Knowledge graph-based fruit tree water and fertilizer integrated intelligent irrigation method

Abstract

This application relates to the field of smart agriculture technology, and provides a knowledge graph-based intelligent irrigation method for fruit trees integrating water and fertilizer. The method includes: obtaining a knowledge graph based on professional knowledge in the fruit tree water and fertilizer field; establishing a strategy library containing various fertilization elements and professional knowledge in the fruit tree water and fertilizer field based on the knowledge graph and fruit tree fertilization examples; constructing a fertilization strategy similarity calculation model in the orchard water and fertilizer field by integrating the semantic structure similarity of the orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation examples based on the knowledge graph and the strategy library; and matching the optimal irrigation strategy when a fertilization element is received by combining the similarity calculation model with a reasoning mechanism. This application can accurately and quickly match and invoke fertilization strategies, effectively avoiding unreasonable situations such as water and fertilizer deficiencies in fruit trees.

Description

Technical Field

[0001] This application belongs to the field of smart agriculture technology, and in particular relates to a smart irrigation method for fruit trees based on knowledge graphs that integrates water and fertilizer. Background Technology

[0002] The integrated water and fertilizer technology can improve water resource utilization and effectively control fertilizer concentration within the ideal range during operation, thus promoting crop root development and nutrient absorption. It is being used more and more widely in farmland, orchards, and greenhouses.

[0003] However, in practice, it has been found that existing integrated water and fertilizer technology, especially in the field of fruit tree water and fertilizer, is difficult to accurately and quickly match and apply fertilization strategies, resulting in frequent occurrences of unreasonable situations such as water and fertilizer shortages in fruit trees. Summary of the Invention

[0004] This application provides a knowledge graph-based intelligent irrigation method for fruit trees with integrated water and fertilizer management to solve the above-mentioned technical problems.

[0005] The first aspect of this application provides a knowledge graph-based intelligent irrigation method for fruit trees integrating water and fertilizer, including:

[0006] A knowledge graph was obtained based on professional knowledge in the field of fruit tree water and fertilizer;

[0007] Based on knowledge graphs and fruit tree fertilization examples, a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer was established.

[0008] Based on knowledge graphs and policy bases, a similarity calculation model for fertilization strategies in the orchard water and fertilizer domain is constructed by integrating the semantic structure similarity of the orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances.

[0009] When fertilization factors are received, the optimal irrigation strategy is matched by combining a similarity calculation model with an inference mechanism.

[0010] Furthermore, the knowledge graph obtained based on professional knowledge in the field of fruit tree water and fertilizer specifically includes:

[0011] Based on expertise in fruit tree water and fertilizer, a knowledge graph was constructed using a bottom-up approach.

[0012] Furthermore, the knowledge graph obtained based on professional knowledge in the field of fruit tree water and fertilizer specifically includes:

[0013] Collect professional knowledge in the field of fruit tree water and fertilizer, and perform part-of-speech tagging on professional terms in the field of fruit tree water and fertilizer;

[0014] Summarize and analyze the hierarchical and attribute relationships among various professional terms, describe the knowledge attributes in the field of fruit tree water and fertilizer, and define the attribute types.

[0015] By constructing classes and attributes of domain knowledge and combining them with instances, a knowledge graph is obtained.

[0016] Furthermore, the strategy library, which includes various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer, is established based on knowledge graphs and fruit tree fertilization examples. Specifically,

[0017] Structured, semi-structured, and unstructured knowledge related to orchard water and fertilizer management is categorized and stored. Structured knowledge is stored using relational data stores like MySQL and Oracle; the structured portion of semi-structured knowledge is stored in a relational database, while the unstructured portion is stored on hard drives and servers. Unstructured knowledge is stored on hard drives. Knowledge representation is achieved using XML and OWL ontology languages. Knowledge retrieval primarily involves parsing OWL and XML data using parsing tools to represent the knowledge.

[0018] A database of fruit tree fertilization strategies was established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as the regional, variety, target yield, and growth stage attributes of fruit tree water and fertilizer examples.

[0019] Furthermore, based on knowledge graphs and strategy bases, a similarity calculation model for fertilization strategies in the orchard water and fertilizer domain is constructed by integrating the semantic structure similarity of the orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances. The formula is as follows:

[0020]

[0021] In the above formula, The weights correspond to irrigation attribute elements, the semantic structure of the ontology, and fertilization irrigation instances, respectively. It refers to the similarity of water and fertilizer irrigation attributes in orchards, including irrigation attributes such as irrigation time, location, fruit tree variety, and expected yield. This refers to the semantic structural similarity of the orchard domain ontology; This refers to the similarity of fertilization and irrigation instances in the strategy library; .

[0022] Furthermore, when fertilization factors are received, the optimal irrigation strategy is matched through a similarity calculation model combined with an inference mechanism, including the following:

[0023] Irrigation strategies are screened based on the received fertilization factors, and the screened irrigation strategies are calculated using a similarity calculation model to obtain at least one fertilization strategy.

[0024] The fertilization strategy is derived from a pre-defined reasoning to obtain a recommended fertilization strategy.

[0025] The recommended fertilization strategy is evaluated based on the preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy.

[0026] Furthermore, the fertilization factors include the fruit tree stage, expected yield, location, and topography.

[0027] Furthermore, the fertilization strategy is derived from a preset inference to obtain a recommended fertilization strategy, specifically:

[0028] By combining the agenda of the Drools engine, rule reasoning is performed using local variables and the weights of elements.

[0029] Furthermore, the process of combining the Drools engine's agenda with rule reasoning using local variables and element weights is as follows:

[0030] Add fertilization strategies to the agenda, iteratively execute the rules in the agenda until a recommended fertilization strategy is obtained;

[0031] If there are conflicts between the matched rules, the conflicting rules need to be temporarily stored in the conflict set, and the rules will be activated and added to the agenda after the conflict is resolved.

[0032] Furthermore, the recommended fertilization strategy is evaluated according to preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy. Specifically:

[0033] Based on the preset evaluation criteria, the recommended fertilization strategy is evaluated to determine its rationality. If it is rational, it is output as the optimal irrigation strategy and applied directly. If it is not rational, it is continuously adjusted in conjunction with knowledge of fruit tree water and fertilizer until a rational water and fertilizer strategy is obtained.

[0034] As can be seen from the above, the embodiments of this application apply knowledge graphs to fruit tree water and fertilizer irrigation technology, which can accurately and quickly match and call fertilization strategies, effectively avoiding unreasonable situations such as fruit tree water shortage and fertilizer shortage.

[0035] A second aspect of this application provides a terminal including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect.

[0036] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect.

[0037] The fourth aspect of this application provides a computer program product that, when run on a terminal, causes the terminal to perform the steps of the method described in the first aspect. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic flowchart of the intelligent irrigation method for fruit trees based on knowledge graphs provided in the embodiments of this application;

[0040] Figure 2 This is a schematic diagram of the knowledge graph provided in an embodiment of this application;

[0041] Figure 3 This is a schematic diagram of the irrigation strategy output process provided in the embodiments of this application;

[0042] Figure 4 This is a schematic diagram of the preset inference mechanism structure provided in the embodiments of this application;

[0043] Figure 5 This diagram illustrates the 20 irrigation strategies with the highest similarity, derived from the example of sweet cherries. Detailed Implementation

[0044] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0045] It should be understood that, when used in this application specification and appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof. Furthermore, the sequence number of each step in the embodiments of this application does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0046] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0047] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0048] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0049] See Figure 1 , Figure 1 This is a schematic flowchart of a knowledge graph-based intelligent irrigation method for fruit trees, integrating water and fertilizer management, provided in an embodiment of this application. Figure 1 As shown, a knowledge graph-based intelligent irrigation method for fruit trees integrating water and fertilizer management includes the following steps:

[0050] Step 101: Based on professional knowledge in the field of fruit tree water and fertilizer, construct a knowledge graph in a bottom-up manner;

[0051] Step 102: Based on the knowledge graph and fruit tree fertilization examples, establish a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer.

[0052] Step 103: Based on the knowledge graph and strategy base, construct a similarity calculation model for fertilization strategies in the orchard water and fertilizer domain by integrating the semantic structure similarity of the orchard domain ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances.

[0053] Step 104: When fertilization factors are received, the optimal irrigation strategy is matched by combining a similarity calculation model with an inference mechanism.

[0054] It should be noted that a knowledge graph is a network graph rich in semantic information; essentially, it is a graph-based data structure. There are three main construction methods for knowledge graphs: top-down, bottom-up, and a combination of both.

[0055] The top-down approach requires first creating a knowledge base, and then extracting entity information from the large amount of collected data and adding it to the knowledge base.

[0056] The bottom-up approach involves first extracting entities from the data, and then adding the obtained entities, relationships, and attributes to the knowledge graph after processing such as entity alignment, semantic fusion, and information merging.

[0057] The combined approach requires first building a basic schema layer from a large amount of data, then continuously mining more valuable knowledge to update the schema layer, and finally designing a mapping from the schema layer to the data layer to populate entities and form a relatively complete knowledge graph.

[0058] Obviously, by comparing the three different ways of constructing knowledge graphs, it can be seen that the embodiment of this application constructs knowledge graphs in a bottom-up manner, which is very suitable for the data knowledge construction needs of the fruit tree water and fertilizer field, which has a large amount of data and complex intersections between data. Therefore, it effectively improves the reliability and usability of knowledge graphs in the fruit tree water and fertilizer field.

[0059] In this embodiment of the application, step 101 involves constructing a knowledge graph in a bottom-up manner based on professional knowledge in the field of fruit tree water and fertilizer, such as... Figure 2 As shown, it can include the following:

[0060] Collect professional knowledge in the field of fruit tree water and fertilizer, and perform part-of-speech tagging on professional terms in the field of fruit tree water and fertilizer;

[0061] Summarize and analyze the hierarchical and attribute relationships among various professional terms, describe the knowledge attributes in the field of fruit tree water and fertilizer, and define the attribute types.

[0062] By constructing classes and attributes of domain knowledge and combining them with instances, a knowledge graph is obtained.

[0063] Since knowledge graphs play a fundamental role in similarity calculation models and optimal irrigation strategy output, a large amount of data was collected during the construction of the water knowledge graph to ensure the applicability of integrated water and fertilizer technology for fruit trees. At the same time, part-of-speech tagging ensured the relevance, professionalism and accuracy of the technology in the field of water and fertilizer for fruit trees.

[0064] In this embodiment of the application, step 102 involves establishing a fruit tree fertilization strategy library based on a knowledge graph and fruit tree fertilization examples. Specifically,

[0065] This system integrates database technologies to store, represent, and retrieve orchard water and fertilizer knowledge. It categorizes and stores structured, semi-structured, and unstructured knowledge based on these categories. Structured knowledge is stored using relational databases such as MySQL and Oracle; the structured portion of semi-structured knowledge is stored in a relational database, while the unstructured portion is stored on hard drives and servers. Unstructured knowledge is stored on hard drives. Knowledge representation is achieved using XML and OWL ontology languages. Knowledge retrieval primarily involves parsing OWL and XML data using a parsing tool to represent the knowledge.

[0066] A database of fruit tree fertilization strategies was established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as the regional characteristics, fruit tree varieties, target yields, and growth stages of fruit tree examples.

[0067] Clearly, since the entire strategy library is built based on fertilization instances, it is practically feasible.

[0068] In this embodiment of the application, step 103 involves constructing a fertilization strategy similarity calculation model for the orchard water and fertilizer domain based on the knowledge graph and strategy base, integrating the semantic structure similarity of the orchard domain ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances. The formula for the similarity calculation model is as follows:

[0069]

[0070] In the above formula, The weights correspond to irrigation attribute elements, the semantic structure of the ontology, and fertilization irrigation instances, respectively. It refers to the similarity of water and fertilizer irrigation attributes in orchards, including irrigation attributes such as irrigation time, location, fruit tree variety, and expected yield. This refers to the semantic structural similarity of the orchard domain ontology; This refers to the similarity of fertilization and irrigation instances in the strategy library; .

[0071] Clearly, the embodiments of this application, based on knowledge graphs and strategy bases, calculate the similarity of semantic structure of the orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances. The proposed fertilization strategy similarity calculation model in the orchard water and fertilizer domain, when receiving fertilization elements, matches the optimal irrigation strategy through a similarity calculation model combined with a reasoning mechanism. Therefore, it makes the fertilization strategy more reasonable, thereby making the cultivation of fruit trees more scientific and rational.

[0072] In this embodiment of the application, step 104, when fertilization factors are received, matching the optimal irrigation strategy through a similarity calculation model combined with an inference mechanism, may include the following:

[0073] like Figure 3 As shown, irrigation strategies are screened based on the received fertilization factors, and the screened irrigation strategies are calculated using a similarity calculation model to obtain at least one fertilization strategy.

[0074] The fertilization strategy is derived from a pre-defined reasoning to obtain a recommended fertilization strategy.

[0075] The recommended fertilization strategy is evaluated based on the preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy.

[0076] Among them, the fertilization factors can be the fruit tree stage, expected yield, location, topography, etc., and can be set according to needs, without being limited here;

[0077] For example, such as Figure 4 As shown, the fertilization strategy is derived from preset reasoning to obtain a recommended fertilization strategy. This can be achieved by combining the agenda of the Drools engine with the weights of elements using local variables for rule-based reasoning. Specifically,

[0078] Add fertilization strategies to the agenda, and iteratively execute the rules in these agendas until a recommended fertilization strategy is obtained;

[0079] If there are conflicts between the matched rules, the conflicting rules need to be temporarily stored in the conflict set, and the rules will be activated and added to the agenda after the conflict is resolved.

[0080] It should be noted that in actual operations, due to the numerous regional or natural constraints in agricultural operations, especially in water and fertilizer irrigation, the probability of such conflicts occurring is extremely low, and this issue can be ignored.

[0081] For example, the recommended fertilization strategy is evaluated based on preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy. Figure 5 As shown, it can be:

[0082] Based on the preset evaluation criteria, the recommended fertilization strategy is evaluated to determine its rationality. If it is rational, it is output as the optimal irrigation strategy and applied directly. If it is not rational, it is continuously adjusted in conjunction with knowledge of fruit tree water and fertilizer until a rational water and fertilizer strategy is obtained.

[0083] Obviously, the embodiments of this application use Drools rules based on similarity calculation as the reasoning mechanism, which can accurately and quickly match and call fertilization strategies while greatly reducing the risk of overfitting and preventing downtime.

[0084] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0085] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0086] The methods described in this application can be implemented in whole or in part by a computer program product. When the computer program product is run on a terminal, the terminal executes the steps in the various method embodiments described above.

[0087] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A knowledge graph-based intelligent irrigation method for fruit trees integrating water and fertilizer, characterized in that, include: A knowledge graph was obtained based on professional knowledge in the field of fruit tree water and fertilizer; Based on knowledge graphs and fruit tree fertilization examples, a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer was established. Based on knowledge graphs and policy bases, a similarity calculation model for fertilization strategies in the orchard water and fertilizer domain is constructed by integrating the semantic structure similarity of the orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances. When fertilization factors are received, the optimal irrigation strategy is matched by a similarity calculation model combined with an inference mechanism. The aforementioned strategy library, based on knowledge graphs and fruit tree fertilization examples, establishes a system containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer management. Structured, semi-structured, and unstructured knowledge related to orchard water and fertilizer management is categorized and stored. Structured knowledge is stored using relational data stores like MySQL and Oracle; the structured portion of semi-structured knowledge is stored in a relational database, while the unstructured portion is stored on hard drives and servers. Unstructured knowledge is stored entirely on hard drives. Knowledge representation is achieved using XML and OWL ontology languages. Knowledge retrieval is performed by parsing OWL and XML data using a parsing tool, followed by knowledge representation. A database of fruit tree fertilization strategies was established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as the regional, variety, target yield, and growth stage attributes of fruit tree water and fertilizer examples.

2. The method according to claim 1, characterized in that, The knowledge graph obtained based on professional knowledge in the field of fruit tree water and fertilizer is specifically as follows: Based on expertise in fruit tree water and fertilizer, a knowledge graph was constructed using a bottom-up approach.

3. The method according to claim 1, characterized in that, The knowledge graph obtained based on professional knowledge in the field of fruit tree water and fertilizer is specifically as follows: Collect professional knowledge in the field of fruit tree water and fertilizer, and perform part-of-speech tagging on professional terms in the field of fruit tree water and fertilizer; Summarize and analyze the hierarchical and attribute relationships among various professional terms, describe the knowledge attributes in the field of fruit tree water and fertilizer, and define the attribute types. By constructing classes and attributes of domain knowledge and combining them with instances, a knowledge graph is obtained.

4. The method according to claim 1, characterized in that, Based on knowledge graphs and policy bases, and integrating the semantic structure similarity of orchard ontology, the similarity of orchard water and fertilizer irrigation attribute elements, and the similarity of fertilization and irrigation instances, a fertilization strategy similarity calculation model is constructed in the orchard water and fertilizer domain. The formula is as follows: ； In the above formula, The weights correspond to irrigation attribute elements, the semantic structure of the ontology, and fertilization irrigation instances, respectively. It refers to the similarity of water and fertilizer irrigation attributes in orchards, including irrigation attributes such as irrigation time, location, fruit tree variety, and expected yield. This refers to the semantic structural similarity of the orchard domain ontology; This refers to the similarity of fertilization and irrigation instances in the strategy library; .

5. The method according to claim 1, characterized in that, When fertilization factors are received, the optimal irrigation strategy is matched through a similarity calculation model combined with an inference mechanism, including the following: Irrigation strategies are screened based on the received fertilization factors, and the screened irrigation strategies are calculated using a similarity calculation model to obtain at least one fertilization strategy. The fertilization strategy is derived from a pre-defined reasoning to obtain a recommended fertilization strategy. The recommended fertilization strategy is evaluated based on the preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy.

6. The method according to claim 5, characterized in that, The fertilization factors are the fruit tree stage, expected yield, location, and topography.

7. The method according to claim 5, characterized in that, The fertilization strategy is derived from a preset inference to obtain a recommended fertilization strategy, specifically: By combining the agenda of the Drools engine, rule reasoning is performed using local variables and the weights of elements.

8. The method according to claim 7, characterized in that, The agenda, combined with the Drools engine, employs a local variable approach combined with the weights of elements for rule-based reasoning, specifically as follows: Add fertilization strategies to the agenda, iteratively execute the rules in the agenda until a recommended fertilization strategy is obtained; If there are conflicts between the matched rules, the conflicting rules need to be temporarily stored in the conflict set, and the rules will be activated and added to the agenda after the conflict is resolved.

9. The method according to claim 5, characterized in that, The recommended fertilization strategy is evaluated according to preset evaluation criteria. When the evaluation criteria are met, it is output as the optimal irrigation strategy. Specifically: Based on the preset evaluation criteria, the recommended fertilization strategy is evaluated to determine its rationality. If it is rational, it is output as the optimal irrigation strategy and applied directly. If it is not rational, it is continuously adjusted in conjunction with knowledge of fruit tree water and fertilizer until a rational water and fertilizer strategy is obtained.

Images