analyzing current data and trends to proactively identify and suggest relationships and connections that will be useful in the future.

[0070] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes algorithms involved in the analysis and generation of language data.

[0071] "Supplementing with external sources" refers to the process of creating a more complete dataset by acquiring additional information from external databases and information services, in addition to existing data.

[0072] In implementing this invention, the system consists of a server, a terminal, and a user working together. The server plays a central role in collecting and processing personal relationship information. The terminal plays the role of presenting the information obtained from the server to the user.

[0073] First, the user accesses this system using a terminal. The user grants permission to access information related to business and social networking. The server collects this data. This data includes email history, social media contact history, and business card exchange information. The collected data is organized and pre-processed. Specifically, Python or other scripting languages ​​are used to remove unnecessary information from the data and convert it into a parseable format. For example, text data is tokenized, and only specific information is extracted.

[0074] Next, the server uses natural language processing techniques to extract characteristics from the organized data. This step involves analysis using libraries such as spaCy and NLTK. Based on the extracted characteristics, the server uses a machine learning model to predict the optimal business connection for the user. Here, the model is built using tools such as TENSORFLOW® and PyTorch, and connection predictions are made based on past success patterns.

[0075] The prediction results obtained through these processes are sent from the server to the terminal. The terminal displays this information to the user, prompting them to take specific action. The information included in the suggestions is generated based on prompts such as, "Please suggest new connections in the manufacturing industry that would be beneficial for sales professionals." As a result, users can leverage the suggestions to efficiently explore new business opportunities and expand their networks.

[0076] Finally, the user's response to the suggestions and the newly acquired information are returned to the server as feedback. This feedback is used to improve the performance of the generative AI model and to inform future predictions. This allows the system to continuously learn and continue to provide the best possible suggestions for the user.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] Users access the system using their devices and grant permission to access business-related information. The server, with user permission, collects input such as email history, social media contact history, and business card exchange information. This allows the server to build a dataset to understand the user's current business relationships.

[0080] Step 2:

[0081] The server organizes and preprocesses the collected relational information. Specifically, it filters out duplicate entries and noisy information. The information is also converted into a parseable format. The input is the collected raw data, and the output is a clean, organized dataset. Database management systems and scripting languages ​​are used in this process.

[0082] Step 3:

[0083] The server uses natural language processing techniques to extract characteristics from pre-processed data. For example, it tokenizes important keywords from past emails or messages. The input is a well-organized dataset, and the output is the extracted keywords and features. A text analysis library is used in this step.

[0084] Step 4:

[0085] The server uses a generative AI model based on characteristics to predict the best business connections for the user. The model learns past success patterns and relevant attributes to generate new potential business partners. The input is extracted features, and the output is a list of predicted business connections. A machine learning framework is used for this.

[0086] Step 5:

[0087] The server sends the prediction results to the terminal, which then displays them to the user. The terminal displays the suggestions and their rationale on the screen, prompting the user for specific action. The input is a predicted connection list, and the output is information in a format viewable by the user.

[0088] Step 6:

[0089] Based on the information presented, users make contact with business connections and provide feedback on the results and any new information they gather. The server receives this feedback and updates the generative AI model. This cycle allows the system to continuously learn, making subsequent suggestions more refined. The input is user feedback, and the output is the updated generative AI model.

[0090] (Application Example 1)

[0091] 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."

[0092] In today's business environment, the ability to quickly build new business relationships and maximize new business opportunities is essential. However, finding business opportunities is a time-consuming and laborious process, and the timeliness of face-to-face proposals is particularly important in brick-and-mortar stores. Traditional systems lack effective and efficient ways for users to find new business partners and receive direct proposals.

[0093] 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.

[0094] In this invention, the server includes means for collecting user relationship information, means for analyzing the relationship information and extracting characteristics, means for predicting the most suitable contact for the user using a generative model, means for suggesting the predicted contact to the user, means for collecting user feedback and updating the generative model, and means for displaying connection suggestions in real time through an interactive display. This enables the user to quickly and efficiently find the most suitable business partner and receive suggestions directly in a real-world face-to-face setting.

[0095] "User relationship information" refers to data that users use to build business relationships, including contact history, business card information, and external business-related information.

[0096] "Analysis" is data processing that extracts specific characteristics based on collected information.

[0097] "Extracting characteristics" is the process of identifying key elements in the formation of business relationships with users.

[0098] A "generative model" is an algorithm used to make predictions and suggestions related to business using AI technology.

[0099] "Predicting contacts" refers to the act of using AI to determine and present appropriate business connections for the user.

[0100] "Means of suggestion" refers to a function that communicates potential business relationships to the user.

[0101] "Means for collecting opinions and updating generative models" refers to a function that improves the accuracy of AI models based on feedback information obtained from users.

[0102] An "interactive display" is a display device that shows information in real time and enables interaction with the user.

[0103] The system implementing this invention includes a process of collecting and analyzing user relationship information, and then using a generative model to suggest the most suitable business relationships to the user. The server collects data such as the user's email history, SNS connection information, and business card exchange history.

[0104] The server organizes the data, prepares it for analysis, and then extracts characteristics using natural language processing techniques. This process utilizes Python data analysis libraries such as Pandas and NumPy, as well as spaCy for natural language processing.

[0105] Once the analysis is complete, the server uses a generative AI model to predict suitable contacts for the user. Based on this prediction, suggestions are displayed in real time on the interactive display of smart glasses. This allows users to respond quickly in the physical business environment.

[0106] By providing feedback on suggestions received from the system, users can update the generating AI model and improve the accuracy of the suggestions. This feedback loop allows users to gain increasingly effective business connections.

[0107] For example, a business owner operating a physical store can develop new collaborative relationships with local event organizers. The real-time connection suggestions provided by this system give owners the opportunity to instantly connect with potential business partners.

[0108] Examples of prompts for a generative AI model are as follows:

[0109] "As the owner of a café chain, please propose a new business connection with a local event planning company. Consider past success stories and similar industries to develop a concrete proposal."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects relational information such as the user's email history, social networking information, and business card exchange history. In this process, it retrieves data from external services via APIs and converts it into a specific format. The input is data from external services, and the output is formatted relational information.

[0113] Step 2:

[0114] The server organizes the collected relational information and performs preprocessing to remove noise and unnecessary data. It then organizes the data into a DataFrame using the Python Pandas library. In this process, the input is the formatted information obtained in step 1, and the output is an analyzable dataset.

[0115] Step 3:

[0116] The server uses natural language processing techniques to extract characteristics from an analyzable dataset. Here, it identifies elements useful for business relationships from users' past success stories. spaCy is used to extract specific keywords and phrases. The input is a pre-processed dataset, and the output is user characteristic information.

[0117] Step 4:

[0118] The server uses a generative AI model to predict the most suitable contact for the user. It uses previously obtained characteristic information as prompts, inputting it into the model to obtain a predicted list of candidates. The input is the characteristic information obtained in step 3, and the output is the list of predicted contacts.

[0119] Step 5:

[0120] The device displays a predicted contact list to the user via an interactive display. This display is capable of providing real-time information. The input is the contact list obtained in step 4, and the output is a visual presentation to the user.

[0121] Step 6:

[0122] The user reviews the displayed contact suggestions and submits feedback to the server. This feedback is necessary to improve the model. The input is the user's feedback, and the output is an update to the generative model.

[0123] 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.

[0124] This invention combines a system for expanding a user's business network with an emotion engine for analyzing the user's emotions. This system understands the user's emotional state and provides a more detailed understanding of their reactions to proposed business connections, enabling more appropriate recommendations.

[0125] Users log in to the system's application and grant permission to access data for building their business network. The server collects business-related data such as the user's email history, social media contact history, and business card exchange information, supplementing it with information from external business databases as needed. This makes it possible to gain a more complete understanding of the user's network.

[0126] The server preprocesses the collected data and converts it into an analyzable format. It analyzes the data using natural language processing techniques and extracts features useful to the user. Then, it uses a generative AI model to predict the most suitable business connections for the user.

[0127] In addition to this series of processes, an emotion engine is used to analyze the user's emotions towards the suggested connections. The device analyzes the user's facial expressions, tone of voice, and reactions as they view the suggestions via the emotion engine and sends this information to the server.

[0128] For example, if a user expresses positive feelings towards a newly suggested manufacturing industry executive, the server incorporates this response as positive feedback into the generative model. Based on this information, the system adjusts to suggest more suitable connections in the future.

[0129] Ultimately, the user contacts the proposed business connections and provides feedback on the results. The server integrates the collected sentiment ratings and user feedback to update the generative AI model. This process is expected to continuously improve the efficiency and accuracy of business network building.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The user logs into the application and grants the server permission to access business-related data. The server verifies this permission and prepares to begin data collection.

[0133] Step 2:

[0134] The server collects users' email history, social media interactions, and business card exchange records, and supplements related data by retrieving additional information from external business databases.

[0135] Step 3:

[0136] The server preprocesses the collected data, removing duplicates and standardizing the format. Appropriate filtering is applied to prepare the data for analysis.

[0137] Step 4:

[0138] The server uses natural language processing technology to analyze the data and extract valuable features about the user's business network. This includes industry, relationship duration, and past business results.

[0139] Step 5:

[0140] The server uses a generated AI model to predict the optimal business connection for the user based on extracted features. The prediction is based on a model that has learned from similar successful cases.

[0141] Step 6:

[0142] The server lists the proposed connections and sends them to the terminal along with the reasons and relevant background information.

[0143] Step 7:

[0144] The device notifies the user of suggestions and displays that information on the screen. The user reviews the suggestions along with the visual information.

[0145] Step 8:

[0146] When a user views a suggestion, the emotion engine analyzes the user's facial expressions and voice data to evaluate their feelings towards the suggestion. This information is sent to the server with the user's permission.

[0147] Step 9:

[0148] The device sends the analyzed emotional information to the server. The server receives this information to gain a deeper understanding of the user's reaction and records the evaluation results.

[0149] Step 10:

[0150] The user actually approaches the proposed connection and reports the results and feedback of the established relationship to the server via the terminal.

[0151] Step 11:

[0152] The server integrates user feedback and emotional evaluations to update the generative AI model. This accumulates data for more refined suggestions in the future.

[0153] (Example 2)

[0154] 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".

[0155] When expanding a business network, it is essential to provide users with the most suitable business contact points and to make efficient and accurate proposals. However, existing systems have been unable to reflect feedback that takes into account the emotional state of users, making it difficult to improve the quality of proposals.

[0156] 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.

[0157] In this invention, the server includes means for collecting user relationship data, means for analyzing the relationship data and extracting features, and means for analyzing the user's emotions at the terminal. This makes it possible to predict the optimal business contact point for the user based on the emotional data and reflect this in future proposals.

[0158] "User relationship data" refers to business-related contact information such as email history, social media contact history, and business card exchange information that users possess.

[0159] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to predict the optimal business touchpoints for users.

[0160] "Points of contact" refers to the people or organizations with whom a user should build relationships in order to expand their business network.

[0161] "Methods for analyzing emotions" refers to technologies that identify emotions from a user's facial expressions and tone of voice, and send that data to a server.

[0162] "Feedback" refers to the act of a user reporting their evaluation and results regarding suggested touchpoints to the system.

[0163] This invention is a system for efficiently expanding a user's business network, and it proposes the optimal business contact point by considering the user's emotional state. The server, terminal, and user each work together as follows:

[0164] When a user logs into an application aimed at expanding their business network, the server collects related data such as email history, social media contact history, and business card exchange information with the user's permission. If necessary, data is supplemented from external business databases to understand the overall picture of the user's network. This data is initially pre-processed and analyzed using natural language processing techniques. Tools such as NLTK and spaCy are expected to be used for this process.

[0165] Based on the collected data, a generative AI model is used to predict the optimal business touchpoints to recommend to the user. This model utilizes machine learning techniques to select touchpoints that are highly relevant to the user. The generated suggestions are then presented to the user.

[0166] The device uses an emotion engine when the user confirms the suggested interaction. It analyzes facial expressions and tone of voice using the device's camera and microphone to determine the user's emotional state. This analysis is performed in real time, and the resulting emotional data is sent to a server.

[0167] As a concrete example, suppose a user accepts a proposal from a manufacturing industry executive, and the device analyzes their positive emotions. This information is fed back to the server and used to update the generating AI model, enabling more accurate and personalized proposals in the future.

[0168] An example of a prompt might be, "Describe how to analyze the user's feelings towards the proposed business connection and reflect that in the next suggestion." This would allow for predicting touchpoints that are highly relevant to the user and supporting the construction of business networks.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] When users log in to an application for expanding their business network, they provide permission to access their data. This input data includes email history, social media contact history, business card information, etc. The server collects this data and also accesses external business databases to supplement the information. As output, user relationship data is accumulated.

[0172] Step 2:

[0173] The server preprocesses the collected relational data. This input is given as unorganized data. The server normalizes the data using natural language processing techniques and extracts important features. The output is a dataset in a format suitable for analysis. Text analysis libraries such as NLTK and spaCy are used for this process.

[0174] Step 3:

[0175] The server uses a generative AI model to predict the most suitable business touchpoints for users based on preprocessed data. A feature-extracted dataset is used as input. The model scores the most relevant touchpoints and generates a list of recommended touchpoints as output. This model generation is performed using machine learning techniques.

[0176] Step 4:

[0177] The device uses an emotion engine to analyze the user's emotions when they view suggested touchpoints received from the server. The input is real-time data of the user's facial expressions and tone of voice. The device analyzes data from the camera and microphone and generates emotion data as output. The analysis results are then sent back to the server.

[0178] Step 5:

[0179] The server updates the generative AI model using sentiment data and user feedback. Input consists of user feedback and sentiment analysis data. The server integrates this information, adds it to the model as new training data, and outputs the updated model. This process improves the accuracy of future suggestions.

[0180] (Application Example 2)

[0181] 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".

[0182] There is a challenge in suggesting personalized ads that take into account the user's emotional state. To address this challenge, improving the user experience is essential. In particular, maximizing advertising effectiveness is possible if appropriate ads can be presented based on the user's real-time emotions.

[0183] 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.

[0184] In this invention, the server includes means for collecting information about user relationships, means for analyzing the relationship information and extracting features, and means for predicting the optimal connections for users using a generative model. This makes it possible to analyze the user's emotional state and recommend advertisements based on the analyzed emotional state.

[0185] "Information about user relationships" refers to all data related to the records and interactions of social connections that users have.

[0186] "Means of analysis and feature extraction" refers to processes and algorithms used to identify useful patterns and characteristics from collected data.

[0187] A "generative model" refers to a machine learning model trained to make predictions and suggestions based on user data.

[0188] "Connections" refer to relationships with other individuals or organizations that are expected to be valuable to the user.

[0189] "Means of analyzing emotional states" refers to technologies and methods that estimate emotions based on a user's words, actions, facial expressions, voice, etc.

[0190] "Means of recommending advertisements" refers to a system that selects and displays appropriate advertisements to users based on analyzed information.

[0191] This invention aims to realize an advertising suggestion system that takes into account the user's emotional state. A detailed embodiment of this system is described below.

[0192] This system primarily consists of a server, user terminals, and an emotion analysis engine. The user terminals utilize devices such as smart glasses or smartphones, enabling real-time analysis of the user's emotional state.

[0193] The server first collects information about the user's relationships, including their communication history, online activity, and other social data. Next, it analyzes this information to extract features and uses a generative AI model to predict the most suitable business connections for the user. In addition, it uses an emotion analysis engine to analyze the user's emotions.

[0194] The user's device acquires facial expressions and voice data through sensors, which are then processed by an emotion analysis engine. Specifically, analysis software such as Affectiva and Google® Cloud Vision API are used. This information is sent to a server, where a generative AI model optimizes advertisements based on this emotion data.

[0195] Data processing begins with preprocessing real-time data obtained from sensors on the device. Voice and motion data are analyzed to identify the user's emotional state. By analyzing the emotional data, it is determined what the user is interested in and what kind of advertisements should be shown.

[0196] For example, if smart glasses detect a user's feeling of "fun" while they are walking around town, advertisements for popular leisure facilities or cafes in that area will be displayed. This improves the accuracy of ad targeting for the user.

[0197] Prompts play a crucial role in generative AI models. For example, you can input prompts like the following:

[0198] "The user's emotion is 'interesting,' and they are interested in fashion. Please select three related products that you can suggest."

[0199] This prompt allows the system to provide information optimized for each individual user.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The user terminal acquires the user's voice and facial expressions in real time using sensors. The input is sensor data, which is passed to the emotion analysis engine. This data is preprocessed to extract voice patterns and facial features. The extracted features are used to identify emotional states.

[0203] Step 2:

[0204] The emotion analysis engine estimates the user's emotional state based on pre-processed data. The input is extracted feature data, and the output is the estimated result of the user's emotional state. Specifically, emotion recognition software such as Affectiva is used to identify emotion categories (e.g., joy, sadness, interest).

[0205] Step 3:

[0206] The server receives information about the user's emotional state and relationships, and analyzes it using a generative AI model. The input is the user's emotional state and collected relationship information, and the output is a list of appropriate advertisements based on the emotional state. In terms of data calculation, it fuses past relationship data with current emotional data to predict the optimal advertisement.

[0207] Step 4:

[0208] The generative AI model selects the most suitable advertisement for the user based on the prompt text. The input is the prompt text and the analysis result, and the output is the advertisement that best matches the user's current sentiment and interests. In operation, the generative model uses a machine learning-trained algorithm to recommend advertisements tailored to the user.

[0209] Step 5:

[0210] The server sends the selected advertisements to the user's device. The input is the output of the generating AI model, i.e., the list of advertisements, and the output is the display of advertisements on the user's device. In operation, the selected advertisement information is transferred to smart glasses or a smartphone via an interface, and the user is notified.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] 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.

[0217] 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).

[0218] 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.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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".

[0227] The present invention aims to provide a system that effectively expands a user's business network and proposes new business connections. The following describes specific embodiments for carrying out the present invention.

[0228] First, the user accesses the connection recommendation system through the application. The user grants permission to access their business relationship data. Based on this, the server collects business-related data such as the user's email history, social media contact history, and business card exchange information.

[0229] Next, the server organizes and preprocesses the data. This means removing unnecessary information from the data and preparing it for analysis. The server then uses natural language processing techniques to extract features from the organized data. For example, it might identify specific characteristics and industries of successful business relationships the user has had in the past.

[0230] Once feature extraction is complete, the server uses a generative AI model to predict suitable business connections for the user. This prediction is made by listing new business partners in the same industry and role, based on the analysis results.

[0231] The server then sends connection suggestions to the user's terminal based on the prediction results. The terminal displays this information to the user. The suggestions include the reasons why each connection is considered appropriate, as well as relevant background information.

[0232] For example, if a user works in sales, past successful business approaches might lead to suggestions for connections involving specific roles in the manufacturing industry. Based on this, the user can effectively expand their network.

[0233] Finally, the user contacts the suggested connections and provides feedback on the results and any newly acquired information. Based on this feedback, the server updates the generating AI model, and a mechanism is activated to improve the accuracy of the suggestions. This allows for the efficient provision of increasingly beneficial business connections to the user.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The user logs into the application and grants the server permission to access business-related data. This prepares the server to begin collecting data.

[0237] Step 2:

[0238] The server securely collects users' email history, social media contact history, and business card exchange information. It also retrieves relevant information from external business databases as needed.

[0239] Step 3:

[0240] The server preprocesses the collected data, removing unnecessary information and duplicates. Furthermore, it structures the text data using natural language processing techniques, converting it into a parseable format.

[0241] Step 4:

[0242] The server analyzes the data to identify patterns of the user's past business success and extract key features. These features may include industry, job title, and relationship depth.

[0243] Step 5:

[0244] The server uses a generated AI model to predict the best business connections for the user based on extracted features. The model is trained on similar successful cases.

[0245] Step 6:

[0246] The server lists the predicted connections and sends them to the terminal, along with suggestions. This includes the reasons and background information for the predictions.

[0247] Step 7:

[0248] The device notifies the user of suggestions and displays the information visually. The user can then use this information to consider new business connections.

[0249] Step 8:

[0250] Users receive a proposal, attempt to make contact, and provide feedback on the results and their impressions. This helps improve future proposals.

[0251] Step 9:

[0252] The server collects user feedback and updates the generated AI model, improving the accuracy of future suggestions. This cycle continuously enhances the system's effectiveness.

[0253] (Example 1)

[0254] 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."

[0255] In today's business environment, individuals are required to expand their business networks efficiently and effectively. However, manually finding, organizing, and managing valuable business connections is time-consuming and laborious. Therefore, there is a need for a system that automatically suggests suitable business connections for individuals and enables them to effectively capitalize on new opportunities.

[0256] 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.

[0257] In this invention, the server includes means for collecting personal relationship information, means for analyzing the relationship information and extracting characteristics, and means for predicting the optimal connection for the individual using a machine learning model. This makes it possible to efficiently propose business connections optimized for the individual.

[0258] "Personal relationship information" refers to data such as contact information, interaction history, and business card information that individuals use when forming business or social networks.

[0259] "Extracting characteristics" refers to the process of identifying useful patterns and features from collected data and extracting them as concrete information.

[0260] A "machine learning model" refers to an algorithm or statistical model that learns patterns based on provided data and can automatically make predictions and classifications on new data.

[0261] "Predicting connections" refers to analyzing current data and trends to proactively identify and suggest relationships and connections that will be useful in the future.

[0262] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes algorithms involved in the analysis and generation of language data.

[0263] "Supplementing with external sources" refers to the process of creating a more complete dataset by acquiring additional information from external databases and information services, in addition to existing data.

[0264] In implementing this invention, the system consists of a server, a terminal, and a user working together. The server plays a central role in collecting and processing personal relationship information. The terminal plays the role of presenting the information obtained from the server to the user.

[0265] First, the user accesses this system using a terminal. The user grants permission to access information related to business and social networking. The server collects this data. This data includes email history, social media contact history, and business card exchange information. The collected data is organized and pre-processed. Specifically, Python or other scripting languages ​​are used to remove unnecessary information from the data and convert it into a parseable format. For example, text data is tokenized, and only specific information is extracted.

[0266] Next, the server uses natural language processing techniques to extract characteristics from the organized data. This step involves analysis using libraries such as spaCy and NLTK. Based on the extracted characteristics, the server uses a machine learning model to predict the optimal business connection for the user. Here, the model is built using tools such as TensorFlow and PyTorch, and connection predictions are made based on past success patterns.

[0267] The prediction results obtained through these processes are sent from the server to the terminal. The terminal displays this information to the user, prompting them to take specific action. The information included in the suggestions is generated based on prompts such as, "Please suggest new connections in the manufacturing industry that would be beneficial for sales professionals." As a result, users can leverage the suggestions to efficiently explore new business opportunities and expand their networks.

[0268] Finally, the user's response to the suggestions and the newly acquired information are returned to the server as feedback. This feedback is used to improve the performance of the generative AI model and to inform future predictions. This allows the system to continuously learn and continue to provide the best possible suggestions for the user.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] Users access the system using their devices and grant permission to access business-related information. The server, with user permission, collects input such as email history, social media contact history, and business card exchange information. This allows the server to build a dataset to understand the user's current business relationships.

[0272] Step 2:

[0273] The server organizes and preprocesses the collected relational information. Specifically, it filters out duplicate entries and noisy information. The information is also converted into a parseable format. The input is the collected raw data, and the output is a clean, organized dataset. Database management systems and scripting languages ​​are used in this process.

[0274] Step 3:

[0275] The server uses natural language processing techniques to extract characteristics from pre-processed data. For example, it tokenizes important keywords from past emails or messages. The input is a well-organized dataset, and the output is the extracted keywords and features. A text analysis library is used in this step.

[0276] Step 4:

[0277] The server uses a generative AI model based on characteristics to predict the best business connections for the user. The model learns past success patterns and relevant attributes to generate new potential business partners. The input is extracted features, and the output is a list of predicted business connections. A machine learning framework is used for this.

[0278] Step 5:

[0279] The server sends the prediction results to the terminal, which then displays them to the user. The terminal displays the suggestions and their rationale on the screen, prompting the user for specific action. The input is a predicted connection list, and the output is information in a format viewable by the user.

[0280] Step 6:

[0281] The user makes contact with business connections based on the presented information and provides the results and new information as feedback. The server receives this feedback and updates the generative AI model. Through this cycle, the system continuously learns and the next proposal becomes more refined. The input is the user's feedback, and the output is the updated generative AI model.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0284] In the modern business environment, there is a need for the ability to quickly build new business relationships and maximize new business opportunities. However, searching for business opportunities is a time-consuming and laborious process, and particularly in physical stores, the timeliness of face-to-face proposals is important. Conventional systems have the problem of lacking a method for users to effectively and efficiently find new business partners and directly show proposals to users.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes means for collecting the user's relationship information, means for analyzing the relationship information to extract characteristics, means for predicting the optimal contact for the user using a generative model, means for proposing the predicted contact to the user, means for collecting opinions from the user and updating the generative model, and means for displaying connection proposals in real time through an interactive display. Thereby, the user can quickly and efficiently find the optimal business partner and directly receive proposals in a real face-to-face situation.

[0287] "User relationship information" refers to data that users use to build business relationships, including contact history, business card information, and external business-related information.

[0288] "Analysis" is data processing that extracts specific characteristics based on collected information.

[0289] "Extracting characteristics" is the process of identifying key elements in the formation of business relationships with users.

[0290] A "generative model" is an algorithm used to make predictions and suggestions related to business using AI technology.

[0291] "Predicting contacts" refers to the act of using AI to determine and present appropriate business connections for the user.

[0292] "Means of suggestion" refers to a function that communicates potential business relationships to the user.

[0293] "Means for collecting opinions and updating generative models" refers to a function that improves the accuracy of AI models based on feedback information obtained from users.

[0294] An "interactive display" is a display device that shows information in real time and enables interaction with the user.

[0295] The system implementing this invention includes a process of collecting and analyzing user relationship information, and then using a generative model to suggest the most suitable business relationships to the user. The server collects data such as the user's email history, SNS connection information, and business card exchange history.

[0296] The server organizes the data, prepares it for analysis, and then extracts characteristics using natural language processing techniques. This process utilizes Python data analysis libraries such as Pandas and NumPy, as well as spaCy for natural language processing.

[0297] Once the analysis is complete, the server uses a generative AI model to predict suitable contacts for the user. Based on this prediction, suggestions are displayed in real time on the interactive display of smart glasses. This allows users to respond quickly in the physical business environment.

[0298] By providing feedback on suggestions received from the system, users can update the generating AI model and improve the accuracy of the suggestions. This feedback loop allows users to gain increasingly effective business connections.

[0299] For example, a business owner operating a physical store can develop new collaborative relationships with local event organizers. The real-time connection suggestions provided by this system give owners the opportunity to instantly connect with potential business partners.

[0300] Examples of prompts for a generative AI model are as follows:

[0301] "As the owner of a café chain, please propose a new business connection with a local event planning company. Consider past success stories and similar industries to develop a concrete proposal."

[0302] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0303] Step 1:

[0304] The server collects relational information such as the user's email history, social networking information, and business card exchange history. In this process, it retrieves data from external services via APIs and converts it into a specific format. The input is data from external services, and the output is formatted relational information.

[0305] Step 2:

[0306] The server sorts out the collected relationship information and performs preprocessing to remove noise and delete unnecessary data. It is sorted into a data frame format using the Pandas library in Python. In this process, the input is the formatted information obtained in step 1, and the output is an analyzable dataset.

[0307] Step 3:

[0308] The server uses natural language processing technology to extract characteristics from the analyzable dataset. Here, useful elements for business relationships are identified from the user's past success cases. Specific keywords and phrases are extracted using spaCy. The input is the preprocessed dataset, and the output is the user's characteristic information.

[0309] Step 4:

[0310] The server uses a generative AI model to predict the optimal contact information for the user. The previously obtained characteristic information is used as a prompt and input into the model to obtain a list of predicted candidates. The input is the characteristic information obtained in step 3, and the output is a list of predicted contact information.

[0311] Step 5:

[0312] The terminal displays the list of predicted contact information to the user through an interactive display. This display can provide real-time information. The input is the list of contact information obtained in step 4, and the output is a visual presentation to the user.

[0313] Step 6:

[0314] The user checks the proposed contact information and submits feedback to the server. This feedback is necessary for improving the model. The input is the content of the feedback from the user, and the output is an update to the generative model.

[0315] 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.

[0316] This invention combines a system for expanding a user's business network with an emotion engine for analyzing the user's emotions. This system understands the user's emotional state and provides a more detailed understanding of their reactions to proposed business connections, enabling more appropriate recommendations.

[0317] Users log in to the system's application and grant permission to access data for building their business network. The server collects business-related data such as the user's email history, social media contact history, and business card exchange information, supplementing it with information from external business databases as needed. This makes it possible to gain a more complete understanding of the user's network.

[0318] The server preprocesses the collected data and converts it into an analyzable format. It analyzes the data using natural language processing techniques and extracts features useful to the user. Then, it uses a generative AI model to predict the most suitable business connections for the user.

[0319] In addition to this series of processes, an emotion engine is used to analyze the user's emotions towards the suggested connections. The device analyzes the user's facial expressions, tone of voice, and reactions as they view the suggestions via the emotion engine and sends this information to the server.

[0320] For example, if a user expresses positive feelings towards a newly suggested manufacturing industry executive, the server incorporates this response as positive feedback into the generative model. Based on this information, the system adjusts to suggest more suitable connections in the future.

[0321] Ultimately, the user contacts the proposed business connections and provides feedback on the results. The server integrates the collected sentiment ratings and user feedback to update the generative AI model. This process is expected to continuously improve the efficiency and accuracy of business network building.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The user logs into the application and grants the server permission to access business-related data. The server verifies this permission and prepares to begin data collection.

[0325] Step 2:

[0326] The server collects users' email history, social media interactions, and business card exchange records, and supplements related data by retrieving additional information from external business databases.

[0327] Step 3:

[0328] The server preprocesses the collected data, removing duplicates and standardizing the format. Appropriate filtering is applied to prepare the data for analysis.

[0329] Step 4:

[0330] The server uses natural language processing technology to analyze the data and extract valuable features about the user's business network. This includes industry, relationship duration, and past business results.

[0331] Step 5:

[0332] The server uses a generated AI model to predict the optimal business connection for the user based on extracted features. The prediction is based on a model that has learned from similar successful cases.

[0333] Step 6:

[0334] The server lists the proposed connections and sends them to the terminal along with the reasons and relevant background information.

[0335] Step 7:

[0336] The device notifies the user of suggestions and displays that information on the screen. The user reviews the suggestions along with the visual information.

[0337] Step 8:

[0338] When a user views a suggestion, the emotion engine analyzes the user's facial expressions and voice data to evaluate their feelings towards the suggestion. This information is sent to the server with the user's permission.

[0339] Step 9:

[0340] The device sends the analyzed emotional information to the server. The server receives this information to gain a deeper understanding of the user's reaction and records the evaluation results.

[0341] Step 10:

[0342] The user actually approaches the proposed connection and reports the results and feedback of the established relationship to the server via the terminal.

[0343] Step 11:

[0344] The server integrates user feedback and emotional evaluations to update the generative AI model. This accumulates data for more refined suggestions in the future.

[0345] (Example 2)

[0346] 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".

[0347] When expanding a business network, it is essential to provide users with the most suitable business contact points and to make efficient and accurate proposals. However, existing systems have been unable to reflect feedback that takes into account the emotional state of users, making it difficult to improve the quality of proposals.

[0348] 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.

[0349] In this invention, the server includes means for collecting user relationship data, means for analyzing the relationship data and extracting features, and means for analyzing the user's emotions at the terminal. This makes it possible to predict the optimal business contact point for the user based on the emotional data and reflect this in future proposals.

[0350] "User relationship data" refers to business-related contact information such as email history, social media contact history, and business card exchange information that users possess.

[0351] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to predict the optimal business touchpoints for users.

[0352] "Points of contact" refers to the people or organizations with whom a user should build relationships in order to expand their business network.

[0353] "Methods for analyzing emotions" refers to technologies that identify emotions from a user's facial expressions and tone of voice, and send that data to a server.

[0354] "Feedback" refers to the act of a user reporting their evaluation and results regarding suggested touchpoints to the system.

[0355] This invention is a system for efficiently expanding a user's business network, and it proposes the optimal business contact point by considering the user's emotional state. The server, terminal, and user each work together as follows:

[0356] When a user logs into an application aimed at expanding their business network, the server collects related data such as email history, social media contact history, and business card exchange information with the user's permission. If necessary, data is supplemented from external business databases to understand the overall picture of the user's network. This data is initially pre-processed and analyzed using natural language processing techniques. Tools such as NLTK and spaCy are expected to be used for this process.

[0357] Based on the collected data, a generative AI model is used to predict the optimal business touchpoints to recommend to the user. This model utilizes machine learning techniques to select touchpoints that are highly relevant to the user. The generated suggestions are then presented to the user.

[0358] The device uses an emotion engine when the user confirms the suggested interaction. It analyzes facial expressions and tone of voice using the device's camera and microphone to determine the user's emotional state. This analysis is performed in real time, and the resulting emotional data is sent to a server.

[0359] As a concrete example, suppose a user accepts a proposal from a manufacturing industry executive, and the device analyzes their positive emotions. This information is fed back to the server and used to update the generating AI model, enabling more accurate and personalized proposals in the future.

[0360] An example of a prompt might be, "Describe how to analyze the user's feelings towards the proposed business connection and reflect that in the next suggestion." This would allow for predicting touchpoints that are highly relevant to the user and supporting the construction of business networks.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] When users log in to an application for expanding their business network, they provide permission to access their data. This input data includes email history, social media contact history, business card information, etc. The server collects this data and also accesses external business databases to supplement the information. As output, user relationship data is accumulated.

[0364] Step 2:

[0365] The server preprocesses the collected relational data. This input is given as unorganized data. The server normalizes the data using natural language processing techniques and extracts important features. The output is a dataset in a format suitable for analysis. Text analysis libraries such as NLTK and spaCy are used for this process.

[0366] Step 3:

[0367] The server uses a generative AI model to predict the most suitable business touchpoints for users based on preprocessed data. A feature-extracted dataset is used as input. The model scores the most relevant touchpoints and generates a list of recommended touchpoints as output. This model generation is performed using machine learning techniques.

[0368] Step 4:

[0369] The device uses an emotion engine to analyze the user's emotions when they view suggested touchpoints received from the server. The input is real-time data of the user's facial expressions and tone of voice. The device analyzes data from the camera and microphone and generates emotion data as output. The analysis results are then sent back to the server.

[0370] Step 5:

[0371] The server updates the generative AI model using sentiment data and user feedback. Input consists of user feedback and sentiment analysis data. The server integrates this information, adds it to the model as new training data, and outputs the updated model. This process improves the accuracy of future suggestions.

[0372] (Application Example 2)

[0373] 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."

[0374] There is a challenge in suggesting personalized ads that take into account the user's emotional state. To address this challenge, improving the user experience is essential. In particular, maximizing advertising effectiveness is possible if appropriate ads can be presented based on the user's real-time emotions.

[0375] 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.

[0376] In this invention, the server includes means for collecting information about user relationships, means for analyzing the relationship information and extracting features, and means for predicting the optimal connections for users using a generative model. This makes it possible to analyze the user's emotional state and recommend advertisements based on the analyzed emotional state.

[0377] "Information about user relationships" refers to all data related to the records and interactions of social connections that users have.

[0378] "Means of analysis and feature extraction" refers to processes and algorithms used to identify useful patterns and characteristics from collected data.

[0379] A "generative model" refers to a machine learning model trained to make predictions and suggestions based on user data.

[0380] "Connections" refer to relationships with other individuals or organizations that are expected to be valuable to the user.

[0381] "Means of analyzing emotional states" refers to technologies and methods that estimate emotions based on a user's words, actions, facial expressions, voice, etc.

[0382] "Means of recommending advertisements" refers to a system that selects and displays appropriate advertisements to users based on analyzed information.

[0383] This invention aims to realize an advertising suggestion system that takes into account the user's emotional state. A detailed embodiment of this system is described below.

[0384] This system primarily consists of a server, user terminals, and an emotion analysis engine. The user terminals utilize devices such as smart glasses or smartphones, enabling real-time analysis of the user's emotional state.

[0385] The server first collects information about the user's relationships, including their communication history, online activity, and other social data. Next, it analyzes this information to extract features and uses a generative AI model to predict the most suitable business connections for the user. In addition, it uses an emotion analysis engine to analyze the user's emotions.

[0386] The user's device acquires facial expressions and voice data through sensors, which are then processed by an emotion analysis engine. Specifically, analysis software such as Affectiva and Google Cloud Vision API are used. This information is sent to a server, where a generative AI model optimizes advertisements based on this emotion data.

[0387] Data processing begins with preprocessing real-time data obtained from sensors on the device. Voice and motion data are analyzed to identify the user's emotional state. By analyzing the emotional data, it is determined what the user is interested in and what kind of advertisements should be shown.

[0388] For example, if smart glasses detect a user's feeling of "fun" while they are walking around town, advertisements for popular leisure facilities or cafes in that area will be displayed. This improves the accuracy of ad targeting for the user.

[0389] Prompts play a crucial role in generative AI models. For example, you can input prompts like the following:

[0390] "The user's emotion is 'interesting,' and they are interested in fashion. Please select three related products that you can suggest."

[0391] This prompt allows the system to provide information optimized for each individual user.

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1:

[0394] The user terminal acquires the user's voice and facial expressions in real time using sensors. The input is sensor data, which is passed to the emotion analysis engine. This data is preprocessed to extract voice patterns and facial features. The extracted features are used to identify emotional states.

[0395] Step 2:

[0396] The emotion analysis engine estimates the user's emotional state based on pre-processed data. The input is extracted feature data, and the output is the estimated result of the user's emotional state. Specifically, emotion recognition software such as Affectiva is used to identify emotion categories (e.g., joy, sadness, interest).

[0397] Step 3:

[0398] The server receives information about the user's emotional state and relationships, and analyzes it using a generative AI model. The input is the user's emotional state and collected relationship information, and the output is a list of appropriate advertisements based on the emotional state. In terms of data calculation, it fuses past relationship data with current emotional data to predict the optimal advertisement.

[0399] Step 4:

[0400] The generative AI model selects the most suitable advertisement for the user based on the prompt text. The input is the prompt text and the analysis result, and the output is the advertisement that best matches the user's current sentiment and interests. In operation, the generative model uses a machine learning-trained algorithm to recommend advertisements tailored to the user.

[0401] Step 5:

[0402] The server sends the selected advertisements to the user's device. The input is the output of the generating AI model, i.e., the list of advertisements, and the output is the display of advertisements on the user's device. In operation, the selected advertisement information is transferred to smart glasses or a smartphone via an interface, and the user is notified.

[0403] 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.

[0404] 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.

[0405] 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.

[0406] [Third Embodiment]

[0407] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0408] 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.

[0409] 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).

[0410] 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.

[0411] 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.

[0412] 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).

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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".

[0419] The present invention aims to provide a system that effectively expands a user's business network and proposes new business connections. The following describes specific embodiments for carrying out the present invention.

[0420] First, the user accesses the connection recommendation system through the application. The user grants permission to access their business relationship data. Based on this, the server collects business-related data such as the user's email history, social media contact history, and business card exchange information.

[0421] Next, the server organizes and preprocesses the data. This means removing unnecessary information from the data and preparing it for analysis. The server then uses natural language processing techniques to extract features from the organized data. For example, it might identify specific characteristics and industries of successful business relationships the user has had in the past.

[0422] Once feature extraction is complete, the server uses a generative AI model to predict suitable business connections for the user. This prediction is made by listing new business partners in the same industry and role, based on the analysis results.

[0423] The server then sends connection suggestions to the user's terminal based on the prediction results. The terminal displays this information to the user. The suggestions include the reasons why each connection is considered appropriate, as well as relevant background information.

[0424] For example, if a user works in sales, past successful business approaches might lead to suggestions for connections involving specific roles in the manufacturing industry. Based on this, the user can effectively expand their network.

[0425] Finally, the user contacts the suggested connections and provides feedback on the results and any newly acquired information. Based on this feedback, the server updates the generating AI model, and a mechanism is activated to improve the accuracy of the suggestions. This allows for the efficient provision of increasingly beneficial business connections to the user.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The user logs into the application and grants the server permission to access business-related data. This prepares the server to begin collecting data.

[0429] Step 2:

[0430] The server securely collects users' email history, social media contact history, and business card exchange information. It also retrieves relevant information from external business databases as needed.

[0431] Step 3:

[0432] The server preprocesses the collected data, removing unnecessary information and duplicates. Furthermore, it structures the text data using natural language processing techniques, converting it into a parseable format.

[0433] Step 4:

[0434] The server analyzes the data to identify patterns of the user's past business success and extract key features. These features may include industry, job title, and relationship depth.

[0435] Step 5:

[0436] The server uses a generated AI model to predict the best business connections for the user based on extracted features. The model is trained on similar successful cases.

[0437] Step 6:

[0438] The server lists the predicted connections and sends them to the terminal, along with suggestions. This includes the reasons and background information for the predictions.

[0439] Step 7:

[0440] The device notifies the user of suggestions and displays the information visually. The user can then use this information to consider new business connections.

[0441] Step 8:

[0442] Users receive a proposal, attempt to make contact, and provide feedback on the results and their impressions. This helps improve future proposals.

[0443] Step 9:

[0444] The server collects user feedback and updates the generated AI model, improving the accuracy of future suggestions. This cycle continuously enhances the system's effectiveness.

[0445] (Example 1)

[0446] 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."

[0447] In today's business environment, individuals are required to expand their business networks efficiently and effectively. However, manually finding, organizing, and managing valuable business connections is time-consuming and laborious. Therefore, there is a need for a system that automatically suggests suitable business connections for individuals and enables them to effectively capitalize on new opportunities.

[0448] 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.

[0449] In this invention, the server includes means for collecting personal relationship information, means for analyzing the relationship information and extracting characteristics, and means for predicting the optimal connection for the individual using a machine learning model. This makes it possible to efficiently propose business connections optimized for the individual.

[0450] "Personal relationship information" refers to data such as contact information, interaction history, and business card information that individuals use when forming business or social networks.

[0451] "Extracting characteristics" refers to the process of identifying useful patterns and features from collected data and extracting them as concrete information.

[0452] A "machine learning model" refers to an algorithm or statistical model that learns patterns based on provided data and can automatically make predictions and classifications on new data.

[0453] "Predicting connections" refers to analyzing current data and trends to proactively identify and suggest relationships and connections that will be useful in the future.

[0454] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes algorithms involved in the analysis and generation of language data.

[0455] "Supplementing with external sources" refers to the process of creating a more complete dataset by acquiring additional information from external databases and information services, in addition to existing data.

[0456] In implementing this invention, the system consists of a server, a terminal, and a user working together. The server plays a central role in collecting and processing personal relationship information. The terminal plays the role of presenting the information obtained from the server to the user.

[0457] First, the user accesses this system using a terminal. The user grants permission to access information related to business and social networking. The server collects this data. This data includes email history, social media contact history, and business card exchange information. The collected data is organized and pre-processed. Specifically, Python or other scripting languages ​​are used to remove unnecessary information from the data and convert it into a parseable format. For example, text data is tokenized, and only specific information is extracted.

[0458] Next, the server uses natural language processing techniques to extract characteristics from the organized data. This step involves analysis using libraries such as spaCy and NLTK. Based on the extracted characteristics, the server uses a machine learning model to predict the optimal business connection for the user. Here, the model is built using tools such as TensorFlow and PyTorch, and connection predictions are made based on past success patterns.

[0459] The prediction results obtained through these processes are sent from the server to the terminal. The terminal displays this information to the user, prompting them to take specific action. The information included in the suggestions is generated based on prompts such as, "Please suggest new connections in the manufacturing industry that would be beneficial for sales professionals." As a result, users can leverage the suggestions to efficiently explore new business opportunities and expand their networks.

[0460] Finally, the user's response to the suggestions and the newly acquired information are returned to the server as feedback. This feedback is used to improve the performance of the generative AI model and to inform future predictions. This allows the system to continuously learn and continue to provide the best possible suggestions for the user.

[0461] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0462] Step 1:

[0463] Users access the system using their devices and grant permission to access business-related information. The server, with user permission, collects input such as email history, social media contact history, and business card exchange information. This allows the server to build a dataset to understand the user's current business relationships.

[0464] Step 2:

[0465] The server organizes and preprocesses the collected relational information. Specifically, it filters out duplicate entries and noisy information. The information is also converted into a parseable format. The input is the collected raw data, and the output is a clean, organized dataset. Database management systems and scripting languages ​​are used in this process.

[0466] Step 3:

[0467] The server uses natural language processing techniques to extract characteristics from pre-processed data. For example, it tokenizes important keywords from past emails or messages. The input is a well-organized dataset, and the output is the extracted keywords and features. A text analysis library is used in this step.

[0468] Step 4:

[0469] The server uses a generative AI model based on characteristics to predict the best business connections for the user. The model learns past success patterns and relevant attributes to generate new potential business partners. The input is extracted features, and the output is a list of predicted business connections. A machine learning framework is used for this.

[0470] Step 5:

[0471] The server sends the prediction results to the terminal, which then displays them to the user. The terminal displays the suggestions and their rationale on the screen, prompting the user for specific action. The input is a predicted connection list, and the output is information in a format viewable by the user.

[0472] Step 6:

[0473] Based on the information presented, users make contact with business connections and provide feedback on the results and any new information they gather. The server receives this feedback and updates the generative AI model. This cycle allows the system to continuously learn, making subsequent suggestions more refined. The input is user feedback, and the output is the updated generative AI model.

[0474] (Application Example 1)

[0475] 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."

[0476] In today's business environment, the ability to quickly build new business relationships and maximize new business opportunities is essential. However, finding business opportunities is a time-consuming and laborious process, and the timeliness of face-to-face proposals is particularly important in brick-and-mortar stores. Traditional systems lack effective and efficient ways for users to find new business partners and receive direct proposals.

[0477] 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.

[0478] In this invention, the server includes means for collecting user relationship information, means for analyzing the relationship information and extracting characteristics, means for predicting the most suitable contact for the user using a generative model, means for suggesting the predicted contact to the user, means for collecting user feedback and updating the generative model, and means for displaying connection suggestions in real time through an interactive display. This enables the user to quickly and efficiently find the most suitable business partner and receive suggestions directly in a real-world face-to-face setting.

[0479] "User relationship information" refers to data that users use to build business relationships, including contact history, business card information, and external business-related information.

[0480] "Analysis" is data processing that extracts specific characteristics based on collected information.

[0481] "Extracting characteristics" is the process of identifying key elements in the formation of business relationships with users.

[0482] A "generative model" is an algorithm used to make predictions and suggestions related to business using AI technology.

[0483] "Predicting contacts" refers to the act of using AI to determine and present appropriate business connections for the user.

[0484] "Means of suggestion" refers to a function that communicates potential business relationships to the user.

[0485] "Means for collecting opinions and updating generative models" refers to a function that improves the accuracy of AI models based on feedback information obtained from users.

[0486] An "interactive display" is a display device that shows information in real time and enables interaction with the user.

[0487] The system implementing this invention includes a process of collecting and analyzing user relationship information, and then using a generative model to suggest the most suitable business relationships to the user. The server collects data such as the user's email history, SNS connection information, and business card exchange history.

[0488] The server organizes the data, prepares it for analysis, and then extracts characteristics using natural language processing techniques. This process utilizes Python data analysis libraries such as Pandas and NumPy, as well as spaCy for natural language processing.

[0489] Once the analysis is complete, the server uses a generative AI model to predict suitable contacts for the user. Based on this prediction, suggestions are displayed in real time on the interactive display of smart glasses. This allows users to respond quickly in the physical business environment.

[0490] By providing feedback on suggestions received from the system, users can update the generating AI model and improve the accuracy of the suggestions. This feedback loop allows users to gain increasingly effective business connections.

[0491] For example, a business owner operating a physical store can develop new collaborative relationships with local event organizers. The real-time connection suggestions provided by this system give owners the opportunity to instantly connect with potential business partners.

[0492] Examples of prompts for a generative AI model are as follows:

[0493] "As the owner of a café chain, please propose a new business connection with a local event planning company. Consider past success stories and similar industries to develop a concrete proposal."

[0494] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0495] Step 1:

[0496] The server collects relational information such as the user's email history, social networking information, and business card exchange history. In this process, it retrieves data from external services via APIs and converts it into a specific format. The input is data from external services, and the output is formatted relational information.

[0497] Step 2:

[0498] The server organizes the collected relational information and performs preprocessing to remove noise and unnecessary data. It then organizes the data into a DataFrame using the Python Pandas library. In this process, the input is the formatted information obtained in step 1, and the output is an analyzable dataset.

[0499] Step 3:

[0500] The server uses natural language processing techniques to extract characteristics from an analyzable dataset. Here, it identifies elements useful for business relationships from users' past success stories. spaCy is used to extract specific keywords and phrases. The input is a pre-processed dataset, and the output is user characteristic information.

[0501] Step 4:

[0502] The server uses a generative AI model to predict the most suitable contact for the user. It uses previously obtained characteristic information as prompts, inputting it into the model to obtain a predicted list of candidates. The input is the characteristic information obtained in step 3, and the output is the list of predicted contacts.

[0503] Step 5:

[0504] The device displays a predicted contact list to the user via an interactive display. This display is capable of providing real-time information. The input is the contact list obtained in step 4, and the output is a visual presentation to the user.

[0505] Step 6:

[0506] The user reviews the displayed contact suggestions and submits feedback to the server. This feedback is necessary to improve the model. The input is the user's feedback, and the output is an update to the generative model.

[0507] 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.

[0508] This invention combines a system for expanding a user's business network with an emotion engine for analyzing the user's emotions. This system understands the user's emotional state and provides a more detailed understanding of their reactions to proposed business connections, enabling more appropriate recommendations.

[0509] Users log in to the system's application and grant permission to access data for building their business network. The server collects business-related data such as the user's email history, social media contact history, and business card exchange information, supplementing it with information from external business databases as needed. This makes it possible to gain a more complete understanding of the user's network.

[0510] The server preprocesses the collected data and converts it into an analyzable format. It analyzes the data using natural language processing techniques and extracts features useful to the user. Then, it uses a generative AI model to predict the most suitable business connections for the user.

[0511] In addition to this series of processes, an emotion engine is used to analyze the user's emotions towards the suggested connections. The device analyzes the user's facial expressions, tone of voice, and reactions as they view the suggestions via the emotion engine and sends this information to the server.

[0512] For example, if a user expresses positive feelings towards a newly suggested manufacturing industry executive, the server incorporates this response as positive feedback into the generative model. Based on this information, the system adjusts to suggest more suitable connections in the future.

[0513] Ultimately, the user contacts the proposed business connections and provides feedback on the results. The server integrates the collected sentiment ratings and user feedback to update the generative AI model. This process is expected to continuously improve the efficiency and accuracy of business network building.

[0514] The following describes the processing flow.

[0515] Step 1:

[0516] The user logs into the application and grants the server permission to access business-related data. The server verifies this permission and prepares to begin data collection.

[0517] Step 2:

[0518] The server collects users' email history, social media interactions, and business card exchange records, and supplements related data by retrieving additional information from external business databases.

[0519] Step 3:

[0520] The server preprocesses the collected data, removing duplicates and standardizing the format. Appropriate filtering is applied to prepare the data for analysis.

[0521] Step 4:

[0522] The server uses natural language processing technology to analyze the data and extract valuable features about the user's business network. This includes industry, relationship duration, and past business results.

[0523] Step 5:

[0524] The server uses a generated AI model to predict the optimal business connection for the user based on extracted features. The prediction is based on a model that has learned from similar successful cases.

[0525] Step 6:

[0526] The server lists the proposed connections and sends them to the terminal along with the reasons and relevant background information.

[0527] Step 7:

[0528] The device notifies the user of suggestions and displays that information on the screen. The user reviews the suggestions along with the visual information.

[0529] Step 8:

[0530] When a user views a suggestion, the emotion engine analyzes the user's facial expressions and voice data to evaluate their feelings towards the suggestion. This information is sent to the server with the user's permission.

[0531] Step 9:

[0532] The device sends the analyzed emotional information to the server. The server receives this information to gain a deeper understanding of the user's reaction and records the evaluation results.

[0533] Step 10:

[0534] The user actually approaches the proposed connection and reports the results and feedback of the established relationship to the server via the terminal.

[0535] Step 11:

[0536] The server integrates user feedback and emotional evaluations to update the generative AI model. This accumulates data for more refined suggestions in the future.

[0537] (Example 2)

[0538] 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."

[0539] When expanding a business network, it is essential to provide users with the most suitable business contact points and to make efficient and accurate proposals. However, existing systems have been unable to reflect feedback that takes into account the emotional state of users, making it difficult to improve the quality of proposals.

[0540] 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.

[0541] In this invention, the server includes means for collecting user relationship data, means for analyzing the relationship data and extracting features, and means for analyzing the user's emotions at the terminal. This makes it possible to predict the optimal business contact point for the user based on the emotional data and reflect this in future proposals.

[0542] "User relationship data" refers to business-related contact information such as email history, social media contact history, and business card exchange information that users possess.

[0543] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to predict the optimal business touchpoints for users.

[0544] "Points of contact" refers to the people or organizations with whom a user should build relationships in order to expand their business network.

[0545] "Methods for analyzing emotions" refers to technologies that identify emotions from a user's facial expressions and tone of voice, and send that data to a server.

[0546] "Feedback" refers to the act of a user reporting their evaluation and results regarding suggested touchpoints to the system.

[0547] This invention is a system for efficiently expanding a user's business network, and it proposes the optimal business contact point by considering the user's emotional state. The server, terminal, and user each work together as follows:

[0548] When a user logs into an application aimed at expanding their business network, the server collects related data such as email history, social media contact history, and business card exchange information with the user's permission. If necessary, data is supplemented from external business databases to understand the overall picture of the user's network. This data is initially pre-processed and analyzed using natural language processing techniques. Tools such as NLTK and spaCy are expected to be used for this process.

[0549] Based on the collected data, a generative AI model is used to predict the optimal business touchpoints to recommend to the user. This model utilizes machine learning techniques to select touchpoints that are highly relevant to the user. The generated suggestions are then presented to the user.

[0550] The device uses an emotion engine when the user confirms the suggested interaction. It analyzes facial expressions and tone of voice using the device's camera and microphone to determine the user's emotional state. This analysis is performed in real time, and the resulting emotional data is sent to a server.

[0551] As a concrete example, suppose a user accepts a proposal from a manufacturing industry executive, and the device analyzes their positive emotions. This information is fed back to the server and used to update the generating AI model, enabling more accurate and personalized proposals in the future.

[0552] An example of a prompt might be, "Describe how to analyze the user's feelings towards the proposed business connection and reflect that in the next suggestion." This would allow for predicting touchpoints that are highly relevant to the user and supporting the construction of business networks.

[0553] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0554] Step 1:

[0555] When users log in to an application for expanding their business network, they provide permission to access their data. This input data includes email history, social media contact history, business card information, etc. The server collects this data and also accesses external business databases to supplement the information. As output, user relationship data is accumulated.

[0556] Step 2:

[0557] The server preprocesses the collected relational data. This input is given as unorganized data. The server normalizes the data using natural language processing techniques and extracts important features. The output is a dataset in a format suitable for analysis. Text analysis libraries such as NLTK and spaCy are used for this process.

[0558] Step 3:

[0559] The server uses a generative AI model to predict the most suitable business touchpoints for users based on preprocessed data. A feature-extracted dataset is used as input. The model scores the most relevant touchpoints and generates a list of recommended touchpoints as output. This model generation is performed using machine learning techniques.

[0560] Step 4:

[0561] The device uses an emotion engine to analyze the user's emotions when they view suggested touchpoints received from the server. The input is real-time data of the user's facial expressions and tone of voice. The device analyzes data from the camera and microphone and generates emotion data as output. The analysis results are then sent back to the server.

[0562] Step 5:

[0563] The server updates the generative AI model using sentiment data and user feedback. Input consists of user feedback and sentiment analysis data. The server integrates this information, adds it to the model as new training data, and outputs the updated model. This process improves the accuracy of future suggestions.

[0564] (Application Example 2)

[0565] 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."

[0566] There is a challenge in suggesting personalized ads that take into account the user's emotional state. To address this challenge, improving the user experience is essential. In particular, maximizing advertising effectiveness is possible if appropriate ads can be presented based on the user's real-time emotions.

[0567] 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.

[0568] In this invention, the server includes means for collecting information about user relationships, means for analyzing the relationship information and extracting features, and means for predicting the optimal connections for users using a generative model. This makes it possible to analyze the user's emotional state and recommend advertisements based on the analyzed emotional state.

[0569] "Information about user relationships" refers to all data related to the records and interactions of social connections that users have.

[0570] "Means of analysis and feature extraction" refers to processes and algorithms used to identify useful patterns and characteristics from collected data.

[0571] A "generative model" refers to a machine learning model trained to make predictions and suggestions based on user data.

[0572] "Connections" refer to relationships with other individuals or organizations that are expected to be valuable to the user.

[0573] "Means of analyzing emotional states" refers to technologies and methods that estimate emotions based on a user's words, actions, facial expressions, voice, etc.

[0574] "Means of recommending advertisements" refers to a system that selects and displays appropriate advertisements to users based on analyzed information.

[0575] This invention aims to realize an advertising suggestion system that takes into account the user's emotional state. A detailed embodiment of this system is described below.

[0576] This system primarily consists of a server, user terminals, and an emotion analysis engine. The user terminals utilize devices such as smart glasses or smartphones, enabling real-time analysis of the user's emotional state.

[0577] The server first collects information about the user's relationships, including their communication history, online activity, and other social data. Next, it analyzes this information to extract features and uses a generative AI model to predict the most suitable business connections for the user. In addition, it uses an emotion analysis engine to analyze the user's emotions.

[0578] The user's device acquires facial expressions and voice data through sensors, which are then processed by an emotion analysis engine. Specifically, analysis software such as Affectiva and Google Cloud Vision API are used. This information is sent to a server, where a generative AI model optimizes advertisements based on this emotion data.

[0579] Data processing begins with preprocessing real-time data obtained from sensors on the device. Voice and motion data are analyzed to identify the user's emotional state. By analyzing the emotional data, it is determined what the user is interested in and what kind of advertisements should be shown.

[0580] For example, if smart glasses detect a user's feeling of "fun" while they are walking around town, advertisements for popular leisure facilities or cafes in that area will be displayed. This improves the accuracy of ad targeting for the user.

[0581] Prompts play a crucial role in generative AI models. For example, you can input prompts like the following:

[0582] "The user's emotion is 'interesting,' and they are interested in fashion. Please select three related products that you can suggest."

[0583] This prompt allows the system to provide information optimized for each individual user.

[0584] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0585] Step 1:

[0586] The user terminal acquires the user's voice and facial expressions in real time using sensors. The input is sensor data, which is passed to the emotion analysis engine. This data is preprocessed to extract voice patterns and facial features. The extracted features are used to identify emotional states.

[0587] Step 2:

[0588] The emotion analysis engine estimates the user's emotional state based on pre-processed data. The input is extracted feature data, and the output is the estimated result of the user's emotional state. Specifically, emotion recognition software such as Affectiva is used to identify emotion categories (e.g., joy, sadness, interest).

[0589] Step 3:

[0590] The server receives information about the user's emotional state and relationships, and analyzes it using a generative AI model. The input is the user's emotional state and collected relationship information, and the output is a list of appropriate advertisements based on the emotional state. In terms of data calculation, it fuses past relationship data with current emotional data to predict the optimal advertisement.

[0591] Step 4:

[0592] The generative AI model selects the most suitable advertisement for the user based on the prompt text. The input is the prompt text and the analysis result, and the output is the advertisement that best matches the user's current sentiment and interests. In operation, the generative model uses a machine learning-trained algorithm to recommend advertisements tailored to the user.

[0593] Step 5:

[0594] The server sends the selected advertisements to the user's device. The input is the output of the generating AI model, i.e., the list of advertisements, and the output is the display of advertisements on the user's device. In operation, the selected advertisement information is transferred to smart glasses or a smartphone via an interface, and the user is notified.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] [Fourth Embodiment]

[0599] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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).

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] 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".

[0612] The present invention aims to provide a system that effectively expands a user's business network and proposes new business connections. The following describes specific embodiments for carrying out the present invention.

[0613] First, the user accesses the connection recommendation system through the application. The user grants permission to access their business relationship data. Based on this, the server collects business-related data such as the user's email history, social media contact history, and business card exchange information.

[0614] Next, the server organizes and preprocesses the data. This means removing unnecessary information from the data and preparing it for analysis. The server then uses natural language processing techniques to extract features from the organized data. For example, it might identify specific characteristics and industries of successful business relationships the user has had in the past.

[0615] Once feature extraction is complete, the server uses a generative AI model to predict suitable business connections for the user. This prediction is made by listing new business partners in the same industry and role, based on the analysis results.

[0616] The server then sends connection suggestions to the user's terminal based on the prediction results. The terminal displays this information to the user. The suggestions include the reasons why each connection is considered appropriate, as well as relevant background information.

[0617] For example, if a user works in sales, past successful business approaches might lead to suggestions for connections involving specific roles in the manufacturing industry. Based on this, the user can effectively expand their network.

[0618] Finally, the user contacts the suggested connections and provides feedback on the results and any newly acquired information. Based on this feedback, the server updates the generating AI model, and a mechanism is activated to improve the accuracy of the suggestions. This allows for the efficient provision of increasingly beneficial business connections to the user.

[0619] The following describes the processing flow.

[0620] Step 1:

[0621] The user logs into the application and grants the server permission to access business-related data. This prepares the server to begin collecting data.

[0622] Step 2:

[0623] The server securely collects users' email history, social media contact history, and business card exchange information. It also retrieves relevant information from external business databases as needed.

[0624] Step 3:

[0625] The server preprocesses the collected data, removing unnecessary information and duplicates. Furthermore, it structures the text data using natural language processing techniques, converting it into a parseable format.

[0626] Step 4:

[0627] The server analyzes the data to identify patterns of the user's past business success and extract key features. These features may include industry, job title, and relationship depth.

[0628] Step 5:

[0629] The server uses a generated AI model to predict the best business connections for the user based on extracted features. The model is trained on similar successful cases.

[0630] Step 6:

[0631] The server lists the predicted connections and sends them to the terminal, along with suggestions. This includes the reasons and background information for the predictions.

[0632] Step 7:

[0633] The device notifies the user of suggestions and displays the information visually. The user can then use this information to consider new business connections.

[0634] Step 8:

[0635] Users receive a proposal, attempt to make contact, and provide feedback on the results and their impressions. This helps improve future proposals.

[0636] Step 9:

[0637] The server collects user feedback and updates the generated AI model, improving the accuracy of future suggestions. This cycle continuously enhances the system's effectiveness.

[0638] (Example 1)

[0639] 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".

[0640] In today's business environment, individuals are required to expand their business networks efficiently and effectively. However, manually finding, organizing, and managing valuable business connections is time-consuming and laborious. Therefore, there is a need for a system that automatically suggests suitable business connections for individuals and enables them to effectively capitalize on new opportunities.

[0641] 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.

[0642] In this invention, the server includes means for collecting personal relationship information, means for analyzing the relationship information and extracting characteristics, and means for predicting the optimal connection for the individual using a machine learning model. This makes it possible to efficiently propose business connections optimized for the individual.

[0643] "Personal relationship information" refers to data such as contact information, interaction history, and business card information that individuals use when forming business or social networks.

[0644] "Extracting characteristics" refers to the process of identifying useful patterns and features from collected data and extracting them as concrete information.

[0645] A "machine learning model" refers to an algorithm or statistical model that learns patterns based on provided data and can automatically make predictions and classifications on new data.

[0646] "Predicting connections" refers to analyzing current data and trends to proactively identify and suggest relationships and connections that will be useful in the future.

[0647] "Natural language processing technology" refers to technologies that enable computers to understand and process human language, and includes algorithms involved in the analysis and generation of language data.

[0648] "Supplementing with external sources" refers to the process of creating a more complete dataset by acquiring additional information from external databases and information services, in addition to existing data.

[0649] In implementing this invention, the system consists of a server, a terminal, and a user working together. The server plays a central role in collecting and processing personal relationship information. The terminal plays the role of presenting the information obtained from the server to the user.

[0650] First, the user accesses this system using a terminal. The user grants permission to access information related to business and social networking. The server collects this data. This data includes email history, social media contact history, and business card exchange information. The collected data is organized and pre-processed. Specifically, Python or other scripting languages ​​are used to remove unnecessary information from the data and convert it into a parseable format. For example, text data is tokenized, and only specific information is extracted.

[0651] Next, the server uses natural language processing techniques to extract characteristics from the organized data. This step involves analysis using libraries such as spaCy and NLTK. Based on the extracted characteristics, the server uses a machine learning model to predict the optimal business connection for the user. Here, the model is built using tools such as TensorFlow and PyTorch, and connection predictions are made based on past success patterns.

[0652] The prediction results obtained through these processes are sent from the server to the terminal. The terminal displays this information to the user, prompting them to take specific action. The information included in the suggestions is generated based on prompts such as, "Please suggest new connections in the manufacturing industry that would be beneficial for sales professionals." As a result, users can leverage the suggestions to efficiently explore new business opportunities and expand their networks.

[0653] Finally, the user's response to the suggestions and the newly acquired information are returned to the server as feedback. This feedback is used to improve the performance of the generative AI model and to inform future predictions. This allows the system to continuously learn and continue to provide the best possible suggestions for the user.

[0654] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0655] Step 1:

[0656] Users access the system using their devices and grant permission to access business-related information. The server, with user permission, collects input such as email history, social media contact history, and business card exchange information. This allows the server to build a dataset to understand the user's current business relationships.

[0657] Step 2:

[0658] The server organizes and preprocesses the collected relational information. Specifically, it filters out duplicate entries and noisy information. The information is also converted into a parseable format. The input is the collected raw data, and the output is a clean, organized dataset. Database management systems and scripting languages ​​are used in this process.

[0659] Step 3:

[0660] The server uses natural language processing techniques to extract characteristics from pre-processed data. For example, it tokenizes important keywords from past emails or messages. The input is a well-organized dataset, and the output is the extracted keywords and features. A text analysis library is used in this step.

[0661] Step 4:

[0662] The server uses a generative AI model based on characteristics to predict the best business connections for the user. The model learns past success patterns and relevant attributes to generate new potential business partners. The input is extracted features, and the output is a list of predicted business connections. A machine learning framework is used for this.

[0663] Step 5:

[0664] The server sends the prediction results to the terminal, which then displays them to the user. The terminal displays the suggestions and their rationale on the screen, prompting the user for specific action. The input is a predicted connection list, and the output is information in a format viewable by the user.

[0665] Step 6:

[0666] Based on the information presented, users make contact with business connections and provide feedback on the results and any new information they gather. The server receives this feedback and updates the generative AI model. This cycle allows the system to continuously learn, making subsequent suggestions more refined. The input is user feedback, and the output is the updated generative AI model.

[0667] (Application Example 1)

[0668] 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".

[0669] In today's business environment, the ability to quickly build new business relationships and maximize new business opportunities is essential. However, finding business opportunities is a time-consuming and laborious process, and the timeliness of face-to-face proposals is particularly important in brick-and-mortar stores. Traditional systems lack effective and efficient ways for users to find new business partners and receive direct proposals.

[0670] 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.

[0671] In this invention, the server includes means for collecting user relationship information, means for analyzing the relationship information and extracting characteristics, means for predicting the most suitable contact for the user using a generative model, means for suggesting the predicted contact to the user, means for collecting user feedback and updating the generative model, and means for displaying connection suggestions in real time through an interactive display. This enables the user to quickly and efficiently find the most suitable business partner and receive suggestions directly in a real-world face-to-face setting.

[0672] "User relationship information" refers to data that users use to build business relationships, including contact history, business card information, and external business-related information.

[0673] "Analysis" is data processing that extracts specific characteristics based on collected information.

[0674] "Extracting characteristics" is the process of identifying key elements in the formation of business relationships with users.

[0675] A "generative model" is an algorithm used to make predictions and suggestions related to business using AI technology.

[0676] "Predicting contacts" refers to the act of using AI to determine and present appropriate business connections for the user.

[0677] "Means of suggestion" refers to a function that communicates potential business relationships to the user.

[0678] "Means for collecting opinions and updating generative models" refers to a function that improves the accuracy of AI models based on feedback information obtained from users.

[0679] An "interactive display" is a display device that shows information in real time and enables interaction with the user.

[0680] The system implementing this invention includes a process of collecting and analyzing user relationship information, and then using a generative model to suggest the most suitable business relationships to the user. The server collects data such as the user's email history, SNS connection information, and business card exchange history.

[0681] The server organizes the data, prepares it for analysis, and then extracts characteristics using natural language processing techniques. This process utilizes Python data analysis libraries such as Pandas and NumPy, as well as spaCy for natural language processing.

[0682] Once the analysis is complete, the server uses a generative AI model to predict suitable contacts for the user. Based on this prediction, suggestions are displayed in real time on the interactive display of smart glasses. This allows users to respond quickly in the physical business environment.

[0683] By providing feedback on suggestions received from the system, users can update the generating AI model and improve the accuracy of the suggestions. This feedback loop allows users to gain increasingly effective business connections.

[0684] For example, a business owner operating a physical store can develop new collaborative relationships with local event organizers. The real-time connection suggestions provided by this system give owners the opportunity to instantly connect with potential business partners.

[0685] Examples of prompts for a generative AI model are as follows:

[0686] "As the owner of a café chain, please propose a new business connection with a local event planning company. Consider past success stories and similar industries to develop a concrete proposal."

[0687] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0688] Step 1:

[0689] The server collects relational information such as the user's email history, social networking information, and business card exchange history. In this process, it retrieves data from external services via APIs and converts it into a specific format. The input is data from external services, and the output is formatted relational information.

[0690] Step 2:

[0691] The server organizes the collected relational information and performs preprocessing to remove noise and unnecessary data. It then organizes the data into a DataFrame using the Python Pandas library. In this process, the input is the formatted information obtained in step 1, and the output is an analyzable dataset.

[0692] Step 3:

[0693] The server uses natural language processing techniques to extract characteristics from an analyzable dataset. Here, it identifies elements useful for business relationships from users' past success stories. spaCy is used to extract specific keywords and phrases. The input is a pre-processed dataset, and the output is user characteristic information.

[0694] Step 4:

[0695] The server uses a generative AI model to predict the most suitable contact for the user. It uses previously obtained characteristic information as prompts, inputting it into the model to obtain a predicted list of candidates. The input is the characteristic information obtained in step 3, and the output is the list of predicted contacts.

[0696] Step 5:

[0697] The device displays a predicted contact list to the user via an interactive display. This display is capable of providing real-time information. The input is the contact list obtained in step 4, and the output is a visual presentation to the user.

[0698] Step 6:

[0699] The user reviews the displayed contact suggestions and submits feedback to the server. This feedback is necessary to improve the model. The input is the user's feedback, and the output is an update to the generative model.

[0700] 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.

[0701] This invention combines a system for expanding a user's business network with an emotion engine for analyzing the user's emotions. This system understands the user's emotional state and provides a more detailed understanding of their reactions to proposed business connections, enabling more appropriate recommendations.

[0702] Users log in to the system's application and grant permission to access data for building their business network. The server collects business-related data such as the user's email history, social media contact history, and business card exchange information, supplementing it with information from external business databases as needed. This makes it possible to gain a more complete understanding of the user's network.

[0703] The server preprocesses the collected data and converts it into an analyzable format. It analyzes the data using natural language processing techniques and extracts features useful to the user. Then, it uses a generative AI model to predict the most suitable business connections for the user.

[0704] In addition to this series of processes, an emotion engine is used to analyze the user's emotions towards the suggested connections. The device analyzes the user's facial expressions, tone of voice, and reactions as they view the suggestions via the emotion engine and sends this information to the server.

[0705] For example, if a user expresses positive feelings towards a newly suggested manufacturing industry executive, the server incorporates this response as positive feedback into the generative model. Based on this information, the system adjusts to suggest more suitable connections in the future.

[0706] Ultimately, the user contacts the proposed business connections and provides feedback on the results. The server integrates the collected sentiment ratings and user feedback to update the generative AI model. This process is expected to continuously improve the efficiency and accuracy of business network building.

[0707] The following describes the processing flow.

[0708] Step 1:

[0709] The user logs into the application and grants the server permission to access business-related data. The server verifies this permission and prepares to begin data collection.

[0710] Step 2:

[0711] The server collects users' email history, social media interactions, and business card exchange records, and supplements related data by retrieving additional information from external business databases.

[0712] Step 3:

[0713] The server preprocesses the collected data, removing duplicates and standardizing the format. Appropriate filtering is applied to prepare the data for analysis.

[0714] Step 4:

[0715] The server uses natural language processing technology to analyze the data and extract valuable features about the user's business network. This includes industry, relationship duration, and past business results.

[0716] Step 5:

[0717] The server uses a generated AI model to predict the optimal business connection for the user based on extracted features. The prediction is based on a model that has learned from similar successful cases.

[0718] Step 6:

[0719] The server lists the proposed connections and sends them to the terminal along with the reasons and relevant background information.

[0720] Step 7:

[0721] The device notifies the user of suggestions and displays that information on the screen. The user reviews the suggestions along with the visual information.

[0722] Step 8:

[0723] When a user views a suggestion, the emotion engine analyzes the user's facial expressions and voice data to evaluate their feelings towards the suggestion. This information is sent to the server with the user's permission.

[0724] Step 9:

[0725] The device sends the analyzed emotional information to the server. The server receives this information to gain a deeper understanding of the user's reaction and records the evaluation results.

[0726] Step 10:

[0727] The user actually approaches the proposed connection and reports the results and feedback of the established relationship to the server via the terminal.

[0728] Step 11:

[0729] The server integrates user feedback and emotional evaluations to update the generative AI model. This accumulates data for more refined suggestions in the future.

[0730] (Example 2)

[0731] 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".

[0732] When expanding a business network, it is essential to provide users with the most suitable business contact points and to make efficient and accurate proposals. However, existing systems have been unable to reflect feedback that takes into account the emotional state of users, making it difficult to improve the quality of proposals.

[0733] 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.

[0734] In this invention, the server includes means for collecting user relationship data, means for analyzing the relationship data and extracting features, and means for analyzing the user's emotions at the terminal. This makes it possible to predict the optimal business contact point for the user based on the emotional data and reflect this in future proposals.

[0735] "User relationship data" refers to business-related contact information such as email history, social media contact history, and business card exchange information that users possess.

[0736] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to predict the optimal business touchpoints for users.

[0737] "Points of contact" refers to the people or organizations with whom a user should build relationships in order to expand their business network.

[0738] "Methods for analyzing emotions" refers to technologies that identify emotions from a user's facial expressions and tone of voice, and send that data to a server.

[0739] "Feedback" refers to the act of a user reporting their evaluation and results regarding suggested touchpoints to the system.

[0740] This invention is a system for efficiently expanding a user's business network, and it proposes the optimal business contact point by considering the user's emotional state. The server, terminal, and user each work together as follows:

[0741] When a user logs into an application aimed at expanding their business network, the server collects related data such as email history, social media contact history, and business card exchange information with the user's permission. If necessary, data is supplemented from external business databases to understand the overall picture of the user's network. This data is initially pre-processed and analyzed using natural language processing techniques. Tools such as NLTK and spaCy are expected to be used for this process.

[0742] Based on the collected data, a generative AI model is used to predict the optimal business touchpoints to recommend to the user. This model utilizes machine learning techniques to select touchpoints that are highly relevant to the user. The generated suggestions are then presented to the user.

[0743] The device uses an emotion engine when the user confirms the suggested interaction. It analyzes facial expressions and tone of voice using the device's camera and microphone to determine the user's emotional state. This analysis is performed in real time, and the resulting emotional data is sent to a server.

[0744] As a concrete example, suppose a user accepts a proposal from a manufacturing industry executive, and the device analyzes their positive emotions. This information is fed back to the server and used to update the generating AI model, enabling more accurate and personalized proposals in the future.

[0745] An example of a prompt might be, "Describe how to analyze the user's feelings towards the proposed business connection and reflect that in the next suggestion." This would allow for predicting touchpoints that are highly relevant to the user and supporting the construction of business networks.

[0746] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0747] Step 1:

[0748] When users log in to an application for expanding their business network, they provide permission to access their data. This input data includes email history, social media contact history, business card information, etc. The server collects this data and also accesses external business databases to supplement the information. As output, user relationship data is accumulated.

[0749] Step 2:

[0750] The server preprocesses the collected relational data. This input is given as unorganized data. The server normalizes the data using natural language processing techniques and extracts important features. The output is a dataset in a format suitable for analysis. Text analysis libraries such as NLTK and spaCy are used for this process.

[0751] Step 3:

[0752] The server uses a generative AI model to predict the most suitable business touchpoints for users based on preprocessed data. A feature-extracted dataset is used as input. The model scores the most relevant touchpoints and generates a list of recommended touchpoints as output. This model generation is performed using machine learning techniques.

[0753] Step 4:

[0754] The device uses an emotion engine to analyze the user's emotions when they view suggested touchpoints received from the server. The input is real-time data of the user's facial expressions and tone of voice. The device analyzes data from the camera and microphone and generates emotion data as output. The analysis results are then sent back to the server.

[0755] Step 5:

[0756] The server updates the generative AI model using sentiment data and user feedback. Input consists of user feedback and sentiment analysis data. The server integrates this information, adds it to the model as new training data, and outputs the updated model. This process improves the accuracy of future suggestions.

[0757] (Application Example 2)

[0758] 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".

[0759] There is a challenge in suggesting personalized ads that take into account the user's emotional state. To address this challenge, improving the user experience is essential. In particular, maximizing advertising effectiveness is possible if appropriate ads can be presented based on the user's real-time emotions.

[0760] 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.

[0761] In this invention, the server includes means for collecting information about user relationships, means for analyzing the relationship information and extracting features, and means for predicting the optimal connections for users using a generative model. This makes it possible to analyze the user's emotional state and recommend advertisements based on the analyzed emotional state.

[0762] "Information about user relationships" refers to all data related to the records and interactions of social connections that users have.

[0763] "Means of analysis and feature extraction" refers to processes and algorithms used to identify useful patterns and characteristics from collected data.

[0764] A "generative model" refers to a machine learning model trained to make predictions and suggestions based on user data.

[0765] "Connections" refer to relationships with other individuals or organizations that are expected to be valuable to the user.

[0766] "Means of analyzing emotional states" refers to technologies and methods that estimate emotions based on a user's words, actions, facial expressions, voice, etc.

[0767] "Means of recommending advertisements" refers to a system that selects and displays appropriate advertisements to users based on analyzed information.

[0768] This invention aims to realize an advertising suggestion system that takes into account the user's emotional state. A detailed embodiment of this system is described below.

[0769] This system primarily consists of a server, user terminals, and an emotion analysis engine. The user terminals utilize devices such as smart glasses or smartphones, enabling real-time analysis of the user's emotional state.

[0770] The server first collects information about the user's relationships, including their communication history, online activity, and other social data. Next, it analyzes this information to extract features and uses a generative AI model to predict the most suitable business connections for the user. In addition, it uses an emotion analysis engine to analyze the user's emotions.

[0771] The user's device acquires facial expressions and voice data through sensors, which are then processed by an emotion analysis engine. Specifically, analysis software such as Affectiva and Google Cloud Vision API are used. This information is sent to a server, where a generative AI model optimizes advertisements based on this emotion data.

[0772] Data processing begins with preprocessing real-time data obtained from sensors on the device. Voice and motion data are analyzed to identify the user's emotional state. By analyzing the emotional data, it is determined what the user is interested in and what kind of advertisements should be shown.

[0773] For example, if smart glasses detect a user's feeling of "fun" while they are walking around town, advertisements for popular leisure facilities or cafes in that area will be displayed. This improves the accuracy of ad targeting for the user.

[0774] Prompts play a crucial role in generative AI models. For example, you can input prompts like the following:

[0775] "The user's emotion is 'interesting,' and they are interested in fashion. Please select three related products that you can suggest."

[0776] This prompt allows the system to provide information optimized for each individual user.

[0777] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0778] Step 1:

[0779] The user terminal acquires the user's voice and facial expressions in real time using sensors. The input is sensor data, which is passed to the emotion analysis engine. This data is preprocessed to extract voice patterns and facial features. The extracted features are used to identify emotional states.

[0780] Step 2:

[0781] The emotion analysis engine estimates the user's emotional state based on pre-processed data. The input is extracted feature data, and the output is the estimated result of the user's emotional state. Specifically, emotion recognition software such as Affectiva is used to identify emotion categories (e.g., joy, sadness, interest).

[0782] Step 3:

[0783] The server receives information about the user's emotional state and relationships, and analyzes it using a generative AI model. The input is the user's emotional state and collected relationship information, and the output is a list of appropriate advertisements based on the emotional state. In terms of data calculation, it fuses past relationship data with current emotional data to predict the optimal advertisement.

[0784] Step 4:

[0785] The generative AI model selects the most suitable advertisement for the user based on the prompt text. The input is the prompt text and the analysis result, and the output is the advertisement that best matches the user's current sentiment and interests. In operation, the generative model uses a machine learning-trained algorithm to recommend advertisements tailored to the user.

[0786] Step 5:

[0787] The server sends the selected advertisements to the user's device. The input is the output of the generating AI model, i.e., the list of advertisements, and the output is the display of advertisements on the user's device. In operation, the selected advertisement information is transferred to smart glasses or a smartphone via an interface, and the user is notified.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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."

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] The following is further disclosed regarding the embodiments described above.

[0810] (Claim 1)

[0811] Means for collecting user relationship data,

[0812] A means for analyzing the aforementioned related data and extracting features,

[0813] A method for predicting the optimal connection for a user using a generative model,

[0814] A means for proposing the aforementioned predicted connection to the user,

[0815] A means of collecting user feedback and updating the generative model,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, further comprising means for supplementing user relationship data with external information.

[0819] (Claim 3)

[0820] The system according to claim 1, further comprising means for providing prediction reasons and background information when making a proposal to the user.

[0821] "Example 1"

[0822] (Claim 1)

[0823] Means of collecting personal relationship information,

[0824] Means for analyzing the aforementioned relationship information and extracting characteristics,

[0825] A method for predicting the optimal connection for an individual using machine learning models,

[0826] Means for proposing the aforementioned predicted connection to an individual,

[0827] A means of collecting responses from individuals to update machine learning models,

[0828] Methods for applying natural language processing techniques to organized information,

[0829] A system that includes this.

[0830] (Claim 2)

[0831] The system according to claim 1, further comprising means for supplementing personal relationship information from external sources.

[0832] (Claim 3)

[0833] The system according to claim 1, further comprising means for providing predictive basis and additional information when making a proposal to the aforementioned individual.

[0834] "Application Example 1"

[0835] (Claim 1)

[0836] A means of collecting user relationship information,

[0837] Means for analyzing the aforementioned relationship information and extracting characteristics,

[0838] A method for predicting the most suitable contact for a user using a generative model,

[0839] A means for suggesting the predicted contacts to the user,

[0840] A means of collecting user feedback and updating the generative model,

[0841] A means of displaying connection suggestions in real time through an interactive display,

[0842] Information processing device including

[0843] (Claim 2)

[0844] The information processing apparatus according to claim 1, further comprising means for supplementing user relationship information with external information.

[0845] (Claim 3)

[0846] The information processing apparatus according to claim 1, further comprising means for providing prediction reasons and background information when making a proposal to the user.

[0847] "Example 2 of combining an emotion engine"

[0848] (Claim 1)

[0849] Means for collecting user relationship data,

[0850] A means for analyzing the aforementioned related data and extracting features,

[0851] A method for predicting the optimal touchpoint for a user using a generative AI model,

[0852] A means for proposing the aforementioned predicted contact point to the user,

[0853] A means of analyzing user emotions on a device,

[0854] A means for collecting emotional data and feedback from users to update the generative AI model,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, further comprising means for supplementing user relationship data with external information.

[0858] (Claim 3)

[0859] The system according to claim 1, further comprising means for providing prediction reasons and background information when making a proposal to the user.

[0860] "Application example 2 when combining with an emotional engine"

[0861] (Claim 1)

[0862] Means for collecting information about user relationships,

[0863] A means for analyzing information regarding the aforementioned relationship and extracting features,

[0864] A method for predicting the optimal connections for users using generative models,

[0865] A means for proposing the aforementioned predicted connections to the user,

[0866] A means of collecting user feedback and updating the generative model,

[0867] A means of analyzing the emotional state of users,

[0868] A means of recommending advertisements based on analyzed emotional states,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, further comprising means for supplementing information about user relationships with external information.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for providing prediction reasons and accompanying information when making a proposal to the user. [Explanation of Symbols]

[0874] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting user relationship data, A means for analyzing the aforementioned related data and extracting features, A method for predicting the optimal connection for a user using a generative model, A means for proposing the aforementioned predicted connection to the user, A means of collecting user feedback and updating the generative model, A system that includes this.

2. The system according to claim 1, further comprising means for supplementing user relationship data with external information.

3. The system according to claim 1, further comprising means for providing prediction reasons and background information when making a proposal to the user.

Images