CN118229355B

CN118229355B - Popularization method and system based on agricultural product technical service

Info

Publication number: CN118229355B
Application number: CN202410655274.8A
Authority: CN
Inventors: 陈琳; 赵学生; 肖润; 郗军妮
Original assignee: Shenzhen Disai Shuzhi Technology Co ltd; Shenzhen Dianchou Agricultural Supply Chain Co ltd
Current assignee: Shenzhen Disai Shuzhi Technology Co ltd; Shenzhen Dianchou Agricultural Supply Chain Co ltd
Priority date: 2024-05-24
Filing date: 2024-05-24
Publication date: 2024-07-23
Anticipated expiration: 2044-05-24
Also published as: CN118229355A

Abstract

The invention relates to the technical field of service popularization, in particular to a popularization method and a system for agricultural product technology service. The method comprises the following steps: acquiring and dividing sensing data of an agricultural product station to acquire sensing data of a greenhouse area and sensing data of a processing area; analyzing according to the greenhouse area sensing data to obtain agricultural product yield prediction data and agricultural product planting quality data; analyzing according to the sensing data of the processing area to obtain residual data of agricultural product processing and predicted data of the yield of agricultural product processing; acquiring and sorting order data of an agricultural product station, acquiring agricultural product planting sorting data, evaluating the agricultural product planting sorting data, and acquiring order delivery timeliness data; evaluating based on the agricultural product planting quality data, the agricultural product processing residual data and the order delivery timeliness data to obtain agricultural product competitiveness data; and analyzing the agricultural product station order data to obtain customer agricultural product service preference data. The invention can improve the safety of agricultural products.

Description

Popularization method and system based on agricultural product technical service

Technical Field

The invention relates to the technical field of service popularization, in particular to a popularization method and a system for agricultural product technology service.

Background

With the development of global economy and the improvement of the living standard of people, the quality, safety and traceability of agricultural products are increasingly receiving attention of consumers and governments. Traditional agricultural production and sales methods have been difficult to meet the demands of modern society, and therefore agricultural technical services are becoming an important direction of agricultural development. At present, agricultural product technical services mainly comprise agricultural information services, agricultural technology consultation, agricultural product quality detection, agricultural product marketing popularization and the like. These services can help farmers to improve production efficiency, optimize quality of agricultural products, and enhance market competitiveness, thereby realizing sustainable development of agriculture. However, agricultural technical services face some challenges in the promotion process. However, it is difficult for existing agricultural technical services to ensure product quality and safety.

Disclosure of Invention

Based on the above, the present invention is needed to provide a popularization method and system based on agricultural product technical service, so as to solve at least one of the above technical problems.

In order to achieve the above purpose, a popularization method based on agricultural product technical service comprises the following steps:

Step S1: acquiring agricultural product station sensing data, and dividing agricultural product station areas of the agricultural product station sensing data so as to acquire greenhouse area sensing data and processing area sensing data;

Step S2: constructing a greenhouse area sensing network according to the greenhouse area sensing data, and evaluating the planting quality of the agricultural products according to the greenhouse area sensing network so as to obtain the planting quality data of the agricultural products; carrying out agricultural product yield prediction on the agricultural product planting quality data so as to obtain agricultural product yield prediction data;

Step S3: carrying out agricultural product processing residual condition evaluation according to the sensing data of the processing area so as to obtain agricultural product processing residual data; carrying out agricultural product processing yield prediction on the agricultural product yield prediction data according to the agricultural product processing residual data, thereby obtaining the agricultural product processing yield prediction data;

step S4: acquiring agricultural product station order data, and carrying out agricultural product planting sequencing according to the agricultural product station order data, so as to acquire agricultural product planting sequencing data; carrying out order delivery timeliness assessment according to the agricultural product planting ordering data and the greenhouse area sensing network, so as to obtain order delivery timeliness data;

step S5: carrying out agricultural product competitiveness evaluation based on the agricultural product planting quality data, the agricultural product processing residual data and the order delivery timeliness data, so as to obtain agricultural product competitiveness data;

Step S6: carrying out customer agricultural product service preference analysis on the agricultural product station order data so as to obtain customer agricultural product service preference data; and constructing an agricultural product service promotion model according to the agricultural product station order data, the customer agricultural product service preference data and the agricultural product competitiveness data, and uploading the agricultural product service promotion model to an agricultural product station service cloud platform to execute an agricultural product service promotion task.

The invention can help farm managers to better know the environmental conditions of each area by acquiring the sensing data of the agricultural product stations and dividing the sensing data into areas, thereby carrying out targeted management and adjustment. Meanwhile, the sensing data are divided into the greenhouse area and the processing area, so that fine management is facilitated for different environments. The greenhouse area sensing data is utilized to construct a sensing network and carry out agricultural product planting quality evaluation, so that the real-time monitoring and evaluation of the planting environment can be realized, the timely adjustment of the planting management strategy is facilitated, and the quality and yield of agricultural products are improved. By evaluating the sensing data of the processing area, possible problems such as residues and the like in the processing process can be found in time, so that the processing flow is improved, and the safety and quality of agricultural products are ensured. By ordering the order data and evaluating delivery timeliness, the change of the demands and markets of the clients can be better known, so that the planting and delivery schedule is optimized, and the efficiency and flexibility of the supply chain are improved. The competitive assessment is carried out based on the planting quality, processing residues, delivery timeliness and other data, so that farm managers can be helped to know the position and advantage of the farm managers in the market, and accordingly more effective marketing and competition strategies are formulated. By analyzing the order data and the customer service preference, the requirements and the preference of the customer can be better understood, so that the product popularization and service strategy are optimized, and the customer satisfaction degree and loyalty degree are improved. Meanwhile, a service promotion model is built and uploaded to the service cloud platform, so that automatic and personalized promotion service can be realized, and promotion efficiency and coverage range are improved.

Optionally, step S2 specifically includes:

step S21: extracting regional spatial characteristics of the greenhouse regional sensing data so as to obtain greenhouse regional spatial characteristic data;

Step S22: constructing a greenhouse region space coordinate system based on the greenhouse region space characteristic data;

Step S23: carrying out three-dimensional space sensing fusion on a greenhouse area space coordinate system according to the greenhouse area sensing data, thereby obtaining a greenhouse area sensing network;

step S24: carrying out agricultural product planting quality assessment according to the greenhouse area sensing network so as to obtain agricultural product planting quality data;

step S25: and predicting the yield of the agricultural products according to the agricultural product planting quality data, so as to obtain the yield prediction data of the agricultural products.

According to the method, regional spatial characteristics of sensed data of the greenhouse region are extracted, meaningful spatial characteristics such as temperature, humidity, illumination and the like can be extracted from massive sensed data, the environmental states of all regions in the greenhouse can be known, and basis is provided for subsequent agricultural management and decision making. The greenhouse region space coordinate system is constructed based on the greenhouse region space characteristic data, so that the space information in the greenhouse can be better organized and managed, and a space reference is provided for data analysis and model establishment. By carrying out three-dimensional space sensing fusion on the greenhouse area sensing data, the data from different sensors can be integrated together to form a comprehensive and multidimensional greenhouse area sensing network, so that the environment state inside the greenhouse can be reflected more accurately. The agricultural product planting quality evaluation is carried out according to the greenhouse area sensing network, the growth condition and the growth environment of crops can be evaluated based on real-time environmental data, problems can be found in time, measures are taken, and the quality and the yield of agricultural products are improved. The agricultural product yield prediction is carried out on the agricultural product planting quality data, the future yield can be predicted through historical data and environmental factors, references are provided for production planning and market prediction, and a farm manager is helped to make a more intelligent decision.

Optionally, step S24 specifically includes:

Step S241: extracting greenhouse region photographic images from the greenhouse region sensing network, so as to obtain the greenhouse region photographic images;

step S242: extracting growth characteristics of the planted agricultural products from the greenhouse region camera image, thereby obtaining growth data of the planted agricultural products;

Step S243: acquiring an agricultural product growth rule, wherein the agricultural product growth rule comprises an agricultural product proper growth temperature interval, an agricultural product periodic growth characteristic and an agricultural product proper survival soil condition;

step S244: constructing an agricultural product growth environment assessment system based on agricultural product growth rules;

step S245: carrying out growth environment assessment on the greenhouse area sensing network through an agricultural product growth environment assessment system so as to obtain agricultural product growth environment assessment data;

step S246: performing growth quality assessment on the growing data of the planted agricultural products according to the agricultural product growing rules, so as to obtain the agricultural product growing quality assessment data;

step S247: and carrying out evaluation weighting combination on the agricultural product growing environment evaluation data and the agricultural product growing quality evaluation data so as to obtain agricultural product planting quality data.

According to the invention, visual information in the greenhouse, including the growth state of crops, the condition of diseases and insect pests and the like, can be obtained by extracting the image of the greenhouse region, and visual support is provided for subsequent data analysis and decision. The growth characteristics of the planted agricultural products are extracted from the greenhouse region camera image, and the characteristics of the growth condition, the leaf color, the growth height and the like of the crops can be obtained from the image, so that the growth condition of the crops can be monitored and evaluated. Obtaining agricultural product growth rules, including knowing the proper growth temperature, periodic growth characteristics, proper soil conditions, etc. of the agricultural product, provides a basis for evaluating the crop growth environment and quality. The agricultural product growing environment assessment system is constructed based on the agricultural product growing rules, so that whether the environmental conditions in the greenhouse meet the requirements of crop growth can be systematically assessed, and guidance is provided for adjusting and improving the greenhouse environment. The agricultural product growth environment assessment system is used for carrying out growth environment assessment on the greenhouse area sensing network, so that the environmental quality inside the greenhouse can be assessed from real-time sensing data, and problems can be found in time and measures can be taken. And (3) carrying out growth quality assessment on the growing data of the planted agricultural products according to the agricultural product growing rules, comparing the coincidence degree of the actual growing data and the growing rules, and assessing the growing quality and the health condition of the crops. The evaluation weighting combination is carried out on the agricultural product growth environment evaluation data and the agricultural product growth quality evaluation data, so that the factors of the greenhouse environment and the crop growth condition can be comprehensively considered, and comprehensive evaluation data and reference basis are provided for the agricultural product planting quality.

Optionally, step S242 specifically includes:

Performing edge detection on the greenhouse region photographic image so as to obtain region edge point data;

calculating the curvature of the adjacent edge points of the regional edge point data, thereby obtaining the curvature data of the adjacent edge points;

Performing curvature classification calculation according to the curvature data of the adjacent edge points, so as to obtain right-angle curvature edge point data, sharp curvature edge point data and smooth curvature edge point data;

Performing right-angle curvature edge point elimination on the region edge point data according to the right-angle curvature edge point data, so as to obtain first region edge point data; removing the smooth curvature edge points from the area edge point data according to the smooth curvature edge point data, so as to obtain second area edge point data;

Performing edge point mapping on the greenhouse region photographic image according to the second region edge point data, so as to obtain an agricultural product region marking image;

And extracting the outline characteristics of the agricultural product from the agricultural product region marked image according to the sharp curvature edge point data, thereby obtaining the growing data of the planted agricultural product.

According to the invention, the edge detection is carried out on the greenhouse region shooting image, so that the edge information of the greenhouse region can be accurately extracted, and the subsequent analysis and treatment of the greenhouse region are facilitated. Calculating the curvature of adjacent edge points can help identify curvature variations of the edges, thereby further analyzing the shape and structural features of the greenhouse area. According to the classification of curvature, edge points can be classified into a right-angle curvature, a sharp curvature, and a smooth curvature, which contributes to a finer understanding of the characteristics and morphology of edge points. According to the curvature classification result, edge points with right-angle curvature and smooth curvature are removed, and an agricultural product planting support, unnecessary noise or an excessively smooth area can be removed, so that the accuracy of subsequent processing is improved. And the second region edge point data is utilized to carry out edge point mapping on the greenhouse region photographic image, so that the agricultural product region can be accurately marked, and positioning and reference are provided for the subsequent agricultural product growth data extraction. Based on the sharp curvature edge point data, the outline characteristics of the agricultural products including the shape, the size and other information can be effectively extracted, and a basis is provided for further growth data analysis and evaluation.

Optionally, step S3 specifically includes:

step S31: extracting microbial sensing characteristics of the sensing data of the processing area, thereby obtaining the microbial sensing data of the area;

Step S32: constructing a three-dimensional model of the processing area according to the sensing data of the processing area, and extracting the spatial characteristics of the processing device from the three-dimensional model of the processing area so as to obtain the spatial data of the processing device;

step S33: carrying out actual processing region division on the three-dimensional processing region model according to the processing tool space data, thereby obtaining an actual processing region division model;

Step S34: classifying microorganism distribution areas of the actual processing area division model according to the area microorganism sensing data, so as to obtain microorganism dense area data and microorganism open area data;

step S35: respectively evaluating the microbial residual condition of the actual processing area division model according to the microbial dense area data and the microbial open area data, so as to obtain microbial activity evaluation data and microbial isolation evaluation data;

step S36: performing evaluation, weighting and combination on the microbial activity evaluation data and the microbial isolation evaluation data so as to obtain agricultural product processing residual data;

Step S37: and carrying out agricultural product processing yield prediction on the agricultural product yield prediction data according to the agricultural product processing residual data, thereby obtaining the agricultural product processing yield prediction data.

The invention can acquire the data about the distribution and change of microorganisms in the processing area by extracting the microorganism sensing characteristics in the sensing data of the processing area, thereby being beneficial to monitoring and managing the sanitary condition of the processing environment. The three-dimensional model of the processing area can be established to provide more real and visual space information, and a foundation is provided for the subsequent extraction of the space characteristics of the processing device and the division of the actual processing area. Extracting spatial features of the processing tool helps to understand the position, layout and use of the processing tool, and provides data support for subsequent processing region partitioning and microorganism distribution region classification. The actual processing area range can be more accurately determined by dividing the processing area according to the processing tool space data, and accurate space reference is provided for classifying the microorganism distribution area and evaluating the microorganism residue condition. The processing area division model is combined with the microorganism sensing data, so that a microorganism dense area and a microorganism open area can be distinguished, and a basis is provided for subsequent microorganism viability evaluation. And the microbial residue condition is evaluated according to the data of the microorganism dense area and the microorganism open area, so that the sanitary condition and the microbial pollution degree of the processing area can be known, and a reference is provided for safe processing of agricultural products. The agricultural product yield is predicted according to the agricultural product processing residual data, so that the agricultural product processing factory can be helped to reasonably plan production and resource allocation, and the production efficiency and the product quality are improved.

Optionally, step S34 specifically includes:

step S341: calculating the microorganism dense duty ratio of the actual processing area according to the microorganism dense area data to the actual processing area division model, thereby obtaining the microorganism dense data of the actual processing area;

Step S342: acquiring a microorganism survival rule, and calculating the microorganism survival probability of the sensing data of the processing area according to the microorganism survival rule, so as to acquire microorganism survival probability data;

Step S343: performing actual processing area microorganism activity evaluation on the microorganism dense data of the actual processing area according to the microorganism survival probability data, so as to obtain microorganism activity evaluation data;

Step S344: calculating the actual processing region interval according to the microorganism open region data to the actual processing region division model, thereby obtaining the actual processing region interval data;

Step S345: calculating the microbial activity range of the sensing data of the processing area according to the microbial survival rule, so as to obtain microbial activity range data;

step S346: and carrying out microbial isolation evaluation on the actual processing area interval data according to the microbial activity range data, thereby obtaining microbial isolation evaluation data.

According to the invention, the distribution condition of microorganisms in the processing area can be quantified by calculating the ratio of the microorganism dense area in the actual processing area, so that basic data is provided for subsequent microorganism viability evaluation. The acquisition of the microorganism survival rules and the calculation of the microorganism survival probability are helpful for knowing the survival condition of microorganisms under specific environmental conditions, and data support is provided for evaluating the survival degree of microorganisms in a processing area. And evaluating microorganism dense data of the actual processing area according to the microorganism survival probability data, so that the survival condition of microorganisms in the actual processing area can be determined, and a basis is provided for the sanitation management of the processing area. By analyzing and calculating the microorganism open area data, the interval condition in the actual processing area can be determined, and the possibility and range of microorganism transmission in the processing area can be known. And calculating the activity range of the microorganism according to the microorganism survival rule, predicting the possible position and range of the microorganism in the processing area, and providing data support for microorganism isolation evaluation. The interval data of the actual processing area is evaluated based on the microorganism activity range data, so that the isolation degree of microorganisms in the processing area can be judged, and a basis is provided for preventing cross infection and transmission of microorganisms.

Optionally, step S4 specifically includes:

step S41: acquiring order data of an agricultural product station;

Step S42: carrying out order delivery time sequence feature extraction and order agricultural product quantity feature extraction on the agricultural product order data so as to obtain order delivery time sequence data and order agricultural product quantity data;

Step S43: order time sequence ordering is carried out on the order data of the agricultural product station according to the order delivery time sequence data, so that the agricultural product order time sequence ordering data is obtained;

step S44: sorting the agricultural product quantity according to the agricultural product station order data to obtain agricultural product order agricultural product quantity sorting data;

Step S45: carrying out agricultural product order sorting coupling according to the agricultural product order time sequence sorting data and the agricultural product order agricultural product quantity sorting data, so as to obtain agricultural product order sorting data;

Step S46: extracting the characteristics of the real-time planted agricultural products according to the greenhouse area sensing network, so as to obtain real-time planted agricultural product data, and analyzing the greenhouse area planting strategy of the agricultural product order ordering data according to the real-time planted agricultural product data, so as to obtain the agricultural product planting ordering data;

Step S47: and carrying out order delivery timeliness assessment according to the agricultural product planting ordering data and the greenhouse area sensing network, so as to obtain order delivery timeliness data.

The invention can build a complete order database by collecting the order data of the agricultural product station, and provides a basis for subsequent analysis and decision. And extracting time sequence characteristics and agricultural product quantity characteristics from the order data, so that the delivery time of the order and the supply and demand conditions of the agricultural products can be known, and data support is provided for order management and optimization. By ordering the order data in time sequence and the amount of agricultural products, the orders can be arranged according to the delivery time sequence and the amount of agricultural products, which is beneficial to order priority and effective resource allocation. The time sequence ordering of the orders and the agricultural product quantity ordering are coupled, the delivery time of the orders and the demand of the agricultural product quantity can be comprehensively considered, and the processing sequence of the orders can be well arranged. And the real-time agricultural product planting data are acquired through the greenhouse area sensing network, and planting strategy analysis is carried out according to the data, so that the production and planting plan of agricultural products can be optimized, and the yield and quality can be improved. Based on the agricultural product planting sequencing data and the greenhouse area sensing network, the delivery timeliness of the orders is evaluated, timely adjustment of planting schedules and order processing sequences is facilitated, timely delivery of the orders is ensured, and customer satisfaction and operation efficiency are improved.

Optionally, step S47 specifically includes:

Step S471: extracting planting area characteristics according to the greenhouse area sensing network, so as to obtain planting area data;

step S472: dividing the planting area data into areas to be planted according to the agricultural product planting sequencing data, so as to obtain planting area division data;

step S473: according to the agricultural product growing rule, carrying out the ripening period calculation of the agricultural products to be planted on the agricultural product planting sequencing data, so as to obtain the ripening period data of the agricultural products to be planted;

Step S474: harvesting time sequence prediction is carried out on the real-time agricultural product data to obtain real-time agricultural product harvesting time sequence data, and the agricultural product planting period to be planted is calculated on the real-time agricultural product harvesting time sequence data and the agricultural product maturation period to be planted to obtain agricultural product planting period to be planted data;

step S475: estimating the yield of the agricultural products to be planted according to the agricultural product growth rule and the planting area division data, so as to obtain the yield data of the agricultural products to be planted;

Step S476: carrying out order delivery time and timeliness assessment on the agricultural product order data according to the mature period data of the agricultural products to be planted, thereby obtaining order delivery time and timeliness assessment data;

step S477: carrying out order delivery yield and timeliness assessment on the agricultural product order data according to the agricultural product yield data to be planted, so as to obtain order delivery yield and timeliness assessment data;

Step S478: and carrying out weighted evaluation and combination on the order delivery time and timeliness evaluation data and the order delivery yield and timeliness evaluation data, thereby obtaining order delivery timeliness data.

According to the invention, the greenhouse area sensing network is used for extracting the characteristics of the planting area, and the data of the planting area such as temperature, humidity, soil quality and the like are obtained. These data provide an important reference for optimizing the planting plan for the planting area. And dividing the planting area data into areas to be planted according to the agricultural product planting sequencing data, and determining which areas are suitable for planting which agricultural products. This step helps to increase the efficiency of the use of the planting area and ensures optimal conditions for the growth of the agricultural product. And calculating the ripening period of the agricultural products to be planted according to the agricultural product planting sequencing data according to the agricultural product growth rule, and predicting the ripening time of the agricultural products. This helps to schedule order delivery time, ensuring timely delivery of agricultural products. The method comprises the steps of calculating the planting period of the agricultural products to be planted by predicting the harvesting time sequence of the agricultural products to be planted in real time and combining the maturation period data of the agricultural products to be planted. This helps to rationally schedule planting and harvesting and optimize planting plans. And estimating the yield of the agricultural products to be planted according to the agricultural product growth rule and the planting area division data. This helps to understand the expected yield and provides data support for order placement and inventory management. And (5) carrying out order delivery time and timeliness evaluation on the agricultural product order data according to the mature period data of the agricultural products to be planted. This helps to predict the time of order delivery, ensure on-time delivery, and improve customer satisfaction. And carrying out order delivery yield and timeliness evaluation on the agricultural product order data according to the agricultural product yield data to be planted. This helps ensure that the supply of agricultural products for the order meets customer requirements. And obtaining comprehensive order delivery timeliness data by weighting, evaluating and merging the order delivery time and the yield timeliness data. This data helps the agricultural product station make more accurate adjustments in decision and management, improving order processing efficiency.

Optionally, step S6 specifically includes:

step S61: carrying out high-frequency customer statistics on the agricultural product order data so as to obtain high-frequency customer order data;

Step S62: extracting order agricultural product quantity features and order deadline features from the high-frequency customer order data to obtain customer order agricultural product quantity data and customer order time data;

Step S63: carrying out customer product quantity preference analysis according to the customer order agricultural product quantity data so as to obtain customer product quantity preference data;

step S64: performing a customer delivery deadline preference analysis based on the customer order deadline data, thereby obtaining customer delivery deadline preference data;

Step S65: establishing customer agricultural product service portraits according to the customer product quantity preference data and the customer delivery deadline preference data, thereby obtaining customer agricultural product service preference data;

Step S66: and constructing an agricultural product service promotion model according to the agricultural product station order data, the customer agricultural product service preference data and the agricultural product competitiveness data, and uploading the agricultural product service promotion model to an agricultural product station service cloud platform to execute an agricultural product service promotion task.

The invention identifies the customer group who frequently purchases agricultural products by carrying out high-frequency customer statistics on the agricultural product order data. This helps the farm focus on prioritizing orders for these high value customers, improving customer loyalty and satisfaction. Features such as order agricultural product quantity and order deadline are extracted from the high-frequency customer order data, so that purchasing behavior and preference of customers can be known. This provides an important data basis for subsequent customer analysis. And analyzing the agricultural product quantity data according to the customer order to know the demand preference of the customer for different agricultural products. This helps the farm to optimize inventory management, ensure adequate inventory and meet customer needs. Analysis is performed based on the customer order deadline data to learn customer preferences for order delivery times. This helps the farm produce station to arrange order processing and delivery reasonably, improving order delivery timeliness. And integrating the client product quantity preference data and the client delivery deadline preference data to establish a client agricultural product service portrait. This helps the personalized service in agricultural product station, accurate propelling movement accords with customer's demand's product and service. And constructing an agricultural product service promotion model based on the order data, the customer service preference and the agricultural product competitiveness data, and providing a targeted promotion strategy for the agricultural product station. This helps to increase sales and market share, enhancing the competitiveness of the agricultural product station.

Optionally, the present specification further provides a promotion system based on agricultural product technical service, for executing a promotion method based on agricultural product technical service as described above, the promotion system based on agricultural product technical service comprising:

The agricultural product station area dividing module is used for acquiring agricultural product station sensing data and dividing the agricultural product station sensing data into agricultural product station areas so as to acquire greenhouse area sensing data and processing area sensing data;

the agricultural product planting quality evaluation module is used for constructing a greenhouse area sensing network according to the greenhouse area sensing data and evaluating the agricultural product planting quality according to the greenhouse area sensing network so as to obtain agricultural product planting quality data; carrying out agricultural product yield prediction on the agricultural product planting quality data so as to obtain agricultural product yield prediction data;

the agricultural product processing residual condition evaluation module is used for evaluating the agricultural product processing residual condition according to the sensing data of the processing area so as to obtain the agricultural product processing residual data; carrying out agricultural product processing yield prediction on the agricultural product yield prediction data according to the agricultural product processing residual data, thereby obtaining the agricultural product processing yield prediction data;

the order delivery timeliness evaluation module is used for acquiring the order data of the agricultural product station and carrying out agricultural product planting sequencing according to the order data of the agricultural product station so as to acquire agricultural product planting sequencing data; carrying out order delivery timeliness assessment according to the agricultural product planting ordering data and the greenhouse area sensing network, so as to obtain order delivery timeliness data;

the agricultural product competitiveness evaluation module is used for carrying out agricultural product competitiveness evaluation based on the agricultural product planting quality data, the agricultural product processing residual data and the order delivery timeliness data so as to obtain agricultural product competitiveness data;

The agricultural product service promotion model construction module is used for carrying out customer agricultural product service preference analysis on the agricultural product station order data so as to obtain customer agricultural product service preference data; and constructing an agricultural product service promotion model according to the agricultural product station order data, the customer agricultural product service preference data and the agricultural product competitiveness data, and uploading the agricultural product service promotion model to an agricultural product station service cloud platform to execute an agricultural product service promotion task.

The popularization system based on the agricultural product technical service can realize any popularization method based on the agricultural product technical service, is used for combining the operation and signal transmission media among all modules to finish the popularization method based on the agricultural product technical service, and the internal modules of the system are mutually cooperated, so that the quality, the safety and the market competitiveness of agricultural products can be improved.

Drawings

Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of a non-limiting implementation, made with reference to the accompanying drawings in which:

FIG. 1 is a flow chart of the steps of a popularization method based on agricultural product technical service;

FIG. 2 is a detailed step flow chart of step S2 of the present invention;

FIG. 3 is a detailed step flow chart of step S3 of the present invention;

the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

In order to achieve the above objective, referring to fig. 1 to 3, the present invention provides a popularization method based on agricultural product technical service, the method comprising the following steps:

In this embodiment, when acquiring sensed data of an agricultural product station, a sensor network is used to be disposed in a greenhouse and a processing area, such as a temperature sensor, a humidity sensor, an illumination sensor, etc., to monitor environmental parameters in real time. The data is transmitted to the data processing center through a wireless transmission technology, and the data is stored and managed by utilizing a distributed data storage technology. And dividing the agricultural product station area by using a GIS (geographic information system) technology, and ensuring the corresponding relation between the sensing data and the actual area.

in this embodiment, a sensing network is constructed by using sensing data of a greenhouse region, and a deep learning model such as a Convolutional Neural Network (CNN) is used to model the environment in the greenhouse. And extracting land features and vegetation indexes by combining high-resolution image data obtained by a remote sensing technology, and monitoring and predicting the growth state of agricultural products. The network structure is optimized through a back propagation algorithm, so that accurate assessment of agricultural product planting quality and yield prediction are realized.

In this embodiment, the spectral sensor and the chemical sensor are used to detect and analyze residues in the processing of agricultural products. And detecting chemical components on the surface of the agricultural product by utilizing a spectrum technology, and identifying the types and the contents of residues by combining a machine learning algorithm. The processing process is monitored in real time by adopting an on-line monitoring technology, so that the food safety and quality in the agricultural product processing process are ensured.

In this embodiment, the order management system of the farm product station integrates and analyzes the order data of the farm product station, and the planting of different farm products is ordered by using an ordering algorithm such as quick ordering or merge ordering. And the logistics management system is combined to realize the butt joint of order information and real-time inventory, so that the order processing efficiency and the delivery timeliness are improved. And the delivery route is optimized through a path planning algorithm, so that the delivery time and the cost are reduced, and the customer experience is improved.

In this embodiment, the evaluation results of the planting quality, the processing residue and the order delivery timeliness are comprehensively analyzed, and the overall operation condition of the agricultural product station is evaluated by adopting multidimensional data analysis technologies such as principal component analysis, factor analysis and the like. Combining SWOT analysis and other methods to identify the advantages and disadvantages of agricultural product stations and obtain agricultural product competitiveness data

In this embodiment, the order data is analyzed and mined using data mining and machine learning techniques to identify customer consumption preferences and behavioral patterns. And establishing a client file by combining a client relationship management system, and recording historical purchase records and feedback information of clients. And constructing a personalized recommendation system based on a big data analysis technology, pushing agricultural products and services conforming to the preference of the customer, and improving the satisfaction and loyalty of the customer.

Optionally, step S2 specifically includes:

In this embodiment, when the greenhouse region sensing data is used for region spatial feature extraction, image processing technologies, such as edge detection and color segmentation, may be used to extract the growth state and distribution of vegetation from the image obtained by the monitoring camera. And (3) identifying plant outlines and color features of different areas by carrying out threshold processing and morphological operation on the images, and further obtaining spatial feature data such as vegetation density, growth state and the like of each position in the greenhouse area.

In this embodiment, when the greenhouse region spatial coordinate system is constructed based on the greenhouse region spatial feature data, three-dimensional point cloud data in the greenhouse can be obtained by using technologies such as laser scanning, and the point cloud data under different view angles are fused into a unified three-dimensional space model through a point cloud registration algorithm. Then, according to the characteristic points or characteristic areas in the model, a local coordinate system of the greenhouse area is established so as to facilitate the space positioning and fusion of the subsequent sensing data.

In this embodiment, when three-dimensional space sensing fusion is performed on the greenhouse region space coordinate system according to the greenhouse region sensing data, the data acquired by different sensor nodes can be synchronized in time and space through the position information of the sensor nodes and the acquisition time of the sensor data. And then, fusing the sensor data by utilizing a multi-sensor fusion algorithm such as Kalman filtering or particle filtering to obtain the overall environmental state of the greenhouse region such as temperature, humidity and illumination distribution.

in this embodiment, when the quality of agricultural product planting is evaluated according to the greenhouse area sensing network, the growth rate and the health condition of the plant can be monitored and evaluated in real time by combining the plant growth model and the sensing data. By comparing the environment parameters with a preset growth model, abnormal conditions in the sensing data are analyzed, and the environment parameters of the greenhouse are timely adjusted, so that good growth state and high-quality yield of agricultural products are ensured.

In this embodiment, when the agricultural product yield is predicted from the agricultural product planting quality data, the yield prediction model may be constructed using the historical yield data and the environmental factors. By analyzing and modeling the historical data, key factors influencing the yield are identified, and model training and verification are carried out by utilizing a machine learning algorithm, so that accurate prediction and management of the yield of future agricultural products are realized.

Optionally, step S24 specifically includes:

In this embodiment, the image data inside the greenhouse is extracted by using a computer vision technology through the camera nodes in the greenhouse area sensing network. The method comprises preprocessing the photographed image by using an image processing algorithm, such as denoising, image enhancement and the like, and then identifying growth states and position information of different plants from the image by using an image segmentation and feature extraction technology, such as a Convolutional Neural Network (CNN), so as to finally obtain the greenhouse region photographed image data.

In this embodiment, when the growth feature extraction is performed on the greenhouse region captured image, a machine learning algorithm, such as a target detection model (e.g., YOLO or SSD) in deep learning, may be used to identify the plant region in the image, and extract the growth features of the plant, such as the number of leaves, the color of the leaves, the plant height, and so on. At the same time, image analysis techniques, such as texture analysis and morphological feature extraction, may also be used to further extract growth data for the planted agricultural product.

In this embodiment, when the agricultural product growth rule is obtained, the growth guide and the environmental requirement for the specific agricultural product may be obtained from an agricultural expert or a related document. For example, for tomato growth regulations, suitable growth temperature ranges (e.g., 20 ℃ to 30 ℃), growth cycle characteristics (e.g., flowering phase, fruiting phase), suitable soil pH values, and the like are included.

in this embodiment, when an agricultural product growing environment evaluation system is constructed based on agricultural product growing rules, the growing rules need to be converted into evaluation indexes and evaluation systems. For example, environmental parameters such as temperature, humidity, illumination and the like are used as evaluation indexes, and a corresponding evaluation model is established to evaluate the quality of agricultural product growth environment in the greenhouse area.

In this embodiment, when the growth environment evaluation system of the agricultural product is used to evaluate the growth environment of the greenhouse area sensing network, the data collected by the sensor nodes, such as a temperature sensor, a humidity sensor, etc., may be used to evaluate the growth environment in the greenhouse in combination with the previously established evaluation system, for example, to determine whether the temperature is in a suitable range, whether the humidity is too high or too low, etc., and generate corresponding evaluation data.

In this embodiment, when the growth quality evaluation is performed on the growth data of the planted agricultural product according to the agricultural product growth rule, the degree of coincidence between the actual growth data and the growth rule may be compared. For example, for the growth quality assessment of tomatoes, the quality of the growth quality of tomatoes can be assessed by comparing the actual plant height, fruit size, color and other indexes with expected values in the growth rules.

In this embodiment, when the evaluation weighting and combination are performed on the evaluation data of the agricultural product growing environment and the evaluation data of the agricultural product growing quality, the evaluation data of the two aspects can be combined by adopting weighted summation or other mathematical models according to the importance and the weights of different evaluation indexes, so as to obtain the final agricultural product planting quality data for agricultural production management and decision.

Optionally, step S242 specifically includes:

In this embodiment, an edge detection algorithm (e.g., canny edge detection) is used to process the greenhouse region captured image, detect edge points in the image, and extract the edge point data for subsequent calculation.

in this embodiment, for the extracted edge point data of the region, by calculating the curvature of the adjacent edge points, the curvature value between the adjacent edge points can be calculated by using a curvature calculation formula in the differential geometry, so as to obtain the curvature data of the adjacent edge points.

In this embodiment, the curvature values are classified according to the calculated curvature data of the adjacent edge points, for example, statistical analysis is performed according to the magnitude of the curvature values, so as to obtain curvature threshold values, and then the curvature values in the curvature data of the adjacent edge points are classified into three types of right-angle curvature, sharp curvature and smooth curvature according to the curvature threshold values, so that subsequent processing and analysis can be performed.

In this embodiment, according to the right-angle curvature edge point data and the smooth curvature edge point data, the area edge point data are respectively subjected to the elimination processing. For example, for right angle curvature edge point data, edge points with larger curvature can be removed by setting a curvature threshold value so as to remove right angle edges in the image; for smooth curvature edge point data, the smooth characteristic of the edge line can be reserved through a curvature smoothing algorithm, and noise and unnecessary details are removed.

in this embodiment, edge point mapping is performed on the original greenhouse region captured image by using the removed second region edge point data, that is, the position information of the edge point is mapped onto the original image to form an agricultural product region marker image for subsequent agricultural product contour feature extraction.

In this embodiment, the agricultural product contour feature extraction is performed in the agricultural product region marker image using sharp curvature edge point data. Morphological operations and edge detection algorithms, such as contour detection algorithms (e.g., findContours functions in OpenCV), may be used to extract contour information of the agricultural product, including area, perimeter, etc., from the image to obtain growth data of the planted agricultural product.

Optionally, step S3 specifically includes:

in this embodiment, microorganism-sensing data in the processing region is acquired using microorganism sensors that can detect the presence and quantity of microorganisms. Microbial growth of air or surfaces is detected using biosensing techniques, such as optical, biochemical or electrochemical based sensors. And (3) extracting the quantity, the type and the distribution characteristics of microorganisms by analyzing the data output by the sensor to form regional microorganism sensing data.

In this embodiment, a three-dimensional model of the processing region is constructed using data acquired by the processing region sensor. The geometric information of the processing area is acquired by using a laser scanner, a camera or other equipment, and an accurate three-dimensional model is built by combining sensor data. Then, the three-dimensional model is analyzed, and features such as the position, the size, the shape and the like of the processing tool in the space are extracted to form processing tool space data.

In this embodiment, the three-dimensional model of the machining region is divided into actual machining regions based on the machining tool space data. And combining the processing tool with other spatial features through a spatial analysis algorithm, and dividing the processing area to form an actual processing area division model.

In this embodiment, the microorganism distribution region classification is performed on the actual processing region division model based on the region microorganism sensing data. And classifying the areas in the processing area division model according to the number and distribution characteristics of microorganisms by utilizing a cluster analysis or classification algorithm to obtain microorganism dense area data and microorganism open area data.

In this embodiment, the actual processing region division model is evaluated for the residual condition of microorganisms according to the microorganism dense region data and the microorganism open region data, respectively. And (3) evaluating the survival condition and distribution condition of the microorganisms in different areas through a statistical method or a machine learning algorithm, and obtaining the microbial activity evaluation data and the microbial isolation evaluation data.

In this embodiment, the evaluation weight combination is performed by integrating the evaluation data of the microbial activity and the evaluation data of the microbial isolation. According to the weighting strategy, the influence of the microbial activity and isolation on the processing area is comprehensively considered, so that the processing residual data of the agricultural products are obtained, and the microbial residual condition of the processing area is reflected.

In this embodiment, the agricultural product processing yield prediction data is subjected to agricultural product processing yield prediction based on the agricultural product processing residual data. And (3) correlating the microbial residue condition of the processing area with the yield of the agricultural products by using a statistical model or a machine learning algorithm, predicting the yield of the agricultural products, obtaining the predicted data of the processing yield of the agricultural products, and providing a reference for a production decision.

Optionally, step S34 specifically includes:

In this embodiment, for the microorganism-dense region data in the actual processing region division model, the number and distribution of microorganisms in the region are first determined. By analyzing the sensor data, the dense proportion of microorganisms in the area, namely the proportion of the space occupied by the microorganisms, is calculated. For example, assuming that the number of microorganisms detected in a specific area is 1000 and the total space of the area is 100 square meters, the microorganism concentration ratio is 1000 microorganisms per 100 square meters=10 microorganisms per square meter. Thus, microorganism-dense data of the actual processing area is obtained.

In this embodiment, a microorganism survival rule, that is, a survival probability rule of a microorganism under different environmental conditions is obtained. And determining the survival probability of the microorganism under the environmental conditions of specific temperature, humidity, oxygen content and the like according to microbiological knowledge and experimental data. For example, for a certain bacterium, it is known from experimental data that the survival probability is 80% at 25 degrees celsius and at a suitable humidity. The probability of microorganism survival in the sensor data is then calculated based on the actual environmental conditions of the processing area, such as temperature, humidity, etc., in combination with the microorganism survival rules.

In this example, the microorganism viability was evaluated on the microorganism density data of the actual processing region according to the calculated microorganism viability probability data. The microorganism survival probability is multiplied by the number of microorganisms actually detected to obtain the number of microorganisms survived. For example, if 1000 microorganisms are detected in a region and the survival rate is calculated to be 0.8 according to the survival probability, the number of microorganisms that survive in the region is predicted to be 1000×0.8=800. Thus, microbial activity evaluation data were obtained.

In this embodiment, the actual processing region interval calculation is performed on the actual processing region division model according to the microorganism open region data. The separation distance between the actual processing areas is determined by analyzing the spatial distance around the open areas. For example, if a certain safe distance is defined around the open area, the separation distance between this area and the other areas is considered to be 1 meter. In this way, actual processing region interval data is obtained.

In this embodiment, the microorganism activity range calculation is performed on the processing region sensing data according to the microorganism survival rule. And determining the activity range of the microorganism in the space according to the living condition of the microorganism and environmental factors. For example, a microorganism can move in air at a distance of 2 meters under a specific temperature and humidity condition. According to this rule, an estimation of the microorganism activity range is made for the microorganism-dense area of the processing area.

In this embodiment, the microbial isolation of the actual processing area is evaluated based on the microbial activity range data. The degree of isolation of microorganisms between different regions is assessed by comparing the range of microorganism activity to the separation distance between the actual processing regions. For example, if the microorganism's range of motion is 2 meters and the distance between the actual process areas is 3 meters, the microorganism isolation in that area is assessed to be high and the risk of microorganism transmission between different areas is low.

Optionally, step S4 specifically includes:

step S41: acquiring order data of an agricultural product station;

In this embodiment, order data is extracted from a database or other data source of the farm product station, including information such as order number, order date, order product, order quantity, etc. Order data, including details of the order as well as customer information, is derived, for example, from an online platform or order management system of the farm.

In this embodiment, feature extraction is performed on the order data, including timing features of order delivery and agricultural product quantity features of the order. And extracting the delivery time sequence of the order by analyzing time information in the order data, analyzing the quantity information of the agricultural products in the order, and extracting the agricultural product quantity characteristics of the order.

In this embodiment, the order data of the agricultural product station is ordered in time sequence according to the order delivery time sequence data, that is, ordered according to the order delivery time sequence. For example, orders are ordered from early to late by order date for subsequent analysis and processing of the order's chronology.

in this embodiment, the order data of the agricultural product station is ordered according to the order agricultural product amount data, that is, ordered according to the ordered number of agricultural products in the order. For example, orders are ordered from a large to a small number of ordered agricultural products for subsequent analysis and processing of the agricultural product quantity characteristics of the order.

In this embodiment, order sorting coupling is performed according to the order sorting data of the agricultural products and the order sorting data of the agricultural products, that is, order sorting is performed by combining the order chronology and the agricultural product quantity characteristics. For example, a multi-factor ordering algorithm may be employed that comprehensively considers the delivery time of the order and the number of agricultural products to arrive at a final order ordering result.

in this embodiment, the greenhouse area sensing network is utilized to extract characteristic data of the planted agricultural products, such as temperature, humidity, illumination and other information, in real time. According to the real-time data, analyzing the growth condition of the planted agricultural products, and combining the agricultural product order ordering data, carrying out greenhouse area planting strategy analysis, and determining the optimal planting scheme.

In the embodiment, timeliness of order delivery is evaluated according to the agricultural product planting sequencing data and the greenhouse area sensing network. And (3) evaluating whether the delivery of the order is timely or not by analyzing the growth cycle of the planted agricultural products and the time sequence characteristics of the delivery of the order. For example, the timeliness assessment may take into account the degree of matching of the order delivery to the planting cycle, as well as the difference in actual time of the order delivery from the expected time.

Optionally, step S47 specifically includes:

in this embodiment, environmental parameters, such as temperature, humidity, illumination, etc., of each region in the greenhouse are collected through the greenhouse region sensing network. The data are used for feature extraction, such as dividing a greenhouse area into different planting areas according to the difference of environmental parameters. For example, a region of similar temperature and humidity is divided into one planting region, and so on.

In this embodiment, the planting area is divided by using a clustering algorithm according to historical agricultural product planting ranking data, such as planting condition and yield of each agricultural product in the past year, and combining features of each area in the greenhouse. For example, according to the characteristics of temperature, humidity, illumination and the like, the interior of the greenhouse is divided into areas suitable for planting different agricultural products, so that planting area division data are obtained. For example, for agricultural products in a warm and humid environment, areas with higher temperatures and humidities are selected for division.

In this embodiment, the maturity period of each agricultural product is calculated according to the growth law of the agricultural product and the existing planting order data, in combination with the characteristics of each region in the greenhouse. For example, for vegetable agricultural products, the time period from planting to ripening is calculated based on the growth rate and environmental requirements.

In this embodiment, a time series model or other predictive model may be constructed using the real-time collected plant agricultural product data in combination with the maturation period data of each agricultural product. The models can predict the maturation time of each agricultural product according to historical data and current environmental conditions. Then, an optimal harvesting time for each planted agricultural product is determined based on the prediction. Then, the optimal harvesting time of the planted agricultural products and the planting period of the agricultural products to be planted are calculated. The planting cycle is the time span from the start of planting to the completion of harvesting. By the method, the planting period of agricultural products to be planted can be obtained, and planting and harvesting can be performed at the optimal time, so that the yield and quality are improved.

In this embodiment, according to the known growth rule of agricultural products and the characteristics of each region in the greenhouse, the yield of agricultural products to be planted is estimated by using regression analysis or other prediction models in combination with the historical planting data. This includes consideration of factors such as planting density, temperature, humidity, etc. in the greenhouse area, and the effect of the agricultural product growth cycle on yield.

In this embodiment, the order delivery time and timeliness of the agricultural product order data are evaluated in combination with the maturity cycle data of the agricultural product to be planted. By comparing the delivery time of the order with the maturity period of the corresponding agricultural product, it is assessed whether the delivery of the order is completed within the appropriate time.

in this embodiment, according to the yield data of the agricultural products to be planted, the yield timeliness of order delivery is evaluated in combination with the agricultural product order data. And judging whether the yield of the order meets the requirement or not by comparing the matching condition of the quantity of agricultural products required by the order and the actual yield.

In this embodiment, the order delivery time timeliness evaluation data and the order delivery yield timeliness evaluation data are weighted, evaluated and combined to comprehensively consider the two conditions of the order delivery time and the yield, thereby obtaining final order delivery timeliness evaluation data. For example, the time and yield weights may be set according to actual demand, and the two evaluation results may be weighted-averaged.

Optionally, step S6 specifically includes:

In this embodiment, frequent pattern mining algorithms in data mining techniques, such as Apriori algorithm, are used to analyze the agricultural product order data. A population of customers who purchase agricultural products frequently is identified, and a support threshold and a confidence threshold are set to determine high frequency customers, e.g., with a support greater than 0.5 and a confidence greater than 0.7. This allows high frequency customer order data to be obtained.

In this embodiment, feature extraction is performed on the high-frequency customer order data, and feature engineering techniques in machine learning are adopted. And carrying out statistical feature extraction, such as average value, standard deviation and the like, on the quantity of agricultural products in the order, and time feature extraction, such as order duration, earliest delivery time and the like, of the order deadline.

In this embodiment, a histogram or box plot is drawn over the customer product quantity data using a data visualization tool, such as matplotlib or Seaborn, to observe customer preferences for different products. Through statistical analysis, the types and quantity ranges of agricultural products purchased by customers are identified.

In this embodiment, the customer order deadline data is modeled using a time series analysis method, such as ARIMA model. By observing the time series plot and the autocorrelation function plot, customer preferences for the delivery deadline of the order are identified, such as if there is a tendency to advance or retard delivery.

In this embodiment, the customers are clustered using a cluster analysis algorithm, such as a K-means algorithm, in combination with customer product volume preference data and delivery deadline preference data. Each group represents a different customer agricultural product service preference, such as a high product volume but flexible delivery deadline group or a low product volume but strict delivery deadline group.

In this embodiment, a supervised learning algorithm, such as a random forest or XGBoost, is used to construct a promotion model using the established customer farm product service representation and farm product station order data. The model takes the customer characteristics, the agricultural product service characteristics and the agricultural product competitive characteristics as inputs, predicts the response of the customer to different service popularization activities, and formulates corresponding popularization strategies. And finally, uploading the model to an agricultural product station service cloud platform, executing popularization tasks and monitoring effects in real time.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The popularization method based on agricultural product technical service is characterized by comprising the following steps:

Step S3: carrying out agricultural product processing residual condition evaluation according to the sensing data of the processing area so as to obtain agricultural product processing residual data; carrying out agricultural product processing yield prediction on the agricultural product yield prediction data according to the agricultural product processing residual data so as to obtain the agricultural product processing yield prediction data, wherein the step S3 specifically comprises the following steps:

Step S36: weighting and combining the microbial activity evaluation data and the microbial isolation evaluation data to obtain agricultural product processing residual data;

Step S37: carrying out agricultural product processing yield prediction on the agricultural product yield prediction data according to the agricultural product processing residual data, thereby obtaining the agricultural product processing yield prediction data;

2. The agricultural product technical service-based popularization method according to claim 1, wherein the step S2 is specifically:

3. The agricultural product technical service-based popularization method according to claim 2, wherein the step S24 is specifically:

Step S247: and weighting and combining the agricultural product growing environment evaluation data and the agricultural product growing quality evaluation data so as to obtain agricultural product planting quality data.

4. The agricultural product technical service-based popularization method according to claim 3, wherein the step S242 is specifically:

5. The agricultural product technical service-based popularization method according to claim 1, wherein the step S34 is specifically:

6. The agricultural product technical service-based popularization method according to claim 1, wherein the step S4 is specifically:

step S41: acquiring order data of an agricultural product station;

7. The agricultural product technical service-based popularization method according to claim 6, wherein the step S47 is specifically:

step S478: and carrying out weighted combination on the order delivery time and timeliness evaluation data and the order delivery output and timeliness evaluation data, thereby obtaining order delivery timeliness data.

8. The agricultural product technical service-based popularization method according to claim 1, wherein the step S6 is specifically:

9. A promotion system based on agricultural technical services for performing the promotion method based on agricultural technical services according to claim 1, the promotion system based on agricultural technical services comprising: