Highway design document generation method and device based on survey and design knowledge base

Abstract

The application provides a highway design document generation method and device based on survey and design knowledge base, and relates to the technical field of highways. The method comprises the following steps: taking a facility to be designed as a node and an association relationship between different facilities to be designed as an edge to construct a design knowledge graph of a highway to be designed; constructing a survey and design knowledge base based on design specifications of the highway; wherein the survey and design knowledge base is used for the design of the highway; determining a design constraint condition of the highway to be designed, and extracting a plurality of candidate design schemes from the survey and design knowledge base according to the design constraint condition; adjusting the design knowledge graph based on the design constraint condition to obtain a target knowledge graph; and determining a target design scheme of the highway to be designed according to a matching degree of the target knowledge graph and each candidate design scheme. The application can ensure the matching degree between the finally determined target design scheme and design requirements.

Description

Technical Field

[0001] This invention relates to the field of highway technology, and in particular to a method and apparatus for generating highway design documents based on a survey and design knowledge base. Background Technology

[0002] my country's highway design is rapidly transforming towards high quality and intelligentization. As the core framework for project implementation, highway design schemes must comprehensively consider multiple constraints, including topography, geology, environmental protection, engineering costs, and construction organization. Traditional methods relying on manual experience are no longer adequate for the efficient decision-making needs of complex engineering scenarios. In the wave of industry digitalization, knowledge bases are gradually being integrated into the engineering design field. By collecting heterogeneous data from multiple sources, such as standards and specifications, historical cases, and expert experience, a structured knowledge system is constructed to provide data support for the intelligent generation of design schemes, becoming an important direction for improving the efficiency and scientific rigor of scheme preparation.

[0003] Existing technologies mainly adopt a modular knowledge base generation scheme based on rule matching. This requires pre-decomposing industry standards, design parameters, and typical construction methods related to highway design into independent knowledge modules such as roadbed, pavement, bridge and tunnel, and traffic engineering. A mapping index between keywords and modules is established through manual annotation. After inputting basic parameters such as project topography, geology, and design level, the system retrieves the corresponding knowledge units through keyword matching, splices them together according to fixed logic to form a preliminary design scheme, and simultaneously conducts standard compliance verification.

[0004] However, existing technologies rely on manually preset rules, which makes it difficult to handle cross-module related decisions in complex scenarios. Therefore, the design solutions generated by existing technologies have a low degree of matching with actual design requirements. Summary of the Invention

[0005] This invention provides a method and apparatus for generating highway design documents based on a survey and design knowledge base, in order to solve the problem that existing technologies rely on manually preset rules, which are difficult to handle cross-module related decisions in complex scenarios, resulting in a low degree of matching between the design schemes generated by existing technologies and actual design requirements.

[0006] In a first aspect, embodiments of the present invention provide a method for generating highway design documents based on a survey and design knowledge base, including: A design knowledge graph of the highway to be designed is constructed, with the facilities to be designed as nodes and the relationships between different facilities as edges. Based on the design specifications for expressways, a survey and design knowledge base is constructed; the survey and design knowledge base is used for expressway design. The design constraints of the highway to be designed are determined, and multiple candidate design schemes are extracted from the survey and design knowledge base based on the design constraints. Based on design constraints, the design knowledge graph is adjusted to obtain the target knowledge graph; Based on the degree of matching between the target knowledge graph and each candidate design scheme, the target design scheme for the highway to be designed is determined.

[0007] Secondly, embodiments of the present invention provide a highway design document generation device based on a survey and design knowledge base, comprising: The construction module is used to build a design knowledge graph of the highway to be designed, with the facilities to be designed as nodes and the relationships between different facilities to be designed as edges. The standards module is used to build a survey and design knowledge base based on highway design standards; the survey and design knowledge base is used for highway design. The extraction module is used to determine the design constraints of the highway to be designed, and extract multiple candidate design schemes from the survey and design knowledge base based on the design constraints. The adjustment module is used to adjust the design knowledge graph based on design constraints to obtain the target knowledge graph; The determination module is used to determine the target design scheme of the highway to be designed based on the degree of matching between the target knowledge graph and each candidate design scheme.

[0008] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0009] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0010] In this embodiment of the invention, a design knowledge graph is constructed using the facilities to be designed as nodes and the relationships between facilities as edges. This structurally models the relationships between facility entities, their process connections, and spatial constraints, providing a complete data foundation for subsequent scheme matching. Simultaneously, a survey and design knowledge base is built based on design specifications, enabling the system to retrieve and reuse the specification knowledge, providing a standard reference for scheme generation. Based on this, multiple candidate schemes are extracted from the survey and design knowledge base according to design requirements, and the design knowledge graph is dynamically adjusted in conjunction with constraints, ensuring that the target knowledge graph reflects the associated constraints in the actual design scenario. Finally, the matching degree between the target knowledge graph and each candidate scheme is quantitatively compared, and the candidate design scheme with the highest matching degree is selected as the target design scheme, effectively improving the matching degree between the target design scheme and the design requirements. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating the implementation of the highway design document generation method based on a survey and design knowledge base provided in this embodiment of the invention. Figure 2 This is a flowchart illustrating the implementation of step S150 of the highway design document generation method based on a survey and design knowledge base provided in this embodiment of the invention. Figure 3 This is a schematic diagram of the structure of the highway design document generation device based on the survey and design knowledge base provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0013] See Figure 1 The document illustrates a flowchart of the highway design document generation method based on a survey and design knowledge base provided in this embodiment of the invention, which is described in detail below: Step S110: Construct a design knowledge graph of the highway to be designed, with the facilities to be designed as nodes and the relationships between different facilities to be designed as edges.

[0014] In some embodiments, the highway to be designed includes multiple different types of facilities such as roadbed, pavement, bridges, tunnels, culverts, traffic safety facilities, and electromechanical facilities. These facilities have close interdependencies and constraints in terms of spatial layout, construction procedures, and functional logic. Constructing a design knowledge graph is to comprehensively represent these facilities and their internal relationships, using a graph structure to describe these entities and their relationships. Nodes in the design knowledge graph represent various facilities on the highway, such as a specific bridge, a section of roadbed, or a tunnel; edges represent multi-dimensional relationships between different facilities, including spatial constraints, connections in design procedures, and functional dependencies. For example, a bridge must be erected within a specific geographical area; tunnel entrances must smoothly connect with the roadbed section; pavement construction can only proceed after the roadbed is laid; and the power supply lines for electromechanical facilities must rely on utility tunnels in the traffic engineering.

[0015] In one possible implementation, the specific processing method of step S110 includes: determining all facilities to be designed on the highway to be designed according to the route planning scheme of the highway to be designed, and extracting the basic attribute parameters of each facility to be designed; determining the connection relationship and spatial constraint relationship of the design process of different facilities to be designed as the association relationship between different facilities to be designed; and constructing a design knowledge graph of the highway to be designed with each facility to be designed as a node, the basic attribute parameters of each facility to be designed as node attributes, and the association relationship between different facilities to be designed as edges.

[0016] In some embodiments, the route planning scheme includes information such as the alignment, mileage markers, technical grade, and preliminary design plans for large structures along the route of the highway to be designed. By analyzing the route planning scheme, a complete list of facilities that need to be designed for the project can be identified. For each identified facility to be designed, its basic attribute parameters need to be further extracted. These basic attribute parameters describe the characteristics of the facility and key information that affects the subsequent design plan. For example, for bridges, the basic attribute parameters may include bridge length, bridge width, structural type, span combination, etc.; for tunnels, they may include tunnel length, cross-sectional shape, surrounding rock grade, etc.; for roadbeds, they may include cut and fill height, roadbed width, slope ratio, etc.

[0017] It should be noted that there are complex relationships between the different facilities to be designed, and these relationships determine the design logic and the overall integrity of the scheme. Among these, the connection relationships between design procedures reflect the sequential order of the facilities' design; for example, tunnel excavation and initial support must be completed before secondary lining construction can proceed. Spatial constraints reflect the mutual constraints of the facilities' geometric positions; for example, the elevation of culverts must be consistent with the elevation of drainage ditches. Based on this, each facility to be designed is treated as an independent node, and its basic attribute parameters are stored and associated as the attribute information of that node. Simultaneously, the determined connection relationships and spatial constraints between different facilities are used as edges to connect corresponding facility nodes.

[0018] By constructing a design knowledge graph, scattered and unstructured project information can be transformed into structured knowledge, enabling subsequent calculation processes to clearly understand what facilities exist, what their characteristics are, and what mutual constraints exist between them, thus providing a data foundation for intelligent solution generation and evaluation.

[0019] Step S120: Based on the design specifications for expressways, construct a survey and design knowledge base; wherein, the survey and design knowledge base is used for the design of expressways.

[0020] In some embodiments, the survey and design of highways must strictly adhere to a series of technical standards, specifications, procedures, and detailed rules issued by national, industry, and local governments. These survey and design specifications are the fundamental basis for ensuring project quality, safety, and durability. However, the specifications are usually documents described in natural language, with numerous contents, complex clauses, and scattered knowledge points, making them difficult for computer systems to directly understand and efficiently utilize. In order to transform the specification knowledge into computable and reasonable knowledge resources, a structured survey and design knowledge base needs to be constructed.

[0021] In one possible implementation, the specific processing method of step S120 includes: semantically aligning multiple design rule texts in the highway design specifications to obtain the standard design specifications for highways; extracting the control indicators of each facility to be designed in each dimension from the standard design specifications; and constructing a survey and design knowledge base based on the correlation of each dimension of each facility to be designed and the control indicators of each dimension.

[0022] In some embodiments, design specifications from different sources may differ in their expression, terminology, and granularity. To eliminate these differences and form a unified knowledge source, it is first necessary to semantically align the original design rule texts. Semantic alignment refers to using techniques such as natural language processing and text mining to associate and unify texts that describe the same technical concept but with different expressions. For example, different specifications may use different terms such as cement concrete strength and concrete grade to describe the same technical indicator. The semantic alignment process can associate these synonymous or near-synonymous terms under the same standard concept, thereby forming a set of internally consistent standard design specifications.

[0023] It is important to note that after obtaining the standard design specifications, it is necessary to extract control indicators for each facility to be designed across various dimensions. These control indicators are specific quantitative or qualitative requirements for facility design, construction, and acceptance as outlined in the specifications. For example, for a roadbed, a control indicator for its strength dimension could be that the resilient modulus of the roadbed top surface should not be less than 30 MPa; for a pavement, a control indicator for its smoothness dimension could be that the International Roughness Index (IRI) should not exceed 2.0 m / km. After extracting the control indicators for each facility, it is also necessary to clarify the relationships between these indicators across different dimensions and between different facilities. For example, the strength index of the roadbed directly affects the thickness design of the pavement layer. Finally, these extracted control indicators and their relationships are stored and represented in a structured form, resulting in a survey and design knowledge base.

[0024] The survey and design knowledge base transforms scattered regulatory provisions into a structured indicator system centered around facilities and dimensions. When designing a scheme, users can directly consult the knowledge base to obtain the quantitative indicator requirements that a specific facility must meet under specific constraints, thereby ensuring that the generated scheme is technically compliant and enabling automatic and objective evaluation of different candidate schemes.

[0025] Step S130: Determine the design constraints of the highway to be designed, and extract multiple candidate design schemes from the survey and design knowledge base based on the design constraints.

[0026] In some embodiments, design constraints are personalized limitations and requirements specific to a particular project, and may include design environment information, design time information, engineering cost information, and route control requirements. After obtaining the design constraints, it is necessary to extract corresponding knowledge units from the survey and design knowledge base based on these specific design constraints, and combine them to generate multiple feasible candidate design schemes.

[0027] In one possible implementation, the specific processing method of step S130 includes: extracting the design constraints of the highway to be designed from the design requirements of the highway to be designed; inputting the design constraints into the survey and design knowledge base to obtain multiple facility design schemes corresponding to each facility to be designed; and combining the multiple facility design schemes corresponding to each facility to be designed based on the relationship between the design constraints and each facility to be designed to obtain multiple candidate design schemes.

[0028] In some embodiments, design requirements are a collection of documents describing project objectives, scope, and constraints. By parsing these documents, structured design constraints can be extracted. These constraints are diverse in type; for example, design environmental information constraints may include the topographical and geological conditions, climate and hydrological conditions of the project area, and the distribution of ecologically sensitive areas; design time information constraints may include the total project duration requirements and key milestone duration requirements; project cost information constraints may include the upper limit of the total project investment and cost control targets for each sub-project; and route control requirements constraints may include coordination requirements with existing road networks, pipelines, and urban and rural planning.

[0029] After determining the specific design constraints, these constraints are input into the survey and design knowledge base as query and filtering parameters to obtain facility design schemes. For example, if the design constraints specify that the expected traffic load level for a certain road segment is heavy traffic, inputting this information into the survey and design knowledge base allows it to retrieve specific technical parameters such as pavement structure combination design schemes and base course thickness requirements under the heavy traffic load level, thereby obtaining one or more feasible facility design schemes for the pavement facilities of that road segment.

[0030] It is important to note that after obtaining multiple alternative schemes for each facility to be designed, they cannot be simply combined arbitrarily. This is because different facility schemes influence and constrain each other; for example, selecting a certain high embankment subgrade scheme may affect the structural form and burial depth of the underpass culvert. Therefore, when combining schemes to form an overall design scheme, the relationships between the facilities to be designed must be used as the combination rules. All alternative schemes for each facility must be traversed and combined to form multiple candidate design schemes that can satisfy all design constraints as a whole. This process ensures that the generated candidate schemes are not only feasible at the individual facility level but also consistent at the overall system level.

[0031] Step S140: Based on the design constraints, adjust the design knowledge graph to obtain the target knowledge graph.

[0032] In some embodiments, the initial design knowledge graph is constructed based on route planning schemes and general engineering experience, without reflecting the impact of specific design constraints on the tightness of relationships between facilities. For example, under time constraints, the temporal connection between bridge and roadbed construction becomes more important than usual. To enable the knowledge graph to reflect these differences in the importance of relationships between facilities under specific constraints, the initial design knowledge graph needs to be dynamically adjusted based on design constraints to obtain a target knowledge graph with importance weights.

[0033] In one possible implementation, step S140 specifically includes: comparing the association relationship corresponding to each edge in the design knowledge graph with each design constraint to obtain the matching degree between each edge and each design constraint; calculating the weight of each edge by weighting the multiple matching degrees corresponding to each edge based on the preset weight of each design constraint; and adding the weight of each edge to the design knowledge graph to obtain the target knowledge graph.

[0034] In some embodiments, for each edge in the design knowledge graph, the associated relationship needs to be compared with each specific constraint to determine its relevance and fit, and a matching score is assigned. For example, for a process connection edge linking a bridge node and a roadbed node, it is compared with the constraint of a total construction period of 24 months. If the bridge is a key project controlling the construction period, and its construction progress is closely linked to the preparation process of roadbed filling, then the matching degree between this edge and the construction period constraint is high; otherwise, it is low. In this way, the association strength between each edge and each constraint can be quantified.

[0035] Since different design constraints have varying degrees of impact on solution development, a weight coefficient needs to be pre-assigned to each constraint to reflect its importance. For example, in ecologically sensitive areas, environmental protection constraints have a very high weight; in projects with tight budgets, cost constraints have an even greater weight. For each edge, multiple matching degrees obtained by comparing it with all constraints are weighted and averaged according to the weight of the corresponding constraint to obtain a comprehensive weight value. This weight value represents the importance of the relationship represented by the edge under the specific constraints of the project. After obtaining the weights of all edges, these weight values ​​are added as new attributes to the corresponding edges of the design knowledge graph to obtain the target knowledge graph. The adjusted target knowledge graph can adaptively change according to specific project needs, providing a quantitative basis for subsequent evaluation of candidate solutions.

[0036] Step S150: Determine the target design scheme of the highway to be designed based on the degree of matching between the target knowledge graph and each candidate design scheme.

[0037] In some embodiments, by calculating the degree of matching between each candidate design scheme and the target knowledge graph, the optimal target design scheme can be selected from the candidate design schemes, and the target design scheme can be stored in the design document.

[0038] like Figure 2 As shown, the specific processing method of step S150 above includes steps S1501-S1503, the specific contents of which are as follows: Step S1501: Construct a candidate knowledge graph corresponding to each candidate design scheme, using the facilities in each candidate design scheme as nodes and the relationships between each facility as edges.

[0039] In some embodiments, in order to determine the degree of matching between candidate design schemes and target knowledge graphs, each candidate design scheme needs to be transformed into a knowledge graph, with all the facilities to be designed contained in the candidate design scheme as nodes and the relationships between facilities such as construction sequence and spatial location in the candidate design scheme as edges, to construct the candidate knowledge graph corresponding to the candidate design scheme.

[0040] Step S1502: For any candidate knowledge graph, calculate the matching degree between the candidate knowledge graph and the target knowledge graph based on the nodes and edges in the candidate knowledge graph.

[0041] In some embodiments, the matching degree is a comprehensive quantitative metric used to measure the similarity between the target knowledge graph and the candidate knowledge graph in terms of node composition and edge structure. There can be various specific methods for calculating the matching degree, such as calculating the size of the largest common subgraph of the two graphs, or calculating the similarity based on the feature vectors of nodes and edges.

[0042] In one possible implementation, step S1502 specifically includes: selecting multiple target edges and target nodes corresponding to each target edge from the target knowledge graph; wherein the weight of the target edge is greater than a preset weight threshold; determining the ratio of the number of target nodes corresponding to any node in the candidate knowledge graph to the total number of all target nodes as the first matching degree between the candidate knowledge graph and the target knowledge graph; determining the ratio of the number of target nodes corresponding to any node in the candidate knowledge graph to the total number of all nodes in the candidate knowledge graph as the second matching degree between the candidate knowledge graph and the target knowledge graph; when the first matching degree is greater than the second matching degree, and the difference between the first matching degree and the second matching degree is greater than a preset threshold, updating the first matching degree to the product of the first matching degree and a preset decay coefficient; determining the ratio of the number of target edges corresponding to any edge in the candidate knowledge graph to the total number of all target edges as the third matching degree between the candidate knowledge graph and the target knowledge graph; and performing a weighted average of the first matching degree and the third matching degree to obtain the degree of matching between the candidate knowledge graph and the target knowledge graph.

[0043] In some embodiments, considering the varying importance of different edges in the target knowledge graph, a preset weight threshold is needed to filter out target edges with higher weights and the key target nodes connected by these edges. These target edges and nodes represent the most critical facilities and relationships in the highway to be designed, and are the key objects of evaluation for assessing the merits of the proposed solutions. The first matching degree is used to evaluate the coverage of target nodes by the candidate design solutions corresponding to the candidate knowledge graph. The second matching degree is used to measure the focus of the candidate design solution, i.e., what proportion of its own nodes are core nodes. Since a candidate design solution may contain all target nodes, but also a large number of irrelevant nodes unrelated to the design requirements of the highway to be designed, the first matching degree between the candidate design solution and the target knowledge graph may be high, but the second matching degree will be low. Therefore, when the first matching degree is much greater than the second matching degree, it indicates that there are too many interfering items in the candidate design solution. To suppress this situation and avoid scoring distortion, a preset attenuation coefficient can be introduced. When the first matching degree is significantly greater than the second matching degree, the first matching degree is attenuated to reduce its score.

[0044] In some embodiments, the third matching degree is used to represent the proportion of edges in the candidate design scheme to all target edges. The third matching degree determines the similarity between the relationships between different facilities in the candidate design scheme and the relationships between different facilities in the highway to be designed. For each candidate design scheme, the weighted average of the first and third matching degrees is calculated, and the resulting comprehensive score is the final matching degree between the candidate design scheme and the target knowledge graph. This multi-dimensional matching degree calculation method, with constraints and attenuation mechanisms, can more accurately determine the candidate scheme that best fits the design requirements and specifications.

[0045] Step S1503: The candidate design scheme with the highest matching degree with the target knowledge graph is determined as the target design scheme of the highway to be designed.

[0046] In some embodiments, by calculating and comparing the matching degree of all candidate solutions, the solution with the highest matching degree is selected as the target design solution, which can ensure a high degree of matching between the target design solution and the target knowledge graph, and ensure the degree of matching between the target design solution and the actual design requirements.

[0047] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0048] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0049] Figure 3 The diagram shows a schematic representation of a highway design document generation device based on a survey and design knowledge base, as provided in an embodiment of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 3 As shown, the highway design document generation device 3 based on the survey and design knowledge base includes: Module 31 is used to construct a design knowledge graph of the highway to be designed, with the facilities to be designed as nodes and the relationships between different facilities to be designed as edges. Standards module 32 is used to build a survey and design knowledge base based on highway design standards; the survey and design knowledge base is used for highway design. Extraction module 33 is used to determine the design constraints of the highway to be designed, and extract multiple candidate design schemes from the survey and design knowledge base according to the design constraints; The adjustment module 34 is used to adjust the design knowledge graph based on design constraints to obtain the target knowledge graph; The determination module 35 is used to determine the target design scheme of the highway to be designed based on the degree of matching between the target knowledge graph and each candidate design scheme.

[0050] In one possible implementation, module 31 is specifically used to determine all facilities to be designed on the highway to be designed according to the route planning scheme of the highway to be designed, and extract the basic attribute parameters of each facility to be designed; determine the connection relationship and spatial constraint relationship of the design process of different facilities to be designed as the association relationship between different facilities to be designed; and construct the design knowledge graph of the highway to be designed with each facility to be designed as a node, the basic attribute parameters of each facility to be designed as node attributes, and the association relationship between different facilities to be designed as edges.

[0051] In one possible implementation, the specification module 32 is specifically used to semantically align multiple design rule texts in the highway design specification to obtain the standard design specification for the highway; extract the control indicators for each facility to be designed in each dimension from the standard design specification; and construct a survey and design knowledge base based on the correlation between each dimension of each facility to be designed and the control indicators for each dimension.

[0052] In one possible implementation, the extraction module 33 is specifically used to extract the design constraints of the highway to be designed from the design requirements of the highway to be designed; input the design constraints into the survey and design knowledge base to obtain multiple facility design schemes corresponding to each facility to be designed; and combine the multiple facility design schemes corresponding to each facility to be designed based on the relationship between the design constraints and each facility to be designed to obtain multiple candidate design schemes.

[0053] In one possible implementation, the adjustment module 34 is specifically used to compare the association relationship corresponding to each edge in the design knowledge graph with each design constraint to obtain the matching degree between each edge and each design constraint; based on the preset weight of each design constraint, the multiple matching degrees corresponding to each edge are weighted and calculated to obtain the weight of each edge; and the weight of each edge is added to the design knowledge graph to obtain the target knowledge graph.

[0054] In one possible implementation, module 35 is specifically used to construct a candidate knowledge graph corresponding to each candidate design scheme, with the facilities in each candidate design scheme as nodes and the relationships between each facility as edges; for any candidate knowledge graph, the matching degree between any candidate knowledge graph and the target knowledge graph is calculated based on the nodes and edges in any candidate knowledge graph; and the candidate design scheme with the highest matching degree with the target knowledge graph is determined as the target design scheme of the highway to be designed.

[0055] In one possible implementation, the determining module 35 is further configured to filter multiple target edges and target nodes corresponding to each target edge from the target knowledge graph; wherein the weight of the target edge is greater than a preset weight threshold; the ratio of the number of target nodes corresponding to any node in the candidate knowledge graph to the total number of all target nodes is determined as the first matching degree between the candidate knowledge graph and the target knowledge graph; the ratio of the number of target nodes corresponding to any node in the candidate knowledge graph to the total number of all nodes in the candidate knowledge graph is determined as the second matching degree between the candidate knowledge graph and the target knowledge graph; when the first matching degree is greater than the second matching degree, and the difference between the first matching degree and the second matching degree is greater than a preset threshold, the first matching degree is updated to the product of the first matching degree and a preset decay coefficient; the ratio of the number of target edges corresponding to any edge in the candidate knowledge graph to the total number of all target edges is determined as the third matching degree between the candidate knowledge graph and the target knowledge graph; a weighted average is performed on the first matching degree and the third matching degree to obtain the degree of matching between the candidate knowledge graph and the target knowledge graph.

[0056] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 40 and a memory 41. The memory 41 stores a computer program 42. When the processor 40 executes the computer program 42, it implements the steps in the various method embodiments described above. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module / unit in the various device embodiments described above.

[0057] For example, computer program 42 may be divided into one or more modules / units, which are stored in memory 41 and executed by processor 40 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0058] Electronic device 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0059] The processor 40 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0060] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store the computer program 42 and other programs and data required by the electronic device 4. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0061] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0062] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0063] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0064] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0065] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for generating highway design documents based on a survey and design knowledge base, characterized in that, include: A design knowledge graph of the highway to be designed is constructed, with the facilities to be designed as nodes and the relationships between different facilities as edges. A survey and design knowledge base is constructed based on highway design specifications; wherein, the survey and design knowledge base is used for highway design. The design constraints of the highway to be designed are determined, and multiple candidate design schemes are extracted from the survey and design knowledge base based on the design constraints. Based on the design constraints, the design knowledge graph is adjusted to obtain the target knowledge graph; The target design scheme for the highway to be designed is determined based on the degree of matching between the target knowledge graph and each candidate design scheme.

2. The method for generating highway design documents based on a survey and design knowledge base according to claim 1, characterized in that, The design knowledge graph of the highway to be designed is constructed using the facilities to be designed as nodes and the relationships between different facilities as edges, including: Based on the route planning scheme of the expressway to be designed, all facilities to be designed on the expressway to be designed are identified, and the basic attribute parameters of each facility to be designed are extracted. The design process connection and spatial constraint relationship of different facilities to be designed are determined as the relationship between different facilities to be designed; A design knowledge graph of the highway to be designed is constructed, with each facility to be designed as a node, the basic attribute parameters of each facility to be designed as node attributes, and the relationship between different facilities to be designed as edges.

3. The method for generating highway design documents based on a survey and design knowledge base according to claim 2, characterized in that, The aforementioned design specifications for highways will be used to construct a survey and design knowledge base, including: Semantic alignment was performed on multiple design rule texts in the design specifications for expressways to obtain the standard design specifications for expressways. From the aforementioned standard design specifications, extract the control indicators for each facility to be designed in each dimension; The survey and design knowledge base is constructed based on the relationships between each dimension of each facility to be designed and the control indicators of each dimension.

4. The method for generating highway design documents based on a survey and design knowledge base according to claim 3, characterized in that, The process involves determining the design constraints for the highway to be designed, and extracting multiple candidate design schemes from the survey and design knowledge base based on the design constraints, including: Extract the design constraints of the highway to be designed from the design requirements of the highway to be designed; The design constraints are input into the survey and design knowledge base to obtain multiple facility design schemes for each facility to be designed. Based on the design constraints and the relationships between each facility to be designed, multiple facility design schemes corresponding to each facility to be designed are combined to obtain multiple candidate design schemes.

5. The method for generating highway design documents based on a survey and design knowledge base according to claim 4, characterized in that, The process of adjusting the design knowledge graph based on the design constraints to obtain the target knowledge graph includes: The association relationship corresponding to each edge in the design knowledge graph is compared with each design constraint to obtain the matching degree between each edge and each design constraint. Based on the preset weight of each design constraint, the weight of each edge is obtained by weighting the multiple matching degrees corresponding to each edge. The weight of each edge is added to the design knowledge graph to obtain the target knowledge graph.

6. The method for generating highway design documents based on a survey and design knowledge base according to any one of claims 1-5, characterized in that, The step of determining the target design scheme for the highway to be designed based on the matching degree between the target knowledge graph and each candidate design scheme includes: Using the facilities in each candidate design scheme as nodes and the relationships between each facility as edges, construct a candidate knowledge graph corresponding to each candidate design scheme; For any candidate knowledge graph, calculate the degree of matching between the candidate knowledge graph and the target knowledge graph based on the nodes and edges in the candidate knowledge graph; The candidate design scheme with the highest matching degree with the target knowledge graph is determined as the target design scheme of the highway to be designed.

7. The method for generating highway design documents based on a survey and design knowledge base according to claim 6, characterized in that, The step of calculating the matching degree between any candidate knowledge graph and the target knowledge graph based on the nodes and edges in any candidate knowledge graph includes: Multiple target edges and the target nodes corresponding to each target edge are selected from the target knowledge graph; wherein the weight of the target edge is greater than a preset weight threshold. The ratio of the number of target nodes corresponding to any node in the candidate knowledge graph to the total number of all target nodes is determined as the first matching degree between the candidate knowledge graph and the target knowledge graph. The ratio of the number of target nodes corresponding to any node in any candidate knowledge graph to the total number of all nodes in any candidate knowledge graph is determined as the second matching degree between any candidate knowledge graph and the target knowledge graph. When the first matching degree is greater than the second matching degree, and the difference between the first matching degree and the second matching degree is greater than a preset threshold, the first matching degree is updated to the product of the first matching degree and the preset attenuation coefficient; The ratio of the number of target edges corresponding to the edges of any candidate knowledge graph to the total number of all target edges is determined as the third matching degree between the candidate knowledge graph and the target knowledge graph. The first matching degree and the third matching degree are weighted and averaged to obtain the matching degree between any candidate knowledge graph and the target knowledge graph.

8. A highway design document generation device based on a survey and design knowledge base, characterized in that, include: The construction module is used to build a design knowledge graph of the highway to be designed, with the facilities to be designed as nodes and the relationships between different facilities to be designed as edges. The specification module is used to build a survey and design knowledge base based on highway design specifications; wherein, the survey and design knowledge base is used for highway design. The extraction module is used to determine the design constraints of the highway to be designed, and extract multiple candidate design schemes from the survey and design knowledge base according to the design constraints; An adjustment module is used to adjust the design knowledge graph based on the design constraints to obtain a target knowledge graph; The determination module is used to determine the target design scheme of the highway to be designed based on the degree of matching between the target knowledge graph and each candidate design scheme.

9. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images