Biological infection condition monitoring and evaluation method and system

Abstract

The invention discloses a biological infection condition monitoring evaluation method and system, and relates to the technical field of data processing, and the method comprises the steps: reading biological infection data, carrying out data system conversion, executing co-reference disambiguation, and building a biological infection map; establishing a tracking evaluation module based on the biological infection atlas; carrying out regional biological state monitoring, and returning biological monitoring data; performing infection positioning decision and evolution trend prediction, and determining an infection characteristic single column; and carrying out display interface visualization and alarm, and determining a prevention and control plan. The technical problems that different infection data cannot be accurately integrated in real time in existing biological infection condition monitoring, the infection condition cannot be accurately positioned, the evolution trend cannot be predicted, and the timeliness and the accuracy of a biological infection condition monitoring evaluation result are poor are solved. Omnibearing and multi-level monitoring and evaluation of biological infection conditions are achieved, and the technical effect of improving the accuracy and timeliness of infection condition monitoring and evaluation results is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to data processing, and specifically to a method and system for monitoring and evaluating biological infection conditions. Background Art

[0002] In today's world, monitoring and evaluation of biological infections are crucial for maintaining public health and preventing disease outbreaks. With the rapid development of biotechnology and the increasing frequency of global exchanges, the risk of biological infections is increasing. How to effectively monitor and evaluate the status of biological infections has become an urgent problem to be solved in the field of public health. Due to the limitations, dispersion, complexity and uncertainty of infection data sources, traditional monitoring and evaluation of biological infection status relies on regular inspections and on-site sampling, as well as reports from medical institutions and epidemiological surveys. It is difficult to conduct a comprehensive and accurate assessment of the entire biological infection status, and it is impossible to accurately evaluate the development trend and potential risks of infection events, which makes it difficult to meet the needs of modern public health management.

[0003] Therefore, in the current technologies related to biological infection status monitoring and evaluation, there is a technical problem that it is difficult to integrate different infection data in real time and accurately, which leads to the inability to accurately locate the infection status and predict the evolution trend, resulting in poor timeliness and accuracy of the biological infection status monitoring and evaluation results. Summary of the Invention

[0004] This application provides a method and system for monitoring and evaluating biological infection conditions, which solves the technical problem of existing biological infection condition monitoring that it is difficult to integrate different infection data in real time and accurately, which leads to the inability to accurately locate the infection condition and predict the evolution trend, resulting in poor timeliness and accuracy of the biological infection condition monitoring and evaluation results. It realizes all-round and multi-level monitoring and evaluation of biological infection conditions, and achieves the technical effect of improving the accuracy and timeliness of infection condition monitoring and evaluation results.

[0005] The present application provides a method for monitoring and evaluating biological infection conditions, the method comprising: linking a biological resource library based on a data interface, reading biological infection data and performing data system conversion, performing coreference disambiguation to build a biological infection map, wherein the biological infection map has distinguishing marks based on visual features and biological features; building a tracking and evaluation module based on the biological infection map, wherein the tracking and evaluation module includes a case analysis block and a system analysis block; cooperating with a regional monitoring device to monitor regional biological conditions, assisting with a network time protocol, and returning biological monitoring data, wherein the regional monitoring device includes a biological sensor and an auxiliary monitoring device; based on the biological monitoring data, performing multi-source fusion of same-frequency data, combining with the tracking and evaluation module, making infection location decisions and predicting evolution trends, and determining a single infection feature column; visualizing and issuing an alarm on a display interface for the single infection feature column, and determining a prevention and control plan based on the single infection feature column, wherein authorization authentication exists for single column calls.

[0006] In a possible implementation, the biological infection map is constructed by performing the following processing: identifying the biological infection data, performing a primary clustering based on the infection source, performing a secondary clustering based on the biological species, and determining the clustering results; traversing the clustering results, and mining and constructing an infection data system based on common standards, wherein the infection data system includes an infection system layer and an evaluation system layer, and the infection data system corresponds one-to-one to the clustering results; traversing the infection data system for association, and performing co-reference disambiguation to generate the biological infection map.

[0007] In a possible implementation, the biological infection map has distinguishing marks based on visual features and biological features, and the following processing is performed: the visual features are intuitive representational features, and the biological features are molecular biological features; the biological infection map is traversed to perform unary map marking based on the visual features and binary map marking based on the biological features; the unary map marking and the binary map marking are traversed to associate the mapping marking nodes based on feature homology.

[0008] In a possible implementation, the multi-source fusion of same-frequency data further performs the following processing: identifying the timestamp to determine the multi-source data of the same frequency, and determining the main data structure, wherein the main data structure is any data structure in the biological monitoring data; based on the main data structure, performing heterogeneous conversion on the multi-source data of the same frequency to determine homogeneous data; traversing the homogeneous data, performing homogeneous data group fusion, and determining fused monitoring data.

[0009] In a possible implementation, the determination of the infection feature single column also performs the following processing: decomposing the fused monitoring data, combining with the individual case analysis block, performing spatiotemporal analysis of the individual cases in turn, and determining a first evaluation result, wherein the spatiotemporal analysis includes a space-based horizontal analysis and a time-based vertical analysis, and the first evaluation result includes a real-time evaluation result and an evolution prediction result; combining with the system analysis block, performing spatiotemporal analysis on the fused monitoring data to determine a second evaluation result; combining the first evaluation result and the second evaluation result, integrating and adding them into the infection feature single column, wherein the infection feature single column is updated synchronously with monitoring and tracking.

[0010] In a possible implementation, the integration and addition into the infection feature single column also performs the following processing: mapping the first evaluation result and the second evaluation result, determining the first promotion relationship by conducting an infection impact analysis of individual cases; guided by the same biological population, combined with the infection feature single column, determining the second infection evolution chain; guided by cross-biological populations, combined with the infection feature single column, determining the third infection evolution chain; adding the first promotion relationship, the second infection evolution chain and the third infection evolution chain into the infection feature single column.

[0011] In a possible implementation, the biological infection status monitoring and evaluation method also performs the following processing: identifying the infection feature list, determining the subjective trend elements of biological movement and infection evolution with the organism as the center; determining key monitoring points based on the subjective trend elements; and performing reverse monitoring adjustments of the monitoring system based on the key monitoring points.

[0012] The present application also provides a biological infection status monitoring and evaluation system, including: a biological infection map building module, the biological infection map building module is used to link the biological resource library based on the data interface, read the biological infection data and perform data system conversion, perform coreference disambiguation to build a biological infection map, the biological infection map has distinguishing marks based on visual features and biological features; a tracking and evaluation module building module, the tracking and evaluation module building module is based on the biological infection map, the tracking and evaluation module includes an individual analysis block and a system analysis block; a biological monitoring data return module, the biological monitoring data return module is used to assist The same-area monitoring device monitors the regional biological status, assists the network time protocol, and returns the biological monitoring data, wherein the regional monitoring device includes a biological sensor and an auxiliary monitoring device; an infection feature single column determination module, the infection feature single column determination module performs multi-source fusion of the same-frequency data based on the biological monitoring data, combines the tracking and evaluation module to make infection positioning decisions and evolution trend predictions, and determine the infection feature single column; a prevention and control plan determination module, the prevention and control plan determination module is used to visualize and alarm the infection feature single column on the display interface, and determine the prevention and control plan based on the infection feature single column, wherein the single column call has permission authentication.

[0013] The present application proposes a biological infection status monitoring and evaluation method and system, which is based on a data interface to link to a biological resource library, read biological infection data and perform data system conversion, perform coreference disambiguation to build a biological infection map, and the biological infection map has distinguishing marks based on visual features and biological features; based on the biological infection map, a tracking and evaluation module is built, and the tracking and evaluation module includes a case analysis block and a system analysis block; a coordinated regional monitoring device is used to monitor the regional biological status, assist in the network time protocol, and return biological monitoring data, wherein the regional monitoring device includes a biological sensor and an auxiliary monitoring device; based on the biological monitoring data, multi-source fusion of the same-frequency data is performed, combined with the tracking and evaluation module, infection location decision-making and evolution trend prediction are carried out to determine the infection feature column; the infection feature column is visualized and alarmed on the display interface, and a prevention and control plan is determined based on the infection feature column, wherein the column call has permission authentication. The present invention solves the technical problem that existing biological infection status monitoring is difficult to integrate different infection data in real time and accurately, which leads to the inability to accurately locate the infection status and predict the evolution trend, resulting in poor timeliness and accuracy of the biological infection status monitoring and evaluation results. It realizes all-round and multi-level monitoring and evaluation of biological infection status, and achieves the technical effect of improving the accuracy and timeliness of infection status monitoring and evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0015] Figure 1 A flow chart of a method for monitoring and evaluating biological infection conditions provided in an embodiment of the present application.

[0016] Figure 2 This is a schematic diagram of the structure of a biological infection status monitoring and evaluation system provided in an embodiment of the present application.

[0017] Figure 3 A schematic diagram of a biological infection map in a biological infection status monitoring and evaluation method provided in an embodiment of the present application.

[0018] Explanation of the accompanying symbols: biological infection map building module 10, tracking and evaluation module building module 20, biological monitoring data feedback module 30, infection feature single column determination module 40, prevention and control plan determination module 50. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0022] The present application provides a method for monitoring and evaluating biological infection status, such as Figure 1 As shown, the method includes: Step S100 involves connecting to a biological resource library via a data interface, reading biological infection data, performing data system conversion, and performing coreference disambiguation to construct a biological infection map. The biological infection map includes distinguishing markers based on visual features and biological characteristics. Through a data interface connection method (such as an API connection, a database connection, or a file transfer connection), the data processing system can exchange and communicate data with an external biological resource library. The biological resource library is a database containing a large amount of biological infection data resources. Specifically, the data processing system reads biological infection data, such as experimental data, sequencing data, and clinical data, from the biological resource library via the data interface. This biological infection data records various information and characteristics of biological infections. Specifically, the search targets based on the biological resource library include sensitive data categories guided by search permissions, public data categories, and shared data categories. For example, for a specific infection source, relevant literature and records are searched to determine basic infection information such as infection channels, infection rates, evolutionary variation characteristics, and influencing factors, thereby mining and refining basic information. At the same time, due to the diversity of retrieval sources, data heterogeneity exists, making it difficult to conduct joint analysis of heterogeneous data. By converting the data structure and format, data uniformity is achieved, laying a solid foundation for subsequent graph construction. Among them, data conversion is the conversion of raw data from one format or structure to another, that is, from the raw data format in the biological resource library to a data format that can be analyzed and processed by the data processing system. Co-reference disambiguation is used in natural language processing to solve the problem that multiple different expressions (such as words, phrases, and sentences) may point to the same entity. In biological infection data, co-reference disambiguation may be used to solve the problem that different data items or records may point to the same biological infection event or pathogen. By performing co-reference disambiguation, the accuracy and consistency of the data can be improved, providing a more reliable data foundation for the subsequent construction of biological infection maps. The Biological Infection Atlas is a visualization tool used to display information such as biological infection status, pathogen relationships, and infection pathways. Within the Biological Infection Atlas, one can clearly visualize the connections between different pathogens, the timeline of infection events, infection sources, and transmission pathways. The Biological Infection Atlas uses distinguishing markers based on both visual and biological features. Visual distinguishing markers (such as color, shape, and size) are used to distinguish different pathogens, infection events, or infected areas; biological features (such as pathogen genetic sequence, antigenicity, and drug resistance) are used to distinguish different pathogens or infection types, providing a deeper understanding of the mechanisms and characteristics of biological infections. Overall, by connecting to biological resource repositories through data interfaces, accessing biological infection data, performing data system conversion, performing coreference disambiguation, and constructing the Biological Infection Atlas, a comprehensive and in-depth analysis and visualization of biological infection status can be achieved.

[0023] In one possible implementation, step S100 further includes step S110, identifying the biological infection data, performing a primary clustering based on the infection source, performing a secondary clustering based on the biological species, and determining the clustering results. Data related to biological infection is screened out from the original data, which may include test results of various biological samples (such as blood, tissues, cells, etc.), case reports, epidemiological data, etc., such as infection sources (such as bacteria, viruses, parasites, etc.), biological species (such as humans, animals, plants, etc.), geographical location, infection time, etc. Clustering based on the infection source means using a clustering algorithm such as K-means, hierarchical clustering, DBSCAN, etc., selecting the infection source as the main feature of the cluster, and analyzing the infection source field, including extracting and marking the infection source information from the identified biological infection data. , biological infection data are divided into different groups based on the similarity of infection sources. The data of each cluster or group has similar infection source characteristics. For example, all infections caused by the same bacteria may be classified into one category, which can identify the main sources of infection and understand their distribution in different regions or different time periods; secondary clustering based on biological species means that within each cluster group determined by the infection source, the clustering algorithm is used again to analyze the biological species field, and the data points are further subdivided into smaller groups. Within each infection source cluster, multiple subclusters based on biological species are formed. For example, infection source A (such as a virus) causes poultry (such as chickens and ducks) to be infected, and also causes livestock (such as pigs and cattle) to be infected; infection source B (such as another virus) causes wild animals (such as monkeys and deer) to be infected; infection source C (such as bacteria) causes a variety of aquatic organisms (such as fish and shrimp) to be infected; after a clustering based on the infection source, the clusters are divided into cluster 1 (including all infection events caused by infection source A, regardless of the species), cluster 2 (including all infection events caused by infection source B), and cluster 3 (including all infection events caused by infection source C); after a second clustering based on the species, the clusters are divided into cluster 1 (including all infection events caused by infection source A, regardless of the species), cluster 2 (including all infection events caused by infection source B), and cluster 3 (including all infection events caused by infection source C). After the second clustering, the clustering results are as follows: within cluster 1 (infection source A), it includes sub-cluster 1.1, poultry infection (chickens, ducks) and sub-cluster 1.2, livestock infection (pigs, cattle); cluster 2 (infection source B) may only form one sub-cluster because it only involves wild animals; within cluster 3 (infection source C), sub-cluster 3.1 is generated, aquatic organism infection (fish, shrimp), which provides a clearer understanding of the impact of different infection sources on different biological species, that is, a more detailed analysis of the infection status of different biological species under the same or different infection sources, and a further understanding of the susceptibility or response of different biological species to these infection sources.

[0024] Step S100 also includes step S120, traversing the clustering results, mining and constructing an infection data system based on common standards, wherein the infection data system includes an infection system layer and an evaluation system layer, and the infection data system corresponds one-to-one to the clustering results. Mining and constructing an infection data system based on common standards refers to performing cluster analysis on a set of data (which may be data about a certain disease or infection), and then further constructing a structured data system based on the clustering results to better understand and analyze the characteristics, trends or impacts of the infection. When constructing an infection data system, it is necessary to organize and classify data based on certain common characteristics or standards, which may include infection type, transmission route, infection rate, mortality rate, geographic location, population characteristics, etc. The infection data system is a structured data framework used to organize and represent various data related to infection, usually including multiple levels such as the infection system layer and the evaluation system layer. The infection system layer may contain basic information about the infection. Information such as infection type, pathogen, transmission route, infection cycle, etc., provides a basic understanding of the infection itself; the evaluation system layer may focus on the evaluation or measurement of the infection, such as infection rate, morbidity, mortality, cure rate, medical resource utilization, etc., providing a quantitative assessment of the impact of the infection; the one-to-one correspondence between the infection data system and the clustering results means building a dedicated infection data system for each cluster or group. Since different clusters may represent different infection types, geographical areas or population characteristics, each cluster may require a specific data system to accurately reflect its characteristics. By building a separate data system for each cluster, the differences and connections between different clusters can be more accurately analyzed and understood.

[0025] Step S100 also includes step S130, traversing the infection data system to associate, and generating the biological infection map by coreference disambiguation. The entire infection data system is checked and analyzed one by one, and the correlation between different pathogens in the same or different hosts is calculated. The infection pattern is found using association rule mining technology. Association rule mining is a data mining method for discovering interesting relationships between items in an item set. In the context of the biological infection map, the transmission pattern between pathogens can be revealed. Finally, a network analysis is performed to identify the connections and patterns between different data points. Specifically, the pathogen data of each host infection is sorted out to form a two-dimensional data table. The rows represent hosts, the columns represent pathogens, and the cell values ​​represent whether a specific host is infected with a specific pathogen. The correlation coefficient between pathogens (such as the Pearson correlation coefficient) is calculated to quantify their tendency to appear at the same time. The independence of the distribution of two pathogens between different hosts is tested based on the chi-square test to determine their correlation. Then, the Apriori algorithm is used to Find frequently co-occurring pathogen combinations in the data, and then extract association rules, such as "If the host is infected with pathogen A, then it is also infected with pathogen B", etc. Finally, use the pathogens as nodes and the association relationships between them (such as the relationships in the association rules) as edges to construct a network, establish connections between different data points (i.e., association relationships), and reveal the inherent laws and patterns of infection events. Then, when there are multiple similar or related pathogens, use coreference disambiguation to identify different disease names, pathogen types or categories, etc. Finally, construct a biological infection map based on the results of association analysis. Specifically, based on the results of association and coreference disambiguation, determine the nodes and edges in the map, where nodes represent hosts or pathogens and edges represent infection relationships. To generate a biological infection map, different types of nodes and edges can be distinguished by attributes such as color, size, and shape to display information more intuitively.

[0026] In one possible implementation, step S100 further includes step S140, wherein the visual features are intuitive representational features, and the biological features are molecular biometric features. Visual features, or intuitive representational features, refer to those that can be observed and described directly through the senses (e.g., vision, hearing, etc.) or with the aid of visualization tools. Examples include symptoms such as fever, cough, and rash; infection sites such as the respiratory tract, digestive tract, and skin; and epidemiological data such as the number of infected people, the extent of the spread, and mortality rates. Biological features, or molecular biometric features, refer to characteristics related to the molecular level of an organism, typically requiring detection and identification through laboratory analysis or molecular biotechnology. Examples include pathogen genomic information obtained through gene sequencing, specific proteins expressed by pathogens or host cells during infection, or the host's immune response to infection, such as antibody levels and cytokine expression. The process also includes step S150, traversing the biological infection map and performing unary labeling of the map based on the visual features and binary labeling of the map based on the biological features. Unary graph labeling based on visual features refers to labeling individual elements (such as nodes or edges) in a graph. For example, different colors, shapes, or sizes can be used to represent different infection sites or symptom severity. Binary graph labeling based on biological features refers to labeling pairs of elements in a graph (such as edges between two nodes). For example, different line types, colors, or labels can be used to represent different pathogen types or infection pathways. This also includes step S160, traversing the unary graph labeling and the binary graph labeling, and mapping the associations of the labeled nodes based on feature homology. In a biological infection map, different nodes (or elements) are identified and associated based on the homology of specific features (such as visual features or biological features). Feature homology refers to the similarity or identity between the marking features of different elements or element pairs in the map. Specifically, different elements or element pairs with feature homology are connected to form an association network, that is, elements or element pairs with the same or similar features are identified, and a mapping relationship between them is established to strengthen the association between corresponding nodes in the map, for example, by adjusting the position, size, color and other attributes of the nodes.

[0027] Step S200: Building a tracking and evaluation module based on the biological infection map. The tracking and evaluation module includes an individual case analysis block and a system analysis block. The tracking and evaluation module, built based on the biological infection map, is typically used to conduct detailed tracking and analysis of biological infection events in order to evaluate the infection situation, transmission path, and effectiveness of control measures. The tracking and evaluation module consists of an individual case analysis block and a system analysis block. Specifically, the individual case analysis block focuses on the detailed analysis of a single biological infection case, which may include case information integration, infection path tracing, mutation analysis, and control measure evaluation. Case information integration refers to the collection of all information related to a specific case, such as basic case information, infection time, location, exposure history, symptoms, and diagnosis results. Infection path tracing refers to determining the possible source of infection and transmission path by analyzing the case's contact history and movement trajectory. Visual features in the biological infection map, such as color and shape, are usually required to mark different sources of infection and transmission paths. Mutation analysis refers to genetic sequencing of the pathogen in the case to analyze whether there are mutations and the impact of mutations on the transmissibility and pathogenicity of the pathogen. Control measure evaluation is to evaluate the effectiveness of the control measures taken for the case (such as isolation and treatment) and whether further adjustment and optimization are needed. The system analysis module focuses more on the systematic analysis and evaluation of the entire biological infection event, which may include infection trend analysis, transmission pattern identification, risk assessment and early warning, and resource allocation recommendations. Specifically, infection trend analysis analyzes the overall data in the biological infection map to assess changes in infection trends, such as the number of infected people, the scope of infection, and the speed of spread. Transmission pattern identification identifies the main transmission modes in the infection event, such as human-to-human transmission, animal transmission, and environmental transmission, and the impact of different transmission modes on infection trends. Risk assessment and early warning evaluates the risk of the infection event based on historical data and current conditions, and issues early warnings to enable timely control measures. Resource allocation recommendations are based on the severity and trend of the infection event, making reasonable resource allocation recommendations, such as the allocation of medical resources and vaccine distribution. The tracking and evaluation module achieves comprehensive tracking and evaluation of biological infection events through the organic combination of the individual case analysis module and the system analysis module. The individual case analysis module focuses on details and in-depth analysis, providing a solid foundation for the system analysis module. The system analysis module focuses more on the overall and macro perspective, providing a scientific basis for the formulation of effective prevention and control strategies.

[0028] Step S300, cooperate with the regional monitoring device to monitor the regional biological status, assist the network time protocol, and return the biological monitoring data, wherein the regional monitoring device includes a biosensor and an auxiliary monitoring device. The regional monitoring device may include a biosensor and an auxiliary monitoring device. The biosensor is a device that can detect specific parameters or changes of an organism or its components (such as cells, tissues, biological molecules, etc.). Through specific detection mechanisms (such as chemical, biological, physical, etc.), it monitors changes in biological status and environmental conditions in real time, thereby obtaining key data about biological infections; the auxiliary monitoring device is used to ensure the comprehensiveness and accuracy of monitoring, such as video monitoring systems, meteorological monitoring stations, environmental parameter monitors, etc., for collecting various types of data related to biological infections; the biosensors and auxiliary monitoring devices work together to form a multi-level monitoring network that covers a wide area, ensuring comprehensive monitoring of biological infections, and is used to collect data in real time. The data is then transmitted over the network to a central processing system for analysis and processing. The Network Time Protocol (NTP) is a protocol used to synchronize computer clocks, ensuring that devices on the network have an accurate time base. In biomonitoring systems, the NTP is used to ensure that returned biomonitoring data has accurate timestamps, accurately reflecting the chronological order and duration of events. Specifically, with the assistance of the NTP, biomonitoring data collected by regional monitoring devices is accurately timestamped and transmitted back over the network to the central processing system. This data includes, but is not limited to, biological status, environmental changes, and pathogen detection results. For example, biological data such as enzymes, antibodies, nucleic acids, cells, and tissues that reflect infection status or the distribution of viruses within and outside the body can be used. Real-time data collection from biosensors and auxiliary monitoring devices, combined with the time synchronization capabilities of the NTP, ensures the accuracy and timeliness of biomonitoring data.

[0029] Step S400: Based on the biological monitoring data, multi-source fusion of the same-frequency data is performed, and combined with the tracking and evaluation module, infection location decision-making and evolution trend prediction are performed to determine the infection feature list. Information from different data sources (such as biosensors and auxiliary monitoring devices) is integrated to obtain a more comprehensive, accurate, and consistent dataset. This includes preprocessing the raw data, such as filtering, deduplication, and error correction, to eliminate noise, errors, and redundant information. Data of different formats and structures are converted into unified data to facilitate further integration and analysis. The cleaned and converted data are then integrated to obtain a comprehensive, consistent, and usable dataset. Specifically, the multi-source fused data is combined with the individual case analysis module in the tracking and evaluation module to accurately locate infected cases, including determining key information such as the source, time, and location of infection. In combination with the functions of the system analysis module, historical data and current fused data are used to construct a predictive model using machine learning to predict the evolution of infection events, which may include increases or decreases in the number of infected people, expansion or contraction of the infection area, and changes in the speed of transmission. Based on the analysis results of the fused data and the tracking and evaluation module, the main characteristics of the infection event are determined, such as the type of pathogen, route of infection, susceptible population, and symptoms. Single column representation refers to organizing and presenting the main characteristics of each infection event in a single column.

[0030] In one possible implementation, step S400 further includes step S410, identifying timestamps to determine co-frequency multi-source data and determining a master data structure, where the master data structure is any data structure within the biomonitoring data. In biomonitoring data, timestamps can be used to determine whether data from different sources was generated within the same time period, i.e., whether it is co-frequency data. Specifically, by examining timestamps, it is possible to determine which data originated from different sources within the same time period, such as from different sensors, monitoring devices, or data sources, but share the same timestamp, indicating that they were captured or generated within the same time period. A master data structure is any data structure within the biomonitoring data, used to describe, store, and analyze key data structures for biomonitoring information. It may include key data fields such as sensor readings, patient information, and disease indicators. Specific business needs for biomonitoring, such as disease monitoring, patient management, and treatment efficacy evaluation, are then identified. Available data sources are analyzed, and based on business needs and data source analysis, a master data structure is defined.

[0031] Step S400 also includes step S420, performing heterogeneous conversion on the same-frequency multi-source data based on the master data structure to determine homogeneous data. Heterogeneous conversion refers to converting data from different sources with different formats and structures into a unified, standard format and structure through appropriate data integration and conversion technologies to achieve data integration and sharing. Specifically, a master data structure is selected as the target structure for data conversion. The same-frequency multi-source data is initially cleaned to remove duplicate, erroneous, or irrelevant data. ETL (Extract, Transform, Load) tools, XML or JSON parsers, etc. are used to convert the same-frequency multi-source data into a format and structure compatible with the master data structure. The converted data is then standardized to ensure data consistency, comparability, and reusability. Homogeneous data refers to data that has the same format, structure, and semantics after conversion and standardization. The process also includes step S430, traversing the homogeneous data, fusing homogeneous data groups, and determining fused monitoring data. The process traverses the homogeneous data, fusing homogeneous data groups, and determining fused monitoring data. According to the unique data identifier determined during the traversal process, data from the same source (such as the same sensor, the same device or the same data source) are grouped. For each homologous data group, different data fusion methods, such as weighted averaging, can be used to fuse the data items in each homologous data group to generate fused data values ​​or data points, namely fused monitoring data.

[0032] In one possible implementation, step S400 further includes step S440, decomposing the fused monitoring data, combining the individual case analysis blocks, performing spatiotemporal analysis of the individual cases in sequence, and determining a first evaluation result, wherein the spatiotemporal analysis includes a space-based horizontal analysis and a time-based vertical analysis, and the first evaluation result includes a real-time evaluation result and an evolution prediction result. The fused monitoring data is classified and split according to different indicators, geographical areas, time periods, etc., and the spatiotemporal analysis of individual cases is performed in combination with the individual case analysis blocks. Specifically, in the spatial dimension, the data of individual cases in different geographical locations or regions are compared and analyzed, such as analyzing spatial distribution, spatial correlation, spatial differences, etc.; in the temporal dimension, the data of individual cases at different time points are analyzed to understand the changing trends and evolution laws of the data, such as performing time series analysis, trend prediction, periodic analysis, etc., and then determine the first evaluation results, including real-time evaluation results and evolution prediction results. Based on the current fused monitoring data and the results of spatiotemporal analysis, the individual cases are evaluated in real time. The real-time evaluation results may include current status, risk level, anomaly detection, etc.; the trend prediction method in spatiotemporal analysis is used to predict the future evolution of the individual cases. The evolution prediction results may include future status, potential risks, development trends, etc.

[0033] Step S400 also includes step S450, combining the system analysis block to perform a spatiotemporal analysis on the fused monitoring data to determine a second evaluation result. Specifically, within the selected system analysis block, a horizontal comparison and analysis of the spatial features in the fused monitoring data is performed, including geographic distribution patterns, spatial correlation analysis (such as clustering, hotspot detection), spatial difference comparison, etc.; a vertical analysis of the time series data in the fused monitoring data is performed, including time series trend analysis, periodicity analysis, anomaly detection, change point detection, etc., combining the spatial and temporal dimensions to analyze the spatiotemporal correlations and patterns in the fused monitoring data, and then determining the second evaluation result, including an evaluation of the real-time status within the system analysis block based on the results of the spatiotemporal analysis, and a prediction of the future trend of the system analysis block using the prediction model in the spatiotemporal analysis.

[0034] Step S400 also includes step S460, combining the first assessment result and the second assessment result, integrating and adding them into the infection feature column, wherein the infection feature column is updated synchronously with monitoring and tracking. The first assessment result and the second assessment result are combined to form a comprehensive assessment result, covering multiple aspects such as real-time status, development trends, and potential risks, and the combined assessment results are integrated into the infection feature column. For example, the real-time status assessment result can be added to the "current status" subfield, and the evolution prediction and trend prediction results can be added to the "future prediction" subfield; the monitoring and tracking system is a platform for real-time monitoring and tracking of infection situations, which may include data collection, data analysis, report generation and other functions. A synchronous update mechanism with the monitoring and tracking system is established to ensure that the data in the infection feature column is consistent with the monitoring and tracking system. When the monitoring and tracking system collects new infection data, the relevant records in the infection feature column are automatically updated to ensure that the data in the infection feature column is always kept up to date.

[0035] In one possible implementation, step S460 further includes step S461, mapping the first assessment result and the second assessment result, and determining a first advancement relationship by performing an infection impact analysis on individual cases. The first assessment result (real-time assessment result and evolution prediction result) is mapped to the second assessment result (the spatiotemporal analysis result based on the system analysis block), and an infection impact analysis is performed on the selected individual cases, including assessing the degree, scope, and duration of the impact of the infection event on individuals, groups, or systems. Based on the infection impact analysis results of the individual cases, a first advancement relationship is determined, which may describe the development trend of the infection event, the effectiveness of prevention and control measures, or key areas or groups requiring further attention. For example, the infection trajectory of a particular infection event may cause overall qualitative or quantitative changes.

[0036] Step S460 also includes step S462, which determines a second infection evolution chain based on the same biological population and in combination with the infection feature list. The same biological population refers to all individuals of the same species occupying a certain space within a certain period of time. Infection data related to a specific biological population is screened from the infection feature list, such as the infection status, infection time, infection location, pathogen type, etc. of individuals in the population. The screened data is arranged in chronological order to construct a timeline that shows the development process of the infection event in the biological population, including the occurrence, spread, and possible end of the infection. Based on the geographic location information in the infection data, a spatial distribution map of the infection event is drawn to show the distribution of the infection event in different regions, which helps to identify the central area and spread path of the infection. The pathogen type in the infection data is then analyzed to understand the infection status and spread patterns of different pathogens in the biological population. Finally, a second infection evolution chain is constructed, which describes in detail the development process of the infection event in the biological population, including the starting point of the infection, the spread path, the change of the pathogen, etc.

[0037] Step S460 also includes step S463, which is guided by cross-biological populations and combined with the infection feature list to determine the third infection evolution chain. Infection data involving multiple biological populations are screened from the infection feature list, including the infection situation, infection time, infection location, and the types of pathogens involved in different biological populations. The screened data are analyzed to identify the infection paths between different biological populations, that is, the ways and means of pathogens spreading from one biological population to another, such as direct transmission (such as contact transmission, food chain transmission), indirect transmission (such as vector transmission, environmental transmission), etc.; the evolution of pathogens in different biological populations is analyzed, including possible mutations and adaptive changes of pathogens during cross-population transmission; the results of the cross-population infection path and the cross-population evolution analysis of pathogens are combined to construct a third infection evolution chain, which describes in detail the transmission path, evolution trend, and possible impact of pathogens between different biological populations. It also includes step S464, which adds the first propulsion relationship, the second infection evolution chain, and the third infection evolution chain to the infection feature list.

[0038] Step S500, visualize and alarm the infection feature column on the display interface, and determine the prevention and control plan based on the infection feature column, wherein the column call has permission authentication. Visualizing and alarming the infection feature column on the display interface specifically refers to intuitively displaying the key information in the infection feature column (such as pathogen type, infection range, number of infected people, etc.) on the user interface in the form of graphics, charts, maps, etc. The visualization interface can quickly understand the infection situation and identify infection trends. When certain indicators in the infection feature column (such as a sudden increase in the number of infected people, a rapid expansion of the infection range, etc.) exceed the preset threshold, the system will automatically trigger the alarm mechanism, such as through sound, pop-up windows, emails, text messages, etc., to ensure that relevant personnel can quickly learn about it and take corresponding response measures; determining the prevention and control plan based on the infection feature column specifically refers to analyzing the pathogen type, transmission route, susceptible population, etc. of the infection event according to the information in the infection feature column to understand the characteristics of the infection event, and then Based on the analysis results of infection characteristics and combined with existing prevention and control resources and capabilities, specific prevention and control plans are formulated, such as isolation measures, treatment plans, vaccination plans, publicity and education content, etc. Among them, the existence of permission authentication for single-column calls means that when processing sensitive information such as biological infections, the permission authentication mechanism can prevent unauthorized personnel from accessing or modifying the data in the infection feature column. It usually includes user identity authentication and authorization. User identity authentication is used to confirm whether the user's identity is legal, such as logging in with a username and password. Authorization determines which data the user can access and modify based on the user's role and permission settings. For example, in the evaluation of biological infection data, different roles are set (such as data analysts, prevention and control experts, decision makers, etc.), and different permissions are assigned to each role to ensure the security and reliability of biological infection data.

[0039] In a possible implementation, step S500 further includes step S510, identifying the infection feature list, and determining the subjective trend elements of biological movement and infection evolution centered on the organism. Identify the key information contained in the infection signature column, including pathogen type, infection time, infection location, species and number of organisms involved, infection symptoms, and treatment progress. Then, analyze the species of organisms involved in the infection signature column to understand which organisms are more susceptible to infection and the infection relationships between them. For example, certain animals or insects may serve as hosts or transmission vectors for pathogens, playing an important role in the spread of infection. Observe changes in the number of organisms in the infection signature column and analyze the impact of infection events on the number of organisms. If an infection event causes a significant decrease in the number of organisms, it means that the pathogen is highly lethal. Conversely, if the number of organisms remains stable or increases, it means that the pathogen has less impact on the organisms or that the organisms have a certain degree of resistance. Identify the subjective trend factors of biological movement and infection evolution. Pathogen mutations may cause changes in their infectivity, transmission speed, or pathogenicity, which in turn affects the development trend of infection events. The stronger the adaptability of an organism, the greater its ability to resist infection, which may inhibit the development trend of infection events. For example, the migration of migratory birds may carry pathogens from one area to another, leading to the spread of infection events.

[0040] Step S500 further includes step S520, which determines key monitoring points based on the subjective trend factors. As infection monitoring progresses, it is configured and regulated with an organism-centric approach to avoid ineffective monitoring and improve demand alignment. Specifically, pathogen mutation monitoring is performed using high-throughput sequencing technology, bioinformatics analysis, and other methods. Genetic sequence data of pathogens is regularly collected and analyzed to monitor mutations. An appropriate monitoring frequency, such as weekly, monthly, or quarterly, is set based on the pathogen's mutation rate and infection trends. Organism adaptability assessments are conducted through questionnaires, serological testing, and vaccination records. Adaptability indicators, such as the organism's natural immunity level and vaccination rate, are regularly assessed. An appropriate assessment cycle, such as quarterly, semi-annually, or annually, is set based on the organism's life cycle and infection characteristics. The effectiveness of prevention and control measures is evaluated through on-site inspections, data collection, and analysis. The effectiveness of implemented prevention and control measures, such as the implementation of isolation measures and the coverage of vaccination programs, is regularly assessed. An appropriate assessment cycle, such as weekly, monthly, or quarterly, is set based on the characteristics of the prevention and control measures and infection trends.

[0041] Step S500 also includes step S530, which reversely adjusts the monitoring system based on the key monitoring points. After determining the key monitoring points of the monitoring system, the monitoring system is adjusted and optimized accordingly based on the data and changes of these monitoring points to ensure that the monitoring system can effectively capture important information and provide timely and accurate data support for the formulation and adjustment of prevention and control strategies. Specifically, reversely adjusting the monitoring system refers to adjusting the parameter settings of the monitoring system, such as monitoring frequency, data collection range, etc., based on the data and changes of the key monitoring points, to ensure that the monitoring system can more effectively capture important information, optimize the process of data processing and analysis, improve the speed and accuracy of data processing, strengthen the stability and security of the monitoring system, and ensure that the system can operate stably and protect the security of data.

[0042] In the above, refer to Figure 1 A method for monitoring and evaluating biological infection status according to an embodiment of the present invention is described in detail. Figure 2 A biological infection status monitoring and evaluation system according to an embodiment of the present invention is described.

[0043] According to an embodiment of the present invention, a biological infection status monitoring and evaluation system is designed to address the technical problem of existing biological infection status monitoring systems, which is the difficulty in accurately integrating different infection data in real time. This leads to an inability to accurately locate infection status and predict evolutionary trends, resulting in poor timeliness and accuracy of biological infection status monitoring and evaluation results. This system implements comprehensive, multi-level monitoring and evaluation of biological infection status, achieving the technical effect of improving the accuracy and timeliness of infection status monitoring and evaluation results. The biological infection status monitoring and evaluation system includes: a biological infection map construction module 10, a tracking and evaluation module construction module 20, a biological monitoring data return module 30, an infection feature single column determination module 40, and a prevention and control plan determination module 50.

[0044] A biological infection map construction module 10 is used to connect to a biological resource library based on a data interface, read biological infection data and perform data system conversion, perform coreference disambiguation, and construct a biological infection map. The biological infection map has distinguishing marks based on visual features and biological features; A tracking and evaluation module building module 20, wherein the tracking and evaluation module building module 20 builds a tracking and evaluation module based on the biological infection map, and the tracking and evaluation module includes an individual case analysis block and a system analysis block; A biological monitoring data return module 30 is used to cooperate with a regional monitoring device to monitor regional biological status, assist in network time protocol, and return biological monitoring data, wherein the regional monitoring device includes a biosensor and an auxiliary monitoring device; An infection feature single column determination module 40, which performs multi-source fusion of same-frequency data based on the biological monitoring data and combines it with the tracking and evaluation module to make infection location decisions and predict evolution trends to determine infection feature single columns; The prevention and control plan determination module 50 is used to visualize and warn the infection feature column on a display interface, and determine the prevention and control plan based on the infection feature column, wherein the column call has permission authentication.

[0045] The specific configuration of the biological infection map construction module 10 will be described in detail below. The biological infection map construction module 10 further includes: identifying the biological infection data, performing a primary clustering based on the infection source, performing a secondary clustering based on the biological species, and determining the clustering results; traversing the clustering results, mining and constructing an infection data system based on common criteria, wherein the infection data system includes an infection system layer and an evaluation system layer, and the infection data system corresponds one-to-one with the clustering results; traversing the infection data system to perform associations, and performing coreference disambiguation to generate the biological infection map.

[0046] The specific configuration of the biological infection map construction module 10 will be described in detail below. The biological infection map construction module 10 may further include: the visual features are intuitive representational features, and the biological features are molecular biological features; traversing the biological infection map, performing unary map tagging based on the visual features and binary map tagging based on the biological features; traversing the unary map tags and binary map tags, and associating mapped tag nodes based on feature homology.

[0047] The specific configuration of infection feature single column determination module 40 will be described in detail below. Infection feature single column determination module 40 may further include: identifying timestamps to determine co-frequency multi-source data and determining a master data structure, where the master data structure is any data structure in the biological monitoring data; performing heterogeneous conversion on the co-frequency multi-source data based on the master data structure to determine homogeneous data; and traversing the homogeneous data to fuse homogeneous data groups to determine fused monitoring data.

[0048] The specific configuration of the infection feature single column determination module 40 will be described in detail below. The infection feature single column determination module 40 further includes: decomposing the fused monitoring data, combining with the individual case analysis block, performing spatiotemporal analysis of the individual cases in sequence, and determining a first evaluation result, wherein the spatiotemporal analysis includes a spatial-based horizontal analysis and a time-based longitudinal analysis, and the first evaluation result includes a real-time evaluation result and an evolution prediction result; combining with the system analysis block, performing spatiotemporal analysis on the fused monitoring data to determine a second evaluation result; combining the first evaluation result and the second evaluation result, integrating and adding them into the infection feature single column, wherein the infection feature single column is updated synchronously with monitoring and tracking.

[0049] The specific configuration of the infection feature single column determination module 40 will be described in detail below. The infection feature single column determination module 40 further includes: mapping the first assessment result and the second assessment result, determining a first propulsion relationship by performing an infection impact analysis on individual cases; determining a second infection evolution chain based on the same biological population and in combination with the infection feature single column; determining a third infection evolution chain based on cross-biological populations and in combination with the infection feature single column; and adding the first propulsion relationship, the second infection evolution chain, and the third infection evolution chain to the infection feature single column.

[0050] The specific configuration of the prevention and control plan determination module 50 will be described in detail below. The prevention and control plan determination module 50 may further include: identifying the infection feature list, determining the subjective trend elements of biological movement and infection evolution centered on the organism; determining key monitoring points based on the subjective trend elements; and reversely adjusting the monitoring system based on the key monitoring points.

[0051] A biological infection status monitoring and evaluation system provided by an embodiment of the present invention can execute a biological infection status monitoring and evaluation method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0052] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0053] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.

Claims

1. A method for monitoring and evaluating biological infection conditions, characterized in that: The method comprises: Based on the data interface, the biological resource library is connected, the biological infection data is read and the data system is converted, and coreference disambiguation is performed to build a biological infection map. The biological infection map has distinguishing marks based on visual features and biological features; Based on the biological infection map, a tracking and evaluation module is built, wherein the tracking and evaluation module includes an individual case analysis block and a system analysis block; Cooperate with a regional monitoring device to monitor regional biological status, assist in network time protocol, and return biological monitoring data, wherein the regional monitoring device includes a biosensor and an auxiliary monitoring device; Based on the biological monitoring data, multi-source fusion of the same-frequency data is performed, and combined with the tracking and evaluation module, infection location decision-making and evolution trend prediction are carried out to determine the infection feature list; The infection feature column is visualized and warned on a display interface, and a prevention and control plan is determined based on the infection feature column, wherein the column call has permission authentication.

2. A method for monitoring and evaluating biological infection status according to claim 1, characterized in that: The construction of the biological infection map includes: Identifying the biological infection data, performing a primary clustering based on the infection source, performing a secondary clustering based on the biological species, and determining a clustering result; Traversing the clustering results, mining and constructing an infection data system based on common standards, wherein the infection data system includes an infection system layer and an evaluation system layer, and the infection data system corresponds one-to-one to the clustering results; The infection data system is traversed to perform association and coreference disambiguation to generate the biological infection graph.

3. A method for monitoring and evaluating biological infection status according to claim 2, characterized in that: The biological infection map has distinguishing marks based on visual features and biological characteristics, including: The visual features are intuitive representational features, and the biological features are molecular biological features; Traversing the biological infection map, performing unary tagging of the map based on the visual features and binary tagging of the map based on the biological features; The graph unary tags and the graph binary tags are traversed, and association of mapping tag nodes is performed based on feature homology.

4. A method for monitoring and evaluating biological infection status according to claim 1, characterized in that: The multi-source fusion of same-frequency data includes: Identifying timestamps to determine the same-frequency multi-source data and determining a master data structure, wherein the master data structure is any data structure in the biological monitoring data; Based on the main data structure, performing heterogeneous conversion on the same-frequency multi-source data to determine homogeneous data; The homogeneous data are traversed, homologous data groups are fused, and fused monitoring data are determined.

5. A method for monitoring and evaluating biological infection status according to claim 4, characterized in that: The infection characteristics are listed separately, including: Decomposing the fused monitoring data, combining it with the case analysis blocks, sequentially performing spatiotemporal analysis of each case, and determining a first evaluation result, wherein the spatiotemporal analysis includes a spatially based horizontal analysis and a time-based vertical analysis, and the first evaluation result includes a real-time evaluation result and an evolution prediction result; In combination with the system analysis block, performing spatiotemporal analysis on the fused monitoring data to determine a second evaluation result; The first assessment result and the second assessment result are combined and integrated into the infection feature list, wherein the infection feature list is updated synchronously with monitoring and tracking.

6. A method for monitoring and evaluating biological infection conditions according to claim 5, characterized in that: The integration and addition into the infection feature list includes: Mapping the first assessment result and the second assessment result, and determining a first advancement relationship by performing infection impact analysis on individual cases; Guided by the same biological population and combined with the infection characteristics, the second infection evolution chain is determined; Guided by cross-biological populations and combined with the infection characteristics listed above, the third infection evolution chain is determined; The first advancement relationship, the second infection evolution chain, and the third infection evolution chain are added to the infection feature single column.

7. A method for monitoring and evaluating biological infection status according to claim 1, characterized in that: The method further comprises: Identify the infection signature, centering on the organism, and determine the subjective trend elements of biological movement and infection evolution; Based on the subjective trend factors, determine key monitoring points; Based on the key monitoring points, the monitoring system is adjusted in reverse.

8. A biological infection status monitoring and evaluation system, characterized in that: The system is used to implement a biological infection status monitoring and evaluation method according to any one of claims 1 to 7, and the system comprises: A biological infection map construction module, which is used to connect to the biological resource library based on the data interface, read the biological infection data and perform data system conversion, perform coreference disambiguation to build a biological infection map, and the biological infection map has distinguishing marks based on visual features and biological features; A tracking and evaluation module building module, wherein the tracking and evaluation module building module is based on the biological infection map and builds a tracking and evaluation module, wherein the tracking and evaluation module includes an individual case analysis block and a system analysis block; A biological monitoring data return module, which is used to cooperate with a regional monitoring device to monitor regional biological status, assist in network time protocol, and return biological monitoring data, wherein the regional monitoring device includes a biosensor and an auxiliary monitoring device; An infection feature single column determination module, which performs multi-source fusion of same-frequency data based on the biological monitoring data and combines it with the tracking and evaluation module to make infection location decisions and predict evolution trends to determine the infection feature single column; The prevention and control plan determination module is used to visualize and warn the infection feature column on a display interface, and determine the prevention and control plan based on the infection feature column, wherein the column call has permission authentication.

Images