Health monitoring system with AI-powered user identification and automated reporting

Abstract

An intelligent health monitoring system, consisting of: a weighing platform incorporating at least one load cell arrangement configured to generate electrical signals corresponding to the user's body weight; a vertical housing that carries an ultrasonic or infrared distance sensor configured to determine the size of the user positioned on the weighing platform; a blood pressure measuring unit comprising a cuff, a pneumatic pump, a pressure sensor and a valve arrangement, wherein the unit is operationally coupled to a microcontroller for calculating the systolic and diastolic pressure; a pulse detection unit comprising a photoplethysmography (PPG) or optical sensor configured to measure heart rate and oxygen saturation; a body composition analysis unit comprising at least two bioelectrical impedance electrodes configured to pass a controlled current through the user's body and measure the corresponding voltage drop to calculate the fat and muscle percentage; a user identification module comprising a camera, an optical recognition engine and an AI-powered optical character recognition processor configured to extract identification information from a personal identification card; a human-machine interface consisting of a touchscreen display that shows the test progress, measurement results, and user input options; a microcontroller or embedded processing unit configured to receive sensor signals, digitize and process the measurements, and synchronize them with identification data; a secure communication module configured to transmit the processed data to a remote cloud platform via an encrypted application programming interface; and a cloud-based web platform with role-specific portals for customers, administrators and developers, the platform being configured to store health data, perform predictive analytics using machine learning techniques and deliver test reports via at least one cross-platform messaging or SMS channel.

Description

Technical field

[0001] The present invention relates to electronic devices for health monitoring and in particular to an intelligent health station capable of measuring multiple health parameters, integrating artificial intelligence and machine learning for identification and analysis, and transmitting the results to a central web-based platform for automated reporting and predictive health insights. Background of the invention

[0002] Conventional health monitoring devices on the market are fragmented and limited in their functionality. Traditional BMI devices only measure height and weight, while separate, standalone devices are required for blood pressure monitoring, pulse measurement, or body fat analysis. Most of these devices operate in isolation, generating raw data without providing integrated health information or predictive insights. Furthermore, conventional systems lack direct user identification, and results are either stored locally or manually entered, leading to duplication of effort and errors.

[0003] While some health kiosks already exist, they primarily focus on standalone measurements and lack AI / ML capabilities for analysis or prediction. They also don't offer multifunctional web platforms that allow different user types, such as customers, administrators, and developers, to interact with the system. Furthermore, the immediate transmission of health reports via digital channels like cross-platform messaging or SMS is not yet standard practice.

[0004] Therefore, there is a need for a unified intelligent health monitoring system that integrates multiple health tests into one device, automates user identification, uses AI / ML-supported analytics, and communicates the results instantly and securely via a scalable web platform.

[0005] Health monitoring devices have undergone significant development in recent decades, evolving from simple weight and height measuring devices to sophisticated diagnostic stations capable of capturing multiple physiological parameters. The first solutions in this field were mechanical scales and stadiometers, which allowed medical personnel to manually calculate body mass index (BMI). While functional, these devices required human intervention at every step and lacked automation. With the advent of digital technology, standalone digital scales became widely available. Equipped with load cells and digital displays, these devices enabled more precise weight measurements. Some models even combined height measurement with electronic BMI calculation.Despite these advances, such devices remained rudimentary, providing only a numerical output of BMI without any form of data integration, recording, or predictive analysis. They essentially functioned as a replacement for manual calculation, not as intelligent health management tools.

[0006] In parallel, the healthcare sector saw the development of personalized devices for monitoring vital functions such as blood pressure, heart rate, oxygen saturation, and body fat percentage. Blood pressure monitors, typically based on oscillometric or auscultatory principles, became available in both clinical and home versions. Pulse oximeters evolved into compact fingertip devices capable of measuring oxygen saturation and heart rate in real time. Body composition analyzers based on bioelectrical impedance analysis emerged as standalone devices capable of measuring body fat percentage, fluid balance, and muscle mass. While these instruments enabled users to gather important health information, they were rarely integrated into a unified ecosystem.Anyone wanting to comprehensively monitor their health needed separate devices for weight, blood pressure, pulse, and body fat analysis, and then had to manually combine the results. This fragmentation posed challenges in terms of convenience, data continuity, and long-term health monitoring.

[0007] Attempts have been made to develop integrated health kiosks that combine some of these functions in a single station. Health kiosks in pharmacies, gyms, or corporate wellness centers typically measure weight, height, blood pressure, and sometimes pulse. The readings are displayed on a screen and, in some cases, printed out on a slip of paper. While these kiosks represent progress by centralizing multiple measurements, they still have several limitations. First, they are generally not linked to unique user identities. The results are often anonymous, recorded on a printed slip of paper that the user can lose, or manually entered into external systems. Without reliable identification and storage, long-term health tracking is impossible. Second, most kiosks lack any intelligence or advanced analytics.They provide raw data but offer no interpretation, trend analysis, or prevention suggestions. For users without medical expertise, these measurements may be of limited use. Third, the communication channels of such kiosks are outdated and rely primarily on local printing rather than digital sharing, limiting access to and immediate use of health data.

[0008] Another category of existing solutions includes mobile health applications and wearable devices such as smartwatches and fitness trackers. These devices have sensors for monitoring heart rate, counting steps, tracking sleep, and, in some advanced cases, ECG monitoring. They are paired with smartphone applications that provide visual dashboards and long-term trend analyses. While wearables offer a convenient way to continuously monitor health, they also have significant drawbacks. Their accuracy in measuring physiological parameters is often questioned, especially compared to devices used in clinical settings. Due to variations in skin tone, motion artifacts, and inconsistent placement, they can produce poorer results across different user groups.Furthermore, wearables tend to focus more on lifestyle monitoring than medical diagnostics, and their fragmented ecosystem means they are not universally compatible with clinical platforms. Importantly, most wearables lack blood pressure monitoring or body composition analysis, leaving gaps in a comprehensive health assessment.

[0009] Hospitals and clinics have advanced diagnostic stations that integrate multiple sensors and provide accurate physiological data. However, these systems are expensive, bulky, and require trained personnel to operate. Their complexity makes them unsuitable for widespread use in public spaces or private homes. Furthermore, they are not designed for automatic user identification or consumer-driven health monitoring, but rather for supervised clinical evaluation. Therefore, their applications are limited to medical settings and do not contribute to preventive healthcare or personal wellness management.

[0010] The lack of intelligent user identification is one of the most persistent shortcomings of existing health monitoring solutions. Current kiosks and devices typically operate on a session-based model, where data is directly linked to the user without verification. While manual entry of name or phone number is sometimes possible, this is error-prone and inconsistent. Such limitations prevent the creation of persistent digital health records, which are crucial for identifying long-term patterns and enabling personalized healthcare. Without a mechanism that securely and automatically links health measurements to an individual's identity, the potential of digital health monitoring remains untapped.

[0011] Another drawback of the current state of technology is the lack of secure and scalable integration with cloud platforms. While some devices offer proprietary applications for data storage, they often remain closed systems that are incompatible with third-party health records, insurance platforms, or hospital databases. This creates information silos that diminish the value of the collected health data. True digital healthcare requires seamless interoperability and secure data transfer. Existing devices fall short in this regard, often relying on USB transfer, local storage, or unsecured network protocols. The absence of standardized, secure APIs in most health monitoring solutions means they cannot effectively participate in the growing ecosystem of connected healthcare.

[0012] Automation in communication and reporting is another area where existing solutions fall short of modern requirements. While some kiosks print receipts or send email reports, real-time integration with messaging platforms like cross-platform messaging or SMS is typically lacking. In today's digital environment, users expect immediate delivery of their results in an accessible format on mobile devices. The fact that current devices don't utilize these ubiquitous communication channels reduces their effectiveness and limits user interaction. Furthermore, manually processing reports leads to data loss, duplication, and a lack of continuity in health monitoring.

[0013] Artificial intelligence and machine learning have transformed many industries, but their application in consumer health monitoring devices is limited. Existing devices typically lack predictive analytics or proactive health suggestions. For example, a blood pressure monitor might simply display a high reading without contextualizing the result or advising the user to see a doctor. Similarly, BMI devices provide a numerical ratio without identifying whether a trend over time indicates a risk of obesity or malnutrition. This lack of intelligence forces users to interpret the data themselves, often without medical expertise, which can lead to misunderstandings or the ignoring of important health warnings.The integration of AI / ML could enable the automatic detection of health patterns, the early detection of anomalies, and the generation of prevention recommendations, but this function is largely lacking in current devices.

[0014] Furthermore, scalability and maintenance pose challenges for existing systems. Health kiosks often require manual maintenance, calibration, and software updates. Remote diagnostics and wireless firmware updates are rarely supported, making large-scale deployments inefficient. When a kiosk malfunctions, on-site technician visits are typically required, resulting in downtime and high operating costs. This lack of remote control and diagnostics limits the scalability of such systems and hinders widespread adoption.

[0015] Cost-effectiveness is also a drawback of current solutions. Integrated diagnostic stations, like those used in clinical settings, are prohibitively expensive for mass deployment in schools, workplaces, or community centers. While individual devices may be affordable, they do not offer comprehensive health assessments, requiring users to purchase multiple devices to cover different parameters. The lack of a single, affordable, multi-parameter device with integrated intelligence leaves a market gap in preventive and community-based healthcare.

[0016] Ultimately, existing solutions often fail to meet the growing importance of a unified digital health ecosystem. Healthcare providers, insurers, and governments are increasingly relying on digital health records to ensure continuity of care, yet consumer-level devices remain disconnected. Data collected at home or at kiosks is rarely integrated into central platforms, leading to fragmentation and inefficiency. Without devices capable of feeding accurate, identified, and secure health data into cloud systems, the vision of comprehensive digital healthcare remains incomplete.

[0017] While current health monitoring technology shows incremental improvements, it is insufficient to create the comprehensive, intelligent, and connected ecosystem required for modern preventive healthcare. Devices are too fragmented, limited, or isolated to meet the need for unified health monitoring, predictive insights, and real-time communication. The drawbacks of manual identification, lack of integration, limited intelligence, poor scalability, and the absence of digital communication channels underscore the urgent need for a new solution that combines hardware precision with software intelligence, enables seamless data flow to cloud ecosystems, and delivers actionable health insights to users, not just numbers. Summary of the invention

[0018] The invention describes an intelligent health monitoring system consisting of integrated hardware and a cloud-based software platform. The hardware is equipped with sensors for measuring body mass index, pulse, blood pressure, and body fat percentage. It also includes a load cell for weight measurement, an ultrasonic or infrared distance sensor for height measurement, a pulse oximeter or heart rate sensor, a blood pressure monitor, and a bioelectrical impedance analyzer for body fat analysis.

[0019] The device features an optical recognition module with a camera and AI-powered optical character recognition (OCR) that automatically identifies the user by scanning an ID card. If the OCR scan fails, the device offers manual input as an alternative. A microcontroller coordinates data acquisition, processing, and communication, while a human-machine interface (HMI) facilitates user interaction. An integrated thermal printer can be provided for generating physical reports.

[0020] The data collected by the hardware is securely transmitted to a central cloud platform via an encrypted application programming interface (API). The platform is multifunctional and includes a customer portal for accessing personal health data and reports, an admin panel for managing devices and monitoring system data, and a developer panel for remote diagnostics, firmware updates, and technical maintenance.

[0021] The invention also includes machine learning models for analyzing health data trends, providing predictive health insights, and recommending preventive health measures. The results are automatically communicated to the user via SMS or cross-platform messaging, enabling real-time access to health reports.

[0022] The main objective of the present invention is to provide an intelligent health monitoring system that integrates multiple health measurement functions, including body mass index, blood pressure, pulse, and body fat analysis, into a single device, thus eliminating the need for users to rely on fragmented, individual devices. A further objective is to ensure that each measurement is directly assigned to an identified user through automated recognition techniques, such as AI-assisted optical character recognition of identification documents. This eliminates the risk of manual errors and enables the creation of permanent and secure digital health records.Another objective is to connect the hardware device to a cloud-based web platform that supports multiple roles, including customers, administrators, and developers, enabling efficient data management, device monitoring, and maintenance across distributed deployments. The invention also seeks to overcome the limitations of existing systems by integrating artificial intelligence and machine learning techniques to analyze collected health data, identify trends, predict potential risks, and generate preventative recommendations. In this way, raw physiological data is transformed into meaningful health insights.

[0023] A further objective of the invention is the immediate, automated, and user-friendly communication of results through the integration of the system with messaging platforms such as cross-platform messaging and SMS. This ensures that reports are transmitted securely and in real time to users. Another objective is to enable remote diagnostics, firmware updates, and maintenance via a dedicated developer interface to reduce downtime and lower operating costs for on-site device maintenance. A further objective is the scalability and modularity of the system, allowing for the integration of additional health sensors and diagnostic modules without redesigning the entire device. This expands the system's application to various areas of healthcare.Another goal is to design the device in a kiosk format with ergonomic sensor placement, intuitive human-machine interaction, and integrated printing options. This makes the system user-friendly and suitable for use in public or semi-public spaces such as clinics, gyms, workplaces, and community centers.

[0024] The overarching goal of the invention is ultimately to create a comprehensive and intelligent digital health ecosystem that bridges the gap between individual health monitoring and centralized health management. By combining automated identification, multi-parameter measurement, predictive analytics, secure cloud integration, real-time reporting, and remote controllability, the invention aims to address the shortcomings of existing solutions and provide a cost-effective, accurate, and networked system that delivers actionable health insights to users while supporting preventive healthcare at scale. BRIEF DESCRIPTION OF THE FIGURE

[0025] These and other features, aspects, and advantages of the present invention will be better understood if the following detailed description is read with reference to the accompanying drawing, in which the same symbols consistently represent the same parts. The following applies: Fig. Figure 1 shows a block diagram of a health monitoring system with AI-powered user identification, web platform integration, and automated reporting.

[0026] Experts will also recognize that the elements in the drawing are shown for the sake of simplicity and are not necessarily to scale. For example, the flowcharts illustrate the process by highlighting the main steps to enhance understanding of the aspects of this disclosure. Furthermore, with regard to the design of the device, one or more components of the device may be represented in the drawing by conventional symbols, and the drawing may show only the specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawing with details that are readily apparent to those skilled in the art after reading this description. Detailed description of the invention

[0027] For a better understanding of the inventive principles, reference is made below to the embodiment shown in the drawing, which is described in specific terminology. However, this does not limit the scope of the invention. Changes and further modifications of the illustrated system, as well as further applications of the inventive principles, are possible, as would normally occur to a person skilled in the art in the field of invention.

[0028] It is clear to the person skilled in the art that the preceding general description and the following detailed description are exemplary and explanatory of the invention and are not intended as a limitation of it.

[0029] References in this specification to “an aspect”, “another aspect”, or similar expressions mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, occurrences of the expressions “in one embodiment”, “in another embodiment”, and similar expressions in this specification may all refer to the same embodiment, but need not.

[0030] The terms "includes," "include," or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a list of steps may not only contain those steps but may also include other steps not expressly listed or inherent in such process or method. Likewise, the statement "includes..." in the case of one or more devices, subsystems, elements, structures, or components does not, without further limitations, preclude the existence of other devices, subsystems, elements, structures, components, or additional devices, subsystems, elements, structures, or components.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by a person skilled in the art in the field of the invention. The system, methods, and examples provided here serve only for illustration and are not to be construed as a limitation.

[0032] Embodiments of the present disclosure are described in detail below with reference to the attached drawing.

[0033] In Fig.Figure 1 shows a block diagram of a health monitoring system with AI-supported user identification, web platform integration, and automated reporting. The system 100 comprises: a weighing platform (102) with at least one integrated load cell assembly (102a) that generates electrical signals according to the user's body weight; a vertical housing (104) with an ultrasonic or infrared distance sensor (104a) that determines the height of the user positioned on the weighing platform; a blood pressure measurement unit (106) with a cuff, a pneumatic pump, a pressure sensor, and a valve assembly, which is operationally connected to a microcontroller for calculating systolic and diastolic pressure; a pulse detection unit (108) with a photoplethysmography (PPG) or optical sensor for measuring heart rate and oxygen saturation;a body composition analysis unit (110) with at least two bioelectrical impedance electrodes that pass a controlled current through the user's body and measure the corresponding voltage drop to calculate the fat and muscle percentage; a user identification module (112) comprising a camera, an optical recognition machine, and an AI-controlled optical character recognition processor configured to extract identification information from an identity card; a human-machine interface (114) comprising a touchscreen display configured to show test progress, measurement results, and user input options; a microcontroller or embedded processing unit (116) configured to receive sensor signals, digitize and process the measurements, and synchronize them with identification data;a secure communication module (118) configured to transmit the processed data to a remote cloud platform via an encrypted application programming interface; and a cloud-based web platform (120) comprising role-specific portals for customers, administrators, and developers, the platform being configured to store health data, perform predictive analytics using machine learning techniques, and deliver test reports via at least one of the following channels: cross-platform messaging or SMS.

[0034] In one embodiment, the load cell arrangement (102a) comprises at least four strain gauge sensors mounted at different positions on the weighing platform. These sensors are connected to a load cell amplifier configured to eliminate noise, perform analog-to-digital conversion, and provide calibrated weight measurements to the microcontroller.

[0035] In one embodiment, the distance sensor (104a) in the vertical housing is coupled with a positioning technique implemented in the microcontroller, wherein the technique compensates for the posture of the user, the inclination of the sensor and the ambient light conditions, thus ensuring accurate height measurement regardless of the posture of the user.

[0036] In one embodiment, the blood pressure measuring unit (106) is configured to perform an oscillometric analysis using a closed-loop pneumatic control system. The system comprises a magnetically actuated valve and proportional pressure modulation, wherein the microcontroller derives systolic, diastolic, and mean arterial pressure values ​​by analyzing the envelopes of the oscillation amplitudes corresponding to the arterial pulsations.

[0037] In one embodiment, the body composition analysis unit (110) is also configured to operate in a bioelectrical impedance spectroscopy mode at multiple frequencies, wherein this mode enables the differentiation between intracellular and extracellular water content, and wherein the microcontroller applies curve fitting techniques to derive the hydration status, muscle content, and fat content from the impedance data.

[0038] In one embodiment, the user identification module (112) also includes a preprocessing pipeline with image enhancement, edge detection and character segmentation modules prior to AI-based OCR, wherein the OCR engine is trained using a deep neural network architecture to recognize alphanumeric sequences in multiple languages ​​and fonts for robust identity extraction.

[0039] In one embodiment, the human-machine interface (114) is configured to execute a guided workflow consisting of sequential on-screen instructions, animated measurement displays, and real-time progress feedback, with the workflow dynamically adapting to the test results and prompting the user to take corrective action when the sensor values ​​deviate from acceptable thresholds.

[0040] In one embodiment, the microcontroller (116) is operationally coupled to a non-volatile memory unit configured to locally cache measurement results and user identification data in encrypted form during network failures, and also configured to perform a delayed synchronization with the cloud platform after connectivity is restored, thereby ensuring data integrity and continuity.

[0041] In one embodiment, the secure communication module (118) uses a two-layer encryption protocol that includes at least one Transport Layer Security (TLS) layer and a token-based application-level authentication mechanism, thereby preventing unauthorized interception, spoofing or replay attacks during the transmission of health data to the cloud platform.

[0042] In one embodiment, the cloud-based web platform (120) includes a machine learning pipeline comprising a preprocessing module for normalizing incoming health data, a feature extraction module for temporal trend coding, and a predictive modeling module using recurrent neural networks or gradient boosting techniques, wherein the pipeline is configured to generate anomaly alerts, health risk assessments, and suggestions for a preventive lifestyle.

[0043] The intelligent health monitoring system presented here operates as a fully integrated unit, combining precision sensors with intelligent processing techniques and ensuring cloud connectivity. The weighing platform incorporates a load cell assembly with multiple orthogonally mounted strain gauges to guarantee uniform force distribution regardless of the user's posture. The analog signals generated by the load cells are amplified by a highly sensitive load cell amplifier, which features a noise reduction filter to eliminate ambient interference. The amplified signals are digitized and sent to the microcontroller, which performs a calibration procedure that corrects zero-point drift and applies a linearization function derived from a factory-stored calibration curve.This method ensures stable and precise weight measurement under different temperature and mechanical stress conditions.

[0044] The user's height is measured by a distance sensor located in the device's vertical column. The raw sensor data is preprocessed by a height measurement procedure implemented in the microcontroller. This procedure uses adaptive filtering to remove interfering reflections, and a compensation module adjusts the final measurement based on the sensor's tilt angle and the detected surface contour of the user's head. A corrective feedback loop dynamically adjusts the measurement interval to the user's movements, thus minimizing errors. Once weight and height are measured, the system calculates the body mass index (BMI) using the formula BMI = weight / (height × height). The BMI result is then linked to the user's unique identification data before transmission.

[0045] The blood pressure monitor uses an oscillometric analysis method. During operation, the pneumatic pump inflates the cuff to a pressure above the expected systolic value. The pressure is then released in a controlled manner via a solenoid valve. The pressure sensor detects pressure fluctuations in the cuff, and the microcontroller performs envelope detection to capture the amplitude of the oscillations, which correspond to arterial pulsations. A curve-fitting algorithm identifies the point of maximum oscillation as the mean arterial pressure and applies empirical scaling coefficients to determine the systolic and diastolic pressures. The algorithm also includes error detection logic that identifies irregular pulse patterns or motion artifacts and, if necessary, prompts the user to repeat the measurement.

[0046] Pulse rate and oxygen saturation are measured using a photoplethysmographic sensor. The raw optical signal is subjected to a bandpass filter that isolates the AC component corresponding to the arterial blood pulse. A peak detection method calculates the heart rate by identifying successive maxima within a defined time window. Simultaneously, the ratio of red to infrared light absorption is processed using an oxygen saturation method that applies calibration constants from clinical reference data. To improve robustness, a motion compensation module employs adaptive filtering that discards erroneous waveforms and interpolates valid measurements.

[0047] The body composition analysis module uses bioelectrical impedance spectroscopy. A controlled, multi-frequency sinusoidal current is applied via electrodes in contact with the user. The resulting voltage drop is measured and digitized. The microcontroller performs an impedance extraction technique and applies Fourier analysis to separate the resistive and reactive components of the measurement signal. From these parameters, the intra- and extracellular water distribution is estimated, and a regression-based model is applied to derive body fat percentage, muscle mass, and fluid balance. To ensure accuracy, the technology incorporates a temperature compensation factor that adjusts the impedance values ​​to the ambient and skin temperature.

[0048] The user identification module integrates a camera and an AI-powered optical character recognition (OCR) engine. The captured image is pre-processed using contrast enhancement and edge detection, followed by the segmentation of alphanumeric areas. The OCR engine utilizes a convolutional neural network trained on various fonts and multilingual datasets to recognize characters with high accuracy. A probabilistic scoring module evaluates each recognized character. If the sequences fall below a certain confidence threshold, either a rescan or manual input via the touchscreen interface is triggered. This identification data is then cryptographically linked to the measurement protocol to ensure authenticity.

[0049] All sensor data and identification information are processed by the microcontroller and encrypted before being temporarily stored in local, non-volatile memory. A synchronization technique regularly checks network connectivity. If available, the system transmits the data to the cloud platform via an encrypted communication protocol with TLS at the transport layer and token-based authentication at the application layer. In case of connection loss, the delayed synchronization routine queues the encrypted packets for later transmission, thus ensuring the continuity of health data.

[0050] On the cloud platform, incoming data is routed through a preprocessing module that normalizes units, corrects outliers, and stores the results in a secure database. The machine learning pipeline then processes the normalized data. A feature extraction technique encodes temporal changes in weight, BMI, blood pressure, and body composition, converting the raw values ​​into time-series vectors. A recurrent neural network processes these vectors to identify patterns indicative of hypertension, obesity, or abnormal heart rate variability. Gradient boosting techniques are used for classification tasks, such as categorizing users into health risk levels. The predictive module generates anomaly alerts when measurements exceed predefined thresholds or when trends suggest a potential decline in health status.

[0051] The system also features a recommendation engine that uses rule-based logic combined with machine learning to provide preventative health recommendations. For example, repeatedly elevated BMI values ​​can trigger a recommendation to change lifestyle habits, while fluctuating blood pressure readings can prompt a consultation with a doctor. The recommendation technology assigns a priority rating to each suggestion, ensuring that critical health warnings are clearly highlighted.

[0052] The results are integrated into a reporting module that formats the data into user-friendly outputs. Each report includes a unique QR code linked to the cloud dataset for verification. Reports are automatically delivered via messaging integration services that enable cross-platform messaging and SMS application programming interfaces to send the results to the user's registered contact number. The messaging technology ensures delivery confirmation and re-attempts transmission in case of failure.

[0053] The cloud platform also supports role-based access. The customer portal restricts access to an individual user's health history using tokenized authentication, enabling visualization dashboards and the retrieval of historical data. The administrator portal uses database indexing techniques to track machine operating status and provides analytics on usage frequency, failure rates, and performance efficiency. The developer portal includes secure firmware distribution techniques for over-the-air updates with cryptographic signing of firmware packages to protect against tampering. Remote diagnostic techniques allow the retrieval of machine logs, calibration checks, and error codes, enabling service technicians to troubleshoot issues without physical access.

[0054] In its kiosk configuration, the system is structured to guide the user through a workflow controlled via the human-machine interface. The touchscreen executes state machine technology, presenting sequential instructions, confirming correct sensor placement, and validating data quality before proceeding to the next measurement. Integrated error handling routines within the workflow provide alerts when sensor values ​​fall outside the permissible range, thus ensuring reliable operation even in unattended public environments.

[0055] The combination of precise sensor hardware, robust preprocessing techniques, AI-powered detection, predictive analytics, and secure communication protocols ensures that the system functions as a reliable, intelligent, and networked health monitoring solution. These techniques not only enable accurate measurements but also transform raw physiological data into actionable insights, thus closing critical gaps in existing, fragmented health monitoring technologies.

[0056] In one embodiment, the hardware device consists of a base platform with an integrated load cell for weight measurement. A vertical column houses a distance sensor for detecting the user's height. The device also includes a pulse sensor integrated into a finger clip or contact pad, a blood pressure cuff connected to the device for measuring systolic and diastolic pressure, and electrodes or contact plates for body fat analysis using bioelectrical impedance. The measurements are coordinated by a microcontroller, which digitizes and synchronizes the sensor data before transmitting it to the processing module.

[0057] An integrated optical recognition system is mounted on the device to capture and process user ID cards. Using AI-powered OCR techniques, the machine extracts text data such as name and identification number and links it to health information. If the OCR fails, the machine offers a manual input option via the user interface.

[0058] The HMI consists of a touchscreen display that guides the user through the measurement process, shows the live status of the tests performed, and displays summarized results. For permanent recording, the device has an integrated printer that generates a physical report with all measured health parameters.

[0059] The data collected by the device is securely transmitted to a central cloud platform via encrypted APIs. The cloud system divides access into three functional areas: • Through the customer panel, users can view personal health data, historical trends and reports via a secure login. • The admin panel manages machine registrations, monitors data storage, and ensures compliance with data protection and security requirements. • The developer panel enables remote firmware updates, troubleshooting, and system diagnostics.

[0060] The cloud platform uses AI and ML techniques to detect abnormal measurements, track long-term health trends, and generate predictive insights. For example, repeatedly elevated blood pressure readings can trigger a warning about health risks, and an abnormal BMI trend can lead to preventive health recommendations.

[0061] Reports are automatically delivered to the user's registered contact via cross-platform messaging and SMS integration. This feature ensures that users immediately receive a digital copy of their health report without the need for manual downloads.

[0062] In another embodiment, the system is modular and scalable, allowing for the future integration of additional health sensors such as blood glucose sensors, ECG modules, or respiratory function analyzers. The platform architecture supports seamless integration with external healthcare systems, hospitals, and insurance providers.

[0063] The drawing and the preceding description show examples of embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another embodiment. For example, the sequence of the processes described here can be changed and is not limited to the manner described here. Furthermore, the actions of a flowchart need not be implemented in the sequence shown; nor does it necessarily have to be performed by all actions. Actions that are not dependent on other actions can also be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples.Numerous variations are possible, whether explicitly stated in the specification or not, such as differences in structure, dimensions, and material use. The range of embodiments is at least as broad as specified in the following claims.

[0064] Advantages, further benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and all components that can lead to an advantage, benefit, or solution occurring or becoming more apparent are not to be construed as critical, necessary, or essential features or components of individual or all claims. REFERENCES 100 A health monitoring system with AI-powered user identification, web platform integration and automated reporting. 102 Weighing platform 102a Load cell assembly 104 Vertical Case 104a Ultrasonic or infrared distance sensor 106 Blood pressure monitor 108 Pulse detection unit 110 Device for analyzing body composition 112 User identification module 114 Human-Machine Interface 116 Microcontrollers or Embedded Processing Units 118 A Secure Communication Module 120 Load-based web platform

Claims

[1] An intelligent health monitoring system consisting of: a weighing platform incorporating at least one load cell arrangement configured to generate electrical signals corresponding to the user's body weight; a vertical housing that carries an ultrasonic or infrared distance sensor configured to determine the size of the user positioned on the weighing platform; a blood pressure measuring unit comprising a cuff, a pneumatic pump, a pressure sensor and a valve arrangement, wherein the unit is operationally coupled to a microcontroller for calculating the systolic and diastolic pressure; a pulse detection unit comprising a photoplethysmography (PPG) or optical sensor configured to measure heart rate and oxygen saturation; a body composition analysis unit comprising at least two bioelectrical impedance electrodes configured to pass a controlled current through the user's body and measure the corresponding voltage drop to calculate the fat and muscle percentage; a user identification module comprising a camera, an optical recognition engine and an AI-powered optical character recognition processor configured to extract identification information from a personal identification card; a human-machine interface consisting of a touchscreen display that shows the test progress, measurement results, and user input options; a microcontroller or embedded processing unit configured to receive sensor signals, digitize and process the measurements, and synchronize them with identification data; a secure communication module configured to transmit the processed data to a remote cloud platform via an encrypted application programming interface; and a cloud-based web platform with role-specific portals for customers, administrators and developers, the platform being configured to store health data, perform predictive analytics using machine learning techniques and deliver test reports via at least one cross-platform messaging or SMS channel. [2] System according to claim 1, wherein the load cell arrangement comprises at least four strain gauge sensors mounted at different positions on the weighing platform, the sensors being connected to a load cell amplifier configured to eliminate noise, perform analog-to-digital conversion and provide calibrated weight measurements to the microcontroller. [3] System according to claim 1, wherein the distance sensor in the vertical housing is coupled with a positioning technique implemented in the microcontroller, wherein the technique compensates for the posture of the user, the inclination of the sensor and the ambient light conditions, thus ensuring accurate height measurement regardless of the posture of the user. [4] System according to claim 1, wherein the blood pressure measuring unit is configured to perform an oscillometric analysis using a closed-loop pneumatic control system, the system comprising a magnetically driven valve and proportional pressure modulation, wherein the microcontroller derives systolic, diastolic and mean arterial pressure values ​​by analyzing the envelopes of the oscillation amplitudes corresponding to the arterial pulsations. [5] System according to claim 1, wherein the body composition analysis unit is further configured to operate in a bioelectrical impedance spectroscopy mode at multiple frequencies, wherein this mode enables the differentiation between intracellular and extracellular water content, and wherein the microcontroller applies curve fitting techniques to derive the hydration status, muscle content and fat content from the impedance data. [6] System according to claim 1, wherein the user identification module further comprises a preprocessing pipeline with image enhancement, edge detection and character segmentation modules prior to the artificial intelligence-based optical character recognition, and wherein an optical character recognition engine is trained using a deep neural network architecture to recognize alphanumeric sequences in multiple languages ​​and fonts for robust identity extraction. [7] System according to claim 1, wherein the human-machine interface is configured to execute a guided workflow consisting of sequential on-screen instructions, animated measurement displays and real-time progress feedback, the workflow dynamically adapting to the test results and prompting the user to take corrective action when the sensor values ​​deviate from acceptable thresholds. [8] System according to claim 1, wherein the microcontroller is operationally coupled with a non-volatile memory unit configured to locally cache measurement results and user identification data in encrypted form during network failures and also configured to perform delayed synchronization with the cloud platform after connectivity is restored, thereby ensuring data integrity and continuity. [9] System according to claim 1, wherein the secure communication module uses a two-layer encryption protocol comprising at least one Transport Layer Security (TLS) layer and a token-based authentication mechanism at the application level, thereby preventing unauthorized interception, spoofing or replay attacks during the transmission of health data to the cloud platform. [10] System according to claim 1, wherein the cloud-based web platform comprises a machine learning pipeline including a preprocessing module for normalizing incoming health data, a feature extraction module for temporal trend coding, and a predictive modeling module using recurrent neural networks or gradient boosting techniques, wherein the pipeline is configured to generate anomaly alerts, health risk assessments, and suggestions for a preventive lifestyle.

Images