Panda health monitoring method and system based on model, electronic equipment and medium

Abstract

The invention relates to the field of animal health monitoring, and discloses a panda health monitoring method and system based on a model, electronic equipment and a medium. The method comprises the following steps: acquiring sample data related to pandas; preprocessing the sample data to obtain preprocessed sample data; performing feature extraction on the preprocessed sample data to obtain key features; performing feature optimization on the key features to obtain key optimization features; determining a health risk result based on the key optimization features and a risk assessment model; and determining the health state of the panda based on the health risk result. The panda health is continuously monitored in combination with biomarkers and environmental parameters, and the change of health conditions of individuals or populations, potential disease risks and the like can be found in time. Besides, in the processing process, the data dimension is reduced, key features are enhanced, the model can be prevented from being interfered by noise, the efficiency and accuracy of data processing are improved, and the real-time performance, accuracy and comprehensiveness of health monitoring are enhanced.

Description

Technical Field

[0001] The present application relates to the field of animal health monitoring, and in particular to a model-based giant panda health monitoring method, system, electronic device and medium. Background Art

[0002] At present, the methods for monitoring (or detecting) the health of wild animals (e.g., giant pandas) mainly include traditional methods such as direct observation, physical examination and sample analysis. However, traditional monitoring methods often rely on limited sample sizes, resulting in the data obtained may not fully represent the health status of the entire giant panda population. Because giant pandas live in a wide range of habitats, it is relatively difficult to obtain representative samples, which limits the accuracy of health assessments. First, traditional analysis methods mostly use qualitative analysis or simple statistical analysis, which makes it difficult to deeply explore the complex relationships behind the data. For example, judging food residues and health indicators in giant panda feces by naked eyes often cannot accurately reflect the actual health status of giant pandas. Second, traditional monitoring methods usually require time for on-site confirmation, sampling and analysis, resulting in an inability to quickly respond to potential health problems, and timely detection and prevention are crucial to giant panda health problems.

[0003] In view of this, the applicant proposes the present invention to solve the related technical problems. Summary of the invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments disclosed in the present invention provide a model-based giant panda health monitoring method, system, electronic device and computer-readable storage medium, which combines biomarkers (biomarkers of feces, etc.) and environmental parameters (temperature, humidity, etc.) to monitor the health of giant pandas. Through continuous monitoring of giant pandas, changes in the health status of individuals or populations can be discovered in a timely manner, and potential diseases and nutritional problems can be identified. The model-based giant panda health monitoring method of the present application reduces the data dimension, and enhancing key features can avoid the model from being interfered by noise data, improve the efficiency and accuracy of data processing, and thus enhance the real-time, accuracy and comprehensiveness of health monitoring.

[0005] In a first aspect, an embodiment disclosed in the present invention provides a model-based giant panda health monitoring method, the method comprising: Acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters; Preprocessing the sample data to obtain preprocessed sample data; Performing feature extraction on the preprocessed sample data to obtain key features; Performing feature optimization on the key features to obtain key optimized features; determining health risk outcomes based on the key optimization features and the risk assessment model; Based on the health risk results, the health status of the giant panda is determined.

[0006] In a second aspect, the embodiments disclosed in the present invention further provide a model-based giant panda health monitoring system, the system comprising: A sample data acquisition module, used to acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters; A preprocessing module, used for preprocessing the sample data to obtain preprocessed sample data; A feature acquisition module, used to extract features from the preprocessed sample data to obtain key features; A feature optimization module, used to optimize the key features to obtain key optimized features; A result acquisition module, used to determine the health risk results based on the key optimization features and the risk assessment model; The health status acquisition module is used to determine the health status of the giant panda based on the health risk results.

[0007] In a third aspect, an embodiment disclosed in the present invention further provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs; the one or more programs are executed by the one or more processors to implement the model-based giant panda health monitoring method as described above.

[0008] In a fourth aspect, the embodiments disclosed in the present invention further provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the model-based giant panda health monitoring method as described above.

[0009] The embodiment disclosed in the present invention provides a model-based giant panda health monitoring method, system, electronic device and computer-readable storage medium, the method comprising: obtaining sample data related to giant pandas, the sample data including biomarkers and environmental parameters; preprocessing the sample data to obtain preprocessed sample data; extracting features from the preprocessed sample data to obtain key features; optimizing the key features to obtain key optimized features; determining health risk results based on the key optimized features and risk assessment models; determining the health status of giant pandas based on the health risk results. The present invention reduces the data dimension, and enhancing key features can avoid the model from being disturbed by noise data, improve the efficiency and accuracy of processing data, and thus enhance the real-time, accuracy and comprehensiveness of health monitoring. The present application combines biomarkers (biomarkers of feces, etc.) and environmental parameters (temperature, humidity, etc.) to monitor the health of giant pandas. Through continuous monitoring of giant pandas, it is possible to timely discover changes in the health status of individuals or populations, identify potential disease risks and nutritional problems, thereby providing early warning and rapid response support for the protection of giant pandas, and reducing the impact of disease outbreaks on individual or population giant pandas. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments disclosed in the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0011] Figure 1 The present invention is a flowchart of a model-based giant panda health monitoring method in an embodiment disclosed in the present invention.

[0012] Figure 2 It is a structural schematic diagram of a model-based giant panda health monitoring system in the embodiment disclosed in the present invention. DETAILED DESCRIPTION

[0013] The embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments disclosed in the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0014] It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. In the present invention, "monitoring" and "detection" can have the same meaning.

[0015] The names of the messages or information exchanged between multiple devices in the embodiments disclosed in the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0016] In response to the above problems, the embodiments disclosed in the present invention provide a model-based giant panda health monitoring method, which reduces data dimensions and enhances key features to avoid the model being interfered with by noise data, improves the efficiency and accuracy of data processing, and thereby enhances the real-time, accuracy and comprehensiveness of health monitoring.

[0017] Figure 1 The flowchart of a model-based giant panda health monitoring method in the embodiment disclosed in the present invention is shown in FIG. The method can be executed by a model-based giant panda health monitoring system, which can be implemented in software and / or hardware, and the system can be configured in an electronic device. Figure 1 As shown, the method may specifically include the following steps: 110: Acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters.

[0018] Specifically, this application can be used not only for giant pandas, but also for other animals. This application takes giant pandas as an example. The feces of giant pandas not only contain the digestion residues of their food, but also contain rich biological information. The biological information contains biomarkers related to health status, such as intestinal microbial communities, metabolites and pathogens, etc., which can indicate their health status and ecological habits. The data in this application can be text data, image data or other data in other processable formats. The data of this application comes from the giant panda breeding research base (for example, the Chengdu giant panda breeding research base, etc.) or the data processing center related to the Chengdu giant panda breeding research base (for example, the National Supercomputing Chengdu Center associated with the Chengdu giant panda breeding research base, etc.), but is not limited to this, but can come from any channel that can reasonably, legally and compliantly obtain data.

[0019] In an optional embodiment, the giant panda-related sample data includes: Obtain biomarkers associated with giant panda feces at different time periods; Obtaining environmental parameters of the environment in which the giant panda feces is located; Based on the biomarkers and environmental parameters, sample data is determined.

[0020] It is understandable that panda feces are collected at different times, from different individuals and under different environmental conditions, and the biological information in the feces is used as a biomarker. For example, the biomarker can be represented by a vector W d ={microorganisms, metabolites, endocrine indicators, food residues, parasites}, and then use sensors and weather stations to collect the environmental parameters of the above feces. For example, the environmental parameters can be expressed by the vector E d Represents {temperature, humidity, precipitation, food resources} and other information. Finally, the vector set composed of biomarkers and environmental parameters is used as sample data, and the expression of the sample data is: , Among them, D 1 represents sample data, μ represents the environmental state drift function, E d represents the d-dimensional environmental parameter, t represents the differential time factor, W d represents the d-dimensional biomarker, σ represents the diffusion term function, J k Represents the k-order environmental mutation factor.

[0021] This application ensures the accuracy and real-time nature of sample data through data collection by automated equipment, while integrating feces with environmental parameters to effectively integrate data from different sources, avoid data silos, and improve the comprehensiveness of sample data.

[0022] 120: Preprocess the sample data to obtain preprocessed sample data.

[0023] Exemplarily, based on the above embodiment, the sample data is preprocessed by a local differential mapping factor, a functional analysis space embedding factor, a Riemann manifold factor and a heat kernel regularization function to obtain preprocessed sample data, and the expression of the processed sample data is: , Among them, D 2 represents the preprocessed sample data, ψ i represents the i-th local differential mapping factor, represents the jth functional analysis space embedding factor, M g represents the g-dimensional Riemann manifold factor, and H represents the heat kernel regularization function.

[0024] This embodiment standardizes and denoises local data through local differential mapping factors, and combines functional analysis space embedding factors to ensure the smoothness of sample data in the embedding space and remove high-frequency noise of the sample data.

[0025] 130: Perform feature extraction on the preprocessed sample data to obtain key features.

[0026] Furthermore, based on the above embodiments, feature selection weight factors, feature penalty factors, regularization weight factors, feature scaling factors and Markov feature optimization functions are used to extract features from preprocessed sample data to obtain key features.

[0027] In an optional embodiment, feature extraction is performed on the preprocessed sample vector to obtain key features, including: The first formula is used to extract the features of the preprocessed sample vector to obtain the key features. The expression of the first formula is: , Among them, T represents the key feature, L represents the Bayesian distribution likelihood function, δ represents the differential function, w represents the feature selection weight factor, x t Represents the preprocessed sample data D 2 Variation distribution vector in the x direction, y t Represents the preprocessed sample data D 2 The variational distribution vector in the y direction, θ represents the feature penalty factor, λ represents the regularization weight factor, r represents the dimension of the key feature T, T r represents the feature optimization factor, f θ represents the Markov feature optimization function, Represents the feature scaling factor.

[0028] The embodiment disclosed in the present invention extracts key features from pre-processed data through the first formula, finds implicit health risk factors from massive data, and shortens data analysis time.

[0029] 140: Optimizing the key features to obtain key optimized features.

[0030] Furthermore, based on the above embodiments, variance density function, feature sparsity factor, feature penalty factor, feature optimization factor, feature scaling factor, Markov feature optimization function, feature gain factor and conditional entropy probability density function are used to optimize key features to obtain key optimized features.

[0031] In an optional embodiment, the key features are optimized to obtain the key optimized features, including: The second formula is used to optimize the key features to obtain the key optimized features. The expression of the second formula is: , Among them, T 1 represents the key optimization feature, Var represents the variance density function, v 1 represents the feature sparse factor, v2 represents the feature gain factor, and I represents the conditional entropy probability density function.

[0032] The embodiments disclosed in the present invention extract the most health-related key optimized features from key features through the second formula, which can significantly reduce the data dimension, avoid the model being interfered by noise data, improve the subsequent model training efficiency, and shorten the data training time.

[0033] 150: Determine the health risk result based on the key optimized features and the risk assessment model.

[0034] Exemplarily, the health risk result can be a health risk score. Based on the above embodiments, the key optimized features are input into the risk assessment model to obtain the health risk score, where the expression of the risk assessment model is: , where R represents the health risk result, k represents the dynamic functional factor, and N s represents the conditional probability distribution function, represents the vector element product symbol.

[0035] The disclosed embodiments of the present invention integrate biological information such as fecal characteristics and environmental parameters through the risk assessment model, quantify the population health risk score, and enhance the real-time performance and accuracy of health monitoring.

[0036] 160: Determine the health status of the giant panda based on the health risk result.

[0037] It can be understood that the risk assessment model is used to deeply analyze the key optimized features to determine whether there is a risk in the health status of the giant panda. Specifically, the health risk score is compared with the health status threshold to determine different health statuses, and a health risk assessment report and dynamic monitoring and update are generated.

[0038] For example, the health status can be divided into the following categories: Healthy: The risk score is lower than a certain threshold (for example, the health risk score R < threshold 1); Sub-healthy: The risk score is between two thresholds (for example, threshold 1 ≤ health risk score R < threshold 2); High risk: The risk score is higher than a certain threshold (for example, the health risk score R ≥ threshold 2).

[0039] Among them, the method for setting the threshold: (1) Based on historical data: Analyze the existing giant panda health data, find the distribution of risk scores in different health statuses, and thus set reasonable thresholds.

[0040] (2) Based on expert experience: Consult veterinarians or experts in related fields and ask them to give threshold recommendations based on their experience.

[0041] (3) Based on statistical analysis: Use statistical methods (e.g., ROC curve) to find the optimal threshold to maximize the accuracy of health status classification.

[0042] The health risk assessment report includes: Basic information: Giant panda’s ID, age, gender, etc.

[0043] Health risk score: The health risk score R calculated above.

[0044] Health status: The health status of the giant panda (e.g., healthy, sub-healthy, high risk) is determined based on the health risk score and health status threshold. In addition, risk factors should also be considered: Based on the feature T 1 The results of the analysis of (key characteristics) should identify factors that may lead to health risks. For example, if microbial diversity is significantly reduced, the report should state that "microbial imbalance may lead to health risks."

[0045] Report Format: Reports can use various formats such as text, tables, charts, etc. to present information and make it easy to understand and analyze.

[0046] Report generation method: You can use programming language report generation tools such as Report Lab to automatically generate reports.

[0047] Through the above information, we can get health status recommendations: According to the health risk results and risk factors, we can give corresponding health status recommendations. For example, if the giant panda is in a "sub-healthy" state, we can recommend "adjusting the diet structure and increasing the intake of probiotics." If the giant panda is in a "high-risk" state, we can recommend "immediate detailed physical examination and treatment."

[0048] Dynamic monitoring and updates: Continuous tracking: Establish a dynamic monitoring system to regularly collect and analyze fecal samples from giant pandas to generate new health risk assessment reports.

[0049] Model update: Based on the latest giant panda sample data, the health monitoring risk assessment model is updated regularly to optimize feature selection, parameter adjustment, etc. to improve the accuracy and reliability of the model.

[0050] Threshold adjustment: Dynamically adjust the health status threshold based on actual conditions to adapt to changes in the giant panda's health.

[0051] It should be noted that diffusion usually refers to the process of dispersion or propagation of a substance or energy in space or time. The diffusion term function σ can be understood as a d-dimensional biomarker W d (e.g., stool sample data) for sample data D 1 The degree to which a function or distribution is affected by a variable. In mathematics and statistics, variation usually refers to making small changes to a function or distribution. The variational distribution vector x t and t Refers to the preprocessed sample data D 2 Small changes in different directions. The factors such as feature gain factor, feature sparse factor and feature scaling factor are empirical values. The health status of giant pandas changes dynamically and is affected by many factors. The dynamic functional factor k is designed to capture these changes and dynamically adjust the risk. Conditional probability refers to the probability of another event occurring under the condition that a certain event occurs. The conditional probability distribution function N s (T 1 ,θ) describes the key optimization feature T 1 Probability distribution under certain conditions, understanding the key optimization characteristics T 1 Importance in different health states.

[0052] In summary, the embodiment disclosed in the present invention provides a giant panda health monitoring method, which obtains sample data including biomarkers and environmental parameters, effectively integrates feces and environmental parameter data from different sources, avoids data silos, and improves the comprehensiveness of sample data; then pre-processes the processed sample data to remove high-frequency noise from the sample data; uses the first formula to extract key features, reduces the data volume of the sample data, and optimizes data processing efficiency, and then uses the second formula to optimize the key features and reduce the data dimension, which can avoid the model being interfered by noise data, improve the efficiency of subsequent model training, and shorten data training time. Finally, the risk assessment model is used to evaluate the health risk results of giant pandas to improve the real-time, accuracy and comprehensiveness of health monitoring.

[0053] Figure 2 FIG. 1 is a schematic diagram of the structure of the giant panda health monitoring system based on the model in the embodiment disclosed in the present invention. Figure 2 As shown, the system includes a sample data acquisition module 210 , a preprocessing module 220 , a feature acquisition module 230 , a feature optimization module 240 , a result acquisition module 250 and a health status acquisition module 260 .

[0054] The sample data acquisition module 210 is used to acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters; The preprocessing module 220 is used to preprocess the sample data to obtain preprocessed sample data; The feature acquisition module 230 is used to extract features from the preprocessed sample data to obtain key features; The feature optimization module 240 is used to optimize the key features to obtain key optimized features; The result acquisition module 250 is used to determine the health risk result based on the key optimization features and the risk assessment model; The health status acquisition module 260 is used to determine the health status of the giant panda based on the health risk results.

[0055] In a specific embodiment, the sample data acquisition module 210 is used to acquire sample data related to giant pandas, including: Obtain biomarkers related to giant panda feces at different time periods; Obtaining environmental parameters of the environment in which the giant panda feces is located; Based on the biomarker and the environmental parameter, sample data is determined, wherein the expression of the sample data is: , Among them, D 1 represents sample data, μ represents the environmental state drift function, E d represents the d-dimensional environmental parameter, t represents the differential time factor, W d represents the d-dimensional biomarker, σ represents the diffusion term function, J k Represents the k-order environmental mutation factor.

[0056] In a specific embodiment, the expression of the preprocessed sample data is: , Among them, D 2 represents the preprocessed sample data, ψ i represents the i-th local differential mapping factor, represents the jth functional analysis space embedding factor, M g represents the g-dimensional Riemann manifold factor, and H represents the heat kernel regularization function.

[0057] In a specific embodiment, the feature acquisition module 230 is used to extract features from the preprocessed sample data to obtain key features, including: The first formula is used to extract features from the preprocessed sample data to obtain key features. The expression of the first formula is: , Among them, T represents the key feature, L represents the Bayesian distribution likelihood function, δ represents the differential function, w represents the feature selection weight factor, x t Represents the preprocessed sample data D 2Variation distribution vector in the x direction, y t Represents the preprocessed sample data D 2 The variational distribution vector in the y direction, θ represents the feature penalty factor, λ represents the regularization weight factor, r represents the dimension of the key feature T, T r represents the feature optimization factor, f θ represents the Markov feature optimization function, Represents the feature scaling factor.

[0058] In a specific embodiment, the feature optimization module 240 is used to optimize the key features to obtain the key optimized features, including: The key feature is optimized using a second formula to obtain a key optimized feature. The expression of the second formula is: , Among them, T 1 represents the key optimization feature, Var represents the variance density function, v 1 represents the feature sparse factor, v 2 represents the feature gain factor, and I represents the conditional entropy probability density function.

[0059] In a specific embodiment, the risk assessment model is expressed as: , Where R represents the health risk result, k represents the dynamic functional factor, N s represents the conditional probability distribution function, Represents the vector element-wise product sign.

[0060] The model-based giant panda health monitoring system provided by the embodiment of the present invention can execute the steps of the model-based giant panda health monitoring method provided by the method embodiment of the present invention, and the execution steps and beneficial effects are not repeated here.

[0061] An embodiment of the present invention further provides an electronic device, the electronic device comprising: one or more processors; a storage device for storing one or more programs; the one or more programs are executed by the one or more processors to implement the model-based panda health monitoring method as described above. In particular, according to an embodiment of the present invention, the process of the model-based panda health monitoring method can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, the computer program containing a program code corresponding to the model-based panda health monitoring method, thereby implementing the model-based panda health monitoring method as described above. In such an embodiment, the computer program can be downloaded and installed from a network (for example, through a built-in communication device, an external communication device), or installed from a specific storage device (or ROM). When the computer program is executed by the processor, the above functions defined in the method of the embodiment of the present invention are executed.

[0062] It should be noted that the above-mentioned computer-readable medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the disclosure of the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0063] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains sample data related to giant pandas, the sample data includes biological markers and environmental parameters; pre-processes the sample data to obtain pre-processed sample data; extracts features from the pre-processed sample data to obtain key features; optimizes the key features to obtain key optimized features; determines health risk results based on the key optimized features and the risk assessment model; and determines the health status of the giant panda based on the health risk results.

[0064] This application can achieve: through continuous monitoring and analysis of giant panda feces, combined with the detection of biomarkers, it is possible to comprehensively evaluate the health status, ecological habits and nutritional status of pandas, overcome the shortcomings of traditional methods, and provide more accurate health monitoring results. The microbiome and metabolite information contained in feces can reflect the adaptive relationship between animals and their environment. The present invention can help researchers better understand how giant pandas adapt to environmental changes and provide important data support for habitat management and ecological protection.

[0065] With the help of big data platforms and diversified sampling technologies, a large number of fecal samples and related ecological data can be collected, which can promote the representativeness of samples, improve the credibility of analysis results, and thus form a more scientific health assessment model. The feature optimization algorithm can detect changes in health status and potential disease risks in real time, thereby providing support for early warning and rapid response of wild animals and reducing the impact of disease outbreaks on populations.

[0066] Based on comprehensive data analysis and health risk assessment models, conservation organizations and managers can formulate management and conservation strategies more scientifically and effectively, optimize resource allocation, and improve the efficiency and response capabilities of conservation work. This invention combines multiple fields such as ecology, biology, and data science, promotes interdisciplinary research and cooperation, promotes the deep integration of health monitoring technology and ecological protection practice, and provides a good foundation for subsequent research.

[0067] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0068] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0069] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present invention.

Claims

1. A model-based method for monitoring the health of giant pandas, characterized in that: The model-based giant panda health monitoring method includes: Acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters; Preprocessing the sample data to obtain preprocessed sample data; Performing feature extraction on the preprocessed sample data to obtain key features; Performing feature optimization on the key features to obtain key optimized features; determining health risk outcomes based on the key optimization features and the risk assessment model; Based on the health risk results, the health status of the giant panda is determined.

2. The model-based giant panda health monitoring method according to claim 1, characterized in that: Get sample data related to giant pandas, including: Obtain biomarkers related to giant panda feces at different time periods; Obtaining environmental parameters of the environment in which the giant panda feces is located; Based on the biomarkers and the environmental parameters, the sample data is determined.

3. The model-based giant panda health monitoring method according to claim 2, characterized in that: The expression of the sample data is: ， Where D1 represents sample data, μ represents the environmental state drift function, and E d represents the d-dimensional environmental parameter, t represents the differential time factor, W d represents the d-dimensional biomarker, σ represents the diffusion term function, J k Represents the k-order environmental mutation factor.

4. The model-based giant panda health monitoring method according to claim 3, characterized in that: The expression of the preprocessed sample data is: ， Among them, D2 represents the preprocessed sample data, ψ i represents the i-th local differential mapping factor, represents the jth functional analysis space embedding factor, M g represents the g-dimensional Riemann manifold factor, and H represents the heat kernel regularization function.

5. The model-based giant panda health monitoring method according to claim 4, characterized in that: The step of extracting features from the preprocessed sample data to obtain key features includes: The first formula is used to extract features from the preprocessed sample data to obtain key features. The expression of the first formula is: ， Among them, T represents the key feature, L represents the Bayesian distribution likelihood function, δ represents the differential function, w represents the feature selection weight factor, x t represents the variational distribution vector of the preprocessed sample data D2 in the x direction, y t represents the variational distribution vector of the preprocessed sample data D2 in the y direction, θ represents the feature penalty factor, λ represents the regularization weight factor, r represents the dimension of the key feature T, T r represents the feature optimization factor, f θ represents the Markov feature optimization function, Represents the feature scaling factor.

6. The model-based giant panda health monitoring method according to claim 5, characterized in that: The key features are optimized to obtain key optimized features, including: The key feature is optimized using a second formula to obtain a key optimized feature. The expression of the second formula is: ， Among them, T1 represents the key optimization feature, Var represents the variance density function, v1 represents the feature sparsity factor, v2 represents the feature gain factor, and I represents the conditional entropy probability density function.

7. The model-based giant panda health monitoring method according to claim 6, characterized in that: The risk assessment model is expressed as: ， Where R represents the health risk result, k represents the dynamic functional factor, N s represents the conditional probability distribution function, Represents the vector element-wise product sign.

8. Model-based giant panda health monitoring system, characterized by: The model-based giant panda health monitoring system includes: A sample data acquisition module, used to acquire sample data related to giant pandas, wherein the sample data includes biological markers and environmental parameters; A preprocessing module, used for preprocessing the sample data to obtain preprocessed sample data; A feature acquisition module, used to extract features from the preprocessed sample data to obtain key features; A feature optimization module, used to optimize the key features to obtain key optimized features; A result acquisition module, used to determine the health risk results based on the key optimization features and the risk assessment model; The health status acquisition module is used to determine the health status of the giant panda based on the health risk results.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device, the storage device being used to store one or more programs, Wherein, when the one or more programs are executed by the one or more processors, the model-based giant panda health monitoring method according to any one of claims 1-7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the model-based giant panda health monitoring method according to any one of claims 1-7 is implemented.

Images