A method for updating cultivated land knowledge graph based on vector increment and related equipment

Abstract

The present application relates to the field of knowledge graph technology, and provides a method for updating a cultivated land knowledge graph based on vector increments and related equipment, the method comprising: obtaining multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in a target area; taking each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot as a cultivated land entity, and obtaining the entity relationship between every two cultivated land entities; constructing a cultivated land knowledge graph based on all cultivated land entities and all entity relationships; constructing multiple rules for updating the cultivated land knowledge graph; when receiving vector increment data, determining a target rule from all rules according to the vector increment data, and updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph. The method of the present application can improve the accuracy of updating the cultivated land knowledge graph.

Description

Technical Field

[0001] The present application relates to the field of knowledge graph technology, and in particular to a method for updating a farmland knowledge graph based on vector increments and related equipment. Background Art

[0002] Most of the existing knowledge graph update and completion methods obtain update data from network text data, perform entity matching, and then update the graph. However, in the field of geographical research, vector patch data also has a large number of knowledge points, and vector patch data has clearer and more specific spatiotemporal attributes and strong knowledge structure. When constructing and updating the knowledge graph for cultivated land, the changes in geography-related incremental data are often ignored, and the nodes in the knowledge graph are usually directly deleted or modified, resulting in the problem of low accuracy in updating the knowledge graph. Summary of the invention

[0003] The present application provides a method and related equipment for updating a farmland knowledge graph based on vector increments, which can solve the problem of low accuracy in updating the knowledge graph.

[0004] In a first aspect, an embodiment of the present application provides a method for updating a farmland knowledge graph based on vector increments, and the method for updating a farmland knowledge graph includes:

[0005] Obtain multiple farmland indicators, multiple farmland business scenarios, multiple data types, and identifiers of multiple farmland plots in the target area;

[0006] Each cultivated land indicator, each cultivated land business scenario, each data type, and each cultivated land plot identifier are taken as cultivated land entities, and the entity relationship between every two cultivated land entities is obtained;

[0007] A cultivated land knowledge graph is constructed based on all cultivated land entities and all entity relationships; multiple nodes in the cultivated land knowledge graph correspond one-to-one to multiple cultivated land entities, and the edge between two nodes is the entity relationship between the corresponding two cultivated land entities;

[0008] Construct multiple rules for updating the farmland knowledge graph;

[0009] When vector incremental data is received, a target rule is determined from all rules according to the vector incremental data, and the cultivated land knowledge graph is updated according to the target rule to obtain an updated cultivated land knowledge graph.

[0010] Optionally, the entity relationship is one of an attribute relationship, a semantic relationship, a spatiotemporal relationship, and a correlation relationship.

[0011] Optionally, a farmland knowledge graph is constructed based on all farmland entities and all entity relationships, including:

[0012] Obtain relevant data for each data type, each cultivated land indicator, and each cultivated land plot in the target area;

[0013] Multiple farmland entities are taken as multiple nodes, and the entity relationship between two farmland entities is taken as the edge between the corresponding two nodes;

[0014] For each node corresponding to a data type, the relevant data of the data type corresponding to the node is used as the attribute of the node;

[0015] For each node corresponding to the cultivated land indicator, the relevant data of the cultivated land indicator corresponding to the node is used as the attribute of the node;

[0016] For the node corresponding to each identifier of the cultivated land parcel, the relevant data of the cultivated land parcel corresponding to the node is used as the attribute of the node.

[0017] Optionally, multiple rules include adding new rules, inheriting only rules, and modifying inherited rules.

[0018] Optionally, add the following rules:

[0019] If the cultivated land entity corresponding to the vector incremental data is a new entity, a new node is constructed in the cultivated land knowledge graph, and the entity relationship between the new entity and the existing cultivated land entity in the cultivated land knowledge graph is obtained. The entity relationship is used as the edge of the new node, and the vector incremental data is used as the attribute of the new node.

[0020] Optional, only inherited rules are:

[0021] If the cultivated land entity corresponding to the vector incremental data is an existing cultivated land entity in the cultivated land knowledge graph, and the attributes of the vector incremental data and the corresponding node of the existing cultivated land entity are the same, then the corresponding node of the existing cultivated land entity is taken as the parent node, and a child node of the parent node is generated. The attributes of the child node are the same as those of the parent node, the edges of the child node are the same as those of the parent node, and the parent node is marked as a historical node.

[0022] Optionally, modify the inheritance rules to:

[0023] If the cultivated land entity corresponding to the vector incremental data is an existing cultivated land entity in the cultivated land knowledge graph, and the attributes of the vector incremental data and the corresponding nodes of the existing cultivated land entity are different, then the corresponding node of the existing cultivated land entity is taken as the parent node, and a child node of the parent node is generated. The attributes of the child node are the attributes of the parent node modified according to the vector incremental data, the edges of the child node are the same as the edges of the parent node, and the parent node is marked as a historical node.

[0024] In a second aspect, an embodiment of the present application provides a device for updating a farmland knowledge graph based on vector increments, comprising:

[0025] A first acquisition module is used to acquire multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in a target area;

[0026] The second acquisition module is used to take each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot as a cultivated land entity, and obtain the entity relationship between every two cultivated land entities;

[0027] The first construction module is used to construct a farmland knowledge graph based on all farmland entities and all entity relationships; multiple nodes in the farmland knowledge graph correspond one-to-one to multiple farmland entities, and an edge between two nodes is an entity relationship between the corresponding two farmland entities;

[0028] The second construction module is used to construct a plurality of rules for updating the cultivated land knowledge graph;

[0029] The updating module is used to determine the target rule from all rules according to the vector incremental data when receiving the vector incremental data, and update the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph.

[0030] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for updating the cultivated land knowledge graph based on vector increments when executing the above-mentioned computer program.

[0031] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned method for updating the cultivated land knowledge graph based on vector increments.

[0032] The above solution of the present application has the following beneficial effects:

[0033] In some embodiments of the present application, by obtaining multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in the target area, each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot are used as cultivated land entities, and the entity relationship between every two cultivated land entities is obtained, and then a cultivated land knowledge graph is constructed based on all cultivated land entities and all entity relationships, and then multiple rules for updating the cultivated land knowledge graph are constructed, and finally when vector incremental data is received, the target rule is determined from all rules according to the vector incremental data, and the cultivated land knowledge graph is updated according to the target rule to obtain an updated cultivated land knowledge graph. Among them, a cultivated land knowledge graph is constructed based on cultivated land indicators, cultivated land business scenarios, data types, and cultivated land plots, which improves the information richness of the cultivated land knowledge graph and realizes a comprehensive description of cultivated land knowledge. Multiple rules are constructed and corresponding rules are selected for updating based on vector incremental data, avoiding direct deletion or modification of nodes in the cultivated land knowledge graph, thereby improving the accuracy of updating the cultivated land knowledge graph. At the same time, the cultivated land knowledge graph is updated based on the vector incremental data, and the vector incremental data is organized into the knowledge graph, further improving the accuracy of updating the cultivated land knowledge graph.

[0034] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 A flowchart of a method for updating a cultivated land knowledge graph based on vector increments provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of the structure of a farmland knowledge graph provided in one embodiment of the present application;

[0038] Figure 3 A schematic diagram of the structure of a device for updating a farmland knowledge graph based on vector increments provided in one embodiment of the present application;

[0039] Figure 4 A schematic diagram of the structure of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0040] 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.

[0041] 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 combinations thereof.

[0042] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0043] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0044] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0045] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0046] In response to the problem of low accuracy in the existing updating of knowledge graphs, an embodiment of the present application provides a method for updating a cultivated land knowledge graph based on vector increments. The method for updating the cultivated land knowledge graph obtains multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in a target area, and then uses each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot as a cultivated land entity, and obtains the entity relationship between every two cultivated land entities. A cultivated land knowledge graph is constructed based on all cultivated land entities and all entity relationships, and then multiple rules for updating the cultivated land knowledge graph are constructed. Finally, when vector incremental data is received, a target rule is determined from all rules according to the vector incremental data, and the cultivated land knowledge graph is updated according to the target rule to obtain an updated cultivated land knowledge graph. Among them, a cultivated land knowledge graph is constructed based on cultivated land indicators, cultivated land business scenarios, data types, and cultivated land plots, which improves the information richness of the cultivated land knowledge graph and realizes a comprehensive description of cultivated land knowledge. Multiple rules are constructed and corresponding rules are selected for updating based on vector incremental data, avoiding direct deletion or modification of nodes in the cultivated land knowledge graph, thereby improving the accuracy of updating the cultivated land knowledge graph. At the same time, the cultivated land knowledge graph is updated based on the vector incremental data, and the vector incremental data is organized into the knowledge graph, further improving the accuracy of updating the cultivated land knowledge graph.

[0047] Next, an exemplary description is given of the method for updating the cultivated land knowledge graph based on vector increments provided in this application.

[0048] like Figure 1 As shown, the method for updating the cultivated land knowledge graph based on vector increment of the present application includes the following steps:

[0049] Step 11, obtaining multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in the target area.

[0050] The above-mentioned cultivated land indicators are indicators related to cultivated land (such as newly added cultivated land area, cultivated land outflow area, cultivated land reserves, cultivated land transfer rate, etc.), cultivated land business scenarios are businesses conducted on cultivated land (such as cultivated land occupation and compensation balance, input and output balance, non-grainization, etc.), and descriptions of future development status of cultivated land (such as the need to improve the quality of cultivated land and the need to ensure the quantity of cultivated land), data types are cultivated land-related data types (such as land classification maps, land plots approved as construction land, permanent basic farmland plots, etc.), target areas are areas where knowledge graphs need to be used for cultivated land knowledge analysis, such as a province, etc., and the identification of cultivated land plots is used to distinguish different plots (such as Plot 1, Plot 2).

[0051] In some embodiments of the present application, multiple cultivated land indicators, multiple cultivated land business scenarios, and multiple data types can be obtained based on the laws, regulations, standards, business procedures, paper reports, case studies, and existing ontology models for cultivated land protection, combined with existing land use data. The existing maps, vector patches, and other data of the target area can also be used to obtain the identification of multiple cultivated land plots in the target area.

[0052] Step 12: take each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot as a cultivated land entity, and obtain the entity relationship between every two cultivated land entities.

[0053] The above-mentioned entity relationship is one of attribute relationship (such as data attribute relationship, object attribute relationship), semantic relationship (such as inheritance and hierarchical relationship centered on time, space, ownership and management association), time-space relationship (topological relationship, time relationship, etc.), and correlation relationship (linear relationship, non-linear relationship, association relationship, etc.).

[0054] For example, the entity relationship between cultivated land entities can be collected manually, such as the entity relationship between the cultivated land reserves and the newly added cultivated land area is a linear positive correlation.

[0055] Step 13: construct a farmland knowledge graph based on all farmland entities and all entity relationships.

[0056] In the above-mentioned cultivated land knowledge graph, multiple nodes correspond one-to-one to multiple cultivated land entities, and the edge between two nodes is the entity relationship between the corresponding two cultivated land entities.

[0057] In some embodiments of the present application, the step of constructing a farmland knowledge graph based on all farmland entities and all entity relationships includes:

[0058] The first step is to obtain relevant data for each data type, each cultivated land indicator, and each cultivated land plot in the target area.

[0059] In the second step, multiple farmland entities are taken as multiple nodes, and the entity relationship between two farmland entities is taken as the edge between the corresponding two nodes.

[0060] The third step is to use the relevant data of the data type corresponding to each node as the attribute of the node.

[0061] Exemplarily, the relevant data of a data type is data of the data type, such as the current land type map of the target area.

[0062] The fourth step is to use the relevant data of the cultivated land indicator corresponding to each node as the attribute of the node.

[0063] Exemplarily, the relevant data of the cultivated land indicator includes the indicator value, update time, change type (increase, decrease, etc.) compared with the last updated indicator value, associated fields, name of the indicator, etc.

[0064] The fifth step is to use the relevant data of the cultivated land parcel corresponding to the node as the attribute of the node for the node corresponding to the identifier of each cultivated land parcel.

[0065] Exemplarily, the relevant data of the cultivated land parcel includes the area of ​​the cultivated land parcel, the name of the land type (such as paddy field, dry land, etc.), the length of the parcel, the planting attributes, the change type, the update time, etc.

[0066] It should be noted that the attribute of the node corresponding to the cultivated land business scenario is the cultivated land business scenario. Before constructing the cultivated land knowledge graph, for the cultivated land entity that includes the time dimension in the relevant data, a quadruple including the cultivated land entity can be constructed, and then the cultivated land knowledge graph can be constructed based on the quadruple, so that the edges between the nodes corresponding to the two cultivated land entities contain entity relationships and time information, thereby improving the accuracy and information richness of the cultivated land knowledge graph. For example, in the quadruple (Plot 1, belongs to, Yuetang Village, [2021-11, 2023-11]), a time dimension is added to the triple to represent time facts, where "Plot 1" and "Yutang Village" are cultivated land entities, "belongs to" is an entity relationship, and "[2021-11, 2023-11]" represents the effective time interval of the fact that "Plot 1, belongs to, Yuetang Village". After the introduction of the time dimension, the cultivated land knowledge graph Can be decomposed into a series of static knowledge graphs ,in, represents the static knowledge graph of the first time period, Represents the static knowledge graph of the second time period, Indicates Static knowledge graph for a time period, Indicates The static knowledge graph of each time period. The farmland entity without time dimension maintains the same attributes in all time periods.

[0067] It is worth mentioning that the construction of the cultivated land knowledge graph based on cultivated land indicators, cultivated land business scenarios, data types, and cultivated land plots has improved the information richness of the cultivated land knowledge graph and achieved a comprehensive description of cultivated land knowledge. In addition, the introduction of the time dimension in the cultivated land knowledge graph can improve the information integrity of the facts in the cultivated land knowledge graph, making the cultivated land knowledge graph have time series.

[0068] Step 14: construct multiple rules for updating the cultivated land knowledge graph.

[0069] Specifically, the multiple rules include adding new rules, inheriting only rules, and modifying inherited rules.

[0070] The new rules are:

[0071] If the cultivated land entity corresponding to the vector incremental data is a new entity, a new node is constructed in the cultivated land knowledge graph, and the entity relationship between the new entity and the existing cultivated land entity in the cultivated land knowledge graph is obtained. The entity relationship is used as the edge of the new node, and the vector incremental data is used as the attribute of the new node.

[0072] The only inheritance rules are:

[0073] If the cultivated land entity corresponding to the vector incremental data is an existing cultivated land entity in the cultivated land knowledge graph, and the attributes of the vector incremental data and the corresponding node of the existing cultivated land entity are the same, then the corresponding node of the existing cultivated land entity is taken as the parent node, and a child node of the parent node is generated. The attributes of the child node are the same as those of the parent node, the edges of the child node are the same as those of the parent node, and the parent node is marked as a historical node.

[0074] Modify the inheritance rules to:

[0075] If the cultivated land entity corresponding to the vector incremental data is an existing cultivated land entity in the cultivated land knowledge graph, and the attributes of the vector incremental data and the corresponding nodes of the existing cultivated land entity are different, then the corresponding node of the existing cultivated land entity is taken as the parent node, and a child node of the parent node is generated. The attributes of the child node are the attributes of the parent node modified according to the vector incremental data, the edges of the child node are the same as the edges of the parent node, and the parent node is marked as a historical node.

[0076] It should be noted that the vector incremental data is the data newly added to the constructed cultivated land knowledge graph, which can describe the change status of the cultivated land entity. For example, the vector incremental data is the cultivated land area in the vector patch data increased by 20 square kilometers, and the information described is "the newly added cultivated land area is 20 square kilometers". Manual analysis of this information can obtain that the cultivated land entity corresponding to the vector incremental data is the newly added cultivated land area. In the newly added rules, the entity relationship between the newly added entity and the existing cultivated land entity in the cultivated land knowledge graph can be obtained manually.

[0077] The parent node is marked as a historical node to indicate that the information described by the parent node is historical information in the cultivated land knowledge graph. The child node replaces the parent node. When updating again, the child node is used, but the parent node still exists in the cultivated land knowledge graph as a historical node.

[0078] Exemplarily, there is an edge between the parent node and the node corresponding to plot 1. When the inheritance-only rule or the modified inheritance rule is executed, the generated child node also has an edge between the node corresponding to plot 1, that is, the child node inherits all edges of the parent node.

[0079] In some embodiments of the present application, for vector incremental data that are entity change attributes (such as changes in the identification of cultivated land plots, changes in land class names, etc.), the cultivated land knowledge graph can be updated by calculating the semantic similarity between the vector incremental data and each cultivated land entity, matching the cultivated land entities corresponding to the vector incremental data, and then modifying the attributes of the nodes corresponding to the cultivated land entities.

[0080] It is worth mentioning that by constructing multiple rules and selecting corresponding rules for updating according to the vector incremental data, direct deletion or modification of nodes in the cultivated land knowledge graph is avoided, thereby improving the accuracy of updating the cultivated land knowledge graph.

[0081] Step 15, when receiving the vector incremental data, determine the target rule from all the rules according to the vector incremental data, and update the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph.

[0082] The above-mentioned vector incremental data are newly added data to the constructed cultivated land knowledge graph.

[0083] Specifically, the rules that the vector incremental data conforms to are determined based on the cultivated land entities corresponding to the vector incremental data and all existing cultivated land entities in the cultivated land knowledge graph, the conforming rules are used as target rules, and the cultivated land knowledge graph is updated according to the target rules to obtain an updated cultivated land knowledge graph.

[0084] Exemplarily, if the information described by the vector incremental data is "plot data of a nature reserve", where the nature reserve is the cultivated land entity corresponding to the vector incremental data, and there is no node corresponding to the nature reserve in the cultivated land knowledge graph, and the newly added rules are met, then a new node corresponding to the nature reserve is created, and in practice the nature reserve and plot 1 have an attribute relationship, then there is an edge between the new node and the node corresponding to plot 1, the attribute of the edge is an attribute relationship, and the attributes of the new node are the area of ​​plot 5, the time when the node was created, etc.

[0085] If the information described by the vector incremental data is "the newly added cultivated land area is 20 square kilometers" (for example, the cultivated land area in the vector patch data has increased by 20 square kilometers), the cultivated land entity is the newly added cultivated land area, and there is a node corresponding to the newly added cultivated land area in the cultivated land knowledge graph, and the indicator value in the attribute of the current node is 15 square kilometers, which is different from the vector incremental data and meets the modification inheritance rules, then the node is used as the parent node, and a child node corresponding to the newly added cultivated land area is created. The child node inherits all the attributes and entity relationships (edges) of the parent node, and the indicator value in the attribute is modified to 20 square kilometers, and the parent node is marked as a historical node.

[0086] If the information described by the vector incremental data is "the amount of cultivated land reserves is 50 hectares", there is a node corresponding to the amount of cultivated land in the cultivated land knowledge graph, and the indicator value in the attribute of the node is 50 hectares, which is the same as the vector incremental data and meets the inheritance only rule, then the node is taken as the parent node, and a child node corresponding to the amount of cultivated land is created, the child node inherits the attributes and entity relationships of the parent node, and then the parent node is marked as a historical node.

[0087] It should be noted that after the update, the vector incremental data of other nodes are obtained according to the entity relationship of the node obtained after the update. For example, if the newly added cultivated land area changes and is updated, the cultivated land reserves that have a linear positive correlation with the newly added cultivated land area will change accordingly. It is necessary to calculate the vector incremental data of the cultivated land reserves and update the nodes corresponding to the cultivated land reserves according to the process described in step 15.

[0088] In some embodiments of the present application, the vector incremental data has a label corresponding to the rule, and the target rule can be directly determined by the label. For example, the label delete corresponds to the inheritance-only rule. When the vector incremental data carries delete, the inheritance-only rule is directly used as the target rule.

[0089] Exemplarily, three code examples for implementing the above modification of inheritance rules are:

[0090] First example:

[0091] ;

[0092] It means that if there is a data land class named cultivated land in the incremental land class map, and if no new cultivated land area node is established, a new cultivated land area node will be established first, and a parent-child relationship will be established with the original newly added cultivated land area node. The child node inherits all the attributes and relationships of the parent node, and then the index value attribute of the new node is modified to the index value of the newly added land class map.

[0093] Second example:

[0094] ;

[0095] The third example:

[0096] ;

[0097] It means that if there is an indicator node that is linearly positively correlated with the cultivated land reserves node and the node status is change, if a new cultivated land reserves node is not established, a new cultivated land reserves node will be established first. This node inherits all the attributes and relationships of the parent node, and then the indicator value attribute of the cultivated land reserves node is modified to the original attribute plus the indicator value of this node.

[0098] As shown in the above example, in some cases, the vector incremental data describes not the final index value of the current index, but the change value of the index value. In this case, when modifying the index value of the new node, an addition operation or a subtraction operation is required.

[0099] It should be noted that the purpose of treating the parent node as a historical node and not deleting it is to preserve the historical status of the cultivated land knowledge graph, so as to facilitate the analysis of the historical status of the cultivated land conditions in the target area. By constructing the cultivated land knowledge graph and updating it according to the above steps, the real-time nature of the cultivated land knowledge graph can be guaranteed. The real-time cultivated land knowledge graph can be used to realize the spatiotemporal characteristics of cultivated land, the assessment method of "non-grainization" problems, and the protection of cultivated land, the precise assessment of land consolidation, and the recommendation of case solutions based on local conditions.

[0100] It is worth mentioning that the cultivated land knowledge graph is constructed based on cultivated land indicators, cultivated land business scenarios, data types, and cultivated land plots, which improves the information richness of the cultivated land knowledge graph and realizes a comprehensive description of cultivated land knowledge. Multiple rules are constructed and corresponding rules are selected for updating based on vector incremental data, avoiding direct deletion or modification of nodes in the cultivated land knowledge graph, thereby improving the accuracy of updating the cultivated land knowledge graph. At the same time, the cultivated land knowledge graph is updated based on the vector incremental data, and the vector incremental data is organized into the knowledge graph, further improving the accuracy of updating the cultivated land knowledge graph.

[0101] The following is an illustrative explanation of the farmland knowledge graph of this application with reference to a specific example.

[0102] like Figure 2 As shown in the figure, the cultivated land knowledge graph includes nodes corresponding to five types of cultivated land entities: data (i.e. data type), plots (i.e. identification of cultivated land plots), indicators (i.e. cultivated land indicators), and business scenarios (i.e. cultivated land business scenarios). The data includes the third national land survey data, annotated as construction land, land type map, permanent basic farmland, and nature reserves. The plots include plot 1, plot 2, plot 3, and administrative divisions. The indicators include newly added cultivated land area, cultivated land outflow area, cultivated land transfer rate, and cultivated land reserves. The business knowledge points include balance of occupation and compensation, balance of inflow and outflow, and non-grainization. Arrows represent edges between nodes, i.e., entity relationships between corresponding cultivated land entities. Entity relationships include: semantic relationships (including belonging relationships), correlation relationships (association relationships, nonlinear positive correlations, linear negative correlations), and topological relationships (adjacent, contained). The attributes of nodes corresponding to plots include basic information (plot number, i.e., identification) and change information (land type name, plot area, plot length, planting attributes, change type, and update time). The attributes of nodes corresponding to indicators include update time, change type, associated fields, indicator values, and indicator names.

[0103] The following is an exemplary description of the farmland knowledge graph updating device based on vector increments provided in this application.

[0104] like Figure 3 As shown, the embodiment of the present application provides a device for updating a farmland knowledge graph based on vector increments. The device 300 for updating a farmland knowledge graph based on vector increments includes:

[0105] The first acquisition module 301 is used to acquire multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in a target area;

[0106] The second acquisition module 302 is used to take each cultivated land indicator, each cultivated land business scenario, each data type, and each cultivated land plot identifier as a cultivated land entity, and obtain the entity relationship between every two cultivated land entities;

[0107] The first construction module 303 is used to construct a farmland knowledge graph based on all farmland entities and all entity relationships; multiple nodes in the farmland knowledge graph correspond to multiple farmland entities one by one, and an edge between two nodes is an entity relationship between the corresponding two farmland entities;

[0108] The second construction module 304 is used to construct a plurality of rules for updating the cultivated land knowledge graph;

[0109] The updating module 305 is used to determine the target rule from all the rules according to the vector incremental data when receiving the vector incremental data, and update the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph.

[0110] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0111] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0112] like Figure 4 As shown, an embodiment of the present application provides a terminal device. The terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 4 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on the at least one processor D100, wherein the processor D100 implements the steps of any of the above-mentioned method embodiments when executing the computer program D102.

[0113] Specifically, when the processor D100 executes the computer program D102, it obtains multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in the target area, and then uses each cultivated land indicator, each cultivated land business scenario, each data type, and the identifier of each cultivated land plot as a cultivated land entity, and obtains the entity relationship between every two cultivated land entities, and then constructs a cultivated land knowledge graph based on all cultivated land entities and all entity relationships, and then constructs multiple rules for updating the cultivated land knowledge graph. Finally, when receiving vector incremental data, the target rule is determined from all rules according to the vector incremental data, and the cultivated land knowledge graph is updated according to the target rule to obtain an updated cultivated land knowledge graph. Among them, a cultivated land knowledge graph is constructed based on cultivated land indicators, cultivated land business scenarios, data types, and cultivated land plots, which improves the information richness of the cultivated land knowledge graph and realizes a comprehensive description of cultivated land knowledge. Multiple rules are constructed and corresponding rules are selected for updating based on vector incremental data, avoiding direct deletion or modification of nodes in the cultivated land knowledge graph, thereby improving the accuracy of updating the cultivated land knowledge graph. At the same time, the cultivated land knowledge graph is updated based on the vector incremental data, and the vector incremental data is organized into the knowledge graph, further improving the accuracy of updating the cultivated land knowledge graph.

[0114] The processor D100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0115] In some embodiments, the memory D101 may be an internal storage unit of the terminal device D10, such as a hard disk or memory of the terminal device D10. In other embodiments, the memory D101 may also be an external storage device of the terminal device D10, such as a plug-in hard disk, a smart memory card (SMC, SmartMedia Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), etc. equipped on the terminal device D10. Further, the memory D101 may also include both an internal storage unit of the terminal device D10 and an external storage device. The memory D101 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory D101 may also be used to temporarily store data that has been output or is to be output.

[0116] An embodiment of the present application further 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 in the above-mentioned method embodiments can be implemented.

[0117] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code to the apparatus / terminal device of the method for updating the cultivated land knowledge graph based on vector increment. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0119] 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.

[0120] 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.

[0121] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for updating cultivated land knowledge graph based on vector increment, characterized in that: include: Obtain multiple farmland indicators, multiple farmland business scenarios, multiple data types, and identifiers of multiple farmland plots in the target area; Each cultivated land indicator, each cultivated land business scenario, each data type, and each cultivated land plot identifier are taken as cultivated land entities, and the entity relationship between every two cultivated land entities is obtained; Construct a farmland knowledge graph based on all farmland entities and all entity relationships; In the farmland knowledge graph, multiple nodes correspond to multiple farmland entities one by one, and an edge between two nodes is an entity relationship between the corresponding two farmland entities; Constructing a plurality of rules for updating the cultivated land knowledge graph; When receiving the vector incremental data, determining a target rule from all the rules according to the vector incremental data, and updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph; The multiple rules include newly added rules, inherited rules only, and modified inherited rules; When the target rule is a newly added rule, the step of updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph includes: Construct a new node in the cultivated land knowledge graph, and obtain the entity relationship between the newly added entity corresponding to the vector incremental data and the existing cultivated land entity in the cultivated land knowledge graph, use the entity relationship as the edge of the new node, and use the vector incremental data as the attribute of the new node; When the target rule is an inheritance-only rule or the modified inheritance rule, the step of updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph includes: The node corresponding to the existing cultivated land entity corresponding to the vector incremental data is taken as the parent node, and a child node of the parent node is generated, the edge of the child node is the same as the edge of the parent node, and the parent node is marked as a historical node; wherein, if the target rule is an inheritance-only rule, the attributes of the child node are the same as the attributes of the parent node; if the target rule is a modified inheritance rule, the attributes of the child node are the attributes of the parent node modified according to the vector incremental data.

2. The method for updating the cultivated land knowledge graph according to claim 1, characterized in that: The entity relationship is one of an attribute relationship, a semantic relationship, a spatiotemporal relationship, and a correlation relationship.

3. The method for updating the cultivated land knowledge graph according to claim 1, characterized in that: The method of constructing a farmland knowledge graph based on all farmland entities and all entity relationships includes: Acquire relevant data of each data type, relevant data of each cultivated land indicator, and relevant data of each cultivated land plot in the target area; Multiple farmland entities are taken as multiple nodes, and the entity relationship between two farmland entities is taken as the edge between the corresponding two nodes; For each node corresponding to a data type, use the relevant data of the data type corresponding to the node as the attribute of the node; For each node corresponding to the cultivated land indicator, relevant data of the cultivated land indicator corresponding to the node is used as the attribute of the node; For the node corresponding to each identifier of the cultivated land parcel, the relevant data of the cultivated land parcel corresponding to the node is used as the attribute of the node.

4. A device for updating cultivated land knowledge graph based on vector increment, characterized in that: include: A first acquisition module is used to acquire multiple cultivated land indicators, multiple cultivated land business scenarios, multiple data types, and identifiers of multiple cultivated land plots in a target area; The second acquisition module is used to take each cultivated land indicator, each cultivated land business vector, each data type, and each cultivated land plot identifier as a cultivated land entity, and obtain the entity relationship between every two cultivated land entities; The first construction module is used to construct a farmland knowledge graph based on all farmland entities and all entity relationships; In the farmland knowledge graph, multiple nodes correspond to multiple farmland entities one by one, and an edge between two nodes is an entity relationship between the corresponding two farmland entities; A second construction module is used to construct a plurality of rules for updating the cultivated land knowledge graph; An updating module, configured to, when receiving vector incremental data, determine a target rule from all rules according to the vector incremental data, and update the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph; The second building block is specifically used to implement: The multiple rules include newly added rules, inherited rules only, and modified inherited rules; The update module is specifically used to implement: When the target rule is a newly added rule, the step of updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph includes: Construct a new node in the cultivated land knowledge graph, and obtain the entity relationship between the newly added entity corresponding to the vector incremental data and the existing cultivated land entity in the cultivated land knowledge graph, use the entity relationship as the edge of the new node, and use the vector incremental data as the attribute of the new node; When the target rule is an inheritance-only rule or the modified inheritance rule, the step of updating the cultivated land knowledge graph according to the target rule to obtain an updated cultivated land knowledge graph includes: The node corresponding to the existing cultivated land entity corresponding to the vector incremental data is taken as the parent node, and a child node of the parent node is generated, the edge of the child node is the same as the edge of the parent node, and the parent node is marked as a historical node; wherein, if the target rule is an inheritance-only rule, the attributes of the child node are the same as the attributes of the parent node; if the target rule is a modified inheritance rule, the attributes of the child node are the attributes of the parent node modified according to the vector incremental data.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for updating the farmland knowledge graph based on vector increments as described in any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for updating the farmland knowledge graph based on vector increments as described in any one of claims 1 to 3 is implemented.

Images