Design selection knowledge graph construction and application method, device, equipment and medium

Abstract

The embodiment of the application discloses a kind of design selection knowledge graph construction and application method related to power distribution network design field, comprising: obtaining to be parsed design material;Analysis the to-be-analyzed design material to extract design selection data conforming to pre-set data structure, wherein the design selection data includes legend information, legend attribute information, legend material information and legend stringing information;Based on the design selection data extraction and construction n target entities, wherein n is positive integer, the target entity includes legend entity, material group entity, stringing relationship entity, stringing entity, material entity and conductor entity;According to the association between all target entities and each target entity, design selection knowledge graph is constructed.The target entity is parsed from design material in the application, and design selection knowledge graph is constructed, and based on the design selection knowledge graph proposed in the application, the efficiency of design personnel in carrying out distribution network design selection work can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of knowledge graph technology and power distribution network technology, and in particular to a method, apparatus, equipment and medium for constructing and applying a design selection knowledge graph. Background Technology

[0002] When designing and selecting power distribution network configurations, designers typically rely on their experience to configure the material types, wiring relationships, wiring schemes, and conductors used in each scheme for any given diagram. For designers unfamiliar with power distribution network design, this experience-based process is tedious and inefficient. Furthermore, for large-scale power distribution network projects, relying on experience will consume a significant amount of time and effort, compromising the designers' work efficiency.

[0003] Therefore, there is an urgent need for an application solution that can effectively improve the efficiency of designers in power distribution network design. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a method, apparatus, device, and medium for constructing and applying a design selection knowledge graph, as detailed below:

[0005] In a first aspect, embodiments of this application provide a method for constructing a design selection knowledge graph, including:

[0006] Obtain the design materials to be analyzed;

[0007] The design materials to be analyzed are used to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information.

[0008] Based on the design selection data, n target entities are extracted and constructed, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities.

[0009] A design selection knowledge graph is constructed based on all target entities and the relationships between them.

[0010] According to a specific implementation of this application, the step of extracting and constructing n target entities based on the design selection data includes:

[0011] Based on the knowledge representation method of attribute graphs, n target entities are extracted and constructed from the design selection data.

[0012] According to a specific implementation of this application, the step of constructing a design selection knowledge graph based on all target entities and the relationships between them includes:

[0013] Based on the relationships between target entities, different types of target entities are combined to obtain m graph patterns corresponding to m legend entities, where m is a positive integer;

[0014] The triples corresponding to each graph pattern are stored in a preset graph database to generate the design selection knowledge graph.

[0015] According to one specific embodiment of this application, the preset graph database is the Neo4j graph database.

[0016] According to a specific embodiment of this application, after constructing a design selection knowledge graph based on all target entities and the relationships between them, the method further includes:

[0017] Retrieve the newly added target entity;

[0018] Update the design selection knowledge graph according to the type of newly added legend entities;

[0019] If the newly added target entity is a newly added legend entity, a new graph pattern is constructed based on the newly added legend entity and its associated target entity, and the triples corresponding to the graph pattern are stored in the preset graph database to update the design selection knowledge graph.

[0020] If the newly added target entity is not a newly added legend entity, then according to the type of the newly added target entity and its association with the corresponding graph pattern, the newly added target entity is added to the corresponding graph pattern to update the design selection knowledge graph.

[0021] Secondly, embodiments of this application provide a method for applying a design selection knowledge graph, including:

[0022] Retrieve the legend information to be queried and the query target;

[0023] Analyze the legend information to be queried to obtain the legend entity to be queried;

[0024] Match the target entity corresponding to the query legend entity in the preset design selection knowledge graph, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, overhead line relationship entity, overhead line entity, material entity, and conductor entity.

[0025] According to a specific implementation of this application, the step of matching the target entity corresponding to the query legend entity in a preset design selection knowledge graph and exporting the output entity corresponding to the query target includes:

[0026] Obtain multiple target entities corresponding to the entity to be queried in the legend, each target entity including a historical usage count attribute;

[0027] The target entities are sorted according to the historical usage count attribute, and the target entity with the highest historical usage count is exported as the output entity corresponding to the query target.

[0028] Thirdly, embodiments of this application provide an apparatus for constructing a design selection knowledge graph, comprising:

[0029] The material acquisition module is used to acquire the design materials to be analyzed.

[0030] The material analysis module is used to analyze the design material to be analyzed in order to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information.

[0031] The entity construction module is used to extract and construct n target entities based on the design selection data, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities.

[0032] The graph construction module is used to construct a design selection knowledge graph based on all target entities and the relationships between them.

[0033] Fourthly, embodiments of this application provide an application device for a design selection knowledge graph, comprising:

[0034] The query acquisition module is used to obtain the legend information to be queried and the query target;

[0035] The query analysis module is used to analyze the legend information to be queried in order to obtain the legend entity to be queried;

[0036] The graph query module is used to match the target entity corresponding to the query legend entity in the preset design selection knowledge graph, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, overhead line relationship entity, overhead line entity, material entity, and conductor entity.

[0037] Fifthly, embodiments of this application provide a computer device, the computer device including a processor and a memory, the memory storing a computer program, the computer program executing the design selection knowledge graph construction method described in the first aspect and any embodiment of the first aspect, and the application method of the design selection knowledge graph described in the second aspect when running on the processor.

[0038] Sixthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when run on a processor, executes the design selection knowledge graph construction method described in the first aspect and any embodiment of the first aspect, as well as the design selection knowledge graph application method described in the second aspect.

[0039] This application provides a method for constructing and applying a design selection knowledge graph, including: acquiring design materials to be analyzed; analyzing the design materials to be analyzed to extract design selection data conforming to a preset data structure, wherein the design selection data includes legend information, legend attribute information, legend material information, and legend wiring information; extracting and constructing n target entities based on the design selection data, where n is a positive integer, and the target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities; and constructing a design selection knowledge graph based on all target entities and the relationships between them. This invention first designs a graph-based model for distribution network design selection to improve design efficiency, then extracts and constructs target entities from design drawings, and constructs a design selection knowledge graph according to predefined knowledge types. Thanks to this design selection knowledge graph, designers can significantly improve their efficiency in carrying out distribution network design selection work. Attached Figure Description

[0040] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope of protection of the present invention. In the various drawings, similar components are numbered similarly.

[0041] Figure 1 This illustration shows a flowchart of a method for constructing a design selection knowledge graph according to an embodiment of this application.

[0042] Figure 2 This illustration shows a structured representation of design selection data in a design selection knowledge graph construction method provided in an embodiment of this application;

[0043] Figure 3This illustration shows a schematic diagram of a graph pattern for a design selection knowledge graph provided in an embodiment of this application.

[0044] Figure 4 This illustration shows a flowchart of a design selection knowledge graph application method provided in an embodiment of this application.

[0045] Figure 5 This illustration shows a schematic diagram of a device module for constructing a design selection knowledge graph according to an embodiment of this application;

[0046] Figure 6 The diagram shows a schematic of the device module of an application device for a design selection knowledge graph provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0048] The components of the embodiments of the invention described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0049] In the following, the terms “comprising,” “having,” and their cognates, which may be used in various embodiments of the invention, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as excluding, firstly, the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations thereof.

[0050] Furthermore, the terms "first," "second," and "third" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0051] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of the invention pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be interpreted as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of the invention.

[0052] Example 1

[0053] refer to Figure 1 This is a flowchart illustrating a method for constructing a design selection knowledge graph according to an embodiment of this application. The method for constructing a design selection knowledge graph according to an embodiment of this application is as follows: Figure 1 As shown, it includes:

[0054] Step S101: Obtain the design material to be analyzed;

[0055] Specifically, the design selection knowledge graph proposed in this embodiment can be applied to distribution network design in the power grid field. All related information of the legend in the design drawings is stored in the design selection knowledge graph so that when the distribution network is designed, the related information of the legend can be called to allocate the corresponding material group, materials, overhead line scheme and conductor to the legend.

[0056] The design material to be parsed can be a file including design selection data, such as a pole and line design drawing in DWG format. This embodiment does not limit the specific format of the design material to be parsed; it can be set according to the actual application scenario.

[0057] In the specific implementation process, the design materials to be analyzed may include large-scale online design schemes or design schemes within a user-defined scope. The method of obtaining the design materials to be analyzed can be set according to the actual application scenario. This embodiment does not make specific limitations in this regard.

[0058] Step S102: Analyze the design material to be analyzed to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information.

[0059] Specifically, after obtaining the design materials to be analyzed, the design selection data of each item in the design materials to be analyzed is extracted according to the custom preset data structure.

[0060] For example, when extracting legend information as design selection data for utility poles, the preset data structure can be as follows: Figure 2 As shown.

[0061] It should be noted that the legend information in this embodiment includes basic information related to the legend, such as name, pole number, and voltage level. The legend attribute information includes setting information related to the legend, such as geographic information attributes, segmented tower attributes, and pole attributes. The legend material information includes design selection information related to the legend, such as specification "JKLYJ-1-70" and name "overhead insulated conductor." The legend wiring information is conductor connection information related to the legend, such as conductor direction, conductor type, and conductor installation method.

[0062] In the specific implementation process, the type and specific content of the design selection data can be determined according to the actual application scenario. Designers can limit the specific content of the obtained design selection data by customizing the preset data structure, which is not limited here.

[0063] Step S103: Based on the design selection data, extract and construct n target entities, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities.

[0064] Specifically, after obtaining all the design selection data in the design materials to be analyzed, some entities can be extracted from the design selection data, and some entities can be constructed based on the design selection data to extract or construct n target entities, where the number of n is determined according to the actual application scenario and is not specifically limited here.

[0065] Specifically, the legend entity, the overhead line entity, the material entity, and the conductor entity are target entities that can be directly extracted from the design selection data, while the material group entity and the overhead line relationship entity are target entities constructed based on the relationship between materials and legends and the relationship between overhead lines and legends.

[0066] In the specific implementation process, the legend information can be materialized to obtain the legend entity, the legend material information can be materialized to obtain the material group entity and the material entity, and the legend wiring information can be materialized to obtain the wiring relationship entity, the wiring entity and the conductor entity.

[0067] Specifically, such as Figure 3 As shown, the material group entity is an entity obtained by materializing a complete material group information for the corresponding legend and then naming it individually. Each legend can be associated with one or more material group entities, and each material group entity can be associated with multiple material entities. Different material group entities can be associated with the same material entities. For example, the legend entity consists of Material 1 entity, Material 2 entity, and Material 3 entity.

[0068] The overhead line relationship entities are entities obtained by materializing the overhead line schemes that can be used in the corresponding illustrations and then naming them individually. Each overhead line relationship entity can be associated with multiple overhead line schemes, and each overhead line scheme can use the same conductor or different conductors. For example, an overhead line relationship entity can be associated with overhead line 1 entity and overhead line 2 entity, and both overhead line 1 entity and overhead line 2 entity use the same conductor entity.

[0069] It should be noted that in actual use, associating each legend with a material group entity and a wiring relationship entity can effectively simplify the scale of the design selection knowledge graph.

[0070] According to a specific implementation of the embodiments of this application, the step of constructing n target entities based on the design selection data includes:

[0071] Based on the knowledge representation of attribute graph entities, n target entities are extracted and constructed from the design selection data.

[0072] In a specific embodiment, each target entity is constructed according to the attribute graph entity construction method, which can effectively reduce the size of the design and selection knowledge graph and facilitate its later development and utilization.

[0073] Specifically, the steps for constructing the target entity using the attribute graph knowledge representation method include:

[0074] Step 1: Determine the attribute types included for each entity based on the actual business requirements;

[0075] Step 2: Extract detailed data associated with each type of entity from the dataset of the design selection data;

[0076] Step 3: Perform deduplication on the detailed data of each type of entity;

[0077] Step 4: Give each entity a unique name according to the preset naming rules;

[0078] Step 5: Store each entity in a designated location in the preset graph database according to its type.

[0079] It is important to know that for material group entities, the materials must first be materialized to obtain each material entity. Then, the detailed material information in the material group is replaced with the material entity name. Finally, the material group entity is named. Material group entities have no attributes.

[0080] For overhead line relationship entities, the overhead line scheme and conductors must first be materialized. Then, the detailed overhead line information and conductor information in the overhead line relationship are replaced with the overhead line scheme entity name and conductor entity name. If an overhead line relationship entity has multiple overhead line information and the conductor entities corresponding to the overhead line entities are the same, the identical overhead line scheme entities need to be named to distinguish them. Finally, the overhead line relationship entity is named. The overhead line relationship entity has no attributes.

[0081] This embodiment makes the design selection knowledge graph simpler and more intuitively reflects the actual business logic by constructing material group entities and overhead line relationship entities, without displaying too much material and overhead line information in the knowledge graph. Users can intuitively distinguish which materials are configured and which overhead line scheme is deployed in the current legend by calling the material group entities.

[0082] In addition, during the application process, by calling the material group entity and the overhead line relationship entity, users can match the corresponding material group entity through the legend entity and the overhead line relationship entity of the legend, thereby directly configuring the corresponding material entity, overhead line entity and conductor entity for the legend, which effectively improves the speed and efficiency of power distribution network design and selection.

[0083] Step S104: Construct a design selection knowledge graph based on all target entities and the relationships between them.

[0084] Specifically, the target entities include corresponding relationships, that is, the edges between the nodes of the knowledge graph.

[0085] like Figure 3 As shown, the relationship between the nodes can be as follows: Material 1 entity, Material 2 entity and Material 3 entity form a material group entity. The relationship between the material group entity and the legend entity is selection. The legend entity is associated with the wiring relationship entity. The wiring 1 entity and the wiring 2 entity form a wiring relationship entity. Both the wiring 1 entity and the wiring 2 entity are wire entities.

[0086] For example, the relationship between the legend entity and the material group entity and the wiring relationship entity is "association"; the relationship between the material group entity and the material entity is "composition"; and the relationship between the wiring relationship entity and the conductor entity is "adoption". The relationships between entities can be shown in Table 1:

[0087] Table 1

[0088] entity relation entity wiring_7 use conductor_11 pole_14 Related overhead line solution pole_14 Selection pole_selection_953 materials composition pole_selection_953

[0089] Specifically, wiring_7 is the wiring scheme, conductor_11 is the conductor entity, pole_14 is the legend entity, and pole_selection_953 is the material group entity.

[0090] It should be noted that the relationships between entities can be adaptively set according to the actual application scenario.

[0091] According to a specific implementation of this application, the step of constructing a design selection knowledge graph based on all target entities and the relationships between them includes:

[0092] Based on the relationships between target entities, different types of target entities are combined to obtain m graph patterns corresponding to m legend entities, where m is a positive integer;

[0093] The triples corresponding to each graph pattern are stored in a preset graph database to generate the design selection knowledge graph.

[0094] Specifically, the preset graph database is the Neo4j graph database.

[0095] In a specific embodiment, each legend entity has a corresponding one such as Figure 3 The diagram pattern shown.

[0096] In the graph mode, a legend entity can be associated with a material group entity and a wiring relationship entity. A material group entity includes multiple material entities, and a wiring relationship entity includes multiple wiring schemes. Each wiring scheme has a corresponding conductor entity.

[0097] The graph pattern can be adaptively expanded based on the association relationship combination method disclosed in this embodiment, which will not be elaborated in detail in this embodiment.

[0098] In practical applications, combining the target entities can yield ternary structures such as (legend entity, wiring relationship entity, material group entity), (material entity, composition, material group entity), (wiring relationship entity, wiring scheme, wiring entity), (wiring entity, use, conductor entity), and (legend entity, wiring scheme, wiring relationship entity).

[0099] It should be noted that corresponding attributes can be set in the relationship between the head entity and the tail entity. For example, the quantity attribute of the composition relationship in (material entity, composition, material group entity) can be set.

[0100] This embodiment does not elaborate on the specific process of constructing the knowledge graph. In actual implementation, the knowledge graph construction method corresponding to the Neo4j graph database can be used to carry out the construction process of this embodiment, or the knowledge graph construction method corresponding to other types of graph databases can be used to carry out the construction process of this embodiment.

[0101] According to a specific embodiment of this application, after constructing a design selection knowledge graph based on all target entities and the relationships between them, the method further includes:

[0102] Retrieve the newly added target entity;

[0103] Update the design selection knowledge graph according to the type of newly added legend entities;

[0104] If the newly added target entity is a newly added legend entity, a new graph pattern is constructed based on the newly added legend entity and its associated target entity, and the triples corresponding to the graph pattern are stored in the preset graph database to update the design selection knowledge graph.

[0105] If the newly added target entity is not a newly added legend entity, then according to the type of the newly added target entity and its association with the corresponding graph pattern, the newly added target entity is added to the corresponding graph pattern to update the design selection knowledge graph.

[0106] Specifically, the newly added target entity is a target entity that is not included in the current design selection knowledge graph, and can be any one or more of the following: legend entity, material group entity, material entity, overhead line relationship entity, and conductor entity.

[0107] For example, the newly added target entity can be a new target entity in the power distribution network design scheme created by the user during the use of the design selection knowledge graph; or it can be a target entity corresponding to the design selection data added by the user when updating the design selection knowledge graph based on new design materials. This embodiment does not specifically limit the method of obtaining the newly added target entity, and can be adaptively set according to the actual application scenario.

[0108] In the design selection knowledge graph provided in this embodiment, each legend entity has a corresponding graph pattern. When adding a new target entity to the design selection knowledge graph provided in this embodiment, it is necessary to first determine whether the new target entity is a legend entity. If the new target entity is a legend entity, a corresponding graph pattern needs to be added to the design selection knowledge graph to generate a new graph branch. If the new target entity is not a legend entity, it means that the new target entity can be matched with a corresponding graph pattern in the current design selection knowledge graph, and is added to the corresponding graph pattern according to the association relationship corresponding to the type of the target entity. After updating the graph pattern corresponding to the legend entity, the knowledge graph of each graph pattern is constructed in the form of triples.

[0109] This embodiment increases the data volume of the design selection knowledge graph by continuously updating it, so that designers can find the design selection parameters that match the legend more conveniently and quickly when using the knowledge graph.

[0110] In summary, this application provides a method for constructing a design selection knowledge graph. By adding material group entities and overhead line relationship entities during the construction process, this embodiment effectively simplifies the structure of the design selection knowledge graph, enabling a more intuitive display of material composition and overhead line scheme types related to the legend to users, thereby effectively improving the efficiency of users in power grid design selection. Furthermore, by materializing various types of design selection data and associating and combining them based on the specific information of each entity, this embodiment effectively improves the construction quality of the design selection knowledge graph. This ensures that the final constructed design selection knowledge graph accurately reflects actual business knowledge, making it easier to guide the application of distribution network design selection.

[0111] Example 2

[0112] refer to Figure 4 This is a flowchart illustrating a method for applying a design selection knowledge graph according to an embodiment of this application. The method for applying a design selection knowledge graph according to an embodiment of this application, such as... Figure 4 As shown, it includes:

[0113] Step S401: Obtain the legend information to be queried and the query target;

[0114] Step S402: Analyze the legend information to be queried to obtain the legend entity to be queried;

[0115] Step S403: Match the target entity corresponding to the entity to be queried in the preset design selection knowledge graph, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, overhead line relationship entity, material entity, and conductor entity.

[0116] In a specific embodiment, the design selection knowledge graph provided in Embodiment 1 can be applied to any query system or power grid design system so that users can query the corresponding material information and overhead line information in real time based on the legend information.

[0117] Specifically, the query target can be material information or overhead line information, and can be adaptively set according to the actual application scenario.

[0118] In practical implementation, when users design power grid distribution networks, they add legend information to the design drawings. The system can automatically export the material groups and wiring relationships associated with that legend information. The material groups include various types of materials, and the wiring relationships include various wiring schemes and the corresponding conductor types. Users can complete the design selection for the legend based on the exported material groups and wiring relationships.

[0119] According to a specific implementation of this application, the step of matching the target entity corresponding to the query legend entity in a preset design selection knowledge graph and exporting the output entity corresponding to the query target includes:

[0120] Obtain multiple target entities corresponding to the entity to be queried in the legend, each target entity including a historical usage count attribute;

[0121] The target entities are sorted according to the historical usage count attribute, and the target entity with the highest historical usage count is exported as the output entity corresponding to the query target.

[0122] In the specific implementation process, the material information in the material group can also be sorted according to the number of times each material has been used in the user's history. Users can select the material information with the most historical usages as the material type of the current legend based on the sorting in the material group.

[0123] Specifically, the user's historical usage count can be stored as query attribute information in the attribute of the corresponding graph mode of the design selection knowledge graph, so that the user can call it when performing the query step.

[0124] It should be noted that the attributes of the graph mode corresponding to the design selection knowledge graph can also be adaptively configured according to the actual application scenario, and are not limited to a single one here.

[0125] In summary, the embodiments of this application provide a method for applying a design selection knowledge graph, which can be applied to a query system to quickly export material group entities and overhead line relationship entities that match the legend entities based on the legend entities input by the user, thereby further improving the efficiency of users in power distribution network design and selection.

[0126] refer to Figure 5 This is a schematic diagram of a device module for a design selection knowledge graph construction device 500 provided in an embodiment of this application. The design selection knowledge graph construction device 500 provided in this embodiment of the application, as... Figure 5 As shown, it includes:

[0127] Material acquisition module 501 is used to acquire the design materials to be analyzed;

[0128] The material analysis module 502 is used to analyze the design material to be analyzed in order to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information.

[0129] The entity construction module 503 is used to extract and construct n target entities based on the design selection data, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities.

[0130] The graph construction module 504 is used to construct a design selection knowledge graph based on all target entities and the relationships between them.

[0131] refer to Figure 6 This is a schematic diagram of a device module for an application device 600 for a design selection knowledge graph provided in an embodiment of this application. The application device 600 for a design selection knowledge graph provided in an embodiment of this application, such as... Figure 6 As shown, it includes:

[0132] The query acquisition module 601 is used to acquire the legend information to be queried and the query target;

[0133] The query analysis module 602 is used to analyze the legend information to be queried in order to obtain the legend entity to be queried;

[0134] The graph query module 603 is used to match the target entity corresponding to the query legend entity in the preset design selection knowledge graph, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, overhead line relationship entity, overhead line entity, material entity, and conductor entity.

[0135] In addition, this application embodiment also provides a computer device, which includes a processor and a memory. The memory stores a computer program, and the computer program executes the design selection knowledge graph construction method and the design selection knowledge graph application method in the foregoing method embodiment when it is run on the processor.

[0136] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run on a processor, it executes the design selection knowledge graph construction method and the design selection knowledge graph application method in the foregoing method embodiments.

[0137] Furthermore, the specific implementation process of the design selection knowledge graph construction device, the design selection knowledge graph application device, the computer equipment, and the computer-readable storage medium mentioned in the above embodiments can be found in the specific implementation process of the above method embodiments, and will not be repeated here.

[0138] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, as an alternative implementation, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0139] In addition, the functional modules or units in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0140] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0141] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for constructing a design selection knowledge graph, characterized in that, include: Obtain the design materials to be analyzed; The design materials to be analyzed are used to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information. Based on the design selection data, n target entities are extracted and constructed, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities. Construct a design selection knowledge graph based on all target entities and the relationships between them; The construction of a design selection knowledge graph based on all target entities and the relationships between them includes: Based on the relationships between target entities, different types of target entities are combined to obtain m graph patterns corresponding to m legend entities, where m is a positive integer; The triples corresponding to each graph pattern are stored in a preset graph database to generate the design selection knowledge graph.

2. The method of claim 1, wherein, The extraction and construction of n target entities based on the design selection data includes: Based on the knowledge representation method of attribute graphs, n target entities are extracted and constructed from the design selection data.

3. The method of claim 1, wherein, After constructing the design selection knowledge graph based on all target entities and the relationships between them, the method further includes: Retrieve the newly added target entity; Update the design selection knowledge graph according to the type of newly added legend entities; If the newly added target entity is a newly added legend entity, a new graph pattern is constructed based on the newly added legend entity and its associated target entity, and the triples corresponding to the graph pattern are stored in the preset graph database to update the design selection knowledge graph. If the newly added target entity is not a newly added legend entity, then according to the type of the newly added target entity and its association with the corresponding graph pattern, the newly added target entity is added to the corresponding graph pattern to update the design selection knowledge graph.

4. An application method of a design selection knowledge graph, characterized in that, include: Retrieve the legend information to be queried and the query target; Analyze the legend information to be queried to obtain the legend entity to be queried; In the preset design selection knowledge graph, match the target entity corresponding to the entity to be queried in the legend, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, overhead line relationship entity, overhead line entity, material entity, and conductor entity. The design selection knowledge graph is obtained according to any one of claims 1-3.

5. The method according to claim 4, characterized in that, The step of matching the target entity corresponding to the query legend entity in the preset design selection knowledge graph and exporting the output entity corresponding to the query target includes: Obtain multiple target entities corresponding to the entity to be queried in the legend, each target entity including a historical usage count attribute; The target entities are sorted according to the historical usage count attribute, and the target entity with the highest historical usage count is exported as the output entity corresponding to the query target.

6. A device for constructing a design selection knowledge graph, characterized in that, include: The material acquisition module is used to acquire the design materials to be analyzed. The material analysis module is used to analyze the design material to be analyzed in order to extract design selection data that conforms to a preset data structure. The design selection data includes legend information, legend attribute information, legend material information, and legend wiring information. The entity construction module is used to extract and construct n target entities based on the design selection data, where n is a positive integer. The target entities include legend entities, material group entities, wiring relationship entities, wiring entities, material entities, and conductor entities. The graph construction module is used to construct a design selection knowledge graph based on all target entities and the relationships between them. The construction of a design selection knowledge graph based on all target entities and the relationships between them includes: Based on the relationships between target entities, different types of target entities are combined to obtain m graph patterns corresponding to m legend entities, where m is a positive integer; The triples corresponding to each graph pattern are stored in a preset graph database to generate the design selection knowledge graph.

7. An application device of a design selection knowledge graph, characterized in that, include: The query acquisition module is used to obtain the legend information to be queried and the query target; The query analysis module is used to analyze the legend information to be queried in order to obtain the legend entity to be queried; The graph query module is used to match the target entity corresponding to the query legend entity in the preset design selection knowledge graph, and export the output entity corresponding to the query target. The output entity is at least one of the following: material group entity, wiring relationship entity, wiring entity, material entity, and conductor entity. The design selection knowledge graph is obtained according to any one of claims 1-3.

8. A computer device, comprising: The computer device includes a processor and a memory, the memory storing a computer program, which, when run on the processor, executes the method for constructing the design selection knowledge graph according to any one of claims 1 to 3 and the method for applying the design selection knowledge graph according to claim 4 or 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when run on a processor, executes the method for constructing the design selection knowledge graph according to any one of claims 1 to 3 and the method for applying the design selection knowledge graph according to claim 4 or 5.

Images