A method and system for processing data of a paraquat aqueous solution test

Abstract

This application relates to the field of agricultural production data processing technology, and discloses a method and system for processing efficacy test data of diquat aqueous solution. The method includes: retrieving efficacy test records from a pre-set database, wherein the efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes; querying and retrieving corresponding environmental time reference data from a locally stored meteorological database based on the geographical location information and the application date; identifying application behavior characteristic words based on the agricultural notes; determining the application start time based on the application behavior characteristic words and the environmental time reference data; and converting the observation time information of each efficacy observation data within the same test batch into elapsed time relative to the application start time, using the application start time as a reference. This application can accurately determine the application start time, solving the problem of efficacy evaluation deviation caused by inconsistent time reference points in traditional methods.

Description

Technical Field

[0001] This application relates to the field of agricultural production data processing technology, and more specifically, to a method and system for processing efficacy test data of diquat aqueous solution. Background Technology

[0002] In agricultural production, to accurately evaluate the herbicidal effect of diquat aqueous solution formulations, it is usually necessary to conduct trials in different plots, under different weather and soil conditions, and continuously observe the growth status of weeds, record the spread of the herbicide after spraying, and track changes in the duration of effectiveness. In the data aggregation stage, the conventional approach is to aggregate datasets from different sources into a single location and organize them into a processable structure, while establishing relationships such as the same experimental batch, the same plot, the same treatment dosage, and the same observation object. Subsequently, data from different environmental conditions, different recording times, and different observation calibers need to be aligned and standardized using a unified expression method, such as a unified date format, unified units, unified scoring range, or mapping similar observations to the same field. However, in actual implementation, data related to changes in the duration of effectiveness often come from different batches and different recording habits, leading to numerous challenges in data processing. Inconsistent time reference points are a common problem; for example, some trials use the time of spraying completion as day zero, while others use midnight on the day of spraying as day zero, and still others use the first observation of weed wilting as the starting point. Inconsistent sampling frequencies are also prevalent. Furthermore, the time field is expressed inconsistently. For example, some records show 7 days after spraying, some show a specific date, and some show the second follow-up visit. Moreover, the follow-up interval varies depending on personnel arrangements. These differences will be amplified during the alignment and standardization phase because data aggregators often need to organize the time series of different batches into the same comparison framework before calculating the relevant indicators and conclusions regarding the duration of effectiveness.

[0003] When data volume increases or sources expand, processors often employ a fixed full-processing approach to quickly aggregate data, merging all records into the same structure before performing time alignment and indicator calculations. If the timeline definition differs significantly from the sampling point distribution, time alignment often requires selecting a specific alignment caliber or recalculating and resampling from a given starting point. If this selection is not explicitly locked and consistently implemented across batches, duration-of-efficacy curves may fail to splice, become incomparable, or be incorrectly shifted. Furthermore, time alignment failures can trigger a chain reaction of quality verification issues, such as the same batch being identified as missing, the same observation being misjudged as duplicate, or certain points being identified as outliers without determining whether the source is environmental or recording caliber differences. Ultimately, even if duration-of-efficacy indicators and comparative conclusions are output, inconsistencies may arise across environments and batches. During review, it becomes difficult to trace back to the time reference point and alignment rules used for each indicator, leading to a prolonged formulation optimization cycle and difficulty in reaching stable conclusions in environmental adaptability assessments. Accurately determining the start time of drug administration, i.e., the zero point, is crucial for accurately assessing drug efficacy. Traditional processing methods often rely on manually recorded application dates or vague time descriptions, leading to discrepancies in the zero-point time of test data from different batches. This makes it impossible to compare efficacy curves at a unified time reference point. Such minute deviations in the starting point can be amplified into significant efficacy errors, making it impossible to effectively compare efficacy data between different batches and potentially leading to erroneous assessment conclusions.

[0004] To address the aforementioned issues, existing technologies urgently need improvement. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application provides a method and system for processing efficacy test data of diquat aqueous solution, which has the advantage of being able to accurately determine the start time of application, thereby improving the accuracy of efficacy evaluation.

[0006] In a first aspect, this application provides a method for processing efficacy test data of diquat aqueous solution, including: Retrieve efficacy test records from a pre-set database. These records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. Based on geographical location information and application date, the corresponding environmental time reference data is retrieved by querying the locally stored meteorological database; Based on agricultural notes, characteristic words of pesticide application behavior were identified; Based on the vocabulary of drug application behavior characteristics and environmental time reference data, the drug application start time is determined; Based on the start time of drug application, the observation time information of each drug efficacy observation data within the same test batch is converted into elapsed time relative to the start time of drug application.

[0007] The above scheme can accurately determine the start time of drug administration by identifying drug administration behavior feature words in unstructured text information and combining them with environmental time reference data, thus solving the problem of drug efficacy evaluation deviation caused by inconsistent time reference points in traditional methods.

[0008] Furthermore, this application also proposes that the environmental time reference data include sunrise time, sunset time, and peak temperature time.

[0009] The above scheme provides specific environmental time reference data, offering richer and more accurate reference for determining the start time of pesticide application.

[0010] Furthermore, this application also proposes a step for identifying characteristic words of pesticide application behavior based on agricultural notes information, including: The agricultural notes are matched with preset word matching rules to identify time-oriented pesticide application behavior features from the agricultural notes. The preset word matching rules store pesticide application behavior features and their corresponding time period feature identifiers. The time period feature identifiers are used to indicate the relationship between the pesticide application time pointed to by the pesticide application behavior features and the sunrise time, sunset time, and peak temperature time.

[0011] The above scheme, through word matching rules and time period feature identification, effectively identifies and analyzes the time-related characteristics of pesticide application behavior words in unstructured agricultural notes.

[0012] Furthermore, this application also proposes that the time period feature identifier includes a first time period feature identifier and a second time period feature identifier; The first time period characteristic identifier is used to indicate whether the drug administration time is before or after sunrise or sunset; The second time period feature is used to indicate that the time of pesticide application coincides with the time of peak temperature.

[0013] The above scheme refines the types of time period feature identifiers, enabling a more accurate description of the relationship between application time and key environmental time points.

[0014] Furthermore, this application also proposes a step for determining the drug application start time based on drug application behavior characteristic vocabulary and environmental time reference data, including: If the drug administration time indicated by the drug administration behavior feature words is related to the sunrise or sunset time, then the drug administration start time is obtained by adding or subtracting the first preset time offset at the sunrise or sunset time according to the first time period feature identifier. If the application time indicated by the characteristic words of the application behavior is related to the peak temperature, then the peak temperature is determined as the start time of application according to the characteristic identifier of the second time period.

[0015] The above scheme provides two specific methods for determining the start time of drug application based on different time period characteristics, improving the flexibility and accuracy of the determination process.

[0016] Furthermore, this application also proposes a step for obtaining the drug application start time by adding or subtracting a first preset time offset from the sunrise or sunset time based on the first time period characteristic identifier, including: Calculate the solar altitude angle based on geographical location information and the date of application; Based on geographical location information and application date, the corresponding environmental information is retrieved by querying the locally stored meteorological database; The first preset time offset is corrected based on the solar altitude angle and environmental information to obtain the corrected first preset time offset. The drug administration start time is obtained by adding or subtracting the corrected first preset time offset at sunrise or sunset.

[0017] The above scheme incorporates solar altitude angle and environmental information to correct for time offset, making the determination of the start time of pesticide application more precise and in line with actual conditions.

[0018] Furthermore, this application also proposes that environmental information include wind speed, air humidity, and vegetation cover index.

[0019] The above scheme clarifies the specific content of environmental information, providing concrete data support for the correction of time offset.

[0020] Furthermore, this application also proposes a step of correcting the first preset time offset based on the solar altitude angle and environmental information to obtain the corrected first preset time offset, including: Based on solar altitude angle, wind speed, air humidity and vegetation coverage index, correction coefficients are calculated according to a preset environmental impact correction model. The first preset time offset is then corrected according to the correction coefficients to obtain the corrected first preset time offset.

[0021] The above scheme, through the environmental impact correction model, achieves intelligent correction of time offset, improving the accuracy and automation of the correction.

[0022] Furthermore, this application also proposes that the preset environmental impact correction model is a parameterized correction model calibrated based on historical efficacy test data.

[0023] The above scheme clarifies the source and nature of the modified model, ensuring its scientific validity and practicality.

[0024] Secondly, this application also proposes a data processing system for testing the efficacy of diquat aqueous solution, comprising: The test record acquisition module is used to retrieve efficacy test records from a preset database. The efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. The environmental time reference data acquisition module is used to query and obtain the corresponding environmental time reference data from a locally stored meteorological database based on geographical location information and application date. The pesticide application behavior feature vocabulary recognition module is used to identify pesticide application behavior feature vocabulary based on agricultural notes information; The application start time determination module is used to determine the application start time based on application behavior feature vocabulary and environmental time reference data; The time conversion module is used to convert the observation time information of each efficacy observation data in the same test batch into elapsed time relative to the start time of drug application, based on the start time of drug application.

[0025] As can be seen from the above, the method and system for processing efficacy test data of diquat aqueous solution provided in this application obtains efficacy test records from a preset database, obtains environmental time reference data based on geographical location information and application date, identifies application behavior characteristic words based on agricultural notes, and determines the application start time in combination with environmental time reference data. Finally, the observation time information of efficacy observation data is converted based on the application start time, which can accurately determine the application start time, thereby improving the accuracy of efficacy evaluation. It has the advantage of being able to accurately determine the application start time, thereby improving the accuracy of efficacy evaluation. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating a method for processing efficacy test data of diquat aqueous solution, as provided in an embodiment of this application.

[0027] Figure 2 This is a schematic diagram of a data processing system for testing the efficacy of diquat aqueous solution, provided in an embodiment of this application.

[0028] Labeling Explanation: 210 Test Record Acquisition Module; 220 Environmental Time Reference Data Acquisition Module; 230 Drug Application Behavior Feature Vocabulary Recognition Module; 240 Drug Application Start Time Determination Module; 250 Time Conversion Module. Detailed Implementation

[0029] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0030] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0031] In agricultural scientific research and production practice, accurate evaluation of herbicide efficacy is a crucial step in formulation optimization and scientific application. This is especially true for fast-acting contact herbicides like diquat, whose efficacy changes dramatically within hours of application, exhibiting a steep upward trend in the efficacy curve. This time sensitivity places extremely high demands on the accuracy of data recording. However, in actual field trials, efficacy test data often originates from different regions, batches, and is recorded by different field personnel, resulting in significant heterogeneity of data over time.

[0032] A common problem is the inconsistent way different trial records describe the timing of pesticide application. Some recorders note the specific date of application but omit the hour and minute; others tend to use vague natural language, such as writing in the agricultural notes that spraying was completed in the morning, after the dew dried, or before evening. When these diverse data are aggregated for unified analysis, data processors face a thorny challenge: how to determine a consistent and precise starting point for these efficacy observations.

[0033] If we roughly take midnight on the day of application as the common starting point for all data, then the efficacy curves of a trial applied at 7:00 AM and a trial applied at 5:00 PM will be forcibly aligned on the timeline, even though there is actually a physical time difference of up to ten hours between the two. For a pesticide like diquat, whose efficacy is measured in hours, this deviation is fatal and can lead to completely erroneous conclusions in efficacy evaluation. For example, it might lead to the incorrect judgment that a formulation has a slow onset of action, or an incorrect comparison of the duration of effect under different conditions. This data misalignment caused by inconsistent time reference points severely restricts the accuracy and reliability of efficacy evaluation and prolongs the development cycle of new formulations.

[0034] To address this technical challenge, this application provides a method for processing efficacy test data of diquat aqueous solution. Instead of relying on precise timestamps provided by recorders, it reverse-engineers seemingly unstructured agricultural notes in the records as clues to decipher the actual application time. By associating these textual descriptions, which contain elements of human behavior, with the objective and precisely calculable natural rhythms of the test site on the day of application, a minute-level application start time can be intelligently derived. This precisely reconstructed time serves as the unified zero point for all efficacy observation data in that batch, converting the time information of all observation data into elapsed time relative to this zero point. In this way, regardless of the original recording habits, efficacy data from all batches can be accurately projected onto the same physical timeline, enabling fair and accurate comparisons between different test data.

[0035] Specifically, see Figure 1 The method includes the following steps: S1. Obtain efficacy test records from a preset database. The efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. S2. Based on the geographical location information and the application date, query and obtain the corresponding environmental time reference data through the locally stored meteorological database; S3. Based on agricultural notes, identify characteristic words of pesticide application behavior; S4. Determine the start time of drug application based on the vocabulary of drug application behavior characteristics and environmental time reference data; S5. Based on the start time of drug application, convert the observation time information of each drug efficacy observation data in the same test batch into elapsed time relative to the start time of drug application.

[0036] First, efficacy test records are retrieved from a pre-set database. These records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. Next, based on the geographical location and application date, corresponding environmental time reference data is retrieved from a locally stored meteorological database. Then, based on the agricultural notes, characteristic words related to the application behavior are identified. Next, based on these characteristic words and the environmental time reference data, the application start time is determined. Finally, using the application start time as a baseline, the observation time information of each efficacy observation data point within the same test batch is converted into elapsed time relative to the application start time.

[0037] The acquired records are typically stored in a pre-set database, either entered by field personnel via a mobile application or imported in batches from files. Each record contains several key fields. The first is the geographical location of the application site. This information is crucial and can be in various formats, such as precise latitude and longitude coordinates, like 34.75 degrees North latitude and 113.66 degrees East longitude, or the national standard administrative division code, such as the code for a specific province, city, or county. Geographical location information is the fundamental basis for determining local natural environmental parameters. The second is the application date, recorded in a standard year-month-day format, such as July 15, 2023, used to pinpoint environmental changes within a specific day. The third, and the core of this method, is the unstructured text information of agricultural remarks. This is an open text field where field personnel can record any supplementary notes related to the current application. It was these seemingly casual words, such as spraying before the morning dew had dried, respraying during the midday heat, and completing the work on all plots before sunset, that provided valuable, implicit clues for accurately determining the timing of pesticide application.

[0038] After obtaining the raw records, the next step is to query and retrieve the corresponding environmental time reference data based on the geographical location information and application date in the records. This data serves as an objective physical world reference, providing a solid anchor for interpreting ambiguous agricultural notes. This data is typically obtained from a locally stored meteorological database that pre-stores historical and forecast meteorological and astronomical data from around the world. Alternatively, it can be obtained in real-time by accessing external meteorological services via a network interface.

[0039] Specifically, environmental time reference data includes sunrise, sunset, and peak temperature times. Sunrise and sunset are precisely calculated using astronomical algorithms based on geographical location and date, with an accuracy down to the second. These two times define two fundamental turning points in the daily changes in sunlight and are closely related to the timing of many agricultural activities; for example, farmers typically begin their work after sunrise and finish before sunset. Peak temperature refers to the moment when the temperature reaches its highest point during the day, usually occurring in the afternoon, such as around 2 PM. This time can also be determined through meteorological models and historical data analysis. It corresponds to certain agricultural activities, such as operations performed during periods of high temperature. These three time points together constitute an objective time coordinate system used to calibrate and locate events described in agricultural notes. The acquisition of environmental time reference data employs high-precision astronomical algorithms and local meteorological interpolation algorithms. The calculation of sunrise and sunset times is based on the geographical location's latitude and longitude coordinates, altitude, and a specific date. By solving the equations for solar declination and hour angle, the local time when the sun's center is 0.833 degrees below the horizon is determined. The peak temperature was determined by retrieving hourly temperature sequences from the five nearest meteorological stations at the application site, reconstructing the temperature change curve of that location using spline interpolation, and then extracting the extreme points where the first derivative of the curve is zero and the second derivative is negative.

[0040] With objective environmental and temporal reference data, the next crucial step is to analyze agricultural notes and identify characteristic words that characterize pesticide application behavior. This process is accomplished by matching agricultural notes with pre-defined word matching rules. A dedicated vocabulary database is pre-built and maintained, storing a large number of commonly used words or phrases related to pesticide application time; these are the characteristic words for pesticide application behavior. For example, words like "dew not yet dried," "morning dew," and "early morning" all point to the early morning period; words like "noon," "the sun is at its strongest," and "midday" point to the midday period; while words like "evening," "before sunset," and "before dark" point to the twilight period.

[0041] The pre-defined vocabulary matching rules not only store the vocabulary related to pesticide application behavior, but also associate each vocabulary with a corresponding time period feature identifier. This time period feature identifier is a structured label whose core function is to indicate the logical relationship between the pesticide application time indicated by the vocabulary and the objective reference points such as sunrise, sunset, and peak temperature obtained in the previous step. For example, for the vocabulary "dew not yet dried," its time period feature identifier might be defined as related to sunrise and located after sunrise. In this way, through matching and recognition, an unstructured natural language description is successfully transformed into structured information containing objective time references and logical relationships. For the unstructured text processing of agricultural notes, a multi-level semantic mapping matrix is ​​established to transform ambiguous time points in natural language into logical labels that can be recognized by machines. The vocabulary matching rules are not simple text searches, but a rule engine that includes a thesaurus and logical priority weights. For example, for the time period of early morning, the vocabulary matching rules store a series of related words including "dew," "morning," "sunrise," and "taking advantage of the cool weather." Each word is pre-assigned a time period feature identifier to determine how the word is associated with astronomical times. The time period feature identifiers are divided into two categories: absolute association and relative association. The first type of time period feature identifier uses offsets to lock in dynamic time points before or after sunrise or sunset, while the second type of time period feature identifier is directly aligned to the inflection point of local temperature changes.

[0042] Furthermore, to handle different types of application time descriptions, time period feature identifiers are subdivided into different categories. Specifically, time period feature identifiers include first time period feature identifiers and second time period feature identifiers. The first time period feature identifier indicates that the application time is before or after sunrise or sunset. This identifier is specifically used to handle descriptions that use sunrise or sunset as reference points, such as spraying after sunrise or finishing before sunset. The second time period feature identifier indicates that the application time coincides with the peak temperature. This identifier is used to handle descriptions that point to the hottest part of the day, such as midday re-spraying. Through this classification, different computational logic can be matched to the feature vocabulary of different types of application behaviors.

[0043] After identifying the characteristic terms of pesticide application and obtaining their corresponding time period characteristic identifiers, an accurate start time for pesticide application can be determined by combining environmental time reference data. This determination process follows clear calculation rules. If the pesticide application time indicated by the identified characteristic term is related to sunrise or sunset, that is, it is associated with the first time period characteristic identifier, then according to the identifier, a first preset time offset is added to or subtracted from the sunrise or sunset time to obtain the pesticide application start time. This preset time offset is an empirical value set based on agricultural experience and common sense about physics. For example, for the term "dew not yet dried," the time period characteristic identifier indicates that it occurs after sunrise, so a first preset time offset of 60 minutes can be set, and the pesticide application start time is calculated as the sunrise time of the day plus 60 minutes. Conversely, for "completed before sunset," the time period characteristic identifier indicates that it occurs before sunset, so a first preset time offset of 90 minutes can be set, and the pesticide application start time is calculated as the sunset time of the day minus 90 minutes.

[0044] On the other hand, if the identified pesticide application behavior feature words point to a pesticide application time that is related to the peak temperature time, i.e., they are associated with the second time period feature identifier, the processing method is more direct. Following the indication of the second time period feature identifier, the peak temperature time of the day is directly determined as the pesticide application start time. For example, for the term "noon re-spray," its time period feature identifier indicates that it coincides with the peak temperature time. If the peak temperature time of the day is found to be 2:00 PM, then 2:00 PM is determined as the pesticide application start time. A confidence check mechanism is also introduced into the logic for determining the pesticide application start time. When multiple conflicting words appear in agricultural notes, arbitration is conducted based on the semantic strength of the words. Time information with clear numerical expression has the highest priority. If only vague descriptions exist, descriptions related to the peak temperature are used first, followed by descriptions related to sunrise and sunset. This multi-level determination logic ensures that even in complex and non-standard agricultural records, physically meaningful zero points of time can still be extracted.

[0045] The final step is to use this precisely calculated application start time as a benchmark to convert the time information of all efficacy observation data within the same test batch into elapsed time relative to that application start time. For example, suppose the first efficacy observation time for plot one is recorded as 08:30:00 on July 16, 2023. After conversion, the time information for this observation point becomes 26 hours and 00 minutes after application. Similarly, if the first observation time for plot two is 18:30:00 on July 16, 2023, its converted time information will be 24 hours and 30 minutes after application.

[0046] Through this series of transformations, efficacy data from different plots and recorded by different personnel were unified onto a common timeline with the actual physical application point as the zero point. Researchers can directly compare the efficacy performance of two plots 24 hours after application when analyzing the data, without time discrepancies caused by the ambiguity of the original records. This greatly improves the accuracy and efficiency of efficacy evaluation for fast-acting pesticides like diquat, providing a reliable data foundation for formulation optimization and environmental adaptability assessment.

[0047] Furthermore, the steps of adding or subtracting a first preset time offset at sunrise or sunset based on the first time period characteristic identifier can be further refined as follows: First, calculate the solar altitude angle based on the geographical location information and the application date. Second, query and obtain the corresponding environmental information from the locally stored meteorological database based on the geographical location information and the application date. Then, correct the first preset time offset based on the solar altitude angle and the environmental information to obtain the corrected first preset time offset. Finally, add or subtract this corrected first preset time offset at sunrise or sunset to obtain the final application start time.

[0048] The first step in this correction process is to calculate the solar altitude angle. The solar altitude angle is an astronomical parameter precisely calculated based on geographical location, date, and specific time, directly determining the intensity of solar radiation received per unit area of ​​the Earth's surface. Solar radiation is the primary energy source driving surface water evaporation; therefore, the curve showing the change in the solar altitude angle is a fundamental physical quantity for assessing the rate of dew evaporation. The second step is to obtain more refined environmental information. This is not merely about macroscopic sunrise and sunset times, but rather microclimate parameters directly related to surface physical processes. Specifically, this environmental information includes wind speed, air humidity, and vegetation cover index. Wind speed describes the intensity of air movement at the surface; higher wind speeds indicate stronger air convection and faster diffusion of water molecules, thus accelerating evaporation. Air humidity, especially relative humidity, reflects the saturation level of water vapor in the air; higher humidity results in lower evaporation potential and a slower evaporation process. Vegetation cover indexes, such as the Normalized Difference Vegetation Index (NDDI) calculated from remote sensing satellite data, can quantify the density of surface vegetation. Dense vegetation can significantly slow down the evaporation of dew by blocking sunlight, obstructing airflow, and increasing local humidity.

[0049] After obtaining the solar altitude angle and this detailed environmental information, the first preset time offset can be corrected. This correction process is accomplished through a preset environmental impact correction model. Specifically, based on the solar altitude angle, wind speed, air humidity, and vegetation cover index, a correction coefficient is calculated according to the preset environmental impact correction model. Then, the first preset time offset is corrected based on this correction coefficient to obtain the corrected first preset time offset.

[0050] This environmental impact correction model is essentially a mathematical function or a set of logical rules used to quantify the comprehensive impact of various microenvironmental factors on the duration of physical processes, such as dew evaporation time. To ensure the model's accuracy and practicality, this pre-set environmental impact correction model is a parameterized correction model calibrated based on a large amount of historical efficacy test data. That is, by collecting experimental data from the past with known precise application times and corresponding microenvironmental conditions, the parameters in the model are trained and calibrated to best fit the relationship between environmental factors and the duration of physical processes in the real world. A parameterization scheme based on physical laws is adopted for the specific construction of the environmental impact correction model. The model is based on water evaporation dynamics, using a first pre-set time offset as the baseline duration. The calculation formula for the correction coefficient integrates multiple physical variables: the sine of the solar altitude angle determines the input intensity of radiative energy; the difference between wind speed and relative humidity determines the air's capacity to hold and transport water vapor; and the vegetation cover index corrects near-surface wind speed by adjusting surface roughness. The coefficients in the model are derived through regression analysis of over five thousand sets of historical efficacy test data from twenty different climate zones across the country. When specific environmental information is input, the model will dynamically output a correction coefficient between 0.3 and 3.0, thereby achieving fine-tuning of the offset.

[0051] Secondly, see Figure 2 This application also provides a data processing system for testing the efficacy of diquat aqueous solution, comprising: The test record acquisition module 210 is used to acquire efficacy test records from a preset database. The efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. The environmental time reference data acquisition module 220 is used to query and obtain the corresponding environmental time reference data from a locally stored meteorological database based on geographical location information and application date. The pesticide application behavior feature vocabulary recognition module 230 is used to identify pesticide application behavior feature vocabulary based on agricultural notes information; The application start time determination module 240 is used to determine the application start time based on the application behavior feature vocabulary and environmental time reference data; The time conversion module 250 is used to convert the observation time information of each efficacy observation data within the same test batch into elapsed time relative to the drug application start time, using the drug application start time as a reference. These modules work together to automate the aforementioned data processing method, enabling efficient and accurate time axis alignment of a large amount of heterogeneous efficacy test data.

[0052] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for processing efficacy test data of diquat aqueous solution, characterized in that, include: Retrieve efficacy test records from a pre-set database, wherein the efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes; Based on the geographical location information and the application date, the corresponding environmental time reference data is retrieved by querying the locally stored meteorological database; Based on the agricultural notes, characteristic words of pesticide application behavior were identified; Based on the vocabulary of the drug application behavior and the environmental time reference data, the drug application start time is determined; Based on the drug application start time, the observation time information of each drug efficacy observation data in the same test batch is converted into elapsed time relative to the drug application start time.

2. The method for processing efficacy test data of diquat aqueous solution according to claim 1, characterized in that, The environmental time reference data includes sunrise time, sunset time, and peak temperature time.

3. The method for processing efficacy test data of diquat aqueous solution according to claim 2, characterized in that, The step of identifying pesticide application behavior characteristic words based on the agricultural notes information includes: The agricultural notes are matched with preset word matching rules to identify time-oriented pesticide application behavior features from the agricultural notes. The preset word matching rules store the pesticide application behavior features and their corresponding time period feature identifiers. The time period feature identifiers are used to indicate the relationship between the pesticide application time pointed to by the pesticide application behavior features and the sunrise time, sunset time and temperature peak time.

4. The method for processing efficacy test data of diquat aqueous solution according to claim 3, characterized in that, The time period feature identifier includes a first time period feature identifier and a second time period feature identifier; The first time period feature identifier is used to indicate that the drug administration time is before or after the sunrise or sunset time; The second time period feature identifier is used to indicate that the application time coincides with the peak temperature time.

5. The method for processing efficacy test data of diquat aqueous solution according to claim 4, characterized in that, The step of determining the drug administration start time based on the drug administration behavior feature vocabulary and the environmental time reference data includes: If the drug application time indicated by the drug application behavior feature words is related to the sunrise time or the sunset time, then the drug application start time is obtained by adding or subtracting a first preset time offset from the sunrise time or the sunset time according to the first time period feature identifier. If the application time indicated by the application behavior feature words is related to the peak temperature time, then the peak temperature time is determined as the application start time according to the second time period feature identifier.

6. The method for processing efficacy test data of diquat aqueous solution according to claim 5, characterized in that, The step of obtaining the drug application start time by adding or subtracting a first preset time offset at the sunrise or sunset time according to the first time period feature identifier includes: Calculate the solar altitude angle based on the geographical location information and the application date; Based on the geographical location information and the application date, the corresponding environmental information is retrieved by querying the locally stored meteorological database; The first preset time offset is corrected based on the solar altitude angle and the environmental information to obtain the corrected first preset time offset. The drug application start time is obtained by adding or subtracting the corrected first preset time offset from the sunrise or sunset time.

7. The method for processing efficacy test data of diquat aqueous solution according to claim 6, characterized in that, The environmental information includes wind speed, air humidity, and vegetation cover index.

8. The method for processing efficacy test data of diquat aqueous solution according to claim 7, characterized in that, The step of correcting the first preset time offset based on the solar altitude angle and the environmental information to obtain the corrected first preset time offset includes: Based on the solar altitude angle, wind speed, air humidity, and vegetation coverage index, a correction coefficient is calculated according to a preset environmental impact correction model. The first preset time offset is then corrected according to the correction coefficient to obtain the corrected first preset time offset.

9. The method for processing efficacy test data of diquat aqueous solution according to claim 8, characterized in that, The preset environmental impact correction model is a parameterized correction model calibrated based on historical drug efficacy test data.

10. A data processing system for testing the efficacy of diquat aqueous solution, characterized in that, include: The test record acquisition module is used to acquire efficacy test records from a preset database. The efficacy test records include unstructured text information such as the geographical location of the application site, the application date, and agricultural notes. The environmental time reference data acquisition module is used to query and obtain the corresponding environmental time reference data from a locally stored meteorological database based on the geographical location information and the application date. The pesticide application behavior feature vocabulary recognition module is used to identify pesticide application behavior feature vocabulary based on the agricultural notes information. The application start time determination module is used to determine the application start time based on the application behavior feature words and the environmental time reference data; The time conversion module is used to convert the observation time information of each efficacy observation data in the same test batch into the elapsed time relative to the drug application start time, based on the drug application start time.

Images