Nursing data sharing method and system based on Internet of Things

Abstract

The invention discloses a nursing data sharing method and system based on the Internet of Things. The method comprises the steps that S1, multi-modal nursing data are collected in real time through a distributed Internet of Things terminal cluster, and a feature signal set is formed; s2, constructing a data coordination engine, executing federal learning preprocessing operation on the feature signal set, and forming a coordination signal flow; s3, dynamically calculating a data contribution degree weight and generating a verification signal chain; s4, monitoring vital sign abnormal indexes in the coordination signal flow in real time, and generating a trigger signal vector; and S5, updating incentive mechanism parameters according to the contribution degree voucher in the verification signal chain, optimizing a service quality strategy based on a network resource allocation scheme in the trigger signal vector, and forming a closed-loop control signal. According to the invention, the problem of data islanding effect in the medical care data sharing process can be solved.

Description

Technical Field

[0001] The present invention relates to the cross - field of Internet of Things technology and medical care data processing, and specifically relates to a method and system for sharing nursing data based on the Internet of Things. Background Art

[0002] Currently, the medical care field is facing an explosive growth of data brought about by the popularization of Internet of Things devices, but the traditional data sharing model has significant defects. Information islands are formed among medical institutions due to inconsistent data standards. When patients seek medical treatment across institutions, key nursing data cannot be synchronized in a timely manner, resulting in low medical treatment efficiency. Most existing encryption technologies adopt static strategies, which are difficult to meet the sensitivity requirements of the dynamic changes of nursing data. Moreover, the traditional centralized storage architecture has a risk of single - point failure. The data leakage incident of a medical cloud platform in 2020 exposed the security risks of centralized management.

[0003] In terms of data transmission, conventional network scheduling algorithms cannot distinguish the urgency of nursing data. In emergency scenarios, the transmission delay of key vital sign data may affect the treatment effect. In terms of device compatibility, the communication protocols adopted by Internet of Things terminals of different manufacturers vary significantly. Statistics of a top - tier hospital show that 43 types of devices it accesses involve 7 different protocol standards, resulting in high data integration costs. The lack of a data rights confirmation mechanism leads to low willingness to share data. Research shows that the proportion of medical institutions refusing data sharing due to unclear ownership is as high as 67%. Summary of the Invention

[0004] In view of the above - mentioned disadvantages of the prior art, the purpose of the present invention is to provide a method and system for sharing nursing data based on the Internet of Things, which is used to solve the problems of data island effect, privacy and security risks, and low efficiency of emergency data transmission existing in the process of sharing medical care data. The present invention constructs a collaborative sharing mechanism integrating federated learning and blockchain technology, implements multi - modal data standardization processing at the edge computing layer, uses a dynamic contribution degree evaluation model to incentivize data sharing, and at the same time establishes an emergency channel priority transmission system based on smart contracts, combined with zero - knowledge proof and dynamic spectrum allocation technology, to achieve safe and efficient data flow. In the specific implementation process, the data collected by the distributed terminal cluster is encapsulated with feature signals, and the edge node completes data cleaning and alignment under privacy protection. The blockchain network generates verifiable contribution vouchers through quantitative evaluation. When critical indicators are detected, a cross - domain priority transmission protocol is triggered, and finally the overall system performance is optimized through closed - loop feedback, improving the sharing efficiency while ensuring data security.

[0005] The present invention provides a method for sharing nursing data based on the Internet of Things, including: S1: Real - time collect multi - modal nursing data through a distributed Internet of Things terminal cluster and form a feature signal set; S2: Build a data coordination engine and perform federated learning preprocessing operations on the feature signal set to form a coordinated signal flow. The coordinated signal flow includes encrypted standardized data blocks and an associated quality assessment matrix. The preprocessing operations include abnormal data cleaning, spatio-temporal dimension alignment, and feature vector standardization. S3: Deploy a sharing incentive mechanism based on the blockchain network. Parse the quality assessment matrix in the coordinated signal flow through a smart contract, dynamically calculate the data contribution weight, and generate a verification signal chain. S4: Real-time monitor the vital sign abnormality indicators in the coordinated signal flow. When a preset critical threshold is triggered, generate a trigger signal vector. The trigger signal vector includes an encrypted first aid digital pass and an optimized network resource allocation scheme. S5: Update the incentive mechanism parameters according to the contribution vouchers in the verification signal chain. At the same time, optimize the service quality policy based on the network resource allocation scheme in the trigger signal vector, and form a closed-loop control signal. The closed-loop control signal is synchronized to the data coordination engine to achieve collaborative optimization.

[0006] In an embodiment of the present invention, in step S1, the generation process of the feature signal set includes: deploying a dynamic perception adapter in a distributed Internet of Things terminal cluster. The adapter automatically matches the data encapsulation protocol according to the terminal device type, performs feature extraction on multi-modal nursing data through parallel processing threads. The extraction process fuses the device physical fingerprint and the patient biometric feature to generate a composite identification code. At the same time, establish the binding relationship between the timestamp sequence and the spatial coordinates. The data sensitivity classification mark is dynamically generated by real-time analyzing the relevance between the data content and the clinical context. When detecting core physiological parameters related to patient privacy, the encryption level is automatically increased. The composite identification code includes the device uniqueness identifier generated by irreversible hashing operation and the derivative code after the patient identity feature is obfuscated.

[0007] In an embodiment of the present invention, in step S2, the specific implementation method of abnormal data cleaning is: build a dynamic rule knowledge graph in the data coordination engine. The graph integrates clinical diagnosis and treatment specifications, device technical parameters, and historical data distribution characteristics. Detect outliers in the feature signal set through a sliding time window. The detection process uses an adaptive threshold algorithm based on density clustering. When an abnormal value beyond the physiologically reasonable range is identified, trigger a data repair mechanism. The repair mechanism includes missing value imputation, mutation value smoothing, and context relevance correction. The repaired data block generates a quality assessment matrix with a version identifier, which records the original data confidence and the correction operation track.

[0008] In an embodiment of the present invention, in step S2, the implementation method for spatio-temporal dimension alignment includes: establishing a unified spatio-temporal coordinate system at the edge computing node, correcting the time deviation and spatial offset of the data collected by the device through the indoor positioning system and the geofencing technology. The alignment process uses the sliding window correlation analysis method to match the sampling timings of different devices, implements time-domain compensation for the data stream with communication delay, and at the same time establishes a spatial mapping model according to the device deployment topology structure, converting the discrete spatial data collected by heterogeneous sensors into a continuous distribution data set in the standard coordinate system. The spatio-temporal correction parameters generated by the alignment operation are synchronously injected into the metadata area of the coordination signal stream.

[0009] In an embodiment of the present invention, in step S3, the dynamic calculation process of the data contribution degree weight includes: constructing a multi-dimensional evaluation function in the blockchain network. This function integrates the integrity index in the quality evaluation matrix, the timeliness coefficient of the timestamp sequence, and the clinical value evaluation parameter. Among them, the integrity index is jointly calculated by the data field missing rate and the check code matching degree, the timeliness coefficient decays dynamically according to the interval between the data generation time and the sharing request time, and the clinical value evaluation parameter retrieves and matches the demand priority of the current medical scenario through the knowledge graph. The output value of the evaluation function generates an immutable contribution degree certificate after being verified by node consensus. This certificate forms a non-linear mapping relationship with the data access permission token.

[0010] In an embodiment of the present invention, in step S4, the generation mechanism of the emergency digital pass includes: when it is detected that the abnormal vital sign index exceeds the preset critical threshold, start the multi-factor identity verification process. The verification process integrates the digital certificate of the medical institution, the device biometric signature, and the patient's temporary authorization code, and verifies the identity legitimacy through the zero-knowledge proof protocol without disclosing sensitive information. After successful verification, generate an encrypted pass with a time validity period. This pass contains the decryption key fragment of the emergency care data and the cross-institutional access permission statement. The key fragment needs to be combined with the key fragment held by the recipient to decrypt the core medical data.

[0011] In an embodiment of the present invention, in step S4, the operation logic of the network resource allocation scheme includes: when the priority transmission channel is activated, real-time monitor the wireless channel load status and the network topology structure, calculate the optimal spectrum resource allocation scheme through the game theory model. The allocation process takes into account the transmission delay requirement and the channel interference suppression requirement, implements double guarantees of bandwidth reservation and frequency hopping communication for the emergency data transmission, and at the same time establishes a temporary relay node routing table, dynamically adjusts the data transmission path according to the network congestion degree. The allocation scheme includes the channel switching timing diagram and the modulation and coding strategy combination parameters.

[0012] In one embodiment of the present invention, in step S5, the service quality policy optimization process includes: constructing a policy decision tree in the data sharing application layer, where the decision tree dynamically adjusts the data transmission priority queue according to the network resource allocation scheme in the closed-loop control signal. The optimization process uses a reinforcement learning algorithm to simulate the system performance indicators under different policies, and implements end-to-end transmission guarantee for the emergency care data stream, including establishing an exclusive buffer, increasing the retransmission priority, and dynamically adjusting the error correction coding strength. At the same time, it balances the service quality requirements of the regular data stream to prevent system oscillations caused by excessive network resource preemption.

[0013] In one embodiment of the present invention, in step S5, the implementation method of collaborative optimization includes: establishing a two-way feedback channel between the data coordination engine and the blockchain network for the closed-loop control signal. The feedback channel transmits the gradient update amount of the federated learning model and the network resource configuration policy parameters. The coordination engine adjusts the feature extraction rules and data cleaning thresholds according to the feedback signal, and the blockchain network synchronously updates the contribution degree calculation function and the consensus verification mechanism in the smart contract. The two-way feedback channel uses differential privacy technology to process the transmission parameters to ensure that the original data distribution characteristics and individual contribution details are not leaked during the optimization process.

[0014] The present invention also provides an Internet of Things-based nursing data sharing system, including: A collection module that collects multi-modal nursing data in real time through a distributed Internet of Things terminal cluster and forms a set of feature signals; A coordination module that constructs a data coordination engine and performs federated learning preprocessing operations on the set of feature signals to form a coordinated signal stream; A verification module that deploys a sharing incentive mechanism based on the blockchain network, parses the quality assessment matrix in the coordinated signal stream through a smart contract, and generates a verification signal chain; An early warning module that monitors the vital sign abnormality indicators in the coordinated signal stream in real time. When a preset critical threshold is triggered, it generates a trigger signal vector, which includes an encrypted emergency digital pass and an optimized network resource allocation scheme; An optimization module that updates the incentive mechanism parameters according to the contribution degree vouchers in the verification signal chain, and at the same time optimizes the service quality policy based on the network resource allocation scheme in the trigger signal vector, and forms a closed-loop control signal, which is synchronized to the data coordination engine to achieve collaborative optimization.

[0015] A method and system for sharing nursing data based on the Internet of Things provided by the present invention construct a collaborative sharing mechanism integrating federated learning and blockchain technology, implement multi-modal data standardization processing at the edge computing layer, use a dynamic contribution evaluation model to incentivize data sharing, and establish an emergency channel priority transmission system based on smart contracts. Combining zero-knowledge proof and dynamic spectrum allocation technology, secure and efficient data flow is achieved. In the specific implementation process, the data collected by the distributed terminal cluster is encapsulated with feature signals, and the edge node completes data cleaning and alignment under privacy protection. The blockchain network generates verifiable contribution vouchers through quantitative evaluation. When critical indicators are detected, a cross-domain priority transmission protocol is triggered. Finally, the overall system performance is optimized through closed-loop feedback, improving the sharing efficiency while ensuring data security. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a flowchart of the method for sharing nursing data based on the Internet of Things; Figure 2 It is a system architecture diagram of the system for sharing nursing data based on the Internet of Things. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following specific examples illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0019] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention schematically. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0020] In the following description, numerous specific details are set forth to provide a more thorough explanation of embodiments of the present invention. However, it will be apparent to those skilled in the art that embodiments of the present invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the present invention.

[0021] Please refer to Figure 1-2 , which shows the Internet of Things-based nursing data sharing method and system of the present invention. The Internet of Things-based nursing data sharing method of the present invention includes: S1: Real-time collecting multi-modal nursing data through a distributed Internet of Things terminal cluster and forming a feature signal set; S2: Constructing a data coordination engine and performing federated learning preprocessing operations on the feature signal set to form a coordinated signal stream, the coordinated signal stream includes encrypted standardized data blocks and associated quality assessment matrices, and the preprocessing operations include abnormal data cleaning, spatio-temporal dimension alignment, and feature vector standardization; S3: Deploying a sharing incentive mechanism based on the blockchain network, parsing the quality assessment matrix in the coordinated signal stream through a smart contract, dynamically calculating the data contribution degree weights, and generating a verification signal chain; S4: Real-time monitoring the vital sign abnormal indicators in the coordinated signal stream, when a preset critical threshold is triggered, generating a trigger signal vector, the trigger signal vector includes an encrypted first aid digital pass and an optimized network resource allocation scheme; S5: Updating the incentive mechanism parameters according to the contribution degree vouchers in the verification signal chain, and at the same time optimizing the service quality strategy based on the network resource allocation scheme in the trigger signal vector, and forming a closed-loop control signal, the closed-loop control signal is synchronized to the data coordination engine to achieve collaborative optimization.

[0022] As Figure 1As shown, the core process consists of five interrelated technical stages, achieving data security sharing and emergency care response through the step-by-step transformation and feedback mechanism of the signal flow. In the initial stage, the distributed Internet of Things (IoT) terminal cluster serves as the physical basis for data collection, composed of a variety of heterogeneous medical devices, including but not limited to wearable vital sign monitors, ward environment sensors, mobile care terminals, and medical imaging devices. These terminal devices generate raw data streams according to their respective manufacturer protocols through built-in communication modules. For example, an electrocardiogram monitor uses a medical-specific wireless protocol to transmit waveform data, while a temperature and humidity sensor may use a low-power wide area network protocol to upload environmental parameters. During the data collection process, lightweight preprocessing modules deployed within the terminal cluster perform preliminary encapsulation on the raw data, attaching device uniqueness identifiers and timestamp information to form basic signal units containing multi-dimensional features. Before being transmitted to the edge nodes, these signal units are preliminarily marked according to a preset data sensitivity grading strategy. For example, blood oxygen saturation data is marked as a high-sensitivity level, while ward temperature data is marked as a low-sensitivity level. This grading mark provides a basis for subsequent differential processing. The generation of the feature signal set not only includes the original care data itself but also integrates auxiliary information such as device operating status parameters and network transmission quality indicators, forming a multi-dimensional data matrix to provide complete context information for subsequent processing steps.

[0023] Further, after the feature signal set is transmitted to the edge computing node, it enters the processing stage of the data coordination engine. As the core component of federated learning preprocessing, this engine is deployed on the edge server cluster close to the data source and adopts a containerized architecture to achieve elastic scheduling of computing resources. The preprocessing operation first performs abnormal data cleaning on the feature signal set. By loading a dynamically updated clinical rule knowledge base, such as the normal physiological parameter range, device measurement error tolerance, etc., a multi-dimensional detection model is established. The cleaning process uses the sliding time window analysis technique to perform pattern recognition on continuous time-series data. When an outlier beyond the reasonable range is detected, a data repair pipeline is triggered. The repair mechanism includes multiple processing logics: for temporary signal loss, an interpolation algorithm based on context similarity is used; for sudden abnormal spikes, wavelet transform smoothing processing is implemented; and for systematic deviations, device calibration parameters are called for compensation. The data stream after cleaning and repair enters the spatio-temporal alignment module, which eliminates data deviations caused by device clock asynchrony or deployment location differences by fusing the spatial coordinate data of the indoor positioning system and the time reference of the network time protocol. The aligned data undergoes feature vector normalization processing to convert data with different dimensions and sampling rates into a unified mathematical representation form. For example, the blood pressure value is converted from millimeters of mercury to the Z value under the standard normal distribution. The quality assessment matrix generated during the entire preprocessing process details the processing trajectory of each data block, including the original data confidence score, repair operation type, and normalization conversion parameters. This matrix is protected by a lightweight encryption algorithm and then injected into the coordination signal stream. After the coordination signal stream is formed, it enters the implementation stage of the sharing incentive mechanism based on the blockchain network. The blockchain nodes are deployed on the medical institution consortium chain, and an improved Byzantine fault-tolerant consensus mechanism is adopted to balance the efficiency and security requirements. The smart contract plays a core role in this stage. First, it parses the quality assessment matrix in the coordination signal stream and inputs the data integrity index, timeliness coefficient, and clinical value parameters it contains into the multi-dimensional contribution degree assessment model. The integrity index is obtained by calculating the data field completeness rate and checksum matching degree. The timeliness coefficient uses an exponential decay function to process the time difference between the data generation time and the sharing request time. The clinical value parameter is obtained by querying the medical knowledge graph to match the priority weight of the current application scenario. After the assessment model outputs the contribution degree weight values of each data provider, the smart contract calls the verifiable computing framework to generate encrypted contribution degree vouchers, which are organized into a traceable verification signal chain through the Merkle tree structure. At the same time, the blockchain network dynamically generates data access permission tokens according to the contribution degree weights and uses attribute-based encryption technology to achieve fine-grained access control. The key innovation in this stage is to deeply integrate the data processing process of federated learning with the incentive mechanism of the blockchain, convert the value of the original data into a circulable digital right through the contribution degree quantification model, and ensure the transparency and audibility of the computing process.

[0024] Such as Figure 1As shown in the figure, in the distributed Internet of Things terminal cluster, the dynamic perception adapter, as the core middleware, adopts a modular design to support the plug-and-play of multiple communication protocols. The adapter is built with a protocol conversion engine that can automatically identify the communication specifications of terminal devices. For example, it can reorganize the data packets of the Bluetooth Low Energy protocol into the MQTT format, or convert the sensor data of the Zigbee protocol into the JSON structure that can be processed by the RESTful interface. During the data encapsulation process, the parallel processing thread pool performs real-time feature extraction on multimodal data. For example, it extracts the coefficient of variation of the RR interval from the electrocardiogram signal and calculates the respiratory entropy value from the respiratory waveform. These feature parameters and the original data together form the feature signal unit. To strengthen the data traceability ability, the generation of the composite identification code integrates the device physical fingerprint and the patient's biometric characteristics: the device fingerprint generates a unique identifier by extracting wireless signal characteristics, the hash value of the hardware serial number, and the firmware version information; the patient's biometric characteristics adopt a non-invasive acquisition method. For example, it extracts the identity feature vector from the electrocardiogram waveform and then undergoes fuzzy hashing processing to ensure privacy security. The binding of the timestamp sequence adopts a high-precision synchronization protocol, records the data generation time at the nanosecond-level time resolution, and forms a four-dimensional spatio-temporal tag with the three-dimensional space coordinates provided by the indoor positioning system. The implementation of data sensitivity grading and marking depends on the real-time content analysis engine. This engine parses the nursing record text through natural language processing, combines computer vision technology to identify sensitive areas in medical images, and dynamically adjusts the data encryption level. When detecting core parameters related to patient privacy, such as HIV test results or genetic disease markers, the system automatically switches to a quantum-resistant encryption algorithm and triggers a distributed storage strategy to store the data in fragments on multiple edge nodes.

[0025] Furthermore, as the decision-making core of the cleaning operation, the dynamic rule knowledge graph integrates three major types of knowledge sources: the clinical diagnosis and treatment standard library contains thousands of physiological parameter threshold rules formulated by medical experts, the device technical parameter library collects metadata such as the measurement accuracy and sampling rate of mainstream medical devices, and the historical data distribution feature library analyzes the statistical laws of past nursing data through machine learning models. In the outlier detection link, the system adopts an improved density-based clustering algorithm, which introduces a dynamic radius parameter adjustment mechanism for the characteristics of strong time series and multi-dimensional correlation of medical data. For the vital sign data stream, the algorithm calculates the local anomaly factor within a sliding time window, and marks a data point as suspected abnormal when the density difference between it and its adjacent points exceeds the adaptive threshold. The data repair mechanism adopts a hierarchical processing strategy: for occasional missing data, a prediction model based on a long short-term memory network is used for interpolation; for persistent anomalies, the device diagnosis protocol is activated, and the sensor self-check program is triggered through remote instructions. During the execution of the repair operation, the system generates detailed operation logs, recording the original abnormal values, the basis for selecting the repair method, and the corrected values. After being desensitized, these information are written into the quality assessment matrix. The matrix adopts a hierarchical storage structure. The basic layer contains quantitative indicators such as integrity scores and timeliness indices, the metadata layer stores the key parameters of the repair process, and the traceability layer ensures the immutability of operation records through hash chain technology. The data blocks after cleaning and repair carry version identifiers in the coordinated signal flow, supporting data traceability and quality verification in subsequent links. The entire cleaning process is completed at the edge computing node, which not only ensures the timeliness of data processing but also avoids the privacy risks brought by the departure of the original data from the local domain.

[0026] Specifically, the spatio-temporal dimension alignment method constructs a basic framework for multi-source data fusion. By establishing a unified spatio-temporal coordinate system at the edge computing node, it effectively solves the integration problem caused by inconsistent spatio-temporal benchmarks of heterogeneous device data. The establishment of this coordinate system relies on the centimeter-level accurate space reference provided by the indoor positioning system, combined with the time reference source formed by the fusion of the Beidou satellite time service system and the Network Time Protocol (NTP), to form a standard reference system with four-dimensional spatio-temporal attributes. During specific implementation, the geofencing technology is applied to the boundary calibration of the device deployment area. By fusing the Received Signal Strength Indication (RSSI) fingerprint matching and Ultra-Wideband (UWB) positioning data, it dynamically corrects the signal drift error caused by environmental reflection. For the time synchronization problem, the system adopts an improved clock offset compensation algorithm to establish a hierarchical time calibration mechanism between the edge node and the terminal device: the terminal device sends beacon frames containing local clock information at fixed intervals, and the edge node calculates the joint estimated value of the round-trip delay and the clock deviation, and uses Kalman filtering for dynamic adjustment to control the clock error within milliseconds. The time series alignment of the data stream adopts the sliding window cross-correlation analysis method. For device data with different sampling rates, first, the sampling rate is normalized through cubic spline interpolation, and then the cross-correlation function is calculated within the sliding time window to determine the optimal phase alignment point. In terms of spatial data mapping, a three-dimensional grid model is constructed according to the physical deployment topology of medical devices, and the discrete sensor readings are converted into a continuous spatial distribution map through radial basis function interpolation. At the same time, a coordinate transformation matrix is used to convert the spatial data collected by different positioning systems into a unified coordinate system. The spatio-temporal correction parameters generated during the alignment process, including the clock offset compensation amount, the coordinate transformation matrix coefficients, and the interpolation function parameters, etc., are encrypted and embedded in the metadata area of the coordinated signal stream to provide a traceable spatio-temporal benchmark for subsequent data analysis. The innovation of this technology lies in the deep integration of indoor positioning error compensation and multi-device clock synchronization. Through the dynamic calibration mechanism, the spatio-temporal deviation of heterogeneous devices is reduced to a clinically acceptable range. For example, the data time alignment accuracy between the electrocardiogram monitor and the respiratory monitoring device reaches ±10 ms, and the spatial positioning error does not exceed 30 cm, significantly improving the accuracy of multi-modal data fusion.

[0027] Such as Figure 1As shown, the data contribution weight calculation mechanism constructs a fair and transparent value evaluation system, the core of which is to construct a multi-dimensional evaluation function to realize the quantitative modeling of data value. The design of this function integrates the evaluation indicators of three dimensions: data quality, timeliness, and clinical value. The integrity index is obtained by calculating the weighted harmonic mean of the data field missing rate and the check code matching degree, where the check code matching degree adopts a dual verification mechanism of cyclic redundancy check (CRC) and hash value. The timeliness coefficient is modeled by an exponential decay function. According to the time difference Δt between the data generation time and the sharing request time, the decay value is calculated according to the formula α·exp(-βΔt), where α is the basic weight coefficient and β is the decay rate parameter. These parameters are dynamically adjusted according to the type of medical data. For example, the β value of emergency data is set smaller to slow down the decay rate. The clinical value evaluation parameter is determined by querying the medical knowledge graph, which has pre-constructed an association network of disease-symptom-examination items. When the sharing request involves a specific clinical scenario, the system retrieves the medical entity with the highest matching degree through a graph traversal algorithm and extracts its preset priority weight. The output value of the evaluation function needs to be verified by the consensus of blockchain nodes, using an improved practical Byzantine fault tolerance (PBFT) algorithm to control the consensus delay within seconds while ensuring security. The generation of contribution vouchers adopts a verifiable delay function (VDF) to ensure the verifiability and anti-tampering of the calculation process. Each voucher contains the contribution value, the evaluation timestamp, and the signature information of the verification node. The data access permission token is designed using an attribute-based encryption (ABE) scheme, mapping the contribution value to the attribute conditions in the access policy. For example, institutions with high contributions can obtain more fine-grained data access permissions. The innovation of this mechanism lies in establishing a dynamic evaluation model that links data quality and clinical value, ensuring the credibility of the evaluation results through the blockchain consensus mechanism, and at the same time using attribute encryption technology to achieve precise control of access permissions. For example, in the tumor research scenario, high-contribution research institutions can obtain access rights to the complete dataset containing gene test results, while ordinary institutions can only access the desensitized statistical features.

[0028] Furthermore, the emergency digital pass generation mechanism constructs a secure and efficient emergency identity verification system, the core of which lies in balancing the identity verification efficiency and privacy protection requirements in emergency situations. When the vital sign monitoring system detects that a preset critical threshold is triggered, the system initiates a multi-factor identity verification process: First, it verifies the legitimacy of the terminal device through the device biometric signature, and uses the hardware fingerprint extraction technology based on the Physical Unclonable Function (PUF) to generate a unique device identifier; Second, it calls the medical institution digital certificate chain to verify the compliance of the requesting institution, and the certificate chain includes the root certificate issued by the health supervision department and the institution-specific sub-certificate; Finally, it obtains the patient's temporary authorization code, which is generated instantaneously through Near Field Communication (NFC) or biometric recognition (such as fingerprint), and has the characteristic of being valid only once. The verification process adopts the zero-knowledge proof protocol, transforms the verification elements into arithmetic circuit representations, and confirms the identity legitimacy through non-interactive proof without disclosing sensitive information. The encrypted pass generated after successful verification adopts a hierarchical encryption structure: the outer layer uses the national cipher SM4 algorithm to encrypt the institution access permission statement, and the inner layer uses the threshold cryptography scheme to split the data decryption key into multiple segments, one of which is embedded in the pass, and the rest are pre-stored in the key management system of the target emergency institution. The validity period of the pass is set in accordance with the golden time principle of clinical first aid and is dynamically adjusted according to different types of critical diseases. For example, the validity period of the myocardial infarction first aid pass is set to 120 minutes, and that of the stroke first aid is set to 180 minutes. The innovation of this mechanism lies in the combination of zero-knowledge proof and threshold encryption, which not only meets the need for rapid verification in emergency situations but also ensures the security and controllability of core medical data. For example, emergency personnel need to hold both the digital pass and the hospital key segment to decrypt the patient's complete medical record, preventing the data from being stolen by unauthorized parties during transmission.

[0029] Such as Figure 1As shown, the dynamic spectrum allocation algorithm constructs an intelligent emergency communication support system, the core of which lies in achieving the optimal allocation of limited wireless resources. When the priority transmission channel is activated, the system collects real-time wireless channel state information (CSI), including channel noise power, multipath fading characteristics, and adjacent channel interference level, to construct a dynamic spectrum map. The network topology analysis module obtains the working status and load conditions of routing nodes through detection messages and constructs a weighted directed graph model. The spectrum allocation problem is modeled as a non-cooperative game under incomplete information, where the emergency data transmission requirement is the priority participant and the conventional data stream is the secondary participant. The objective function of the game model takes into account both minimizing transmission delay and suppressing channel interference, and a Nash equilibrium solution algorithm is used to obtain the optimal spectrum allocation scheme. In specific implementation, orthogonal frequency division multiplexing (OFDM) subcarrier resource blocks are reserved for emergency data, and high-order modulation methods (such as 1024-QAM) are configured to improve transmission efficiency. At the same time, frequency hopping spread spectrum technology is adopted to enhance anti-interference ability. The construction of the routing table of the temporary relay node adopts a heuristic search algorithm, which dynamically selects the optimal relay path according to the network congestion degree. When the packet loss rate of a certain path is detected to exceed the threshold, it automatically switches to the standby routing node. The specific parameters of the spectrum allocation scheme include the channel switching time sequence, modulation and coding strategy combination, and power control parameters. These parameters are encapsulated into a machine-readable configuration instruction set and are loaded into the communication device in real time through software-defined radio (SDR) technology. The innovation of this technology lies in the deep integration of the game theory model and software-defined network (SDN) technology, realizing the dynamic reconfiguration of spectrum resources in the emergency scenario. For example, in the sudden cardiopulmonary resuscitation scenario, the system can complete the dedicated channel allocation within 200 ms, stably control the transmission delay of key vital sign data within 50 ms, and reduce the adjacent channel interference by more than 15 dB through intelligent power control, ensuring the reliability and real-time of emergency data transmission.

[0030] As Figure 2As shown in the figure, the present invention relates to a nursing data sharing system based on the Internet of Things, including a collection module, a coordination module, a verification module, an early warning module, and an optimization module. The collection module collects multi-modal nursing data in real time through a distributed Internet of Things terminal cluster and forms a set of characteristic signals; the coordination module constructs a data coordination engine and performs federated learning preprocessing operations on the set of characteristic signals to form a coordinated signal flow; the verification module deploys a sharing incentive mechanism based on the blockchain network, parses the quality assessment matrix in the coordinated signal flow through a smart contract, and generates a verification signal chain; the early warning module monitors the vital sign abnormality indicators in the coordinated signal flow in real time. When a preset critical threshold is triggered, a trigger signal vector is generated, and the trigger signal vector includes an encrypted first aid digital pass and an optimized network resource allocation scheme; the optimization module updates the incentive mechanism parameters according to the contribution degree vouchers in the verification signal chain, and at the same time optimizes the service quality strategy based on the network resource allocation scheme in the trigger signal vector, and forms a closed-loop control signal, and the closed-loop control signal is synchronized to the data coordination engine to achieve collaborative optimization.

[0031] As Figure 2As shown in the figure, the technical implementation of the service quality strategy optimization process constructs a dynamic and adaptive network resource management system. The policy decision engine deployed in the data sharing application layer constructs a multi-dimensional state vector space in real time by parsing the network resource allocation scheme in the closed-loop control signal. This space includes key parameters such as the current network bandwidth utilization rate, data transmission delay distribution, channel bit error rate statistics, and the proportion of emergency care data traffic. The construction of the decision tree adopts the Monte Carlo tree search algorithm, and each decision node corresponds to a specific service quality adjustment strategy, such as adjusting the priority queue weight coefficient, configuring the redundancy of error correction coding, or setting the routing path switching threshold. The training process of the reinforcement learning model simulates the system performance indicators under different strategy combinations, including the end-to-end transmission success rate, resource utilization efficiency, and system stability coefficient, and continuously optimizes the strategy selection through the deep Q-network (DQN) algorithm. The safeguard measures for the emergency care data stream include a three-level protection mechanism: at the physical layer, a dedicated buffer is allocated for the emergency care data packets to avoid competing for storage resources with regular data; at the link layer, the priority of the automatic repeat request (ARQ) is enhanced to ensure the priority retransmission of critical data packets; at the application layer, the redundancy ratio of the forward error correction coding (FEC) is dynamically adjusted, and the coding scheme of the Reed-Solomon code or the low-density parity-check code is adaptively selected according to the real-time channel quality. The service quality balance of the regular data stream is achieved through a dual control loop: the main control loop dynamically adjusts the bandwidth allocation weight according to the network load status, and the secondary control loop monitors the system oscillation index. When it is detected that the resource allocation fluctuation exceeds the safety threshold, the fuzzy PID controller is activated for damping adjustment. The optimized policy parameters are sent to each network device through the software-defined network (SDN) controller to achieve a second-level synchronous update of the network-wide policy. The innovation of this mechanism lies in the combination of reinforcement learning and classical control theory, showing good adaptability in the scenario of sudden traffic, such as when the emergency care data transmission request suddenly increases by 300%, the system can complete the policy adjustment within 500 ms, control the transmission delay variance of the emergency data packets within 10 ms, and at the same time keep the throughput of the regular data stream not less than 80% of the baseline level.

[0032] As Figure 2As shown, the collaborative optimization mechanism establishes a cross-level dynamic feedback system, achieving full-link coordination of data processing and incentive mechanisms through a two-way communication channel. The closed-loop control signal constructs a feedback data pipeline with time-sequence tags between the data coordination engine and the blockchain network. This pipeline adopts a duplex communication mode. The uplink transmits the gradient update amount and feature importance parameters of the federated learning model, while the downlink delivers the network resource allocation strategy parameters and contribution degree evaluation rule change instructions. The update process of the federated learning model introduces differential privacy technology, injecting noise conforming to the Gaussian distribution before gradient aggregation. The noise intensity is dynamically adjusted according to the data sensitivity classification to ensure that the model update cannot reverse-derive the original training data. After receiving the feedback signal, the data coordination engine activates the adaptive adjustment module: the feature extraction rule dynamically optimizes the feature selection weight according to the feature importance ranking reflected by the gradient update amount; the data cleaning threshold is flexibly adjusted in combination with the network resource status. For example, when the network is congested, the strictness of abnormal data filtering is increased to reduce the transmission load. The smart contract of the blockchain network synchronously updates the contribution degree calculation function, fusing the latest clinical value evaluation parameters through an online learning mechanism, and the consensus verification mechanism dynamically adjusts the timeout threshold according to the network delay index. The privacy protection mechanism of the feedback channel adopts homomorphic encryption technology to ensure that the gradient parameters and policy instructions during the transmission process are always in an encrypted state and cannot be decrypted to obtain valid information even if intercepted. The innovation of this collaborative mechanism lies in establishing a positive feedback loop between data processing and incentive mechanisms. For example, when the system detects a sharp increase in the sharing demand for a certain type of physiological parameter, it automatically increases the contribution degree weight coefficient of this type of data, incentivizing relevant institutions to give priority to sharing such data. At the same time, the coordination engine optimizes the corresponding feature extraction algorithm, forming a virtuous interaction between data value mining and sharing incentives.

[0033] Specifically, the verification signal chain construction process establishes an auditable trust transfer system, whose technical core lies in the deep integration of the verifiability of distributed computing and the immutability of blockchain. The verifiable computing framework is deployed on each consensus node of the blockchain network. The arithmetic circuit compiler is used to parse the quality assessment matrix into a computational flow chart composed of basic logic gates, and the contribution weight calculation process is transformed into a circuit structure containing adders, multipliers, and comparators. The generation of computational correctness evidence adopts a non-interactive zero-knowledge proof protocol. By encoding the circuit execution trace as a polynomial commitment and leveraging the bilinear pairing property, a concise proof is generated. When verifying the evidence, the consensus node only needs to perform calculations with sublinear complexity to confirm the correctness of the entire computational process, significantly reducing the verification overhead. The storage structure of the verification signal chain adopts an improved Merkle Patricia Tree (MPT) design. Each voucher node contains a triple structure of the hash value of the predecessor node, the current contribution value, and a snapshot of the computational state. The state snapshot is encoded using a lightweight serialization protocol, recording the key intermediate variables during the computational process, such as the hash digest of the quality assessment matrix, the parameters of the evaluation function, and the voting results of the consensus nodes. The traceability mechanism of the chain structure is implemented by combining a skip list and a hash pointer, supporting fast positioning of historical voucher records. For example, when querying the contribution change trend of a certain institution within three months, the retrieval time complexity can be reduced to O(log n). The update process of the voucher chain adopts sharding parallel processing technology, storing the newly generated contribution vouchers in slices according to the regions where medical institutions are located. When querying across slices, the target slice is located through a distributed hash table (DHT). The innovation of this verification signal chain lies in achieving verifiability throughout the entire life cycle of the computational process. For example, when a regulatory agency needs to audit a certain data sharing transaction, it can confirm the compliance of the contribution assessment without decrypting the original data by verifying the zero-knowledge proof and computational state snapshot on the chain. At the same time, using the aggregation verification feature of the Merkle tree, the time efficiency of batch verifying tens of thousands of voucher records is improved by two orders of magnitude.

[0034] A method and system for sharing nursing data based on the Internet of Things according to the present invention constructs a collaborative sharing mechanism integrating federated learning and blockchain technology, implements multi-modal data standardization processing at the edge computing layer, uses a dynamic contribution assessment model to incentivize data sharing, and at the same time establishes an emergency channel priority transmission system based on smart contracts, combining zero-knowledge proof and dynamic spectrum allocation technology to achieve secure and efficient data flow. During the specific implementation process, the data collected by the distributed terminal cluster is encapsulated with feature signals, and the edge node completes data cleaning and alignment under privacy protection. The blockchain network generates verifiable contribution vouchers through quantitative evaluation. When critical indicators are detected, it triggers a cross-domain priority transmission protocol, and finally optimizes the overall system performance through closed-loop feedback, improving the sharing efficiency while ensuring data security.

[0035] Therefore, through a method and system for sharing nursing data based on the Internet of Things of the present invention, problems such as data island effect, privacy and security risks, and low efficiency of emergency data transmission existing in the process of sharing medical nursing data can be solved.

[0036] The above embodiments are only illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A method for sharing nursing data based on the Internet of Things, characterized in that, Including: S1: Real-time collect multimodal nursing data through a distributed Internet of Things terminal cluster and form a set of characteristic signals; S2: Construct a data coordination engine and perform federated learning preprocessing operations on the set of characteristic signals to form a coordinated signal stream, the coordinated signal stream includes encrypted standardized data blocks and associated quality assessment matrices, and the preprocessing operations include abnormal data cleaning, spatio-temporal dimension alignment, and feature vector standardization; S3: Deploy a shared incentive mechanism based on the blockchain network, parse the quality assessment matrix in the coordinated signal stream through a smart contract, dynamically calculate the data contribution degree weights, and generate a verification signal chain; S4: Real-time monitor the vital sign abnormal indicators in the coordinated signal stream, and when a preset critical threshold is triggered, generate a trigger signal vector, the trigger signal vector includes an encrypted first aid digital pass and an optimized network resource allocation scheme; S5: Update the incentive mechanism parameters according to the contribution vouchers in the verification signal chain, and at the same time optimize the service quality strategy based on the network resource allocation scheme in the trigger signal vector, and form a closed-loop control signal, the closed-loop control signal is synchronized to the data coordination engine to achieve collaborative optimization.

2. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein In step S1, the generation process of the set of characteristic signals includes: deploying a dynamic perception adapter in the distributed Internet of Things terminal cluster, the adapter automatically matches the data encapsulation protocol according to the terminal device type, performs feature extraction on the multimodal nursing data through parallel processing threads, the extraction process fuses the device physical fingerprint and the patient biometric characteristics to generate a composite identification code, and at the same time establishes a binding relationship between the timestamp sequence and the spatial coordinates, wherein the data sensitivity classification mark is dynamically generated by real-time analyzing the relevance between the data content and the clinical context, and automatically improves the encryption level when detecting core physiological parameters related to patient privacy, the composite identification code includes the device uniqueness identifier generated by irreversible hash operation and the derivative code after fuzzy processing of the patient identity characteristics.

3. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein In step S2, the specific implementation method of the abnormal data cleaning is: construct a dynamic rule knowledge graph in the data coordination engine, the graph integrates clinical diagnosis and treatment specifications, device technical parameters, and historical data distribution characteristics, perform outlier detection on the set of characteristic signals through a sliding time window, the detection process uses an adaptive threshold algorithm based on density clustering, and trigger a data repair mechanism when identifying abnormal values beyond the physiologically reasonable range, the repair mechanism includes missing value imputation, mutation value smoothing, and context relevance correction, and the repaired data block generates a quality assessment matrix with a version identifier, the matrix records the original data confidence and the correction operation track.

4. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein, In step S2, the implementation method for spatio-temporal dimension alignment includes: establishing a unified spatio-temporal coordinate system at the edge computing node, correcting the time deviation and spatial offset of the data collected by the device through the indoor positioning system and the geofencing technology. The alignment process uses the sliding window correlation analysis method to match the sampling timings of different devices, implements time-domain compensation for the data stream with communication delay, and simultaneously establishes a spatial mapping model according to the device deployment topology structure, converting the discrete spatial data collected by heterogeneous sensors into a continuous distribution data set in the standard coordinate system. The spatio-temporal correction parameters generated by the alignment operation are synchronously injected into the metadata area of the coordination signal stream.

5. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein In step S3, the dynamic calculation process of the data contribution weight includes: constructing a multi-dimensional evaluation function in the blockchain network. This function integrates the integrity index in the quality evaluation matrix, the timeliness coefficient of the timestamp sequence, and the clinical value evaluation parameter. Among them, the integrity index is jointly calculated by the data field missing rate and the check code matching degree, the timeliness coefficient decays dynamically according to the interval between the data generation time and the sharing request time, and the clinical value evaluation parameter retrieves and matches the demand priority of the current medical scenario through the knowledge graph. The output value of the evaluation function generates an immutable contribution certificate after being verified by node consensus, and this certificate forms a non-linear mapping relationship with the data access permission token.

6. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein In step S4, the generation mechanism of the emergency digital pass includes: when it is detected that the abnormal vital sign index exceeds the preset critical threshold, a multi-factor identity verification process is started. The verification process integrates the digital certificate of the medical institution, the device biometric signature, and the patient's temporary authorization code, and verifies the identity legality through the zero-knowledge proof protocol without revealing sensitive information. After successful verification, an encrypted pass with a time validity period is generated. This pass contains the decryption key fragment of the emergency care data and the cross-institutional access permission statement. The key fragment needs to be combined with the key fragment held by the receiving party to decrypt the core medical data.

7. The method for sharing nursing data based on the Internet of Things according to claim 1, characterized in that In step S4, the operation logic of the network resource allocation scheme includes: when the priority transmission channel is activated, the wireless channel load status and the network topology structure are monitored in real time, and the optimal spectrum resource allocation scheme is calculated through the game theory model. The allocation process takes into account the requirements of transmission delay and the suppression of channel interference, provides double guarantees of bandwidth reservation and frequency hopping communication for the emergency data transmission, and simultaneously establishes a temporary relay node routing table, dynamically adjusting the data transmission path according to the network congestion degree. The allocation scheme includes the channel switching timing diagram and the combined parameters of the modulation and coding strategy.

8. The method for sharing nursing data based on the Internet of Things according to claim 7, wherein, In step S5, the service quality strategy optimization process includes: constructing a strategy decision tree in the data sharing application layer. This decision tree dynamically adjusts the data transmission priority queue according to the network resource allocation scheme in the closed-loop control signal. The optimization process uses the reinforcement learning algorithm to simulate the system performance indicators under different strategies, providing end-to-end transmission guarantee for the emergency care data stream, including establishing a dedicated buffer area, increasing the retransmission priority, and dynamically adjusting the error correction coding strength, and at the same time balancing the service quality requirements of the regular data stream to prevent system oscillation caused by excessive preemption of network resources.

9. The method for sharing nursing data based on the Internet of Things according to claim 1, wherein In step S5, the implementation method of the collaborative optimization includes: a bidirectional feedback channel is established between the data coordination engine and the blockchain network for the closed-loop control signal. The feedback channel transmits the gradient update amount of the federated learning model and the network resource allocation policy parameters. The coordination engine adjusts the feature extraction rules and data cleaning thresholds according to the feedback signal. The blockchain network synchronously updates the contribution degree calculation function and the consensus verification mechanism in the smart contract. The bidirectional feedback channel processes the transmission parameters using differential privacy technology to ensure that the original data distribution characteristics and individual contribution details are not leaked during the optimization process.

10. An Internet of Things-based nursing data sharing system, which is used to use the Internet of Things-based nursing data sharing method described in any one of claims 1-9, and is characterized in that, including: a collection module, which collects multi-modal nursing data in real time through a distributed Internet of Things terminal cluster and forms a feature signal set; a coordination module, which constructs a data coordination engine and performs federated learning preprocessing operations on the feature signal set to form a coordinated signal stream; a verification module, which deploys a shared incentive mechanism based on the blockchain network, analyzes the quality assessment matrix in the coordinated signal stream through a smart contract, and generates a verification signal chain; a warning module, which monitors the vital sign abnormality indicators in the coordinated signal stream in real time. When a preset critical threshold is triggered, a trigger signal vector is generated. The trigger signal vector includes an encrypted first aid digital pass and an optimized network resource allocation scheme; an optimization module, which updates the incentive mechanism parameters according to the contribution degree vouchers in the verification signal chain, and at the same time optimizes the service quality policy based on the network resource allocation scheme in the trigger signal vector, and forms a closed-loop control signal. The closed-loop control signal is synchronized to the data coordination engine to achieve collaborative optimization.

Images