User health monitoring method and system based on intelligent ring and multi-modal data

Abstract

The invention discloses a user health monitoring method and system based on an intelligent ring and multi-modal data. The method comprises the following steps: acquiring multi-modal sensing data of a target user through the intelligent ring; based on a preset feature extraction algorithm, extracting a health feature parameter corresponding to each piece of sensing data; based on a health baseline corresponding to the target user, according to the health feature parameters, determining health scores of multiple dimensions of the target user; and calculating a health score corresponding to the target user based on a weight rule according to the health scores of the multiple dimensions of the target user. Therefore, accurate health assessment based on multi-modal data and baseline comparison can be realized, the comprehensiveness and accuracy of user health monitoring are improved, and the risk of score deviation caused by data noise or improper dimension weight is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a user health monitoring method and system based on a smart ring and multimodal data. Background Technology

[0002] With the rapid popularization of wearable devices in the field of health monitoring, users and medical institutions are increasingly emphasizing the use of multimodal data for accurate health assessments. Among these challenges, accurately and timely monitoring of users' health levels has become a key technical issue. Current technologies typically collect sensor data from single or limited modalities using smart wearable devices, employing fixed threshold analysis or simple weighting methods to calculate health indicators and determine a user's health status. However, existing solutions lack comprehensive feature extraction and dynamic baseline comparison of multimodal data, making it difficult to accurately determine multi-dimensional health scores and optimize weight allocation. They also fail to adapt to individual differences and data noise, resulting in insufficient comprehensiveness and accuracy in health assessments. Furthermore, improper dimensional weighting or noise interference can easily lead to scoring biases, limiting the reliability and effectiveness of user health monitoring. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a user health monitoring method and system based on smart rings and multimodal data, which can realize accurate health assessment based on multimodal data and baseline comparison, improve the comprehensiveness and accuracy of user health monitoring, and reduce the risk of scoring deviation caused by data noise or improper dimensional weights.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a user health monitoring method based on a smart ring and multimodal data, the method comprising: Acquire multimodal sensor data of the target user through a smart ring; Based on a preset feature extraction algorithm, health feature parameters corresponding to each of the sensor data are extracted. Based on the health baseline corresponding to the target user, and according to the health feature parameters, determine the health scores of the target user in multiple dimensions; Based on the target user's health scores across multiple dimensions, a corresponding health score is calculated using weighted rules.

[0005] As an optional implementation, in a first aspect of the invention, the smart ring is provided with a plurality of sensors; the sensors are photoelectric sensors, motion sensors, temperature sensors or bioimpedance sensors.

[0006] As an optional implementation, in the first aspect of the present invention, the sensing data is heart rate data, heart rate variability data, blood oxygen saturation data, activity intensity data, step count data, sleep stage data, exercise pattern data, wrist skin temperature, fingertip skin temperature, respiratory rate data, or pressure level data.

[0007] As an optional implementation, in the first aspect of the present invention, the step of extracting health feature parameters corresponding to each of the sensing data based on a preset feature extraction algorithm includes: Each of the aforementioned sensor data is cleaned and / or filtered to obtain the corresponding processed data; For each piece of processed data, features are extracted from the processed data according to the feature extraction algorithm corresponding to the data type, so as to obtain the corresponding health feature parameters.

[0008] As an optional implementation, in the first aspect of the present invention, the health characteristic parameters are resting heart rate parameters, RMSSD parameters, deep sleep duration parameters, mid-sleep mean blood oxygenation parameters, or body temperature amplitude parameters.

[0009] As an optional implementation, in the first aspect of the present invention, determining the health score of the target user across multiple dimensions based on the health baseline corresponding to the target user and according to the health feature parameters includes: For each dimension, the health baseline parameters of the target user corresponding to that dimension are determined; the health baseline parameters are determined based on the target user's historical sensor data. The health score corresponding to this dimension is determined based on the health feature parameters corresponding to this dimension and the health baseline parameters.

[0010] As an optional implementation, in the first aspect of the present invention, determining the health score corresponding to the dimension based on the health feature parameters corresponding to the dimension and the health baseline parameters includes: Calculate the degree of difference between the health characteristic parameter and the health baseline parameter corresponding to this dimension; The difference is input into the score calculation algorithm model corresponding to the dimension to obtain the health score corresponding to the dimension.

[0011] As an optional implementation, in the first aspect of the present invention, the step of calculating the health score corresponding to the target user based on multiple dimensions of the target user's health score and weighting rules includes: Calculate the product of the health score of each dimension of the target user and the weight corresponding to that dimension to obtain the dimension weight score corresponding to each dimension; Calculate the sum of the dimension weight scores for all dimensions, and then calculate the health score for the target user.

[0012] A second aspect of this invention discloses a user health monitoring system based on a smart ring and multimodal data, the system comprising: The acquisition module is used to acquire sensor data of multiple modalities of the target user through the smart ring; The extraction module is used to extract the health feature parameters corresponding to each of the sensor data based on a preset feature extraction algorithm; The determination module is used to determine the health scores of the target user in multiple dimensions based on the health baseline corresponding to the target user and according to the health feature parameters. The scoring module is used to calculate the health score corresponding to the target user based on the target user's health scores in multiple dimensions and weighted rules.

[0013] As an optional implementation, in a second aspect of the invention, the smart ring is provided with a plurality of sensors; the sensors are photoelectric sensors, motion sensors, temperature sensors or bioimpedance sensors.

[0014] As an optional implementation, in a second aspect of the invention, the sensing data is heart rate data, heart rate variability data, blood oxygen saturation data, activity intensity data, step count data, sleep stage data, exercise pattern data, wrist skin temperature, fingertip skin temperature, respiratory rate data, or pressure level data.

[0015] As an optional implementation, in a second aspect of the present invention, the extraction module extracts the health feature parameters corresponding to each of the sensing data based on a preset feature extraction algorithm in the following specific ways: Each of the aforementioned sensor data is cleaned and / or filtered to obtain the corresponding processed data; For each piece of processed data, features are extracted from the processed data according to the feature extraction algorithm corresponding to the data type, so as to obtain the corresponding health feature parameters.

[0016] As an optional implementation, in the second aspect of the present invention, the health characteristic parameters are resting heart rate parameters, RMSSD parameters, deep sleep duration parameters, mid-sleep mean blood oxygenation parameters, or body temperature amplitude parameters.

[0017] As an optional implementation, in a second aspect of the invention, the determining module determines the health scores of the target user across multiple dimensions based on the target user's corresponding health baseline and according to the health feature parameters, including: For each dimension, the health baseline parameters of the target user corresponding to that dimension are determined; the health baseline parameters are determined based on the target user's historical sensor data. The health score corresponding to this dimension is determined based on the health feature parameters corresponding to this dimension and the health baseline parameters.

[0018] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module determines the health score corresponding to the dimension based on the health feature parameters corresponding to the dimension and the health baseline parameters includes: Calculate the degree of difference between the health characteristic parameter and the health baseline parameter corresponding to this dimension; The difference is input into the score calculation algorithm model corresponding to the dimension to obtain the health score corresponding to the dimension.

[0019] As an optional implementation, in a second aspect of the invention, the scoring module calculates the health score corresponding to the target user based on multiple dimensions of the target user's health score and weighting rules, including: Calculate the product of the health score of each dimension of the target user and the weight corresponding to that dimension to obtain the dimension weight score corresponding to each dimension; Calculate the sum of the dimension weight scores for all dimensions, and then calculate the health score for the target user.

[0020] A third aspect of this invention discloses another user health monitoring system based on a smart ring and multimodal data, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the user health monitoring method based on smart rings and multimodal data disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the user health monitoring method based on smart rings and multimodal data disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention acquires multimodal sensor data of target users through a smart ring and extracts health feature parameters. It combines this data with a health baseline to determine multidimensional health scores and calculates health ratings based on weighting rules. This enables accurate health assessment based on multimodal data and baseline comparison, improves the comprehensiveness and accuracy of user health monitoring, and reduces the risk of scoring bias caused by data noise or improper dimensional weighting. Attached Figure Description

[0023] 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.

[0024] Figure 1 This is a flowchart illustrating a user health monitoring method based on a smart ring and multimodal data, as disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of the structure of a user health monitoring system based on a smart ring and multimodal data disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another user health monitoring system based on a smart ring and multimodal data disclosed in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] This invention discloses a user health monitoring method and system based on a smart ring and multimodal data. The method acquires multimodal sensor data of the target user through a smart ring and extracts health feature parameters. Combined with a health baseline, a multi-dimensional health score is determined, and a health rating is calculated based on weighted rules. This enables accurate health assessment based on multimodal data and baseline comparison, improving the comprehensiveness and accuracy of user health monitoring and reducing the risk of scoring bias due to data noise or improper dimensional weights. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a user health monitoring method based on a smart ring and multimodal data, as disclosed in an embodiment of the present invention. Figure 1 The described user health monitoring method based on smart rings and multimodal data can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 1 As shown, this user health monitoring method based on smart rings and multimodal data may include the following operations: 101. Acquire sensor data of multiple modalities of the target user through a smart ring.

[0032] Optionally, the smart ring is equipped with multiple sensors.

[0033] Optionally, the sensor may be a photoelectric sensor, a motion sensor, a temperature sensor, or a bioimpedance sensor.

[0034] Optional sensor data may include heart rate data, heart rate variability data, blood oxygen saturation data, activity intensity data, step count data, sleep stage data, exercise pattern data, wrist skin temperature, fingertip skin temperature, respiratory rate data, or stress level data.

[0035] Specifically, the smart ring integrates multimodal sensors to collect raw physiological signals, including but not limited to: Photoelectric sensor (PPG): Used to monitor heart rate (HR), heart rate variability (HRV), and blood oxygen saturation (SpO2).

[0036] Triaxial accelerometer and gyroscope: Used to monitor activity intensity, steps, sleep stages (based on body motion analysis), and movement pattern recognition.

[0037] Temperature sensor: Used to monitor the skin temperature of the wrist or fingertips and its nighttime variation trends.

[0038] Bioimpedance sensor: Used to monitor respiratory rate and pressure levels (based on skin conductance response).

[0039] 102. Based on the preset feature extraction algorithm, extract the health feature parameters corresponding to each sensor data.

[0040] 103. Based on the target user's corresponding health baseline, determine the target user's health scores in multiple dimensions according to health characteristic parameters.

[0041] 104. Based on the target user's health scores across multiple dimensions, calculate the target user's corresponding health score according to weighting rules.

[0042] As can be seen, the above-mentioned embodiments of the invention acquire multimodal sensor data of the target user through a smart ring and extract health feature parameters. Combined with a health baseline, a multidimensional health score is determined and a health score is calculated based on weight rules. This enables accurate health assessment based on multimodal data and baseline comparison, improves the comprehensiveness and accuracy of user health monitoring, and reduces the risk of scoring deviation caused by data noise or improper dimension weights.

[0043] As an optional embodiment, the step above, extracting health feature parameters corresponding to each sensor data point based on a preset feature extraction algorithm, includes: Each sensor data point is cleaned and / or filtered to obtain the corresponding processed data. For each piece of processed data, features are extracted from the processed data according to the feature extraction algorithm corresponding to the data type, so as to obtain the corresponding health feature parameters.

[0044] Optional health characteristic parameters include resting heart rate, RMSSD, deep sleep duration, mid-sleep mean blood oxygenation, or body temperature amplitude.

[0045] Specifically, algorithms used for heart rate (HR) feature extraction may include: The raw PPG signal was filtered using a bandpass filter (0.5Hz–4Hz); Heart rate peaks are extracted using peak detection algorithms, such as the R-peak detection method based on adaptive thresholds. Calculate the number of heartbeats over a preset time period and remove abnormal peaks based on signal stability.

[0046] Specifically, feature extraction algorithms for heart rate variability (HRV / RMSD) feature extraction may include: Based on the inter-Beat Interval (IBI) sequences detected by PPG; Use RMSSD = √(average value (ΔNN²)); Artifact removal is performed on the NN interval, such as using a 20% threshold to remove data points with extreme fluctuations.

[0047] Specifically, feature extraction algorithms, particularly those for sleep feature extraction, may include: The characteristic durations of accelerometer activity index, heart rate fluctuations, and body temperature changes were calculated comprehensively. Sleep stages (awake / light sleep / deep sleep) are identified by a 30-second sliding window pattern. Deep sleep characteristics can be calculated as the total duration of the segment consisting of "low heart rate + low body movement + stable body temperature".

[0048] Specifically, the feature extraction algorithm used for blood oxygen (SpO2) feature extraction may include: Calculate the red light / infrared light ratio R = (AC_red / DC_red) / (AC_IR / DC_IR); Blood oxygen saturation values ​​are calculated based on calibration curves; The abnormal amplitude points are smoothed using a moving median filter.

[0049] Specifically, feature extraction algorithms, particularly those for extracting body temperature features, may include: Use moving average filtering (such as 5-point averaging) to eliminate instantaneous measurement noise; Calculate body temperature amplitude = maximum body temperature that evening – minimum body temperature; Furthermore, the slope of the body temperature trend can be extracted as an additional feature.

[0050] As can be seen, through the above optional embodiments, health feature parameters are obtained based on the feature extraction algorithm corresponding to the data type after data cleaning and / or filtering of each type of sensor data. Thus, on the basis of accurate health assessment, the purity and reliability of feature parameters are improved through data preprocessing and targeted extraction, providing high-quality data support for health score calculation and reducing the risk of feature misjudgment caused by interference from the original data.

[0051] As an optional embodiment, the step described above, determining the target user's health score across multiple dimensions based on the target user's corresponding health baseline and according to health characteristic parameters, includes: For each dimension, determine the health baseline parameters for the target user corresponding to that dimension; Optionally, the health baseline parameters are determined based on the target user's historical sensor data; The health score corresponding to this dimension is determined based on the health characteristic parameters and the health baseline parameters.

[0052] As can be seen, through the above optional embodiments, by determining the health baseline parameters for each dimension based on the target user's historical sensor data and calculating the health score in combination with health feature parameters, the personalization and accuracy of the score assessment are improved by baseline comparison on the basis of accurate multi-dimensional health score determination, providing a scientific basis for health scoring and reducing the risk of health assessment errors caused by inaccurate baselines.

[0053] As an optional embodiment, the step above, determining the health score corresponding to the dimension based on the health feature parameters and the health baseline parameters, includes: Calculate the degree of difference between the health characteristic parameters and the health baseline parameters corresponding to this dimension; The difference is input into the score calculation algorithm model corresponding to that dimension to obtain the health score corresponding to that dimension.

[0054] Specifically, the dimensions of this health score can be sleep dimension, activity dimension, or physical recovery dimension.

[0055] Optionally, the formula for calculating the degree of difference can be: Difference = (Eigenvalue - Baseline value) / Baseline value.

[0056] Optionally, if the difference exceeds 20%, it can be considered a significant deviation from the interval and the weight can be increased.

[0057] Optionally, the score calculation algorithm model can adopt a linear normalization model with upper and lower bounds: Where k represents the sensitivity coefficients for different dimensions, for example: Sleep dimension: k=60; Activity dimension: k=40; Heart rate dimension: k=50; HRV dimension: k=70.

[0058] Specifically, each dimension (such as activity, sleep, recovery, and stress) ultimately outputs a health score between 0 and 100.

[0059] As can be seen, through the above optional embodiments, by calculating the difference between health feature parameters and health baseline parameters and inputting them into the corresponding dimension score calculation algorithm model to obtain a health score, the accuracy and interpretability of the score calculation are improved by difference quantification and model mapping on the basis of accurate health score calculation, providing a reliable output for multi-dimensional health assessment and reducing the risk of score error caused by calculation model bias.

[0060] As an optional embodiment, the step above, calculating the target user's health score based on multiple dimensions of the target user's health score and weighting rules, includes: Calculate the product of the health score of each dimension of the target user and the weight corresponding to that dimension to obtain the dimension weight score for each dimension. Calculate the sum of the dimensional weight scores for all dimensions, and calculate the health score for the target user.

[0061] Specifically, an example of dimensional weighting could be: sleep quality 40%, activity level 25%, physical recovery (including HRV and resting heart rate) 25%, and physiological stability (body temperature, SpO2, etc.) 10%.

[0062] Optionally, the formula for calculating the total score can be: ; For example: The score for the sleep dimension is 85 × 0.4 = 34. Score for the activity dimension: 72 × 0.25 = 18; The score for the recovery dimension is: 69 × 0.25 = 17.25; The score for the physiological stability dimension is 90 × 0.1 = 9; the score calculation process is as follows: ; The final score can be rounded up to 78.

[0063] Optionally, the weights can be automatically adjusted based on the following factors: Is the user sick this week? Has HRV continued to decline over the past 3 days? Has your sleep decreased dramatically? Does excessive exercise lead to fatigue? For example, if a user is in the "physical recovery period", the system will increase the weight of the recovery dimension (e.g., from 25% to 40%) and decrease the weight of the activity dimension.

[0064] As can be seen, through the above optional embodiments, a health score is obtained by summing the product of the health score of each dimension and its corresponding weight. Based on the accurate calculation of the health score, the comprehensiveness and balance of the score result are improved by optimizing the weight rules, providing an overall quantitative indicator for the user's health status and reducing the risk of score distortion caused by improper allocation of dimension weights.

[0065] As an optional embodiment, the method further includes: Determine whether the target user's health score is lower than the historical health score and whether the difference between the two scores is greater than a preset difference threshold. If so, generate health suggestions for the target user based on the health score of at least one dimension.

[0066] Specifically, the system can filter out the dimensions corresponding to scores below a preset threshold from all health scores of the target user, identify these as unhealthy dimensions for the target user, and then generate health recommendations corresponding to the unhealthy dimensions based on the preset correspondence between dimensions and health recommendations.

[0067] In one specific implementation scheme, an AI scoring system based on multimodal health data fusion using a smart ring is implemented based on the technical solution in this embodiment. It primarily utilizes the smart ring to collect multi-dimensional physiological data from users and performs data fusion and analysis through artificial intelligence (AI) algorithms to ultimately generate an intuitive and personalized wellness score. Specifically, in the application scenarios of this system, ordinary users face the following core pain points: 1. Data Overload and Difficulty in Interpretation: The device provides massive amounts of isolated raw data (such as "1.5 hours of deep sleep last night" and "average heart rate 55 bpm"). Users lack medical knowledge and cannot understand the actual meaning of this data, let alone synthesize these indicators to assess their overall health.

[0068] 2. Lack of personalized baselines: Existing scoring systems mostly use general standards (such as the "10,000 steps goal"). However, everyone's physical condition, age, genes, and lifestyle are vastly different, and a fixed standard cannot scientifically measure individual health changes. For example, the same resting heart rate represents completely different health levels for professional athletes and sedentary office workers.

[0069] 3. Delayed feedback and lack of insight: Users can usually only see a summary of data from the past day or week, which is a "hindsight" report that cannot provide forward-looking, actionable insights to help users improve their health.

[0070] 4. Difficulty in maintaining motivation: A dry list of data is unlikely to create effective positive incentives, and users are likely to lose interest in wearing and paying attention to the product for a long time.

[0071] Therefore, there is an urgent need for a health assessment system that can transform complex data into a simple, intuitive, personalized, and motivating system. Smart rings, due to their ability to be worn continuously 24 / 7 and their high measurement accuracy, are the best hardware platform for realizing this system.

[0072] Specifically, at the system architecture level, the system includes: Data acquisition layer (smart ring): Responsible for collecting the above-mentioned multi-dimensional raw physiological data seamlessly and continuously.

[0073] Data preprocessing and feature extraction layer (terminal / cloud): Cleans and filters the raw data and extracts key feature values ​​(such as average resting heart rate, RMSSD value of HRV, deep sleep duration, average blood oxygen during sleep, body temperature amplitude, etc.).

[0074] And, the AI ​​health scoring engine (cloud-based), which is the core of the system, includes: Personalized baseline model: The system establishes an independent health baseline for each user. This baseline is not a fixed value, but is dynamically generated through the user's own data during the initial learning period (e.g., 2-4 weeks) and continues to evolve.

[0075] Multimodal data fusion algorithms: These algorithms use machine learning models (such as gradient boosting trees and neural networks) or weighted fusion algorithms to comprehensively calculate feature values ​​from different dimensions. For example, the score = (sleep score * weight W1) + (activity score * weight W2) + (physical recovery score * weight W3) + ... Specifically, the weights can be dynamically adjusted based on the season and the user's status (such as whether they are sick).

[0076] Health score generator: Maps the merged results to an intuitive score (e.g., 0-100 points) or grade (e.g., excellent, good, average, poor).

[0077] Application Presentation Layer (APP): Displays the scores and their components in a visual manner (such as scores, trend charts, radar charts), and generates personalized "health improvement suggestions" based on the score results.

[0078] Specifically, the algorithm scoring process executed by this system includes: S1: Multi-dimensional data collection: The smart ring continuously collects the user's physiological activity data.

[0079] S2: Local Preprocessing and Upload: The ring or mobile app performs preliminary data processing and uploads it to the cloud server.

[0080] S3: Personalized Feature Extraction and Baseline Comparison: The cloud engine extracts daily features and compares them with the user's personal health baseline. For example, "Today's HRV has decreased by 15% compared to the personal baseline."

[0081] S4: Multimodal data fusion and AI score calculation: The AI ​​engine integrates the comparison results of all dimensions to calculate a comprehensive health score.

[0082] Let's take a user as an example to illustrate the implementation process of this system: 1. The user has been wearing the smart ring for more than a month, and the system has established a stable personal health baseline for them (e.g., average resting heart rate of 58, average HRV of 55ms, and average deep sleep of 1 hour and 45 minutes).

[0083] 2. One day, a user stayed up late for work. The next day, the system data showed that the user's resting heart rate had increased to 63, HRV had decreased to 48ms, and deep sleep lasted only 1 hour.

[0084] 3. The cloud-based AI engine compares this data with the individual's baseline and finds that many indicators deviate significantly from the normal range.

[0085] 4. The engine calculated the overall health score for the day using weighted averages, resulting in a score of 65 (a significant decrease from the previous day's 85).

[0086] 5. The system analysis revealed that the main reasons for the score decline were abnormalities in the "physical recovery" and "sleep" dimensions. Based on the data, a specific suggestion was generated: "Your body has not fully recovered, mainly due to insufficient sleep and poor sleep quality. It is recommended to avoid caffeine tonight and try to go to bed 30 minutes earlier than usual." 6. When users see this score and suggestions on the app's homepage, they can immediately understand the impact of their behavior from the previous night on their health and are more willing to follow the recommendations for adjustments. Through this immediate and positive feedback loop, the system helps users continuously improve their health behaviors.

[0087] Compared with the prior art, the technical solution in this embodiment has the following advantages: 1. Intuitive and easy to understand: Transforming complex data into a simple score greatly lowers the cognitive threshold for users, making their health status clear at a glance.

[0088] 2. Highly Personalized: The rating is based on the user's own dynamic baseline, rather than a universal standard, making the assessment results more scientific and accurate, and truly reflecting "your own health".

[0089] 3. Comprehensive and integrated: It integrates data from multiple dimensions such as sleep, activity, cardiovascular function, and stress, avoiding the one-sidedness of assessment based on a single indicator.

[0090] 4. Positive Incentives and Behavioral Guidance: Gamified score design can effectively motivate users to pay attention to their health and guide them to take improvement measures through specific and feasible suggestions, forming a closed loop of health.

[0091] 5. Proactive Insights: By analyzing long-term trends, the system can provide early warnings of subtle changes in health risks (such as a persistent decline in HRV) before users experience significant discomfort.

[0092] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a user health monitoring system based on a smart ring and multimodal data, as disclosed in an embodiment of the present invention. Figure 2 The described user health monitoring system based on smart rings and multimodal data can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes local processing servers or cloud processing servers). For example... Figure 2 As shown, the user health monitoring system based on a smart ring and multimodal data may include: The acquisition module 201 is used to acquire sensor data of multiple modalities of the target user through the smart ring.

[0093] The extraction module 202 is used to extract the health feature parameters corresponding to each sensor data based on a preset feature extraction algorithm.

[0094] The determination module 203 is used to determine the health scores of the target user in multiple dimensions based on the target user's corresponding health baseline and according to health characteristic parameters.

[0095] The scoring module 204 is used to calculate the health score corresponding to the target user based on the target user's health scores in multiple dimensions and weighted rules.

[0096] As can be seen, the above-mentioned embodiments of the invention acquire multimodal sensor data of the target user through a smart ring and extract health feature parameters. Combined with a health baseline, a multidimensional health score is determined and a health score is calculated based on weight rules. This enables accurate health assessment based on multimodal data and baseline comparison, improves the comprehensiveness and accuracy of user health monitoring, and reduces the risk of scoring deviation caused by data noise or improper dimension weights.

[0097] As an alternative embodiment, the smart ring is equipped with multiple sensors; the sensors are photoelectric sensors, motion sensors, temperature sensors, or bioimpedance sensors.

[0098] As can be seen, the sensor settings of the smart ring are specified through the above optional embodiments, so that the smart ring can acquire a variety of sensor data that comprehensively characterize the user's health, assist in realizing accurate health assessment based on multimodal data and baseline comparison, improve the comprehensiveness and accuracy of user health monitoring, and reduce the risk of scoring bias caused by data noise or improper dimensional weights.

[0099] As an optional embodiment, the sensing data may be heart rate data, heart rate variability data, blood oxygen saturation data, activity intensity data, step count data, sleep stage data, exercise pattern data, wrist skin temperature, fingertip skin temperature, respiratory rate data, or stress level data.

[0100] As can be seen, the content of the sensor data is defined through the above optional embodiments to comprehensively characterize the user's health level, assist in achieving accurate health assessment based on multimodal data and baseline comparison, improve the comprehensiveness and accuracy of user health monitoring, and reduce the risk of scoring bias caused by data noise or improper dimensional weights.

[0101] As an optional embodiment, the extraction module extracts the specific method of health feature parameters corresponding to each sensor data based on a preset feature extraction algorithm, including: Each sensor data point is cleaned and / or filtered to obtain the corresponding processed data. For each piece of processed data, features are extracted from the processed data according to the feature extraction algorithm corresponding to the data type, so as to obtain the corresponding health feature parameters.

[0102] As can be seen, through the above optional embodiments, health feature parameters are obtained based on the feature extraction algorithm corresponding to the data type after data cleaning and / or filtering of each type of sensor data. Thus, on the basis of accurate health assessment, the purity and reliability of feature parameters are improved through data preprocessing and targeted extraction, providing high-quality data support for health score calculation and reducing the risk of feature misjudgment caused by interference from the original data.

[0103] As an optional embodiment, the health characteristic parameters are resting heart rate parameters, RMSSD parameters, deep sleep duration parameters, mid-sleep mean blood oxygenation parameters, or body temperature amplitude parameters.

[0104] As can be seen, the above optional embodiments limit the types of health feature parameters to comprehensively characterize the user's health features, assist in achieving accurate health assessment based on multimodal data and baseline comparison, improve the comprehensiveness and accuracy of user health monitoring, and reduce the risk of scoring bias caused by data noise or improper dimensional weights.

[0105] As an optional embodiment, the determining module determines the target user's health scores across multiple dimensions based on the target user's corresponding health baseline and according to health characteristic parameters, including: For each dimension, determine the health baseline parameters for the target user corresponding to that dimension; optionally, the health baseline parameters are determined based on the target user's historical sensor data. The health score corresponding to this dimension is determined based on the health characteristic parameters and the health baseline parameters.

[0106] As can be seen, through the above optional embodiments, by determining the health baseline parameters for each dimension based on the target user's historical sensor data and calculating the health score in combination with health feature parameters, the personalization and accuracy of the score assessment are improved by baseline comparison on the basis of accurate multi-dimensional health score determination, providing a scientific basis for health scoring and reducing the risk of health assessment errors caused by inaccurate baselines.

[0107] As an optional embodiment, the specific method by which the determining module determines the health score corresponding to the dimension based on the health feature parameters and the health baseline parameters includes: Calculate the degree of difference between the health characteristic parameters and the health baseline parameters corresponding to this dimension; The difference is input into the score calculation algorithm model corresponding to that dimension to obtain the health score corresponding to that dimension.

[0108] As can be seen, through the above optional embodiments, by calculating the difference between health feature parameters and health baseline parameters and inputting them into the corresponding dimension score calculation algorithm model to obtain a health score, the accuracy and interpretability of the score calculation are improved by difference quantification and model mapping on the basis of accurate health score calculation, providing a reliable output for multi-dimensional health assessment and reducing the risk of score error caused by calculation model bias.

[0109] As an optional embodiment, the scoring module calculates the target user's health score based on multiple dimensions of health scores and weighted rules, including the following specific methods: Calculate the product of the health score of each dimension of the target user and the weight corresponding to that dimension to obtain the dimension weight score for each dimension. Calculate the sum of the dimensional weight scores for all dimensions, and calculate the health score for the target user.

[0110] As can be seen, through the above optional embodiments, a health score is obtained by summing the product of the health score of each dimension and its corresponding weight. Based on the accurate calculation of the health score, the comprehensiveness and balance of the score result are improved by optimizing the weight rules, providing an overall quantitative indicator for the user's health status and reducing the risk of score distortion caused by improper allocation of dimension weights.

[0111] Example 3 Please see Figure 3 , Figure 3 This is yet another user health monitoring system based on a smart ring and multimodal data disclosed in this invention. Figure 3 The described user health monitoring system based on smart rings and multimodal data is applied in a data processing system / data processing device / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the user health monitoring system based on a smart ring and multimodal data may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the user health monitoring method based on smart ring and multimodal data described in Embodiment 1.

[0112] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the user health monitoring method based on a smart ring and multimodal data described in Embodiment 1.

[0113] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the user health monitoring method based on smart rings and multimodal data described in Embodiment 1.

[0114] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0116] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0117] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0123] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0124] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0125] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0126] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0127] Finally, it should be noted that the user health monitoring method and system based on smart rings and multimodal data disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for user health monitoring based on smart ring and multi-modal data, the method comprising: The method comprises: obtaining a plurality of modalities of sensing data of a target user through an intelligent ring; extracting a health feature parameter corresponding to each of the sensing data based on a preset feature extraction algorithm; determining a plurality of dimensions of health scores of the target user according to the health feature parameters based on a health baseline corresponding to the target user; calculating a health score corresponding to the target user based on a weight rule according to the plurality of dimensions of health scores of the target user.

2. The method for user health monitoring based on smart ring and multi-modal data as claimed in claim 1, wherein, The intelligent ring is provided with a plurality of sensors; the sensors are photoelectric sensors, motion sensors, temperature sensors or bioimpedance sensors.

3. The method for user health monitoring based on smart ring and multi-modal data as claimed in claim 1, wherein, The sensing data is heart rate data, heart rate variability data, blood oxygen saturation data, activity intensity data, step count data, sleep stage data, motion mode data, wrist skin temperature, fingertip skin temperature, respiratory rate data or stress level data.

4. The smart ring and multi-modal data based user health monitoring method as claimed in claim 1, wherein, The health feature parameter corresponding to each of the sensing data is extracted based on the preset feature extraction algorithm, which comprises: performing data cleaning and / or data filtering on each of the sensing data to obtain corresponding processed data; performing feature extraction on each of the processed data according to a feature extraction algorithm corresponding to the data type of the processed data to obtain a corresponding health feature parameter.

5. The method for user health monitoring based on smart ring and multi-modal data as claimed in claim 4, wherein, The health feature parameter is a resting heart rate parameter, an RMSSD parameter, a deep sleep duration parameter, a mean blood oxygen parameter in middle sleep or a body temperature amplitude parameter.

6. The smart ring and multi-modal data based user health monitoring method as claimed in claim 1, wherein, The plurality of dimensions of health scores of the target user are determined according to the health feature parameters based on the health baseline corresponding to the target user, which comprises: for each dimension, determining a health baseline parameter of the target user corresponding to the dimension; the health baseline parameter is determined according to historical sensing data of the target user; determining a health score corresponding to the dimension according to the health feature parameter corresponding to the dimension and the health baseline parameter.

7. The method for user health monitoring based on smart ring and multi-modal data as claimed in claim 6, wherein, The health score corresponding to the dimension is determined according to the health feature parameter corresponding to the dimension and the health baseline parameter, which comprises: calculating a difference degree between the health feature parameter corresponding to the dimension and the health baseline parameter; inputting the difference degree into a score calculation algorithm model corresponding to the dimension to obtain the health score corresponding to the dimension.

8. The smart ring and multi-modal data based user health monitoring method as claimed in claim 1, wherein, The health score corresponding to the target user is calculated based on the weight rule according to the plurality of dimensions of health scores of the target user, which comprises: calculating a product of the health score of each dimension of the target user and a weight corresponding to the dimension to obtain a dimension weight score corresponding to each dimension; calculating a summation value of the dimension weight scores corresponding to all dimensions to calculate the health score corresponding to the target user.

9. A user health monitoring system based on smart ring and multi-modal data, characterized in that, The system comprises: an acquisition module configured to obtain a plurality of modalities of sensing data of a target user through an intelligent ring; an extraction module configured to extract a health feature parameter corresponding to each of the sensing data based on a preset feature extraction algorithm; a determination module configured to determine a plurality of dimensions of health scores of the target user according to the health feature parameters based on a health baseline corresponding to the target user; A scoring module is configured to calculate a health score of the target user based on a weight rule according to health scores of multiple dimensions of the target user.

10. A user health monitoring system based on smart ring and multi-modal data, characterized in that, The system comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the method for monitoring user health based on the smart ring and multi-modal data according to any one of claims 1-8.

Images