Health analysis method and system based on sensing of intelligent ring charging equipment

Abstract

The invention discloses a health analysis method and system based on intelligent ring charging equipment perception. The method comprises the steps that user physiological data obtained through an intelligent ring and environment sensing data obtained through charging equipment of the intelligent ring are continuously received; based on an association relationship between time and a user, fusing the user physiological data and the environment sensing data to obtain an association data set; performing association analysis on the association data set according to a preset AI algorithm to obtain association analysis results of a plurality of users and environments; and according to a preset result and conclusion corresponding rule, generating at least one health suggestion corresponding to the association analysis result. Therefore, real-time closed-loop health insight of the physiological environment based on the intelligent ring and the charging equipment can be realized, the comprehensiveness and guidance of user health monitoring are improved, and the risk of inaccurate health suggestion caused by disjunction of the physiological environment is reduced.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a health analysis method and system based on the sensing capabilities of a smart ring charging device. Background Technology

[0002] With the rapid growth in demand for the integration of wearable devices and smart homes, users and medical institutions are increasingly emphasizing comprehensive health guidance through real-time closed-loop analysis of physiological and environmental data. Current technologies typically collect physiological sensor data independently via smart rings, process the data using fixed threshold analysis or independent models, and generate health recommendations based on standard rules to support daily health management. However, existing solutions lack the ability to continuously receive physiological and environmental data from smart rings and their charging devices, perform time-series correlation fusion, and conduct in-depth analysis tailored to individual users. This makes it difficult to form closed-loop health insights and optimize recommendation generation. Commonly used isolated data processing strategies cannot adapt to dynamic changes in the physiological environment, resulting in insufficient comprehensiveness and guidance in health monitoring. Disconnects from the physiological environment can easily lead to inaccurate or ineffective recommendations, limiting the accuracy and practical effectiveness of user health management. 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 health analysis method and system based on the perception of a smart ring charging device, which can realize real-time closed-loop health insight based on the physiological environment of the smart ring and charging device, improve the comprehensiveness and guidance of user health monitoring, and reduce the risk of inaccurate health advice due to the disconnect between the physiological environment and the health environment.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a health analysis method based on the sensing capabilities of a smart ring charging device, the method comprising: It continuously receives user physiological data acquired through the smart ring and environmental sensor data acquired through the charging device of the smart ring; Based on the correlation between time and users, the user's physiological data and the environmental sensor data are fused to obtain a correlated dataset; The associated dataset is analyzed using a preset AI algorithm to obtain the association analysis results of multiple users and environments; Based on the preset rules for the correspondence between results and conclusions, at least one health recommendation corresponding to the correlation analysis result is generated.

[0005] As an optional implementation, in the first aspect of the invention, the charging device is provided with a plurality of sensors; the sensors are temperature sensors, humidity sensors, air pressure sensors, ambient light sensors, sound sensors, carbon dioxide sensors, VOCs sensors, TVOC sensors, dust sensors or PM2.5 sensors.

[0006] As an optional implementation, in the first aspect of the present invention, the user physiological data includes at least one of heart rate data, HRV data, blood oxygen saturation data, body temperature data, and exercise data; and / or, the environmental sensing data includes at least one of temperature data, humidity data, air pressure data, ambient light data, sound data, carbon dioxide data, VOCs data, TVOC data, dust data, and PM2.5 data.

[0007] As an optional implementation, in the first aspect of the present invention, the step of fusing the user's physiological data and the environmental sensor data based on the correlation between time and user to obtain a correlated dataset includes: Determine the user information and time information corresponding to each physiological data point in the user's physiological data; Determine the user information and time information corresponding to each data point in the environmental sensing data; The user physiological data and the environmental sensing data are matched with the same user information and time information to obtain the associated data of multiple physiological data and sensing data; All the aforementioned related data are combined into a related dataset.

[0008] As an optional implementation, in the first aspect of the present invention, the step of performing association analysis on the associated dataset according to a preset AI algorithm to obtain association analysis results of multiple users and environments includes: The associated dataset is input into the trained user environment analysis algorithm model to obtain the association analysis results of multiple users and environments; the user environment analysis algorithm model is trained using a training dataset that includes multiple training associated datasets and corresponding association analysis conclusion annotations.

[0009] As an optional implementation, in the first aspect of the invention, the correlation analysis results are the correlation between nighttime CO2 concentration and deep sleep duration or the correlation between peak environmental noise and the number of sleep interruptions.

[0010] As an optional implementation, in the first aspect of the present invention, generating at least one health recommendation corresponding to the correlation analysis result according to a preset correspondence rule between results and conclusions includes: At least one of the association analysis results is input into the trained LLM model to obtain the corresponding health recommendations output; the LLM model is trained on a training dataset that includes multiple training association analysis results and corresponding health recommendation annotations.

[0011] As an optional implementation, in the first aspect of the present invention, the method further includes: Identify home appliance control recommendations included in the health advice; Generate device control commands corresponding to the suggested home appliance control instructions; The device control command is sent to the corresponding home appliance for execution.

[0012] A second aspect of this invention discloses a health analysis system based on the sensing capabilities of a smart ring charging device, the system comprising: The acquisition module is used to continuously receive user physiological data acquired through the smart ring and environmental sensing data acquired through the charging device of the smart ring; The fusion module is used to fuse the user's physiological data and the environmental sensor data based on the relationship between time and user to obtain a related dataset; The analysis module is used to perform correlation analysis on the associated dataset according to a preset AI algorithm to obtain correlation analysis results for multiple users and environments; The suggestion module is used to generate at least one health suggestion corresponding to the correlation analysis result based on preset rules for the correspondence between results and conclusions.

[0013] As an optional implementation, in a second aspect of the invention, the charging device is provided with a plurality of sensors; the sensors are temperature sensors, humidity sensors, air pressure sensors, ambient light sensors, sound sensors, carbon dioxide sensors, VOCs sensors, TVOC sensors, dust sensors, or PM2.5 sensors.

[0014] As an optional implementation, in a second aspect of the invention, the user physiological data includes at least one of heart rate data, HRV data, blood oxygen saturation data, body temperature data, and exercise data; and / or, the environmental sensing data includes at least one of temperature data, humidity data, air pressure data, ambient light data, sound data, carbon dioxide data, VOCs data, TVOC data, dust data, and PM2.5 data.

[0015] As an optional implementation, in a second aspect of the invention, the specific method by which the fusion module fuses the user physiological data and the environmental sensor data to obtain a correlated dataset based on the correlation between time and user includes: Determine the user information and time information corresponding to each physiological data point in the user's physiological data; Determine the user information and time information corresponding to each data point in the environmental sensing data; The user physiological data and the environmental sensing data are matched with the same user information and time information to obtain the associated data of multiple physiological data and sensing data; All the aforementioned related data are combined into a related dataset.

[0016] As an optional implementation, in the second aspect of the present invention, the specific method by which the analysis module performs association analysis on the associated dataset according to a preset AI algorithm to obtain the association analysis results of multiple users and environments includes: The associated dataset is input into the trained user environment analysis algorithm model to obtain the association analysis results of multiple users and environments; the user environment analysis algorithm model is trained using a training dataset that includes multiple training associated datasets and corresponding association analysis conclusion annotations.

[0017] As an optional implementation, in a second aspect of the invention, the correlation analysis results are a correlation between nighttime CO2 concentration and deep sleep duration or a correlation between peak environmental noise and the number of sleep interruptions.

[0018] As an optional implementation, in a second aspect of the invention, the suggestion module generates at least one health suggestion corresponding to the correlation analysis result according to a preset correspondence rule between results and conclusions, including: At least one of the association analysis results is input into the trained LLM model to obtain the corresponding health recommendations output; the LLM model is trained on a training dataset that includes multiple training association analysis results and corresponding health recommendation annotations.

[0019] As an optional implementation, in a second aspect of the invention, the system is further configured to perform the following steps: Identify home appliance control recommendations included in the health advice; Generate device control commands corresponding to the suggested home appliance control instructions; The device control command is sent to the corresponding home appliance for execution.

[0020] A third aspect of this invention discloses another health analysis system based on the sensing capabilities of a smart ring charging device, 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 health analysis method based on the sensing of a smart ring charging device 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 health analysis method based on the sensing of a smart ring charging device 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 continuously receives physiological data from a smart ring and environmental sensor data from a charging device, fuses and analyzes these data based on time and user association, and ultimately generates health recommendations. This enables real-time closed-loop health insights based on the physiological environment of the smart ring and charging device, improving the comprehensiveness and guidance of user health monitoring and reducing the risk of inaccurate health recommendations due to a disconnect between the physiological environment and the data. 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 health analysis method based on the sensing capabilities of a smart ring charging device, as disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a health analysis system based on the sensing capabilities of a smart ring charging device, as disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another health analysis system based on the sensing of a smart ring charging device 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 health analysis method and system based on the sensing capabilities of a smart ring charging device. By continuously receiving physiological data from the smart ring and environmental sensor data from the charging device, the system fuses and analyzes these data based on time and user association, ultimately generating health recommendations. This enables real-time closed-loop health insights based on the physiological environment of the smart ring and charging device, improving the comprehensiveness and guidance of user health monitoring and reducing the risk of inaccurate health recommendations due to a disconnect between the physiological environment and the data. Detailed explanations follow.

[0031] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a health analysis method based on the sensing capabilities of a smart ring charging device, as disclosed in an embodiment of the present invention. Figure 1 The described health analysis method based on the sensing capabilities of a smart ring charging device can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, the health analysis method based on the sensing of a smart ring charging device may include the following operations: 101. Continuously receive user physiological data obtained through the smart ring and environmental sensor data obtained through the charging device of the smart ring.

[0032] Optionally, the charging device is equipped with multiple sensors.

[0033] Optionally, the sensor may be a temperature sensor, humidity sensor, air pressure sensor, ambient light sensor, sound sensor, carbon dioxide sensor, VOCs sensor, TVOC sensor, dust sensor, or PM2.5 sensor.

[0034] Optionally, user physiological data may include at least one of heart rate data, HRV data, blood oxygen saturation data, body temperature data, and exercise data.

[0035] Optionally, the environmental sensing data includes at least one of the following: temperature data, humidity data, air pressure data, ambient light data, sound data, carbon dioxide data, VOCs data, TVOC data, dust data, and PM2.5 data.

[0036] 102. Based on the correlation between time and users, user physiological data and environmental sensor data are fused to obtain a correlated dataset.

[0037] 103. Perform correlation analysis on the associated dataset based on the preset AI algorithm to obtain the correlation analysis results of multiple users and environments.

[0038] 104. Based on the preset rules for the correspondence between results and conclusions, generate at least one health recommendation corresponding to the correlation analysis result.

[0039] As can be seen, the above-mentioned embodiments of the invention continuously receive physiological data from the smart ring and environmental sensor data from the charging device, fuse them based on time and user association, and complete the association analysis to finally generate health advice. This enables real-time closed-loop health insight based on the physiological environment of the smart ring and the charging device, improves the comprehensiveness and guidance of user health monitoring, and reduces the risk of inaccurate health advice due to the disconnect between the physiological environment and the data.

[0040] As an optional embodiment, the above steps, which involve fusing user physiological data and environmental sensor data based on the correlation between time and users to obtain a correlated dataset, include: Determine the user information and time information corresponding to each physiological data point in the user's physiological data; Determine the user information and time information corresponding to each sensor data in the environmental sensor data; Corresponding data with identical user and time information in user physiological data and environmental sensor data is used to obtain correlated data of multiple physiological and sensor data. All related data are combined into a related dataset.

[0041] As can be seen, through the above optional embodiments, by matching user information and time information for each piece of physiological data and environmental sensor data, dual-source data of the same user at the same time are accurately matched and formed into an associated dataset, realizing accurate multi-source data fusion based on dual-dimensional alignment, improving the data quality and reliability of subsequent association analysis, and reducing the risk of basic analysis errors caused by time or user mismatch.

[0042] As an optional embodiment, the above steps, including performing association analysis on the associated dataset according to a preset AI algorithm to obtain association analysis results for multiple users and environments, include: The associated dataset is input into the trained user environment analysis algorithm model to obtain the association analysis results of multiple users and environments. The user environment analysis algorithm model is trained using a training dataset that includes multiple training associated datasets and corresponding association analysis conclusion annotations.

[0043] Optionally, the correlation analysis results can be the correlation between nighttime CO2 concentration and deep sleep duration or the correlation between peak ambient noise and the number of sleep interruptions.

[0044] Specifically, the correlation analysis results can be a correlation analysis between PM2.5 and the user's blood oxygen saturation. An example of the specific analysis process is as follows: Data collected from user B every 2 hours on a certain day yielded the following: Time: 07:00; PM2.5 concentration (μg / m³): 25 (excellent); SpO2 (%): 98; Time: 09:00; PM2.5 concentration (μg / m³): 42 (Good); SpO2 (%): 97; Time: 11:00; PM2.5 concentration (μg / m³): 85 (light pollution); SpO2 (%): 95; Time: 13:00; PM2.5 concentration (μg / m³): 110 (moderate pollution); SpO2 (%): 94; Time: 15:00; PM2.5 concentration (μg / m³): 130 (severe pollution); SpO2 (%): 93; Time: 17:00; PM2.5 concentration (μg / m³): 95 (light pollution); SpO2 (%): 95; Specifically, the numerical rules are as follows: PM2.5 classification standards: ≤35 (excellent), 36-75 (good), 76-115 (lightly polluted), 116-150 (moderately polluted).

[0045] Blood oxygenation correlation threshold: When PM2.5 > 75 μg / m³, SpO2 ≤ 95% and shows a significant negative correlation with PM2.5 (r < -0.6), it is determined that "PM2.5 affects blood oxygen".

[0046] Specifically, the calculation formula is (Pearson correlation analysis + bias calculation): 1. Pearson correlation coefficient r: r = Cov(PM2.5, SpO2) / √[Var(PM2.5)*Var(SpO2)].

[0047] The calculated values ​​are: Cov (PM2.5, SpO2) = -198.67, Var (PM2.5) = 1681.33, Var (SpO2) = 3.89.

[0048] The final value of r is -0.79 (strong negative correlation).

[0049] 2. Blood oxygen deviation ΔSpO2: Average SpO2 during polluted periods (PM2.5>75) - Average SpO2 during periods with good air quality (PM2.5≤35).

[0050] The average SpO2 during the pollution period was (95+94+93+95) / 4 = 94.25%.

[0051] The average SpO2 during prime time is 98%.

[0052] ΔSpO2 = 94.25 - 98 = -3.75%.

[0053] Specifically, the association analysis results are as follows: PM2.5 showed a strong negative correlation with user B's blood oxygen saturation (r=-0.79). When PM2.5 exceeded the standard, blood oxygen decreased by an average of 3.75%, indicating that air pollution significantly affected his blood oxygen level.

[0054] Specifically, the health advice received includes: When PM2.5 > 75 μg / m³, reduce the time spent outdoors and turn on an air purifier indoors; if SpO2 remains below 94%, it is recommended to seek medical attention to check respiratory function.

[0055] Specifically, the correlation analysis results can be a correlation analysis between PM2.5 and the user's blood oxygen saturation. An example of the specific analysis process is as follows: Data collected from user C at the same time each day for 3 days yielded the following results: Time: Day 1 21:00; Ambient humidity RH (%): 35 (low humidity); HRV (SDNN value, ms): 85; Time: Day 1 22:00; Ambient humidity RH (%): 38 (low humidity); HRV (SDNN value, ms): 88; Time: Day 2 21:00; Ambient humidity RH (%): 52 (suitable); HRV (SDNN value, ms): 110; Time: Day 2, 22:00; Ambient humidity (RH%): 55 (suitable); HRV (SDNN value, ms): 115; Time: Day 3 21:00; Ambient humidity RH (%): 70 (high humidity); HRV (SDNN value, ms): 95; Time: Day 3, 22:00; Ambient humidity (RH%): 72 (high humidity); HRV (SDNN value, ms): 98; The numerical rules are as follows: Humidity classification: <40% (low humidity), 40%-60% (suitable), >60% (high humidity).

[0056] HRV correlation threshold: SDNN ≥ 100ms is normal (good autonomic nerve function). SDNN compliance rate < 60% during low or high humidity periods is judged as "humidity affecting autonomic nerve function".

[0057] The calculation formula is as follows: 1. SDNN compliance rate for each humidity range: Compliance rate = (number of samples with SDNN ≥ 100ms) / total number of samples in that range × 100%.

[0058] Low humidity range: 0 / 2 = 0% (not met).

[0059] Suitable range: 2 / 2 = 100% (meets the standard).

[0060] High humidity range: 0 / 2 = 0% (not met).

[0061] 2. Difference in compliance rate: Compliance rate of suitable interval - Compliance rate of unsuitable interval = 100% - 0% = 100%.

[0062] Specifically, the association analysis results are as follows: User C's HRV only met the target when the humidity was between 40% and 60%. The autonomic nervous system function was weaker in low and high humidity environments, indicating that the environmental humidity has a significant impact on its cardiovascular regulation ability.

[0063] Specifically, the health advice received includes: Maintain indoor humidity between 45% and 55%. Use a humidifier when humidity is low and a dehumidifier when humidity is high. Being in a suitable humidity environment one hour before bedtime helps improve autonomic nervous system regulation during sleep.

[0064] As can be seen, through the above optional embodiments, by inputting the associated dataset into the trained user environment analysis algorithm model, the association analysis results of multiple users and the environment are directly output, thereby realizing the accurate physiological-environment causal relationship mining based on deep learning, improving the depth and accuracy of health insights, and reducing the risk of missing key associations due to insufficient rules.

[0065] As an optional embodiment, the step above, generating at least one health recommendation corresponding to a correlation analysis result based on a preset correspondence rule between results and conclusions, includes: At least one association analysis result is input into the trained LLM model to obtain the corresponding health recommendations output; the LLM model is trained on a training dataset that includes multiple training association analysis results and corresponding health recommendation annotations.

[0066] As can be seen, through the above optional embodiments, personalized health advice can be directly generated by inputting the association analysis results into the trained LLM model, realizing the intelligent transformation from complex associations to readable and actionable guidance, improving the relevance of the advice and the user adoption rate, and reducing the risk of health guidance failure due to the difficulty in understanding the analysis results.

[0067] As an optional embodiment, the method further includes the following steps: Identify home appliance control recommendations included in health advice; Generate device control commands corresponding to home appliance control suggestions; Send device control commands to the corresponding home appliances for execution.

[0068] As can be seen, through the above optional embodiments, by identifying the home device control content in the health advice and automatically generating device control commands for execution, a closed loop of the entire chain from health advice to real-time smart home intervention is realized, improving the automation and execution of user health management and reducing the risk of lack of actual improvement due to advice remaining only in words.

[0069] In a specific implementation scheme, based on the technical solution of this invention, a system is implemented that uses a smart ring charging box as an environmental monitoring node, combined with cloud-based artificial intelligence (AI) analysis, to provide users with personalized health advice. Specifically, in the implementation of this system, technicians believe that existing health analysis systems have a significant limitation: they only focus on internal human data, completely ignoring the enormous impact of external environmental factors on health. A user's health status is the result of the interaction between their internal physiological state and the external environment. For example: Poor sleep quality at night may not be due to physical reasons, but rather to factors such as excessively high bedroom temperature, low humidity, or excessive carbon dioxide concentration.

[0070] Feeling tired and dizzy during the day may be related to high concentrations of volatile organic compounds (VOCs) or PM2.5 indoors.

[0071] Slow recovery from exercise may be related to noise pollution in the surrounding environment interfering with deep sleep.

[0072] Currently, environmental monitoring devices (such as thermometers, hygrometers, and air purifiers) exist independently, and their data is completely isolated from the user's physiological data, making correlation analysis impossible. Users struggle to accurately determine whether their discomfort stems from physical discomfort or environmental factors. To address these limitations, engineers believe that the charging case of a smart ring is an excellent, albeit overlooked, platform. Typically placed in fixed locations like bedside tables or desks, it experiences several hours of close contact with the user daily (during charging), making it an ideal carrier for deploying environmental sensors. Therefore, there is an urgent need for a system that can integrate the ring's internal physiological data with the external environmental data collected by the charging case, using AI analysis to provide truly comprehensive health insights and actionable recommendations.

[0073] Specifically, the system includes: 1. Smart ring: Used to collect the user's vital signs data (such as heart rate, HRV, blood oxygen, body temperature, and exercise data).

[0074] 2. Environmental monitoring charging box: Built-in multimodal environmental sensor group: including temperature sensor, humidity sensor, air pressure sensor, ambient light sensor, microphone (for monitoring noise decibels), carbon dioxide sensor, VOCs / TVOC sensor, PM2.5 / dust sensor.

[0075] Microprocessor (MCU): Responsible for controlling sensor sampling and temporary data storage.

[0076] Wireless communication module (e.g., BLE / Wi-Fi): Used to upload collected environmental data to the cloud / mobile phone. Wi-Fi is preferred to ensure... It continuously transmits data over the network while charging.

[0077] Power supply and charging circuitry: Charges the ring and powers its own sensors and circuitry.

[0078] 3. User mobile terminal (APP): Serving as a data relay station and initial feedback interface, it receives and displays data from the ring and charging case, as well as AI suggestions.

[0079] 4. Cloud-based AI analysis platform: Data fusion module: Receives and synchronizes physiological data from the ring and environmental data from the charging case in real time.

[0080] AI analytics engine: Employs machine learning models to learn the correlation patterns between environmental and physiological data. For example, it establishes correlation models such as "nighttime CO2 concentration - deep sleep duration" and "peak environmental noise - number of sleep interruptions".

[0081] Knowledge base and suggestion generator: Based on the analysis results, it matches personalized and actionable suggestions from a pre-set knowledge base.

[0082] User data warehouse: Stores all historical data for long-term trend analysis and model optimization.

[0083] The system operates by including the following steps: S1: Dual-end data acquisition: The smart ring continuously collects the user's physiological data while being worn.

[0084] The environmental monitoring charging box continuously or periodically collects surrounding environmental data while plugged in (charging the ring).

[0085] S2: Data Upload and Integration: The ring synchronizes physiological data to a mobile app via Bluetooth, and then the app uploads it to the cloud.

[0086] The charging box uploads its environmental data directly to the cloud via Wi-Fi.

[0087] The cloud platform aligns and merges the physiological and environmental data of the same user within the same time period using user ID and timestamp.

[0088] S3: AI-based correlation analysis and suggestion generation: The AI ​​engine analyzes the fused dataset. For example, it identifies that "over the past three nights, when the CO2 concentration in the bedroom exceeded 1200 ppm, the user's deep sleep rate decreased by an average of 25%."

[0089] Based on the analysis results, corresponding suggestion rules are triggered. For example, a suggestion may be generated: "Insufficient ventilation was detected in your room while you were sleeping. It is recommended to open the window for 10 minutes before going to bed or turn on the fresh air system."

[0090] S4: Suggestions and Feedback: The generated AI suggestions are delivered to users via app push notifications, SMS, or email.

[0091] The system records user feedback on suggestions (such as clicking "Done" or ignoring them) to optimize subsequent suggestion models.

[0092] Taking sleep improvement as an example, the implementation process of this system is explained: 1. Users place the smart ring into the environmental monitoring charging case to charge every night.

[0093] 2. The charging box continuously monitors the bedroom's temperature, humidity, carbon dioxide concentration, and noise level throughout the night, and uploads the data to the cloud via home Wi-Fi.

[0094] 3. At the same time, the user's nocturnal heart rate variability (HRV), body movement, and blood oxygen data collected by the ring are also synchronized to the cloud via the mobile phone.

[0095] 4. The cloud-based AI platform merged and analyzed these two sets of data. The model discovered a persistent pattern: whenever the CO2 concentration rose above 1300 ppm between 2 and 4 a.m., the user's HRV significantly decreased, and body movement increased, indicating a decline in sleep quality.

[0096] 5. Based on this analysis, the generator suggests sending a message to the user via the app the following morning: "Last night, we detected that your sleep depth was affected in the latter half due to high carbon dioxide levels in the room. We suggest you leave a crack in the window before going to bed tonight, or turn on the bedroom's fresh air system." 6. After the user follows the advice, subsequent data collected by the system shows that sleep quality has improved. This positive feedback is recorded to reinforce the effectiveness of the advice.

[0097] In summary, the solutions disclosed in the embodiments of the present invention have the following advantages: 1. Comprehensive data dimensions: For the first time, it deeply integrates accurate environmental data with continuous physiological data at the level of personal health, and constructs a health database from the dual perspective of "human body-environment".

[0098] 2. Precise and in-depth insights: AI analysis can reveal the impact of previously overlooked environmental factors on health, helping users find the root cause of health problems (whether it is a physical problem or an environmental problem).

[0099] 3. Actionable and personalized recommendations: The recommendations provided are no longer general suggestions like "drink more water", but specific and actionable environmental improvement measures (such as "ventilation", "humidification", "air purification"), and are based on the user's individual data response patterns.

[0100] 4. Unobtrusive monitoring: It makes full use of the "idle" state and fixed location of the charging box, so users do not need to purchase or operate additional environmental monitoring equipment, thus achieving truly unobtrusive environmental data collection.

[0101] 5. Value-added services and business model innovation: The charging box has been upgraded from a simple accessory to an important data entry point, laying the foundation for value-added services such as linkage with smart home devices (such as air conditioners, air purifiers, and fresh air systems) and provision of subscription-based health reports.

[0102] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a health analysis system based on the sensing capabilities of a smart ring charging device, as disclosed in an embodiment of the present invention. Figure 2 The described health analysis system based on the sensing capabilities of a smart ring charging device can be applied to data processing systems / data processing devices / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the health analysis system based on the smart ring charging device's sensing capabilities may include: The acquisition module 201 is used to continuously receive user physiological data acquired through the smart ring and environmental sensing data acquired through the charging device of the smart ring.

[0103] The fusion module 202 is used to fuse user physiological data and environmental sensor data to obtain a related dataset based on the relationship between time and user.

[0104] The analysis module 203 is used to perform correlation analysis on the associated dataset according to the preset AI algorithm to obtain the correlation analysis results of multiple users and environments.

[0105] The suggestion module 204 is used to generate at least one health suggestion corresponding to the correlation analysis result based on the preset correspondence rules between the results and conclusions.

[0106] As can be seen, the above-mentioned embodiments of the invention continuously receive physiological data from the smart ring and environmental sensor data from the charging device, fuse them based on time and user association, and complete the association analysis to finally generate health advice. This enables real-time closed-loop health insight based on the physiological environment of the smart ring and the charging device, improves the comprehensiveness and guidance of user health monitoring, and reduces the risk of inaccurate health advice due to the disconnect between the physiological environment and the data.

[0107] As an optional embodiment, the charging device is equipped with multiple sensors; the sensors are temperature sensors, humidity sensors, air pressure sensors, ambient light sensors, sound sensors, carbon dioxide sensors, VOCs sensors, TVOC sensors, dust sensors, or PM2.5 sensors.

[0108] As can be seen, the sensor settings of the charging device are specified through the above optional embodiments, so that the charging device of the smart ring can acquire a variety of sensor data that comprehensively characterize environmental health features, assisting in the realization of real-time closed-loop health insight based on the physiological environment of the smart ring and the charging device, improving the comprehensiveness and guidance of user health monitoring, and reducing the risk of inaccurate health advice due to the disconnect between physiological environment and health.

[0109] As an optional embodiment, the user's physiological data includes at least one of heart rate data, HRV data, blood oxygen saturation data, body temperature data, and exercise data; and / or, the environmental sensing data includes at least one of temperature data, humidity data, air pressure data, ambient light data, sound data, carbon dioxide data, VOCs data, TVOC data, dust data, and PM2.5 data.

[0110] As can be seen, the above optional embodiments limit the content of user physiological data and environmental sensor data to comprehensively characterize the health characteristics of users and the environment, assist in realizing real-time closed-loop health insights based on the physiological environment of smart rings and charging devices, improve the comprehensiveness and guidance of user health monitoring, and reduce the risk of inaccurate health advice due to the disconnect between physiological environment and health.

[0111] As an optional embodiment, the specific method by which the fusion module fuses user physiological data and environmental sensor data to obtain a correlated dataset based on the correlation between time and users includes: Determine the user information and time information corresponding to each physiological data point in the user's physiological data; Determine the user information and time information corresponding to each sensor data in the environmental sensor data; Corresponding data with identical user and time information in user physiological data and environmental sensor data is used to obtain correlated data of multiple physiological and sensor data. All related data are combined into a related dataset.

[0112] As can be seen, through the above optional embodiments, by matching user information and time information for each piece of physiological data and environmental sensor data, dual-source data of the same user at the same time are accurately matched and formed into an associated dataset, realizing accurate multi-source data fusion based on dual-dimensional alignment, improving the data quality and reliability of subsequent association analysis, and reducing the risk of basic analysis errors caused by time or user mismatch.

[0113] As an optional embodiment, the analysis module performs correlation analysis on the associated dataset according to a preset AI algorithm to obtain the correlation analysis results of multiple users and environments in the following specific ways: The associated dataset is input into the trained user environment analysis algorithm model to obtain the association analysis results of multiple users and environments. The user environment analysis algorithm model is trained using a training dataset that includes multiple training associated datasets and corresponding association analysis conclusion annotations.

[0114] As can be seen, through the above optional embodiments, by inputting the associated dataset into the trained user environment analysis algorithm model, the association analysis results of multiple users and the environment are directly output, thereby realizing the accurate physiological-environment causal relationship mining based on deep learning, improving the depth and accuracy of health insights, and reducing the risk of missing key associations due to insufficient rules.

[0115] As an optional embodiment, the correlation analysis results are the correlation between nighttime CO2 concentration and deep sleep duration or the correlation between peak ambient noise and the number of sleep interruptions.

[0116] As can be seen, the above optional embodiments limit the content of the correlation analysis results to comprehensively characterize the correlation health characteristics of users and the environment, assist in realizing real-time closed-loop health insights based on the physiological environment of smart rings and charging devices, improve the comprehensiveness and guidance of user health monitoring, and reduce the risk of inaccurate health advice due to the disconnect between physiological environment and health.

[0117] As an optional embodiment, the suggestion module generates at least one health suggestion corresponding to a correlation analysis result according to a preset correspondence rule between results and conclusions, including the following specific methods: At least one association analysis result is input into the trained LLM model to obtain the corresponding health recommendations output; the LLM model is trained on a training dataset that includes multiple training association analysis results and corresponding health recommendation annotations.

[0118] As can be seen, through the above optional embodiments, personalized health advice can be directly generated by inputting the association analysis results into the trained LLM model, realizing the intelligent transformation from complex associations to readable and actionable guidance, improving the relevance of the advice and the user adoption rate, and reducing the risk of health guidance failure due to the difficulty in understanding the analysis results.

[0119] As an optional embodiment, the system is also used to perform the following steps: Identify home appliance control recommendations included in health advice; Generate device control commands corresponding to home appliance control suggestions; Send device control commands to the corresponding home appliances for execution.

[0120] As can be seen, through the above optional embodiments, by identifying the home device control content in the health advice and automatically generating device control commands for execution, a closed loop of the entire chain from health advice to real-time smart home intervention is realized, improving the automation and execution of user health management and reducing the risk of lack of actual improvement due to advice remaining only in words.

[0121] Example 3 Please see Figure 3 , Figure 3 This is another health analysis system based on the sensing of a smart ring charging device disclosed in the embodiments of the present invention. Figure 3 The described health analysis system based on the sensing capabilities of a smart ring charging device 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 health analysis system based on the smart ring charging device's sensing capabilities 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 health analysis method based on the smart ring charging device described in Embodiment 1.

[0122] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the health analysis method based on the sensing of a smart ring charging device described in Embodiment 1.

[0123] 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 health analysis method based on the smart ring charging device described in Embodiment 1.

[0124] 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.

[0125] 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, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] 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.

[0133] Computer-readable media include 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] Finally, it should be noted that the health analysis method and system based on the sensing of a smart ring charging device 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; and these 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 health analysis method based on the sensing capabilities of a smart ring charging device, characterized in that, The method includes: It continuously receives user physiological data acquired through the smart ring and environmental sensor data acquired through the charging device of the smart ring; Based on the correlation between time and users, the user's physiological data and the environmental sensor data are fused to obtain a correlated dataset; The associated dataset is analyzed using a preset AI algorithm to obtain the association analysis results of multiple users and environments; Based on the preset rules for the correspondence between results and conclusions, at least one health recommendation corresponding to the correlation analysis result is generated.

2. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The charging device is equipped with multiple sensors; the sensors are temperature sensors, humidity sensors, air pressure sensors, ambient light sensors, sound sensors, carbon dioxide sensors, VOCs sensors, TVOC sensors, dust sensors, or PM2.5 sensors.

3. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The user physiological data includes at least one of heart rate data, HRV data, blood oxygen saturation data, body temperature data, and exercise data; and / or, the environmental sensing data includes at least one of temperature data, humidity data, air pressure data, ambient light data, sound data, carbon dioxide data, VOCs data, TVOC data, dust data, and PM2.5 data.

4. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The aforementioned method, based on the correlation between time and user, fuses the user's physiological data and the environmental sensor data to obtain a correlated dataset, including: Determine the user information and time information corresponding to each physiological data point in the user's physiological data; Determine the user information and time information corresponding to each data point in the environmental sensing data; The user physiological data and the environmental sensing data are matched with the same user information and time information to obtain the associated data of multiple physiological data and sensing data; All the aforementioned related data are combined into a related dataset.

5. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The step of performing association analysis on the associated dataset according to a preset AI algorithm to obtain association analysis results for multiple users and environments includes: The associated dataset is input into the trained user environment analysis algorithm model to obtain the association analysis results of multiple users and environments; the user environment analysis algorithm model is trained using a training dataset that includes multiple training associated datasets and corresponding association analysis conclusion annotations.

6. The health analysis method based on the sensing of a smart ring charging device according to claim 5, characterized in that, The correlation analysis results are the correlation between nighttime CO2 concentration and deep sleep duration or the correlation between peak environmental noise and the number of sleep interruptions.

7. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The step of generating at least one health recommendation corresponding to the correlation analysis result based on a preset rule for corresponding results and conclusions includes: At least one of the association analysis results is input into the trained LLM model to obtain the corresponding health recommendations output; the LLM model is trained on a training dataset that includes multiple training association analysis results and corresponding health recommendation annotations.

8. The health analysis method based on the sensing of a smart ring charging device according to claim 1, characterized in that, The method further includes: Identify home appliance control recommendations included in the health advice; Generate device control commands corresponding to the suggested home appliance control instructions; The device control command is sent to the corresponding home appliance for execution.

9. A health analysis system based on the sensing capabilities of a smart ring charging device, characterized in that, The system includes: The acquisition module is used to continuously receive user physiological data acquired through the smart ring and environmental sensing data acquired through the charging device of the smart ring; The fusion module is used to fuse the user's physiological data and the environmental sensor data based on the relationship between time and user to obtain a related dataset; The analysis module is used to perform correlation analysis on the associated dataset according to a preset AI algorithm to obtain correlation analysis results for multiple users and environments; The suggestion module is used to generate at least one health suggestion corresponding to the correlation analysis result based on preset rules for the correspondence between results and conclusions.

10. A health analysis system based on the sensing capabilities of a smart ring charging device, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the health analysis method based on the sensing of the smart ring charging device as described in any one of claims 1-8.

Images