A method and device for predicting species diversity of soil seed bank in alpine sandy land
The method improves species diversity prediction in alpine sandy areas by random sampling and updating prediction functions using a knowledge graph, addressing inefficiencies and inaccuracies in existing methods.
Patent Information
- Application Number
- CN202411320735.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-23
AI Technical Summary
Predicting species diversity in soil seed banks of alpine sandy areas is challenging due to environmental fluctuations, sparse vegetation, and inefficient manual monitoring methods, leading to inaccurate prediction results.
A method involving random sampling of species points, determining node types based on a knowledge graph, and updating species diversity prediction functions using environmental parameter adjustments to ensure accuracy and reduce manual workload.
Enhances the accuracy of species diversity prediction in alpine sandy areas by reducing manual effort and maintaining prediction function efficiency despite environmental changes.
Smart Images

Figure CN118839828B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of plant monitoring, and in particular to a method and device for predicting species diversity in a soil seed bank in alpine sandy areas. Background Art
[0002] Alpine sandy land is usually located at high altitude or high latitude, with low annual average temperature and long freezing period, which poses a severe challenge to the preservation and germination of soil seed bank. Low temperature may inhibit the germination rate of seeds and affect the expression of species diversity. At the same time, the sandy environment is usually dry and windy, which not only increases the risk of soil erosion, but also may affect the distribution and density of soil seed bank through the action of wind. Sandy soil has loose texture and poor water and fertilizer retention capacity. Sandy soil is often nutrient-poor, which limits the growth and reproduction of plants. In addition, the vegetation in alpine sandy land is usually sparse, and the diversity of aboveground vegetation is low, which may lead to relatively low species diversity in soil seed bank. Therefore, due to the influence of multiple factors such as climatic conditions, soil characteristics, sparse vegetation, ecological fragility, human factors, temporal dynamic changes, spatial heterogeneity, etc., it is difficult to predict the species diversity of soil seed bank in alpine sandy land.
[0003] In the existing technology, for large areas of alpine sandy land, a large number of fixed collection points are often preset in the area, and the species diversity of the soil seed bank in the large area of alpine sandy land is monitored regularly through soil sample collection, experimental treatment, species analysis and other processes. This type of method brings a lot of manual work and is inefficient. Some studies also consider establishing a corresponding species diversity prediction model for each collection point to regularly calculate the species diversity at different locations in large areas of alpine sandy land. However, the diversity of the soil seed bank in the alpine sandy area is very susceptible to fluctuations in environmental parameters, which makes the prediction results obtained after the prediction model runs for a period of time inaccurate. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for predicting species diversity in a soil seed bank in an alpine sandy area.
[0005] In a first aspect, an embodiment of the present invention provides a method for predicting species diversity in a soil seed bank in an alpine sandy area, the method comprising:
[0006] Randomly sample multiple species sampling points from a set of multiple preset species collection points in the target alpine sandy soil area;
[0007] Determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point;
[0008] Comparing the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determining whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point;
[0009] According to the node type of the species sampling point, the species collection point association knowledge graph is read to determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point or an unreliable sampling point;
[0010] According to the node type of each node in the set of species collection points, the species diversity prediction function corresponding to each node in the set of species collection points is updated, and the actual seed library species diversity value corresponding to each node is determined according to the updated species diversity prediction function of each node.
[0011] Optionally, the step of reading the species collection point association knowledge graph according to the node type of the species sampling point and determining whether the node type of each node in the set of species collection points is a reliable sampling point, a semi-reliable sampling point or an unreliable sampling point specifically includes:
[0012] According to the position of the species sampling point whose node type is a reliable node in the species collection point association knowledge graph, all species collection points on the existing path with any two reliable nodes as the starting point and the end point are determined to be reliable nodes;
[0013] For the remaining nodes in the set of species collection points, all species collection points on the existing path with a reliable node and an unreliable node as the starting point and the end point respectively are determined as semi-reliable nodes;
[0014] The remaining nodes in the set of species collection points are determined to be unreliable nodes.
[0015] Optionally, updating the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points specifically includes:
[0016] For a node whose node type in the set of species collection points is a reliable node, retaining a species diversity prediction function corresponding to the node;
[0017] For a node whose node type in the set of species collection points is an unreliable node, reconstructing a corresponding species diversity prediction function according to current environmental parameters corresponding to the species collection point;
[0018] For nodes whose node type in the set of species collection points is a semi-reliable node, the corresponding species diversity prediction function is corrected according to the values in the entity relationships of all triples on the existing paths in the species collection point association knowledge graph.
[0019] Optionally, the correcting of the corresponding species diversity prediction function according to the values in the entity relationships of all triples on the existing paths in the knowledge graph of species collection point associations specifically includes:
[0020] Accumulating the values in the entity relationships of all triples between the species collection point and the endpoint whose node type is a reliable node on the existing path to obtain a reliable parameter adjustment weight;
[0021] Accumulating the values in the entity relationships of all triples between the species collection point and the endpoint whose node type is an unreliable node on the existing path to obtain an unreliable parameter adjustment weight;
[0022] The reliable parameter adjustment weight and the unreliable parameter adjustment weight are used as interpolation weights to interpolate the species diversity prediction functions corresponding to the two endpoints on the existing path to obtain a revised species diversity prediction function corresponding to the species collection point.
[0023] Optionally, after determining the actual seed bank species diversity value corresponding to each node, the method further includes:
[0024] Based on the main environmental parameters of the collection points of each species, the knowledge graph of the association degree of the collection points of the species is updated.
[0025] Optionally, updating the species collection point association knowledge graph based on the main environmental parameters of each species collection point specifically includes:
[0026] Cancel all the current triple structures of the knowledge graph of the association degree of the collection points of the species;
[0027] Compare the similarity of the main environmental parameters between each target species collection point in the species collection point association knowledge graph and any other species collection point that is geographically adjacent to it; if the similarity of the main environmental parameters is greater than a preset similarity threshold, establish a triple relationship with the target species collection point as the head entity, any one species collection point as the tail entity, and the similarity of the main environmental parameters as the value in the entity relationship.
[0028] Optionally, the environmental parameters include precipitation, temperature, humidity, soil water retention rate, soil nutrient content and the amount of major vegetation.
[0029] In a second aspect, an embodiment of the present invention provides a device for predicting species diversity in a soil seed bank in an alpine sandy land, the device comprising:
[0030] A random sampling module, for randomly sampling a plurality of species sampling points from a set of a plurality of preset species collection points in a target alpine sandy soil area;
[0031] A node value determination module is used to determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point;
[0032] A sampling point judgment module is used to compare the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determine whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point;
[0033] A collection point judgment module is used to read the species collection point association knowledge graph according to the node type of the species sampling point, and determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point or an unreliable sampling point;
[0034] The diversity determination module is used to update the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points, and determine the actual seed library species diversity value corresponding to each node according to the updated species diversity prediction function of each node.
[0035] In a third aspect, an embodiment of the present invention provides an electronic device, including:
[0036] one or more processors;
[0037] A memory for storing one or more programs;
[0038] When the one or more programs are executed by the one or more processors, the one or more processors execute the method as described in the first aspect.
[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having executable instructions stored thereon, wherein when the executable instructions are executed by a processor, the processor executes the method as described in the first aspect.
[0040] The alpine sandy soil seed bank species diversity prediction method, device, electronic device and storage medium provided by the embodiments of the present invention realize the updating of the species diversity prediction function of a large number of species collection points in the target area during regular monitoring of species diversity, thereby ensuring the accuracy of monitoring. At the same time, based on the data structure of the knowledge graph, a large amount of manual collection and analysis workload is reduced when updating the prediction function, saving the time of node classification and function update, and greatly improving the efficiency of each monitoring. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.
[0042] Figure 1 A schematic diagram of a process for predicting species diversity in a soil seed bank in alpine sandy land provided by an embodiment of the present invention;
[0043] Figure 2 A schematic diagram of a process flow of a species collection point classification method provided in an embodiment of the present invention;
[0044] Figure 3 A schematic flow chart of a method for correcting a species diversity prediction function of a semi-reliable node provided in an embodiment of the present invention;
[0045] Figure 4 A schematic diagram of a flow chart of a knowledge graph updating method provided in an embodiment of the present invention;
[0046] Figure 5 A schematic diagram of the structure of a device for predicting species diversity in a soil seed bank in alpine sandy land provided by an embodiment of the present invention;
[0047] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0048] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0049] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0050] Alpine sandy land is usually located at high altitude or high latitude, with low annual average temperature and long freezing period, which poses a severe challenge to the preservation and germination of soil seed bank. Low temperature may inhibit the germination rate of seeds and affect the expression of species diversity. At the same time, the sandy environment is usually dry and windy, which not only increases the risk of soil erosion, but also may affect the distribution and density of soil seed bank through the action of wind. Sandy soil has loose texture and poor water and fertilizer retention capacity. Sandy soil is often nutrient-poor, which limits the growth and reproduction of plants. In addition, the vegetation in alpine sandy land is usually sparse, and the diversity of aboveground vegetation is low, which may lead to relatively low species diversity in soil seed bank. Therefore, due to the influence of multiple factors such as climatic conditions, soil characteristics, sparse vegetation, ecological fragility, human factors, temporal dynamic changes, spatial heterogeneity, etc., it is difficult to predict the species diversity of soil seed bank in alpine sandy land.
[0051] In the existing technology, for large areas of alpine sandy land, a large number of fixed collection points are often preset in the area, and the species diversity of the soil seed bank in the large area of alpine sandy land is monitored regularly through soil sample collection, experimental treatment, species analysis and other processes. This type of method brings a lot of manual work and is inefficient. Some studies also consider establishing a corresponding species diversity prediction model for each collection point to regularly calculate the species diversity at different locations in large areas of alpine sandy land. However, the diversity of the soil seed bank in the alpine sandy area is very susceptible to fluctuations in environmental parameters, which makes the prediction results obtained after the prediction model runs for a period of time inaccurate.
[0052] Based on this, the embodiment of the present invention provides a method for predicting species diversity in the soil seed bank of alpine sandy land. Figure 1 A schematic flow chart of a method for predicting species diversity in a soil seed bank in alpine sandy land provided by an embodiment of the present invention is shown, which specifically includes steps S110 to S150.
[0053] Step S110, randomly sampling a plurality of species sampling points from a set of a plurality of preset species collection points in the target alpine sandy soil area.
[0054] Similar to the prior art, the embodiment of the present invention sets a plurality of preset species collection points in the target alpine sandy soil area. Since the target alpine sandy soil area to be studied is often large in area, the number of species collection points is generally in the range of tens to thousands of data volumes, and a customized design will be performed based on factors such as the area of the area and the regional environment. The simplest implementation method is to install collection equipment, sensors, analysis equipment, communication systems and other devices at almost uniform intervals in the target alpine sandy soil area to cover the entire target alpine sandy soil area. Similarly, for each species collection point, the embodiment of the present invention will establish a respective species diversity prediction model to predict the species diversity of each location, thereby realizing the monitoring of the number of species at different locations in the entire target alpine sandy soil area. The species diversity prediction model used can be implemented by a species diversity prediction function, such as a multiple linear regression function, a generalized linear function, a decision tree, a random forest, and the like.
[0055] Unlike the prior art, one of the goals of the embodiment of the present invention is to avoid the situation where the accuracy of the established species diversity prediction function gradually fails when the target alpine sandy soil area environment changes dynamically. It is understandable that when the species diversity prediction function gradually fails, each time the species diversity is determined, the species diversity prediction function corresponding to each species collection point needs to be recalculated. When the number of species collection points is large, the amount of calculation of the reconstructed function model will be too large, affecting the efficiency of species diversity determination. Therefore, when the embodiment of the present invention regularly determines the species diversity of each species collection point, it is necessary to randomly sample multiple species sampling points from the set of species collection points, and then predict the species diversity of the entire area based on these species sampling points to reduce the amount of calculation.
[0056] Step S120, determining the species diversity value of the current seed bank corresponding to each species sampling point, and determining the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point.
[0057] After randomly sampling multiple species sampling points, it is necessary to determine whether the species diversity prediction function corresponding to these species sampling points has become invalid due to environmental changes. Therefore, on the one hand, it is necessary to calculate the ideal seed bank species diversity value based on the previously determined species diversity prediction function, which is the current ideal value predicted by the existing model; on the other hand, it is also necessary to determine the current seed bank species diversity value corresponding to each species sampling point through processes such as sample collection, sample processing, seed analysis and counting. Sample collection can be done manually or automatically, and seed extraction can be done by physical or chemical methods, etc. This process is not specifically limited in the embodiments of the present invention.
[0058] Step S130, comparing the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determining whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point.
[0059] After obtaining the current seed bank species diversity value and the ideal seed bank species diversity value, the two values can be compared to determine whether the current measurement value meets the predicted ideal value. Specifically, the difference between the two values can be compared to determine whether it is less than a threshold. The threshold can be set to a smaller empirical value to allow for appropriate measurement errors and calculation errors. If the difference between the current seed bank species diversity value and the ideal seed bank species diversity value corresponding to a certain species sampling point is less than the threshold, it is considered that environmental changes have not affected the validity of the species diversity prediction function corresponding to the species sampling point, and the node type of the species sampling point is determined to be a reliable node; if the difference between the current seed bank species diversity value and the ideal seed bank species diversity value corresponding to a certain species sampling point is greater than or equal to the threshold, it is considered that environmental changes have affected the validity of the species diversity prediction function corresponding to the species sampling point, and the node type of the species sampling point is determined to be an unreliable node.
[0060] Step S140, according to the node type of the species sampling point, read the species collection point association knowledge graph, and determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point, or an unreliable sampling point.
[0061] After determining the node type of the species sampling point, the embodiment of the present invention needs to further determine the node type of each node in the set of species sampling points based on this information. This process requires the use of the data structure of the pre-established species sampling point association knowledge graph. Figure 2 A schematic flow chart of a species collection point classification method provided in an embodiment of the present invention is shown, which specifically includes steps S141 to S143.
[0062] Step S141, according to the position of the species sampling point whose node type is a reliable node in the species sampling point association knowledge graph, it is determined that all species sampling points on the existing path with any two reliable nodes as the starting point and the end point are reliable nodes.
[0063] Step S142: for the remaining nodes in the set of species collection points, all species collection points on the existing path with a reliable node and an unreliable node as the starting point and the end point respectively are determined as semi-reliable nodes.
[0064] Step S143: the remaining nodes in the set of species collection points are determined as unreliable nodes.
[0065] Different from the node types of species collection points being divided into two categories, the node types of species sampling points will be divided into three categories: reliable nodes, semi-reliable nodes, and unreliable nodes; that is, in the entire set of species sampling points, except for the species collection points initially randomly sampled, whose node types have been determined in step S130, the node types of other nodes in the set will be determined in steps S141~S143.
[0066] At this time, the species collection point association knowledge graph pre-established in the embodiment of the present invention is needed. The species collection point association knowledge graph is a knowledge graph structure used to determine the similarity between species collection points that are geographically adjacent in the target alpine sandy area. Each species collection point is a node in the species collection point association knowledge graph. If the similarity of the main environmental parameters of two species collection points that are geographically adjacent is high, a triple structure can be established in the knowledge graph with the two species collection points as the head entity and the tail entity respectively, and the similarity of the main environmental parameters of the two species collection points as the numerical value in the entity relationship. The many triple structures thus established constitute the content of the entire species collection point association knowledge graph. Among them, the concept of geographical proximity in the embodiment of the present invention is that all species collection points in the target alpine sandy soil area are generally set at almost uniform intervals in the area. Therefore, for any species collection point, the species collection points within a preset distance value can be regarded as geographically adjacent collection points. In addition, the environmental parameters in the embodiment of the present invention include multiple parameters such as precipitation, temperature, humidity, soil water retention rate, soil nutrient content, and the number of major vegetation, which are not listed one by one in the embodiment of the present invention. Theoretically, the number of all environmental factors that affect the species diversity of the alpine sandy soil seed bank is as high as dozens, and all of them can be used as parameters to construct the species diversity prediction function corresponding to the species collection point. However, the prediction function constructed by dozens of parameters is relatively complex, which will greatly affect the calculation and maintenance efficiency. In actual operation, for the species diversity prediction function corresponding to each species collection point, the M environmental factors with the highest priority of the species collection point, for example, five, will be selected as the main environmental parameters to construct the species diversity prediction function, while ensuring the prediction accuracy and calculation and maintenance efficiency of the species diversity prediction function. The priority of the environmental factors can be calculated by performing principal component analysis on various environmental parameters collected by each sensor at the species collection point for a period of time. Therefore, in the embodiment of the present invention, the comparison of the similarity of environmental parameters between two species collection points is actually the comparison of the similarity of the main environmental parameters between the two species collection points.
[0067] Therefore, based on the triple relationship established in the knowledge graph of species collection point association, it can be determined whether there is an existing path between two nodes. According to the logic of triple establishment, it can be understood that the similarity of the main environmental parameters between two species collection points with existing paths is high.
[0068] Based on this, except for the species sampling points initially randomly sampled, whose node types have been determined in step S130, step S141 is first used to determine which nodes are reliable nodes among all other nodes in the set. All determination processes are based on species sampling points whose node types have been determined, similar to seed nodes. If two species sampling points whose node types are reliable nodes are connected by an existing path in the species collection point association knowledge graph, and the existing path is composed of multiple triples, it can be determined that the main environmental parameters of all nodes on the existing path have a certain degree of similarity, and these nodes are all reliable nodes. For nodes whose node types are reliable nodes in the set of species collection points, their environmental characteristic parameters often do not have obvious changes, and the species diversity prediction function corresponding to the node can be retained accordingly.
[0069] In addition to the species sampling points randomly sampled initially and the reliable nodes determined in step S141, step S142 is used to determine the semi-reliable nodes of the remaining other species collection points. If two species sampling points whose node types are respectively a reliable node and an unreliable node are connected by an existing path in the species collection point association knowledge graph, and the existing path is composed of multiple triples, it can be determined that the main environmental parameters of all nodes on the existing path will retain the original main environmental characteristics of the reliable node as the endpoint on the one hand, and will be affected by the new main environmental characteristics of the unreliable node as the other endpoint on the other hand. The embodiment of the present invention determines these nodes as semi-reliable nodes. For the nodes whose node type in the set of species collection points is a semi-reliable node, the corresponding species diversity prediction function is corrected according to the values in the entity relationships of all triples on the existing path in the species collection point association knowledge graph.
[0070] Attached Figure 3 A flow chart of a method for correcting a species diversity prediction function of a semi-reliable node in an embodiment of the present invention is shown, which specifically includes steps S142 - 1 to S142 - 3 .
[0071] Step S142-1, accumulating the values in the entity relationships of all triples between the species collection point and the endpoint whose node type is a reliable node on the existing path to obtain a reliable parameter adjustment weight;
[0072] Step S142-2, accumulating the values in the entity relationships of all triples between the species collection point and the endpoint whose node type is an unreliable node on the existing path to obtain an unreliable parameter adjustment weight;
[0073] Step S142-3, using the reliable parameter adjustment weight and the unreliable parameter adjustment weight as interpolation weights, interpolating the species diversity prediction functions corresponding to the two endpoints on the existing path to obtain a modified species diversity prediction function corresponding to the species collection point.
[0074] It can be seen that for semi-reliable nodes, in order to take into account the original environmental characteristics and newly added environmental characteristics of the two endpoints on the existing path, the main environmental characteristics of the two endpoints can be interpolated and calculated by linear interpolation. It can be understood that as a species sampling point at the endpoint of a reliable node, when it is confirmed as a reliable node, its main environmental parameters should remain unchanged adaptively; while as a species sampling point at the endpoint of another unreliable node, when it is confirmed as an unreliable node, its main environmental parameters should be updated according to the new environmental parameter collection results.
[0075] Therefore, when modifying the species diversity prediction function of the species collection points on such existing paths, it is necessary to interpolate the main environmental parameters of the two endpoints, and the interpolation weights of the two endpoints are determined by the sum of the values in the entity relationships in the subpaths from the species collection points to the two endpoints. For example, the species diversity prediction function of the reliable node endpoint is , the species diversity prediction function after reconstruction of unreliable node endpoints is: ; Accumulate the values of the entity relationships of all triples between the species collection point on the existing path and the endpoint whose node type is a reliable node to obtain the reliable parameter adjustment weight , accumulate the values of all triples in the entity relationship between the species collection point and the endpoint of the node type unreliable node on the existing path to obtain the unreliable parameter adjustment weight The corrected species diversity prediction function of the species collection point is:
[0076]
[0077] Except for the species sampling points randomly sampled initially, the reliable nodes determined in step S141, and the semi-reliable nodes determined in step S142, all the remaining species collection points are determined as unreliable nodes in step S143. In the embodiment of the present invention, for the unreliable nodes, whether they are the unreliable nodes of the species sampling points determined in step S130 or the unreliable nodes in the remaining nodes determined in step S143, the species diversity prediction function can be reconstructed according to the re-determined main environmental factors.
[0078] Step S150, updating the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points, and determining the actual seed library species diversity value corresponding to each node according to the updated species diversity prediction function of each node.
[0079] Based on the above steps, the species diversity prediction functions of all nodes in the set of species collection points in the target alpine sandy soil area have been determined, and finally the actual seed bank species diversity value corresponding to each node is determined according to the updated species diversity prediction function of each node to obtain the final result.
[0080] In summary, all nodes are divided into five categories: (1) reliable nodes among species sampling points; (2) unreliable nodes among species sampling points; (3) reliable nodes among non-species sampling points; (4) semi-reliable nodes among non-species sampling points; and (5) unreliable nodes among non-species sampling points. In the classification process, only the nodes of categories (1) and (2) as species sampling points need to be classified by manually collecting soil data and analyzing it, which involves a large amount of calculation. These two types of nodes generally account for only 5% to 10% of all species collection points, which is determined according to the density of random sampling in step S110. In the process of updating the species diversity prediction function, only the nodes of categories (2) and (5) need to re-collect soil data manually and reconstruct the data after analysis, which involves a large amount of calculation. These two types of nodes generally account for only 0% to 5% of all species collection points. The species diversity prediction functions of other nodes will be retained or only modified through mathematical calculations. It can be seen from this that the diversity of soil seed banks in high-altitude sandy areas is very susceptible to fluctuations in environmental parameters, which makes the prediction results obtained after the prediction model has been running for a period of time inaccurate. If the species diversity prediction function corresponding to each species collection point is to be reconstructed every time the species diversity data is monitored regularly, the monitoring efficiency will be greatly reduced.
[0081] In addition, after the prediction of the actual seed bank species diversity values of the species collection points in the target alpine sandy soil area is completed regularly each time, it is necessary to update the species collection point association knowledge graph based on the main environmental parameters of each species collection point. Figure 4 A flow chart of the knowledge graph updating method provided in an embodiment of the present invention is shown, which specifically includes steps S410 to S420.
[0082] Step S410, canceling all current triple structures of the species collection point association knowledge graph.
[0083] Step S420, compare the similarity of the main environmental parameters between each target species collection point in the species collection point association knowledge graph and any other species collection point that is geographically adjacent to it; if the similarity of the main environmental parameters is greater than a preset similarity threshold, establish a triple relationship with the target species collection point as the head entity, any one species collection point as the tail entity, and the similarity of the main environmental parameters as the value in the entity relationship.
[0084] After canceling all current triple structures, the process of re-establishing triples is similar to the process of initially creating the triple content of the species collection point association knowledge graph, which will not be repeated here.
[0085] The method for predicting species diversity of the soil seed bank in alpine sandy areas provided by the embodiment of the present invention, in the face of the fact that the diversity of the soil seed bank in alpine sandy areas is very easily affected by fluctuations in environmental parameters, can update the species diversity prediction function of a large number of species collection points in the target area during regular monitoring of species diversity, thereby ensuring the accuracy of monitoring; at the same time, based on the data structure of the knowledge graph, it reduces a large amount of manual collection and analysis workload when updating the prediction function, saves time for node classification and function updating, and greatly improves the efficiency of each monitoring.
[0086] Based on any of the above embodiments, Figure 5 The schematic diagram of the structure of the species diversity prediction device of the alpine sandy soil seed bank provided by the embodiment of the present invention is shown, and the specific contents are as follows:
[0087] A random sampling module 510 is used to randomly sample a plurality of species sampling points from a set of a plurality of preset species collection points in a target alpine sandy soil region;
[0088] The node value determination module 520 is used to determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point;
[0089] The sampling point judgment module 530 is used to compare the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determine whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point;
[0090] The collection point judgment module 540 is used to read the species collection point association knowledge graph according to the node type of the species sampling point, and determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point, or an unreliable sampling point;
[0091] The diversity determination module 550 is used to update the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points, and determine the actual seed library species diversity value corresponding to each node according to the updated species diversity prediction function of each node.
[0092] The alpine sandy soil seed bank species diversity prediction device provided by the embodiment of the present invention realizes the updating of the species diversity prediction function of a large number of species collection points in the target area during regular monitoring of species diversity, thereby ensuring the accuracy of monitoring. At the same time, based on the data structure of the knowledge graph, a large amount of manual collection and analysis workload is reduced when updating the prediction function, saving the time of node classification and function update, and greatly improving the efficiency of each monitoring.
[0093] Based on any of the above embodiments, Figure 6 The physical structure diagram of the electronic device provided by the embodiment of the present invention is shown, and the electronic device may include: a processor (processor) 610, a communication interface (CommunicationsInterface) 620, a memory (memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call the logic instructions in the memory 630 to execute the following method:
[0094] Randomly sample multiple species sampling points from a set of multiple preset species collection points in the target alpine sandy soil area;
[0095] Determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point;
[0096] Comparing the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determining whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point;
[0097] According to the node type of the species sampling point, the species collection point association knowledge graph is read to determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point or an unreliable sampling point;
[0098] According to the node type of each node in the set of species collection points, the species diversity prediction function corresponding to each node in the set of species collection points is updated, and the actual seed library species diversity value corresponding to each node is determined according to the updated species diversity prediction function of each node.
[0099] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0100] On the other hand, an embodiment of the present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including:
[0101] Randomly sample multiple species sampling points from a set of multiple preset species collection points in the target alpine sandy soil area;
[0102] Determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank according to the species diversity prediction function corresponding to the species sampling point;
[0103] Comparing the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determining whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point;
[0104] According to the node type of the species sampling point, the species collection point association knowledge graph is read to determine whether the node type of each node in the set of the species collection points is a reliable sampling point, a semi-reliable sampling point or an unreliable sampling point;
[0105] According to the node type of each node in the set of species collection points, the species diversity prediction function corresponding to each node in the set of species collection points is updated, and the actual seed library species diversity value corresponding to each node is determined according to the updated species diversity prediction function of each node.
[0106] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for predicting species diversity in alpine sandy soil seed banks, characterized in that: The method comprises: Randomly sample multiple species sampling points from a set of multiple pre-set species collection points in the target alpine sandy soil area; Determine the species diversity value of the current seed bank corresponding to each species sampling point, and determine the species diversity value of the ideal seed bank based on the species diversity prediction function corresponding to the species sampling point; Comparing the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determining whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point; According to the position of the species sampling points with the node type of reliable node in the species collection point association knowledge map, all species collection points on the existing path with any two reliable nodes as the starting point and the end point are determined to be reliable nodes; For the remaining nodes in the set of species collection points, all species collection points on the existing path with a reliable node and an unreliable node as the starting point and the end point are determined as semi-reliable nodes; The remaining nodes in the set of species collection points are determined to be unreliable nodes; updating the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points, and determining the actual seed bank species diversity value corresponding to each node according to the updated species diversity prediction function of each node; Among them, each species collection point is a node in the species collection point association knowledge graph. Based on the similarity of the main environmental parameters of two geographically adjacent species collection points, a triple structure is established in the species collection point association knowledge graph with the two species collection points as the head entity and the tail entity respectively and the similarity of the main environmental parameters of the two species collection points as the numerical value in the entity relationship; the main environmental parameters include precipitation, temperature, humidity, soil water retention rate, soil nutrient content and the number of major vegetation.
2. The method according to claim 1, characterized in that The updating of the species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points specifically includes: For nodes whose node type in the set of species collection points is a reliable node, retaining the species diversity prediction function corresponding to the node; For a node whose node type in the set of species collection points is an unreliable node, reconstructing a corresponding species diversity prediction function according to current environmental parameters corresponding to the node; For nodes whose node type in the set of species collection points is a semi-reliable node, the corresponding species diversity prediction function is modified according to the values in the entity relationships of all triples on the existing paths in the species collection point association knowledge graph.
3. The method according to claim 2, characterized in that The method of modifying the corresponding species diversity prediction function according to the values in the entity relationships of all triples on the existing paths in the knowledge graph of species collection point association specifically includes: Accumulating the values of the entity relationships of all triples between the species collection point and the endpoint of the node type being a reliable node on the existing path to obtain a reliable parameter adjustment weight; Accumulating the values of the entity relationships of all triples between the species collection point and the endpoint of the node type being an unreliable node on the existing path to obtain an unreliable parameter adjustment weight; The species diversity prediction function corresponding to the two endpoints on the existing path is interpolated using the reliable parameter adjustment weight and the unreliable parameter adjustment weight as interpolation weights to obtain a revised species diversity prediction function corresponding to the species collection point.
4. The method according to claim 1, wherein After determining the actual seed bank species diversity value corresponding to each node, the method further includes: Based on the main environmental parameters of the collection points of each species, the knowledge graph of the association degree of the collection points of the species is updated.
5. The method according to claim 4, characterized in that The updating of the species collection point association knowledge graph based on the main environmental parameters of each species collection point specifically includes: Cancel all current triple structures of the knowledge graph of the association degree of the collection points of the species; Compare the similarity of the main environmental parameters between each target species collection point in the species collection point association knowledge graph and any other species collection point geographically adjacent to it; if the similarity of the main environmental parameters is greater than a preset similarity threshold, establish a triple relationship with the target species collection point as the head entity, the any species collection point as the tail entity, and the similarity of the main environmental parameters as the value in the entity relationship.
6. A device for predicting species diversity in alpine sandy soil seed banks, characterized in that: The device comprises: A random sampling module is used to randomly sample multiple species sampling points from a set of multiple preset species collection points in the target alpine sandy soil area; A node value determination module is used to determine the species diversity value of the current seed bank corresponding to each species sampling point, and to determine the species diversity value of the ideal seed bank based on the species diversity prediction function corresponding to the species sampling point; A sampling point judgment module is used to compare the species diversity value of the current seed bank corresponding to each species sampling point with the species diversity value of the ideal seed bank, and determine whether the node type of the species sampling point is a reliable sampling point or an unreliable sampling point; The collection point judgment module is used to determine that all species collection points on an existing path with any two reliable nodes as the starting point and the end point are reliable nodes based on the position of the species sampling points with the node type being a reliable node in the species collection point association knowledge map; for the remaining nodes in the set of species collection points, all species collection points on the existing path with one reliable node and one unreliable node as the starting point and the end point are semi-reliable nodes; for the remaining nodes in the set of species collection points, they are determined to be unreliable nodes; a diversity determination module, configured to update a species diversity prediction function corresponding to each node in the set of species collection points according to the node type of each node in the set of species collection points, and determine an actual seed bank species diversity value corresponding to each node according to the updated species diversity prediction function of each node; Among them, each species collection point is a node in the species collection point association knowledge graph. Based on the similarity of the main environmental parameters of two geographically adjacent species collection points, a triple structure is established in the species collection point association knowledge graph with the two species collection points as the head entity and the tail entity respectively and the similarity of the main environmental parameters of the two species collection points as the numerical value in the entity relationship; the main environmental parameters include precipitation, temperature, humidity, soil water retention rate, soil nutrient content and the number of major vegetation.
7. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors are enabled to perform the method according to any one of claims 1 to 5.
8. A computer-readable storage medium having executable instructions stored thereon, characterized in that: When the executable instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Marsh vegetation and soil seed bank species diversity prediction method and system
CN112416997A
Heterogeneous information network knowledge graph completion method and device based on matrix fusion
CN113420163A
Knowledge graph multivariate relation link prediction method based on graph transformation network
CN116757280A
Excellent multi-effect gene mining method, device, equipment and medium
CN117116355A
