Crop planting information intelligent management method and system based on pesticide knowledge graph

Abstract

The application relates to a crop planting information intelligent management method and system based on a pesticide knowledge graph, which comprises the following steps: acquiring a pesticide knowledge graph of pesticide and crop entity relationships, wherein nodes in the pesticide knowledge graph are expressed by a ternary group constituted by pesticides, crops and crop diseases; acquiring growth data of crops in real time, and writing the growth data into a block chain; matching the growth data with the pesticide knowledge graph through hyperbolic space, and outputting pesticide use suggestions to planting personnel; generating a planting log based on the planting operation records of the planting personnel through prompt learning; and writing the planting log into the block chain. The application recommends pesticide use suggestions through a knowledge graph technology and a hyperbolic space technology, and automatically generates a raw material planting log through a machine learning method based on prompt learning, so that the credibility, integrity and safety of crop planting information are realized.

Description

Technical Field

[0001] This invention belongs to the field of pesticide information and knowledge graph technology, specifically relating to an intelligent management method and system for crop planting information based on pesticide knowledge graph. Background Technology

[0002] With economic development, people are paying increasing attention to food safety. Agricultural products on the market often contain pesticide residues to some extent, making it difficult for consumers to judge their safety and reliability. Therefore, establishing a digital information management system that meets the needs of both businesses and consumers, manages pesticide usage data, and provides traceability and early warning systems for raw material cultivation information, is the most effective way to solve this problem. Summary of the Invention

[0003] To address the issues of incomplete data recording and lack of transparency in existing raw material planting information, and to improve the integrity and security of planting information, this invention provides a first aspect of an intelligent management method for crop planting information based on a pesticide knowledge graph. The method includes: acquiring a pesticide knowledge graph representing the entity relationship between pesticides and crops, wherein nodes in the pesticide knowledge graph are expressed using triples consisting of pesticide-crop-crop disease; acquiring crop growth data in real time and writing the growth data into a blockchain; matching the growth data to the pesticide knowledge graph using hyperbolic space and providing pesticide usage suggestions to growers; generating planting logs based on prompting learning by recording the growers' planting operations; and writing the planting logs into the blockchain.

[0004] In some embodiments of the present invention, the step of matching the growth data with the pesticide knowledge graph through hyperbolic space and outputting pesticide use suggestions to growers includes: mapping the nodes in the pesticide knowledge graph to hyperbolic space using an exponential function; extracting the growth data into nodes or edges of the pesticide knowledge graph and matching the nearest node or edge in the hyperbolic space; and mapping the matched nearest node or edge to the Euclidean space corresponding to the knowledge graph to obtain pesticide use suggestions.

[0005] Furthermore, the distance between two nodes in the hyperbolic space is calculated through the following steps:

[0006]

[0007] in, Let represent the distance between two nodes in hyperbolic space; x and y represent any two nodes in hyperbolic space; <x, y> represents the Minkowski inner product of any two nodes; and K is the negative reciprocal of the curvature of hyperbolic space.

[0008] In some embodiments of the present invention, generating a planting log from the planting operation records of the planters based on cue learning includes: constructing an output template for the planting log and determining multiple target labels for the cue learning model; using the planting operation records of the planters as input to train the cue learning model; and using the trained cue learning model to generate a planting log from the planting operation records of the planters.

[0009] Furthermore, the multiple target tags include the date of the planting operation, the amount of watering, the amount of fertilizer applied, and the amount of pesticide used.

[0010] In the above embodiments, the process of obtaining the pesticide knowledge graph of pesticide and crop entity relationships includes: obtaining a pesticide use rule database and a database of prohibited pesticides, and extracting pesticide and crop entities and their relationships from them; and constructing a pesticide knowledge graph based on pesticide and crop entities and their relationships.

[0011] A second aspect of the present invention provides an intelligent management system for crop planting information based on a pesticide knowledge graph, comprising: an acquisition module for acquiring a pesticide knowledge graph relating pesticide and crop entities, wherein nodes in the pesticide knowledge graph are expressed by triples consisting of pesticide-crop-crop disease; a first writing module for acquiring crop growth data in real time and writing the growth data into a blockchain; an output module for matching the growth data to the pesticide knowledge graph using hyperbolic space and outputting pesticide usage suggestions to growers; a second writing module for generating a planting log based on prompting learning by recording the planting operations of the growers; and writing the planting log into the blockchain.

[0012] A third aspect of the present invention provides an electronic device, comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent management method for crop planting information based on pesticide knowledge graphs provided in the first aspect of the present invention.

[0013] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the intelligent management method for crop planting information based on a pesticide knowledge graph provided in the first aspect of the present invention.

[0014] The beneficial effects of this invention are:

[0015] By effectively integrating pesticide knowledge graphs and pesticide hyperbolic spaces, pesticides are automatically generated based on crop growth conditions, and warnings and alerts are provided regarding harmful substances contained in pesticides. Information extraction is performed using prompt-based machine learning technology to automatically generate planting logs, resulting in concise and complete planting information that is easier to store on the blockchain. This technology further ensures food safety, achieves comprehensive recording and intelligent management of planting data, and truly creates "smart agriculture." Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the basic process of the intelligent management method for crop planting information based on pesticide knowledge graph in some embodiments of the present invention;

[0017] Figure 2 A schematic diagram of some nodes of the pesticide knowledge graph in some embodiments of the present invention;

[0018] Figure 3 This is a schematic diagram illustrating the specific process of the intelligent management method for crop planting information based on pesticide knowledge graph in some embodiments of the present invention;

[0019] Figure 4 This is a schematic diagram of the structure of an intelligent management system for crop planting information based on pesticide knowledge graphs in some embodiments of the present invention;

[0020] Figure 5 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0021] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0022] refer to Figure 1 In a first aspect, the present invention provides an intelligent management method for crop planting information based on a pesticide knowledge graph, comprising: S100. acquiring a pesticide knowledge graph relating pesticide and crop entities, wherein nodes in the pesticide knowledge graph are expressed by triples consisting of pesticide-crop-crop disease; S200. acquiring crop growth data in real time and writing the growth data into a blockchain; S300. matching the growth data with the pesticide knowledge graph using hyperbolic space and outputting pesticide usage suggestions to growers; S400. generating a planting log based on prompting learning by recording the planting operations of the growers; and writing the planting log into the blockchain.

[0023] In S100 of this embodiment, obtaining the pesticide knowledge graph of the relationship between pesticide and crop entities includes:

[0024] S101. Obtain the pesticide use rules database and the prohibited pesticide database, and extract pesticide and crop entities and their relationships from them; specifically, construct a pesticide knowledge graph by extracting pesticide and crop entities and their relationships based on the pesticide use rules and the list of prohibited and restricted pesticides in the China Pesticide Information Network, creating a foundation for generating pesticide use suggestions through subsequent comparison of planting information. Utilize a prompt-based learning machine learning method to automatically identify entities such as crop and pesticide types from pesticides registered in the China Pesticide Information Network, a table comparing the occurrence and control of pests and diseases in fresh crops, and the list of prohibited and restricted pesticides, and extract the relationships between them. These relationships can be that a certain pesticide treats a certain disease in a certain crop, or they can be certain attributes of the crop or pesticide. For example, polyoxin and chitosan can treat late blight in tomatoes and powdery mildew in cucumbers; polyoxin can treat leaf mold in tomatoes; and the growth stages of tomatoes and cucumbers include seedling stage, flowering and fruiting stage, and maturity stage. Optionally, a pesticide knowledge graph can be built using public or custom pesticide or crop databases.

[0025] S102. Construct a pesticide knowledge graph based on pesticide and crop entities and their relationships. Express the pesticide and crop relationships extracted in S11 as triplet pairs such as (polyoxin, tomato, late blight), (chitosan, tomato, late blight), (polyoxin, cucumber, powdery mildew), (chitosan, cucumber, powdery mildew), (polyoxin, tomato, leaf mold), (tomato, crop growth stage, seedling stage), etc., and store these triplet pairs in a knowledge base to form a pesticide knowledge graph (e.g., ...). Figure 1 As shown, entities such as pesticides are stored in the nodes of the graph, and relationships are stored in the edges. Entities are interconnected through relationships to form a knowledge structure network, and relationships in the pesticide knowledge graph can be found by looking up an entity.

[0026] S103. Perform entity disambiguation and coreference resolution on the extracted entities such as pesticides. The entity name "tomato" could represent other real-world entities besides vegetables, requiring differentiation between different entities represented by the same name. Polyoxin and polyoxin are used to address the issue of multiple references corresponding to the same entity object.

[0027] S104. Update the pesticide knowledge graph content in real time according to the regulations published by the China Pesticide Information Network.

[0028] In step S200 of some embodiments of the present invention, crop growth data is acquired in real time and written into the blockchain. Without loss of generality, raw material planting data is collected using wireless sensors and automatically transmitted and stored on the blockchain.

[0029] It is understandable that the hierarchy and logic of a pesticide knowledge graph cannot be represented in a Euclidean embedding space. Hyperbolic embedding, however, maps the input features of the pesticide knowledge graph to a hyperbolic space with different trainable curvatures, maintaining the high fidelity and low dimensionality of the knowledge graph. Therefore, embedding the pesticide knowledge graph into a hyperbolic space forms a pesticide hyperbolic space. Thus, based on collected data, pesticide use suggestions are generated using pesticide hyperbolic space technology on the pesticide knowledge graph, and warnings are issued for harmful pesticides.

[0030] In view of this, in step S300 of some embodiments of the present invention, the step of matching the growth data with the pesticide knowledge graph through hyperbolic space and outputting pesticide use suggestions to growers includes:

[0031] S301. Map the nodes in the pesticide knowledge graph to hyperbolic space using an exponential function;

[0032] Specifically, the relationship between pesticides and crops in the pesticide knowledge graph is expressed through triples of (polyoxin, tomato, late blight), where polyoxin and late blight represent nodes V, and tomato represents edge E. Let H be the d-dimensional input node features. d,K For a d-dimensional hyperboloid manifold with a constant negative curvature of -1 / K (K>0), T x H d,K Let represent the Euclidean tangent space centered at point x, 0 denotes the first layer, the superscript E indicates that the nodal feature lies in Euclidean space, and the superscript H denotes a hyperbolic feature. <,> L :R d+1 ×R d+1 →R represents the Minkowski inner product.<x,y> L :=-x0y0+x1y1+...+x d .

[0033] It is understandable that the pesticide knowledge graph can be embedded into the pesticide hyperbolic space for representation learning. Hyperbolic space embedding can preserve the distance between graph entities in a few dimensions. When searching the pesticide knowledge graph based on known crops and growth status, the distance in hyperbolic space can be used as a similarity measure.

[0034] S302. Extract the growth data into nodes or edges of a pesticide knowledge graph, and match the nearest node or edge in the hyperbolic space. Specifically, when querying the pesticide knowledge graph, a query statement is used. For example, based on the seedling type and growth stage, such as "What pesticide should be used for late blight in tomato seedlings?", the answer can be directly obtained as "polyoxin, chitosan," because we have already created a knowledge base at the system level containing entities for "late blight," "polyoxin," and "chitosan," as well as the relationships between them. Calculate the distance between the entities "late blight" and "a certain pesticide" in the hyperbolic space and the distance difference between them and the relationship "tomato." The smaller the distance difference, the higher the similarity, and the more likely the correct answer is to be obtained.

[0035] When calculating distances between nodes in a pesticide knowledge graph using hyperbolic space, it is first necessary to map the nodes to hyperbolic space using an exponential function. The relationships between edges can then be expressed using distances in hyperbolic space.

[0036]

[0037] Given that tomatoes have contracted late blight, what pesticide should be used to treat it? (Given a vertex and an edge, find the other vertex.) The distance between two nodes (x, y ∈ H) can be calculated using the distance formula in hyperbolic space. d,K Distance between:

[0038]

[0039] S303. Map the nearest matched node or edge to the Euclidean space corresponding to the knowledge graph to obtain pesticide use suggestions.

[0040] By calculating the distance between the unknown drug node and the late blight node, the closer the distance is to the tomato, the more likely the pesticide corresponding to that node is a treatment for tomato late blight. Then, by transforming the node back to its corresponding point in the original Euclidean space using a logarithmic function, polyoxin can be obtained, and thus, polyoxin can be used to treat tomato late blight.

[0041]

[0042] In step S400 of some embodiments of the present invention, generating a planting log from the planting operation records of the planter based on prompting learning includes:

[0043] S401. Construct an output template for the planting log and determine multiple target labels for the prompt learning model; use the planting operation records of the planters as input to train the prompt learning model;

[0044] S402. Using the trained prompt learning model, the planting operation records of the planters are used to generate a planting log.

[0045] Specifically, planting logs are automatically generated by using cue learning technology to record the administrator's planting operations. First, each administrator's planting operation will have corresponding records, but these records need to be summarized to form the planting logs. Let the text of the input model be denoted as X (X could be: October 14, 2022, soil moisture content was low, so 10L of water was used to water tomatoes; soil testing data showed low micronutrient levels, so 5kg of nitrogen fertilizer was used; tomato seedlings were infected with late blight, so 100g of polyoxin 10% wettable powder was used per acre). Let the text of the output model be denoted as Y (Y could be: October 14, 2022, 10L of water was used, 5kg of nitrogen fertilizer was used, and 100g of polyoxin 10% wettable powder was used per acre). At this point, a prompt template needs to be constructed and added before the input X. The prompt template is P = "[MASK] year [MASK] month [MASK] day, watering [MASK], fertilizing [MASK], applying pesticides [MASK]." The length of [MASK] can be freely varied according to the output requirements. The part omitted from [MASK] is the part that the model needs to learn. Through the prompt P, the model can further understand the key information that needs to be learned. Then, the output of [MASK] is filled into P to form a summary.

[0046] Taking actual planting operation records as an example, given input x (on October 14, 2022, the soil moisture content was low, so 10L of water was used to irrigate tomatoes; soil testing data showed that the soil micronutrients were low, so 5kg of nitrogen fertilizer was used; the tomato seedlings were infected with late blight, so 100g of polyoxin 10% wettable powder was used per acre.) and output y (on October 14, 2022, 10L of water was used, 5kg of nitrogen fertilizer was used, and 100g of polyoxin 10% wettable powder was used per acre). The unconstrained log generation learns the conditional distribution p(y|x). Based on a cue-based learning method, an additional control symbol z is added, where z represents keywords such as watering, fertilizing, and pesticide application. The conditional distribution learned by the model then becomes: p(y|x,z).

[0047] The prompt-based learning-based automatic generation of planting logs adds a template for log generation. This template is now automatically generated based on control symbols, which constrains the scope of planting log generation.

[0048] Example 2

[0049] refer to Figure 4In a second aspect, the present invention provides an intelligent management system 1 for crop planting information based on a pesticide knowledge graph, comprising: an acquisition module 11 for acquiring a pesticide knowledge graph relating pesticide and crop entities, wherein nodes in the pesticide knowledge graph are expressed by triples consisting of pesticide-crop-crop disease; a first writing module 12 for acquiring crop growth data in real time and writing the growth data into a blockchain; an output module 13 for matching the growth data with the pesticide knowledge graph using hyperbolic space and outputting pesticide usage suggestions to growers; and a second writing module 14 for generating a planting log based on prompting learning by recording the planting operations of the growers and writing the planting log into the blockchain.

[0050] Furthermore, the output module 13 includes: a mapping unit, used to map the nodes in the pesticide knowledge graph to a hyperbolic space using an exponential function; a matching unit, used to extract the growth data into nodes or edges of the pesticide knowledge graph and match the nearest node or edge in the hyperbolic space; and a suggestion unit, used to map the matched nearest node or edge to the Euclidean space corresponding to the knowledge graph to obtain pesticide use suggestions.

[0051] Example 3

[0052] refer to Figure 5 In a third aspect, the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent management method for crop planting information based on pesticide knowledge graphs according to the first aspect of the present invention.

[0053] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0054] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 5 Each box shown can represent a device or multiple devices as needed.

[0055] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0056] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0057] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0058] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent management of crop planting information based on a pesticide knowledge graph, characterized in that, include: A pesticide knowledge graph is obtained to represent the entity relationship between pesticides and crops. The nodes in the pesticide knowledge graph are expressed by triples consisting of pesticide-crop-crop disease. Real-time acquisition of crop growth data, and writing of the growth data into the blockchain; The growth data is matched with the pesticide knowledge graph through hyperbolic space, and pesticide use suggestions are output to growers: the nodes in the pesticide knowledge graph are mapped to hyperbolic space using an exponential function; the growth data is extracted into nodes or edges of the pesticide knowledge graph, and the nearest node or edge is matched in the hyperbolic space; the nearest matched node or edge is mapped to the corresponding Euclidean space of the knowledge graph to obtain pesticide use suggestions; Based on prompt-based learning, the planting operation records of the planters are used to generate planting logs; The planting log is written into the blockchain; the step of generating planting logs from the planting operation records of the planters based on prompting learning includes: constructing an output template for the planting logs and determining multiple target labels for the prompting learning model; The planting operation records of the planters are used as input to train the prompt learning model; the trained prompt learning model is then used to generate a planting log from the planting operation records of the planters. 2.The pesticide knowledge graph-based intelligent management method for crop planting information according to claim 1, characterized in that, The distance between two nodes in the hyperbolic space is calculated using the following steps: ， in, This represents the distance between two nodes in hyperbolic space; x and y Represent any two nodes in hyperbolic space, < x , y > represents the Minkowski inner product of any two nodes. K It is the negative reciprocal of the curvature of hyperbolic space. 3.The pesticide knowledge graph-based intelligent management method for crop planting information according to claim 1, characterized in that, The multiple target tags include the date of the planting operation, the amount of watering, the amount of fertilizer applied, and the amount of pesticide used. 4.The intelligent management method of crop planting information based on the pesticide knowledge graph according to any one of claims 1 to 3, characterized in that, The pesticide knowledge graph for obtaining the relationship between pesticide and crop entities includes: Obtain the pesticide use rules database and the database of prohibited pesticides, and extract pesticide and crop entities and their relationships from them; Construct a pesticide knowledge graph based on pesticide and crop entities and their relationships.

5. A smart management system for crop planting information based on pesticide knowledge graphs, characterized in that, include: The acquisition module is used to acquire a pesticide knowledge graph that represents the relationship between pesticide and crop entities. The nodes in the pesticide knowledge graph are expressed by triples consisting of pesticide-crop-crop disease. The first writing module is used to acquire crop growth data in real time and write the growth data into the blockchain; The output module is used to match the growth data with the pesticide knowledge graph through hyperbolic space and output pesticide use suggestions to growers: It maps nodes in the pesticide knowledge graph to hyperbolic space using an exponential function; it extracts the growth data into nodes or edges of the pesticide knowledge graph and matches the nearest node or edge in the hyperbolic space; it maps the matched nearest node or edge to the corresponding Euclidean space of the knowledge graph to obtain pesticide use suggestions. The second writing module is used to generate a planting log by recording the planting operations of the planters based on prompt learning. The planting log is written into the blockchain; the step of generating planting logs from the planting operation records of the planters based on prompting learning includes: constructing an output template for the planting logs and determining multiple target labels for the prompting learning model; The planting operation records of the planters are used as input to train the prompt learning model; the trained prompt learning model is then used to generate a planting log from the planting operation records of the planters.

6. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, enable the one or more processors to implement the intelligent management method for crop planting information based on pesticide knowledge graphs as described in any one of claims 1 to 4.

7. A computer readable medium having stored thereon a computer program, wherein, When the computer program is executed by the processor, it implements the intelligent management method for crop planting information based on pesticide knowledge graph as described in any one of claims 1 to 4.

Images