Multi-level service point linkage gene screening system, methods and storage media

Abstract

This invention provides a multi-level service point linkage gene screening system, method, and storage medium. This multi-level service point linkage gene screening system, through the coordinated linkage of a data acquisition module, cloud module, medical service module, and application collaboration module, adapts to the multi-scenario usage needs of the elderly population. It ensures the quality of raw data through specialized acquisition equipment and preprocessing mechanisms, accurately outputs disease risk scores and trend prediction results through multi-source data fusion and intelligent modeling, generates scientific intervention suggestions through structured presentation and professional support, and then implements interventions through multi-terminal execution units to form a closed loop. This effectively improves the professionalism, accuracy, and operability of gene screening, achieving full-process, sustainable smart health management and optimizing the efficiency and experience of health services for the elderly population.

Description

Technical Field

[0001] This invention relates to the field of biomedical testing technology, and in particular to a multi-level service point linkage gene screening system, method and storage medium. Background Technology

[0002] As the population ages, the need for early screening and health risk management for prevalent diseases among the elderly, such as Alzheimer's disease, Parkinson's disease, cardiovascular and cerebrovascular diseases, osteoporosis, and cancer, is becoming increasingly urgent. Genetic testing technology, as a key means of early disease risk identification, has demonstrated significant value in the prevention and control of diseases in the elderly through risk assessment based on single nucleotide polymorphisms (SNPs) or specific mutation sites. Driven by the trends of smart healthcare and digital health, genetic testing services are gradually extending to grassroots scenarios such as communities and families. This aims to address the challenges faced by the elderly, such as limited mobility, long medical journeys, and weak proactive health management capabilities, through pre-emptive testing, convenient sampling, and remote interpretation, thereby meeting the needs of grassroots medical systems for personalized, continuous, and precise health services.

[0003] Currently, gene testing technologies for the elderly are mainly distributed across three scenarios: community, home, and telemedicine. In the community health service system, existing chronic disease management systems rely on traditional testing tools such as blood pressure monitors and blood glucose meters. Some solutions attempt to introduce portable nucleic acid testing instruments or simple gene testing kits, but they still adhere to the centralized laboratory testing logic, lacking integrated sampling, automated processing, and intelligent analysis capabilities, and failing to integrate gene data with vital sign data into health records. In the home setting, home sampling tools such as saliva collection kits and oral swab kits have become increasingly common. Some solutions combine mail-in testing services to achieve home sample collection, but none can provide immediate testing, lack age-friendly operation design, and suffer from insufficient sample quality stability. In the telemedicine scenario, internet healthcare platforms offer online consultation and interpretation services for gene testing reports, with doctors providing professional advice via telephone and video. However, the service process is not optimized for the cognitive characteristics of the elderly, and there is a lack of data linkage with community and home settings.

[0004] Although existing technologies have been explored in various scenarios, many problems still need to be solved:

[0005] First, the testing mode is not adaptable enough. Traditional gene testing relies heavily on professional laboratories, and it is difficult to achieve rapid and low-cost on-site screening in communities and home environments. Home sampling tools can only complete sample collection and cannot provide immediate feedback on results, resulting in low participation and insufficient testing frequency among the elderly.

[0006] Secondly, there is a lack of age-friendly design. Existing tools and services lack features such as voice guidance and large font interfaces. The operation process is complicated and cannot meet the needs of the elderly with weak digital operation ability, which can easily lead to non-standard sampling and unstable sample quality.

[0007] Third, the data linkage mechanism is imperfect, and there are serious data silos between various scenarios such as communities, families, and telemedicine. The test information cannot be automatically synchronized to the grassroots health record system, and doctors have difficulty obtaining continuous health data.

[0008] Fourth, a service loop has not yet been formed. Existing technologies lack an automatic connection mechanism between gene testing results and community health intervention resources, making it impossible to achieve full-process management of testing, evaluation, and intervention.

[0009] Fifth, there is insufficient systematic integration. A technical solution that effectively integrates community-based on-site testing, convenient home self-testing, and telemedicine interpretation has not yet been formed, making it difficult to meet the real needs of grassroots health services in an aging society for sustainable, low-cost, and high-frequency genetic risk management. Summary of the Invention

[0010] This invention provides a multi-level service point linkage gene screening system, method, and storage medium, aiming to solve the problems mentioned in the background art.

[0011] To address the aforementioned technical problems, in a first aspect, the present invention provides a multi-level service point linkage gene screening system, which includes a data acquisition module, a cloud module, a medical service module, and an application collaboration module, wherein:

[0012] The data acquisition module is used to collect raw data of the target object, and preprocess and encrypt the raw data to obtain encapsulated data. The raw data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module.

[0013] The cloud module is used to unpack the encapsulated data. The cloud module pre-stores historical data of the target object. The cloud module is also used to determine the single nucleotide polymorphism (SNP) sites corresponding to the gene sample based on a gene locus recognition engine, and to generate a unified health feature vector based on the SNP sites, physical characteristics, behavioral data, and historical data. The unified health feature vector is then used to calculate and output detection results, which include a target disease risk score, trend prediction results, and a feature contribution explanation report. The detection results are then transmitted to the medical service module.

[0014] The medical service module is used to generate structured intervention suggestions corresponding to the target object based on the test results, and transmit the structured intervention suggestions to the application collaboration module;

[0015] The application collaboration module is used to allocate the structured intervention suggestions to different execution units and execute them to obtain the corresponding gene screening execution results.

[0016] Furthermore, the data acquisition module includes a rapid gene detection unit, a home-based self-testing sampling unit, a wearable vital sign monitoring unit, and a home-based application unit, wherein:

[0017] The rapid gene detection unit and the home-based self-testing sampling unit are used to collect gene samples from the target object, wherein the rapid gene detection unit achieves high-precision collection of the gene samples, and the home-based self-testing sampling unit achieves low-precision collection of the gene samples.

[0018] The wearable vital sign monitoring unit is used to collect the physical characteristics and behavioral data;

[0019] The home application unit is used to evaluate the sampling quality of the gene samples collected by the home self-testing sampling unit.

[0020] Furthermore, the cloud module is specifically used for:

[0021] The encapsulated data is decapsulated, and different data are stored in layers with encrypted encryption.

[0022] The gene locus identification engine uses a differential algorithm to determine the single nucleotide polymorphism sites in the gene samples collected by the rapid gene detection unit and the home-based self-testing sampling unit, respectively.

[0023] The single nucleotide polymorphism sites, the physical characteristics, the behavioral data, and the historical data are input into a multi-source fusion feature model for feature fusion to generate the unified health feature vector;

[0024] The unified health feature vector is input into the disease risk calculation model to obtain the target disease risk score, the trend prediction result, and the feature contribution explanation report, which are then integrated into the detection result.

[0025] Furthermore, the medical service module is specifically used for:

[0026] The detection results are received, and data analysis is performed on the target disease risk score, the trend prediction results, and the feature contribution explanation report to obtain risk explanation results, dynamic trend maps, and the meaning of gene effects.

[0027] The risk interpretation results, the dynamic trend map, and the meaning of the gene effect are used as decision-making criteria and input into a preset medical experience-optimized intervention model for analysis to obtain the structured intervention recommendations.

[0028] Furthermore, the execution unit of the application collaboration module includes an electronic record unit, a family push unit, a scheduling unit, and a service work unit, wherein:

[0029] The electronic archive unit is used to store the raw data and the detection results in the form of entries in a database that determines access content according to permissions, based on the structured intervention recommendations;

[0030] The family push unit is used to read access content with corresponding permissions from the electronic file unit according to the structured intervention suggestions, and push it to the target object;

[0031] The scheduling unit is used to generate and manage medical service tasks for the target object based on the structured intervention recommendations;

[0032] The service work unit is used to push the medical service task to different medical staff, obtain the gene screening execution results corresponding to different medical execution tasks, and return the gene screening execution results to the scheduling unit.

[0033] Furthermore, the wearable vital sign monitoring unit is also used to correct the body posture characteristics and behavioral data, and to meet the following conditions:

[0034] ;

[0035] in, The corrected physical characteristics and behavioral data, The collected body features and behavioral data, Due to environmental interference deviation, For deviations in equipment operating status, and This is the deviation correction factor;

[0036] The sampling quality assessment performed by the home application unit involves calculating a quality score for the gene samples and resampling gene samples that do not meet preset score requirements. The quality score must satisfy the following conditions:

[0037] ;

[0038] in, For the quality score, Light index, For image sharpness parameters, To ensure the standardization of the sampling process, For the stability of the test strip signal, - The weights are dynamically learned by the system.

[0039] Furthermore, the unified health feature vector satisfies the following condition:

[0040] ;

[0041] in, For the unified health feature vector, For the first The encoding of each of the single nucleotide polymorphism sites; For the first The physical characteristics of the individual, For the first The behavioral data or the historical data; , , Preset fusion weights;

[0042] The target disease risk score meets the following conditions:

[0043] ;

[0044] in, For disease The target disease risk score, For the Sigmoid function, The gene locus weight represents the weight of a single nucleotide polymorphism site in relation to the disease. The magnitude of the impact, The weights of the aforementioned body features; The weights are those of the unified health feature vector.

[0045] Secondly, the present invention also provides a multi-level service point linkage gene screening method, wherein the multi-level service points include a data collection terminal, a cloud platform, a medical service terminal, and an application collaboration terminal, and the multi-level service point linkage gene screening method includes the following steps:

[0046] The data acquisition module is used to collect raw data of the target object, and preprocess and encrypt the raw data to obtain encapsulated data. The raw data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module.

[0047] The cloud module is used to unpack the encapsulated data. The cloud module pre-stores historical data of the target object. It is also used to determine the single nucleotide polymorphism (SNP) sites corresponding to the gene sample based on a gene locus recognition engine, and to generate a unified health feature vector based on the SNP sites, physical characteristics, behavioral data, and historical data. The unified health feature vector is then used to calculate and output detection results, which include a target disease risk score, trend prediction results, and a feature contribution explanation report. The detection results are then transmitted to the medical service module.

[0048] The medical service terminal generates structured intervention suggestions corresponding to the target object based on the test results, and transmits the structured intervention suggestions to the application collaboration terminal;

[0049] The structured intervention recommendations are distributed to different execution units and executed through the application collaboration terminal to obtain the corresponding gene screening execution results.

[0050] Thirdly, the present invention also provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the multi-level service point linkage gene screening method as described in any of the above embodiments.

[0051] Fourthly, the present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the multi-level service point linkage gene screening method as described in any of the above embodiments.

[0052] The beneficial effects achieved by this invention lie in proposing a multi-level service point linkage gene screening system. This system, through the coordinated linkage of data acquisition modules, cloud modules, medical service modules, and application collaboration modules, adapts to the multi-scenario usage needs of the elderly population. It ensures the quality of raw data with the help of professional acquisition equipment and preprocessing mechanisms, accurately outputs disease risk scores and trend prediction results through multi-source data fusion and intelligent modeling, generates scientific intervention suggestions through structured presentation and professional support, and then implements intervention through multi-terminal execution units to form a closed loop. This effectively improves the professionalism, accuracy, and operability of gene screening, realizes full-process and sustainable smart health management, and optimizes the efficiency and experience of health services for the elderly population. Attached Figure Description

[0053] The present invention will now be described in detail with reference to the accompanying drawings. The above and other aspects of the present invention will become clearer and more readily understood through the detailed description following the accompanying drawings. In the drawings:

[0054] Figure 1 This is a schematic diagram of the structure of the multi-level service point linkage gene screening system provided in an embodiment of the present invention;

[0055] Figure 2 This is a flowchart illustrating the steps of the multi-level service point linkage gene screening method provided in this embodiment of the invention;

[0056] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0058] Example 1

[0059] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of a multi-level service point linkage gene screening system 100 provided in an embodiment of the present invention. The multi-level service point linkage gene screening system 100 includes a data acquisition module 101, a cloud module 102, a medical service module 103, and an application collaboration module 104, wherein:

[0060] The data acquisition module 101 is used to acquire the raw data of the target object, and preprocess and encrypt the raw data to obtain encapsulated data. The raw data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module 102.

[0061] The cloud module 102 is used to unpack the encapsulated data. The cloud module 102 pre-stores the historical data of the target object. The cloud module 102 is also used to determine the single nucleotide polymorphism (SNP) site corresponding to the gene sample based on the gene site recognition engine, and generate a unified health feature vector based on the SNP site, the physical characteristics, the behavioral data, and the historical data. The unified health feature vector is used to calculate and output the detection results, wherein the detection results include a target disease risk score, trend prediction results, and a feature contribution explanation report. Afterward, the detection results are transmitted to the medical service module 103.

[0062] The medical service module 103 is used to generate structured intervention suggestions corresponding to the target object based on the test results, and transmit the structured intervention suggestions to the application collaboration module 104;

[0063] The application collaboration module 104 is used to allocate the structured intervention suggestions to different execution units and execute them to obtain the corresponding gene screening execution results.

[0064] Specifically, the data acquisition module 101 includes a rapid gene detection unit 1011, a home-based self-testing sampling unit 1012, a wearable vital sign monitoring unit 1013, and a home-based application unit 1014, wherein:

[0065] The rapid gene detection unit 1011 and the home-based self-testing sampling unit 1012 are used to collect the gene sample of the target object, wherein the rapid gene detection unit 1011 achieves high-precision collection of the gene sample, and the home-based self-testing sampling unit 1012 achieves low-precision collection of the gene sample.

[0066] The wearable vital sign monitoring unit 1013 is used to collect the physical characteristics and behavioral data;

[0067] The home application unit 1014 is used to evaluate the sampling quality of the gene samples collected by the home self-testing sampling unit 1012.

[0068] In this embodiment of the invention, the rapid gene detection unit 1011 is used for high-precision gene sample collection at the community level. Its design emphasizes visual prompts and protection against misoperation, enabling elderly people, community caregivers, or volunteers to complete sampling without requiring complex professional knowledge. To reduce amplification errors, the rapid gene detection unit 1011 incorporates a temperature control stabilization mechanism and an automatic background subtraction mechanism, and uploads the curve morphology, peak intensity, noise parameters, and other features of the amplification process to the cloud module 102 in structured data form. Specifically, unlike traditional methods that only upload the final result, this embodiment of the invention emphasizes the transmission of original signals and key process features, allowing the cloud module's deep model to further optimize genotype identification accuracy.

[0069] Unlike the rapid gene detection unit 1011, the home-based self-testing sampling unit 1012 is used for low-precision gene sample collection at the individual level. This is primarily designed to address the issue of elderly individuals having limited mobility and difficulty frequently visiting the community. The term "low-precision" refers to the low-precision collection compared to the high-precision collection of the rapid gene detection unit 1011. To improve the quality of home-based sampling, this embodiment uses a home-based application unit 1014 to implement a saliva collector with anti-shake technology for the elderly, a reagent strip with enhanced color development, an image capture mechanism with automatic angle calibration, and a step-by-step voice prompt system. This allows for real-time monitoring of the sampling environment, such as using a camera to measure light levels to confirm whether the illumination meets sampling requirements, using image recognition to detect whether the reagent strip is tilted or damaged, and using a microphone to analyze environmental noise interference during the sampling process.

[0070] The wearable vital sign monitoring unit 1013 is further used to correct the body posture characteristics and behavioral data, and to meet the following conditions:

[0071] ;

[0072] in, The corrected physical characteristics and behavioral data, The collected body features and behavioral data, Due to environmental interference deviation, For deviations in equipment operating status, and This is the deviation correction coefficient. By correcting for postural and behavioral data, the accuracy of vital sign data collected from older adults in less than ideal environments such as while walking, with unstable postures, and changing lighting can still be maintained.

[0073] The sampling quality assessment performed by the home application unit 1014 involves calculating a quality score for the gene samples and resampling gene samples that do not meet preset score requirements. The quality score satisfies the following conditions:

[0074] ;

[0075] in, For the quality score, Light index, For image sharpness parameters, To ensure the standardization of the sampling process, For the stability of the test strip signal, - For the system to dynamically learn weights. When When the data falls below a safety threshold, the home application unit 1014 will automatically prompt for resampling and provide improvement guidance, thereby ensuring that all home genetic sample data meet the minimum quality standards that can be used for cloud analysis.

[0076] During implementation, the data acquisition module 101 also performs timestamp alignment and format standardization on all data to ensure that time series from different devices can be correctly integrated by the cloud. To achieve seamless data transmission, this embodiment of the invention employs end-to-end encryption, a lightweight transmission protocol, and a breakpoint resume mechanism to resolve data loss caused by unstable home networks and accidental touches by elderly users. In addition, all collected data is locally encapsulated for verifiability before transmission, forming data packets with checksums to ensure that the data received by the cloud module 102 has not been tampered with or accidentally damaged.

[0077] The cloud module 102 is specifically used for:

[0078] The encapsulated data is decapsulated, and different data are stored in layers with encrypted encryption.

[0079] The gene locus identification engine uses a differential algorithm to determine the single nucleotide polymorphism sites in the gene samples collected by the rapid gene detection unit and the home-based self-testing sampling unit, respectively.

[0080] The single nucleotide polymorphism sites, the physical characteristics, the behavioral data, and the historical data are input into a multi-source fusion feature model for feature fusion to generate the unified health feature vector;

[0081] The unified health feature vector is input into the disease risk calculation model to obtain the target disease risk score, the trend prediction result, and the feature contribution explanation report, which are then integrated into the detection result.

[0082] The analysis process of cloud module 102 is first initiated by the gene locus recognition engine, which employs differentiated algorithms to address the varying accuracy requirements of different front-end acquisition methods. Specifically, during implementation, for fluorescence amplification curves, the engine extracts S-shaped dynamic features through steps such as noise subtraction, threshold calibration, peak shape analysis, and amplification efficiency fitting. Then, it determines the type of single nucleotide polymorphism (SNP) site using a lightweight convolutional network or attention network. For reagent strip images, an image recognition network is used for region segmentation, color intensity extraction, and the establishment of a mapping relationship between reagent strip color development and genotype.

[0083] Genotype data cannot be directly used for disease risk inference; therefore, unified modeling is required through a multi-source fusion feature engine. This invention employs a weighted fusion multimodal feature model to combine information such as genes, physical signs, behavioral habits, and past medical history into a unified health feature vector. This unified health feature vector satisfies the following conditions:

[0084] ;

[0085] in, For the unified health feature vector, For the first The encoding of each of the single nucleotide polymorphism sites; For the first The physical characteristics of the individual, For the first The behavioral data or the historical data; , , Preset fusion weights.

[0086] A unified health feature vector is input into the disease risk calculation engine to construct different risk scoring models based on the target disease (such as Alzheimer's disease, cardiovascular disease, Parkinson's disease, osteoporosis, etc.). The scoring model uses lightweight deep neural network algorithms and selects the optimal structure according to the characteristics of different diseases.

[0087] In this embodiment of the invention, the target disease risk score satisfies the following conditions:

[0088] ;

[0089] in, For disease The target disease risk score, For the Sigmoid function, The gene locus weight represents the weight of a single nucleotide polymorphism site in relation to the disease. The magnitude of the impact, The weights of the aforementioned body features; The weights are those of the unified health feature vector.

[0090] In addition, the cloud module 102 also undertakes trend prediction modeling tasks. Based on multiple test results, continuous changes in vital signs and behavioral trajectories, it uses time series models to predict the future direction of health risk changes in the elderly. For example, for elderly people with significant fluctuations in vital signs and high genetic risk, the risk acceleration trend can be identified in advance, thereby triggering early intervention strategies.

[0091] To ensure the medical interpretability of the output, a model interpretation method is adopted. Through methods such as SHAP value and feature contribution ranking, the influence of gene loci and physical characteristics on the final risk score can be clearly shown.

[0092] Since different terminals in this embodiment of the invention perform different functions, the cloud module 102 employs layered encrypted storage for data security. Gene-related data is stored in an independent encryption pool using a dual-key mechanism, while vital sign and behavioral data are stored in a rapid response database, ensuring a balance between rapid analysis and high security. During implementation, to reduce the cloud load during long-term operation, an automatic model scheduling and distributed inference framework are used to support simultaneous use by a large number of community terminals.

[0093] The medical service module 103 is specifically used for:

[0094] The detection results are received, and data analysis is performed on the target disease risk score, the trend prediction results, and the feature contribution explanation report to obtain risk explanation results, dynamic trend maps, and the meaning of gene effects.

[0095] The risk interpretation results, the dynamic trend map, and the meaning of the gene effect are used as decision-making criteria and input into a preset medical experience-optimized intervention model for analysis to obtain the structured intervention recommendations.

[0096] The medical experience optimization intervention model is an analysis model that uses medical experience data and pathological data as a database. The medical service module 103 aims to interpret the test results through medical experience data and pathological analysis.

[0097] Specifically, the risk interpretation results can be presented in a professional and easy-to-read format, showing risk scores, feature contribution, and model interpretation information, generating disease risk level descriptions and marking the distribution of peers; risk decomposition interpretations can be provided based on SHAP values ​​or feature contribution rankings, distinguishing between genetic, lifestyle, and abnormal physical signs risks, and identifying the main influencing factors of risk; a dynamic update mechanism and explanations of clinical reference significance can be added to provide evidence support for the judgment.

[0098] For dynamic trend maps, multi-dimensional dynamic visualization technology can be used to integrate vital signs, behaviors, risk scores and genetic baseline risk data from multiple time periods to generate maps such as vital sign change curves and risk fluctuation ranges, which can intuitively reveal risk acceleration points; key health event nodes can be automatically marked, and manual adjustment of time windows can be supported to help comprehensively judge the evolution of health status.

[0099] For gene effect results, the structured display of gene loci and allele types identified by cloud module 102 can be combined with disease risk color-coded partitioning; it supports tracing back to view original evidence such as fluorescence amplification curves and reagent strip images, and verifies the reliability of cloud identification results by checking the integrity of amplification curves, peak signal morphology and reagent strip color development stability; it automatically generates gene function annotations, clarifies the association between loci and related diseases, calculates multi-gene risk scores and presents locus interaction effects, and constructs a complete genetic risk judgment system.

[0100] The final structured intervention recommendations mainly involve transforming test results into structured language by combining medical experience data and pathological analysis to optimize the plan. This covers various aspects such as lifestyle adjustments. For example, the intervention effect is fed back through an automatic tracking mechanism. If the risk improves, a closed loop is formed. If it is ineffective, the warning level is raised and further examination or referral is suggested.

[0101] The execution unit of the application collaboration module 104 includes an electronic file unit 1041, a family push unit 1042, a scheduling unit 1043, and a service work unit 1044, wherein:

[0102] The electronic file unit 1041 is used to store the raw data and the detection results in the form of entries in a database that determines access content according to permissions, based on the structured intervention recommendations;

[0103] The family push unit 1042 is used to read access content with corresponding permissions from the electronic file unit 1041 according to the structured intervention suggestion, and push it to the target object;

[0104] The scheduling unit 1043 is used to generate and manage medical service tasks for the target object based on the structured intervention recommendations;

[0105] The service work unit 1044 is used to push the medical service task to different medical staff, obtain the gene screening execution results corresponding to different medical execution tasks, and return the gene screening execution results to the scheduling unit 1043.

[0106] The implementation of Electronic Record Unit 1041 allows for the storage of every sampling record, every vital sign data point, every genetic test result, every remote diagnostic opinion, and every intervention implementation for the target individual at the family and community levels in a time-series format within a cloud archive, forming a complete health profile spanning multiple years and across various scenarios. Based on a database implementation, Electronic Record Unit 1041 supports automatic data cleaning, timestamp alignment, outlier detection, and version recording, ensuring structural consistency across different data types and providing a foundation for long-term health trend modeling. Furthermore, Electronic Record Unit 1041 employs a hierarchical access control mechanism for refined data management. Different roles, such as the elderly, family members, community healthcare workers, and remote doctors, can view different content according to preset access permissions, thereby preventing privacy data leaks.

[0107] The family push unit 1042 can be considered a data interface at the family level and can be implemented on terminal devices through applications. During implementation, the family push unit 1042 can support the operation guidance, real-time evaluation of sampling quality, and reminders for lost steps of the family-side self-testing sampling unit 1012. It also undertakes tasks such as receiving health results, abnormal push notifications, intervention task management, and collaborative management among family members. Considering the differences in cognitive abilities among elderly users, the application of the family push unit 1042 features elderly-friendly functions in its interface design, such as enlarged buttons, voice guidance, color grading, and automatic error correction, enabling users to complete detection and intervention tasks with minimal operational pressure. Simultaneously, the application of the family push unit 1042 supports family member binding, allowing children to remotely view the elderly person's health status, sampling status, and intervention execution, forming a collaborative network between family care and community services. The application of the family push unit 1042 can also use a behavior analysis module to record the elderly person's habitual patterns during daily use. If it detects prolonged inactivity of the application or failure to complete follow-up tests on time, the system will send an alert to reduce the risk of increased risk due to user behavioral deviations.

[0108] The scheduling unit 1043 is used to integrate resources for performing medical service tasks, including rehabilitation equipment, medical resources, expert services, follow-up personnel, etc., and to allocate intervention tasks to appropriate implementers on time and as needed through an intelligent scheduling mechanism.

[0109] Service work unit 1044 specifically implements the execution of medical service tasks. In this embodiment of the invention, service work unit 1044 can adopt a service priority ranking mechanism to automatically rank high-risk groups or tasks with high intervention urgency. The ranking mechanism can be expressed as the following conditions:

[0110] ;

[0111] in, Score based on service priority. Assess the risk score for the target disease; Factors contributing to task incompleteness include overdue days and degree of delay. These are trend risk factors, such as the degree of risk acceleration and the frequency of abnormal physical signs. - These are system parameters used to balance the weights of different factors. This prioritization model enables healthcare workers to prioritize the most urgent user needs within a limited timeframe, thereby improving the accuracy and efficiency of community health services.

[0112] The beneficial effects achieved by this invention lie in proposing a multi-level service point linkage gene screening system. This system, through the coordinated linkage of data acquisition modules, cloud modules, medical service modules, and application collaboration modules, adapts to the multi-scenario usage needs of the elderly population. It ensures the quality of raw data with the help of professional acquisition equipment and preprocessing mechanisms, accurately outputs disease risk scores and trend prediction results through multi-source data fusion and intelligent modeling, generates scientific intervention suggestions through structured presentation and professional support, and then implements intervention through multi-terminal execution units to form a closed loop. This effectively improves the professionalism, accuracy, and operability of gene screening, realizes full-process and sustainable smart health management, and optimizes the efficiency and experience of health services for the elderly population.

[0113] Example 2

[0114] This invention also provides a multi-level service point linkage gene screening method, wherein the multi-level service points include a data collection terminal, a cloud platform, a medical service terminal, and an application collaboration terminal. Please refer to [link / reference]. Figure 2 , Figure 2 This is a flowchart illustrating the steps of a multi-level service point-linked gene screening method provided in an embodiment of the present invention. The multi-level service point-linked gene screening method includes the following steps:

[0115] S201. The data acquisition module is used to acquire the original data of the target object, and preprocess and encrypt the original data to obtain encapsulated data. The original data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module.

[0116] S202. The cloud module is used to unpack the encapsulated data. The cloud module pre-stores historical data of the target object. The cloud module is also used to determine the single nucleotide polymorphism (SNP) site corresponding to the gene sample based on the gene site recognition engine, and generate a unified health feature vector based on the SNP site, the physical characteristics, the behavioral data, and the historical data. The detection result is calculated and output based on the unified health feature vector, wherein the detection result includes a target disease risk score, trend prediction result, and feature contribution explanation report. Then, the detection result is transmitted to the medical service module.

[0117] S203. The medical service terminal generates a structured intervention suggestion corresponding to the target object based on the test results, and transmits the structured intervention suggestion to the application collaboration terminal;

[0118] S204. The structured intervention suggestions are distributed to different execution units and executed through the application collaboration terminal to obtain the corresponding gene screening execution results.

[0119] The multi-level service point linkage gene screening method is the method steps executed by each module in the multi-level service point linkage gene screening system in the above embodiments. Therefore, this method can achieve the same technical effect. Referring to the description in the above embodiments, it will not be repeated here.

[0120] Example 3

[0121] This invention also provides a computer device, please refer to... Figure 3 , Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. The computer device 300 includes: a memory 302, a processor 301, and a computer program stored in the memory 302 and executable on the processor 301.

[0122] The processor 301 calls the computer program stored in the memory 302 to execute the steps in the multi-level service point linkage gene screening method provided in this embodiment of the invention. Please refer to... Figure 2 Specifically, it includes the following steps:

[0123] S201. The data acquisition module is used to acquire the original data of the target object, and preprocess and encrypt the original data to obtain encapsulated data. The original data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module.

[0124] S202. The cloud module is used to unpack the encapsulated data. The cloud module pre-stores historical data of the target object. The cloud module is also used to determine the single nucleotide polymorphism (SNP) site corresponding to the gene sample based on the gene site recognition engine, and generate a unified health feature vector based on the SNP site, the physical characteristics, the behavioral data, and the historical data. The detection result is calculated and output based on the unified health feature vector, wherein the detection result includes a target disease risk score, trend prediction result, and feature contribution explanation report. Then, the detection result is transmitted to the medical service module.

[0125] S203. The medical service terminal generates a structured intervention suggestion corresponding to the target object based on the test results, and transmits the structured intervention suggestion to the application collaboration terminal;

[0126] S204. The structured intervention suggestions are distributed to different execution units and executed through the application collaboration terminal to obtain the corresponding gene screening execution results.

[0127] The computer device 300 provided in this embodiment of the invention can implement the steps in the multi-level service point linkage gene screening method as described in the above embodiments, and can achieve the same technical effect. Referring to the description in the above embodiments, it will not be repeated here.

[0128] Example 4

[0129] This invention also provides a storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes and steps in the multi-level service point linkage gene screening method provided in this invention and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0130] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by hardware related to computer programs or instructions. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0131] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0132] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0133] The embodiments of the present invention have been described above with reference to the accompanying drawings. The disclosed embodiments are merely preferred embodiments of the present invention. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many equivalent changes in form under the guidance of the present invention without departing from the spirit and scope of the claims. All such changes are within the protection scope of the present invention.

Claims

1. A multi-level service point linkage gene screening system, characterized in that, The multi-level service point linkage gene screening system includes a data acquisition module, a cloud module, a medical service module, and an application collaboration module, wherein: The data acquisition module is used to collect raw data of the target object, and preprocess and encrypt the raw data to obtain encapsulated data. The raw data includes gene samples, physical characteristics and behavioral data. Then, the encapsulated data is transmitted to the cloud module. The cloud module is used to unpack the encapsulated data. The cloud module pre-stores historical data of the target object. The cloud module is also used to determine the single nucleotide polymorphism (SNP) sites corresponding to the gene sample based on a gene locus recognition engine, and to generate a unified health feature vector based on the SNP sites, physical characteristics, behavioral data, and historical data. The unified health feature vector is then used to calculate and output detection results, which include a target disease risk score, trend prediction results, and a feature contribution explanation report. The detection results are then transmitted to the medical service module. The medical service module is used to generate structured intervention suggestions corresponding to the target object based on the test results, and transmit the structured intervention suggestions to the application collaboration module; The application collaboration module is used to allocate the structured intervention suggestions to different execution units and execute them to obtain the corresponding gene screening execution results; The data acquisition module includes a rapid gene detection unit, a home-based self-testing sampling unit, a wearable vital sign monitoring unit, and a home-based application unit, wherein: The rapid gene detection unit and the home-based self-testing sampling unit are used to collect gene samples from the target object, wherein the rapid gene detection unit achieves high-precision collection of the gene samples, and the home-based self-testing sampling unit achieves low-precision collection of the gene samples. The wearable vital sign monitoring unit is used to collect the physical characteristics and behavioral data; The home application unit is used to evaluate the sampling quality of the gene samples collected by the home self-testing sampling unit; The cloud module is specifically used for: The encapsulated data is decapsulated, and different data are stored in layers with encrypted encryption. The gene locus identification engine uses a differential algorithm to determine the single nucleotide polymorphism sites in the gene samples collected by the rapid gene detection unit and the home-based self-testing sampling unit, respectively. The single nucleotide polymorphism sites, the physical characteristics, the behavioral data, and the historical data are input into a multi-source fusion feature model for feature fusion to generate the unified health feature vector; The unified health feature vector is input into the disease risk calculation model to obtain the target disease risk score, the trend prediction result and the feature contribution explanation report, and then integrated into the detection result. The unified health feature vector satisfies the following conditions: ； in, For the unified health feature vector, For the first The encoding of each of the single nucleotide polymorphism sites; For the first The physical characteristics of the individual, For the first The behavioral data or the historical data; , , Preset fusion weights; The target disease risk score meets the following conditions: ； in, For disease The target disease risk score, For the Sigmoid function, The gene locus weight represents the weight of a single nucleotide polymorphism site in relation to the disease. The magnitude of the impact, The weights of the aforementioned body features; The weights are those of the unified health feature vector.

2. The multi-level service point linkage gene screening system according to claim 1, characterized in that, The medical service module is specifically used for: The detection results are received, and data analysis is performed on the target disease risk score, the trend prediction results, and the feature contribution explanation report to obtain risk explanation results, dynamic trend maps, and the meaning of gene effects. The risk interpretation results, the dynamic trend map, and the meaning of the gene effect are used as decision-making criteria and input into a preset medical experience-optimized intervention model for analysis to obtain the structured intervention recommendations.

3. The multi-level service point linkage gene screening system according to claim 1, characterized in that, The execution units of the application collaboration module include an electronic archive unit, a family push unit, a scheduling unit, and a service work unit, wherein: The electronic archive unit is used to store the raw data and the detection results in the form of entries in a database that determines access content according to permissions, based on the structured intervention recommendations; The family push unit is used to read access content with corresponding permissions from the electronic file unit according to the structured intervention suggestions, and push it to the target object; The scheduling unit is used to generate and manage medical service tasks for the target object based on the structured intervention recommendations; The service work unit is used to push the medical service task to different medical staff, obtain the gene screening execution results corresponding to different medical execution tasks, and return the gene screening execution results to the scheduling unit.

4. The multi-level service point linkage gene screening system according to claim 1, characterized in that, The wearable vital sign monitoring unit is also used to correct the body posture characteristics and behavioral data, and to meet the following conditions: ； in, The corrected physical characteristics and behavioral data, The collected body features and behavioral data, Due to environmental interference deviation, For deviations in equipment operating status, and This is the deviation correction factor; The sampling quality assessment performed by the home application unit involves calculating a quality score for the gene samples and resampling gene samples that do not meet preset score requirements. The quality score must satisfy the following conditions: ； in, For the quality score, Light index, For image sharpness parameters, To ensure the standardization of the sampling process, For the stability of the test strip signal, - The weights are dynamically learned by the system.

5. A multi-level service point linkage gene screening method, characterized in that, The multi-level service points include a data acquisition module, a cloud module, a medical service module, and an application collaboration module. The multi-level service point linkage gene screening method includes the following steps: The data acquisition module collects raw data of the target object, preprocesses and encrypts the raw data to obtain encapsulated data, wherein the raw data includes gene samples, physical characteristics and behavioral data; then, the encapsulated data is transmitted to the cloud module. The cloud module unpacks the encapsulated data, which pre-stores historical data of the target object. The cloud module is also used to determine the single nucleotide polymorphism (SNP) sites corresponding to the gene sample based on a gene locus recognition engine, and to generate a unified health feature vector based on the SNP sites, physical characteristics, behavioral data, and historical data. The unified health feature vector is then used to calculate and output detection results, which include a target disease risk score, trend prediction results, and a feature contribution explanation report. The detection results are then transmitted to the medical service module. The medical service module generates structured intervention suggestions for the target object based on the test results, and transmits the structured intervention suggestions to the application collaboration module. The structured intervention recommendations are assigned to different execution units and executed through the application collaboration module to obtain the corresponding gene screening execution results; The data acquisition module includes a rapid gene detection unit, a home-based self-testing sampling unit, a wearable vital sign monitoring unit, and a home-based application unit, wherein: The rapid gene detection unit and the home-based self-testing sampling unit are used to collect gene samples from the target object, wherein the rapid gene detection unit achieves high-precision collection of the gene samples, and the home-based self-testing sampling unit achieves low-precision collection of the gene samples. The wearable vital sign monitoring unit is used to collect the physical characteristics and behavioral data; The home application unit is used to evaluate the sampling quality of the gene samples collected by the home self-testing sampling unit; Specifically executed through the cloud module: The encapsulated data is decapsulated, and different data are stored in layers with encrypted encryption. The gene locus identification engine uses a differential algorithm to determine the single nucleotide polymorphism sites in the gene samples collected by the rapid gene detection unit and the home-based self-testing sampling unit, respectively. The single nucleotide polymorphism sites, the physical characteristics, the behavioral data, and the historical data are input into a multi-source fusion feature model for feature fusion to generate the unified health feature vector; The unified health feature vector is input into the disease risk calculation model to obtain the target disease risk score, the trend prediction result and the feature contribution explanation report, and then integrated into the detection result. The unified health feature vector satisfies the following conditions: ； in, For the unified health feature vector, For the first The encoding of each of the single nucleotide polymorphism sites; For the first The physical characteristics of the individual, For the first The behavioral data or the historical data; , , Preset fusion weights; The target disease risk score meets the following conditions: ； in, For disease The target disease risk score, For the Sigmoid function, The gene locus weight represents the weight of a single nucleotide polymorphism site in relation to the disease. The magnitude of the impact, The weights of the aforementioned body features; The weights are those of the unified health feature vector.

6. A computer device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multi-level service point linkage gene screening method as described in claim 5.

7. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the multi-level service point linkage gene screening method as described in claim 5.

Images