Agricultural pest intelligent prediction method and system based on multi-source data fusion

Abstract

The application relates to the technical field of intelligent agriculture, and discloses an agricultural pest intelligent prediction method and system based on multi-source data fusion, which comprises an agricultural pest prediction multi-source information acquisition module, an agricultural pest prediction module and an agricultural pest prediction result feedback module; scientific modeling and prediction are carried out on the generation overlap state of all pest prediction time points based on pest accumulation information at a first pest prediction time point, meteorological forecast information at the pest prediction time point and interval length statistical information between pest prediction time points, the development trend of pests under natural conditions is accurately simulated, agricultural pest information is scientifically predicted based on agricultural pest monitoring information, agricultural meteorological forecast information and agricultural pest prediction time length, agricultural pest information is accurately predicted based on multi-source agricultural information, and the accuracy and precision of agricultural pest prediction are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart agriculture, in particular to an agricultural pest intelligent prediction method and system based on multi-source data fusion. BACKGROUND

[0002] Pest forecasting is a key link to guide the prevention and control of agricultural pests. Traditional pest forecasting methods mainly include development progress prediction method, period prediction method and effective accumulated temperature prediction method. However, these methods will consume a lot of manpower and material resources when conducting field investigation for a long time, and there are statistical difficulties when facing the problem of pest generation overlap, which makes it difficult to accurately predict the peak period of pests, resulting in lagging prevention and control measures or overuse of pesticides, which not only wastes resources but also may pollute the environment. With the rapid development of intelligent plant protection equipment, especially the application of intelligent pest monitoring lamps, real-time and continuous data support is provided for pest monitoring. The existing agricultural pest prediction cannot effectively integrate multi-source data, lacks dynamic modeling and prediction ability for pest generation overlap, and cannot realize the intelligentization and automation of the pest prediction process, which is difficult to meet the needs of modern plant protection equipment.

[0003] Chinese patent application with publication number CN117808620A and publication date of 2024.04.02 discloses a pest monitoring and early warning method, system, device and storage medium, which determines a monitoring area, obtains historical pest data in the monitoring area, and performs correlation analysis according to the historical pest data. The maximum pest impact factor is screened according to the correlation analysis result. Pest prediction is performed based on the maximum pest impact factor and a pre-constructed multi-level prediction model to predict the pest species and corresponding quantity, and monitoring and early warning are performed according to the pest prediction result. However, the above technical solution cannot perform scientific and accurate pest monitoring based on multi-source data such as pest monitoring data and weather forecast data. SUMMARY

[0004] (I) Technical problems to be solved

[0005] To solve the above problems that the existing agricultural pest prediction cannot effectively integrate multi-source data, lacks dynamic modeling and prediction ability for pest generation overlap, and cannot realize the intelligentization and automation of the pest prediction process, which is difficult to meet the needs of modern plant protection equipment, the above dynamic collection of pest prediction starting time point information, pest prediction time point information, starting time point pest monitoring information, pest prediction time point weather forecast information, accurate statistics of pest prediction time point interval length parameters, scientific analysis of pest prediction information at prediction time point, scientific statistics of pest cumulative information at prediction time point, and visual output of agricultural pest prediction result information are realized.

[0006] (II) Technical solutions

[0007] The application is implemented by the following technical scheme: an agricultural pest intelligent prediction method based on multi-source data fusion, which comprises the following steps:

[0008] S1, collecting pest prediction starting time point data, pest prediction time point data, starting time point pest monitoring text data and pest prediction time point weather forecast text data;

[0009] S2, performing interval duration numerical value statistical processing of each pest prediction time point according to the pest prediction starting time point data and the pest prediction time point data, and generating pest prediction time point interval duration statistical data;

[0010] S3, performing pest growth prediction processing of the first pest prediction time point based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and pest theoretical change text data under different agricultural conditions, and generating first pest prediction time point pest prediction text data;

[0011] S4, performing pest information accumulation processing of the first pest prediction time point according to the starting time point pest monitoring text data and the first pest prediction time point pest prediction text data, and generating first pest prediction time point pest accumulation text data;

[0012] S5, performing pest growth prediction processing of the second pest prediction time point according to the first pest prediction time point pest accumulation text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and pest theoretical change text data under different agricultural conditions, and generating second pest prediction time point pest prediction text data;

[0013] S6, performing pest information accumulation processing of the second pest prediction time point according to the first pest prediction time point pest accumulation text data and the second pest prediction time point pest prediction text data, generating second pest prediction time point pest accumulation text data, and repeatedly performing S5 and S6 until the pest prediction of all pest prediction time points is completed;

[0014] S7, constructing agricultural pest prediction result data and performing agricultural pest prediction result output operation.

[0015] Preferably, the operation steps of collecting pest prediction starting time point data, pest prediction time point data, starting time point pest monitoring text data and pest prediction time point weather forecast text data are as follows:

[0016] S11, collecting text information of the starting time point of agricultural pest prediction online through a data input dialog box of an agricultural pest prediction management platform, and generating pest prediction starting time point data , wherein is expressed in years, months, and days;

[0017] The text information of the prediction time point of the agricultural pest prediction is collected online through the data input dialogue box of the agricultural pest prediction management platform, and a pest prediction time point data set is generated , ; wherein represents the th pest prediction time point data, represents the maximum value of the number of pest prediction time points, wherein is expressed in years, months, and days;

[0018] The pest monitoring text information of the target agricultural area at the starting time point is collected online through the intelligent pest situation forecasting lamp, and starting time point pest monitoring text data is generated , the starting time point pest monitoring text data includes the pest species information, the development stage information of different types of pests, and the development stage type quantity information of different types of pests of the target agricultural area at the starting time point;

[0019] The meteorological forecast text information of the target agricultural area at the prediction time point is collected online through the meteorological prediction platform, and a pest prediction time point meteorological forecast text data set is generated , wherein represents the pest prediction time point data corresponding pest prediction time point meteorological forecast text data, the pest prediction time point meteorological forecast text data includes the average temperature, average humidity, and average precipitation of the target agricultural area at the prediction time point.

[0020] Preferably, according to the pest prediction starting time point data and the pest prediction time point data, the interval duration value of each pest prediction time point is statistically processed, and the operation steps of generating pest prediction time point interval duration statistical data are as follows:

[0021] S21, obtaining the pest prediction starting time point data and the pest prediction time point data set ;

[0022] S22, the pest prediction time point data in the pest prediction time point data set is sequentially numbered according to the pest prediction time point number and the previous time point, and the numerical difference measurement is processed, and a pest prediction time point interval duration statistical data set is generated , wherein represents the pest prediction time point data and the pest prediction starting time point data corresponding pest prediction time point interval duration statistical data; representing the pest prediction time point data corresponding to the pest prediction time point data corresponding pest prediction time point interval duration statistical data; representing the pest prediction time point data corresponding to the first pest prediction time point data corresponding pest prediction time point interval duration statistical data; representing the pest prediction time point data corresponding to the first pest prediction time point data corresponding pest prediction time point interval duration statistical data, wherein , , , and , , , The unit is hour.

[0023] Preferably, the operation steps of performing pest growth prediction processing at the first pest prediction time point based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and the theoretical change text data of pests under different agricultural conditions, and generating the first pest prediction time point pest prediction text data are as follows:

[0024] S31, establishing a set of theoretical change text data of pests under different agricultural conditions , ; wherein represents the theoretical change text data of pests under different agricultural conditions corresponding to the agricultural condition type, represents the maximum value of the number of agricultural condition types; the agricultural condition type represents an index data type for searching agricultural pest growth theory change information, which is mainly formed by combining agricultural pest monitoring information, agricultural weather forecast information and agricultural pest prediction duration information; the theoretical change text data of pests under different agricultural conditions represents agricultural pest growth theory change trend information under different agricultural condition types;

[0025] S32, the starting time point pest monitoring text data , the pest prediction time point weather forecast text data set the pest prediction time point weather forecast text data The statistical data set of the time intervals for pest prediction. The statistical data on the time intervals for pest prediction mentioned in the document Textual data set on the theoretical changes in pests under different agricultural conditions. Textual data on the theoretical changes in insect pests under different agricultural conditions described in the text. Character matching is performed on pest monitoring information, weather forecast information, and predicted time duration to search for pest monitoring text data that matches the stated start time point. The meteorological forecast text data for the pest prediction time points. The statistical data on the time intervals between the pest prediction points Matching textual data on the theoretical changes in pests under different agricultural conditions The data is then used to generate pest prediction text data for the first pest prediction time point, after data identification. ; Generate pest prediction text data for the first pest prediction time point. The specific operating steps are as follows:

[0026] S321. Initialize and update the maximum number of algorithm iterations T;

[0027] S322, Exploration Phase: This phase mainly involves the collection of textual data on the theoretical changes in pests under different agricultural conditions. Textual data on the theoretical changes in pests under different agricultural conditions in the search space Perform a global search and retrieve pest monitoring text data corresponding to the stated start time point. The meteorological forecast text data for the pest prediction time points. The statistical data on the time intervals between the pest prediction points Matching textual data on the theoretical changes in pests under different agricultural conditions The search mathematical formula is ,in This represents a random number within the interval (0,1). This indicates the probability that a specific gorilla will choose a migration mechanism to move to an unknown location. It is the first The next iteration searches for textual data sets on the theoretical changes in pests among individual gorillas under different agricultural conditions. Search the search space for pest monitoring text data corresponding to the starting time point. The meteorological forecast text data for the pest prediction time points. The statistical data on the time intervals between the pest prediction points Matching textual data on the theoretical changes in pests under different agricultural conditions Candidate positions; and represents the search gorilla searching the search space of the set of text data of theoretical changes of pest in the different agricultural conditions respectively represent the upper and lower boundaries of the search space; represents the search gorilla searching the search space of the set of text data of theoretical changes of pest in the different agricultural conditions respectively in the first iteration; represents the search gorilla searching the search space of the set of text data of theoretical changes of pest in the different agricultural conditions respectively matching the text data of pest monitoring at the starting time point , the text data of weather forecast at the pest prediction time point , the statistical data of interval length at the pest prediction time point ; represents the search gorilla searching the search space of the set of text data of theoretical changes of pest in the different agricultural conditions respectively in the first iteration; represents the search gorilla searching the search space of the set of text data of theoretical changes of pest in the different agricultural conditions respectively matching the text data of pest monitoring at the starting time point , the text data of weather forecast at the pest prediction time point , the statistical data of interval length at the pest prediction time point ; , , , rand respectively represents a random number in the range of (0, 1) updated by the algorithm iteration; , , represents the adjustment factor updated by the algorithm iteration; at the end of the exploration stage, the fitness value of all search gorillas is calculated, if the fitness value meets , , , the search gorilla is replaced by , the search gorilla generated by the exploration stage is regarded as the silver-backed search gorilla, i.e. the search gorilla searching the position of the set of text data of theoretical changes of pest in the different agricultural conditions respectively matching the text data of pest monitoring at the starting time point , the text data of weather forecast at the pest prediction time point , the statistical data of interval length at the pest prediction time point ;

[0028] ​​S323、development stage, the development stage adopts two behaviors of following silver-backed search gorillas and competing adult female search gorillas;

[0029] S3231、follow silver-backed search gorillas, if ≥ , the search gorilla individual selects the mechanism of following the silver-backed search gorilla, searches the different agricultural conditions under the theoretical change of pest text data in the search space of the starting time point pest monitoring text data , the weather forecast text data of the pest prediction time point , the interval duration statistical data of the pest prediction time point , the different agricultural conditions under the theoretical change of pest text data , wherein represents the algorithm iteration update adjustment factor, represents the weight factor of the search gorilla population selecting following silver-backed search gorillas and competing adult female search gorillas; the selection formula of following silver-backed search gorillas behavior simulation is , wherein represents the best candidate position of the different agricultural conditions under the theoretical change of pest text data searched by the silver-backed search gorilla individual in the search space of the starting time point pest monitoring text data , the weather forecast text data of the pest prediction time point , the interval duration statistical data of the pest prediction time point represents the control factor of simulating the behavior of following silver-backed search gorillas;

[0030] S3232、compete adult female, if < , the mechanism of following the competing adult female search gorilla is selected, the search gorilla individual entering puberty competes with other male search gorillas in the selection of adult females and searches the different agricultural conditions under the theoretical change of pest text data in the search space of the starting time point pest monitoring text data , the weather forecast text data of the pest prediction time point , the interval duration statistical data of the pest prediction time point , the different agricultural conditions under the theoretical change of pest text data , the competition behavior simulation formula is , wherein ​​Used to simulate the impact force of a male gorilla searching for prey. This is a coefficient vector representing the degree of violence in the conflict; at the end of the development phase, all coefficients are calculated. Search for the fitness value of individual gorillas. If the fitness value satisfies... > Then use Search for individual gorilla substitutes The search for individual gorillas, with the best male gorilla identified in this phase considered the silverback gorilla, is based on the textual data set of pest theory changes under the stated different agricultural conditions. Search the search space for pest monitoring text data corresponding to the starting time point. The meteorological forecast text data for the pest prediction time points. The statistical data on the time intervals between the pest prediction points Matching textual data on the theoretical changes in pests under different agricultural conditions ;

[0031] S324. If the maximum number of iterations T is satisfied, output the pest monitoring text data at the starting time point. The meteorological forecast text data for the pest prediction time points. The statistical data on the time intervals between the pest prediction points Matching textual data on the theoretical changes in pests under different agricultural conditions ;

[0032] S325. The text data on theoretical changes in pests under different agricultural conditions output in step S324 is... The first pest prediction text data was generated after data identification. The pest prediction text data at the first pest prediction time point represents the pest prediction start time point data. Corresponding agricultural pest forecast information.

[0033] Preferably, the steps for generating accumulated pest information at the first pest prediction time point by accumulating pest information based on the pest monitoring text data at the starting time point and the pest prediction text data at the first pest prediction time point are as follows:

[0034] S41. Obtain the pest monitoring text data at the starting time point. And the pest prediction text data at the first pest prediction time point ;

[0035] S42, Transfer the pest monitoring text data at the starting time point. The pest monitoring information and the pest prediction text data of the first pest prediction time point The pest prediction information is classified and counted according to the pest species and the development stages of different pest species, and the pest accumulation text data of the first pest prediction time point is generated .

[0036] Preferably, the operation steps of the pest growth prediction processing of the second pest prediction time point according to the pest accumulation text data of the first pest prediction time point, the weather forecast text data of the pest prediction time point, the interval duration statistical data of the pest prediction time point and the pest theoretical change text data under different agricultural conditions are as follows:

[0037] S51, obtaining the pest accumulation text data of the first pest prediction time point , the weather forecast text data set of the pest prediction time point , the interval duration statistical data set of the pest prediction time point ;

[0038] S52, using K-D tree nearest neighbor search algorithm to perform character matching on the pest monitoring information, the weather forecast information, and the prediction time duration, and search out the pest theoretical change text data under the different agricultural conditions which are matched with the pest accumulation text data of the first pest prediction time point , the weather forecast text data of the pest prediction time point , the interval duration statistical data of the pest prediction time point , the interval duration statistical data of the pest prediction time point , and the pest theoretical change text data under the different agricultural conditions , and generate the pest prediction text data of the second pest prediction time point through data identification . .

[0039] ​​​​​Preferably, the operation steps of accumulating the pest information at the second pest prediction time point according to the pest accumulation text data at the first pest prediction time point and the pest prediction text data at the second pest prediction time point, generating the pest accumulation text data at the second pest prediction time point and repeating the operation steps S5 and S6 until the pest prediction operation of all pest prediction time points is completed are as follows:

[0040] S61, the pest accumulation text data at the first pest prediction time point and the pest prediction text data at the second pest prediction time point

[0041] S62, the pest accumulation text data at the first pest prediction time point and the pest prediction information in the pest prediction text data at the second pest prediction time point are classified and counted according to the pest quantity of the pest species and the development stage of different pest species, and the pest accumulation text data at the second pest prediction time point is generated The operation steps of repeating S5 and S6 until the pest prediction operation of all pest prediction time points in the pest prediction time point data set is completed The pest prediction operation of all pest prediction time points corresponding to the pest prediction operation instruction is continued when the pest prediction operation of all pest prediction time points is not completed.

[0042] Preferably, the operation steps of constructing the agricultural pest prediction result data and performing the agricultural pest prediction result output operation are as follows:

[0043] S71, when the pest prediction operation of all pest prediction time points is completed, the pest prediction time point data generated in step S42 corresponding to the pest accumulation text data at the first pest prediction time point and the pest prediction result information of all pest prediction time points in the pest prediction time point data generated in step S62 are obtained

[0044] S72, the pest prediction result information of all pest prediction time points generated in step S71 is constructed into an agricultural pest prediction result data set through data identification , wherein represents the pest prediction time point data corresponding to the agricultural pest prediction result data

[0045] ​S73、collecting the generated agricultural pest prediction result data set the agricultural pest prediction result data to According to the prediction time point number, the pest prediction result display output job is carried out through the office software, and the office software includes any one of WPS word, WPS table and WPS demonstration.

[0046] The agricultural pest intelligent prediction system based on multi-source data fusion is used to realize the agricultural pest intelligent prediction method based on multi-source data fusion, and the system includes an agricultural pest prediction multi-source information acquisition module, an agricultural pest prediction module and an agricultural pest prediction result feedback module.

[0047] The agricultural pest prediction multi-source information acquisition module includes a pest prediction starting time point acquisition unit, a pest prediction time point acquisition unit, a starting time point pest monitoring information acquisition unit, a pest prediction time point meteorological forecast information acquisition unit and a pest prediction time point interval length statistical unit.

[0048] The pest prediction starting time point acquisition unit collects pest prediction starting time point data through an agricultural pest prediction management platform; the pest prediction time point acquisition unit collects pest prediction time point data through the agricultural pest prediction management platform; the starting time point pest monitoring information acquisition unit collects starting time point pest monitoring text data through an intelligent pest situation forecasting lamp; the pest prediction time point meteorological forecast information acquisition unit collects pest prediction time point meteorological forecast text data through a meteorological prediction platform; and the pest prediction time point interval length statistical unit performs interval length numerical statistical processing on each pest prediction time point according to the pest prediction starting time point data and the pest prediction time point data, and generates pest prediction time point interval length statistical data.

[0049] The agricultural pest prediction module includes a different agricultural condition pest theoretical change information storage unit, a first pest prediction time point pest prediction information analysis unit, a first pest prediction time point pest accumulation information statistical unit, a pest prediction time point pest prediction information analysis unit and a pest prediction time point pest accumulation information statistical unit.

[0050] The different agricultural condition pest theoretical change information storage unit is used for storing different agricultural condition pest theoretical change text data;The first pest prediction time point pest prediction information analysis unit carries out first pest prediction time point pest growth prediction processing based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and different agricultural condition pest theoretical change text data, and generates first pest prediction time point pest prediction text data;The first pest prediction time point pest accumulation information statistical unit carries out first pest prediction time point pest information accumulation processing according to the starting time point pest monitoring text data and the first pest prediction time point pest prediction text data, and generates first pest prediction time point pest accumulation text data;The pest prediction time point pest prediction information analysis unit carries out second pest prediction time point pest growth prediction processing according to the first pest prediction time point pest accumulation text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and different agricultural condition pest theoretical change text data, and generates second pest prediction time point pest prediction text data;The pest prediction time point pest accumulation information statistical unit carries out second pest prediction time point pest information accumulation processing according to the first pest prediction time point pest accumulation text data and the second pest prediction time point pest prediction text data, generates second pest prediction time point pest accumulation text data, and continues to execute remaining pest prediction time point pest prediction operation until all pest prediction time point pest prediction operation is completed;

[0051] The agricultural pest prediction result feedback comprises an agricultural pest prediction result acquisition unit and an agricultural pest prediction result output unit.

[0052] The agricultural pest prediction result acquisition unit constructs agricultural pest prediction result data based on all pest prediction time point pest prediction information combination data processing;The agricultural pest prediction result output unit executes agricultural pest prediction result output operation according to the agricultural pest prediction result data and in combination with office software.

[0053] (Three) beneficial effects

[0054] The present application provides an agricultural pest intelligent prediction method and system based on multi-source data fusion, which has the following beneficial effects:

[0055] I. Through the agricultural pest prediction management platform, the starting time point of pest prediction and the pest prediction time point are accurately collected, the agricultural pest prediction time range is efficiently collected, the starting time point of pest prediction is reliably collected through the intelligent pest situation forecasting lamp and the meteorological prediction platform, the meteorological forecast information of the pest prediction time point is efficiently and scientifically collected, the interval time between the pest prediction starting time point and the pest prediction time point is efficiently counted according to the pest prediction starting time point parameter and the pest prediction time point parameter, the agricultural pest information is scientifically predicted based on the agricultural pest monitoring information, the agricultural meteorological forecast information and the agricultural pest prediction time length, and the agricultural pest information is accurately predicted based on the multi-source agricultural information.

[0056] II. The first pest prediction time point pest development trend is intelligently predicted by combining the starting time point pest monitoring information, the pest prediction time point meteorological forecast information, the pest prediction time point interval time length statistical information, the artificial intelligence recognition algorithm and the scientifically established pest theoretical change information under different agricultural conditions, the first pest prediction time point pest information is scientifically accumulated according to the starting time point pest monitoring information and the first pest prediction time point pest prediction information, the first pest prediction time point agricultural pest generation overlap state is scientifically modeled and predicted, the first pest prediction time point pest accumulation information, the pest prediction time point meteorological forecast information and the pest prediction time point interval time length statistical information are combined to scientifically model and predict the agricultural pest generation overlap state at all pest prediction time points, the development trend of the agricultural pest under the natural state of the agricultural pest is accurately simulated, and the accuracy and precision of the agricultural pest prediction are improved.

[0057] III. The agricultural pest prediction result information is constructed based on the pest prediction information at all pest prediction time points combined with data processing, the digitalization of the agricultural pest prediction result is reliably collected, the agricultural pest prediction result is output according to the time characteristics, the development trend of the agricultural pest is intuitively and visually fed back, and the intuitiveness and applicability of the agricultural pest prediction are improved. BRIEF DESCRIPTION OF DRAWINGS

[0058] Fig. 1 A module schematic diagram of the agricultural pest intelligent prediction system based on multi-source data fusion provided by the present application is provided.

[0059] Fig. 2 A flowchart of the agricultural pest intelligent prediction method based on multi-source data fusion provided by the present application is provided. DETAILED DESCRIPTION

[0060] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the protection scope of the present application.

[0061] The implementation of the agricultural pest intelligent prediction method and system based on multi-source data fusion is as follows:

[0062] Embodiment 1:

[0063] Please refer to Figs. 1-2 The agricultural pest intelligent prediction method based on multi-source data fusion comprises the following steps:

[0064] S1, collecting pest prediction starting time point data, pest prediction time point data, starting time point pest monitoring text data and pest prediction time point weather forecast text data;

[0065] S2, performing interval time length numerical statistical processing of each pest prediction time point according to the pest prediction starting time point data and the pest prediction time point data, to generate pest prediction time point interval time length statistical data;

[0066] S3, performing pest growth prediction processing of the first pest prediction time point based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval time length statistical data and the pest theoretical change text data under different agricultural conditions, and generating first pest prediction time point pest prediction text data;

[0067] S4, performing pest information accumulation processing of the first pest prediction time point according to the starting time point pest monitoring text data and the first pest prediction time point pest prediction text data, to generate first pest prediction time point pest accumulation text data;

[0068] S5, performing pest growth prediction processing of the second pest prediction time point according to the first pest prediction time point pest accumulation text data, the pest prediction time point weather forecast text data, the pest prediction time point interval time length statistical data and the pest theoretical change text data under different agricultural conditions, and generating second pest prediction time point pest prediction text data;

[0069] S6, performing pest information accumulation processing of the second pest prediction time point according to the first pest prediction time point pest accumulation text data and the second pest prediction time point pest prediction text data, to generate second pest prediction time point pest accumulation text data, and repeating S5 and S6 until the pest prediction work of all pest prediction time points is completed;

[0070] S7, construct the agricultural pest prediction result data and perform the agricultural pest prediction result output job.

[0071] Further, please refer to Figs. 1-2 , the operation steps of collecting pest prediction starting time point data, pest prediction time point data, starting time point pest monitoring text data and pest prediction time point weather forecast text data are as follows:

[0072] S11, collect the text information of the starting time point of the agricultural pest prediction online through the data input dialog box of the agricultural pest prediction management platform, and generate pest prediction starting time point data , wherein The unit is year, month and day;

[0073] Collect the text information of the prediction time point of the agricultural pest prediction online through the data input dialog box of the agricultural pest prediction management platform, and generate a set of pest prediction time point data , ; wherein Represents the Pest prediction time point data, Represents the maximum value of the number of pest prediction time points, wherein The unit is year, month and day;

[0074] Collect the text information of the starting time point of the target agricultural area through the intelligent pest monitoring and forecasting lamp, and generate starting time point pest monitoring text data , the starting time point pest monitoring text data includes the pest species information, the development stage information of different types of pests and the development stage type quantity information of different types of pests of the target agricultural area at the starting time point;

[0075] Collect the weather forecast text information of the target agricultural area at the prediction time point online through the weather forecast platform, and generate a set of pest prediction time point weather forecast text data , wherein Represents the pest prediction time point data The corresponding pest prediction time point weather forecast text data, the pest prediction time point weather forecast text data includes the average temperature, the average humidity and the average precipitation of the target agricultural area at the prediction time point.

[0076] According to the pest prediction starting time point data and the pest prediction time point data, the interval time length statistical data of each pest prediction time point is generated. The operation steps are as follows:

[0077] S21, obtain pest prediction starting time point data And pest prediction time point data set ;

[0078] S22, the pest prediction time point data set Pest prediction time point data According to the pest prediction time point number order and the previous time point, the numerical difference is measured and processed, and the pest prediction time point interval duration statistical data set is generated , wherein The pest prediction time point data The pest prediction starting time point data The corresponding pest prediction time point interval duration statistical data The pest prediction time point data The pest prediction time point data The corresponding pest prediction time point interval duration statistical data The pest prediction time point data The first Pest prediction time point data The corresponding pest prediction time point interval duration statistical data The pest prediction time point data The first Pest prediction time point data The corresponding pest prediction time point interval duration statistical data, wherein , , , And , , , The unit of is hour.

[0079] Through the cooperation of the pest prediction starting time point collection unit and the pest prediction time point collection unit, the pest prediction starting time point and the pest prediction time point are accurately collected based on the agricultural pest prediction management platform; The agricultural pest prediction time range is efficiently collected; The starting time point pest monitoring information collection unit and the pest prediction time point weather forecast information collection unit cooperate with each other, and respectively through the intelligent pest monitoring lamp and the weather forecast platform, the starting time point agricultural starting pest state information is reliably collected, and the pest prediction time point weather forecast information is efficiently and scientifically collected; The pest prediction time point interval duration statistical unit efficiently counts the interval duration between the pest prediction starting time point parameters and the pest prediction time point parameters, realizes the scientific prediction of agricultural pest information based on agricultural pest monitoring information, agricultural weather forecast information and agricultural pest prediction time length, and realizes the accurate prediction of agricultural pest information based on multi-source agricultural information.

[0080] Further, please refer to Figs. 1-2 , the operation steps of the pest growth prediction processing of the first pest prediction time point based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and the pest theoretical change text data under different agricultural conditions are as follows:

[0081] S31, establish a set of pest theoretical change text data under different agricultural conditions , ; wherein represents the pest theoretical change text data under different agricultural conditions corresponding to the th agricultural condition type, represents the maximum value of the number of agricultural condition types; the agricultural condition type represents an index data type for searching agricultural pest growth theoretical change information, which is mainly formed by combining agricultural pest monitoring information, agricultural weather forecast information and agricultural pest prediction duration information; the pest theoretical change text data under different agricultural conditions represents the agricultural pest growth theoretical change trend information under different agricultural condition types;

[0082] S32, the starting time point pest monitoring text data , the pest prediction time point weather forecast text data set , the pest prediction time point weather forecast text data , the pest prediction time point interval duration statistical data set , the pest prediction time point interval duration statistical data and the pest theoretical change text data under different agricultural conditions in the set of pest theoretical change text data under different agricultural conditions are matched by characters of pest monitoring information, weather forecast information and prediction time duration, and the pest theoretical change text data under different agricultural conditions , the pest prediction time point weather forecast text data , the pest prediction time point interval duration statistical data which are matched with the starting time point pest monitoring text data , the pest prediction time point weather forecast text data , the pest prediction time point interval duration statistical data are searched out, and the first pest prediction time point pest prediction text data is generated through data identification; the specific operation steps of generating the first pest prediction time point pest prediction text data

[0083] are as follows:

[0084] S322, the exploration stage, the stage is mainly to search the different agricultural conditions under the theoretical change of pest text data set of search space in different agricultural conditions under the theoretical change of pest text data Global search, and search out with the starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistics data Match different agricultural conditions under the theoretical change of pest text data , search mathematical formula is , wherein Indicates a random number in the value (0, 1) interval, Indicates the probability of determining the search gorilla individual migration mechanism to the unknown position; Is the Time iteration search gorilla individual in the search space of different agricultural conditions under the theoretical change of pest text data set Search out with the starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistics data Match different agricultural conditions under the theoretical change of pest text data Candidate position; And Indicate the upper and lower boundaries of search gorilla in the search space of different agricultural conditions under the theoretical change of pest text data set ; Indicates the Time iteration search gorilla individual in the search space of different agricultural conditions under the theoretical change of pest text data set Search out with the starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistics data Match different agricultural conditions under the theoretical change of pest text data Candidate position; Indicates the Time iteration search gorilla individual in the search space of different agricultural conditions under the theoretical change of pest text data set Search out with the starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistics data The different agricultural conditions under the theory of the change of the matching pest text data ; , , , rand respectively represent the random number in the value (0, 1) interval updated by the algorithm iteration; , , Indicate the adjustment factor of the algorithm iteration update; at the end of the exploration stage, calculate all The fitness value of the search gorilla individual, if the fitness value meets ﹥ , use The search gorilla individual replaces The search gorilla individual produced in the exploration stage is regarded as the silver-backed search gorilla, that is, the search space of the different agricultural conditions under the theory of the change of the matching pest text data set The starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistical data The different agricultural conditions under the theory of the change of the matching pest text data Position;

[0085] S323, development stage, the development stage adopts two behaviors of following the silver-backed search gorilla and competing with the adult female search gorilla;

[0086] S3231, follow the silver-backed search gorilla, if ≥ , the search gorilla individual selects the mechanism of following the silver-backed search gorilla, and searches the different agricultural conditions under the theory of the change of the matching pest text data set The starting time point pest monitoring text data , pest prediction time point weather forecast text data , pest prediction time point interval length statistical data The different agricultural conditions under the theory of the change of the matching pest text data , wherein Indicates the adjustment factor of the algorithm iteration update, Indicates the weight factor of the search gorilla population selecting the silver-backed search gorilla and competing with the adult female search gorilla; the selection formula of the behavior of following the silver-backed search gorilla is , wherein Indicates the search space of the different agricultural conditions under the theory of the change of the matching pest text data set The starting time point pest monitoring text data , weather forecast text data at pest prediction time point , interval duration statistical data between pest prediction time points , different agricultural conditions matched theoretical change text data of pests , the best candidate position; , control factors representing the behavior of silverback gorilla simulation following;

[0087] S3232, competing adult females, if < , the search gorilla mechanism of selecting to follow the competing adult female, the search gorilla individual entering puberty competes with other male search gorillas in the selection of adult females and searches in the search space of the different agricultural conditions matched theoretical change text data set of pests at the starting time point , weather forecast text data at pest prediction time point , interval duration statistical data between pest prediction time points , different agricultural conditions matched theoretical change text data of pests , the competition behavior simulation calculation formula is , wherein is used to simulate the impact of male search gorillas, is a coefficient vector of the degree of violence in the conflict; at the end of the development stage, the fitness values of all search gorilla individuals are calculated, if the fitness value meets > , the search gorilla individual is used to replace the search gorilla individual, and the optimal male search gorilla generated in this stage is regarded as a silverback search gorilla, i.e., the different agricultural conditions matched theoretical change text data set of pests searched in the search space , weather forecast text data at pest prediction time point , interval duration statistical data between pest prediction time points , different agricultural conditions matched theoretical change text data of pests ;

[0088] S324, meeting the maximum iteration number T, outputting the different agricultural conditions matched theoretical change text data of pests , weather forecast text data at pest prediction time point , interval duration statistical data between pest prediction time points , different agricultural conditions matched theoretical change text data of pests ;

[0089] S325, the different agricultural conditions under the pest theoretical change text data output in step S324 After data identification, generate the first pest prediction time point pest prediction text data , wherein the first pest prediction time point pest prediction text data represents the pest prediction time point data Corresponding agricultural pest prediction information.

[0090] According to the starting time point pest monitoring text data, the first pest prediction time point pest prediction text data, the first pest prediction time point pest information accumulation processing is generated, and the operation steps of the first pest prediction time point pest accumulation text data are as follows:

[0091] S41, obtain the starting time point pest monitoring text data And the first pest prediction time point pest prediction text data ;

[0092] S42, the starting time point pest monitoring text data The pest monitoring information in the first pest prediction time point pest prediction text data The pest prediction information is classified and accumulated according to the pest species, the number of pests in different stages of development, and the first pest prediction time point pest accumulation text data is generated .

[0093] According to the first pest prediction time point pest accumulation text data, the pest prediction time point weather forecast text data, the pest prediction time point interval length statistical data and the different agricultural conditions under the pest theoretical change text data, the second pest prediction time point pest growth prediction processing is carried out, and the operation steps of generating the second pest prediction time point pest prediction text data are as follows:

[0094] S51, obtain the first pest prediction time point pest accumulation text data , the pest prediction time point weather forecast text data set , the pest prediction time point interval length statistical data set ;

[0095] S52, using K-D tree nearest neighbor search algorithm, the first pest prediction time point pest accumulation text data , the pest prediction time point weather forecast text data set The pest prediction time point weather forecast text data in the first pest prediction time point pest accumulation text data , the pest prediction time point interval length statistical data set The pest prediction time point interval length statistical data in the first pest prediction time point pest accumulation text data And the different agricultural conditions under the pest theoretical change text data set theoretical change text data of insect pests under different agricultural conditions character matching is performed on the insect pest monitoring information, the weather forecast information, and the prediction time length, and the insect pest accumulation text data corresponding to the first insect pest prediction time point is searched out , the weather forecast text data at the insect pest prediction time point , the interval length statistical data between the insect pest prediction time points theoretical change text data of insect pests under different agricultural conditions , and the second insect pest prediction text data at the second insect pest prediction time point is generated through data marking .

[0096] The operation steps of the insect pest information accumulation processing at the second insect pest prediction time point according to the first insect pest prediction time point insect pest accumulation text data and the second insect pest prediction time point insect pest prediction text data are as follows:

[0097] S61, the first insect pest prediction time point insect pest accumulation text data and the second insect pest prediction time point insect pest prediction text data

[0098] S62, the insect pest prediction information in the first insect pest prediction time point insect pest accumulation text data and the insect pest prediction information in the second insect pest prediction time point insect pest prediction text data are classified and counted according to the insect pest species and the development stages of different species of insect pests, the insect pest accumulation text data at the second insect pest prediction time point is generated through accumulation processing, and the operation steps are as follows: S63, the insect pest prediction time point data in the insect pest prediction time point data set is executed to all the insect pest prediction time points corresponding to the insect pest prediction operation instruction.

[0099] The pest prediction information analysis unit at the first pest prediction time point intelligently predicts the pest development trend at the first pest prediction time point based on pest monitoring information at the initial time point, meteorological forecast information at the pest prediction time point, and statistical information on the interval duration of pest prediction time points, combined with artificial intelligence recognition algorithms and scientifically established theoretical information on pest changes under different agricultural conditions. The pest accumulation information statistics unit at the first pest prediction time point scientifically accumulates pest information at the first pest prediction time point based on pest monitoring information at the initial time point and pest prediction information at the first pest prediction time point, realizing scientific modeling and prediction of the overlapping state of agricultural pest generations at the first pest prediction time point. The pest prediction information analysis unit and the pest accumulation information statistics unit at the pest prediction time point work together to scientifically model and predict the overlapping state of agricultural pest generations at all pest prediction time points based on the accumulated pest information at the first pest prediction time point, meteorological forecast information at the pest prediction time point, and statistical information on the interval duration of pest prediction time points, achieving accurate simulation of the pest development trend under the natural state of agricultural pests and improving the accuracy and precision of agricultural pest prediction.

[0100] For further details, please refer to Figs. 1-2 The steps for constructing agricultural pest prediction data and executing the agricultural pest prediction result output operation are as follows:

[0101] S71. When the pest prediction work for all pest prediction time points is completed, obtain the pest prediction time point data generated in step S42. Corresponding to the first pest prediction time point, the cumulative pest text data Step S62 generates pest prediction time point data. to Information on pest prediction results at all pest prediction time points;

[0102] S72. Transfer the pest prediction time point data obtained in step S71. to The pest forecast results for all pest forecast time points were used to construct an agricultural pest forecast result dataset after data identification. ,in Indicates the time point data for pest forecasting Corresponding agricultural pest forecast data;

[0103] S73. Generate the agricultural pest prediction result data set Agricultural pest forecasting results data to The pest forecast results should be displayed and output using office software, including any one of WPS Writer, WPS Spreadsheet, and WPS Presentation, according to the predicted time point number.

[0104] The agricultural pest prediction result acquisition unit acquires the agricultural pest prediction result information based on the pest prediction information at all pest prediction time points and data processing, realizes digital and reliable collection of the agricultural pest prediction result, and the agricultural pest prediction result output unit outputs the agricultural pest prediction result based on the agricultural pest prediction result information and in combination with office software, performs the agricultural pest prediction result output operation, and realizes intuitive and visual feedback of the pest development trend according to the time characteristics of the agricultural pest prediction result, and improves the intuitiveness and applicability of the agricultural pest prediction.

[0105] Embodiment 2:

[0106] Please refer to Figs. 1-2 , the agricultural pest intelligent prediction system based on multi-source data fusion is used to realize the agricultural pest intelligent prediction method based on multi-source data fusion, and the system comprises an agricultural pest prediction multi-source information acquisition module, an agricultural pest prediction module, and an agricultural pest prediction result feedback module.

[0107] The agricultural pest prediction multi-source information acquisition module comprises a pest prediction starting time point acquisition unit, a pest prediction time point acquisition unit, a starting time point pest monitoring information acquisition unit, a pest prediction time point meteorological forecast information acquisition unit, and a pest prediction time point interval duration statistical unit.

[0108] The pest prediction starting time point acquisition unit acquires pest prediction starting time point data through the agricultural pest prediction management platform, the pest prediction time point acquisition unit acquires pest prediction time point data through the agricultural pest prediction management platform, the starting time point pest monitoring information acquisition unit acquires starting time point pest monitoring text data through the intelligent pest monitoring lamp, the pest prediction time point meteorological forecast information acquisition unit acquires pest prediction time point meteorological forecast text data through the meteorological prediction platform, and the pest prediction time point interval duration statistical unit performs interval duration numerical value statistical processing on each pest prediction time point based on the pest prediction starting time point data and the pest prediction time point data, and generates pest prediction time point interval duration statistical data.

[0109] The agricultural pest prediction module comprises a different agricultural condition pest theoretical change information storage unit, a first pest prediction time point pest prediction information analysis unit, a first pest prediction time point pest accumulation information statistical unit, a pest prediction time point pest prediction information analysis unit, and a pest prediction time point pest accumulation information statistical unit.

[0110] The pest theoretical change information storage unit under different agricultural conditions is configured to store pest theoretical change text data under different agricultural conditions; the first pest prediction time point pest prediction information analysis unit is configured to perform pest growth prediction processing at the first pest prediction time point based on the starting time point pest monitoring text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and the pest theoretical change text data under different agricultural conditions, and generate first pest prediction time point pest prediction text data; the first pest prediction time point pest accumulation information statistical unit is configured to perform pest information accumulation processing at the first pest prediction time point based on the starting time point pest monitoring text data and the first pest prediction time point pest prediction text data, and generate first pest prediction time point pest accumulation text data; the second pest prediction time point pest prediction information analysis unit is configured to perform pest growth prediction processing at the second pest prediction time point based on the first pest prediction time point pest accumulation text data, the pest prediction time point weather forecast text data, the pest prediction time point interval duration statistical data and the pest theoretical change text data under different agricultural conditions, and generate second pest prediction time point pest prediction text data; and the pest prediction time point pest accumulation information statistical unit is configured to perform pest information accumulation processing at the second pest prediction time point based on the first pest prediction time point pest accumulation text data and the second pest prediction time point pest prediction text data, generate second pest prediction time point pest accumulation text data, and continue to perform pest prediction work at the remaining pest prediction time points until the pest prediction work at all pest prediction time points is completed.

[0111] The agricultural pest prediction result feedback comprises an agricultural pest prediction result acquisition unit and an agricultural pest prediction result output unit.

[0112] The agricultural pest prediction result acquisition unit is configured to construct agricultural pest prediction result data based on pest prediction information combination data at all pest prediction time points; and the agricultural pest prediction result output unit is configured to perform agricultural pest prediction result output work based on the agricultural pest prediction result data in combination with office software.

[0113] Although the embodiments of the present application have been shown and described, it should be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An intelligent prediction method for agricultural pests based on multi-source data fusion, characterized in that, The method includes the following steps: S1. Collect pest forecast start time data, pest forecast time data, pest monitoring text data at the start time, and meteorological forecast text data at the pest forecast time. S2. Perform statistical processing of the interval duration of each pest prediction time point to generate statistical data on the interval duration of pest prediction time points. S3. Perform pest growth prediction processing at the first pest prediction time point and generate pest prediction text data at the first pest prediction time point. S3 includes the following steps: S31. Establish a textual data set of theoretical changes in insect pests under different agricultural conditions. , ;in Indicates the first Textual data on the theoretical changes in pests under different agricultural conditions corresponding to various agricultural conditions. This represents the maximum number of agricultural condition types. S32, will , middle , middle With the The above Character matching is performed on pest monitoring information, weather forecast information, and prediction time duration to search for results matching the provided information. The above The above The matching The data is then used to generate pest prediction text data for the first pest prediction time point, after data identification. ; in This indicates the pest monitoring text data at the start time point. This represents a collection of meteorological forecast text data indicating the time points for pest prediction. include , Indicates the time point data for pest forecasting The corresponding meteorological forecast text data for the pest prediction time points, This represents a set of statistical data on the time intervals between pest forecasting points. include , Indicates the time point data for pest forecasting Data on the start time of pest forecast Statistical data on the interval between corresponding pest forecast time points; S4. Perform pest information accumulation processing at the first pest prediction time point to generate pest accumulation text data at the first pest prediction time point. S4 includes the following steps: S41, Obtain the and stated ; S42, the above Insect pest monitoring information and the above The pest forecast information is processed by classifying and accumulating the number of pests according to pest type and development stage, and generating text data of the pest accumulation at the first pest forecast time point. ; S5. Perform pest growth prediction processing at the second pest prediction time point and generate pest prediction text data at the second pest prediction time point. S5 includes the following steps: S51, Obtain the The above The above ; S52, The KD-tree nearest neighbor search algorithm is used to... The above middle The above middle With the The above Character matching is performed on pest monitoring information, weather forecast information, and prediction time duration to search for results matching the provided information. The above The above The matching The data is then used to generate pest prediction text data for the second pest prediction time point, after data identification. ; in Indicates the time point data for pest forecasting The corresponding meteorological forecast text data for the pest prediction time points, Indicates the time point data for pest forecasting Data on pest forecast time points Statistical data on the interval between corresponding pest forecast time points; S6. Perform pest information accumulation processing for the second pest prediction time point, generate pest accumulation text data for the second pest prediction time point, and repeat S5 and S6 until the pest prediction work for all pest prediction time points is completed. S6 includes the following steps: S61, Obtain the and stated ; S62, the above Insect pest prediction information and the above The pest forecast information is processed by classifying and accumulating the number of pests according to pest type and development stage, and generating text data of pest accumulation at the second pest forecast time point. Repeat steps S5 and S6 until completion. middle to For all corresponding pest forecasting time points, if the pest forecasting work for all pest forecasting time points has not been completed, continue to execute the pest forecasting work operation instructions. in Also includes and , and They represent the first The and the first Data for individual pest forecast time points; S7. Construct agricultural pest prediction data and execute the agricultural pest prediction result output operation.

2. The intelligent prediction method for agricultural pests based on multi-source data fusion according to claim 1, characterized in that: S1 includes the following steps: S11. Collect the text information of the start time point of agricultural pest forecasting online through the data input dialog box of the agricultural pest forecasting management platform, and generate pest forecasting start time point data. ,in The unit is day; The agricultural pest forecasting and management platform collects text information about the forecast time points online through its data input dialog box, and generates a pest forecast time point data set. , ;in Indicates the first Data for individual pest forecast time points This represents the maximum number of pests at the predicted time point, where The unit is day; The system uses intelligent insect monitoring lamps to collect pest monitoring text information of the target agricultural area at the start time point online, and generates pest monitoring text data at the start time point. The pest monitoring text data at the starting time point includes information on the types of pests in the target agricultural area at the starting time point, information on the development stages of different types of pests, and information on the number of different types of pest development stages. The meteorological forecast text information of the target agricultural area at the forecast time point is collected online through the meteorological forecast platform, and a set of meteorological forecast text data for the pest forecast time point is generated. ,in This indicates the pest prediction time point data. The corresponding meteorological forecast text data for the pest prediction time points.

3. The intelligent prediction method for agricultural pests based on multi-source data fusion according to claim 2, characterized in that: S2 includes the following steps: S21, Obtain the and stated ; S22, the above The above The data are then analyzed by subtracting the predicted time points from the previous time point, and a statistical set of time intervals between the predicted time points is generated. ,in Indicates the With the Statistical data on the interval between corresponding pest forecast time points; Indicates the With the Statistical data on the interval between corresponding pest forecast time points; Indicates the With the Data on individual pest forecast time points Statistical data on the interval between corresponding pest forecast time points; Indicates the With the Data on individual pest forecast time points The corresponding statistical data on the time intervals between pest forecasting points, among which , , , The unit is hours.

4. The intelligent prediction method for agricultural pests based on multi-source data fusion according to claim 3, characterized in that: The step of generating the pest prediction text data for the first pest prediction time point in S32 includes the following steps: S321. Initialize and update the maximum number of algorithm iterations T; S322, Exploration stage, this stage mainly involves the exploration of the aforementioned... The search space Perform a global search and find results matching the above. The above The above The matching ; S323, Development Phase: The development phase employs two behaviors: following silverback gorillas and competing with adult female gorillas. S3231, Follow the silverback gorilla to search for it; if... ≥ The search for individual gorillas involves following the silverback gorillas in the search, according to the mechanism described above. Search the search space for the match with the The above The above The matching ,in This indicates that the algorithm iteratively updates the adjustment factor. The weighting factor represents the choice of the gorilla population to follow silverback gorillas and compete with adult female gorillas. S3232, Competition for adult females, if < The mechanism of choosing a female gorilla to follow the adult female searcher leads to adolescent gorillas competing with other male gorillas for a mate. Search the search space for the match with the The above The above The matching ; S324, satisfying the maximum iteration count T, outputting the same as described above. The above The above The matching ; S325. The output in step S324 The first pest prediction text data was generated after data identification. .

5. The intelligent prediction method for agricultural pests based on multi-source data fusion according to claim 4, characterized in that: S7 includes the following steps: S71. When the pest prediction work for all pest prediction time points is completed, obtain the pest prediction data generated in step S42. The corresponding And step S62 generates the to Information on pest prediction results at all pest prediction time points; S72, The information obtained in step S71 to The pest forecast results for all pest forecast time points were used to construct an agricultural pest forecast result dataset after data identification. ,in Indicates the Corresponding agricultural pest forecast data; S73, The generated... The above to The pest forecast results are displayed and output using office software according to the predicted time point number. The office software includes any one of WPS Writer, WPS Spreadsheet and WPS Presentation.

6. An intelligent agricultural pest prediction system based on multi-source data fusion, used to implement the intelligent agricultural pest prediction method based on multi-source data fusion as described in any one of claims 1-5, characterized in that: The system includes a multi-source information acquisition module for agricultural pest prediction, an agricultural pest prediction module, and an agricultural pest prediction result feedback module.

Images