A distributed mobile remote diagnosis and treatment collaboration system and method for a medical and nursing combination scene and a storage medium
Patent Information
- Application Number
- CN202610898791.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-22
- Publication Date
- 2026-10-27
AI Technical Summary
上述全人工落地的协作模式数据标准化程度低、风险判定主观性强、资源匹配效率低下，跨节点调度缺少量化依据，难以适配规模化、分布式的医养远程协同诊疗需求，因此亟需一套自动化协同方案解决现有人工作业带来的各类弊端
[0009]本发明的有益效果是：整套硬件设备分散布置在各个医养点位，由不同硬件分工完成数据采集、特征处理、风险判别、策略生成和通道调度、设备管控全链路作业，依靠通信联动自动流转全流程数据，统一实现医养全流程数字化处理，能够同步对接多点位居家、社区及医疗机构组成的分布式医养网络，提升多节点医养远程诊疗协同的整体运转效率，便于规模化落地多区域联动的医养服务。
Smart Images
Figure CN122991519A_ABST
Abstract
Description
Technical Field
[0001] This invention mainly relates to the field of smart medical and elderly care information technology, specifically to a distributed mobile remote diagnosis and treatment collaborative system, method and storage medium for integrated medical and elderly care scenarios. Background Technology
[0002] In the current integrated medical and elderly care service scenario, home-based elderly care, community-based health care, and medical institutions are mostly operating independently, and existing remote diagnosis and treatment collaborations largely rely on manual coordination. Medical staff need to collect physiological data such as body temperature and blood oxygen levels, as well as information on daily life and health care, from elderly individuals individually, either offline or by phone. This data is then manually compiled and archived using paper or scattered forms, and the data processing and standardization are entirely manual operations, consuming a significant amount of manpower and time.
[0003] When elderly individuals exhibit abnormal health indicators, staff rely on manual comparison of health data and experience to assess health risk levels, lacking standardized and quantitative criteria. Subsequent coordination with nearby medical institutions and community health centers for remote diagnosis and treatment involves manually contacting each facility individually to inquire about available resources, equipment status, and geographical location, manually selecting and matching available service nodes, and manually finalizing collaborative treatment plans. In a multi-site distributed collaborative operation mode, the operational status of equipment and processors at each facility requires on-site inspection and registration by maintenance personnel, followed by manual issuance of control commands for debugging, start-up, and shutdown. This entirely manual collaborative model suffers from low data standardization, strong subjectivity in risk assessment, low resource matching efficiency, and a lack of quantitative basis for cross-node scheduling, making it difficult to adapt to the needs of large-scale, distributed remote collaborative diagnosis and treatment in the healthcare sector. Therefore, an automated collaborative solution is urgently needed to address the various drawbacks of existing manual operations. Summary of the Invention
[0004] The technical problem to be solved by the present invention is to address the shortcomings of the existing technology by providing a distributed mobile remote diagnosis and treatment collaborative system, method and storage medium for integrated medical and elderly care scenarios.
[0005] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: a distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios, wherein the system is deployed on multiple distributed medical and elderly care nodes, including a distributed data acquisition terminal, a feature processor, a risk identification processor, a collaborative decision processor, a path scheduling processor, and a central main server; The distributed data acquisition terminal is used to collect multi-source health data of the target object from multiple distributed nodes to construct an original health dataset; The feature processor is communicatively connected to the distributed data acquisition terminal and is used to perform standardization processing and feature extraction on the received raw health dataset to generate a structured health feature vector. The risk identification processor is communicatively connected to the feature processor and is used to load a preset risk assessment model, input the structured health feature vector into the risk assessment model, and output the health risk level data of the target object through the calculation of the risk assessment model. The collaborative decision processor is communicatively connected to the risk identification processor and is used to acquire the health risk level data and perform data fusion processing by combining the resource status data of each medical and elderly care distributed node to generate distributed collaborative diagnosis and treatment strategy data. The path scheduling processor is communicatively connected to the collaborative decision processor and the central master server, respectively, and is used to parse the distributed collaborative diagnosis and treatment strategy data and generate diagnosis and treatment channel scheduling data by combining the node operation attribute data of each distributed node; the central master server is used to poll the operation data of each distributed node and each processor and issue control commands.
[0006] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: A distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios, comprising: Multi-source health data of the target objects are collected by distributed data acquisition terminals deployed in multiple medical and elderly care distributed nodes to construct the original health dataset; The feature processor performs standardization and feature extraction on the original health dataset to generate structured health feature vectors; The risk identification processor inputs structured health feature vectors into a preset risk assessment model for calculation and outputs health risk level data of the target object. The collaborative decision processor combines health risk level data with resource status data of each medical and elderly care distributed node to perform data fusion processing and generate distributed collaborative diagnosis and treatment strategy data. The path scheduling processor parses the distributed collaborative diagnosis and treatment strategy data and combines it with the node operation attribute data of each distributed node to generate diagnosis and treatment channel scheduling data. The central master server polls the operating data of each distributed node and each processor, and after quantification and matching, sends control commands to the corresponding devices.
[0007] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: A distributed mobile remote diagnosis and treatment collaboration system for integrated medical and elderly care scenarios includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described above.
[0008] Another technical solution of the present invention to solve the above-mentioned technical problems is as follows: a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described above.
[0009] The beneficial effects of this invention are: the entire set of hardware equipment is distributed in various medical and elderly care locations, and different hardware components are used to complete the entire chain of operations, including data collection, feature processing, risk identification, strategy generation, channel scheduling, and equipment management. The entire process of data is automatically transferred through communication linkage, and the digital processing of the entire medical and elderly care process is realized in a unified manner. It can be synchronously connected to a distributed medical and elderly care network composed of multiple locations, including homes, communities, and medical institutions, which improves the overall operational efficiency of multi-node remote diagnosis and treatment collaboration in medical and elderly care and facilitates the large-scale implementation of multi-regional linkage medical and elderly care services. Attached Figure Description
[0010] Figure 1 This is a block diagram of a distributed mobile remote diagnosis and treatment collaborative system provided in an embodiment of the present invention; Figure 2 A flowchart of a distributed mobile remote diagnosis and treatment collaborative method provided in an embodiment of the present invention. Detailed Implementation
[0011] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.
[0012] Example 1: As Figure 1 As shown, this embodiment of the invention provides a distributed mobile remote diagnosis and treatment collaboration system for integrated medical and elderly care scenarios. The system is deployed on multiple distributed medical and elderly care nodes, including a distributed data acquisition terminal, a feature processor, a risk identification processor, a collaborative decision processor, a path scheduling processor, and a central main server. The distributed data acquisition terminal is used to collect multi-source health data of the target object from multiple distributed nodes to construct an original health dataset; The feature processor is communicatively connected to the distributed data acquisition terminal and is used to perform standardization processing and feature extraction on the received raw health dataset to generate a structured health feature vector. The risk identification processor is communicatively connected to the feature processor and is used to load a preset risk assessment model, input the structured health feature vector into the risk assessment model, and output the health risk level data of the target object through the calculation of the risk assessment model. The collaborative decision processor is communicatively connected to the risk identification processor and is used to acquire the health risk level data and perform data fusion processing by combining the resource status data of each medical and elderly care distributed node to generate distributed collaborative diagnosis and treatment strategy data. The path scheduling processor is communicatively connected to the collaborative decision processor and the central master server, respectively, and is used to parse the distributed collaborative diagnosis and treatment strategy data and generate diagnosis and treatment channel scheduling data by combining the node operation attribute data of each distributed node; the central master server is used to poll the operation data of each distributed node and each processor and issue control commands.
[0013] In the above embodiments, the entire set of hardware equipment is distributed across various medical and elderly care sites. The data collection terminals, various processors, and the central server are divided into segments to handle various tasks. Unlike the previous method of staff collecting information offline one by one and manually sorting and summarizing data, this solution automatically completes the entire process of health data from collection to scheduling and control by means of data communication between various devices. It can simultaneously link community elderly care sites, home-based health care sites, and cooperative medical institutions, reducing a large amount of manual work and facilitating remote diagnosis and treatment collaboration in multiple locations, thereby improving the efficiency of medical and elderly care services.
[0014] Preferably, the received raw health dataset is standardized and its features are extracted to generate a structured health feature vector, including: The range standardization process was performed on the medical and health care physiological parameters, health care status parameters, and environmental parameters in the original health dataset. The expression is as follows: , in, These are the original medical and health care parameter values. This represents the historical minimum value of the medical and elderly care parameters. This represents the historical maximum value of the medical and elderly care parameters. These are the standardized medical and elderly care parameter values; Weighted feature fusion is performed on the standardized medical and elderly care parameters to obtain single-dimensional medical and elderly care feature values, expressed as follows: , in, For the first A single-dimensional medical and elderly care feature value for a target object. Physiological characteristics This refers to the characteristics of a health and wellness state. For the environmental characteristics of medical and elderly care nodes, , , These are the weight coefficients of the corresponding feature terms, and ; The individual medical and elderly care feature values are concatenated according to preset dimensions to generate a structured health feature vector integrating medical and elderly care, expressed as follows: , in, This represents the total number of dimensions related to medical and elderly care features. This is a structured health feature vector.
[0015] Specifically, in practical applications, the optimal weight is selected. , , Taking elderly subjects as an example, the raw physiological data range of blood pressure , Actual measurement Standardized values are obtained after range conversion. After simultaneously completing the health and wellness living assessment and standardizing the indoor temperature and humidity environmental parameters, the individual's comprehensive characteristics are calculated by substituting them into the fusion formula. Data was collected from multiple elderly individuals in sequence, and all data was then processed. By sequentially piecing together the data, a complete structured health feature vector is ultimately formed. .
[0016] In the above embodiments, range standardization and weighted feature fusion are used to perform unified numerical transformation and feature integration on the original parameters of various types of medical and elderly care, and then standardized feature vectors are generated by dimensional concatenation. This solves the problems of inconsistent dimensions and chaotic data types of different categories of health data, which make unified calculation impossible. By relying on fixed weights, the quantitative fusion of physiological, health care, and environmental data is completed, so that various types of medical and elderly care information are standardized and transformed into vector data in a unified format. This provides a regular data source for subsequent risk model input, avoids the calculation bias caused by uneven original data, and improves the data foundation accuracy of subsequent health risk assessment.
[0017] Preferably, the risk identification processor is further used to build and train the risk assessment model, the building process including: Obtain historical health feature datasets and corresponding risk level labels in the integrated medical and elderly care scenario, and construct a training sample set for medical and elderly care risks; The model loss is calculated on the training sample set, and the expression is: , in, This represents the model loss value. The total number of medical and elderly care training samples. For the first The true risk level label for each sample The predicted risk level output by the model; Based on model loss value Perform gradient descent optimization and iteratively update the model weight matrix.W With bias term b This continues until the loss value converges, resulting in a successfully trained risk assessment model.
[0018] Specifically, 5,000 sets of elderly medical and nursing data archived in community elderly care facilities were selected to form a training sample, namely... Set a fixed learning rate for each iteration, and calculate the loss by substituting samples into the training data in each round. Relying on gradient descent to continuously fine-tune W , b Parameters. After multiple iterations, if the fluctuation of the loss value is less than a preset minimum threshold, the parameters are considered to have converged, training is terminated, and the final converged weight matrix and bias parameters are retained to form a dedicated risk assessment model adapted to the physical characteristics of local elderly people.
[0019] In the above embodiments, the model parameters are iteratively optimized using historical medical and elderly care samples combined with the squared loss function and gradient descent algorithm. The weight matrix and bias terms are continuously corrected until the loss converges, completing the autonomous training and optimization of the risk assessment model. By using massive amounts of real medical and elderly care samples to constrain the model parameter values, the model avoids the extensive mode of manually setting assessment parameters based on experience. This allows the model to adapt to the data distribution characteristics of medical and elderly care scenarios, improving the model's adaptability and generalization performance for the health risks of the elderly population, and ensuring the objective stability of subsequent risk level outputs.
[0020] Preferably, a preset risk assessment model is loaded, the structured health feature vector is input into the risk assessment model, and the health risk level data of the target object is output through the calculation of the risk assessment model, including: Structured health feature vectors for the integration of medical and elderly care The input risk assessment model is used to calculate the medical and health care risk score, and the expression is: , in, To score the risks of medical and health care, The weight matrix of medical and elderly care features obtained from training the risk assessment model. For model bias terms, This is a structured health feature vector; Based on the aforementioned medical and health risk score The expression for risk level mapping is: , in, For health risk level data, The pre-defined medical and elderly care risk level mapping function maps the risk score to one of low risk, medium risk, or high risk. Output the health risk level data .
[0021] Specifically, the grading rules are defined in advance: S <35 is considered low risk, 35≤ S ≤70 is considered medium risk. S A score >70 is considered high-risk. The feature vector of an elderly person obtained through preprocessing... Substitute into the formula, and combine with the trained data. W , b Calculation S =52, after being determined by the mapping function, the output data shows that the target object is of medium risk level.
[0022] In the above embodiments, a health risk score is obtained by performing linear operations using the trained weights and biases. Then, a three-level risk label is output through a preset mapping function. The standardized quantitative judgment of health risk is achieved by relying on the solidified model formula. The subjective experience rating method of medical staff in the past is abandoned. All risk judgments are automatically completed based on unified calculation rules. The rating standards are consistent throughout the process, which effectively reduces the individual differences and probability of misjudgment caused by human judgment. It accurately quantifies the health risk level of different elderly people and provides a quantitative basis for the matching of subsequent medical resources.
[0023] Preferably, the health risk level data is acquired and combined with the resource status data of each distributed medical and elderly care node for data fusion processing to generate distributed collaborative diagnosis and treatment strategy data, including: The matching degree of medical and elderly care resources is calculated by matching the health risk level data R with the resource status data of the distributed nodes of medical and elderly care, and the expression is: , in, For the first Resource matching degree of each distributed node in the medical and elderly care system For the health risk level data of the target group, For the first The availability of medical and health care resources in each distributed medical and elderly care node. To match the weight coefficients, and Based on the resource matching degree of each distributed medical and elderly care node The expression for executing the cooperative strategy sorting is: , in, Prioritize services for medical and elderly care facilities. This represents the total number of distributed nodes for medical and elderly care services. The sorting function is a descending order, based on the service priority sequence. Generate distributed collaborative diagnosis and treatment strategy data.
[0024] Specifically, selecting preferred parameters , Risk quantification for an elderly person The system connects to three medical and elderly care sites, with the resource availability of each site as follows: 80. 55. 30; calculate respectively , , Priority is obtained by sorting in descending order. Based on this, collaborative diagnosis and treatment strategy data is generated to prioritize the reception of patients at the No. 1 site.
[0025] In the above embodiments, the matching coefficient of each medical and elderly care site is obtained by weighted calculation of risk data and node resource availability. The nodes are then sorted in descending order to generate a node priority sequence and form a collaborative strategy. The fusion calculation of risk and resource data is completed by relying on quantitative formulas. This replaces the manual work of calling each site one by one and manually screening cooperative sites. It uses quantitative values to objectively represent the degree of node suitability, automatically sorts and generates collaborative plans, significantly shortens the time spent screening resources for multiple medical and elderly care nodes, and improves the rationality of matching medical resources with elderly patients.
[0026] Preferably, the distributed collaborative diagnosis and treatment strategy data is parsed, and combined with the node operation attribute data of each distributed node, diagnosis and treatment channel scheduling data is generated, including: First, calculate the node comprehensive adaptation coefficient based on the node's runtime attribute data. The expression is: , in, For the first The overall adaptability coefficient of each distributed node in the medical and elderly care system For node hardware and permission parameters, Parameters for node location and remaining resources. , To maintain a fixed weighting ratio, ; The optimal arrangement of treatment channels is calculated based on the comprehensive adaptation coefficient of all nodes, and is expressed as follows: , in, For the layout and marking of the passageway, Select a function for the minimum value; According to the layout markings Generate scheduling data for the diagnosis and treatment channels.
[0027] Specifically, select configuration weights , There are 3 candidate nodes to be filtered, with parameters as follows: , ; , ; , Seeking , , Determined by minimum value screening For node number one, the system generates dedicated medical channel scheduling data that connects to that node.
[0028] In the above embodiments, the adaptation coefficient is obtained by weighting two types of parameters: node hardware permissions and location margin. The optimal diagnosis and treatment channel identifier is determined based on the minimum value, and scheduling data is generated. Quantitative calculations are used to complete a comprehensive evaluation of multi-dimensional node attributes. This eliminates the reliance on subjective judgment of line layout by maintenance personnel. By comprehensively considering multiple conditions such as equipment, permissions, geographical location, and remaining resources, the system automatically selects the best to generate diagnosis and treatment transmission channel data, optimizing the rationality of cross-node remote diagnosis and treatment link layout and reducing channel resource waste.
[0029] Preferably, the system polls the operating data of each distributed node and each processor and issues control commands, including: Perform a quantitative calculation of the operating status of the collected equipment operating data, using the following expression: , in, For the first The operational quantization value of each hardware unit. For hardware load parameters, For hardware online status parameters, , To configure the weighting coefficients, ; Based on the operational quantization value Perform instruction matching and determination, and match the corresponding control instruction according to the preset threshold; Send the matched control commands to the corresponding distributed nodes or processors.
[0030] Specifically, select , The system's preset threshold for judgment is 60; a certain processor load Online parameters Calculations yielded If the value exceeds the threshold, the system automatically matches and sends a load reduction control command to the hardware unit; if another device... If the value is below the threshold, the system is considered to be operating normally and no control instructions need to be issued.
[0031] In the above embodiments, equipment operating indicators are weighted and quantified by hardware load and online status parameters. Control commands are automatically generated and issued based on threshold matching rules. Equipment status identification and command automatic distribution are completed based on quantified values. This changes the operation and maintenance mode of on-site inspection and manual issuance of debugging commands. The central terminal remotely polls the operating conditions of all distributed hardware in batches and accurately issues corresponding control commands based on the quantification results, reducing the manpower input for on-site operation and maintenance and realizing remote automated control of the entire system's hardware and software.
[0032] like Figure 2 As shown, this embodiment of the invention also provides a distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios, including: S1. Collect multi-source health data of the target object by deploying distributed data acquisition terminals in multiple medical and elderly care distributed nodes to construct the original health dataset; S2. The feature processor performs standardization and feature extraction on the original health dataset to generate a structured health feature vector. S3. The risk identification processor inputs the structured health feature vector into the preset risk assessment model for calculation and outputs the health risk level data of the target object. S4. The collaborative decision processor combines health risk level data with resource status data of each medical and elderly care distributed node to perform data fusion processing and generate distributed collaborative diagnosis and treatment strategy data. S5, the path scheduling processor parses the distributed collaborative diagnosis and treatment strategy data, and combines it with the node operation attribute data of each distributed node to generate diagnosis and treatment channel scheduling data; S6. The central master server polls the operating data of each distributed node and each processor, and after quantization and matching, sends control commands to the corresponding devices.
[0033] This invention also provides a distributed mobile remote diagnosis and treatment collaboration device for integrated medical and elderly care scenarios, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described above.
[0034] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described above.
[0035] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0036] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and unit can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0037] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0038] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.
[0039] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios, characterized in that, The system is deployed across multiple distributed nodes for medical and elderly care, including distributed data acquisition terminals, feature processors, risk identification processors, collaborative decision processors, path scheduling processors, and a central main server. The distributed data acquisition terminal is used to collect multi-source health data of the target object from multiple distributed nodes to construct an original health dataset; The feature processor is communicatively connected to the distributed data acquisition terminal and is used to perform standardization processing and feature extraction on the received raw health dataset to generate a structured health feature vector. The risk identification processor is communicatively connected to the feature processor and is used to load a preset risk assessment model, input the structured health feature vector into the risk assessment model, and output the health risk level data of the target object through the calculation of the risk assessment model. The collaborative decision processor is communicatively connected to the risk identification processor and is used to acquire the health risk level data and perform data fusion processing by combining the resource status data of each medical and elderly care distributed node to generate distributed collaborative diagnosis and treatment strategy data. The path scheduling processor is communicatively connected to the collaborative decision processor and the central master server, respectively, and is used to parse the distributed collaborative diagnosis and treatment strategy data and generate diagnosis and treatment channel scheduling data by combining the node operation attribute data of each distributed node; the central master server is used to poll the operation data of each distributed node and each processor and issue control commands.
2. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 1, characterized in that, The received raw health dataset is standardized and its features are extracted to generate a structured health feature vector, including: The range standardization process was performed on the medical and health care physiological parameters, health care status parameters, and environmental parameters in the original health dataset. The expression is as follows: ， in, These are the original medical and health care parameter values. This represents the historical minimum value of the medical and elderly care parameters. This represents the historical maximum value of the medical and elderly care parameters. These are the standardized medical and elderly care parameter values; Weighted feature fusion is performed on the standardized medical and elderly care parameters to obtain single-dimensional medical and elderly care feature values, expressed as follows: ， in, For the first A single-dimensional medical and elderly care feature value for a target object. Physiological characteristics This refers to the characteristics of a health and wellness state. For the environmental characteristics of medical and elderly care nodes, , , These are the weight coefficients of the corresponding feature terms, and ; The individual medical and elderly care feature values are concatenated according to preset dimensions to generate a structured health feature vector integrating medical and elderly care, expressed as follows: ， in, This represents the total number of dimensions related to medical and elderly care features. This is a structured health feature vector.
3. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 1, characterized in that, The risk identification processor is also used to build and train the risk assessment model, the building process including: Obtain historical health feature datasets and corresponding risk level labels in the integrated medical and elderly care scenario, and construct a training sample set for medical and elderly care risks; The model loss is calculated on the training sample set, and the expression is: ， in, This represents the model loss value. The total number of medical and elderly care training samples. For the first The true risk level label for each sample The predicted risk level output by the model; Based on model loss value Perform gradient descent optimization and iteratively update the model weight matrix. W With bias term b This continues until the loss value converges, resulting in a successfully trained risk assessment model.
4. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 3, characterized in that, A preset risk assessment model is loaded, the structured health feature vector is input into the risk assessment model, and the health risk level data of the target object is output through the calculation of the risk assessment model, including: Structured health feature vectors for the integration of medical and elderly care The input risk assessment model is used to calculate the medical and health care risk score, and the expression is: ， in, To score the risks of medical and health care, The weight matrix of medical and elderly care features obtained from training the risk assessment model. For model bias terms, This is a structured health feature vector; Based on the aforementioned medical and health risk score The expression for risk level mapping is: ， in, For health risk level data, The pre-defined medical and elderly care risk level mapping function maps the risk score to one of low risk, medium risk, or high risk. Output the health risk level data .
5. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 1, characterized in that, The health risk level data is acquired and combined with the resource status data of each distributed medical and elderly care node for data fusion processing to generate distributed collaborative diagnosis and treatment strategy data, including: The matching degree of medical and elderly care resources is calculated by matching the health risk level data R with the resource status data of the distributed nodes of medical and elderly care, and the expression is: ， in, For the first Resource matching degree of each distributed node in the medical and elderly care system For the health risk level data of the target group, For the first The availability of medical and health care resources in each distributed medical and elderly care node. To match the weight coefficients, and Based on the resource matching degree of each distributed medical and elderly care node The expression for executing the cooperative strategy sorting is: ， in, Prioritize services for medical and elderly care facilities. This represents the total number of distributed nodes for medical and elderly care services. The sorting function is a descending order, based on the service priority sequence. Generate distributed collaborative diagnosis and treatment strategy data.
6. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 1, characterized in that, The distributed collaborative diagnosis and treatment strategy data is parsed, and combined with the node operation attribute data of each distributed node, to generate diagnosis and treatment channel scheduling data, including: First, calculate the node comprehensive adaptation coefficient based on the node's runtime attribute data. The expression is: ， in, For the first The overall adaptability coefficient of each distributed node in the medical and elderly care system For node hardware and permission parameters, Parameters for node location and remaining resources. , To maintain a fixed weighting ratio, ; The optimal arrangement of treatment channels is calculated based on the comprehensive adaptation coefficient of all nodes, and is expressed as follows: ， in, For the layout and marking of the passageway, Select a function for the minimum value; According to the layout markings Generate scheduling data for the diagnosis and treatment channels.
7. The distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios according to claim 1, characterized in that, Poll the operating data of each distributed node and each processor, and issue control commands, including: Perform a quantitative calculation of the operating status of the collected equipment operating data, using the following expression: ， in, For the first The operational quantization value of each hardware unit. For hardware load parameters, For hardware online status parameters, , To configure the weighting coefficients, ; Based on the operational quantization value Perform instruction matching and determination, and match the corresponding control instruction according to the preset threshold; Send the matched control commands to the corresponding distributed nodes or processors.
8. A distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios, characterized in that, include: S1. Collect multi-source health data of the target object by deploying distributed data acquisition terminals in multiple medical and elderly care distributed nodes to construct the original health dataset; S2. The feature processor performs standardization and feature extraction on the original health dataset to generate a structured health feature vector. S3. The risk identification processor inputs the structured health feature vector into the preset risk assessment model for calculation and outputs the health risk level data of the target object. S4. The collaborative decision processor combines health risk level data with resource status data of each medical and elderly care distributed node to perform data fusion processing and generate distributed collaborative diagnosis and treatment strategy data. S5, the path scheduling processor parses the distributed collaborative diagnosis and treatment strategy data, and combines it with the node operation attribute data of each distributed node to generate diagnosis and treatment channel scheduling data; S6. The central master server polls the operating data of each distributed node and each processor, and after quantization and matching, sends control commands to the corresponding devices.
9. A distributed mobile remote diagnosis and treatment collaborative system for integrated medical and elderly care scenarios, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described in claim 8.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the distributed mobile remote diagnosis and treatment collaboration method for integrated medical and elderly care scenarios as described in claim 8.