Artificial intelligence-based recognition system for real-time identification of social media profiles and their linking at events

Abstract

A system for real-time identification and social media profile connection of people at events, consisting of: a plurality of image sensors configured to capture facial images of attendees in an event environment; a multi-sensor fusion module configured to receive and integrate data from the plurality of image sensors as well as at least one additional sensor selected from the group consisting of audio recorders, Bluetooth beacons, RFID readers, and inertial measurement units (IMUs); an artificial intelligence engine with a deep learning-based facial recognition sub-module that can process the fused sensor data to identify individuals by comparing biometric facial data with a database of pre-registered participants; A cloud-based social media integration module configured to retrieve verified social media profiles of identified individuals via secure API connections to one or more social media platforms; a data protection management framework implemented to enforce data minimization, user consent management, encryption, and compliance with applicable data protection regulations; a communications interface configured to deliver connection requests and notifications in real time to subscriber devices, including mobile applications, wearable devices, or interactive kiosks; and a control unit that orchestrates the operation of the system modules to enable seamless and automated attendee identification and social media connection during the event.

Description

Field of the invention

[0001] The present invention relates to the field of artificial intelligence and biometric identification systems, focusing in particular on real-time recognition and identification of individuals in event environments. It utilizes advanced sensor fusion techniques that combine image, audio, and proximity data to improve the accuracy and reliability of identity verification. The invention also relates to secure integration with social media platforms for automatically retrieving and linking verified social media profiles. Background of the invention

[0002] In the age of digital connectivity, social media platforms have become indispensable tools for professional networking and social interaction. Events such as conferences, trade fairs, exhibitions, and social gatherings provide attendees with valuable opportunities to make new contacts and build relationships. However, real-time identification and seamless connection between attendees remain challenging, often requiring the manual exchange of contact information or a delayed social media search after the event. Existing attendee identification solutions rely primarily on manual badge scanning or QR code exchange, which is time-consuming and disrupts natural interaction. Furthermore, these approaches lack integration with social media profiles, limiting the potential for immediate and meaningful digital connections.There is a need for an intelligent system that automatically identifies people at events and enables instant, real-time social media-based interactions while complying with data privacy regulations.

[0003] In today's hyperconnected world, social and professional events serve as important platforms for networking, knowledge sharing, and relationship building. Conferences, trade fairs, exhibitions, and social gatherings bring together diverse people, many of whom use social media platforms to deepen and maintain the connections made at such events. Despite the obvious potential, identifying individuals and linking their social media profiles in real time remains a persistent challenge. Until now, organizers and attendees have relied on manual methods such as exchanging physical business cards, scanning QR codes, or using badges with embedded RFID or NFC technology.While these approaches enable the exchange of contacts, they are limited by the need for direct, targeted interaction between participants and do not provide a seamless, automated mechanism for real-time profile identification and linking.

[0004] One of the most widely used methods in the event industry is the use of RFID-enabled badges. These badges are equipped with RFID tags that can be read by scanning devices at strategic locations or by event staff. RFID systems can register attendee attendance and enable easy exchange of contact information or access control. Although RFID improves purely manual processes through contactless interaction, it has several significant drawbacks. First, RFID requires proximity or physical scanning, which interrupts the natural flow of networking and may not capture spontaneous encounters. Furthermore, RFID data often contains limited information such as name and company and is not directly integrated with social media platforms.This requires additional manual steps to locate and digitally communicate with people after the event, limiting the immediacy and intensity of interaction.

[0005] Scanning QR codes has also gained popularity in recent years as an alternative to sharing contacts and exchanging digital business cards. Attendees receive QR codes on their ID cards or smartphones, which can be scanned by others to instantly access profile information or websites. While user-friendly and cost-effective, QR codes also require strong active user participation; the code must be consciously scanned, often requiring physical proximity and a willingness to interact. Furthermore, QR codes typically redirect users to static links or profile pages without offering real-time contextual recommendations or adaptive interactions based on attendee interests or event context. Therefore, QR codes do not automatically support intelligent matchmaking or dynamic connection suggestions, limiting their usefulness for meaningful networking outcomes.

[0006] Manual or semi-automated approaches such as business card exchanges, RFID scanning, and QR codes require active user participation and disrupt natural social exchanges. Mobile event apps rely on user engagement and connectivity, limiting real-time usability. Early facial recognition systems struggle with accuracy and lack comprehensive privacy protection. Most systems do not leverage multi-sensor fusion to increase reliability or enable personalized, dynamic networking experiences. Furthermore, implementation limitations and fragmented social media integration hinder scalability and inclusivity. These shortcomings underscore the urgent need for an intelligent, privacy-preserving, AI-based recognition system that seamlessly identifies and connects social media profiles in real time, tailored to live event environments. Summary of the invention

[0007] The present invention provides an advanced artificial intelligence (AI)-based recognition system and device. It enables real-time identification of attendees at live events and instant retrieval of their social media profiles to enable immediate connection and interaction. The system utilizes high-resolution imaging units with integrated AI processors and deep learning-based facial recognition models to recognize individuals in an event environment. Upon successful identification, the system securely accesses linked social media profiles via cloud databases and provides personalized contact recommendations based on attendees' interests and professional backgrounds. The device supports various interaction channels, including mobile apps, wearable devices, and interactive kiosks, allowing attendees to seamlessly accept or decline connection requests.Additionally, the system integrates multi-sensor fusion, including audio, RFID, and Bluetooth beacon inputs, to improve recognition accuracy and user experience. The modular hardware design ensures adaptability for stationary or mobile use, making it suitable for a variety of event scenarios. Data privacy and security are ensured through federated learning and strict access controls in accordance with applicable data protection laws.

[0008] The primary objective of the present invention is to provide an advanced, artificial intelligence-based recognition system that identifies individuals at social and professional events in real time, enabling instant and seamless connection with their corresponding social media profiles. Another key objective is to eliminate manual contact exchanges or the scanning of physical IDs and QR codes by automating the recognition process using sophisticated facial recognition algorithms combined with multi-sensor data fusion techniques. The invention further aims to improve the accuracy and reliability of identification in dynamic and crowded event environments by combining image, audio, Bluetooth, RFID, and motion sensor inputs.Another goal is to securely link identified individuals to their verified social media accounts via cloud-based databases and APIs. This enables personalized networking recommendations and meaningful digital interactions without compromising user privacy. Furthermore, the invention aims to provide a modular and customizable hardware device that can be used in various event scenarios, including fixed and portable units, thus ensuring flexibility and easy integration into different venues. Another goal of the invention is to integrate strict data protection and privacy mechanisms according to global regulations. Federated learning and encrypted communication are used to protect sensitive personal data.Another goal is to develop a user-friendly interface that provides real-time notifications and connection options via mobile apps, wearables, and kiosks, allowing attendees to conveniently accept or decline connection requests. Overall, the invention aims to revolutionize event networking by combining cutting-edge AI technology with seamless social media integration, thus improving the efficiency, spontaneity, and quality of attendee interactions in real time. SHORT DESCRIPTION OF THE FIGURE

[0009] These and other features, aspects, and advantages of the present invention will become more readily understood when the following detailed description is read in conjunction with the accompanying drawings, in which like characters represent like parts throughout. Fig. Figure 1 shows a block diagram of an artificial intelligence-based recognition system for real-time identification and connection of social media profiles at events.

[0010] Those skilled in the art will also appreciate that the elements in the drawings are shown for convenience and are not necessarily to scale. For example, the flowcharts illustrate the method by key steps to enhance understanding of aspects of the present disclosure. Furthermore, with respect to device construction, one or more components of the device may be represented in the drawings by conventional symbols. The drawing may show only the specific details relevant to understanding embodiments of the present disclosure in order not to clutter the drawing with details that would be readily apparent to those skilled in the art from the present description. Detailed description of the invention

[0011] To facilitate understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and a clear description will be given. However, the scope of the invention is not limited thereby. Changes and further modifications to the illustrated system, as well as further applications of the principles of the invention, are possible, as would normally occur to one skilled in the art to which the invention pertains.

[0012] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be limiting thereof.

[0013] References in this specification to "one aspect," "another aspect," or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, the language "in one embodiment," "in another embodiment," and similar language throughout this specification may or may not refer to the same embodiment.

[0014] The terms "comprises," "comprising," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method comprising a list of steps may include not only those steps, but also additional steps not expressly listed or inherent in that process or method. Likewise, the statement "comprises" for one or more devices, subsystems, elements, structures, or components does not exclude, without further limitation, the existence of other devices, subsystems, elements, structures, components, or additional devices, subsystems, elements, structures, or components.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the invention pertains. The systems, methods, and examples provided herein are for illustrative purposes only and should not be considered limiting.

[0016] Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0017] In Fig.Figure 1 shows a block diagram of an artificial intelligence-based recognition system for real-time identification and connection of social media profiles at events. The system 100 includes a plurality of image sensors (102) configured to capture facial images of attendees in an event environment; a multi-sensor fusion module (104) configured to receive and integrate data from the plurality of image sensors and at least one other sensor selected from the group consisting of audio recorders, Bluetooth beacons, RFID readers, and inertial measurement units (IMUs); an AI engine (106) including a deep learning-based facial recognition submodule that processes the fused sensor data to identify unique individuals by matching biometric facial data to a pre-registered attendee database;a cloud-based social media integration module (108) configured to retrieve verified social media profiles of identified individuals via secure API connections to one or more social media platforms; a privacy management framework (110) implemented to enforce data minimization, user consent management, encryption, and compliance with applicable data protection regulations; a communications interface (112) configured to deliver connection requests and notifications in real time to participant devices, including mobile applications, wearable devices, or interactive kiosks; and a control unit (114) that orchestrates the operation of the system modules to enable seamless and automated participant identification and social media connection during the event.

[0018] In one embodiment, the multi-sensor fusion module (104) uses sensor synchronization and adaptive weighting algorithms to improve detection accuracy under different environmental conditions, with the weighting being dynamically adjusted based on sensor reliability metrics, including signal-to-noise ratio, occlusion detection, and ambient light parameters.

[0019] In one embodiment, the artificial intelligence engine (106) utilizes a convolutional neural network architecture trained on a diverse dataset including different facial poses, expressions, and lighting conditions to achieve robustness to partial occlusions and pose variations, and further includes a feature embedding mechanism that maps biometric data into a multidimensional vector space for efficient similarity comparison.

[0020] In one embodiment, the cloud-based social media integration module (108) implements federated identity verification protocols that enable decentralized validation of user profiles without directly exposing personally identifiable information (PII) to the event system. This preserves user privacy while enabling accurate profile matching.

[0021] In one embodiment, the privacy management framework (110) includes real-time anonymization techniques so that unverified or non-consenting individuals detected by the sensors are only processed in aggregated, non-identifiable form and all personal data is securely stored in encrypted databases that can only be accessed via multi-factor authentication.

[0022] In one embodiment, the communication interface (112) supports bidirectional encrypted messaging channels that allow participants to accept, reject, or defer connection requests via social media through their mobile applications, with user preferences dynamically influencing future connection recommendations generated by a machine learning-based matchmaking sub-module.

[0023] In one embodiment, comprising a hardware deployment module that offers modular installation options, including fixed panoramic camera arrays, portable wearable sensor units with edge AI inference capabilities, and stationary kiosks with interactive touchscreens and audio input / output components for user interaction.

[0024] In one embodiment, the wearable sensor units comprise a low-power embedded processing unit optimized for on-device facial recognition pre-processing and coupled with Bluetooth Low Energy (BLE) modules for real-time data transmission to the control unit, minimizing latency and bandwidth usage in high-event density environments.

[0025] In one embodiment, the control unit (114) executes a distributed processing architecture that utilizes edge computing nodes deployed within the venue to locally pre-process sensor data to reduce network congestion and latency before transmitting relevant features to the central cloud AI engine for final identification and profile matching.

[0026] In one embodiment, the artificial intelligence engine (106) further comprises an explainable AI sub-module configured to generate human-interpretable confidence scores and justifications for each identification and social media profile matching decision, facilitating user verifiability and trust.

[0027] The present invention relates to an artificial intelligence-based recognition system that enables the real-time identification of individuals at events and seamless linking to their social media profiles. The system comprises a sophisticated integration of hardware and software components that work together to ensure precise, reliable, and privacy-compliant identification and networking in dynamic event environments. At the core of the invention is a multi-sensor fusion module that synergistically processes data collected by a range of sensors, including imaging devices such as high-resolution cameras, directional microphones for audio recording, Bluetooth beacons, RFID readers, and inertial measurement units. These heterogeneous data streams are synchronized and adaptively weighted based on real-time sensor reliability metrics such as signal quality, ambient light conditions, occlusions, and ambient noise levels.The sensor fusion algorithm uses statistical and machine learning methods to combine sensor inputs to create a comprehensive, noise-resistant biometric signature for each detected person.

[0028] Face recognition is based on deep learning-based artificial intelligence (AI). It utilizes a convolutional neural network (CNN) architecture specifically trained on a large and diverse dataset containing faces with different poses, expressions, occlusions, and lighting scenarios. This CNN processes the fused sensor data and extracts discriminatory features, which are then transformed into a multidimensional embedding space. Similarity calculations enable robust matching with a pre-registered participant database. This embedding process enables the system to efficiently and accurately distinguish between similar faces while ensuring the high throughput required for real-time processing in crowded environments.

[0029] To address privacy concerns associated with biometric identification and social media integration, the system implements a data protection framework with federated identity verification protocols. These protocols enable decentralized authentication of user identities and social media profiles without the event system directly accessing sensitive personally identifiable information (PII). Data minimization techniques ensure that only the information necessary for identification and networking is processed. All stored data is encrypted using state-of-the-art cryptographic techniques. Furthermore, real-time anonymization processes transform data from non-consenting or unverified individuals into aggregated, de-identifiable forms, thus protecting privacy while maintaining situational awareness.

[0030] The cloud-based social media integration module operates through a secure interface to social media platforms via dynamically adaptable APIs. This allows the system to retrieve verified social media profiles of identified individuals, even as the platforms' data access policies evolve. Once the profiles are linked, the system generates personalized network recommendations using a machine-learning matchmaking submodule. This submodule combines graph-based social media analytics with natural language processing of publicly available user interests and event metadata to create prioritized lists of connection suggestions tailored to each participant's profile and preferences.

[0031] Communication with participants is facilitated by a versatile interface that supports multiple endpoints, including mobile applications, wearable devices, and interactive kiosks. This interface manages encrypted, bidirectional messaging channels that deliver real-time notifications of connection requests and allow users to accept, decline, or postpone these requests as desired. An adaptive notification scheduler optimizes the timing and delivery method of these requests by analyzing contextual factors such as participant engagement, proximity to other identified individuals, and ongoing event schedules, thus enhancing the user experience without causing interruptions.

[0032] To ensure computing power and system scalability, the invention utilizes a distributed processing architecture, with edge computing nodes throughout the venue locally preprocessing the raw sensor data. This decentralization significantly reduces network traffic and accelerates the identification process by transmitting only essential feature representations to the central cloud AI engine, which performs the final recognition and profile matching. Additionally, the AI ​​engine integrates an explainable AI component that creates interpretable confidence scores and decision baselines for each identification. This increases transparency and facilitates traceability for event organizers and users.

[0033] In addition to facial recognition, the multi-sensor fusion module integrates audio-based voice recognition captured via directional microphones. This multimodal biometric approach confirms facial data, especially in conditions of obstructed vision or poor lighting, thus improving overall identification reliability. The system also integrates continuous behavioral anomaly detection within the context of data protection to identify potentially unauthorized data access or tamper-evident attempts. This is supported by blockchain-based, tamper-proof logging to secure all transaction data.

[0034] The AI-based recognition system consists of an integrated machine comprised of a high-resolution multi-angle imaging unit, an embedded processing module with AI acceleration capabilities, communication interfaces, and a user interaction subsystem. The imaging unit, which may contain an array of RGB or stereo cameras, is strategically installed at the event venue or mounted on portable platforms such as kiosks or handheld devices. These cameras continuously capture live video streams of event attendees, which are processed locally by the embedded computer. The processing module utilizes CNN-based deep learning algorithms (convolutional neural network) to perform facial recognition and detection in real time.Facial features are extracted through landmark detection and feature embedding generation, then matched against a pre-registered opt-in database of attendees who linked their social media accounts during event registration. This database is securely managed in the cloud and synchronized with the on-premises unit via encrypted channels.

[0035] To improve detection accuracy in dynamic and crowded environments, the system utilizes multi-sensor fusion. Audio sensors enable speech recognition and context awareness, while RFID and Bluetooth beacon scanners capture proximity signals from participant badges or mobile devices. Inertial measurement units (IMUs) support spatial tracking and positioning to ensure continuous detection of people in motion. The fusion of these data streams significantly reduces false alarms and increases robustness.

[0036] After positive identification, the system securely retrieves social media profiles from platforms such as LinkedIn, Twitter, Instagram, and Facebook via APIs. These profiles are processed by natural language processing (NLP) modules to extract key interests, professional roles, and event attendance data. This allows the system to generate personalized connection suggestions. The user interface subsystem sends notifications to attendees via connected mobile applications, smart badges, smart glasses, or interactive kiosks. These notifications prompt users to accept or decline connection requests. Accepted requests trigger immediate synchronization across the entire event network, enabling real-time communication, digital business card exchange, scheduling, and content sharing.

[0037] The device's structural design consists of modular components housed in an industrial-grade enclosure that meets environmental sustainability requirements. This modularity allows it to be used as a fixed unit with adjustable camera mounts and touchscreen kiosks, or as a lightweight, portable device for event staff. The device supports wireless communication protocols such as Wi-Fi, 5G, and Bluetooth to ensure continuous connectivity to cloud services and participant devices.

[0038] The system ensures compliance with global data protection standards such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) through the implementation of federal learning techniques. These techniques enable the improvement of AI models through distributed local training without transferring sensitive raw data to the cloud, thus protecting user privacy. Furthermore, access to personal data is strictly controlled through authentication mechanisms and encrypted communication channels.

[0039] The drawings and the foregoing description illustrate examples of embodiments. Those skilled in the art will recognize that one or more of the described elements may well be combined to form a single functional element. Alternatively, certain elements may be separated into multiple functional elements. Elements of one embodiment may be added to another embodiment. For example, the order of the processes described herein may be changed and is not limited to the manner described herein. Furthermore, the actions of a flowchart need not be performed in the order shown; nor do all actions need to be performed. Also, actions that are not dependent on other actions may be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and use of materials, are possible. The scope of the embodiments is at least as broad as indicated in the following claims.

[0040] Advantages, further benefits, and solutions to problems have been described above with reference to specific embodiments. However, the advantages, advantages, solutions to problems, and any components that may result in or enhance an advantage, advantage, or solution are not to be construed as critical, required, or essential features or components of any or all of the claims. REFERENCES 100 An artificial intelligence-based recognition system for real-time identification of social media profiles and their linking at events. 102 Variety of image sensors 104 Multisensor Fusion Module 106 Artificial Intelligence Engine 108 Cloud-based social media integration module 110 For Data Protection Management 112 Communication interface 114 Control unit

Claims

[1] A system for real-time identification and social media profile connection of people at events, consisting of: a plurality of image sensors configured to capture facial images of attendees in an event environment; a multi-sensor fusion module configured to receive and integrate data from the plurality of image sensors as well as at least one additional sensor selected from the group consisting of audio recorders, Bluetooth beacons, RFID readers, and inertial measurement units (IMUs); an artificial intelligence engine with a deep learning-based facial recognition sub-module that can process the fused sensor data to identify individuals by comparing biometric facial data with a database of pre-registered participants; A cloud-based social media integration module configured to retrieve verified social media profiles of identified individuals via secure API connections to one or more social media platforms; a data protection management framework implemented to enforce data minimization, user consent management, encryption, and compliance with applicable data protection regulations; a communications interface configured to deliver connection requests and notifications in real time to subscriber devices, including mobile applications, wearable devices, or interactive kiosks; and a control unit that orchestrates the operation of the system modules to enable seamless and automated attendee identification and social media connection during the event. [2] The system of claim 1, wherein the multi-sensor fusion module uses sensor synchronization and adaptive weighting algorithms to improve detection accuracy under different environmental conditions, with the weighting being dynamically adjusted based on sensor reliability metrics, including signal-to-noise ratio, occlusion detection, and ambient light parameters. [3] The system of claim 1, wherein the artificial intelligence engine uses a convolutional neural network architecture trained on a diverse dataset including different facial poses, expressions, and lighting conditions to achieve robustness to partial occlusions and pose variations, and further comprising a feature embedding mechanism that maps biometric data into a multidimensional vector space for efficient similarity comparison. [4] The system of claim 1, wherein the cloud-based social media integration module implements federated identity verification protocols that enable decentralized validation of user profiles without directly exposing personally identifiable information (PH) to the event system, thereby preserving user privacy while enabling accurate profile matching. [5] The system of claim 1, wherein the privacy management framework includes real-time anonymization techniques such that unverified or non-consenting individuals detected by the sensors are only processed in aggregated, non-identifiable form and all personal data is securely stored in encrypted databases accessible only through multi-factor authentication. [6] The system of claim 1, wherein the communication interface supports bidirectional encrypted messaging channels that allow participants to accept, reject, or defer connection requests via social media through their mobile applications, with user preferences dynamically influencing future connection recommendations generated by a machine learning-based matchmaking sub-module. [7] The system of claim 1, wherein the wearable sensor units comprise a low-power embedded processing unit optimized for on-device facial recognition pre-processing and coupled with Bluetooth Low Energy (BLE) modules for real-time data transmission to the control unit, thereby minimizing latency and bandwidth usage in high-event density environments. [8] The system of claim 1, wherein the controller executes a distributed processing architecture that utilizes edge computing nodes deployed within the venue to locally pre-process sensor data to reduce network congestion and latency before transmitting relevant features to the central cloud AI engine for final identification and profile matching.

Images