Water and fertilizer integrated intelligent irrigation method for fruit trees based on knowledge graph

Abstract

The invention relates to the technical field of intelligent agriculture, and provides a knowledge graph-based fruit tree water and fertilizer integrated intelligent irrigation method, which comprises the following steps of: obtaining a knowledge graph according to professional knowledge in the field of fruit tree water and fertilizer; based on the knowledge graph and the fruit tree fertilization instance, establishing a strategy library containing each fertilization element and professional knowledge of the fruit tree water and fertilizer field; based on the knowledge graph and the strategy library, constructing a fertilization strategy similarity calculation model of the orchard water and fertilizer field by integrating the semantic structure similarity of the orchard field ontology, the similarity of the orchard water and fertilizer irrigation attribute elements and the fertilization irrigation instance similarity; and when the fertilization elements are received, matching an optimal irrigation strategy through a similarity calculation model in combination with an inference mechanism. The application can accurately and quickly match and call the fertilization strategy, and effectively avoid unreasonable conditions such as water shortage and fertilizer shortage of fruit trees.

Description

Technical Field

[0001] The present application belongs to the field of smart agricultural technology, and in particular, relates to a method for intelligent irrigation of fruit trees with integrated water and fertilizer based on a knowledge graph. Background Art

[0002] Integrated water-fertilizer technology can improve the utilization rate of water resources, and can effectively control the fertilizer concentration within the most ideal range during operation, better promote the development of crop roots and the absorption of nutrients, and is being used more and more widely in farmland, orchards, greenhouses, etc.

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

[0004] The embodiment of the present application provides an intelligent irrigation method for fruit trees integrating water and fertilizer based on a knowledge graph to solve the above-mentioned technical problems.

[0005] The first aspect of the embodiment of the present application provides a fruit tree water-fertilizer integrated intelligent irrigation method based on a knowledge graph, comprising: The knowledge graph is obtained based on the professional knowledge in the field of water and fertilizer for fruit trees; Based on the knowledge graph and fruit tree fertilization examples, a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer is established; Based on the knowledge graph and strategy library, the similarity of the semantic structure of the orchard domain ontology, the similarity of the orchard water, fertilizer and irrigation attribute elements, and the similarity of fertilization and irrigation instances are integrated to build a fertilization strategy similarity calculation model in the orchard water and fertilizer domain. When the fertilization elements are received, the optimal irrigation strategy is matched through the similarity calculation model combined with the reasoning mechanism.

[0006] Furthermore, the knowledge graph is obtained based on the professional knowledge in the field of water and fertilizer for fruit trees, specifically: Based on the professional knowledge in the field of water and fertilizer for fruit trees, a knowledge graph is constructed in a bottom-up manner.

[0007] Furthermore, the knowledge graph is obtained based on the professional knowledge in the field of water and fertilizer for fruit trees, specifically: Collect professional knowledge in the field of water and fertilizer for fruit trees, and perform part-of-speech tagging on professional terms in the field of water and fertilizer for fruit trees; Summarize and analyze the hierarchical relationship and attribute relationship between various professional terms, describe the knowledge attributes in the field of water and fertilizer for fruit trees, and define the attribute types; Construct the classes and attributes of domain knowledge and combine them with instances to obtain a knowledge graph.

[0008] Furthermore, based on the knowledge graph and the fruit tree fertilization example, a strategy library containing various fertilization elements and professional knowledge in the field of water and fertilizer for fruit trees is established, specifically, The structured, semi-structured and unstructured knowledge of water and fertilizer in orchards are stored by types. The structured knowledge is stored in MySQL and Oracle relational data, the structured part of the semi-structured knowledge is stored in relational database, and the unstructured part is stored in hard disk and server. The unstructured knowledge is stored in hard disk. The knowledge is represented by XML and OWL ontology language. The knowledge call is mainly performed by parsing OWL and XML forms through parsing tools to represent the knowledge, as well as: A fruit tree fertilization strategy library is established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as regional, fruit tree variety, target yield and fruit tree growth period attribute factors of fruit tree water and fertilizer examples.

[0009] Furthermore, based on the knowledge graph and the strategy library, the semantic structure similarity of the orchard domain ontology, the similarity of the orchard water, fertilizer and irrigation attribute elements, and the similarity of fertilization and irrigation instances are integrated to construct a fertilization strategy similarity calculation model in the orchard water and fertilizer domain, and the formula is as follows:

[0010] In the above formula, are weights, corresponding to irrigation attribute elements, ontology semantic structure and fertilization irrigation instances; It refers to the similarity of water, fertilizer and irrigation attribute elements in the orchard, where irrigation attributes include irrigation time, location, fruit tree variety and expected yield; It refers to the semantic structure similarity of the orchard domain ontology; It refers to the similarity of fertilization and irrigation instances in the strategy library; .

[0011] Furthermore, when the fertilization factor is received, the optimal irrigation strategy is matched by combining the similarity calculation model with the reasoning mechanism, including the following contents: Screening irrigation strategies according to the received fertilization factors, calculating the screened irrigation strategies through a similarity calculation model, and obtaining at least one fertilization strategy; The fertilization strategy is based on the preset reasoning, and the recommended fertilization strategy is obtained by reasoning; The recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy.

[0012] Furthermore, the fertilization factors are the fruit tree period, expected yield, location, and terrain.

[0013] Furthermore, the fertilization strategy is based on the preset reasoning, and the recommended fertilization strategy is inferred, specifically: Combined with the agenda of the Drools engine, the local variable method is used to combine the weights of the elements for rule reasoning.

[0014] Furthermore, the agenda of the Drools engine is combined with the weight of the elements to perform rule reasoning in a local variable manner, specifically: Add the fertilization strategy to the agenda and iteratively execute the rules in the agenda until the 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 activated and added to the agenda after the conflicts are resolved.

[0015] Furthermore, the recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy, specifically: According to the preset evaluation criteria, the recommended fertilization strategy is evaluated to see whether it is reasonable. If it is reasonable, it is output as the optimal irrigation strategy and directly applied. If it is unreasonable, it is continuously adjusted in combination with the knowledge in the field of water and fertilizer for fruit trees until a reasonable water and fertilizer strategy is obtained.

[0016] As can be seen from the above, the embodiment of the present application applies the knowledge graph to the water and fertilizer irrigation technology of fruit trees, which can accurately and quickly match and call fertilization strategies, and effectively avoid unreasonable situations such as water and fertilizer shortages in fruit trees.

[0017] A second aspect of an embodiment of the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0018] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0019] A fourth aspect of the present application provides a computer program product, which, when executed on a terminal, enables the terminal to execute the steps of the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1It is a flow chart of a method for intelligent irrigation of fruit trees with integrated water and fertilizer based on a knowledge graph provided in an embodiment of the present application; Figure 2 It is a schematic diagram of the knowledge graph provided in the embodiment of the present application; Figure 3 It is a schematic diagram of the irrigation strategy output process provided by an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of the preset reasoning mechanism provided in the embodiment of the present application; Figure 5 This is a schematic diagram of the 20 irrigation strategies with the highest similarity obtained by reasoning using sweet cherry as an example. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections, and: the size of the serial numbers of the steps in the embodiments of the present application does not mean the order of execution, and 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 the present application.

[0024] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0025] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0026] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0027] See also Figure 1 , Figure 1Schematic diagram of a process of an intelligent irrigation method for fruit tree water and fertilizer integration based on a knowledge graph provided in an embodiment of the present application. Figure 1 As shown, a method for intelligent irrigation of fruit trees with integrated water and fertilizer based on knowledge graph, the method comprises the following steps: Step 101, constructing a knowledge graph in a bottom-up manner based on professional knowledge in the field of water and fertilizer for fruit trees; Step 102, based on the knowledge graph and the fruit tree fertilization example, a strategy library including various fertilization elements and professional knowledge in the field of water and fertilizer for fruit trees is established; Step 103, based on the knowledge graph and the strategy library, the semantic structure similarity of the orchard domain ontology, the similarity of the orchard water, fertilizer and irrigation attribute elements, and the similarity of the fertilization and irrigation instances are integrated to construct a fertilization strategy similarity calculation model in the orchard water and fertilizer domain; Step 104, when the fertilization factor is received, the optimal irrigation strategy is matched through the similarity calculation model combined with the reasoning mechanism.

[0028] It should be noted that the knowledge graph is a network graph with rich semantic information. It is essentially a graph-based data structure. The construction mode of the knowledge graph mainly includes three ways: top-down, bottom-up and a combination of the two. The top-down model requires creating a knowledge base first, and then extracting entity information from a large amount of collected data and adding it to the knowledge base; The bottom-up model first extracts entities from the data, and then adds the obtained entities, relationships, and attributes to the knowledge graph after entity alignment, semantic fusion, and information merging. The construction model that combines the two requires first building the most basic model layer in a large amount of data, then updating the model layer by continuously mining more valuable knowledge, and finally designing a mapping from the model layer to the data layer, filling in the entities, and forming a relatively complete knowledge graph.

[0029] Obviously, by comparing the three different ways of constructing the knowledge graph, it can be seen that the embodiment of the present application constructs the knowledge graph in a bottom-up manner, which is very suitable for the data knowledge construction needs in the field of water and fertilizer for fruit trees, which has a large amount of data and complex cross-data. Therefore, the reliability and availability of the knowledge graph in the field of water and fertilizer for fruit trees are effectively improved; In the embodiment of the present application, step 101, based on the professional knowledge in the field of water and fertilizer for fruit trees, a knowledge graph is constructed in a bottom-up manner, such as Figure 2 As shown, it can include the following: Collect professional knowledge in the field of water and fertilizer for fruit trees, and perform part-of-speech tagging on professional terms in the field of water and fertilizer for fruit trees; Summarize and analyze the hierarchical relationship and attribute relationship between various professional terms, describe the knowledge attributes in the field of water and fertilizer for fruit trees, and define the attribute types; Construct the classes and attributes of domain knowledge and combine them with instances to obtain a knowledge graph.

[0030] Since the knowledge graph plays a cornerstone role in similarity calculation models, optimal irrigation strategy output, etc., a large amount of data is collected in the process of constructing the water knowledge graph to ensure the applicability of the integrated water and fertilizer technology for fruit trees. At the same time, part-of-speech tagging is used to ensure the pertinence, professionalism and accuracy in the field of water and fertilizer for fruit trees.

[0031] In the embodiment of the present application, step 102 is to establish a fruit tree fertilization strategy library based on the knowledge graph and the fruit tree fertilization example. Specifically, Combined with database-related technologies, the storage, representation and call functions of orchard water and fertilizer knowledge are realized. The structured, semi-structured and unstructured knowledge of orchard water and fertilizer are stored by type. The structured knowledge is stored in relational data such as MySQL and Oracle, the structured part of the semi-structured knowledge is stored in relational database, the unstructured part is stored in hard disk and server, and the unstructured knowledge is stored in hard disk; the knowledge is represented by XML and OWL ontology language; the knowledge call is mainly to represent the knowledge after parsing OWL and XML forms through parsing tools, and: A fruit tree fertilization strategy library is established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as attribute factors such as region, fruit tree variety, target yield, and fruit tree growth period of fruit tree water and fertilizer examples.

[0032] Obviously, since the strategy library is all built based on fertilization examples, it is feasible.

[0033] In the embodiment of the present application, step 103, based on the knowledge graph and the strategy library, the semantic structure similarity of the orchard domain ontology, the similarity of the orchard water fertilizer irrigation attribute elements, and the similarity of the fertilization irrigation instance are integrated to construct a fertilization strategy similarity calculation model in the orchard water fertilizer field. The similarity calculation model formula is as follows:

[0034] In the above formula, are weights, corresponding to irrigation attribute elements, ontology semantic structure and fertilization irrigation instances; It refers to the similarity of water, fertilizer and irrigation attribute elements in the orchard, where irrigation attributes include irrigation time, location, fruit tree variety and expected yield; It refers to the semantic structure similarity of the orchard domain ontology; It refers to the similarity of fertilization and irrigation instances in the strategy library; .

[0035] Obviously, the embodiment of the present application is based on the knowledge graph and strategy library, and the semantic structure similarity of the orchard domain ontology, the similarity of the orchard water fertilizer irrigation attribute elements, and the similarity of the fertilization irrigation instance are calculated. The proposed fertilization strategy similarity calculation model in the orchard water fertilizer field, when receiving the fertilization element, matches the optimal irrigation strategy through the similarity calculation model combined with the reasoning mechanism. Therefore, the fertilization strategy is more reasonable, and the cultivation of fruit trees is more scientific and reasonable.

[0036] In the embodiment of the present application, in step 104, when the fertilization factor is received, the optimal irrigation strategy is matched by combining the similarity calculation model with the reasoning mechanism, which may include the following contents: like Figure 3 As shown, the irrigation strategies are screened according to the received fertilization elements, and the screened irrigation strategies are calculated through a similarity calculation model to obtain at least one fertilization strategy; The fertilization strategy is based on the preset reasoning, and the recommended fertilization strategy is obtained by reasoning; The recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy.

[0037] Among them, the fertilization factors can be the fruit tree period, expected yield, location, terrain, etc., which can be set according to needs and are not limited here; For example, Figure 4 As shown, the fertilization strategy is inferred according to the preset reasoning, and the recommended fertilization strategy can be: combined with the agenda of the Drools engine, the local variable method is used to combine the weights of the elements for rule reasoning. Specifically, Add fertilization strategies to the agenda and iteratively execute the rules in these agendas 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 activated and added to the agenda after the conflicts are resolved.

[0038] It should be noted that in actual operations, due to the large number of regional or natural constraints in agricultural operations, especially in water and fertilizer irrigation, the probability of such conflicts is extremely low and this issue can be ignored.

[0039] For example, the recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy, such as Figure 5 As shown, it can be: According to the preset evaluation criteria, the recommended fertilization strategy is evaluated to see whether it is reasonable. If it is reasonable, it is output as the optimal irrigation strategy and directly applied. If it is unreasonable, it is continuously adjusted in combination with the knowledge in the field of water and fertilizer for fruit trees until a reasonable water and fertilizer strategy is obtained.

[0040] Obviously, the embodiment of the present application uses Drools rules based on similarity calculation as the reasoning mechanism, which can accurately and quickly match and call the fertilization strategy while greatly reducing the risk of overfitting and preventing downtime.

[0041] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0042] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0043] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be implemented through a computer program product. When the computer program product runs on a terminal, the terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0044] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 application, and should all be included in the protection scope of the present application.

Claims

1. A fruit tree water-fertilizer integrated intelligent irrigation method based on knowledge graph, characterized in that: include: A knowledge graph is obtained based on professional knowledge in the field of water and fertilizer for fruit trees; Based on the knowledge graph and fruit tree fertilization examples, a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer is established; Based on the knowledge graph and strategy library, the similarity of the semantic structure of the orchard domain ontology, the similarity of the orchard water, fertilizer and irrigation attribute elements, and the similarity of fertilization and irrigation instances are integrated to build a fertilization strategy similarity calculation model in the orchard water and fertilizer domain. When the fertilization elements are received, the optimal irrigation strategy is matched through the similarity calculation model combined with the reasoning mechanism.

2. The method according to claim 1, characterized in that The knowledge graph obtained based on the professional knowledge in the field of water and fertilizer for fruit trees is specifically: Based on the professional knowledge in the field of water and fertilizer for fruit trees, a knowledge graph is constructed in a bottom-up manner.

3. The method according to claim 1, characterized in that The knowledge graph obtained based on the professional knowledge in the field of water and fertilizer for fruit trees is specifically: Collect professional knowledge in the field of water and fertilizer for fruit trees, and perform part-of-speech tagging on professional terms in the field of water and fertilizer for fruit trees; Summarize and analyze the hierarchical relationship and attribute relationship between various professional terms, describe the knowledge attributes in the field of water and fertilizer for fruit trees, and define the attribute types; Construct the classes and attributes of domain knowledge and combine them with instances to obtain a knowledge graph.

4. The method according to claim 1, characterized in that: Based on the knowledge graph and the fruit tree fertilization example, a strategy library containing various fertilization elements and professional knowledge in the field of fruit tree water and fertilizer is established, specifically, The structured, semi-structured and unstructured knowledge of water and fertilizer in orchards are stored by types. The structured knowledge is stored in MySQL and Oracle relational data, the structured part of the semi-structured knowledge is stored in relational database, and the unstructured part is stored in hard disk and server. The unstructured knowledge is stored in hard disk. The knowledge is represented by XML and OWL ontology language. The knowledge call is mainly performed by parsing OWL and XML forms through parsing tools to represent the knowledge, as well as: A fruit tree fertilization strategy library is established by integrating professional knowledge in the field of fruit tree water and fertilizer, as well as regional, fruit tree variety, target yield and fruit tree growth period attribute factors of fruit tree water and fertilizer examples.

5. The method according to claim 1, characterized in that Based on the knowledge graph and strategy library, the similarity of the semantic structure of the orchard domain ontology, the similarity of the orchard water, fertilizer and irrigation attribute elements, and the similarity of fertilization and irrigation instances are integrated to construct a fertilization strategy similarity calculation model in the orchard water and fertilizer domain. The formula is as follows: In the above formula, are weights, corresponding to irrigation attribute elements, ontology semantic structure and fertilization irrigation instances; It refers to the similarity of water, fertilizer and irrigation attribute elements in the orchard, where irrigation attributes include irrigation time, location, fruit tree variety and expected yield; It refers to the semantic structure similarity of the orchard domain ontology; It refers to the similarity of fertilization and irrigation instances in the strategy library; .

6. The method according to claim 1, characterized in that When the fertilization elements are received, the optimal irrigation strategy is matched through the similarity calculation model combined with the reasoning mechanism, including the following contents: Screening irrigation strategies according to the received fertilization factors, calculating the screened irrigation strategies through a similarity calculation model, and obtaining at least one fertilization strategy; The fertilization strategy is based on the preset reasoning, and the recommended fertilization strategy is obtained by reasoning; The recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy.

7. The method according to claim 6, characterized in that The fertilization factors mentioned are the fruit tree period, expected yield, location, and terrain.

8. The method according to claim 6, characterized in that The fertilization strategy is based on the preset reasoning, and the recommended fertilization strategy is obtained by reasoning, specifically: Combined with the agenda of the Drools engine, the local variable method is used to combine the weights of the elements for rule reasoning.

9. The method according to claim 8, characterized in that The above-mentioned Drools engine agenda uses a local variable method to combine the weights of elements to perform rule reasoning, specifically: Add the fertilization strategy to the agenda and iteratively execute the rules in the agenda until the 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 activated and added to the agenda after the conflicts are resolved.

10. The method according to claim 6, characterized in that The recommended fertilization strategy is evaluated according to the preset evaluation criteria, and when the evaluation criteria are met, it is output as the optimal irrigation strategy, specifically: According to the preset evaluation criteria, the recommended fertilization strategy is evaluated to see whether it is reasonable. If it is reasonable, it is output as the optimal irrigation strategy and directly applied. If it is unreasonable, it is continuously adjusted in combination with the knowledge in the field of water and fertilizer for fruit trees until a reasonable water and fertilizer strategy is obtained.

Images