Electronic scale with functions of healthy weight management, diabetes risk assessment and AI voice interaction

Abstract

The invention provides an electronic scale with functions of healthy weight management, diabetes risk assessment and AI voice interaction, and the electronic scale has the following technical advantages: (1) multi-modal health assessment: fusing weight, body fat, waistline (laser automatic measurement, error < = 0.5 cm) and clinical parameters (age / gender / family history); accurate evaluation of the diabetes risk is realized through a logistic regression model trained by mass clinical data; (2) AI voice interaction optimization: on the basis of an ASR model (the word error rate is less than or equal to 5%) of a Transform architecture, natural language parameter input is supported, the response time is less than or equal to 1 second, and the operation satisfaction of old users is improved to 92%; (3) full-automatic data acquisition: a weighing module, a body fat module and a waistline module are synchronously triggered, user intervention is not needed, and the data acquisition efficiency is improved; and (4) intelligent data management: local storage supports HIS system docking, and doctors can check three-month trend curves (such as BMI weekly change rate).

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to an electronic scale that combines healthy weight management with diabetes risk assessment and AI voice interaction. Background Technology

[0002] Existing electronic scales have the following application defects in diabetes risk monitoring: (1) Single function: It can only measure basic data such as weight / body fat, lacks the ability to assess disease risk, and cannot meet the needs of chronic disease prevention; (2) Complex interaction: It relies on buttons / touchscreen to input parameters such as height and age, which is cumbersome (requiring 3-5 steps) and has a low usage rate among elderly users (<30%). (3) The assessment model is rudimentary: it uses empirical formulas (such as BMI = weight / height²) and does not integrate key clinical indicators such as waist circumference and family history, resulting in low accuracy in predicting diabetes risk. (4) Data isolation: Measurement results are only displayed locally, without long-term storage / trend analysis functions, and doctors cannot obtain dynamic health data; (5) Incomplete parameter collection: lack of central obesity indicators such as waist circumference (existing electronic scales require users to manually input waist circumference, resulting in a high error rate). Summary of the Invention

[0003] To address the technical problems existing in the prior art, the present invention provides the following technical solution: On the one hand, a health weight management electronic scale that also integrates diabetes risk assessment and AI voice interaction is provided, the electronic scale comprising: The weighing module is used to collect the user's weight data; The body fat measurement module is used to collect users' body fat percentage data; Waist measurement module, used to collect user waist measurement data; The AI ​​voice interaction module is used to realize natural language input (age, gender, family history of diabetes) and result output; The microcontroller (MCU) is electrically connected to the weighing module, body fat measurement module, waist circumference measurement module, and AI voice interaction module, respectively, and is used to control the collaborative work of each module, process data, and run the diabetes risk assessment algorithm. The communication module (Bluetooth 5.3 + WiFi 6) is used to synchronize user data to a mobile app or cloud server. The display module is electrically connected to the MCU and is used to visually display data such as weight, body fat percentage, waist circumference, and diabetes risk. A storage module, electrically connected to the MCU, is used to store user data and diabetes risk assessment algorithm models; A power module is used to supply power to the electronic scale.

[0004] Preferably, the diabetes risk assessment algorithm uses a logistic regression model, with the following formula: In the formula: (R) represents the probability of diabetes risk (0≤R≤1); (e) is the natural index; These are the regression coefficients; (BMI) is the body mass index (kg / m², calculated by dividing weight by the square of height). (WC) is waist circumference (cm); (A) represents age (in years); (G) represents gender (1 = male / 0 = female); (F) indicates a family history of diabetes (1 = family member with the disease / 0 = no family history).

[0005] Preferably, the weighing module is an array of four high-precision pressure sensors with a range of 0-150kg and an accuracy of ±0.1kg.

[0006] Preferably, the body fat measurement module is a bioelectrical impedance analysis (BIA) module with a frequency of 50kHz, a current of ≤1mA, and an accuracy of ±0.5%.

[0007] Preferably, the waist circumference measurement module is an infrared laser ranging module, installed on both sides of the scale body, with a measurement range of 60-120cm and an accuracy of ±0.5cm.

[0008] Preferably, the AI ​​voice interaction module includes a microphone (pickup range 0-5m, signal-to-noise ratio ≥60dB), a speaker (output power 2W), and a voice processing SoC with NPU (such as RK3588).

[0009] Preferably, the display module is a 2.8-inch OLED screen with a resolution of 320×240 and a brightness of ≥300cd / m².

[0010] Preferably, the power module is a rechargeable lithium battery with a capacity of 3000mAh, supporting Type-C fast charging.

[0011] Preferably, the regression coefficient of the diabetes risk assessment algorithm The AUC was obtained by training with at least 10,000 clinical data (at least 5,000 patients with type 2 diabetes and at least 5,000 healthy individuals) and was ≥0.85.

[0012] Preferably, the AI ​​voice interaction module supports real-time ASR (Automatic Speech Recognition) and TTS (Text-to-Speech).

[0013] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: (1) Multimodal health assessment: Integrating weight, body fat, waist circumference (automatic laser measurement, error ≤0.5cm) and clinical parameters (age / gender / family history), a logistic regression model trained with massive clinical data is used to achieve accurate assessment of diabetes risk; (2) AI voice interaction optimization: Based on the Transformer architecture, the ASR model (word error rate ≤5%) supports natural language parameter input, with a response time ≤1 second, and the operation satisfaction of elderly users is improved to 92%; (3) Fully automated data acquisition: The three modules of weighing / body fat / waist circumference are triggered simultaneously without user intervention, which improves data acquisition efficiency; (4) Intelligent data management: Local storage supports HIS system integration, and doctors can view 3-month trend curves (such as weekly BMI change rate). Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a block diagram of an electronic scale that combines health weight management, diabetes risk assessment, and AI voice interaction, as provided in an embodiment of the present invention. Detailed Implementation

[0016] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0017] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0018] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0019] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0020] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0021] This invention provides an electronic scale that combines healthy weight management with diabetes risk assessment and AI voice interaction. For example... Figure 1 The diagram shown illustrates the control system structure of a health weight management electronic scale that combines diabetes risk assessment and AI voice interaction. The electronic scale includes: The weighing module is used to collect the user's weight data; The body fat measurement module is used to collect users' body fat percentage data; Waist measurement module, used to collect user waist measurement data; The AI ​​voice interaction module is used to realize natural language input (age, gender, family history of diabetes) and result output, including voice feedback such as abnormal data retest reminders, BMI classification prompts, waist circumference abnormal reminders and personalized management suggestions; The microcontroller (MCU) is electrically connected to the weighing module, body fat measurement module, waist circumference measurement module, and AI voice interaction module, respectively, and is used to control the collaborative work of each module, process data, run the diabetes risk assessment algorithm, and perform abnormal data retest judgment, BMI classification assessment, waist circumference abnormality detection, and generate personalized weight management suggestions. The communication module (Bluetooth 5.3 + WiFi 6) is used to synchronize user data to a mobile app or cloud server. The display module is electrically connected to the MCU and is used to visually display data such as weight, body fat percentage, waist circumference, and diabetes risk, as well as abnormal data retesting guidance, BMI classification results, waist circumference comparison charts and dynamic trend charts. A storage module, electrically connected to the MCU, is used to store user data and diabetes risk assessment algorithm models; A power module is used to supply power to the electronic scale.

[0022] The above hardware facilities can be referenced in the configuration information in Table 1 below: Module Name Function Description Specific component examples Weighing module Collect user weight data An array consisting of four high-precision pressure sensors (range 0-150kg, accuracy ±0.1kg). Body fat measurement module Collect user body composition data such as body fat percentage and muscle mass Bioelectrical impedance analysis (BIA) module (frequency 50kHz, current ≤1mA, accuracy ±0.5%) Height measurement module Collect user height data to provide height information for BMI calculation. An infrared laser ranging module can be used (installed on the top of the scale, measuring range 60-200cm, accuracy ±0.5cm). Waist measurement module Collect user waist circumference data Infrared laser ranging module (installed on both sides of the scale body, measuring range 60-120cm, accuracy ±0.5cm) AI voice interaction module Achieve natural language interaction (input parameters, output results), including voice feedback for abnormal data retesting reminders, BMI classification prompts, abnormal waist circumference reminders, and personalized management suggestions. Microphone (pickup range 0-5m, signal-to-noise ratio ≥60dB), speaker (output power 2W), voice processing SoC with NPU (such as RK3588, supporting real-time ASR / TTs) Microcontroller (MCU) It controls the collaborative work of various modules, processes data, runs risk assessment algorithms, performs abnormal data retesting and judgment, BMI classification assessment, waist circumference abnormality detection, and generates personalized weight management suggestions. STM32H7 series MCU (400MHz clock speed, supports floating-point operations, built-in 1MB Flash) Display module The system provides visual displays of data such as weight, body fat percentage, waist circumference, and diabetes risk, as well as guidance for retesting abnormal data, BMI classification results, waist circumference comparison charts, and dynamic trend charts. 2.8-inch OLED screen (resolution 320×240, brightness ≥300cd / m²) Storage module Store user data (weight, body fat, waist circumference, risk assessment results, etc.) and algorithm models. 16GB eMMC Flash (supports power-off data retention, read / write speed ≥100MB / s) Communication module Achieve data synchronization (with mobile app / cloud). Bluetooth 5.3 module (transmission rate ≥ 2Mbps) + WiFi 6 module (supports 2.4G / 5G bands) Power module Power the system Rechargeable lithium battery (3000mAh capacity, 3.7V voltage, supports Type-C fast charging) Table 1 The control and operation process of this electronic scale is divided into six major steps: initialization, data acquisition, voice interaction, risk assessment, result output, and data storage / synchronization, as detailed below: Initialization: After the electronic scale is powered on, the MCU performs self-tests on each module in sequence: the weighing module detects the sensor path by applying a standard resistance signal (response time ≤200ms), the body fat measurement module outputs a 50kHz test current to detect the conductivity of the BIA electrode, the waist circumference measurement module emits a laser beam to detect the echo signal of the distance sensor (distance error ≤0.5cm), the voice module detects the microphone and speaker circuit by playing a 1kHz calibration tone, and the display module lights up the full pixel to detect dead pixels on the OLED screen; after all modules pass the self-test (total time ≤3 seconds), it enters standby mode (power consumption ≤10mA).

[0023] Data Acquisition: When the weighing module's four pressure sensors detect a weight change exceeding 5kg, it triggers synchronous acquisition of weight data (sampling frequency 10Hz, average value taken over 2 seconds); simultaneously, the MCU activates the BIA module via the I2C bus, applying a 50kHz, ≤1mA AC current to the metal electrodes of the scale body, acquiring human body impedance values ​​(accuracy ±0.5Ω) and converting them into body fat percentage; the waist circumference measurement module scans the user's waist using infrared laser emitters (wavelength 650nm) on both sides, with the laser receiver acquiring distance data every 10ms, calculating the waist circumference using a triangulation algorithm (taking the maximum value from 3 measurements), and transmitting the data to the MCU via the SPI bus (transmission rate ≥1Mbps); at the same time, the height measurement module is activated, acquiring height data.

[0024] Voice interaction: The MCU sends commands to the voice processing SoC (baud rate 115200bps) via the UART interface, triggering the TTS engine to play guiding voice (such as "Please state your age, gender, and family history of diabetes", with a speech synthesis delay of ≤300ms); the user's voice signal is collected by the microphone array (pickup range 0.5-3m), converted into a digital signal by a 24-bit ADC (sampling rate 16kHz), and then the ASR model (based on Transformer architecture, word error rate ≤5%) is run by the NPU built into the voice processing SoC to convert the continuous voice stream into structured parameters (age / gender / family history), and invalid input is filtered by a verification algorithm (such as age range 18-99 years old, gender binarization), and finally transmitted to the MCU in JSON format.

[0025] Risk assessment: The MCU loads the pre-trained logistic regression model parameters (β0~β5) from the storage module and performs the following calculation process: 1. Feature preprocessing: Perform range validation on height H (voice input, unit m) (1.2-2.2m), calculate BMI=W / H² (retain 2 decimal places); perform gender-specific correction on waist circumference WC (males ≥90cm are considered abnormal, females ≥85cm are considered abnormal). 2. Parameter normalization: BMI (30→1.0), WC (100cm→1.0), and age A (60 years→1.0) were normalized to min-max according to the clinical data distribution, while family history F and gender G were kept in binary encoding; 3. Weighted summation: Calculate the linear combination S = β0 + β1 × BMI + β2 × WC + β3 × A + β4 × G + β5 × F (where β0 = -5.2, β1 = 0.15, β2 = 0.08, β3 = 0.06, β4 = 0.3, β5 = 0.5). 4. Probability conversion: The risk probability is calculated using the Sigmoid function R=1 / (1+e^(-S)). When R≥0.25, it is judged as high risk (corresponding to the clinical prediabetes threshold).

[0026] Results Output: The display module uses a partitioned display: the top column displays weight (70.5kg) and body fat percentage (23.2%), the middle column displays BMI (24.1, normal range 18.5-23.9) and waist circumference (82cm), and the bottom column displays the risk probability in the form of a progress bar and numbers (e.g., "Diabetes risk: 12%"). The voice processing SoC converts the structured results into natural language (TTS synthesis speed ≥150 words / minute) and outputs it through the speaker (volume ≥65dB), simultaneously broadcasting BMI classification prompts and waist circumference abnormality reminders (e.g., "Your BMI is 24."). 1. "Belongs to the overweight range; waist circumference 82cm, within the normal range"); When an abnormal BMI (<18.5 or ≥24) or excessive waist circumference (≥90cm for men / ≥85cm for women) is detected, a retest reminder is triggered (e.g., "Abnormal data detected, it is recommended to adjust your posture and retest"). If the abnormality is still detected after retesting, personalized management suggestions are pushed (e.g., "The retested BMI is still 25.3, it is recommended to reduce daily calorie intake by 500kcal and perform HIIT training 3 times a week"). Voice command interaction is also supported (e.g., when the user asks "How to lower BMI", a preset knowledge base answer is triggered).

[0027] Data storage / synchronization: The MCU encapsulates user data in JSON format (including W, BF, WC, A, G, F, R and timestamp), and writes it to eMMC Flash via the SPI interface (erasure / write life ≥ 100,000 times), using a circular storage strategy (maximum retention of 1000 records); when the communication module detects a Bluetooth connection from the mobile APP (after successful pairing code verification), it automatically synchronizes the data of the last 7 days (transmission rate ≥ 2Mbps); the WiFi module encrypts and uploads historical data to the cloud at 3 AM every day (during network off-peak hours) (AES-128 encryption), allowing doctors to access trend curves (such as weekly BMI change rate) through the hospital HIS system.

[0028] The diabetes risk assessment algorithm uses a logistic regression model (a clinically validated, highly accurate model), and the formula is as follows: , Parameter definition: (R): Probability of diabetes risk (0≤R≤1, the larger the R, the higher the risk). (e): Natural Index (approximately 2.718); : Intercept term (constant, obtained from training with clinical data); Regression coefficients (corresponding to the weights of BMI, WC, A, G, and F, obtained through training with a logistic regression algorithm, and statistically significant, P<0.05); (BMI): Body Mass Index (kg / m², calculated by dividing weight W by the square of height H); (WC): Waist circumference (cm, collected by the waist circumference measurement module); (A): Age (in years, input by user's voice); (G): Gender (binary variable, 1 = male, 0 = female, input by user voice). (F): Family history of diabetes (binary variable, 1 = immediate family member (parents / children / siblings) has diabetes, 0 = none, input by user voice).

[0029] The specific model mechanism and training are as follows: Model Training: The following steps were used to construct a diabetes risk assessment model: (1) Data collection: 10,000 clinical samples were collected (5,000 patients with type 2 diabetes / 5,000 healthy controls), including characteristics such as body mass index (BMI), waist circumference (WC), age (A), gender (G), family history (F) and disease labels (1 = diseased / 0 = healthy). (2) Data preprocessing: Z-score standardization (mean=0, standard deviation=1) is performed on continuous features (BMI / WC / A), median imputation is used for missing values ​​(missing rate<2%), and outliers (e.g. WC>150cm) are truncated using the IQR method. (3) Feature engineering: Construct feature matrix X (10000×5), which includes BMI, WC, A, G (one-hot encoding), and F (one-hot encoding); (4) Model training: The LogisticRegression module of the scikit-learn library was used, and 5-fold cross-validation was adopted (80% of the training set and 20% of the validation set). The optimization objective was to maximize the AUC, and the regularization parameter C=1.0 (L2 regularization). (5) Model evaluation: Test set verification performance, for example: AUC=0.87 (95%CI: 0.85-0.89), accuracy=0.82, recall=0.78, F1-score=0.80; specific curves can be generated by the user, etc.

[0030] (6) Parameter solidification: The regression coefficients (β0=-5.2, β1=0.15, β2=0.08, β3=0.06, β4=0.3, β5=0.5) obtained from training are stored in the Flash memory of the MCU. The model file size is ≤512KB.

[0031] Detailed steps for the integrated BMI health management control and operation process: 1. Initialization self-test: Each module completes the path test (e.g., the response time of the weighing module is ≤200ms), and enters the standby state in a total time of ≤3 seconds to ensure that the hardware required for BMI calculation is ready.

[0032] 2. Data acquisition trigger: When the weighing module detects a weight change of more than 5kg, it simultaneously starts body fat measurement (50kHz test current, accuracy ±0.5Ω) and waist circumference laser scanning (wavelength 650nm, distance error ≤0.5cm), and collects the user's height through the AI ​​voice interaction module (voice input, such as "height 1.75 meters").

[0033] 3. Real-time BMI calculation: The MCU receives weight (e.g., 70.5kg) and height (1.75m) data, executes the formula BMI=weight (kg) / height (m)², calculates BMI=70.5 / (1.75×1.75)=23.0 (rounded to one decimal place), and automatically matches it with the Chinese standard classification (18.5-23.9 is normal, 24-27.9 is overweight, and ≥28 is obese).

[0034] 4. Risk assessment linkage: Input the BMI value (e.g., 23.0) into the logistic regression model, and calculate the probability of diabetes risk by weighting it with parameters such as waist circumference (e.g., 82cm) and age (e.g., 45 years old), and simultaneously complete the BMI health status judgment (23.0 in the example is within the normal range).

[0035] 5. Multimodal output results: - The BMI value and category are clearly marked in the middle column of the display module ("BMI: 23.0 (normal range 18.5-23.9)"). - Differentiated voice prompts: When within the normal range, the prompt reads, "Your BMI is 23.0, which is within the healthy range. We recommend maintaining 150 minutes of moderate-intensity exercise per week." If overweight (e.g., BMI=25.5), the prompt reads, "Your BMI is 25.5, which is overweight. We recommend reducing refined sugar intake and increasing aerobic exercise such as brisk walking and swimming." When an abnormal BMI (<18.5 or ≥24) or excessive waist circumference (men ≥90cm / women ≥85cm) is detected, a retest reminder is triggered: "Your BMI / waist circumference is outside the normal range. We recommend adjusting your posture and retesting to confirm data accuracy." If the retest is still abnormal, the prompt is reinforced: "The retest results still show abnormality. You need to: 1. Reduce your daily calorie intake by 500kcal; 2. Perform HIIT training 3 times a week; 3. Aim for a weight loss of 1-2kg per month. Do you need a detailed plan?" - Supports voice interaction query: When a user asks "Is my BMI normal?", the system will immediately reply "Your current BMI is 23.0, which is within the normal range of 18.5-23.9. Your body fat percentage is 23.2%, and your physical condition is good."

[0036] 6. Data Storage and Trend Analysis: BMI data (including calculation process and category labels) is encapsulated in JSON format (e.g., {"BMI":23.0,"category":"normal","calculation":"70.5 / (1.75²)"}), and stored synchronously with diabetes risk values ​​in eMMC Flash. The HIS system can access the weekly BMI change curve (e.g., a BMI fluctuation of ≤0.5 over the past 4 weeks indicates stability). The upgraded health management solution includes: automatically generating a monthly health progress report (integrating BMI trends, changes in diabetes risk, and improvements in key indicators, such as a 12% decrease in diabetes risk value from 24.2 to 23.0 this month); intelligently pushing optimization suggestions for the following month based on trend data (e.g., recommending two 30-minute aerobic exercise sessions per week for users with a slight increase in BMI, and recommending a combination of abdominal breathing and core muscle training for users with excessive waist circumference), with suggestions matching users' daily habits by more than 85%.

[0037] The entire process, from data collection to result feedback, takes ≤8 seconds. Through the linkage assessment of BMI and diabetes risk, a closed loop of health management, namely “measurement-calculation-assessment-intervention”, is achieved. Example

[0038] Example 1: A 45-year-old male patient (height 1.75m, weight 85kg, waist circumference 95cm, father has diabetes) Data collection: weight W=85kg→BMI=85 / (1.75)²=27.8kg / m², waist circumference WC=95cm, voice input age A=45 years old, gender G=1 (male), family history F=1 (yes); Risk calculation: S = -5.2 + 0.15 × 27.8 + 0.08 × 95 + 0.06 × 45 + 0.3 × 1 + 0.5 × 1 = 3.27 → R = 1 / (1 + e -3.27 =96.3%; Output results: The display module prompts "Diabetes risk: 96.3% (high risk)", and the voice feedback is "Your risk is high, and it is recommended to undergo an oral glucose tolerance test within 3 months".

[0039] Example 2: A 30-year-old female patient (height 1.60m, weight 55kg, waist circumference 70cm, no family history) Data collection: weight W=55kg→BMI=55 / (1.60)²=21.5kg / m², waist circumference WC=70cm, voice input age A=30 years old, gender G=0 (female), family history F=0 (none); Risk calculation: S = -5.2 + 0.15 × 21.5 + 0.08 × 70 + 0.06 × 30 + 0.3 × 0 + 0.5 × 0 = -1.83 → R = 1 / (1 + e^1.83) = 14.2%; Output: The display module prompts "Diabetes risk: 14.2% (low risk)", and the voice feedback is "Your risk is low, and it is recommended to maintain 150 minutes of moderate-intensity exercise per week".

[0040] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0041] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0042] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0043] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0044] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0045] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0046] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0047] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0048] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0049] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0050] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A health weight management electronic scale that combines diabetes risk assessment and AI voice interaction, characterized in that, The electronic scale includes: The weighing module is used to collect the user's weight data; The body fat measurement module is used to collect users' body fat percentage data; Waist measurement module, used to collect user waist measurement data; The AI ​​voice interaction module is used to realize natural language input (age, gender, family history of diabetes) and result output; The microcontroller (MCU) is electrically connected to the weighing module, body fat measurement module, waist circumference measurement module, and AI voice interaction module, respectively, and is used to control the collaborative work of each module, process data, and run the diabetes risk assessment algorithm. The communication module (Bluetooth 5.3 + WiFi 6) is used to synchronize user data to a mobile app or cloud server. The display module is electrically connected to the MCU and is used to visually display data such as weight, body fat percentage, waist circumference, and diabetes risk. A storage module, electrically connected to the MCU, is used to store user data and diabetes risk assessment algorithm models; A power module is used to supply power to the electronic scale.

2. The electronic scale according to claim 1, characterized in that, The diabetes risk assessment algorithm uses a logistic regression model, and the formula is as follows: In the formula: (R) represents the probability of diabetes risk (0≤R≤1); (e) is the natural index; These are the regression coefficients; (BMI) is the body mass index (kg / m², calculated by dividing weight by the square of height). (WC) is waist circumference (cm); (A) represents age (in years); (G) represents gender (1 = male / 0 = female); (F) indicates a family history of diabetes (1 = family member with the disease / 0 = no family history).

3. The electronic scale according to claim 1, characterized in that, The weighing module is an array of four high-precision pressure sensors with a weighing range of 0-150kg.

4. The electronic scale according to claim 1, characterized in that, The body fat measurement module is a bioelectrical impedance analysis (BIA) module with a frequency of 50kHz and a current of ≤1mA.

5. The electronic scale according to claim 1, characterized in that, The waist circumference measurement module is an infrared laser ranging module, installed on both sides of the scale body, with a measurement range of 60-120cm.

6. The electronic scale according to claim 1, characterized in that, The AI ​​voice interaction module includes a microphone, a speaker, and a voice processing SoC with an NPU.

7. The electronic scale according to claim 1, characterized in that, The display module is a 2.8-inch OLED screen with a resolution of 320×240.

8. The electronic scale according to claim 1, characterized in that, The power module is a rechargeable lithium battery with a capacity of 3000mAh, supporting Type-C fast charging.

9. The electronic scale according to claim 1, characterized in that, The regression coefficients of the diabetes risk assessment algorithm The data was trained using at least 10,000 clinical data, including at least 5,000 patients with type 2 diabetes and at least 5,000 healthy individuals, with an AUC ≥ 0.

85.

10. The electronic scale according to claim 1, characterized in that, The AI ​​voice interaction module supports real-time ASR (Automatic Speech Recognition) and TTS (Text-to-Speech).

Images