Digital biological sign information monitoring system and big data analysis method
By collecting and analyzing biological information in real time, combining abnormal and risk indicators, and optimizing the database structure, the problem of low accuracy in data extraction of biological information is solved, and more accurate data extraction and risk warning are achieved.
Patent Information
- Application Number
- CN202410958132.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, due to the real-time update and diversity of biological data, the accuracy of obtaining biological information data is reduced, and the accuracy of extracting key feature data in informationized databases is low.
Biosensors collect biological information in real time during preset time periods, perform digital processing and big data analysis, combine abnormality degree indicators and risk compliance index, extract and store key feature data, generate risk warning information, and optimize the information database structure and Access control.
It improves the accuracy and management accuracy of the extraction of key feature data in the information database, realizes the reliability of real-time monitoring and risk warning, and solves the problem of low data extraction accuracy.
Smart Images

Figure CN118919093A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital information monitoring, and in particular to a digital biological sign information monitoring system and a big data analysis method. Background Art
[0002] With the rapid advancement of science and technology, digital biological sign monitoring technology plays an increasingly important role in the health industry. Among them, body temperature is the main sign, which is one of the most important performance parameters in the biological monitoring process. For many diseases, especially infectious diseases, temperature changes are the most important monitoring factors. As an important part of digital biological monitoring technology, biosensors and health monitoring equipment can monitor various physiological parameters and biomarkers of organisms in real time and accurately. This technology has high sensitivity, high selectivity and real-time monitoring capabilities, and can provide comprehensive biological information. Big data analysis refers to the processing, analysis and mining of large amounts of diverse and high-speed generated data to discover hidden patterns, laws and relationships. In the field of biological information monitoring, big data analysis can deeply process these data and reveal the complex relationships and laws within the organism. However, traditional biological information monitoring methods mainly rely on biological sample analysis in the laboratory and regular physical examinations, which often have time delays, high costs and cannot achieve continuous monitoring. Therefore, digital biological sign information monitoring systems and big data analysis methods have emerged, making real-time monitoring, telemedicine and personalized medicine possible.
[0003] The existing digital biological sign information monitoring system collects and analyzes biological information data in real time to monitor the individual's physiological state and life behavior in real time. At the same time, it predicts the individual's health status and disease risk based on abnormal situations that occur during the real-time monitoring process, and provides corresponding preventive measures.
[0004] For example, the international trade information data digital supervision system and method based on big data, which is announced by the invention patent with announcement number: CN116151933B, includes: obtaining the trade data and operation mode of merchants selling different types of goods in the international trade database; based on the trade data, extracting the evaluation indicators corresponding to the goods, and establishing a grade classification of the evaluation indicator data of the commodity operation mode; analyzing and confirming the actual effective data of the corresponding evaluation indicators under the preset operation data and analyzing the digital evaluation results of the corresponding type of goods; and recommending and warning the operation mode of the analyzed type of goods according to the digital evaluation results.
[0005] For example, the patent application with publication number: CN117952483A discloses a method, system and medium for monitoring the balance of payments indicators based on a digital platform, including: obtaining the income and expenditure data and industry-related data of the enterprise, and converting them into a unified data format; fusing the obtained income and expenditure data with the industry-related data to form a complete data set; establishing a mathematical model of the income and expenditure indicators of the enterprise according to the income and expenditure indicator model; obtaining risk warnings, and predicting the optimized income and expenditure indicators and effects and displaying them visually.
[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:
[0007] In the prior art, due to the real-time update of biological data and the diversity of biological species during data monitoring, the accuracy of obtaining biological information data is reduced, and there is a problem of low accuracy in extracting key feature data in the information database. Summary of the invention
[0008] The embodiments of the present application solve the problem of low accuracy in extracting key feature data from information-based databases in the prior art by providing a digital biological sign information monitoring system and a big data analysis method, thereby improving the accuracy of extracting key feature data from information-based databases.
[0009] The embodiment of the present application provides a digital biological sign information monitoring big data analysis method, including the following steps: S1, according to the biosensor, real-time collection of biological information within a preset time period and digital processing to obtain biological information data; S2, the acquired biological information data is analyzed by big data and entered into an information database, and the biological information data in the information database is managed in an informationized manner; S3, according to the results of the informationized management, the changes in the biological information data are monitored in real time and key feature data are extracted in combination with an abnormality index, and the abnormality index is used to measure the abnormality of the biological information data in the informationized management process; S4, the extracted key feature data is subjected to risk detection to generate risk warning information and take corresponding solutions, and the risk detection is used to identify abnormal data in the key feature data according to the risk compliance index, and the risk compliance index is used to measure the compliance between the key feature data and the preset risk level.
[0010] Furthermore, the big data analysis of the acquired biological information data and the entry of the data into the information database also includes information database design, and the specific process of the information database design is: adding corresponding metadata tags to the biological information data and performing regional classification according to the attribute requirements of the biological information data; converting the biological information data after regional classification into a conceptual model and designing the information database structure according to the actual needs of the information database; standardizing the information database structure according to a preset data interaction format, and designing the corresponding information database interface according to the result of the standardization processing and designing the information database in combination with the database access coefficient, wherein the database access coefficient is the frequency limit degree of simultaneous access of the accessing users to the information database within a preset time period.
[0011] Furthermore, the database access coefficient is calculated by the following formula:
[0012]
[0013] Where n is the number of the access user, n = 1, 2, ..., N, N is the total number of access users, m is the number of the preset time period, m = 1, 2, ..., M, M is the total number of preset time periods, e is a natural constant, SHU n.m represents the database access coefficient of the nth access user in the mth preset time period, Y n.m represents the access frequency of the nth access user in the mth preset time period, Y0 represents the reference access frequency, ΔY represents the reference deviation of the access frequency, and H n.m represents the access frequency threshold of the nth access user in the mth preset time period, H0 represents the reference access frequency threshold, K n.m It indicates the access error rate of the nth access user in the mth preset time period.
[0014] Furthermore, the specific steps for obtaining the abnormality degree index are as follows: setting a corresponding first dimension index according to a preset allowable range of the biological information data and obtaining actual marker data of the biological body within a preset time period, and comparing the actual marker data with the first dimension index to obtain a first deviation; setting a corresponding second dimension index according to a preset temperature range within a preset environment and monitoring the actual temperature value of the biological body within a preset time period in real time, and comparing the actual temperature value with the second dimension index to obtain a second deviation; obtaining the abnormality degree index according to the temperature change rate of the actual temperature value during the real-time monitoring process and combining the obtained first deviation and second deviation.
[0015] Furthermore, the specific steps of obtaining the risk compliance index include: setting a risk level area according to the change trend of the biological information data within a preset time period and the historical information data in the preset database; real-time monitoring of the fluctuation changes in the key feature data extraction process to obtain the fluctuation level coefficient, and obtaining the data compliance coefficient according to the similarity between the key feature data and the abnormal data; combining the obtained fluctuation level coefficient and the data compliance coefficient to obtain the risk compliance index, and the risk compliance index is calculated by the following formula:
[0016]
[0017] Wherein, m is the number of the preset time period, m=1, 2, ..., M, M is the total number of preset time periods, a is the number of the low-risk area, a=1, 2, ..., A, A is the total number of low-risk areas, b is the number of the medium-risk area, b=1, 2, ..., B, B is the total number of medium-risk areas, d is the number of the high-risk area, d=1, 2, ..., D, D is the total number of high-risk areas, XIN m It represents the risk compliance index of the key feature data in the mth preset time period, e is a natural constant, F m represents the data conformity coefficient of the key feature data in the mth preset time period, F0 represents the data reference conformity coefficient, ΔF represents the data conformity coefficient reference deviation, represents the first fluctuation reference coefficient, Pa represents the first fluctuation coefficient of the a-th low-risk level area within the preset time period, represents the second fluctuation reference coefficient, Qb represents the second fluctuation coefficient of the b-th medium risk level area within the preset time period, represents the third fluctuation reference coefficient, U d Represents the third volatility coefficient of the dth high-risk level area within the preset time period.
[0018] The digital biological sign information monitoring system provided in the embodiment of the present application applies a digital biological information monitoring big data analysis method, including a sensor, a processor and a memory; wherein the sensor is used to collect biological information data within a preset time period in real time and input it into the processor according to a preset data transmission rule; the processor is used to perform big data analysis on the biological information data collected in real time and extract key feature data based on the changes of the biological information data in a preset area; the memory is used to store the extracted key feature data in an information database and perform risk detection to generate risk warning information.
[0019] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
[0020] 1. The biological information within a preset time period is collected in real time through biosensors and digitally processed to obtain biological information data, which is then entered into an information database for information management. Then, according to the results of information management, the changes in the biological information data are monitored in real time and key feature data are extracted in combination with abnormality indicators. Finally, risk detection is performed on the extracted key feature data to generate risk warning information, thereby improving the accuracy and reliability of information management, and further improving the accuracy of key feature data extraction in the information database, effectively solving the problem of low accuracy of key feature data extraction in the information database in the prior art.
[0021] 2. The biological information data is regionally classified according to the attribute requirements of the biological information data. At the same time, according to the actual needs of the information database, the biological information data after regional classification is converted into a conceptual model and the information database structure is designed. Then, the information database is designed in combination with the corresponding information database interface and database access coefficient, thereby achieving a more accurate design of the information database structure, and then achieving improved accuracy and reliability of the information database.
[0022] 3. By real-time monitoring of the changes in biological information data during the information management process and real-time recording of the access of users to the biological information data in the information database, the abnormal information data of the biological information data during the access process of the users is identified according to the preset abnormal dimensions to obtain the abnormality degree index, and finally the abnormal behavior data in the biological information data is removed and feature extraction is performed to obtain key feature data, thereby improving the accuracy of the abnormality degree index and achieving more accurate acquisition of key feature data. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 A flowchart of a digital biological sign information monitoring big data analysis method provided in an embodiment of the present application;
[0024] Figure 2 A three-dimensional analysis coordinate diagram of the database access coefficient provided in the embodiment of the present application;
[0025] Figure 3 A flowchart for extracting key feature data provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] The embodiment of the present application solves the problem of low accuracy in extracting key feature data from an information-based database in the prior art by providing a digital biological sign information monitoring system and a big data analysis method. The biological information within a preset time period is collected in real time by a biosensor and non-numerical information in the biological information is converted into numerical information to obtain biological information data. The acquired biological information data is then integrated with data sources and data formats, and simultaneously entered into an information-based database for real-time storage and recording of the access and operation process of the accessing user to the biological information data. The biological information data in the information-based database is then managed in an information-based manner and changes in the biological information data are monitored in real time. At the same time, key feature data is extracted in combination with an abnormality degree index. Finally, abnormal data in the key feature data is identified according to a risk compliance index and a biological risk type and biological risk level are generated, thereby improving the accuracy of extracting key feature data from an information-based database.
[0027] The technical solution in the embodiment of the present application is to solve the problem of low accuracy in extracting key feature data in the above-mentioned information database, and the overall idea is as follows:
[0028] By entering the acquired biological information data into the information database and conducting information management, then monitoring the changes in the biological information data in real time according to the results of the information management and extracting key feature data in combination with the abnormality degree indicators, and finally performing risk detection on the extracted key feature data to generate risk warning information, the effect of improving the accuracy of key feature data extraction in the information database is achieved.
[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0030] like Figure 1As shown, it is a flow chart of the digital biological sign information monitoring big data analysis method provided in the embodiment of the present application. The digital biological sign information monitoring big data analysis method provided in the embodiment of the present application includes the following steps: S1, according to the biosensor, real-time collection of biological information within a preset time period and digital processing to obtain biological information data, the biological information is used to describe the activity pattern and behavioral habits of the organism, the digital processing is used to convert the non-numerical information in the biological information into numerical information, the biological information data includes physiological parameter data and biological behavior data, the physiological parameter data is the numerical information of the changes in the physiological state of the organism, and the biological behavior data is the numerical information of the changes in the external behavior of the organism; S2, big data analysis is performed on the acquired biological information data and entered into the information database, and at the same time, the biological information data in the information database is managed in an informationized manner, and the big data analysis is used to source the biological information data. Integration and data format integration, the information database is used to store and record the access and operation process of the user to the biological information data in real time. The information management includes data backup, data recovery and data update; S3, according to the results of information management, the changes of the biological information data are monitored in real time and the key feature data are extracted in combination with the abnormality index. The abnormality index is used to measure the abnormality of the biological information data in the information management process. The key feature data includes the biological heart rate variability data and the biological blood pressure fluctuation data; S4, the extracted key feature data is subjected to risk detection to generate risk warning information and take corresponding solutions. The risk detection is used to identify the abnormal data in the key feature data according to the risk compliance index. The abnormal data includes the heart rate fluctuation data and the blood pressure fluctuation data. The risk compliance index is used to measure the compliance between the key feature data and the preset risk level. The risk warning information includes the biological risk type and the biological risk level.
[0031] In this embodiment, data source integration is usually used to remove duplicate, erroneous and inconsistent biological information data and convert them into the same unit for comparison and analysis, and then merge the biological information data from different data sources according to unified rules to form a complete data set; due to the diversity of data sources, there will be great differences in data formats. In order to conduct effective data analysis, it is necessary to convert non-numeric data (such as text, image) into numerical data. For large-scale biological information data, data compression is used to reduce the storage space and transmission time of the information database; heart rate variability data usually refers to the variability or fluctuation degree of the heart beat interval (i.e., the time between two consecutive heart beats), and this variability reflects the regulatory ability of the autonomic nervous system (especially the parasympathetic nervous system) to cardiac activity; biological blood pressure volatility data usually refers to the fluctuation degree of blood pressure (systolic and diastolic pressure) over a period of time, and this volatility is usually affected by multiple factors, such as emotions, activity levels and drug effects; by real-time monitoring and analysis of these key feature data, medical professionals can better understand the physiological state of the organism and take corresponding intervention measures, thereby improving the accuracy of key feature data extraction in the information database.
[0032] Furthermore, the organism information data includes physiological parameter data and biological behavior data. The specific process of obtaining the physiological parameter data is: obtaining the physiological parameter information according to the organism type corresponding to the organism information and the physiological parameter type within a preset time period, and filtering the obtained physiological parameter information to obtain the physiological parameter data. The physiological parameter information is used to describe the physiological state of the organism in a preset area within a preset time period, and the filtering process is used to remove noise data in the physiological parameter information; the specific process of obtaining the biological behavior data is: obtaining the biological behavior information and extracting the key behavior information according to the organism type corresponding to the organism information and the biological behavior type within the preset area, and combining the biocompatibility principle to obtain the biological behavior data. The biological behavior information is used to reflect the running trajectory and posture information of the organism in the preset area. The key behavior information includes behavior frequency information and duration information. The biocompatibility principle represents the principle of mutual adaptability between the key behavior information and the environment in which the organism is located.
[0033] In this embodiment, filtering processing is generally performed by converting non-numerical information in the physiological parameter information into numerical information and inputting it into a digital signal processor as an output to eliminate the interference of pulse noise and frequency division noise; the type of organism being monitored is determined by biological characteristics, and the type of biological behavior that may occur is defined based on the type of organism and the preset area. For example, for wild animals, it usually includes foraging, migration, reproduction, and rest. These behavior types can be defined based on existing ecological research, observation records, and expert opinions. GPS tracking is then used to collect the behavioral data of the organism and extract key information related to the defined behavior types, which usually includes the frequency, duration, location, and interaction with other organisms of the behavior; the principle of biocompatibility emphasizes the harmonious coexistence between an organism and its environment. When obtaining biological behavior data, it should be ensured that the monitoring method and equipment have no negative impact on the organism and its ecological environment, thereby improving the accuracy of obtaining information data of the organism.
[0034] Furthermore, before the acquired biological information data is analyzed for big data and entered into the information database, the information database design is also included. The specific process of the information database design is: according to the attribute requirements of the biological information data, corresponding metadata tags are added to the biological information data and regional classification is performed. The metadata tags include the collection time, collection location and data type. The data type includes genome data, transcriptome data and metabolome data. The regional classification means that the biological information data with metadata tags added is classified into a preset area according to the source and attribute of the biological information data; according to the actual needs of the information database, the biological information data after regional classification is converted into a conceptual model and the information database structure is designed. The conceptual model is used to visualize the entities, attributes and relationships in the biological information data. The information database structure is used to correspond the entities, attributes and relationships in the biological information data to the nodes in the preset physical storage structure; the information database structure is standardized according to the preset data interaction format, and the corresponding information database interface is designed according to the result of the standardization processing and the information database is designed in combination with the database access coefficient. The standardization processing includes data format conversion and data integration. The information database interface is used to realize data interaction between the access user and the biological information data. The database access coefficient is the frequency limit degree of the access user's simultaneous access to the information database within a preset time period.
[0035] In this embodiment, genomic data generally refers to the sequence information of all genes of an organism, and is generally used to study the structure, function and variation of genes. Transcriptome data describes the set of all RNAs transcribed in the cells of an organism under specific conditions. Metabolome data generally refers to the set of all small molecule metabolites in an organism, reflecting the metabolic state of the organism. Before performing regional classification, it is necessary to define classification regions, which are generally based on geographical locations (such as different ecological niches, habitats), classification of organisms (such as different species, subspecies), physiological states (such as health, disease), and experimental conditions (such as different treatment groups, time points). The actual needs of an information database generally refer to the query function, screening conditions and integrity of the data. In practical applications, a graphical tool (such as an ER diagram tool) is generally used to draw a conceptual model diagram, in which each entity is represented by a rectangle, an attribute is represented by an ellipse, and a relationship is represented by a diamond. Entities, attributes and relationships are connected by lines to show the association between them. Once the conceptual model is verified and recognized, it can be converted into a logical model to represent a more specific database design (including table structure and field type). Usually, in the preset physical storage structure, each data table corresponds to a node, and each data in the data table corresponds to a field type. A unified naming convention is established for the access objects of the information database to ensure that the data types used in the information database are compatible with the preset data interaction format, and database constraints are used to design an information database interface with interactive functions. The database constraints include primary key constraints, interface constraints and check constraints to ensure the maintainability of the information database and improve the stability and reliability of the information database.
[0036] Furthermore, the specific steps for obtaining the database access coefficient include: recording the access log of the access user to the information database in real time and counting the number of visits of the access user within a preset time period, and obtaining the access frequency in combination with the unit time of the preset time period, the access log includes the access time, the access user ID and the access data type, and the access frequency is used to measure the frequency of the access user's simultaneous access to the information database within the preset time period; obtaining the access frequency threshold according to the historical access data in the preset database, and recording the error log of the access user during the access process in real time and performing secondary statistics on the number of access errors of the access user within the preset time period, the access frequency threshold represents the access range allowed by the normal access mode and behavioral habits of the access user to the information database, and the error log includes the number of access failures and the number of data anomalies; obtaining the access error rate according to the number of access errors obtained by the secondary statistics and the total number of visits of the corresponding access user within the preset time period, and obtaining the database access coefficient in combination with the obtained access frequency and the access frequency threshold, and the access error rate is used to measure the degree of abnormality occurring during the access user's access to the information database within the preset time period.
[0037] In this embodiment, the access frequency represents the ratio of the number of visits of the visiting user to the unit time length; the historical access data is retrieved from the preset database, and the data should include the access frequency of each user (i.e., the number of visits per unit time) and the corresponding timestamp. Generally, the data in recent years are relatively more valuable for reference. For example, a higher weight is assigned to the data in recent years (within 5 years), while a lower weight is assigned to the data in the distant past (five years ago). If some users are more active than other users and the access behaviors of these users are more representative, then these users can be assigned a higher weight. The average weight is obtained by summing and averaging these weights. And multiply it by the access frequency of the accessing user to obtain the access frequency threshold; the access error rate represents the ratio of the number of access errors of the accessing user within a preset time period to the total number of accesses; in practical applications, the accessing users are divided into different groups according to their actual access needs, and then the access coefficient of the accessing users within the preset time period is obtained according to the access behavior of each group within the preset time period. For example, if an accessing user frequently makes errors when accessing the database, and these errors are relatively serious, then it is generally believed that the user's access efficiency to the database is low, and a lower access coefficient (i.e., database access coefficient) is given, thereby achieving more accurate acquisition of the database access coefficient.
[0038] Furthermore, the database access coefficient is calculated by the following formula:
[0039]
[0040] Where n is the number of the access user, n = 1, 2, ..., N, N is the total number of access users, m is the number of the preset time period, m = 1, 2, ..., M, M is the total number of preset time periods, e is a natural constant, SHU n.m represents the database access coefficient of the nth access user in the mth preset time period, Y n.m represents the access frequency of the nth access user in the mth preset time period, Y0 represents the reference access frequency, ΔY represents the reference deviation of the access frequency, and H n.m represents the access frequency threshold of the nth access user in the mth preset time period, H0 represents the reference access frequency threshold, K n.m It indicates the access error rate of the nth access user in the mth preset time period.
[0041] In this embodiment, in order to simplify the analysis, we define Among them, Y1n .m H1n represents the access frequency index of the nth access user in the mth preset time period. .mrepresents the access error rate index of the nth access user in the mth preset time period. The reference access frequency is usually obtained by averaging the access frequencies. The access frequency reference deviation usually represents the difference between the historical access data in the preset database and the reference access frequency after summing and averaging. The reference access frequency threshold is usually obtained by summing and averaging the median, maximum value and minimum value in the access frequency reference deviation. When K n.m <1, such as Figure 2 As shown in FIG. 1 , a three-dimensional analysis coordinate diagram of the database access coefficient provided in the embodiment of the present application is shown. When the access frequency index acts alone, the growth of the database access coefficient is small. When the access frequency index and the access error rate index act simultaneously, the database access coefficient increases rapidly in a straight line of y=x. It should be noted that the access frequency refers to the ratio of the number of visits of the visiting users within the preset access time period to the total number of visits. There is no zero situation. When and At this time, the information database has the least restriction on the visiting users who access the information database at the same time within the preset time period, indicating that the visiting users can access the key feature data with higher levels in the information database, thereby improving the accuracy of the database access coefficient, and then improving the accuracy of the key feature data extraction in the information database, effectively solving the problem of low accuracy of key feature data extraction in the information database in the prior art.
[0042] Further, such as Figure 3 As shown, it is a flowchart for extracting key feature data provided by an embodiment of the present application. The specific steps for extracting key feature data are: real-time monitoring of changes in biological information data during the information management process and real-time recording of access to biological information data in the information database by accessing users; identifying abnormal information data of biological information data during the access process of accessing users according to preset abnormal dimensions to obtain abnormality degree indicators, and the abnormal information data includes abnormal biological markers and abnormal biological temperature; removing abnormal behavior data in the biological information data and performing feature extraction processing to obtain key feature data, and the feature extraction processing includes feature conversion, feature dimensionality reduction and feature encoding.
[0043] In this embodiment, in the information database, it is necessary to implement the tracking and recording function of user access behavior. Whenever a user accesses the biological information data, the access time, access user and access content should be automatically recorded. By analyzing the access behavior, the focus and needs of the accessing user on the biological information data can be understood, providing a basis for subsequent data management and optimization; in practical applications, it is necessary to determine which biological markers and temperatures are considered abnormal within a preset time period, and record them as preset abnormal dimensions. For example, the concentration of certain biological markers may be considered abnormal when it exceeds the normal level by a certain percentage, or the biological temperature is considered abnormal when it exceeds the normal body temperature range; feature conversion usually converts continuous features in key feature data into discrete features, improving the interpretability and generalization ability of key feature data; feature dimensionality reduction usually converts high-dimensional features in key feature data into low-dimensional features, which helps to reduce the risk of overfitting; feature encoding usually converts discrete features and numerical features in key feature data into binary vectors, which helps the information database to automatically identify key feature data efficiently; and more accurate advance of key feature data is achieved.
[0044] Furthermore, the specific steps for obtaining the abnormality index are as follows: setting a corresponding first dimension index according to a preset allowable range of the biological information data and obtaining actual marker data of the biological body within a preset time period, and comparing the actual marker data with the first dimension index to obtain a first deviation, the first dimension index includes the concentration of the biological marker and the activity of the biological marker, the actual marker data includes marker concentration data and marker activity data, and the first deviation is used to measure the deviation between the actual marker data and the first dimension index within the preset time period; setting a corresponding second dimension index according to a preset temperature range within a preset environment and monitoring the actual temperature value of the biological body within the preset time period in real time, and comparing the actual temperature value with the second dimension index to obtain a second deviation, the preset temperature range includes an allowable low temperature deviation range and an allowable high temperature deviation range, the second dimension index includes a low temperature abnormality dimension and a high temperature abnormality dimension, and the second deviation is used to measure the deviation between the actual temperature value and the second dimension index within the preset time period; obtaining the abnormality index according to the temperature change rate of the actual temperature value during the real-time monitoring process and in combination with the obtained first deviation and second deviation, and the temperature change rate is used to reflect the change trend of the biological body temperature within the preset time period.
[0045] In this embodiment, the normal or expected range of the concentration and activity of the biological marker is determined according to the preset allowable range of the biological information data. These ranges can be used as the first dimension indicators, namely the target concentration range and the target activity range. The actual marker concentration data and activity data are collected from the biological sample within the preset time period. For each marker, its actual concentration data and actual activity data are compared with the corresponding target concentration range and target activity range, and the first deviation degree is obtained by the difference between the actual value and the target range; according to the preset temperature range in the preset environment, the allowable low temperature deviation range and the allowable high temperature deviation range are determined. These two ranges can be used as the low temperature abnormality dimension and the high temperature abnormality dimension in the second dimension indicator, respectively, using a temperature sensor or other The temperature monitoring device monitors the temperature value of the environment where the organism is located in real time within a preset time period, and compares the actual temperature value monitored in real time with the low temperature anomaly dimension and the high temperature anomaly dimension. If the actual temperature value is lower than the lower limit of the low temperature anomaly dimension or higher than the upper limit of the high temperature anomaly dimension, it is considered that there is a temperature anomaly. For the low temperature anomaly, the second deviation can be obtained by the difference between the actual temperature value and the lower limit of the low temperature anomaly dimension. For the high temperature anomaly, the second deviation can be obtained by the difference between the actual temperature value and the upper limit of the high temperature anomaly dimension. The abnormality degree index is usually a value or level, which is used to quantify the abnormality degree of the temperature state of the organism. In practical applications, the abnormality degree index is obtained by inputting the acquired temperature change rate, the first deviation and the second deviation into Python.
[0046] Specifically, the abnormality index is calculated by the following formula:
[0047]
[0048] Where m = 1, 2, ..., M, M is the total number of preset time periods, e is a natural constant, YI m It represents the abnormality index of the organism in the mth preset time period, T m represents the first deviation of the actual marker data in the mth preset time period, T0 represents the first reference deviation, L m represents the second deviation of the organism in the mth preset time period, L0 represents the second reference deviation, V m It represents the temperature change rate of the organism in the mth preset time period, and V0 represents the temperature reference change rate.
[0049] Specifically, to simplify the analysis, define Among them, T1 m Indicates the first deviation coefficient of the organism in the mth preset time period, L1 m Indicates the second deviation coefficient of the organism in the mth preset time period, V1 mIt represents the temperature change rate coefficient of the organism in the mth preset time period. The statistical table of the abnormal degree index change is shown in Table 1:
[0050] Table 1 Statistics of changes in abnormality indexes
[0051]
[0052] It should be understood that, in actual applications, the first reference deviation is usually obtained by comparing the deviation between the real-time monitoring value of a physiological parameter of the organism (such as heart rate, blood pressure) and the normal physiological parameter range in the preset database. If the real-time monitoring value exceeds the preset normal range, a deviation value will be generated, and the size of this value reflects the degree of deviation from the normal state; the second reference deviation is usually obtained by comparing the deviation between the real-time monitored temperature value of the organism and the preset temperature range (the allowable low temperature deviation range and the allowable high temperature deviation range); the temperature reference change rate is usually obtained by dividing the temperature change (difference) between two adjacent time points by the time interval. A higher temperature change rate may mean that the temperature of the organism is rising or falling rapidly; when ( and and ), there is no abnormality in the biological information data during the information management process, which enables more accurate acquisition of abnormality indicators, thereby improving the accuracy of key feature data extraction in the information database, effectively solving the problem of low accuracy of key feature data extraction in the information database in the prior art.
[0053] Furthermore, before generating risk warning information, it also includes risk warning for the extracted key feature data. The specific process of risk warning is: collect organism data according to risk assessment objectives and risk assessment application scenarios. Risk assessment indicators include genetic risk assessment and ecological risk assessment. Organism data includes biological characteristic data and ecological environment data of organisms. Biological characteristic data is used to describe the genetic characteristics, physiological state and behavior patterns of organisms, and ecological environment data is used to describe the adaptability of organisms to risk assessment application scenarios; compare organism data with key feature data to identify abnormal data that matches the risk assessment objectives, and at the same time, conduct risk warning for key feature data in combination with the abnormal data. Risk warning is used to evaluate the correlation between abnormal data and risk assessment objectives within a preset time period and to warn of genetic risks and ecological risks of organisms based on the risk compliance index.
[0054] In this embodiment, genetic risk assessment is generally used to evaluate the stability and variation of the genetic material of an organism and its potential impact on the adaptability, viability and genetic diversity of the organism. Ecological risk assessment is generally used to evaluate the position of an organism in an ecosystem, its interaction with other species, its adaptability to the environment and its potential ecological impact. The application scenarios of risk assessment are determined according to specific research or management needs, such as agriculture, forestry, biodiversity conservation, and ecological restoration. The organism data and key feature data are compared by using regression analysis in statistical methods. At the same time, the normal range of key feature data is set according to the operation of historical data. Abnormal data that exceeds the normal range or threshold is identified through comparison. These abnormal data generally indicate an increase in genetic risk or ecological risk. Targeted risk warning strategies are formulated, which generally include sending alarms to relevant institutions or personnel, taking emergency measures to mitigate risks, and adjusting monitoring frequencies, thereby improving the real-time nature of risk warnings.
[0055] Furthermore, the specific steps for obtaining the risk compliance index include: setting a risk level area according to the change trend of the biological information data within a preset time period and the historical information data in the preset database, the risk level area includes a low risk level area, a medium risk level area and a high risk level area; real-time monitoring of the fluctuation changes in the key feature data extraction process to obtain the fluctuation level coefficient, and at the same time obtaining the data compliance coefficient according to the similarity between the key feature data and the abnormal data, the fluctuation level coefficient includes a first fluctuation coefficient, a second fluctuation coefficient and a third fluctuation coefficient, the first fluctuation coefficient is used to measure the fluctuation changes in the key feature data extraction process and the degree of compliance with the preset low risk level in the low risk level area, the second fluctuation coefficient is used to measure the fluctuation changes in the key feature data extraction process and the degree of compliance with the preset medium risk level in the medium risk level area, the third fluctuation coefficient is used to measure the fluctuation changes in the key feature data extraction process and the degree of compliance with the preset high risk level in the high risk level area, and the data compliance coefficient is used to measure the degree of compliance between the key feature data and the abnormal data in the risk level area; combining the obtained fluctuation level coefficient and the data compliance coefficient to obtain the risk compliance index, and the risk compliance index is calculated by the following formula:
[0056]
[0057] Wherein, m is the number of the preset time period, m = 1, 2, ..., M, M is the total number of preset time periods, a is the number of the low-risk area, a = 1, 2, ..., A, A is the total number of low-risk areas, b is the number of the medium-risk area, b = 1, 2, ..., B, B is the total number of medium-risk areas, d is the number of the high-risk area, d = 1, 2, ..., D, D is the total number of high-risk areas, XINm It represents the risk compliance index of the key feature data in the mth preset time period, e is a natural constant, F m represents the data conformity coefficient of the key feature data in the mth preset time period, F0 represents the data reference conformity coefficient, ΔF represents the data conformity coefficient reference deviation, represents the first fluctuation reference coefficient, P a It represents the first volatility coefficient of the a-th low-risk level area within the preset time period. represents the second fluctuation reference coefficient, Q b It represents the second volatility coefficient of the b-th medium risk level area within the preset time period. represents the third fluctuation reference coefficient, U d Represents the third volatility coefficient of the dth high-risk level area within the preset time period.
[0058] In this embodiment, thresholds of different risk level areas are set according to the average value, standard deviation and historical extreme value of historical information data in a preset database. When the key feature data changes stably (that is, the data points on the coordinate axis are a straight line) and do not exceed the preset low risk threshold, it is a low risk level area; when the key feature data changes begin to fluctuate (that is, the data points on the coordinate axis begin to fluctuate outside the straight line), exceeding the low risk threshold but not exceeding the preset high risk threshold, it is a medium risk level area; when the key feature data change amplitude increases (that is, the data points on the coordinate axis are a curve with a large slope) and exceeds the preset high risk threshold, it is a high risk level area; in actual applications, the first fluctuation coefficient is also a short-term fluctuation, which is usually based on the change rate of the key feature data within a short time window (such as a few minutes or hours) to reflect the immediate fluctuation of the data. It is suitable for scenarios that require rapid response; the second volatility coefficient is also a medium-term volatility, which is usually based on trend analysis of key feature data over a longer time window (such as a day or a week) to evaluate the long-term stability and trend changes of the data; the third volatility coefficient is also a long-term volatility, which is usually based on statistical analysis of data over a longer time span (such as a month or a year); the key feature data and abnormal data in the information database are converted into vector form, and the similarity between the key feature data and the abnormal data is evaluated by the cosine value of the angle between the two vectors. If the angle is 0 degrees, the cosine value is 1, indicating complete similarity; if the angle is 90 degrees, the cosine value is 0, indicating dissimilarity; if the angle is 180 degrees, the cosine value is -1, indicating complete opposite. Because it is necessary to measure the similarity between the data, the cosine similarity is mapped to between 0 and 1 as the data conformity coefficient.
[0059] Specifically, the data reference conformity coefficient is usually obtained by the similarity between the historical reference data and the key feature data in the preset database (i.e., the ratio of the historical reference data to the key feature data), the data conformity coefficient reference deviation is usually obtained by the difference between the data reference conformity coefficient and the standard deviation of the historical reference data, the first fluctuation reference coefficient is usually obtained by the amount of change of the key feature data during the short-term fluctuation (daily fluctuation, hourly fluctuation) (i.e., the ratio of the difference between the changed key feature data and the total data volume to the short-term fluctuation time), the second fluctuation reference coefficient is usually obtained by the amount of change of the key feature data during the medium-term fluctuation (weekly fluctuation, monthly fluctuation) (i.e., the ratio of the difference between the changed key feature data and the total data volume to the medium-term fluctuation time), and the third fluctuation reference coefficient is usually obtained by the amount of change of the key feature data during the long-term fluctuation (seasonal fluctuation, annual fluctuation) (i.e., the ratio of the difference between the changed key feature data and the total data volume to the long-term fluctuation time); it should be understood that when and When the risk compliance index is equal to 2, the degree of compliance between the key feature data and the preset risk level is the highest, which improves the accuracy and reliability of the risk compliance index, and further improves the accuracy of key feature data extraction in the information database, effectively solving the problem of low accuracy of key feature data extraction in the information database in the prior art.
[0060] The digital biological sign information monitoring system provided in the embodiment of the present application applies a digital biological information monitoring big data analysis method, including a sensor, a processor and a memory; wherein the sensor is used to collect biological information data within a preset time period in real time and input it into the processor according to a preset data transmission rule; the processor is used to perform big data analysis on the biological information data collected in real time and extract key feature data according to the changes of the biological information data in a preset area; the memory is used to store the extracted key feature data in an information database and perform risk detection to generate risk warning information.
[0061] In this embodiment, the sensor inputs the collected biological information data into the processor according to preset data transmission rules (such as frequency, protocol, etc.). These rules ensure the real-time and accuracy of the data. After receiving the biological information data transmitted by the sensor, the processor will perform big data analysis, which includes data cleaning, preprocessing, statistical analysis and pattern recognition, and then store the key feature data extracted by the processor in the information database through the memory. The information database can efficiently manage, query and update these data to support subsequent data analysis and application. In addition, the risk detection module in the memory will further analyze the stored key feature data to detect possible risks. Once a risk is detected, the memory will generate corresponding risk warning information. These warning information can be notified to relevant personnel in a variety of ways (such as text messages, emails, interface prompts) so that they can take timely measures to deal with the risks, thereby improving the efficiency and accuracy of risk warning information generation.
[0062] To summarize, the embodiment of the present application uses a biosensor to collect biological information within a preset time period in real time and performs digital processing to obtain biological information data, which is then entered into an information database and managed in an information manner. Then, based on the results of the information management, the changes in the biological information data are monitored in real time and key feature data are extracted in combination with abnormality indicators. Finally, risk detection is performed on the extracted key feature data to generate risk warning information, thereby achieving improved accuracy and reliability of information management, and further achieving improved accuracy in extracting key feature data in the information database, effectively solving the problem of low accuracy in extracting key feature data in the information database in the prior art.
[0063] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0064] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0067] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0068] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A digital biological sign information monitoring big data analysis method, characterized in that: The following steps are involved: S1, collecting biological information within a preset time period in real time according to the biosensor and performing digital processing to obtain biological information data; S2, perform big data analysis on the acquired biological information data and enter it into the information database, and perform information management on the biological information data in the information database; S3, monitoring the changes of the biological information data in real time according to the results of the information management and extracting key feature data in combination with an abnormality index, wherein the abnormality index is used to measure the abnormality of the biological information data during the information management process; S4, perform risk detection on the extracted key feature data to generate risk warning information and take corresponding solutions. The risk detection is used to identify abnormal data in the key feature data based on the risk compliance index. The risk compliance index is used to measure the degree of compliance between the key feature data and the preset risk level.
2. The method for analyzing big data of digital biological sign information monitoring according to claim 1, characterized in that: The biological information data includes physiological parameter data and biological behavior data. The specific process of obtaining the physiological parameter data is as follows: Acquire physiological parameter information according to the type of organism corresponding to the organism information and the type of physiological parameter within a preset time period, and filter the acquired physiological parameter information to obtain physiological parameter data; The specific process of obtaining the biological behavior data is as follows: The biological behavior information is obtained and key behavior information is extracted according to the biological species corresponding to the biological information and the biological behavior type in the preset area, and the biological behavior data is obtained in combination with the biocompatibility principle.
3. The method for analyzing big data of digital biological sign information monitoring according to claim 1, characterized in that: The process of performing big data analysis on the acquired biological information data and entering the data into the information database also includes information database design. The specific process of information database design is as follows: According to the attribute requirements of the biological information data, corresponding metadata tags are added to the biological information data and regional classification is performed; According to the actual needs of the information database, the biological information data after regional classification is converted into a conceptual model and the information database structure is designed; The information database structure is standardized according to a preset data interaction format. At the same time, the corresponding information database interface is designed according to the result of the standardization processing, and the information database is designed in combination with the database access coefficient. The database access coefficient is the frequency limit degree of simultaneous access of the accessing users to the information database within a preset time period.
4. The digital biological sign information monitoring big data analysis method according to claim 3, characterized in that: The specific steps of obtaining the database access coefficient include: Record the access logs of users to the information database in real time and count the number of visits by users within a preset time period, and obtain the access frequency based on the unit duration of the preset time period; Obtain access frequency thresholds based on historical access data in a preset database, record error logs of access users in real time, and perform secondary statistics on the number of access errors of access users within a preset time period; The access error rate is obtained based on the number of access errors obtained by secondary statistics and the total number of accesses of the corresponding access users within a preset time period, and the database access coefficient is obtained by combining the obtained access frequency and the access frequency threshold.
5. The digital biological sign information monitoring big data analysis method according to claim 4, characterized in that: The database access coefficient is calculated by the following formula: Where n is the number of the access user, n = 1, 2, ..., N, N is the total number of access users, m is the number of the preset time period, m = 1, 2, ..., M, M is the total number of preset time periods, e is a natural constant, SHU n.m represents the database access coefficient of the nth access user in the mth preset time period, Y n.m represents the access frequency of the nth access user in the mth preset time period, Y0 represents the reference access frequency, ΔY represents the reference deviation of the access frequency, and H n.m represents the access frequency threshold of the nth access user in the mth preset time period, H0 represents the reference access frequency threshold, K n.m It indicates the access error rate of the nth access user in the mth preset time period.
6. The digital biological sign information monitoring big data analysis method according to claim 1, characterized in that: The specific steps of extracting the key feature data are: Real-time monitoring of changes in biological information data during the information management process and real-time recording of users' access to biological information data in the information database; Identify abnormal information data of the biological information data during the access process of the access user according to the preset abnormal dimension to obtain an abnormal degree indicator; Abnormal behavior data in biological information data is removed and feature extraction processing is performed to obtain key feature data.
7. The digital biological sign information monitoring big data analysis method according to claim 1, characterized in that: The specific steps for obtaining the abnormality index are as follows: According to the preset allowable range of the biological information data, a corresponding first dimension indicator is set and actual marker data of the biological body within a preset time period is obtained, and at the same time, the actual marker data is compared with the first dimension indicator to obtain a first deviation; According to a preset temperature range in a preset environment, a corresponding second dimension indicator is set and the actual temperature value of the organism within a preset time period is monitored in real time, and the actual temperature value is compared with the second dimension indicator to obtain a second deviation; The abnormality index is obtained according to the temperature change rate of the actual temperature value in the real-time monitoring process and in combination with the obtained first deviation and second deviation.
8. The method for analyzing big data of digital biological sign information monitoring according to claim 1, characterized in that: Before generating risk warning information, the process also includes performing risk warning on the extracted key feature data. The specific process of risk warning is as follows: Collect organism data based on risk assessment objectives and risk assessment application scenarios; The biological data is compared with the key feature data to identify abnormal data that matches the risk assessment target, and the key feature data is combined with the abnormal data to issue risk warnings.
9. The digital biological sign information monitoring big data analysis method according to claim 1, characterized in that: The specific steps for obtaining the risk compliance index include: Setting risk level areas based on the changing trend of biological information data within a preset time period and historical information data in a preset database; Real-time monitoring of fluctuations in the key feature data extraction process to obtain the fluctuation level coefficient, and at the same time, obtain the data conformity coefficient based on the similarity between the key feature data and the abnormal data; The risk compliance index is obtained by combining the obtained volatility level coefficient and the data compliance coefficient. The risk compliance index is calculated by the following formula: Wherein, m is the number of the preset time period, m = 1, 2, ..., M, M is the total number of preset time periods, a is the number of the low-risk area, a = 1, 2, ..., A, A is the total number of low-risk areas, b is the number of the medium-risk area, b = 1, 2, ..., B, B is the total number of medium-risk areas, d is the number of the high-risk area, d = 1, 2, ..., D, D is the total number of high-risk areas, XIN m It represents the risk compliance index of the key feature data in the mth preset time period, e is a natural constant, F m represents the data conformity coefficient of the key feature data in the mth preset time period, F0 represents the data reference conformity coefficient, ΔF represents the data conformity coefficient reference deviation, represents the first fluctuation reference coefficient, P a It represents the first volatility coefficient of the a-th low-risk level area within the preset time period. represents the second fluctuation reference coefficient, Q b It represents the second volatility coefficient of the b-th medium risk level area within the preset time period. Indicates the third fluctuation reference coefficient, U d Represents the third volatility coefficient of the dth high-risk level area within the preset time period.
10. A digital biological sign information monitoring system, using the digital biological sign information monitoring big data analysis method according to any one of claims 1 to 9, characterized in that: Includes sensors, processors and memory; Wherein, the sensor is used to collect biological information data within a preset time period in real time and input it into the processor according to a preset data transmission rule; The processor is used to perform big data analysis on the biological information data collected in real time and extract key feature data according to the changes of the biological information data in a preset area; The memory is used to store the extracted key feature data in an information database and perform risk detection to generate risk warning information.
Citation Information
Cited By
Campus intelligent consumption analysis system and method based on multi-dimensional data fusion
CN121304226A
