Plant growth environment assessment method based on root exudate data identification

Abstract

The present invention relates to a plant growth environment assessment method based on root secretion data identification, belonging to the technical field of plant growth assessment. The present invention evaluates and analyzes the chemical composition data of the root secretions of each plant planting area, obtains the plant planting area in an abnormal state, thereby obtaining the environmental characteristic data in the target area and the chemical composition data of the root secretions of the plant planting area in an abnormal state, and combines the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of the plant root system, and finally issues an early warning based on the types of diseases that may be caused by the growth of the plant root system, and generates relevant protection strategies based on the types of diseases that may be caused by the growth of the plant root system. The present invention predicts the colony type of the plant planting area by performing colony analysis on the root analyte in combination with environmental factors, thereby determining the type of pathogen, carrying out prevention and control in advance, and reducing economic losses.

Description

Technical Field

[0001] The present invention relates to the technical field of plant growth environment assessment, and in particular to a plant growth environment assessment method based on root exudate data identification. Background Art

[0002] Plant root exudates are biological and chemical substances released into the soil and other environments through root tissues. These exudates enable plants to absorb nutrients and water from the outside world and adapt to the external environment for a long time. Generally, soil-borne pathogenic fungi will start to infect the roots of host plants, and under suitable conditions, cause the roots of host plants and non-host plants to produce secretions, causing the germination of microsclerotia or dormant spores. The growth of pathogenic fungi is affected by certain substances in the host root secretions. In the root secretions of strawberries, there are mainly allelopathic substances such as organic acids, esters, amides, hydrocarbons, and aldehydes and ketones. The higher the concentration of these allelopathic substances, the stronger the inhibitory effect on strawberries, resulting in a more obvious decline in various indicators of strawberry growth and development, such as plant height, root length, and aboveground fresh matter quality. When crop growth is inhibited, it will inevitably reduce its ability to resist the harm of foreign organisms or adversity, and ultimately reduce resistance or tolerance to continuous cropping obstacles. Therefore, root secretions affect the growth environment of plants. Once the growth environment of plants is affected, the plants will be attacked by pathogens, which will cause economic losses. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method for evaluating plant growth environment based on root exudate data identification.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for evaluating a plant growth environment based on root exudate data identification, comprising the following steps:

[0006] Collecting root exudate extracts of plants, and extracting chemical components from the root exudate extracts of plants to obtain chemical component data of the root exudates, and constructing a knowledge graph based on the chemical component data of the root exudates;

[0007] Acquire the chemical composition data of the root secretions of each plant planting area, and acquire the plant planting area in abnormal state by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area;

[0008] Obtain environmental characteristic data in the target area and chemical composition data of root secretions in abnormal plant planting areas, and combine with knowledge graph analysis to obtain the types of diseases that may occur in plant root growth;

[0009] Early warning is given according to the types of diseases that may be caused by the growth of the plant root system, and relevant protection strategies are generated based on the types of diseases that may be caused by the growth of the plant root system.

[0010] Furthermore, in the present method, the root exudate extract of the plant is collected, and the chemical composition data of the root exudate is obtained by extracting the chemical components of the root exudate extract of the plant, and a knowledge graph is constructed according to the chemical composition data of the root exudate, which specifically includes:

[0011] Collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and collecting bacterial colony data when the root exudates appear;

[0012] Counting the colony data when each type of root secretion appears, obtaining the historical colony data when each root secretion appears, and constructing a knowledge graph, introducing a graph neural network, and inputting the historical colony data when each root secretion appears into the knowledge graph;

[0013] Taking the root exudate type as the first node and the colony data as the second node, constructing a directed connection description relationship, and connecting the first node and the second node based on the directed connection description relationship to construct a topological structure diagram;

[0014] A relevant adjacency matrix is ​​obtained according to the topological structure diagram, and the relevant adjacency matrix is ​​input into the knowledge graph for storage.

[0015] Furthermore, in the present method, the chemical composition data of the root secretions of each plant planting area are obtained, and the plant planting area in an abnormal state is obtained by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area, specifically:

[0016] Acquire the chemical composition data of the root secretions of each plant planting area, construct a timestamp, and construct the chemical composition data of the root secretions of each plant planting area based on the time series in combination with the timestamp;

[0017] Taking the chemical composition data of the root secretions of each plant planting area at each timestamp as a state value, and presetting a state threshold, and judging whether the state value is greater than the state threshold;

[0018] When the state value is greater than the state threshold, the plant planting area whose state value is greater than the state threshold is regarded as a plant planting area in an abnormal state;

[0019] When the state value is not greater than the state threshold, the plant planting area whose state value is not greater than the state threshold is taken as a plant planting area in a normal state.

[0020] Furthermore, in this method, the environmental characteristic data in the target area and the chemical composition data of the root secretions of the abnormal plant planting area are obtained, and combined with the knowledge graph analysis, the types of diseases that may be caused by the growth of plant roots are obtained, specifically:

[0021] Acquire environmental characteristic data in the target area and chemical composition data of root secretions in the plant planting area in an abnormal state, and input the chemical composition data of root secretions in the plant planting area in an abnormal state into the knowledge graph for data matching;

[0022] Obtain estimated colony data of each plant planting area, and perform big data retrieval based on the estimated colony data of each plant planting area, and obtain the survival rate of each colony data under each environmental characteristic data through the big data;

[0023] According to the survival rate of each colony data under each environmental characteristic data and the estimated colony data of each plant planting area, the survival rate data of the estimated colony data in each plant planting area are obtained, and a survival rate threshold is set;

[0024] Obtain the estimated colony data corresponding to the survival rate data greater than the survival rate threshold, search through big data, obtain the possible disease types of plant root growth corresponding to each estimated colony data, and output the possible disease types of plant root growth.

[0025] Furthermore, in this method, an early warning is given according to the type of disease that may be caused by the growth of the plant root system, specifically:

[0026] Obtaining estimated environmental change characteristic data within a preset time through big data, and searching through big data in combination with the estimated environmental change characteristic data within the preset time and the types of diseases that may be caused by plant root growth;

[0027] By searching, the reproduction rate of the disease type that may be caused by the growth of the plant root system in each plant planting area is obtained, and the reproduction rate under the estimated environmental change characteristic data is calculated according to the reproduction data of the disease type that may be caused by the growth of the plant root system in each plant planting area;

[0028] A reproduction rate threshold is set, and when the reproduction rate is greater than the reproduction rate threshold, geographical location information of the corresponding plant planting area is obtained, and an early warning is issued according to the geographical location information of the corresponding plant planting area.

[0029] Furthermore, in this method, relevant protection strategies are generated based on the types of diseases that may be caused by the growth of the plant root system, specifically:

[0030] Obtaining protection strategies for each root disease type through big data, inputting the protection strategies for each root disease type into the knowledge graph for storage, and inputting the types of diseases that may be caused by the plant root growth into the knowledge graph for data matching;

[0031] Through data matching, the protection roughness corresponding to each plant planting area is obtained, and the protection roughness corresponding to the plant planting area is displayed in a preset manner.

[0032] A second aspect of the present invention provides a plant growth environment assessment system based on root exudation data identification, the system comprising a memory and a processor, the memory comprising a plant growth environment assessment method program based on root exudation data identification, and when the plant growth environment assessment method program based on root exudation data identification is executed by the processor, any step of the plant growth environment assessment method based on root exudation data identification is implemented.

[0033] A third aspect of the present invention provides a terminal device, including:

[0034] A knowledge graph construction module collects plant root exudate extracts, extracts chemical components from the plant root exudate extracts, obtains chemical component data of the root exudates, and constructs a knowledge graph based on the chemical component data of the root exudates;

[0035] A state recognition module is used to obtain the chemical composition data of the root secretions of each plant planting area, and to obtain the plant planting area in an abnormal state by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area;

[0036] The classification module obtains the environmental characteristic data in the target area and the chemical composition data of the root secretions in the abnormal plant planting area, and combines the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of plant roots;

[0037] The protection strategy analysis module issues an early warning based on the types of diseases that may be caused by the growth of the plant root system, and generates relevant protection strategies based on the types of diseases that may be caused by the growth of the plant root system.

[0038] A fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for a plant growth environment assessment method based on root exudation data identification. When the program for a plant growth environment assessment method based on root exudation data identification is executed by a processor, the steps of any one of the plant growth environment assessment methods based on root exudation data identification are implemented.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention collects root secretion extracts of plants, extracts chemical components from the root secretion extracts of plants, obtains chemical component data of the root secretions, constructs a knowledge graph based on the chemical component data of the root secretions, and then obtains the chemical component data of the root secretions of each plant planting area. By evaluating and analyzing the chemical component data of the root secretions of each plant planting area, the plant planting area in an abnormal state is obtained, thereby obtaining environmental feature data in the target area and the chemical component data of the root secretions of the plant planting area in an abnormal state, and combining the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of plant roots, and finally, an early warning is given based on the types of diseases that may be caused by the growth of plant roots, and related protection strategies are generated based on the types of diseases that may be caused by the growth of plant roots. The present invention predicts the colony type of the plant planting area by performing colony analysis on the root analyte in combination with environmental factors, thereby determining the type of pathogen, preventing and controlling in advance, and reducing economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0042] Figure 1 The overall flow chart of the plant growth environment assessment method based on root exudate data identification is shown;

[0043] Figure 2 A partial flow chart of a method for evaluating plant growth environment based on root exudate data identification is shown;

[0044] Figure 3 A system block diagram of a plant growth environment assessment system based on root exudate data identification is shown;

[0045] Figure 4 A device schematic diagram of a terminal device is shown. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] like Figure 1 As shown, the first aspect of the present invention provides a method for evaluating a plant growth environment based on root exudate data identification, comprising the following steps:

[0049] S102: collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and constructing a knowledge graph based on the chemical component data of the root exudates;

[0050] S104: obtaining chemical composition data of root secretions of each plant planting area, and obtaining plant planting areas in abnormal states by evaluating and analyzing the chemical composition data of root secretions of each plant planting area;

[0051] S106: Obtain environmental characteristic data in the target area and chemical composition data of root secretions in the abnormal plant planting area, and combine with knowledge graph analysis to obtain the types of diseases that may be caused by plant root growth;

[0052] S108: issuing early warnings based on the types of diseases that may be caused by the growth of plant roots, and generating relevant protection strategies based on the types of diseases that may be caused by the growth of plant roots.

[0053] It should be noted that the present invention predicts the colony type of the plant planting area by performing colony analysis on the root analytes in combination with environmental factors, thereby determining the type of pathogen, taking preventive measures in advance, and reducing economic losses.

[0054] Furthermore, in the present method, the root exudate extract of the plant is collected, and the chemical composition data of the root exudate is obtained by extracting the chemical composition of the root exudate extract of the plant, and a knowledge graph is constructed according to the chemical composition data of the root exudate, which specifically includes:

[0055] Collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and collecting bacterial colony data when the root exudates appear;

[0056] Count the colony data when each type of root secretion appears, obtain the historical colony data when each root secretion appears, and construct a knowledge graph. Introduce the graph neural network and input the historical colony data when each root secretion appears into the knowledge graph.

[0057] The root exudate type is used as the first node, the colony data is used as the second node, a directed connection description relationship is constructed, and the first node and the second node are connected based on the directed connection description relationship to construct a topological structure diagram;

[0058] Obtain the relevant adjacency matrix based on the topological structure graph, and input the relevant adjacency matrix into the knowledge graph for storage.

[0059] It should be noted that the chemical components of the plant root exudate extract can be extracted by a component analyzer to obtain the chemical component data of the root exudate, wherein the chemical component data includes data such as the chemical component type and the chemical component concentration.

[0060] Furthermore, in this method, the chemical composition data of the root secretions of each plant planting area are obtained, and the plant planting area in abnormal state is obtained by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area, specifically:

[0061] Obtain the chemical composition data of the root secretions of each plant planting area, construct a timestamp, and combine the timestamps to construct the chemical composition data of the root secretions of each plant planting area based on the time series;

[0062] The chemical composition data of the root secretions of each plant planting area at each timestamp is used as a state value, and a state threshold is preset to determine whether the state value is greater than the state threshold;

[0063] When the state value is greater than the state threshold, the plant planting area with the state value greater than the state threshold is regarded as the plant planting area in an abnormal state;

[0064] When the state value is not greater than the state threshold, the plant planting area with the state value not greater than the state threshold is regarded as the plant planting area in a normal state.

[0065] It should be noted that the state threshold can be a concentration value, which represents a state value, wherein the Markov chain can be integrated to construct a state transfer matrix based on the state value, and the transition probability value of the state value in the state transfer matrix to another state value is calculated by the Markov chain. When the transition probability value is greater than the transition probability threshold, the state value is updated to another state value. When the transition probability value is not greater than the transition probability threshold, the state value is maintained without updating, thereby improving the recognition accuracy of abnormal plant planting areas.

[0066] like Figure 2 As shown, further, in this method, the environmental characteristic data in the target area and the chemical composition data of the root secretions of the plant planting area in an abnormal state are obtained, and combined with the knowledge graph analysis, the types of diseases that may be caused by the growth of the plant roots are obtained, specifically:

[0067] S202: Obtaining environmental feature data in the target area and chemical composition data of root secretions in the plant planting area in an abnormal state, and inputting the chemical composition data of root secretions in the plant planting area in an abnormal state into the knowledge graph for data matching;

[0068] S204: Obtain estimated colony data for each plant planting area, and perform big data retrieval based on the estimated colony data for each plant planting area, and obtain the survival rate of each colony data under each environmental characteristic data through the big data;

[0069] S206: according to the survival rate of each colony data under each environmental characteristic data and the estimated colony data of each plant planting area, the survival rate data of the estimated colony data in each plant planting area are obtained, and a survival rate threshold is set;

[0070] S208: Obtain the estimated colony data corresponding to the survival rate data being greater than the survival rate threshold, search through big data, obtain the disease types that may be caused by the plant root growth corresponding to each estimated colony data, and output the disease types that may be caused by the plant root growth.

[0071] It should be noted that the colony data mainly refers to the colony type. This method can further improve the prediction accuracy of the types of diseases that may occur in plant root growth.

[0072] Furthermore, in this method, an early warning is given based on the types of diseases that may occur in the growth of plant roots, specifically:

[0073] Obtaining estimated environmental change characteristic data within a preset time through big data, and combining the estimated environmental change characteristic data within the preset time with the types of diseases that may be caused by plant root growth through big data retrieval;

[0074] By searching, the reproduction rate of the disease types that may be caused by the growth of plant roots in each plant planting area is obtained, and the reproduction rate under the estimated environmental change characteristic data is calculated based on the reproduction data of the disease types that may be caused by the growth of plant roots in each plant planting area;

[0075] A reproduction rate threshold is set. When the reproduction rate is greater than the reproduction rate threshold, geographical location information of the corresponding plant planting area is obtained, and an early warning is issued according to the geographical location information of the corresponding plant planting area.

[0076] It should be noted that different environmental characteristic data (including climate and environmental characteristics, temperature, humidity, salinity, oxygen concentration, soil permeability, etc.) will lead to inconsistent reproduction rates of various colony types. The reproduction rate data may include the reproduction area of ​​colonies per unit time, the reproduction area of ​​colonies within a preset time, etc. When the environment changes in the future, the environment may no longer be suitable for the growth of pathogen colonies. This method can further adjust the prevention and control strategy to make it more reasonable.

[0077] Furthermore, in this method, relevant protection strategies are generated based on the types of diseases that may occur in the growth of plant roots, specifically:

[0078] Obtain protection strategies for each root disease type through big data, input the protection strategies for each root disease type into the knowledge graph for storage, and input the types of diseases that may occur in plant root growth into the knowledge graph for data matching;

[0079] Through data matching, the protection roughness corresponding to each plant planting area is obtained, and the protection roughness corresponding to the plant planting area is displayed in a preset manner.

[0080] It should be noted that the protection strategy can be a physical protection strategy, a chemical protection strategy, a biological protection strategy, etc.

[0081] In addition, the method may further include:

[0082] Acquire the symbiotic bacteria type of each colony type, and input the symbiotic bacteria type of each colony type into the knowledge graph for storage, and acquire real-time colony structure data in the target area by performing colony structure analysis on soil extraction liquid;

[0083] Determine whether there is a symbiotic bacterial species type in the real-time colony structure data in the target area, and if there is no symbiotic bacterial species type in the real-time colony structure data in the target area, output the real-time colony structure data in the target area;

[0084] If there is a symbiotic bacteria type in the real-time colony structure data in the target area, obtaining the current symbiotic bacteria type according to the symbiotic bacteria type of each colony type and the real-time colony structure data in the target area;

[0085] The colony type with which the current symbiotic bacterial species type coexists is obtained, and the real-time colony structure data in the target area is updated according to the colony type with which the current symbiotic bacterial species type coexists and the current symbiotic bacterial species type, and the warning information is updated based on the real-time colony structure data in the target area.

[0086] It should be noted that, in fact, some pathogens may be symbiotic with a certain type of colony. When symbiotic bacterial species appear during colony analysis, it indicates that other colony structures also exist. This method can further improve the rationality of early warning.

[0087] like Figure 3 As shown, the second aspect of the present invention provides a plant growth environment assessment system 4 based on root exudation data identification. The system includes a memory 41 and a processor 42. The memory 41 includes a plant growth environment assessment method program based on root exudation data identification. When the plant growth environment assessment method program based on root exudation data identification is executed by the processor 42, any step of the plant growth environment assessment method based on root exudation data identification is implemented.

[0088] like Figure 4 As shown, the third aspect of the present invention provides a terminal device, including:

[0089] The knowledge graph construction module 10 collects the root secretion extract of the plant, and obtains the chemical composition data of the root secretion by extracting the chemical components of the root secretion extract of the plant, and constructs a knowledge graph according to the chemical composition data of the root secretion;

[0090] The state recognition module 20 obtains the chemical composition data of the root secretions of each plant planting area, and obtains the plant planting area in abnormal state by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area;

[0091] The classification module 30 obtains the environmental characteristic data in the target area and the chemical composition data of the root secretions of the abnormal plant planting area, and combines the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of the plant root system;

[0092] The protection strategy analysis module 40 issues an early warning based on the types of diseases that may be caused by the growth of the plant root system, and generates relevant protection strategies based on the types of diseases that may be caused by the growth of the plant root system.

[0093] Furthermore, in the present device, the root exudate extract of the plant is collected, and the chemical composition data of the root exudate is obtained by extracting the chemical composition of the root exudate extract of the plant, and a knowledge graph is constructed according to the chemical composition data of the root exudate, which specifically includes:

[0094] Collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and collecting bacterial colony data when the root exudates appear;

[0095] Count the colony data when each type of root secretion appears, obtain the historical colony data when each root secretion appears, and construct a knowledge graph. Introduce the graph neural network and input the historical colony data when each root secretion appears into the knowledge graph.

[0096] The root exudate type is used as the first node, the colony data is used as the second node, a directed connection description relationship is constructed, and the first node and the second node are connected based on the directed connection description relationship to construct a topological structure diagram;

[0097] Obtain the relevant adjacency matrix based on the topological structure graph, and input the relevant adjacency matrix into the knowledge graph for storage.

[0098] Furthermore, in this device, the chemical composition data of the root secretions of each plant planting area is obtained, and the plant planting area in abnormal state is obtained by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area, specifically:

[0099] Obtain the chemical composition data of the root secretions of each plant planting area, construct a timestamp, and combine the timestamps to construct the chemical composition data of the root secretions of each plant planting area based on the time series;

[0100] The chemical composition data of the root secretions of each plant planting area at each timestamp is used as a state value, and a state threshold is preset to determine whether the state value is greater than the state threshold;

[0101] When the state value is greater than the state threshold, the plant planting area with the state value greater than the state threshold is regarded as the plant planting area in an abnormal state;

[0102] When the state value is not greater than the state threshold, the plant planting area with the state value not greater than the state threshold is regarded as the plant planting area in a normal state.

[0103] Furthermore, in this device, the environmental characteristic data in the target area and the chemical composition data of the root secretions of the plant planting area in an abnormal state are obtained, and combined with the knowledge graph analysis, the types of diseases that may be caused by the growth of the plant roots are obtained, specifically:

[0104] Obtaining environmental characteristic data in the target area and chemical composition data of root secretions in the plant planting area in an abnormal state, and inputting the chemical composition data of root secretions in the plant planting area in an abnormal state into the knowledge graph for data matching;

[0105] Obtain estimated colony data for each plant planting area, and perform big data retrieval based on the estimated colony data for each plant planting area, and obtain the survival rate of each colony data under each environmental characteristic data through big data;

[0106] According to the survival rate of each colony data under each environmental characteristic data and the estimated colony data of each plant planting area, the survival rate data of the estimated colony data in each plant planting area are obtained, and a survival rate threshold is set;

[0107] Obtain the estimated colony data corresponding to the survival rate data greater than the survival rate threshold, search through big data, obtain the possible disease types of plant root growth corresponding to each estimated colony data, and output the possible disease types of plant root growth.

[0108] Furthermore, in this device, early warning is given according to the types of diseases that may occur in the growth of plant roots, specifically:

[0109] Obtaining estimated environmental change characteristic data within a preset time through big data, and combining the estimated environmental change characteristic data within the preset time with the types of diseases that may be caused by plant root growth through big data retrieval;

[0110] By searching, the reproduction rate of the disease types that may be caused by the growth of plant roots in each plant planting area is obtained, and the reproduction rate under the estimated environmental change characteristic data is calculated based on the reproduction data of the disease types that may be caused by the growth of plant roots in each plant planting area;

[0111] A reproduction rate threshold is set. When the reproduction rate is greater than the reproduction rate threshold, geographical location information of the corresponding plant planting area is obtained, and an early warning is issued according to the geographical location information of the corresponding plant planting area.

[0112] Furthermore, in this device, relevant protection strategies are generated based on the types of diseases that may occur in the growth of plant roots, specifically:

[0113] Obtain protection strategies for each root disease type through big data, input the protection strategies for each root disease type into the knowledge graph for storage, and input the types of diseases that may occur in plant root growth into the knowledge graph for data matching;

[0114] Through data matching, the protection roughness corresponding to each plant planting area is obtained, and the protection roughness corresponding to the plant planting area is displayed in a preset manner.

[0115] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a program for a plant growth environment assessment method based on root exudation data identification. When the program for a plant growth environment assessment method based on root exudation data identification is executed by a processor, it implements any step of the plant growth environment assessment method based on root exudation data identification.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0117] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0119] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0120] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0121] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating plant growth environment based on root exudate data identification, characterized in that: The following steps are involved: Collecting root exudate extracts of plants, and extracting chemical components from the root exudate extracts of plants to obtain chemical component data of the root exudates, and constructing a knowledge graph based on the chemical component data of the root exudates; Acquire the chemical composition data of the root secretions of each plant planting area, and acquire the plant planting area in abnormal state by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area; Obtain environmental characteristic data in the target area and chemical composition data of root secretions in abnormal plant planting areas, and combine knowledge graph analysis to obtain the types of diseases that may occur in plant root growth; Providing early warnings based on the types of diseases that may be caused by the growth of the plant root system, and generating relevant protection strategies based on the types of diseases that may be caused by the growth of the plant root system; Collecting plant root exudate extracts, and extracting chemical components from the plant root exudate extracts to obtain chemical component data of the root exudates, and constructing a knowledge graph based on the chemical component data of the root exudates, specifically including: Collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and collecting colony data when the root exudates appear; Counting the colony data when each type of root secretion appears, obtaining the historical colony data when each root secretion appears, and constructing a knowledge graph, introducing a graph neural network, and inputting the historical colony data when each root secretion appears into the knowledge graph; Taking the root exudate type as the first node and the colony data as the second node, constructing a directed connection description relationship, and connecting the first node and the second node based on the directed connection description relationship to construct a topological structure diagram; A relevant adjacency matrix is ​​obtained according to the topological structure diagram, and the relevant adjacency matrix is ​​input into the knowledge graph for storage.

2. The method for evaluating plant growth environment based on root exudate data identification according to claim 1, characterized in that: The chemical composition data of the root secretions of each plant planting area are obtained, and the plant planting areas in abnormal state are obtained by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area, specifically: Acquire the chemical composition data of the root secretions of each plant planting area, construct a timestamp, and construct the chemical composition data of the root secretions of each plant planting area based on the time series in combination with the timestamp; Taking the chemical composition data of the root secretions of each plant planting area at each timestamp as a state value, and presetting a state threshold, and judging whether the state value is greater than the state threshold; When the state value is greater than the state threshold, the plant planting area whose state value is greater than the state threshold is regarded as a plant planting area in an abnormal state; When the state value is not greater than the state threshold, the plant planting area whose state value is not greater than the state threshold is taken as a plant planting area in a normal state.

3. The method for evaluating plant growth environment based on root exudate data identification according to claim 1, characterized in that: Obtain the environmental characteristic data in the target area and the chemical composition data of the root secretions in the abnormal plant planting area, and combine with the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of plant roots, specifically: Acquire environmental characteristic data in the target area and chemical composition data of root secretions in the plant planting area in an abnormal state, and input the chemical composition data of root secretions in the plant planting area in an abnormal state into the knowledge graph for data matching; Obtain estimated colony data of each plant planting area, and perform big data retrieval based on the estimated colony data of each plant planting area, and obtain the survival rate of each colony data under each environmental characteristic data through the big data; According to the survival rate of each colony data under each environmental characteristic data and the estimated colony data of each plant planting area, the survival rate data of the estimated colony data in each plant planting area are obtained, and a survival rate threshold is set; Obtain the estimated colony data corresponding to the survival rate data greater than the survival rate threshold, search through big data, obtain the possible disease types of plant root growth corresponding to each estimated colony data, and output the possible disease types of plant root growth.

4. The method for evaluating plant growth environment based on root exudate data identification according to claim 1, characterized in that: Early warning is given based on the types of diseases that may occur in the root growth of the plant, specifically: Obtaining estimated environmental change characteristic data within a preset time through big data, and searching through big data in combination with the estimated environmental change characteristic data within the preset time and the types of diseases that may be caused by plant root growth; By searching, the reproduction rate of the disease type that may be caused by the growth of the plant root system in each plant planting area is obtained, and the reproduction rate under the estimated environmental change characteristic data is calculated according to the reproduction data of the disease type that may be caused by the growth of the plant root system in each plant planting area; A reproduction rate threshold is set, and when the reproduction rate is greater than the reproduction rate threshold, geographical location information of the corresponding plant planting area is obtained, and an early warning is issued according to the geographical location information of the corresponding plant planting area.

5. The method for evaluating plant growth environment based on root exudate data identification according to claim 1, characterized in that: Generate relevant protection strategies based on the types of diseases that may occur in the root growth of the plant, specifically: Obtaining protection strategies for each root disease type through big data, inputting the protection strategies for each root disease type into the knowledge graph for storage, and inputting the types of diseases that may be caused by the plant root growth into the knowledge graph for data matching; Through data matching, the protection roughness corresponding to each plant planting area is obtained, and the protection roughness corresponding to the plant planting area is displayed in a preset manner.

6. A plant growth environment assessment system based on root exudate data identification, characterized in that: The system includes a memory and a processor, wherein the memory includes a program for a plant growth environment assessment method based on root exudation data identification. When the program for a plant growth environment assessment method based on root exudation data identification is executed by the processor, the steps of the plant growth environment assessment method based on root exudation data identification as described in any one of claims 1 to 5 are implemented.

7. A terminal device, characterized in that: include: A knowledge graph construction module collects plant root exudate extracts, extracts chemical components from the plant root exudate extracts, obtains chemical component data of the root exudates, and constructs a knowledge graph based on the chemical component data of the root exudates; A state recognition module is used to obtain the chemical composition data of the root secretions of each plant planting area, and to obtain the plant planting area in an abnormal state by evaluating and analyzing the chemical composition data of the root secretions of each plant planting area; The classification module obtains the environmental characteristic data in the target area and the chemical composition data of the root secretions in the abnormal plant planting area, and combines the knowledge graph analysis to obtain the types of diseases that may be caused by the growth of plant roots; A protection strategy analysis module, which issues an early warning based on the types of diseases that may be caused by the growth of the plant root system, and generates relevant protection strategies based on the types of diseases that may be caused by the growth of the plant root system; Collecting plant root exudate extracts, and extracting chemical components from the plant root exudate extracts to obtain chemical component data of the root exudates, and constructing a knowledge graph based on the chemical component data of the root exudates, specifically including: Collecting root exudate extracts of plants, extracting chemical components from the root exudate extracts of plants, obtaining chemical component data of the root exudates, and collecting colony data when the root exudates appear; Counting the colony data when each type of root secretion appears, obtaining the historical colony data when each root secretion appears, and constructing a knowledge graph, introducing a graph neural network, and inputting the historical colony data when each root secretion appears into the knowledge graph; Taking the root exudate type as the first node and the colony data as the second node, constructing a directed connection description relationship, and connecting the first node and the second node based on the directed connection description relationship to construct a topological structure diagram; A relevant adjacency matrix is ​​obtained according to the topological structure diagram, and the relevant adjacency matrix is ​​input into the knowledge graph for storage.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program for a method for assessing a plant growth environment based on root exudation data identification. When the program for assessing a plant growth environment based on root exudation data identification is executed by a processor, the steps of the method for assessing a plant growth environment based on root exudation data identification as described in any one of claims 1 to 5 are implemented.

Images