A method and system for processing intelligent underwear data based on artificial intelligence

Abstract

This invention proposes an artificial intelligence-based data processing method and system for smart underwear, including: the smart underwear collects user physiological and environmental data through built-in sensors; an edge computing chip preprocesses the collected data to obtain first data, performs sensitivity classification labeling to obtain second data, processes the data according to the sensitivity level to obtain third data, and selects fourth data to be uploaded from the data; a server receives and decrypts the fourth data, integrates multi-source data based on timestamps to construct a health data set, inputs a preset model for analysis, and sends the results to the smart underwear; the edge computing chip provides health advice based on the analysis results through a feedback device and collects user feedback to optimize the model; and the server uses digital twin technology to simulate the user's health status, predict health problems, and develop management plans. This invention not only improves the accuracy of smart underwear data analysis but also enhances the security and privacy protection of user data during transmission and processing.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based intelligent underwear data processing method and system. Background Art

[0002] With the advancement of technology, smart underwear is gaining popularity. These underwear, equipped with various sensors, can collect physiological data such as heart rate and body temperature. However, current data processing for smart underwear faces numerous challenges, including insufficient privacy protection, which exposes large amounts of sensitive physiological data to the risk of leakage. Furthermore, data processing fails to fully tap into the value of data, making it difficult to provide users with accurate and personalized health analysis and feedback. Therefore, a more accurate, secure, and intelligent data processing method is urgently needed. Summary of the Invention

[0003] Based on the above problems, the present invention proposes an artificial intelligence-based smart underwear data processing method and system. Through the solution of the present invention, multiple advanced technologies such as edge computing, deep learning, blockchain and digital twins are combined, which not only improves the accuracy of smart underwear data analysis, but also enhances the security and privacy protection of user data during transmission and processing.

[0004] In view of this, one aspect of the present invention proposes an intelligent underwear data processing method based on artificial intelligence, comprising:

[0005] Smart sensors installed in smart underwear collect the user's physiological data and environmental perception data. The collection frequency is set to different preset values based on the sensor type, and the collected data is time-stamped.

[0006] After preprocessing the collected physiological data and environmental perception data in the edge computing chip of the smart underwear, first data is obtained;

[0007] The edge computing chip performs sensitivity classification and labeling on the first data to obtain second data;

[0008] The edge computing chip processes the second data according to different sensitivity levels to obtain third data;

[0009] The edge computing chip determines fourth data to be uploaded to the server from the third data;

[0010] The server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct a user health data set;

[0011] The server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results, and sends the health analysis results to the smart underwear;

[0012] Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record;

[0013] Based on the health analysis results, the edge computing chip provides personalized health advice and reminders to the user through the feedback device of the smart underwear. At the same time, it collects user feedback on the feedback information, modifies the parameters of the artificial intelligence model in real time, and optimizes subsequent health analysis results.

[0014] The server uses digital twin technology to drive a virtual digital model with the user's physiological data, simulates the user's physical responses in different health conditions and sports scenarios, predicts potential health problems, and develops a health management plan.

[0015] Optionally, the step of the edge computing chip performing sensitivity classification and labeling on the first data to obtain the second data includes:

[0016] extracting temporal features, spatial features, and semantic features of the first data;

[0017] Using a preset feature vector extraction algorithm, different types of sensor data are converted into standardized feature vectors;

[0018] Construct a multimodal feature fusion matrix to fuse data features of different dimensions;

[0019] Analyze the feature fusion matrix based on the preset sensitivity assessment model;

[0020] Calculate the privacy exposure risk value of the data, which takes into account the identifiability, relevance, and harmfulness of the data;

[0021] According to the corresponding relationship between the risk value and the preset sensitivity level, the sensitivity level of the data is determined and marked, thereby obtaining second data.

[0022] Optionally, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data includes:

[0023] extracting first level data from the second data;

[0024] The server sends a first processing program to the edge computing chip;

[0025] The edge computing chip receives the first processing program and processes the first level data using the first processing program, and then sends first feedback data to the server;

[0026] The server receives the first feedback data and verifies the first feedback data;

[0027] If the verification is passed, a first processing program invalidation instruction is sent;

[0028] If the verification fails, adjusting the first processing procedure based on the first feedback data to obtain a second processing procedure;

[0029] Sending an invalidation instruction of the second processing program and the first processing program to the edge computing chip;

[0030] The edge computing chip receives the second processing program and processes the first level data using the second processing program;

[0031] Repeat the above steps until the feedback data sent by the edge computing chip passes the verification.

[0032] Optionally, the step of determining, by the edge computing chip, fourth data to be uploaded to the server from the third data includes:

[0033] Determining the service processing type and service processing content of the server;

[0034] Detecting the degree of data duplication of the third data, performing data downsampling, retaining key time node data, and obtaining intermediate data with timestamps;

[0035] Performing data value evaluation on the intermediate data, including: calculating the information entropy value of the intermediate data; evaluating the contribution of the intermediate data to the business processing type and business processing content of the server; generating a data value score for the intermediate data; and establishing a data value priority queue for the intermediate data based on the data value score;

[0036] Determine the upload priority threshold based on the current network bandwidth, server load, and data transmission cost;

[0037] Segmenting the intermediate data in combination with the data value priority queue, extracting data feature vectors, performing data compression, and generating multiple compressed data packets;

[0038] The compressed data packets are prioritized based on the preset rule screening data and the upload priority threshold to determine an upload data set to obtain fourth data.

[0039] Optionally, the server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct the user health data set, including:

[0040] Receiving and verifying the fourth data, including: verifying the integrity of data transmission: checking the signature of the data packet, checking the integrity of the data packet sequence, and verifying the validity of the timestamp; identifying the source and type of the data; parsing the format of the data packet; and generating a receipt confirmation message;

[0041] Decrypting the fourth data includes: obtaining a decryption key from a secure key management system; performing decryption operations on different encryption types: decrypting homomorphically encrypted data, processing differentially private data, and restoring desensitized data; verifying the correctness of the decryption result; and recording a decryption operation log.

[0042] The steps for aligning the decrypted data timestamps include: extracting data timestamp information; unifying time standards: converting timestamps in different time zones, calibrating device clock deviations, and processing sampling time errors; establishing a time index structure; and identifying data temporal relationships.

[0043] The steps for synchronizing multi-source data after timestamp alignment include: identifying relationships between data; performing time window partitioning: setting the synchronization time window size, handling data sampling frequency differences, and aligning data sampling points; filling missing data: applying interpolation algorithms, marking filled data, and evaluating filling reliability; and handling data conflicts.

[0044] The steps for quality assessment of synchronized data include: detecting outliers: statistical feature analysis, time series pattern recognition, marking abnormal data points; evaluating data consistency; calculating data reliability scores; generating quality assessment reports;

[0045] The data integration steps after synchronization include: building a unified data model: defining data field mapping, unifying measurement units, and standardizing data formats; merging multi-source data; establishing data association indexes; and optimizing storage structures;

[0046] Metadata management steps include: recording data processing; updating data catalogs; generating data summaries;

[0047] The steps for constructing a user health dataset include: organizing a hierarchical data structure; establishing a fast retrieval mechanism; implementing an incremental update strategy; and optimizing access performance.

[0048] Optionally, the server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results, and sends the health analysis results to the smart underwear, including:

[0049] Preprocessing the user health data set includes: performing data standardization processing: normalizing numerical features, encoding category features, and processing time series features; constructing feature vectors: extracting statistical features, generating time series features, and calculating derived features; processing missing values and outliers; and generating an analysis data set;

[0050] Model selection and configuration, including: loading the following preset health analysis models according to the analysis task: disease risk prediction model, fatigue assessment model, health status classification model; configuring the model parameters of the loaded model: setting the inference threshold, adjusting the model weight, and optimizing the prediction parameters; initializing the operating environment of the loaded model; and verifying the model status of the loaded model;

[0051] Performing health risk assessment based on the disease risk prediction model includes: executing disease risk prediction: analyzing abnormalities in physiological indicators, evaluating changes in health trends, and calculating risk probability distribution; generating risk ratings: determining risk levels, identifying key risk factors, and calculating risk confidence; generating early warning information; and recording the assessment process;

[0052] Performing fatigue analysis based on the fatigue assessment model includes: analyzing physiological data patterns: assessing heart rate variability, analyzing activity intensity, and monitoring recovery status; calculating a fatigue index: integrating multi-dimensional indicators, applying a fatigue assessment algorithm, and generating a fatigue level; evaluating recovery recommendations; and recording analysis results.

[0053] Comprehensively process the risk assessment results and fatigue analysis results based on the health status classification model, including: integrating multi-model prediction results: weighting and fusing prediction values, eliminating prediction conflicts, and optimizing result reliability; generating a health report: summarizing key findings, providing detailed explanations, and formulating recommended solutions; marking important reminders; and storing comprehensive analysis results;

[0054] Generate personalized recommendations based on the comprehensive analysis results, including: customizing recommendations based on user profiles: considering user health history, analyzing lifestyle habits, and assessing exercise capacity; formulating improvement plans: generating action recommendations, setting health goals, and planning intervention measures; generating reminder strategies; and optimizing recommendation content;

[0055] generating a health analysis result based on the comprehensive analysis result and the personalized recommendation;

[0056] The steps for transmitting health analysis results include: packaging analysis results: compressing data packets, adding security identifiers, generating verification codes; establishing a secure channel; executing batch transmission; and confirming that the transmission is complete.

[0057] Feedback tracking steps include: monitoring the implementation of recommendations; collecting user feedback; updating personalized parameters; and optimizing health analysis models.

[0058] Optionally, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0059] extracting second-level data from the second data;

[0060] dividing the second-level data into first data to be processed, second data to be processed, and third data to be processed;

[0061] Initial TEE environment, verify the environment integrity, and generate a zero-knowledge proof key pair within the TEE;

[0062] Extracting features from the first data to be processed and constructing a circuit required for proof;

[0063] Generating a zero-knowledge proof, including: converting the first to-be-processed data into a polynomial expression; generating proof parameters using an elliptic curve cryptography algorithm; constructing a commitment scheme to ensure data correctness; generating a non-interactive zero-knowledge proof; and verifying the validity of the generated zero-knowledge proof;

[0064] Generate homomorphic encryption keys based on lattice cryptography;

[0065] Splitting the second to-be-processed data into data blocks suitable for homomorphic operations;

[0066] Perform homomorphic encryption on each data block to generate first encrypted data that supports ciphertext domain operations, and record encryption parameters for subsequent decryption;

[0067] Determine noise parameters based on Laplace mechanism;

[0068] adding differential privacy noise to the third data to be processed according to the noise parameter to obtain second encrypted data;

[0069] Verify the data availability after adding differential privacy noise and dynamically adjust the noise parameters to balance privacy protection and data availability;

[0070] Integrate the generated zero-knowledge proof, the first encrypted data, and the second encrypted data to obtain third data;

[0071] Classify and store the third data, establish a data index structure, record metadata of the data processing process, and generate a data processing report;

[0072] Verify the integrity of third-party data, check privacy protection effects, evaluate data availability, generate processing records and upload them to the blockchain.

[0073] Optionally, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0074] extracting third level data from the second data;

[0075] Determine privacy budget parameters based on the characteristics of Level 3 data and privacy protection requirements;

[0076] According to the data type of the third-level data, select the corresponding noise distribution;

[0077] Conduct preliminary cleaning of the third-level data to remove erroneous values, outliers, and irrelevant redundant information;

[0078] Generate the corresponding random noise using a random number generator based on the selected noise distribution and privacy budget parameters;

[0079] The generated random noise is added to the preprocessed third level data to obtain third data.

[0080] Optionally, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0081] extracting fourth level data from the second data;

[0082] Processing the fourth-level data using a preset fourth-level data processing model to obtain third data;

[0083] The steps of constructing the fourth-level data processing model include:

[0084] Identify multiple participants holding fourth-level training data at the fourth level, and pre-process the fourth-level training data at each participant's local edge computing device or data center; wherein the data of each participant is always retained locally and the original data is not transmitted externally;

[0085] Each participant independently selects the corresponding machine learning model architecture based on its own data characteristics and business needs, and randomly initializes the model parameters in preparation for local training;

[0086] Using local fourth-level training data, each participant begins training the initialized model. Using an optimization algorithm, they continuously update the model parameters over multiple rounds of iterations, allowing the model to gradually fit the characteristics and patterns of the local data.

[0087] After a preset number of rounds of local training, each participant extracts the key parameters of the trained model and uploads these abstracted key parameters, which do not contain original data information, to the server via a secure communication channel;

[0088] After receiving the key parameters uploaded by each participant, the server uses a preset aggregation algorithm to comprehensively consider factors such as the data volume and data quality of each participant, assigns corresponding weights, aggregates and integrates all key parameters, and updates the global model;

[0089] Transmitting the updated new parameters of the global model back to each of the participants through a secure channel;

[0090] Each of the participants uses the received new parameters to replace the original corresponding part in the local model, completes the update of the local model, and obtains its own fourth-level data processing model;

[0091] Based on the updated fourth-level data processing model, each of the participants continues to use new data for training, upload parameters, receive new global models, and continuously optimize model performance, so that the fourth-level data processing model's processing capabilities for fourth-level data will gradually improve.

[0092] Another aspect of the present invention provides an artificial intelligence-based smart underwear data processing system for executing an artificial intelligence-based smart underwear data processing method, comprising: a server, and smart underwear equipped with a smart sensor and an edge computing chip; wherein,

[0093] The smart sensor is configured to: collect physiological data and environmental perception data of the user, wherein the collection frequency is set to different preset values according to the sensor type, and the collected data is time-stamped;

[0094] The edge computing chip is configured as follows:

[0095] After preprocessing the collected physiological data and environmental perception data, first data is obtained;

[0096] performing sensitivity classification and labeling on the first data to obtain second data;

[0097] processing the second data according to different sensitivity levels to obtain third data;

[0098] Determining fourth data to be uploaded to the server from the third data;

[0099] The server is configured to:

[0100] Decrypting the fourth data after receiving it, synchronously integrating the multi-source data according to the timestamp, and constructing a user health data set;

[0101] Inputting the user health data set into a preset health analysis model to obtain the user's health analysis results, and sending the health analysis results to the smart underwear;

[0102] Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record;

[0103] The edge computing chip is further configured to: provide personalized health advice and reminders to the user based on the health analysis results through the feedback device of the smart underwear; at the same time, collect user interactive feedback on the feedback information, modify the parameters of the artificial intelligence model in real time, and optimize subsequent health analysis results;

[0104] The server is also configured to utilize digital twin technology to drive a virtual digital model with user physiological data, simulate the user's physical responses in different health states and exercise scenarios, predict potential health problems, and develop a health management plan.

[0105] The technical solution of the present invention is adopted, and the data processing method of smart underwear based on artificial intelligence includes: using the smart sensor set in the smart underwear to collect the user's physiological data and environmental perception data; pre-processing the collected physiological data and environmental perception data in the edge computing chip of the smart underwear to obtain first data; the edge computing chip performs sensitivity classification and labeling on the first data to obtain second data; the edge computing chip processes the second data according to different sensitivity levels to obtain third data; the edge computing chip determines the fourth data uploaded to the server from the third data; the server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct a user health data set; the server The user's health data set is input into a preset health analysis model to obtain the user's health analysis results, which are then sent to the smart underwear. Throughout the data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record. Based on the health analysis results, the edge computing chip provides personalized health advice and reminders to the user through the smart underwear's feedback device. At the same time, the user's interactive feedback on the feedback information is collected, and the parameters of the artificial intelligence model are modified in real time to optimize subsequent health analysis results. The server uses digital twin technology to drive a virtual digital model with the user's physiological data, simulate the user's physical response in different health states and exercise scenarios, predict potential health problems, and formulate a health management plan. The solution of the present invention combines multiple advanced technologies such as edge computing, deep learning, blockchain, and digital twins, not only improving the accuracy of smart underwear data analysis, but also enhancing the security and privacy protection of user data during transmission and processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0106] Figure 1 This is a flow chart of an artificial intelligence-based smart underwear data processing method provided by one embodiment of the present invention;

[0107] Figure 2 This is a schematic block diagram of an artificial intelligence-based intelligent underwear data processing system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0108] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0109] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0110] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0111] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0112] Refer to the following Figures 1 to 2 To describe an artificial intelligence-based smart underwear data processing method and system provided according to some embodiments of the present invention.

[0113] like Figure 1 As shown, one embodiment of the present invention provides an artificial intelligence-based smart underwear data processing method, comprising:

[0114] Smart sensors installed in smart underwear collect the user's physiological data and environmental perception data. The collection frequency is set to different preset values based on the sensor type, and the collected data is time-stamped.

[0115] In this step, the smart sensors include but are not limited to heart rate sensors, body temperature sensors, pressure sensors, image acquisition sensors, etc. These smart sensors can collect the user's physiological data and environmental perception data. For example, the image acquisition sensor can be used to collect skin image data; and the edge computing chip in the smart underwear can use image recognition technology to process the skin image data, monitor the skin condition, identify skin abnormalities (such as rashes, redness and swelling), and fuse image features with other physiological data for analysis.

[0116] After preprocessing the collected physiological data and environmental perception data in the edge computing chip of the smart underwear, first data is obtained;

[0117] In this step, preprocessing includes filtering and denoising to remove motion artifacts caused by body movement, dynamically adjusting filter parameters using an adaptive filtering algorithm, and data normalization to map data of different scales to the [0, 1] range. The edge computing chip is a customized low-power, high-computing chip with a built-in Trusted Execution Environment (TEE), which can perform zero-knowledge proof-related cryptographic operations, sensitive data processing, and other data processing operations within the TEE.

[0118] The edge computing chip performs sensitivity classification and labeling on the first data to obtain second data;

[0119] In this step, a multimodal data fusion algorithm may be used to perform privacy / sensitivity grading on the smart underwear data, wherein the privacy / sensitivity level includes at least five levels.

[0120] The edge computing chip processes the second data according to different sensitivity levels to obtain third data;

[0121] In this step, you can choose whether to use zero-knowledge proof technology to process private data based on the data type and real-time requirements. During processing, a proof key and verification key are generated according to the predetermined zero-knowledge proof algorithm. The proof key is used to process the private data and generate a zero-knowledge proof, which is temporarily stored along with the processing results. The data that has undergone preliminary edge computing processing is encrypted using the Advanced Encryption Standard (AES) algorithm and transmitted to the server via the IoT communication module using a secure transmission protocol (SSL / TLS). Differential privacy technology is used to add controllable random noise to the data during big data analysis, protecting the statistical characteristics of group data while concealing individual private data. If zero-knowledge proof-related data exists, the verification key, zero-knowledge proof, and processing results are transmitted in sequence.

[0122] The edge computing chip determines fourth data to be uploaded to the server from the third data;

[0123] The server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct a user health data set;

[0124] The server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results (including but not limited to disease risk warning and physical fatigue level assessment), and sends the health analysis results to the smart underwear;

[0125] It is understood that the health analysis model is pre-trained based on a deep learning algorithm, capable of identifying physiological data patterns corresponding to different health states and outputting health analysis results for the user. The health analysis model training method includes collecting a large number of user physiological data samples labeled with health states, using transfer learning to pre-train the model infrastructure on a large public health dataset, and then fine-tuning the model parameters for the specific data collected by the smart underwear, optimizing the loss function until convergence.

[0126] Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record;

[0127] It is understandable that users can view access details and set third-party data access permissions through the smart terminal APP; the blockchain technology adopts the form of a consortium chain, with smart underwear manufacturers, cloud service providers, and authorized medical institutions acting as consortium nodes to jointly maintain the data access ledger.

[0128] Based on the health analysis results, the edge computing chip provides personalized health advice and reminders to the user through the smart underwear's feedback devices (such as micro-vibration motors, voice devices, flexible displays, etc.). At the same time, it collects user feedback on the feedback information, modifies the parameters of the artificial intelligence model in real time, and optimizes subsequent health analysis results.

[0129] The server uses digital twin technology to drive a virtual digital model with the user's physiological data, simulates the user's physical responses in different health conditions and sports scenarios, predicts potential health problems, and develops a health management plan.

[0130] It can be understood that with the help of three-dimensional modeling technology, a three-dimensional pressure distribution model is constructed based on the pressure data collected by the pressure sensor equipped with the smart underwear to assist in judging the comfort of the underwear and body posture changes; the digital twin model has a mapping relationship with the body's physiological system, and through continuous collection and comparison of (processed) physiological data and model simulation data, dynamic calibration and update are carried out to ensure the accuracy of the simulation.

[0131] The solution of this embodiment combines multiple advanced technologies such as edge computing, deep learning, blockchain and digital twins, which not only improves the accuracy of smart underwear data analysis, but also enhances the security and privacy protection of user data during transmission and processing.

[0132] In some possible implementations of the present invention, the step of the edge computing chip performing sensitivity classification and labeling on the first data to obtain second data includes:

[0133] extracting temporal features, spatial features, and semantic features of the first data;

[0134] Using a preset feature vector extraction algorithm, different types of sensor data are converted into standardized feature vectors;

[0135] Construct a multimodal feature fusion matrix to fuse data features of different dimensions;

[0136] Analyze the feature fusion matrix based on the preset sensitivity assessment model;

[0137] Calculate the privacy exposure risk value of the data, which takes into account the identifiability, relevance, and harmfulness of the data;

[0138] According to the corresponding relationship between the risk value and the preset sensitivity level, the sensitivity level of the data is determined and marked, thereby obtaining second data.

[0139] In this embodiment, the sensitivity level can be divided into the following five levels:

[0140] Level 1: Direct identification information (e.g. biometric data such as fingerprints, facial recognition features, iris information, genetic information, etc.);

[0141] Level 2: Indirect identification information (such as precise physiological indicator data, undisclosed major disease information, etc.);

[0142] Level 3: Sensitive behavioral data (such as activity patterns, dressing habits, etc.);

[0143] Level 4: General behavioral data (such as basic physiological status; age distribution of smart underwear users, regional distribution data, average sleep duration of users in a certain area, and other aggregated data);

[0144] Level 5: Environmental perception data (such as temperature and humidity), basic parameters disclosed by the device, and other data not included in the above four levels.

[0145] In this embodiment, the privacy / sensitivity level is divided into five levels, so that corresponding processing methods can be used for data belonging to different levels. It should be understood that the division of privacy / sensitivity levels in this embodiment is merely an example; the division of privacy / sensitivity levels can be defined as needed, or intelligently divided into levels through big data analysis and artificial intelligence, or other level division methods can be used, and the embodiments of the present invention are not limited to this.

[0146] In some possible implementations of the present invention, a dynamic adjustment step and a logging step are also included; the dynamic adjustment step specifically includes: continuously monitoring data usage and changes in privacy risks; dynamically adjusting classification standards based on user feedback and privacy requirements; updating data processing strategies in real time; optimizing sensitivity assessment model parameters; the logging step specifically includes: recording data classification results on the blockchain; recording each data access and processing operation; saving classification adjustment history; and establishing a data processing audit trail.

[0147] The solution of this embodiment can achieve hierarchical and refined protection of data privacy, reduce the risk of sensitive data leakage, and ensure user privacy security; optimize computing resource utilization through differentiated processing strategies, reduce encryption and decryption overhead, and improve data processing efficiency; achieve refined control of data access, provide a flexible permission management mechanism, and support multi-scenario data applications; ensure that data processing is traceable throughout the entire process, support privacy compliance audits, and facilitate problem location and processing; support dynamic adjustment of privacy protection strategies to adapt to the privacy needs of different users and meet the requirements of different application scenarios.

[0148] In some possible implementations of the present invention, the step of the edge computing chip processing the second data according to different sensitivity levels to obtain third data includes:

[0149] extracting first-level data (i.e., data with a sensitivity level marked as first level) from the second data;

[0150] The server sends a first processing program to the edge computing chip;

[0151] The edge computing chip receives the first processing program and processes the first level data using the first processing program, and then sends first feedback data to the server;

[0152] The server receives the first feedback data and verifies the first feedback data;

[0153] If the verification is passed, a first processing program invalidation instruction is sent;

[0154] If the verification fails, adjusting the first processing procedure based on the first feedback data to obtain a second processing procedure;

[0155] Sending an invalidation instruction of the second processing program and the first processing program to the edge computing chip;

[0156] The edge computing chip receives the second processing program and processes the first level data using the second processing program;

[0157] Repeat the above steps until the feedback data sent by the edge computing chip passes the verification.

[0158] In this embodiment, the first level of data is processed using a one-time processing program sent by the server to the edge computing chip, specifically: the server sends a one-time first processing program to the edge computing chip; the edge computing chip receives the first processing program and uses the first processing program to process the data, and then sends first feedback data to the server; the server receives the first feedback data and verifies the first feedback data; if the verification is passed, an invalidation instruction of the first processing program is sent; if the verification is not passed, the first processing program is adjusted based on the first feedback data to obtain a second processing program; the invalidation instruction of the second processing program and the first processing program is sent to the edge computing chip; the edge computing chip receives the second processing program and uses the second processing program to process the data; the above steps are repeated until the feedback data sent by the edge computing chip passes the verification.

[0159] In some possible implementations of the present invention, the step of the edge computing chip determining, from the third data, fourth data to be uploaded to the server includes:

[0160] Determining the service processing type and service processing content of the server;

[0161] Detecting the degree of data duplication of the third data (including: calculating a data similarity matrix, identifying redundant data segments, and marking mergeable data), and performing data downsampling to retain key time node data to obtain intermediate data with timestamps;

[0162] Performing data value assessment on the intermediate data, including: calculating the information entropy value of the intermediate data; evaluating the contribution of the intermediate data to the business processing type and business processing content of the server (including: calculating feature importance scores, analyzing data novelty, evaluating data representativeness, etc.); generating a data value score for the intermediate data; and establishing a data value priority queue for the intermediate data based on the data value score;

[0163] Determine the upload priority threshold based on the current network bandwidth, server load, and data transmission cost;

[0164] Segmenting the intermediate data in combination with the data value priority queue, extracting data feature vectors, performing data compression (including applying a lossless compression algorithm, evaluating compression efficiency, and ensuring data reproducibility), and generating multiple compressed data packets;

[0165] The compressed data packets are prioritized based on the preset rules for filtering data (including checking data integrity, verifying data timeliness, and assessing privacy risks) and the upload priority threshold to determine an upload data set to obtain fourth data.

[0166] The solution of this embodiment can reduce the amount of data transmitted, optimize network bandwidth utilization, reduce transmission delay, and improve data throughput; ensure the value of uploaded data, reduce data redundancy, maintain data integrity, and improve data availability; optimize storage space usage, reduce processing overhead, improve computing efficiency, and balance system load; support dynamic network environments, adapt to different data characteristics, meet diverse needs, and facilitate policy adjustments.

[0167] In some possible implementations of the present invention, the server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data based on the timestamp to construct the user health data set, including:

[0168] Receiving and verifying the fourth data, including: verifying the integrity of data transmission: checking the signature of the data packet, checking the integrity of the data packet sequence, and verifying the validity of the timestamp; identifying the source and type of the data; parsing the format of the data packet; and generating a receipt confirmation message;

[0169] Decrypting the fourth data includes: obtaining a decryption key from a secure key management system; performing decryption operations on different encryption types: decrypting homomorphically encrypted data, processing differentially private data, and restoring desensitized data; verifying the correctness of the decryption result; and recording a decryption operation log.

[0170] The steps for aligning the decrypted data timestamps include: extracting data timestamp information; unifying time standards: converting timestamps in different time zones, calibrating device clock deviations, and processing sampling time errors; establishing a time index structure; and identifying data temporal relationships.

[0171] The steps for synchronizing multi-source data after timestamp alignment include: identifying relationships between data; performing time window partitioning: setting the synchronization time window size, handling data sampling frequency differences, and aligning data sampling points; filling missing data: applying interpolation algorithms, marking filled data, and evaluating filling reliability; and handling data conflicts.

[0172] The steps for quality assessment of synchronized data include: detecting outliers: statistical feature analysis, time series pattern recognition, marking abnormal data points; evaluating data consistency; calculating data reliability scores; generating quality assessment reports;

[0173] The data integration steps after synchronization include: building a unified data model: defining data field mapping, unifying measurement units, and standardizing data formats; merging multi-source data; establishing data association indexes; and optimizing storage structures;

[0174] Metadata management steps include: recording data processing; updating data catalogs; generating data summaries;

[0175] The steps for constructing a user health dataset include: organizing a hierarchical data structure; establishing a fast retrieval mechanism; implementing an incremental update strategy; and optimizing access performance.

[0176] The solutions of the embodiments of the present invention can ensure data integrity, improve data accuracy, enhance data consistency, and optimize data availability; they can also increase data processing speed, optimize resource utilization, reduce processing delays, and support large-scale data processing; facilitate data retrieval, support complex queries, provide real-time access, and optimize data analysis efficiency; ensure data security, provide fault-tolerant mechanisms, support data recovery, and ensure service stability; support data source expansion, adapt to data scale growth, facilitate functional upgrades, and be compatible with new data types; ensure data security processing, control access rights, and protect user privacy.

[0177] In some possible implementations of the present invention, the server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results, and sends the health analysis results to the smart underwear, including:

[0178] Preprocessing the user health data set includes: performing data standardization processing: normalizing numerical features, encoding category features, and processing time series features; constructing feature vectors: extracting statistical features, generating time series features, and calculating derived features; processing missing values and outliers; and generating an analysis data set;

[0179] Model selection and configuration, including: loading the following preset health analysis models according to the analysis task: disease risk prediction model, fatigue assessment model, health status classification model; configuring the model parameters of the loaded model: setting the inference threshold, adjusting the model weight, and optimizing the prediction parameters; initializing the operating environment of the loaded model; and verifying the model status of the loaded model;

[0180] It is understandable that the preset health analysis model includes but is not limited to one or more of a disease risk prediction model, a fatigue level assessment model, and a health status classification model.

[0181] Performing health risk assessment based on the disease risk prediction model includes: executing disease risk prediction: analyzing abnormalities in physiological indicators, evaluating changes in health trends, and calculating risk probability distribution; generating risk ratings: determining risk levels, identifying key risk factors, and calculating risk confidence; generating early warning information; and recording the assessment process;

[0182] Performing fatigue analysis based on the fatigue assessment model includes: analyzing physiological data patterns: assessing heart rate variability, analyzing activity intensity, and monitoring recovery status; calculating a fatigue index: integrating multi-dimensional indicators, applying a fatigue assessment algorithm, and generating a fatigue level; evaluating recovery recommendations; and recording analysis results.

[0183] Comprehensively process the risk assessment results and fatigue analysis results based on the health status classification model, including: integrating multi-model prediction results: weighting and fusing prediction values, eliminating prediction conflicts, and optimizing result reliability; generating a health report: summarizing key findings, providing detailed explanations, and formulating recommended solutions; marking important reminders; and storing comprehensive analysis results;

[0184] Generate personalized recommendations based on the comprehensive analysis results, including: customizing recommendations based on user profiles: considering user health history, analyzing lifestyle habits, and assessing exercise capacity; formulating improvement plans: generating action recommendations, setting health goals, and planning intervention measures; generating reminder strategies; and optimizing recommendation content;

[0185] generating a health analysis result based on the comprehensive analysis result and the personalized recommendation;

[0186] The steps for transmitting health analysis results include: packaging analysis results: compressing data packets, adding security identifiers, generating verification codes; establishing a secure channel; executing batch transmission; and confirming that the transmission is complete.

[0187] Feedback tracking steps include: monitoring the implementation of recommendations; collecting user feedback; updating personalized parameters; and optimizing health analysis models.

[0188] The solution of this embodiment can improve the accuracy of risk prediction, enhance the precision of fatigue assessment, optimize the reliability of health assessment, and improve the timeliness of early warning; it can realize personalized customization of suggestions, adapt to individual differences, provide accurate health guidance, and optimize user experience; support real-time health monitoring, quickly respond to abnormal situations, issue early warning information in a timely manner, and dynamically adjust suggestions; provide explanations of analysis results, clarify the source of risks, support tracking of decision-making basis, and enhance user understanding; optimize computing resource utilization, improve processing efficiency, ensure service stability, and support large-scale analysis; support dynamic model updates, adapt to changes in health status, optimize analysis strategies, and improve system robustness.

[0189] In some possible implementations of the present invention, the method for constructing the health analysis model includes:

[0190] Training data collection and preprocessing steps include: collecting multi-source training data (including physiological data collected by smart underwear, user health record data, annotated data provided by medical institutions, and public health data sets); data cleaning and standardization (including removing outliers and noise, handling missing values, and unifying data formats and units); constructing a standard data set; and generating a data quality report.

[0191] Feature engineering steps include: time series feature extraction (including: calculating statistical features, extracting trend features, constructing period features, and generating frequency domain features); feature selection and dimensionality reduction (including: calculating feature importance, performing correlation analysis, and applying dimensionality reduction algorithms); constructing feature combinations; and verifying feature validity.

[0192] Model architecture design steps include: designing the deep learning network structure (including defining the input layer structure, designing the feature extraction layer, building the attention mechanism, and designing the output layer structure); configuring model parameters (including setting the learning rate strategy, selecting the optimizer type, and defining the loss function); implementing model components; and verifying the model structure.

[0193] Model training steps include: performing transfer learning (including loading a pre-trained model, freezing base layer parameters, and adapting to the target task); implementing phased training (performing a pre-training phase, performing fine-tuning training, and optimizing model parameters); monitoring the training process; and recording training logs.

[0194] Model evaluation and optimization steps include: performing multi-dimensional evaluation (including calculating accuracy metrics, evaluating generalization ability, and analyzing prediction bias); performing model optimization (including adjusting network structure, optimizing hyperparameters, and improving training strategies); performing comparative experiments; and generating evaluation reports.

[0195] The model fusion steps include: building an ensemble learning framework (including: selecting a basic model, designing an fusion strategy, and optimizing weight distribution); implementing model fusion (including: training sub-models, optimizing fusion parameters, and verifying fusion effects); evaluating fusion performance; and selecting the optimal solution.

[0196] Model deployment steps include: model conversion and optimization (including: compressing model size, quantizing model parameters, and optimizing computing efficiency); deployment environment configuration (including: setting up the operating environment, configuring computing resources, and optimizing inference performance); implementing performance testing; and monitoring operating status.

[0197] Continuous optimization steps include: collecting feedback from actual applications; updating training data; optimizing model structure; and improving deployment strategies.

[0198] The solution of the embodiment of the present invention can improve prediction accuracy, enhance model stability, improve generalization ability, and reduce prediction latency; it can support personalized prediction, adapt to changes in data distribution, handle diverse scenarios, and enhance migration capabilities; optimize inference speed, reduce resource consumption, improve concurrent processing capabilities, and reduce storage overhead; it facilitates model updates, supports online learning, simplifies deployment processes, and facilitates fault diagnosis.

[0199] In some possible implementations of the present invention, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0200] extracting second-level data (i.e., data with a sensitivity level marked as the second level) from the second data;

[0201] dividing the second-level data into first data to be processed, second data to be processed, and third data to be processed;

[0202] It is understandable that in order to keep data confidential more finely and accurately, the second-level data that needs to be transmitted to the server can be further refined. According to the different protection strengths / characteristics of data for zero-knowledge proof technology, homomorphic encryption technology, and differential privacy noise encryption technology, the second-level data can be divided into first data to be processed, second data to be processed, and third data to be processed, and the first data to be processed, second data to be processed, and third data to be processed are processed using zero-knowledge proof technology, homomorphic encryption technology, and differential privacy noise encryption technology respectively.

[0203] Initial TEE environment, verify the environment integrity, and generate a zero-knowledge proof key pair within the TEE;

[0204] As you can understand, TEE stands for Trusted Execution Environment, a hardware-based secure computing environment designed to protect the code and data running within it from unauthorized access and tampering. By isolating a portion of the processor from the main operating system, TEE provides a secure execution environment, ensuring the security of sensitive operations and data.

[0205] Extracting features from the first data to be processed and constructing a circuit required for proof;

[0206] It's understandable that, in essence, the "circuit" here isn't a physical circuit, but rather an abstract computational model, similar to the combination of logic gates (AND, OR, NOT, etc.) in digital circuits. It defines the flow and rules for a series of computational operations. It breaks down complex data processing tasks into logical chains composed of basic arithmetic units, transforming and computing the input data according to predetermined logic, ultimately producing an output. These "circuits" are often represented by polynomial functions. Polynomials have many advantageous properties in cryptography, such as computational efficiency and the mathematically difficult nature of security. A simple addition circuit might correspond to the polynomial f(x, y) = x + y, while a multiplication circuit might correspond to g(x, y) = x * y. Complex computations are the result of nested combinations of multiple polynomials. In the context of zero-knowledge proofs, proving a statement about private data to a verifier requires constructing such a circuit. For example, to prove that a user's age is greater than 18 (assuming age is private data), a comparison circuit is constructed with the user's age as input and a Boolean output value. If the value is greater than 18, the output is "true", otherwise, "false". This circuit defines the target relationship to be proved, and all subsequent proof processes revolve around it. Different zero-knowledge proof protocols (such as zk-SNARKs and zk-STARKs) have different requirements and optimization methods for circuit construction. Some protocols prefer simple circuits to reduce computational complexity and proof size, while others focus on scalability to handle large-scale, complex data processing scenarios. When constructing a circuit, the circuit structure should be adjusted based on the selected protocol, and the appropriate polynomial representation should be selected to ensure the subsequent generation and verification of zero-knowledge proofs. When the circuit is running, it only processes an abstract representation of the data, and the actual private data is not exposed. For example, in cryptocurrency transactions, to prove that the transaction amount is within a certain legal range, the constructed circuit processes the encrypted form of the amount or the result of homomorphic encryption. The actual amount cannot be seen by the outside world, but the legitimacy of the transaction can be verified through the circuit output.

[0207] Generating a zero-knowledge proof, including: converting the first to-be-processed data into a polynomial expression; generating proof parameters using an elliptic curve cryptography algorithm; constructing a commitment scheme to ensure data correctness; generating a non-interactive zero-knowledge proof; and verifying the validity of the generated zero-knowledge proof;

[0208] Generate homomorphic encryption keys based on lattice cryptography;

[0209] Splitting the second to-be-processed data into data blocks suitable for homomorphic operations;

[0210] Perform homomorphic encryption on each data block (including: mapping the data onto a polynomial ring; adding random noise; performing lattice cryptographic operations), generate first encrypted data that supports ciphertext domain operations, and record encryption parameters for subsequent decryption;

[0211] Determine noise parameters based on the Laplace mechanism (including: evaluating the privacy budget ε; calculating noise distribution parameters; generating random noise sequences);

[0212] adding differential privacy noise to the third data to be processed according to the noise parameter to obtain second encrypted data;

[0213] Verify the data availability after adding differential privacy noise and dynamically adjust the noise parameters to balance privacy protection and data availability;

[0214] Integrate the generated zero-knowledge proof, the first encrypted data, and the second encrypted data to obtain third data;

[0215] Classify and store the third data, establish a data index structure, record metadata of the data processing process, and generate a data processing report;

[0216] Verify the integrity of third-party data, check privacy protection effects, evaluate data availability, generate processing records and upload them to the blockchain.

[0217] Through the solution of this embodiment, zero-knowledge proof of data can be achieved to ensure that the original data is not exposed; support encrypted data calculation, provide quantifiable differential privacy protection, and prevent data re-identification attacks; retain the core statistical characteristics of the data, support data analysis in an encrypted state, ensure the accuracy of data analysis results, and achieve a balance between privacy protection and data utility; optimize the efficiency of cryptographic operations, reduce encryption overhead, support parallel processing, and reduce storage space occupancy; ensure the security of the data processing environment, support integrity verification of the data processing process, provide reliable audit tracking, and prevent unauthorized data access; support different types of sensitive data processing, adapt to different application scenarios, facilitate function expansion and upgrades, and be compatible with mainstream privacy computing frameworks.

[0218] In some possible implementations of the present invention, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0219] extracting third-level data (i.e., data with a sensitivity level marked as the third level) from the second data;

[0220] Determine the privacy budget parameters based on the characteristics of Level 3 data and privacy protection requirements (the smaller the privacy budget, the greater the added noise intensity and the higher the degree of data privacy protection, but it also has a greater impact on data availability; conversely, the larger the privacy budget, the relatively smaller the noise intensity, the higher the data availability, and the weaker the privacy protection);

[0221] Select the corresponding noise distribution based on the data type of the third-level data (Gaussian distribution is usually used for continuous data and Laplace distribution is often used for discrete data);

[0222] Perform preliminary cleaning of the third-level data to remove erroneous values, outliers, and irrelevant redundant information (to ensure data quality and ensure that subsequent noise addition and processing are based on reliable data);

[0223] Based on the selected noise distribution and privacy budget parameters, a random number generator is used to generate the corresponding random noise (for example, if a Laplace distribution is used, a scale parameter is given to generate a sequence of noise values that conform to the distribution for mixing into the data);

[0224] The generated random noise is added to the preprocessed third level data to obtain third data.

[0225] It's understandable that during key steps like data aggregation and statistical calculations, noise is added to the corresponding elements of the original data (for numerical data) one by one. This process imbues each data point with noise, obfuscating the actual data and preventing attackers from inferring sensitive individual information from minor data differences. This noisy data is then used for subsequent data analysis, mining, or machine learning model training. Even if a third party obtains this data, the noise interference makes it difficult to accurately restore the original data. At the same time, by properly setting a privacy budget, the preserved statistical characteristics of the data can still support common business needs, such as group trend analysis and correlation research. At specific stages of the data processing pipeline, differential privacy evaluation metrics, such as calculating the probability of change in the output of adjacent data sets before and after processing, are used to verify compliance with pre-defined privacy budgets. If privacy protection is found to be insufficient or data availability is excessively compromised, the privacy budget parameters or noise distribution are adjusted to optimize the processing effect.

[0226] The solution of this embodiment effectively conceals the precise information of individual data by adding carefully designed noise, making it extremely difficult for a third party to reversely deduce the original data of a specific individual even if they have access to a large amount of relevant data, thereby protecting the privacy content in the third-level data; despite the introduction of noise, a reasonable setting of the privacy budget can ensure that the approximate statistical characteristics of the data are retained, and it can still be used for group-level data analysis and macro-trend derivation, so that the business will not completely lose the value of data utilization while protecting privacy, and take into account both privacy and functional requirements; the application of differential encryption technology helps to meet the requirements of various data privacy regulations, and in data disclosure and sharing scenarios, it proves to regulators and users that sufficient privacy protection measures have been taken, reducing compliance risks and enhancing user trust; because noise destroys the accuracy of the data, it is difficult for attackers to obtain sensitive information through common means such as differential attacks, thereby enhancing the security and robustness of data in the face of potential privacy attacks.

[0227] In some possible implementations of the present invention, the step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data further includes:

[0228] extracting fourth-level data (i.e., data with a sensitivity level marked as the fourth level) from the second data;

[0229] Processing the fourth-level data using a preset fourth-level data processing model to obtain third data;

[0230] The steps of constructing the fourth-level data processing model include:

[0231] Identify multiple participants holding Level 4 training data (which can be data centers of smart wearable device manufacturers, medical and health institutions, etc.; or smart wearable devices (such as smart underwear, smart bracelets, etc.), various testing equipment, etc.). Preprocess the Level 4 training data on the participant's local edge computing devices or data centers (preprocessing includes basic operations such as noise removal and normalization to make the data suitable for model training). The data of each participant is always retained locally, and the original data is not transmitted externally.

[0232] Each participant independently selects a corresponding machine learning model architecture based on its own data characteristics and business needs (e.g., if focusing on health trend prediction, a long short-term memory network (LSTM) can be selected; if performing simple classification tasks, a decision tree model is also an option; etc.), and randomly initializes the model parameters in preparation for local training;

[0233] Using local Level 4 training data, each participant begins training the initialized model, using optimization algorithms (such as stochastic gradient descent (SGD) and its variants Adagrad and Adam). Over multiple rounds of iterations, the model parameters are continuously updated to gradually fit the characteristics and patterns of the local data.

[0234] After a preset number of rounds of local training, each participant extracts the key parameters of the trained model (such as the weight matrix and bias vector in the neural network), uploads these abstracted key parameters without the original data information to the server via a secure communication channel (in this process, to ensure the security of transmission, encrypted transmission protocols such as SSL / TLS may be used);

[0235] After receiving the key parameters uploaded by each participant, the server uses a preset aggregation algorithm (e.g., weighted average method) to comprehensively consider factors such as the data volume and data quality of each participant, assigns corresponding weights, aggregates and integrates all key parameters, and updates the global model (this process is only a mathematical operation on abstract parameters and cannot reversely deduce the original data of each participant);

[0236] Transmitting the updated new parameters of the global model back to each of the participants through a secure channel;

[0237] Each of the participants uses the received new parameters to replace the original corresponding part in the local model, completes the update of the local model, and obtains its own fourth-level data processing model;

[0238] Based on the updated fourth-level data processing model, each of the participants continues to use new data for training, upload parameters, receive new global models, and continuously optimize model performance, so that the fourth-level data processing model's processing capabilities for fourth-level data will gradually improve.

[0239] In the solution of this embodiment, the original fourth-level data does not leave the local environment throughout the process, avoiding the risk of privacy leakage caused by data sharing. All participants can not only collaborate to improve the model effect, but also protect the privacy rights and interests of the data owner; by aggregating the data features of multiple parties, compared with a single participant relying solely on its own limited data to train the model, the global model incorporates richer information and can capture more comprehensive patterns and trends, significantly enhancing the accuracy and robustness of data prediction, classification and other processing; each participant does not need to expend a lot of resources to collect massive data to train high-level models on their own. Through the federated learning method of sharing model parameters, the cost of data collection, storage and processing is reduced, while overall business efficiency is improved; new participants can easily join the federated learning system as long as they hold the same type of fourth-level data, quickly integrate and contribute their own data features, promote the continuous evolution of the model, and adapt to the dynamic development of the business.

[0240] In some possible implementations of the present invention, the step of the edge computing chip processing the second data according to different sensitivity levels to obtain third data includes:

[0241] Extracting fifth-level data (i.e., data with a sensitivity level marked as fifth) from the second data:

[0242] Performing basic encryption on the fifth-level data;

[0243] Data classification and aggregation are performed on the encrypted data, and general access control is established on the classified and aggregated data to obtain third data.

[0244] In an embodiment of the present invention, the second level of data is processed in combination with zero-knowledge proof technology and other technologies; the third level of data is processed using differential encryption technology; the fourth level of data is processed using federated learning technology; and the fifth level of data is processed using ordinary encryption technology.

[0245] See Figure 2 Another embodiment of the present invention provides an artificial intelligence-based smart underwear data processing system for executing an artificial intelligence-based smart underwear data processing method, comprising: a server, and smart underwear equipped with a smart sensor and an edge computing chip; wherein,

[0246] The smart sensor is configured to: collect physiological data and environmental perception data of the user, wherein the collection frequency is set to different preset values according to the sensor type, and the collected data is time-stamped;

[0247] The edge computing chip is configured as follows:

[0248] After preprocessing the collected physiological data and environmental perception data, first data is obtained;

[0249] performing sensitivity classification and labeling on the first data to obtain second data;

[0250] processing the second data according to different sensitivity levels to obtain third data;

[0251] Determining fourth data to be uploaded to the server from the third data;

[0252] The server is configured to:

[0253] Decrypting the fourth data after receiving it, synchronously integrating the multi-source data according to the timestamp, and constructing a user health data set;

[0254] Inputting the user health data set into a preset health analysis model to obtain the user's health analysis results, and sending the health analysis results to the smart underwear;

[0255] Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record;

[0256] The edge computing chip is further configured to: provide personalized health advice and reminders to the user based on the health analysis results through the feedback device of the smart underwear; at the same time, collect user interactive feedback on the feedback information, modify the parameters of the artificial intelligence model in real time, and optimize subsequent health analysis results;

[0257] The server is also configured to utilize digital twin technology to drive a virtual digital model with user physiological data, simulate the user's physical responses in different health states and exercise scenarios, predict potential health problems, and develop a health management plan.

[0258] It should be known that Figure 2 The block diagram of the AI-based intelligent underwear data processing system is for illustrative purposes only, and the number of modules shown does not limit the scope of protection of the present invention. The AI-based intelligent underwear data processing system provided in this embodiment can be used to implement the various embodiments of the corresponding AI-based intelligent underwear data processing method. For detailed implementation, please refer to the descriptions of the respective method embodiments and will not be elaborated here.

[0259] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0260] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0261] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0262] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0263] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0264] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0265] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0266] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, according to the idea of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0267] Although the present invention is disclosed above, it is not limited thereto. Any person skilled in the art may readily conceive of variations or substitutions, and may make various modifications and alterations without departing from the spirit and scope of the present invention. Combinations of the above-described functions and implementation steps, including software and hardware implementations, are all within the scope of protection of the present invention.

Claims

1. A method for processing smart underwear data based on artificial intelligence, characterized in that: include: Smart sensors installed in smart underwear collect the user's physiological data and environmental perception data. The collection frequency is set to different preset values based on the sensor type, and the collected data is time-stamped. After preprocessing the collected physiological data and environmental perception data in the edge computing chip of the smart underwear, first data is obtained; The edge computing chip performs sensitivity classification and labeling on the first data to obtain second data; The edge computing chip processes the second data according to different sensitivity levels to obtain third data; The edge computing chip determines fourth data to be uploaded to the server from the third data; The server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct a user health data set; The server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results, and sends the health analysis results to the smart underwear; Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record; Based on the health analysis results, the edge computing chip provides personalized health advice and reminders to the user through the feedback device of the smart underwear. At the same time, it collects user feedback on the feedback information, modifies the parameters of the artificial intelligence model in real time, and optimizes subsequent health analysis results. The server uses digital twin technology to drive a virtual digital model with the user's physiological data, simulates the user's physical response in different health states and exercise scenarios, predicts potential health problems, and develops health management plans; The step of processing the second data by the edge computing chip according to different sensitivity levels to obtain third data includes: extracting first level data from the second data; The server sends a first processing program to the edge computing chip; The edge computing chip receives the first processing program and processes the first level data using the first processing program, and then sends first feedback data to the server; The server receives the first feedback data and verifies the first feedback data; If the verification is passed, a first processing program invalidation instruction is sent; If the verification fails, adjusting the first processing procedure based on the first feedback data to obtain a second processing procedure; Sending an invalidation instruction of the second processing program and the first processing program to the edge computing chip; The edge computing chip receives the second processing program and processes the first level data using the second processing program; Repeat the above steps until the feedback data sent by the edge computing chip passes the verification.

2. The method for processing intelligent underwear data based on artificial intelligence according to claim 1, characterized in that: The step of the edge computing chip performing sensitivity classification and labeling on the first data to obtain second data includes: extracting temporal features, spatial features, and semantic features of the first data; Using a preset feature vector extraction algorithm, different types of sensor data are converted into standardized feature vectors; Construct a multimodal feature fusion matrix to fuse data features of different dimensions; Analyze the feature fusion matrix based on the preset sensitivity assessment model; Calculate the privacy exposure risk value of the data, which takes into account the identifiability, relevance, and harmfulness of the data; According to the corresponding relationship between the risk value and the preset sensitivity level, the sensitivity level of the data is determined and marked, thereby obtaining second data.

3. The method for processing intelligent underwear data based on artificial intelligence according to claim 2, characterized in that: The step of determining, by the edge computing chip, fourth data to be uploaded to the server from the third data includes: Determining the service processing type and service processing content of the server; Detecting the degree of data duplication of the third data, performing data downsampling, retaining key time node data, and obtaining intermediate data with timestamps; Performing data value evaluation on the intermediate data, including: calculating the information entropy value of the intermediate data; evaluating the contribution of the intermediate data to the business processing type and business processing content of the server; generating a data value score for the intermediate data; and establishing a data value priority queue for the intermediate data based on the data value score; Determine the upload priority threshold based on the current network bandwidth, server load, and data transmission cost; Segmenting the intermediate data in combination with the data value priority queue, extracting data feature vectors, performing data compression, and generating multiple compressed data packets; The compressed data packets are prioritized based on the preset rule screening data and the upload priority threshold to determine an upload data set to obtain fourth data.

4. The method for processing intelligent underwear data based on artificial intelligence according to claim 3, characterized in that: The server decrypts the fourth data after receiving it, and synchronously integrates the multi-source data according to the timestamp to construct the user health data set, including: Receiving and verifying the fourth data, including: verifying the integrity of data transmission: checking the signature of the data packet, checking the integrity of the data packet sequence, and verifying the validity of the timestamp; identifying the source and type of the data; parsing the format of the data packet; and generating a receipt confirmation message; Decrypting the fourth data includes: obtaining a decryption key from a secure key management system; performing decryption operations on different encryption types: decrypting homomorphically encrypted data, processing differentially private data, and restoring desensitized data; verifying the correctness of the decryption result; and recording a decryption operation log. The steps for aligning the decrypted data timestamps include: extracting data timestamp information; unifying time standards: converting timestamps in different time zones, calibrating device clock deviations, and processing sampling time errors; establishing a time index structure; and identifying data temporal relationships. The steps for synchronizing multi-source data after timestamp alignment include: identifying relationships between data; performing time window partitioning: setting the synchronization time window size, handling data sampling frequency differences, and aligning data sampling points; filling missing data: applying interpolation algorithms, marking filled data, and evaluating filling reliability; and handling data conflicts. The steps for quality assessment of synchronized data include: detecting outliers: statistical feature analysis, time series pattern recognition, marking abnormal data points; evaluating data consistency; calculating data reliability scores; generating quality assessment reports; The data integration steps after synchronization include: building a unified data model: defining data field mapping, unifying measurement units, and standardizing data formats; merging multi-source data; establishing data association indexes; and optimizing storage structures; Metadata management steps include: recording data processing; updating data catalogs; generating data summaries; The steps for constructing a user health dataset include: organizing a hierarchical data structure; establishing a fast retrieval mechanism; implementing an incremental update strategy; and optimizing access performance.

5. The method for processing intelligent underwear data based on artificial intelligence according to claim 4, characterized in that: The server inputs the user health data set into a preset health analysis model to obtain the user's health analysis results, and sends the health analysis results to the smart underwear, including: Preprocessing the user health data set includes: performing data standardization processing: normalizing numerical features, encoding category features, and processing time series features; constructing feature vectors: extracting statistical features, generating time series features, and calculating derived features; processing missing values and outliers; and generating an analysis data set; Model selection and configuration, including: loading the following preset health analysis models according to the analysis task: disease risk prediction model, fatigue assessment model, health status classification model; configuring the model parameters of the loaded model: setting the inference threshold, adjusting the model weight, and optimizing the prediction parameters; initializing the operating environment of the loaded model; and verifying the model status of the loaded model; Performing health risk assessment based on the disease risk prediction model includes: executing disease risk prediction: analyzing abnormalities in physiological indicators, evaluating changes in health trends, and calculating risk probability distribution; generating risk ratings: determining risk levels, identifying key risk factors, and calculating risk confidence; generating early warning information; and recording the assessment process; Performing fatigue analysis based on the fatigue assessment model includes: analyzing physiological data patterns: assessing heart rate variability, analyzing activity intensity, and monitoring recovery status; calculating a fatigue index: integrating multi-dimensional indicators, applying a fatigue assessment algorithm, and generating a fatigue level; evaluating recovery recommendations; and recording analysis results. Comprehensively process the risk assessment results and fatigue analysis results based on the health status classification model, including: integrating multi-model prediction results: weighting and fusing prediction values, eliminating prediction conflicts, and optimizing result reliability; generating a health report: summarizing key findings, providing detailed explanations, and formulating recommended solutions; marking important reminders; and storing comprehensive analysis results; Generate personalized recommendations based on the comprehensive analysis results, including: customizing recommendations based on user profiles: considering user health history, analyzing lifestyle habits, and assessing exercise capacity; formulating improvement plans: generating action recommendations, setting health goals, and planning intervention measures; generating reminder strategies; and optimizing recommendation content; generating a health analysis result based on the comprehensive analysis result and the personalized recommendation; The steps for transmitting health analysis results include: packaging analysis results: compressing data packets, adding security identifiers, generating verification codes; establishing a secure channel; executing batch transmission; and confirming that the transmission is complete. Feedback tracking steps include: monitoring the implementation of recommendations; collecting user feedback; updating personalized parameters; and optimizing health analysis models.

6. The method for processing intelligent underwear data based on artificial intelligence according to claim 5, characterized in that: The step of processing, by the edge computing chip, the second data according to different sensitivity levels to obtain third data further includes: extracting second-level data from the second data; dividing the second-level data into first data to be processed, second data to be processed, and third data to be processed; Initial TEE environment, verify the environment integrity, and generate a zero-knowledge proof key pair within the TEE; Extracting features from the first data to be processed and constructing a circuit required for proof; Generating a zero-knowledge proof, including: converting the first to-be-processed data into a polynomial expression; generating proof parameters using an elliptic curve cryptography algorithm; constructing a commitment scheme to ensure data correctness; generating a non-interactive zero-knowledge proof; and verifying the validity of the generated zero-knowledge proof; Generate homomorphic encryption keys based on lattice cryptography; Splitting the second to-be-processed data into data blocks suitable for homomorphic operations; Perform homomorphic encryption on each data block to generate first encrypted data that supports ciphertext domain operations, and record encryption parameters for subsequent decryption; Determine noise parameters based on Laplace mechanism; adding differential privacy noise to the third data to be processed according to the noise parameter to obtain second encrypted data; Verify the data availability after adding differential privacy noise and dynamically adjust the noise parameters to balance privacy protection and data availability; Integrate the generated zero-knowledge proof, the first encrypted data, and the second encrypted data to obtain third data; Classify and store the third data, establish a data index structure, record metadata of the data processing process, and generate a data processing report; Verify the integrity of third-party data, check privacy protection effects, evaluate data availability, generate processing records and upload them to the blockchain.

7. The method for processing intelligent underwear data based on artificial intelligence according to claim 6, characterized in that: The step of processing, by the edge computing chip, the second data according to different sensitivity levels to obtain third data further includes: extracting third-level data from the second data; Determine privacy budget parameters based on the characteristics of Level 3 data and privacy protection requirements; According to the data type of the third-level data, select the corresponding noise distribution; Conduct preliminary cleaning of the third-level data to remove erroneous values, outliers, and irrelevant redundant information; Generate the corresponding random noise using a random number generator based on the selected noise distribution and privacy budget parameters; The generated random noise is added to the preprocessed third level data to obtain third data.

8. The method for processing intelligent underwear data based on artificial intelligence according to claim 7, characterized in that: The step of processing, by the edge computing chip, the second data according to different sensitivity levels to obtain third data further includes: extracting fourth level data from the second data; Processing the fourth-level data using a preset fourth-level data processing model to obtain third data; The steps of constructing the fourth-level data processing model include: Identify multiple participants holding fourth-level training data at the fourth level, and pre-process the fourth-level training data at each participant's local edge computing device or data center; wherein the data of each participant is always retained locally and the original data is not transmitted externally; Each participant independently selects the corresponding machine learning model architecture based on its own data characteristics and business needs, and randomly initializes the model parameters in preparation for local training; Using local fourth-level training data, each participant begins training the initialized model. Using an optimization algorithm, they continuously update the model parameters over multiple rounds of iterations, allowing the model to gradually fit the characteristics and patterns of the local data. After a preset number of rounds of local training, each participant extracts the key parameters of the trained model and uploads these abstracted key parameters, which do not contain original data information, to the server via a secure communication channel; After receiving the key parameters uploaded by each participant, the server uses a preset aggregation algorithm to comprehensively consider factors such as the data volume and data quality of each participant, assigns corresponding weights, aggregates and integrates all key parameters, and updates the global model; Transmitting the updated new parameters of the global model back to each of the participants through a secure channel; Each of the participants uses the received new parameters to replace the original corresponding part in the local model, completes the update of the local model, and obtains its own fourth-level data processing model; Based on the updated fourth-level data processing model, each of the participants continues to use new data for training, upload parameters, receive new global models, and continuously optimize model performance, so that the fourth-level data processing model's processing capabilities for fourth-level data will gradually improve.

9. An artificial intelligence-based smart underwear data processing system, configured to execute the artificial intelligence-based smart underwear data processing method according to any one of claims 1 to 8, characterized in that: include: Server, smart underwear equipped with smart sensors and edge computing chips; The smart sensor is configured to: collect physiological data and environmental perception data of the user, wherein the collection frequency is set to different preset values according to the sensor type, and the collected data is time-stamped; The edge computing chip is configured as follows: After preprocessing the collected physiological data and environmental perception data, first data is obtained; performing sensitivity classification and labeling on the first data to obtain second data; processing the second data according to different sensitivity levels to obtain third data; Determining fourth data to be uploaded to the server from the third data; The server is configured to: Decrypting the fourth data after receiving it, synchronously integrating the multi-source data according to the timestamp, and constructing a user health data set; Inputting the user health data set into a preset health analysis model to obtain the user's health analysis results, and sending the health analysis results to the smart underwear; Throughout the entire data processing process, data access logs are recorded using blockchain technology, and each data access generates an unalterable record; The edge computing chip is further configured to: provide personalized health advice and reminders to the user based on the health analysis results through the feedback device of the smart underwear; at the same time, collect user interactive feedback on the feedback information, modify the parameters of the artificial intelligence model in real time, and optimize subsequent health analysis results; The server is also configured to utilize digital twin technology to drive a virtual digital model with user physiological data, simulate the user's physical responses in different health states and exercise scenarios, predict potential health problems, and develop a health management plan.

Images