Method and system for detecting efficacy of pesticide preparation

Abstract

The invention relates to the technical field of pesticide detection, in particular to a pesticide preparation efficacy detection method and system, which improve the objectivity and accuracy of efficacy detection through data driving and multi-dimensional evaluation in combination with real-time monitoring and automatic analysis, ensure the reliability of results through abnormal physiological index recognition, and improve the accuracy of efficacy detection. The method has the advantages of high efficiency, flexibility and high environmental adaptability, and the problems of high subjectivity, long consumed time, inaccurate result and the like in a traditional method are solved; the method comprises the following steps: collecting real-time growth state data and growth environment data of crops after a set duration of application of a pesticide preparation to be detected, and initial growth state data of the crops before application; inputting the initial growth state data, the real-time growth state data and the growth environment data into a pesticide effect analysis model to obtain a first pesticide effect detection result; and performing real-time biochemical analysis on the crops to obtain a crop physiological index set.

Description

Technical Field

[0001] The present invention relates to the technical field of pesticide detection, and in particular to a method and system for detecting the efficacy of a pesticide preparation. Background Art

[0002] In agricultural production, the application of pesticide formulations is crucial for preventing and controlling pests and diseases and ensuring crop yield and quality. However, with the increasing variety of pesticides and the increasing demand for high-efficiency, low-toxic, and environmentally friendly pesticide formulations in agricultural production, how to scientifically and accurately detect and evaluate the efficacy of pesticide formulations has become an urgent problem to be solved.

[0003] Existing methods for testing the efficacy of pesticides often rely on field trials, which evaluate the effects of pesticides through visual inspection or simple physiological and biochemical indicators. This method has disadvantages such as strong subjectivity, long time consumption, and inaccurate results. It is difficult to fully and accurately reflect the actual efficacy of pesticide preparations. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for detecting the efficacy of pesticide preparations, which improves the objectivity and accuracy of efficacy detection through data-driven and multi-dimensional evaluation, combined with real-time monitoring and automated analysis, ensures the reliability of the results by identifying abnormal physiological indicators, has the advantages of high efficiency, flexibility and strong environmental adaptability, and improves the problems of strong subjectivity, long time consumption and inaccurate results existing in traditional methods.

[0005] In a first aspect, the present invention provides a method for detecting the efficacy of a pesticide preparation, the method comprising:

[0006] Collecting real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application;

[0007] Inputting the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result;

[0008] Conduct real-time biochemical analysis of crops to obtain a set of crop physiological indicators;

[0009] Traversing the crop physiological indicator set, extracting abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtaining the abnormal physiological indicator set;

[0010] In response to the abnormal physiological indicator set being an empty set, outputting the first efficacy detection result as the final pesticide preparation efficacy detection result;

[0011] In response to the presence of an abnormal physiological indicator in the abnormal physiological indicator set, the first efficacy detection result and the abnormal physiological indicator set are input into the pesticide efficacy evaluation system to obtain a second efficacy detection result, and the second efficacy detection result is output as the final pesticide preparation efficacy detection result.

[0012] Furthermore, the method for setting the time length of the pesticide preparation to be detected includes:

[0013] Analyze the growth cycle and key development stages of target crops during their growth cycle;

[0014] Consider the mechanism of action and effective time of different pesticides in the pesticide characteristics, and determine the time window when the pesticide begins to take effect;

[0015] Monitor the temperature, humidity and light in the growth environment data and calculate the observation time;

[0016] Based on the time window in which the pesticide begins to take effect and the observation time, determine the set time for the pesticide formulation to be tested.

[0017] Furthermore, the method for obtaining the first drug efficacy detection result includes:

[0018] Clean all collected data to remove invalid data, missing values ​​and outliers; and standardize and normalize the cleaned data;

[0019] Integrate initial growth status data, real-time growth status data and growth environment data to form a data set;

[0020] According to the needs of pesticide efficacy analysis, the linear regression model is selected as the basic model of the pesticide efficacy analysis model; characteristic variables that affect efficacy evaluation are extracted from the integrated data set, and the characteristic variables include crop growth rate, leaf color change, soil moisture and temperature; historical data are collected and divided into training sets and test sets, and the pesticide efficacy analysis model is trained with the training set, and the generalization ability of the pesticide efficacy analysis model is verified with the test set;

[0021] Input the preprocessed and integrated data into the trained pesticide efficacy analysis model;

[0022] The pesticide efficacy analysis model calculates the impact of pesticides on crop growth status based on input data and outputs the first efficacy test result.

[0023] Furthermore, the method for obtaining the crop physiological indicator set includes:

[0024] Based on the set observation time, collect physiological index samples from crops, including leaves and roots;

[0025] The collected physiological indicator samples are cleaned, dried and ground;

[0026] Analyze crop physiological indicators, including chlorophyll content, photosynthetic rate, respiration, enzyme activity, nutrient content and water status;

[0027] The physiological indicators obtained from biochemical analysis are sorted out to form a set of crop physiological indicators.

[0028] Furthermore, the crop physiological index set is represented in matrix form, including:

[0029]

[0030] Among them, C i represents the chlorophyll content measured for the i-th time; R i represents the photosynthetic rate measured at the i-th time; R i ′ represents the respiration measured at the ith time; A i represents the enzyme activity measured at the i-th time; N i represents the nutrient element content measured for the i-th time; W i Represents the moisture state of the i-th measurement.

[0031] Furthermore, the method for obtaining the abnormal physiological indicator set includes:

[0032] Construct standard ranges of physiological indicators and define standard ranges of physiological indicators of crops;

[0033] Iterate through the multiple physiological indicator values ​​obtained from each measurement in the acquired crop physiological indicator set;

[0034] Compare each physiological indicator standard value with its corresponding physiological indicator standard range one by one, and mark the physiological indicator value that exceeds the standard range as an abnormal physiological indicator;

[0035] All physiological indicators marked as abnormal are collected to form an abnormal physiological indicator set.

[0036] Furthermore, the abnormal physiological indicator set is:

[0037] When m measurements are performed, each measurement has n physiological indicators, and each physiological indicator corresponds to a preset standard range, and the preset standard range is [L j , U j ], where L j is the lower limit of the jth physiological index, U j is the upper limit of the jth physiological index; the set of abnormal physiological indicators is:

[0038] {(i,j,p ij )|p ij <Lj ∨p ij >U j ,i=1,2,...,m;j=1,2,...,n};

[0039] Among them, (i,j,p ij ) represents the jth physiological index p measured at the i-th time ij , p ij <L j ∨p ij >U j Indicates p ij Exceeds the standard range of the jth physiological indicator.

[0040] On the other hand, the present application also provides a pesticide preparation efficacy detection system, the system comprising:

[0041] A data collection module is used to collect real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application;

[0042] A preliminary efficacy analysis module is used to input the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result;

[0043] Physiological index analysis module, used to conduct real-time biochemical analysis of crops and obtain a set of crop physiological indicators;

[0044] An abnormality detection module is used to traverse the crop physiological indicator set, extract abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtain the abnormal physiological indicator set;

[0045] A result determination module, configured to output the first efficacy detection result as the final pesticide preparation efficacy detection result in response to the abnormal physiological indicator set being an empty set;

[0046] The comprehensive evaluation module is used to respond to the existence of abnormal physiological indicators in the abnormal physiological indicator set, input the first efficacy detection result and the abnormal physiological indicator set as input into the pesticide efficacy evaluation system, obtain the second efficacy detection result, and output the second efficacy detection result as the final pesticide preparation efficacy detection result.

[0047] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0049] Compared with the prior art, the present invention has the following beneficial effects: by actually collecting the growth status data and growth environment data of crops, rather than relying on subjective judgment or simple physiological and biochemical indicators, the objectivity and accuracy of efficacy detection are improved; by considering the changes in the growth status of crops, real-time biochemical analysis is introduced to evaluate the effects of pesticides from multiple angles, and the impact of pesticides on crops is fully understood; by real-time monitoring of the growth status and physiological indicators of crops, any adverse reactions that may be caused by pesticides can be immediately discovered, thereby improving the implementation speed of pesticide use strategies; by inputting data into a pesticide efficacy analysis model and outputting the first efficacy detection result, human intervention is reduced, and efficiency and accuracy are improved; by traversing the set of physiological indicators and extracting abnormal physiological indicators, abnormal conditions that affect the accuracy of efficacy evaluation are effectively identified, and further analyzed to ensure the reliability of the evaluation results; By setting the first efficacy test result and the second efficacy test result, the preliminary result will be directly used when no abnormal physiological indicators are found, and a more in-depth analysis will be conducted when abnormal physiological indicators are found, thereby improving the scientificity and rigor of the final result; the preset standard range of physiological indicators is adjusted according to different pesticide types and crop types, which has good adaptability and scalability; by incorporating growth environment data into the efficacy analysis model, it is convenient to evaluate the performance of pesticides under different environmental conditions, and provide a data basis for the rational use of pesticides; the pesticide formulation efficacy detection method uses data-driven and multi-dimensional evaluation, combined with real-time monitoring and automated analysis, to improve the objectivity and accuracy of efficacy detection, and ensure the reliability of the results through the identification of abnormal physiological indicators. It has the advantages of high efficiency, flexibility and strong environmental adaptability, and improves the problems of strong subjectivity, long time consumption and inaccurate results in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the present invention;

[0051] Figure 2 is a flow chart of a method for obtaining a first drug efficacy test result;

[0052] Figure 3 It is a structural diagram of a pesticide preparation efficacy detection system. DETAILED DESCRIPTION

[0053] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0054] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0055] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0056] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0057] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0058] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0059] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0060] The present application is described below in conjunction with the drawings in the present application.

[0061] Embodiment 1: Figure 1 to Figure 2 As shown, a method for detecting the efficacy of a pesticide preparation of the present invention specifically comprises the following steps:

[0062] S1. Collecting real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application;

[0063] In step S1, it is necessary to collect the real-time growth status data and growth environment data of the crop after the pesticide formulation to be tested has been applied, as well as the initial growth status data of the crop before application; the details are as follows:

[0064] The method for setting the duration of the pesticide formulation to be tested includes: analyzing the growth cycle of the crop, including understanding the growth cycle and key development stages of the target crop; considering the characteristics of the pesticide, including different pesticides have different mechanisms of action and effective time, and determining the time window for the pesticide to start to take effect according to the pesticide instructions or experimental data; using the growth environment data, by monitoring the growth environment data, such as temperature, humidity and light, etc., to calculate the appropriate observation time. For example, when the temperature is high, different pesticides are absorbed by the crop and take effect at different times, so the observation time is shortened accordingly; referring to the initial growth state data, the initial growth state data is convenient for researchers to understand the health status of the crop before the application of the pesticide. If the crop grows well, the effect of the pesticide will appear quickly, otherwise it will take longer to observe the effect; combining historical data and experience, through the historical detection data of similar crops and pesticides, refer to the historical detection number to set a reasonable observation time, and the experience of agricultural experts is also a reference for setting the time; setting the observation window, combining the above factors, setting a reasonable observation window, including one or more time points, so as to compare the growth state changes of the crop in different time periods, and ensure that the key change points of the pesticide effect can be captured;

[0065] Initial growth status data collection, including: time point selection, before the application of pesticide formulations, select a suitable benchmark time point, the benchmark time point is the period when the crop is in a healthy state and free from pests and diseases; data type, collect the initial growth status data of the crop, including physical parameters such as crop height, number of leaves, leaf color, stem thickness and root development; tools and equipment, use professional measuring tools such as rulers, tape measures and electronic scales for precise measurement, and use cameras or high-resolution imaging equipment to record the appearance characteristics of the crop;

[0066] Real-time growth status data collection, including: time point selection, after the application of pesticide formulations, select one or more predetermined time points for data collection, and the "set duration" is determined based on the growth environment data and initial growth status data; data type, collect the growth status data of crops after the application of pesticides, including the height growth of crops, leaf changes, color changes, stem changes and leaf health status, etc.; tools and equipment, use professional tools to measure and record the changes in the growth status of crops, and use drones, remote sensing technology or other automated monitoring equipment to assist data collection during measurement to improve efficiency and accuracy;

[0067] Growth environment data collection, including: time point selection, which is carried out simultaneously with real-time growth status data collection, covering the same observation time window; data type, which collects data on the crop growth environment, including environmental parameters such as soil moisture, soil pH, air humidity, temperature, light intensity and wind speed; tools and equipment, which use equipment such as weather stations, soil moisture sensors, pH meters and light intensity meters to monitor and record these environmental data in real time;

[0068] Data integration and storage, including: data formatting, ensuring that all collected data are in consistent formats to facilitate subsequent processing and analysis; data storage, storing all collected data in a central database to ensure data security and accessibility; data backup, regularly backing up data to prevent data loss or damage.

[0069] By analyzing the growth cycle and key development stages of crops, combined with the mechanism of action and effective time of pesticides, the rationality of the set duration is ensured, so that the detection conforms to scientific laws; the growth environment data is used to dynamically adjust the observation time, better adapt to the evaluation of pesticide effects under different environmental conditions, and improve the reliability of the test results; by collecting detailed initial growth status data, including physical parameters such as crop height and number of leaves, and using professional tools for measurement, the influence of subjective judgment is reduced; real-time growth status data collection is introduced, and modern technologies such as drones and remote sensing technologies are used for monitoring to improve the frequency and accuracy of data collection, so as to facilitate the timely detection of crop changes; by paying attention to the growth status of crops, covering the growth environment Data collection enables comprehensive consideration of various influencing factors when evaluating the effectiveness of pesticides; through data integration and storage, all data formats are ensured to be unified, stored securely, and backed up regularly, which facilitates subsequent data analysis and result verification, and improves the systematicness and standardization of the overall work; the observation window is set according to the initial growth status of the crop and historical data, so that the detection method has high flexibility and can adapt to different crops and pesticide types; the application of automated monitoring equipment improves the efficiency of data collection, reduces labor costs, and makes detection work more efficient; through scientific setting of duration, detailed initial data collection, comprehensive consideration of real-time monitoring and environmental data, and data management, the accuracy and practicality of pesticide efficacy detection are improved.

[0070] S2, inputting the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result;

[0071] Step S2 inputs the collected initial growth state data, real-time growth state data and growth environment data into the pesticide efficacy analysis model to obtain the first efficacy detection result; the details are as follows:

[0072] First, all collected data are cleaned to remove invalid data, missing values ​​and outliers to ensure data quality;

[0073] Standardize or normalize the cleaned data so that the input of the pesticide efficacy analysis model is on the same scale, which is convenient for the training and prediction of the pesticide efficacy analysis model;

[0074] Integrate the initial growth status data, real-time growth status data and growth environment data to form a unified data set, which is convenient for the input of subsequent pesticide efficacy analysis models;

[0075] According to the needs of pesticide efficacy analysis, select mathematical models or machine learning models such as linear regression, decision tree, random forest, support vector machine or neural network;

[0076] Extract characteristic variables useful for drug efficacy evaluation from the integrated data set, including crop growth rate, leaf color change, soil moisture and temperature, etc.;

[0077] Use part of the historical data as a training set to train the pesticide efficacy analysis model, and find the best parameter configuration through the gradient descent method in the optimization algorithm, so that the pesticide efficacy analysis model can fit the training data well;

[0078] Input the preprocessed and integrated data into the trained pesticide efficacy analysis model;

[0079] The pesticide efficacy analysis model calculates the effect of pesticides on crop growth under specific conditions based on the input data and outputs the first efficacy test result;

[0080] Interpret the first efficacy test results output by the pesticide efficacy analysis model; the first efficacy test results include a preliminary evaluation of the pesticide efficacy, such as the efficacy, whether the expected effect has been achieved, etc.;

[0081] Record the first efficacy test results output by the pesticide efficacy analysis model to provide a basis for subsequent steps;

[0082] Use data that has not participated in training as a test set to verify the generalization ability of the pesticide efficacy analysis model to ensure that the pesticide efficacy analysis model still performs well on new data;

[0083] When the performance of the pesticide efficacy analysis model is poor, the pesticide efficacy analysis model can be optimized by adjusting the model parameters or changing the feature selection to improve the accuracy and robustness of the pesticide efficacy analysis model.

[0084] By cleaning all the collected data, removing invalid data, missing values ​​and outliers, the quality of data input into the pesticide efficacy analysis model is ensured, noise interference is reduced, and the credibility of the analysis results is improved; by standardization or normalization, the differences between different dimensions are eliminated, so that the input of the pesticide efficacy analysis model is on the same scale, which is convenient for the training and prediction of the pesticide efficacy analysis model and avoids the deviation caused by different data magnitudes; the initial growth status data, real-time growth status data and growth environment data are integrated into a unified data set to simplify the subsequent data processing process and improve the convenience of data use; according to the needs of pesticide efficacy analysis, a variety of mathematical models or machine learning models are selected to make the method more adaptable and flexible; by extracting characteristic variables useful for efficacy evaluation from the integrated data set, it is ensured that the pesticide efficacy analysis model can capture the key factors affecting the efficacy and improve the predictive ability and interpretability of the pesticide efficacy analysis model; using historical data as a training set, through the optimization algorithm The gradient descent method in the algorithm is used to find the optimal parameter configuration to ensure that the pesticide efficacy analysis model can fit the training data well, and the data not involved in the training is used as the test set to verify the generalization ability of the model, so as to ensure the effectiveness and reliability of the pesticide efficacy analysis model; the first efficacy test result output by the pesticide efficacy analysis model is reasonably interpreted and recorded, which provides a scientific basis for the subsequent steps and ensures the consistency and traceability of each test process; when the performance of the pesticide efficacy analysis model is poor, the pesticide efficacy analysis model is optimized by adjusting the model parameters or changing the feature selection to improve the accuracy and robustness of the pesticide efficacy analysis model, so that the pesticide efficacy analysis model is suitable for the evaluation of pesticide efficacy; through data cleaning, standardization and integration, high-quality input is ensured, a variety of models are selected for training and verification, prediction accuracy is improved, key feature variables are extracted, the explanatory power of the pesticide efficacy analysis model is enhanced, and the process consistency and traceability are ensured through result interpretation and recording, which effectively improves the scientificity and reliability of efficacy detection.

[0085] S3, conduct real-time biochemical analysis on crops to obtain a set of crop physiological indicators;

[0086] Step S3 requires real-time biochemical analysis of crops to obtain a set of crop physiological indicators; the details are as follows:

[0087] Set observation time and collect physiological index samples from crops. The collected physiological index samples need to be representative, and samples from key parts such as leaves and roots should be collected;

[0088] Carry out necessary processing on the collected physiological index samples, such as cleaning, drying and grinding, to facilitate biochemical analysis;

[0089] Analyze crop physiological indicators, including: chlorophyll content, which is measured by chlorophyll extraction and colorimetry to reflect the photosynthesis capacity of crops; photosynthetic rate, which is measured by portable photosynthesis meter to understand the carbon fixation capacity of crops; respiration, which is measured by measuring the respiration rate of crop leaves or whole plants to evaluate the energy metabolism of crops; enzyme activity, which is measured by measuring the enzyme activity related to crop stress resistance, such as catalase and superoxide dismutase; nutrient element content, which is measured by measuring the content of nutrient elements such as nitrogen, phosphorus and potassium in crops to evaluate the nutritional status of crops; water status, which is measured by measuring the relative water content of crop leaves or other water status indicators to understand the water status of crops;

[0090] According to the purpose of the test and the characteristics of the crop, select biochemical analysis methods such as enzyme activity determination, hormone content analysis, metabolite detection, proteomics analysis and transcriptomics analysis;

[0091] Use professional instruments and equipment such as spectrophotometers, chromatographs, mass spectrometers and gene sequencers to conduct biochemical analysis of crop samples according to standard operating procedures;

[0092] Organize the data obtained from biochemical analysis, including the measurement values, units and error ranges of various physiological indicators; according to the needs of pesticide efficacy evaluation, screen out physiological indicators that are closely related to the pesticide action mechanism and crop growth status changes to form a crop physiological indicator set;

[0093] Repeat the analysis of crop samples from the same batch or the same treatment group multiple times to verify the stability and reliability of the analysis results; use standard samples of known concentrations for control analysis to ensure the accuracy and sensitivity of the analysis method; review the collected physiological indicator samples, eliminate outliers or erroneous data, and ensure the accuracy and effectiveness of the crop physiological indicator collection;

[0094] The crop physiological index set is expressed in matrix form, including:

[0095]

[0096] Among them, C i represents the chlorophyll content measured for the i-th time; R i represents the photosynthetic rate measured at the i-th time; R i ′ represents the respiration measured at the ith time; A i represents the enzyme activity measured at the i-th time; N i represents the nutrient element content measured for the i-th time; W i Represents the moisture state of the i-th measurement.

[0097] By covering the determination of a variety of crop physiological indicators, including chlorophyll content, photosynthetic rate, respiration, enzyme activity, nutrient content and water status, the analysis results can fully reflect the physiological status of crops; by using professional instruments and equipment such as spectrophotometers, chromatographs, mass spectrometers and gene sequencers for analysis, high-precision data can be provided; by using standard samples of known concentrations for control analysis, the accuracy and sensitivity of the analysis method can be guaranteed; by repeatedly analyzing the crop samples of the same batch or the same treatment group, the reliability of the experimental results can be improved, and the consistency of the data can be verified by repeated experiments, which is convenient for identifying and eliminating the existing outliers or erroneous data; by combining enzyme activity determination, hormone content analysis, metabolite detection, proteomics analysis and transcriptomics analysis and other biochemical analysis methods, a systematic crop physiological indicator set is formed to deeply understand the biochemical process of crops; according to different detection purposes and crop characteristics, appropriate analysis methods are selected to improve the effectiveness and pertinence of the analysis; by reviewing the collected data, outliers or erroneous data are eliminated to ensure the accuracy and effectiveness of the crop physiological indicator set; by comprehensively measuring a variety of physiological indicators, using professional instruments to ensure accuracy, and enhancing the reliability of the results through repeated analysis and standard sample control.

[0098] S4, traversing the crop physiological indicator set, extracting abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtaining an abnormal physiological indicator set;

[0099] Step S4 requires traversing the crop physiological indicator set, extracting abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtaining an abnormal physiological indicator set; the details are as follows:

[0100] First, define the standard range of physiological indicators, including: standard range determination, the standard range of physiological indicators is determined based on a large amount of experimental data and existing research results, and the standard range reflects the normal fluctuation range of various physiological indicators of crops in a healthy state; literature review, consult relevant literature to understand the normal range of physiological indicators of different crops at different growth stages; expert consultation, consult experts in the field to obtain their opinions and suggestions; historical data, use historical data to determine the normal range through statistical analysis such as calculating the mean and standard deviation;

[0101] Construct standard ranges of physiological indicators and define standard ranges of physiological indicators of crops;

[0102] Traverse the crop physiological indicator set obtained in S3, where the crop physiological indicator set includes multiple physiological indicator values ​​obtained from each measurement;

[0103] Compare the standard value of each physiological indicator with its corresponding standard range of physiological indicators one by one. When a physiological indicator value exceeds the standard range, it is marked as an abnormal physiological indicator;

[0104] Collect all physiological indicators marked as abnormal to form an abnormal physiological indicator set;

[0105] When m measurements are taken, each measurement has n physiological indicators, and each physiological indicator has a preset standard range, which is [L j , U j ], where L j is the lower limit, U j is the upper limit;

[0106] The abnormal physiological indicator set is:

[0107] {(i,j,p ij )|p ij <L j ∨p ij >U j ,i=1,2,...,m;j=1,2,...,n};

[0108] Among them, (i,j,p ij ) represents the jth physiological index p measured at the i-th time ij , p ij <L j ∨p ij >U j Indicates p ij Exceeds the standard range of the jth physiological indicator.

[0109] By providing a set of systematic processes to identify and handle abnormal conditions in crop physiological indicators, and defining standard ranges, these standards are used to determine which indicators are considered abnormal; the standard ranges of physiological indicators are determined based on a large amount of experimental data and existing research results to ensure the scientificity and rationality of the standard ranges; the standard ranges of physiological indicators are determined through literature review, expert consultation, historical data analysis and other methods, and different aspects of theory and practice are comprehensively considered to improve the accuracy of range setting; the obtained crop physiological indicator sets are automatically traversed and compared to efficiently discover abnormal physiological indicators and reduce the workload of manual inspection; those physiological indicators that deviate from the normal range can be quickly identified to facilitate timely measures to deal with potential health problems or environmental pressures; through continuous monitoring and abnormality detection of physiological indicators, data support is provided for crop management to help make more scientific and reasonable decisions; by defining standard ranges of physiological indicators based on experimental data, literature, expert opinions and historical statistics, abnormal values ​​in crop physiological indicators are systematically identified, and data support for crop health status can be provided in a timely and accurate manner to facilitate rapid response and management decisions.

[0110] S5. In response to the abnormal physiological indicator set being an empty set, outputting the first efficacy detection result as the final pesticide preparation efficacy detection result;

[0111] Step S5 is to evaluate the abnormal physiological index set and decide whether further processing is needed or whether the preliminary drug efficacy test results are directly used as the final output; the details are as follows:

[0112] In step S4, the crop physiological indicator set is traversed, and all abnormal physiological indicators that exceed the preset physiological indicator standard range are extracted to form an abnormal physiological indicator set; after traversal, no abnormal physiological indicator is found, that is, the abnormal physiological indicator set is an empty set, all physiological indicators are within the normal range, and no abnormal phenomenon occurs;

[0113] In the case where the abnormal physiological indicator set is an empty set, step S5 directly uses the first efficacy test result obtained in step S2 as the final pesticide preparation efficacy test result output; so that: the efficacy analysis model is credible, because there are no abnormal physiological indicators, the result of the efficacy analysis model is considered to be credible; the efficacy is good, and the first efficacy test result shows that the pesticide is effective, so it is considered that the pesticide preparation has a good protective effect on crops under the test conditions and does not cause obvious side effects or adverse reactions; the process is simplified, and there is no need to further analyze the abnormal physiological indicators, which simplifies the entire detection process;

[0114] When the abnormal physiological indicator set is an empty set, the following operations are performed: the first efficacy test result obtained in step S2 is directly output as the final result; all relevant measurement data and analysis process records are retained for subsequent pesticide formulation evaluation, optimization or promotion and other decision-making processes.

[0115] When the set of abnormal physiological indicators is an empty set, the first efficacy test result is directly used as the final result to avoid unnecessary further analysis, saving time and resources; simplifying the detection process, reducing unnecessary steps, and being able to quickly draw conclusions in the absence of abnormal physiological indicators; since no abnormal physiological indicators were found, the results of the efficacy analysis model are considered credible; making the predictions of the efficacy analysis model consistent with the actual situation, increasing the credibility of the results; if the first efficacy test result shows that the pesticide is effective and has no side effects or adverse reactions, it is considered that the pesticide formulation does perform well under the test conditions and the evaluation results are accurate and reliable; retaining all relevant measurement data and analysis process records to ensure the traceability and transparency of the results for subsequent pesticide formulation evaluation, optimization or promotion and other decision-making processes; since there are no abnormal physiological indicators, it is considered that the pesticide formulation does not cause adverse reactions to crops during use, enhancing the safety and reliability of the pesticide; the retained measurement data and analysis process records provide a solid foundation for subsequent decision-making and help research personnel understand the effects of pesticides and provide references for future improvements; when pesticide formulations perform well and there are no abnormal physiological indicators, consider optimizing the formulation for promotion and use to improve the yield and quality of crops; by setting a standard range for physiological indicators and strictly testing in accordance with the standards, the testing process is standardized, which facilitates the promotion and use of the same method in different regions or on different crops and improves the consistency of testing; based on scientific data analysis and standard setting, the scientific nature of the test results is ensured, and the effects of pesticides are evaluated through scientific methods to avoid errors caused by subjective judgment; it is applicable to the testing of various pesticide formulations and has a wide range of practical value. The testing of pesticide formulations is used in the evaluation of newly developed pesticides or existing pesticides to improve the efficiency and accuracy of testing; when testing the efficacy of pesticide formulations, if no abnormal physiological indicators are found, the preliminary efficacy results are directly used, which has the advantages of high efficiency, accuracy and reliability, simplifies the process, saves time and resources, ensures the credibility of the results, and provides data support for subsequent decision-making, which is suitable for standardized and scientific evaluation of pesticide effects.

[0116] S6. In response to the presence of an abnormal physiological indicator in the abnormal physiological indicator set, the first efficacy detection result and the abnormal physiological indicator set are input into the pesticide efficacy evaluation system to obtain a second efficacy detection result, and the second efficacy detection result is output as the final pesticide preparation efficacy detection result;

[0117] In step S6, when an abnormal physiological indicator is detected in the abnormal physiological indicator set, the abnormal physiological indicator is combined with the preliminary efficacy test result, and the actual efficacy of the pesticide preparation is further evaluated through the pesticide efficacy evaluation system, and the final test result is obtained; specifically as follows:

[0118] First, a pesticide efficacy evaluation system is constructed, including:

[0119] Determine the main evaluation objectives, such as evaluating the control effect of pesticides on specific pests and diseases, crop safety or environmental impact, etc.; select appropriate efficacy evaluation indicators based on the evaluation purpose, including crop growth and development, pest and disease incidence, crop yield and pesticide residues;

[0120] Establish a data collection system to collect crop growth status data, environmental data, and necessary physiological and biochemical index data before and after the application of pesticides; clean, organize, and standardize the data to ensure the accuracy and comparability of the data;

[0121] According to the characteristics of the evaluation indicators and the requirements of the evaluation objectives, select appropriate mathematical models or algorithms to build evaluation models; such as multiple linear regression models, neural network models, decision tree models, etc. In the process of model design, consider the interaction and weight distribution between the evaluation indicators;

[0122] Combine the evaluation model with the data collection system to build a complete pesticide efficacy evaluation system; the pesticide efficacy evaluation system includes data collection, data processing, model calculation and result output modules to ensure the automation and standardization of the evaluation process;

[0123] The introduction of expert systems and knowledge bases provides professional support and knowledge reserves for the pesticide efficacy evaluation system; the expert system gives professional suggestions and improvement measures based on the evaluation results; the knowledge base contains professional knowledge on pesticide use, crop growth, and pest and disease control for reference and reference by the evaluation system;

[0124] Verify the pesticide efficacy evaluation system through field trials or laboratory experiments, select representative pesticide preparations and crop varieties, conduct experimental design and data collection according to the requirements of the pesticide efficacy evaluation system, compare and analyze the experimental results with the predicted results of the pesticide efficacy evaluation system, and evaluate the accuracy and reliability of the pesticide efficacy evaluation system;

[0125] According to the experimental verification results and feedback, the pesticide efficacy evaluation system is optimized and improved by adjusting the evaluation indicators, improving the model algorithm and perfecting the data collection system;

[0126] After the pesticide efficacy evaluation system is constructed, the crop physiological index set is traversed through step S4, and all abnormal physiological indexes that exceed the preset physiological index standard range are extracted to form an abnormal physiological index set. When abnormal physiological indexes are found after traversal, that is, the abnormal physiological index set is a non-empty set, which makes some physiological indexes exceed the normal range, and there are pesticides that have adverse effects on crops;

[0127] In the above case, the first efficacy test result and the set of abnormal physiological indicators are used as inputs and further input into the pesticide efficacy evaluation system to obtain a more detailed second efficacy test result; so that: the first efficacy test result and the abnormal physiological indicators are combined for comprehensive evaluation to ensure the accuracy of the final result and further analyze the abnormal physiological indicators to find out whether these abnormalities are related to the use of pesticides and their specific effects on crops;

[0128] The first efficacy test result and the abnormal physiological index set are input into the pesticide efficacy evaluation system as input data; after being processed by the pesticide efficacy evaluation system, the second efficacy test result is obtained, and this result is output as the final pesticide preparation efficacy test result.

[0129] The comprehensiveness of the evaluation results is ensured by comprehensively considering multiple indicators such as efficacy, crop growth and development, incidence of pests and diseases, crop yield and pesticide residues; the side effects or adverse effects that may be caused by pesticides are discovered in a timely manner by detecting abnormal physiological indicators; the pesticide efficacy evaluation system is based on a large amount of data collection and analysis to ensure the scientificity and reliability of the results; mathematical models or algorithms such as multivariate linear regression and neural networks are used to improve the accuracy and predictive ability of the evaluation; the pesticide efficacy evaluation system includes data collection, data processing, model calculation and result output modules to realize the automation of the evaluation process; through standardized data processing and model construction, the consistency and comparability of the evaluation results are ensured; through detailed experimental design and data analysis, the accurate evaluation of the pesticide effect is ensured; the detection of abnormal physiological indicators helps to discover potential problems and improve the accuracy of the evaluation; the evaluation system is verified through field trials or laboratory experiments, and it is continuously optimized and improved according to the results to ensure the evaluation system The reliability and effectiveness of the system; the introduction of expert systems and knowledge bases provide professional support and knowledge reserves for the evaluation system, enhancing reliability and authority; the pesticide efficacy evaluation system is adjusted according to different pesticide formulations and crop varieties, and has high adaptability and flexibility; through continuous optimization and improvement, the evaluation system is continuously expanded and improved to meet the needs of more application scenarios; the final pesticide formulation efficacy test results provide a scientific basis for the rational use of pesticides; the expert system gives professional suggestions and improvement measures based on the evaluation results, which is conducive to the optimization and improvement of pesticides; by evaluating the impact of pesticides on the environment, the safety of pesticide use is ensured, which is conducive to environmental protection and sustainable development; by constructing a pesticide efficacy evaluation system, a comprehensive evaluation is conducted in combination with abnormal physiological indicators and preliminary efficacy results to ensure the accuracy of the final results; the pesticide efficacy evaluation system includes target setting, data collection and processing, model construction and verification, to achieve automated and standardized evaluation, and improve the scientificity and reliability of detection.

[0130] Embodiment 2: Figure 3As shown, a pesticide preparation efficacy detection system of the present invention specifically includes the following modules:

[0131] A data collection module is used to collect real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application;

[0132] A preliminary efficacy analysis module is used to input the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result;

[0133] Physiological index analysis module, used to conduct real-time biochemical analysis of crops and obtain a set of crop physiological indicators;

[0134] An abnormality detection module is used to traverse the crop physiological indicator set, extract abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtain the abnormal physiological indicator set;

[0135] A result determination module, configured to output the first efficacy detection result as the final pesticide preparation efficacy detection result in response to the abnormal physiological indicator set being an empty set;

[0136] The comprehensive evaluation module is used to respond to the existence of abnormal physiological indicators in the abnormal physiological indicator set, input the first efficacy detection result and the abnormal physiological indicator set as input into the pesticide efficacy evaluation system, obtain the second efficacy detection result, and output the second efficacy detection result as the final pesticide preparation efficacy detection result.

[0137] The data acquisition module collects objective crop growth status data and environmental data, reduces the subjective errors caused by manual visual inspection in traditional methods, and improves the reliability of drug efficacy evaluation; through real-time acquisition of crop growth status and physiological indicators, the efficacy is dynamically monitored, possible problems or changing trends are discovered in time, and the accuracy of evaluation is improved; data processing and analysis are automatically completed by computers, which improves processing efficiency, shortens the time period from data collection to result output, and increases the speed of data processing and analysis; by considering the external growth of crops and combining the changes in internal physiological indicators, a more comprehensive drug efficacy test result is generated through the comprehensive evaluation module, which enhances the comprehensiveness and depth of the evaluation; by identifying abnormal Normal physiological indicators can be further analyzed in the presence of abnormalities to avoid misjudgment that may be caused by single indicator evaluation and improve the accuracy of efficacy evaluation; data and analysis processes are recorded digitally to facilitate backtracking and verification, thereby improving the credibility of research results; modular design can flexibly adapt to the needs of different types of pesticides and different crops, and is easy to upgrade and maintain; by incorporating growth environment data, the influence of environmental factors can be taken into account when evaluating efficacy, facilitating the development of pesticide formulations that are more suitable for specific environmental conditions; the pesticide formulation efficacy detection system improves the accuracy and efficiency of pesticide efficacy detection through comprehensive, real-time and intelligent data collection and analysis, providing technical support for agricultural production.

[0138] The various variations and specific embodiments of the pesticide preparation efficacy detection method in the aforementioned embodiment 1 are also applicable to the pesticide preparation efficacy detection system of this embodiment. Through the aforementioned detailed description of the pesticide preparation efficacy detection method, those skilled in the art can clearly know the implementation method of the pesticide preparation efficacy detection system of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0139] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0140] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting the efficacy of a pesticide preparation, characterized in that: The method comprises: Collecting real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application; Inputting the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result; Conduct real-time biochemical analysis of crops to obtain a set of crop physiological indicators; Traversing the crop physiological indicator set, extracting abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtaining the abnormal physiological indicator set; In response to the abnormal physiological indicator set being an empty set, outputting the first efficacy detection result as the final pesticide preparation efficacy detection result; In response to the presence of an abnormal physiological indicator in the abnormal physiological indicator set, the first efficacy detection result and the abnormal physiological indicator set are input into the pesticide efficacy evaluation system to obtain a second efficacy detection result, and the second efficacy detection result is output as the final pesticide preparation efficacy detection result.

2. A method for detecting the efficacy of a pesticide preparation according to claim 1, characterized in that: The method for setting the time length of the pesticide preparation to be detected comprises: Analyze the growth cycle and key development stages of target crops during their growth cycle; Consider the mechanism of action and effective time of different pesticides in the pesticide characteristics, and determine the time window when the pesticide begins to take effect; Monitor the temperature, humidity and light in the growth environment data and calculate the observation time; Based on the time window in which the pesticide begins to take effect and the observation time, determine the set time for the pesticide formulation to be tested.

3. A method for detecting the efficacy of a pesticide preparation as claimed in claim 1, characterized in that: The method for obtaining the first drug efficacy detection result includes: Clean all collected data to remove invalid data, missing values ​​and outliers; and standardize and normalize the cleaned data; Integrate initial growth status data, real-time growth status data and growth environment data to form a data set; According to the needs of pesticide efficacy analysis, the linear regression model is selected as the basic model of the pesticide efficacy analysis model; characteristic variables that affect efficacy evaluation are extracted from the integrated data set, and the characteristic variables include crop growth rate, leaf color change, soil moisture and temperature; historical data are collected and divided into training sets and test sets, and the pesticide efficacy analysis model is trained with the training set, and the generalization ability of the pesticide efficacy analysis model is verified with the test set; Input the preprocessed and integrated data into the trained pesticide efficacy analysis model; The pesticide efficacy analysis model calculates the impact of pesticides on crop growth status based on input data and outputs the first efficacy test result.

4. A method for detecting the efficacy of a pesticide preparation according to claim 1, characterized in that: The method for obtaining the crop physiological indicator set includes: Based on the set observation time, collect physiological index samples from crops, including leaves and roots; The collected physiological indicator samples are cleaned, dried and ground; Analyze crop physiological indicators, including chlorophyll content, photosynthetic rate, respiration, enzyme activity, nutrient content and water status; The physiological indicators obtained from biochemical analysis are sorted out to form a set of crop physiological indicators.

5. A method for detecting the efficacy of a pesticide preparation as claimed in claim 4, characterized in that: The crop physiological index set is expressed in matrix form, including: Among them, C i represents the chlorophyll content measured for the i-th time; R i represents the photosynthetic rate measured for the i-th time; R i ′ represents the respiration measured at the ith time; A i represents the enzyme activity measured at the i-th time; N i represents the nutrient element content measured for the i-th time; W i Represents the moisture state of the i-th measurement.

6. A method for detecting the efficacy of a pesticide preparation according to claim 1, characterized in that: The method for obtaining the abnormal physiological indicator set includes: Construct standard ranges of physiological indicators and define standard ranges of physiological indicators of crops; Iterate through the multiple physiological indicator values ​​obtained from each measurement in the acquired crop physiological indicator set; Compare each physiological indicator standard value with its corresponding physiological indicator standard range one by one, and mark the physiological indicator value that exceeds the standard range as an abnormal physiological indicator; All physiological indicators marked as abnormal are collected to form an abnormal physiological indicator set.

7. A method for detecting the efficacy of a pesticide preparation as claimed in claim 6, characterized in that: The abnormal physiological indicator set is: When m measurements are performed, each measurement has n physiological indicators, and each physiological indicator corresponds to a preset standard range, and the preset standard range is [L j , U j ], where L j is the lower limit of the jth physiological index, U j is the upper limit of the jth physiological index; the set of abnormal physiological indicators is: {(i,j,p ij )|p ij <L j ∨p ij >U j ,i=1,2,...,m;j=1,2,…,n}; Among them, (i,j,p ij ) represents the jth physiological index p measured at the i-th time ij , p ij <L j ∨p ij >U j Indicates p ij Exceeds the standard range of the jth physiological indicator.

8. A pesticide preparation efficacy detection system, characterized in that: The system comprises: A data collection module is used to collect real-time growth status data and growth environment data of crops after the pesticide formulation to be tested has been applied for a set period of time, as well as initial growth status data of crops before application; A preliminary efficacy analysis module is used to input the initial growth state data, the real-time growth state data and the growth environment data into the pesticide efficacy analysis model to obtain a first efficacy detection result; Physiological index analysis module, used to conduct real-time biochemical analysis of crops and obtain a set of crop physiological indicators; An abnormality detection module is used to traverse the crop physiological indicator set, extract abnormal physiological indicators that exceed the preset physiological indicator standard range, and obtain the abnormal physiological indicator set; A result determination module, configured to output the first efficacy detection result as the final pesticide preparation efficacy detection result in response to the abnormal physiological indicator set being an empty set; The comprehensive evaluation module is used to respond to the existence of abnormal physiological indicators in the abnormal physiological indicator set, input the first efficacy detection result and the abnormal physiological indicator set as input into the pesticide efficacy evaluation system, obtain the second efficacy detection result, and output the second efficacy detection result as the final pesticide preparation efficacy detection result.

9. An electronic device for detecting the efficacy of pesticide preparations, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are 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 steps in the method according to any one of claims 1 to 7 are implemented.

Images