Intersection traffic organization design aided decision method and device based on knowledge graph

Abstract

The application provides a kind of intersection traffic organization design auxiliary decision method and equipment based on knowledge graph.The method comprises steps 1 to step 5.The application combines the characteristics of intersection traffic organization design knowledge, takes knowledge graph as knowledge carrier, combines the business logic of intersection traffic organization design, and proposes an intersection traffic organization design auxiliary decision method based on intersection traffic organization design field knowledge graph, which can improve the efficiency of intersection traffic organization design and improve the quality of intersection traffic organization design decision.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of road traffic engineering technology, and in particular to a knowledge graph-based auxiliary decision-making method and device for intersection traffic organization design. Background Technology

[0002] Engineering design is increasingly recognized as a decision-making process, and intersection traffic organization design is no exception. Providing relevant decision support for designers is crucial for accelerating the design process and generating high-quality design solutions. However, intersection traffic organization design involves a vast amount of knowledge, covering a wide range of topics and employing complex methodologies. Traditional data organization and management methods struggle to meet the demand for querying the massive amounts of knowledge within intersection design documents. Meanwhile, the demand for intersection design is increasing dramatically year by year, and some high-value intersection design examples and related experiences cannot be fully utilized due to a lack of reasonable and effective information storage and management methods. Furthermore, traditional urban road intersection traffic organization design methods rely primarily on manual design, resulting in long design cycles and high requirements for the professional knowledge and personal design experience of traffic organization design personnel, leading to inconsistent design results. Therefore, developing a knowledge graph-based auxiliary decision-making method and device for intersection traffic organization design, which can effectively overcome the shortcomings of the aforementioned technologies, has become a pressing technical problem for the industry. Summary of the Invention

[0003] To address the aforementioned problems in existing technologies, embodiments of the present invention provide a knowledge graph-based auxiliary decision-making method and device for intersection traffic organization design.

[0004] In a first aspect, embodiments of the present invention provide a knowledge graph-based auxiliary decision-making method for intersection traffic organization design, comprising: Step 1, inputting the current status of intersection traffic organization design into the system; Step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, and relying on the knowledge graph in the intersection traffic organization design domain, using knowledge reasoning methods to analyze optimization measures and generate preliminary design schemes; Step 3, conducting preliminary evaluation of the generated relevant schemes, and sending the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary generated schemes, completing iterative fine-tuning and optimization of the schemes; Step 4, outputting the optimized schemes to the user through the output module; Step 5, updating the knowledge in the knowledge graph.

[0005] Based on the above method embodiments, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention uses the current status of intersection traffic organization design as input in step 1. This input includes the parameters of relevant design elements and the traffic problems existing in the relevant elements, providing a data foundation for subsequent auxiliary decision-making.

[0006] Based on the above method embodiments, the intersection traffic organization design auxiliary decision-making method based on knowledge graphs provided in this embodiment of the invention, in step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, specifically includes: Step 2.1: Combining conventional solutions to relevant traffic problems and design experience and specifications in the knowledge graph, a deep learning framework is used to train the auxiliary decision-making model, and then the current status of intersection traffic organization design input in step 1 is mapped to the decision model for knowledge reasoning to complete the analysis of optimization design measures; Step 2.2: The generated decision results are organized to generate a preliminary intersection traffic organization optimization design scheme; The intersection traffic organization optimization design scheme includes: transforming the intersection traffic organization design-related knowledge contained in the knowledge graph into low-dimensional feature vectors and embedding them into the deep learning model for training to obtain optimization measures and traffic problems and other design elements. A relational model of elements is constructed; the current intersection traffic organization design problem and related elements are input into the relational model, and optimization measures are derived through analysis, thereby providing auxiliary decision-making for optimization design; the knowledge graph of the intersection traffic organization design domain includes intersection traffic organization design cases, relevant national standards and specifications for intersection traffic organization design, and intersection traffic organization design knowledge in literature on intersection traffic organization design, forming a knowledge graph of the intersection traffic organization design domain; the construction of the knowledge graph of the intersection traffic organization design domain includes: analyzing the conceptual and structural levels of intersection traffic organization design knowledge, completing the construction of the pattern layer of intersection traffic organization design domain knowledge; preprocessing the collected design document data; extracting specific entities and relationships contained in the intersection traffic organization design domain according to the entity and relation types defined in the pattern layer, and storing the extracted knowledge in the form of a graph database, thereby completing the construction of the knowledge graph.

[0007] Based on the above method embodiments, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention includes the following human-computer interaction process in step 3: sending the preliminary evaluation scheme to the human-computer interaction module, comparing and judging the scheme, determining whether there is a scheme that can be directly output, and if there is no scheme that can be directly accepted and output, the designer selects the best scheme from the existing preliminary schemes, fine-tunes the design elements involved in the shortcomings of the scheme, and re-enters it into the system to iteratively optimize the scheme until the scheme meets the output requirements.

[0008] Based on the above method embodiments, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention completes the final decision-making process by outputting the final decision scheme in step 4.

[0009] Based on the above method embodiments, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention includes, in step 5, updating the knowledge graph: treating the experience generated during the auxiliary decision-making process, including scheme fine-tuning, and the generated schemes as entirely new design knowledge, converting and storing them in the knowledge graph, thus completing the knowledge graph update. The knowledge graph update improves the scientificity and accuracy of the auxiliary decision-making model.

[0010] Secondly, embodiments of the present invention provide a knowledge graph-based auxiliary decision-making system for intersection traffic organization design, comprising: a knowledge graph in the field of intersection traffic organization design, used to organize and structure intersection traffic organization design knowledge from intersection traffic organization design cases, relevant national standards and specifications for intersection traffic organization design, and literature on intersection traffic organization design, forming a knowledge base in the form of a graph structure; and an auxiliary decision-making method module for intersection traffic organization design, used to combine business logic, address the shortcomings of current intersection traffic organization design, and rely on an auxiliary decision-making model trained on data provided by the knowledge graph to perform knowledge... The system reasoning process proposes targeted improvement solutions to complete the auxiliary decision-making for intersection traffic organization design. The intersection traffic organization design human-computer interaction module meets the system's human-computer interaction functional requirements during the auxiliary decision-making process. This interaction involves designers comparing, evaluating, and fine-tuning preliminary solutions, and iteratively optimizing the solutions in conjunction with the system. The intersection traffic organization design optimization solution output module outputs the optimized solution to the user, completing the entire process of auxiliary decision-making for intersection traffic organization design. The central processing module implements the knowledge graph-based auxiliary decision-making method for intersection traffic organization design as described in any of the aforementioned method embodiments.

[0011] Thirdly, embodiments of the present invention provide a knowledge graph-based auxiliary decision-making device for intersection traffic organization design, comprising: a first main module for implementing step 1, inputting the current status of intersection traffic organization design into the system; a second main module for implementing step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, and relying on the knowledge graph in the intersection traffic organization design field, using knowledge reasoning methods to analyze optimization measures and generate preliminary design schemes; a third main module for implementing step 3, performing preliminary evaluation of the generated relevant schemes, and sending the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary generated schemes, completing iterative fine-tuning and optimization of the schemes; a fourth main module for implementing step 4, outputting the optimized schemes to the user through the output module; and a fifth main module for implementing step 5, updating the knowledge graph.

[0012] Fourthly, embodiments of the present invention provide an electronic device, comprising:

[0013] At least one processor; and

[0014] At least one memory communicatively connected to the processor, wherein:

[0015] The memory stores program instructions that can be executed by the processor. The processor can call the program instructions to execute the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided by any of the various implementation methods of the first aspect.

[0016] Fifthly, embodiments of the present invention provide a non-transitory computer-readable storage medium storing computer instructions that cause a computer to execute a knowledge graph-based intersection traffic organization design auxiliary decision-making method provided by any of the various implementations of the first aspect.

[0017] The knowledge graph-based auxiliary decision-making method and device for intersection traffic organization design provided in this invention combines the characteristics of intersection traffic organization design knowledge, uses knowledge graphs as the knowledge carrier, and integrates the business logic of intersection traffic organization design to propose an auxiliary decision-making method for intersection traffic organization design based on knowledge graphs in the field of intersection traffic organization design. This method can improve the efficiency of intersection traffic organization design and enhance the quality of intersection traffic organization design decisions. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of a knowledge graph-based auxiliary decision-making method for intersection traffic organization design is provided in an embodiment of the present invention.

[0020] Figure 2 A schematic diagram of the structure of a knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the structure of a knowledge graph-based intersection traffic organization design auxiliary decision-making system provided in an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of another knowledge graph-based intersection traffic organization design auxiliary decision-making system provided in an embodiment of the present invention;

[0024] Figure 6 A schematic diagram of the workflow of a knowledge graph-based intersection traffic organization design auxiliary decision-making system provided in an embodiment of the present invention;

[0025] Figure 7 A schematic diagram of a knowledge graph in the field of intersection traffic organization design provided for an embodiment of the present invention;

[0026] Figure 8 This is a schematic diagram of the training of the auxiliary decision-making model provided in an embodiment of the present invention;

[0027] Figure 9 A schematic diagram of the preliminary evaluation method system provided in the embodiments of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. In addition, the technical features of the various embodiments or individual embodiments provided by the present invention can be arbitrarily combined with each other to form feasible technical solutions. Such combinations are not constrained by the order of steps and / or structural composition patterns, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0029] The main challenge at present is that knowledge embedded in text documents is difficult to directly utilize in the intersection traffic organization design process, thus failing to support timely decision-making. To address this challenge, a knowledge graph-based method is proposed to integrate organization-related design knowledge into intersection traffic organization design and establish an auxiliary decision-making method for intersection traffic organization design, thereby reducing the workload of intersection traffic organization design and improving work efficiency. Based on this idea, this invention provides a knowledge graph-based auxiliary decision-making method for intersection traffic organization design, see [link to relevant documentation]. Figure 1 The method includes: Step 1, inputting the current status of intersection traffic organization design into the system; Step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, and relying on the knowledge graph of the intersection traffic organization design domain, using knowledge reasoning methods to analyze optimization measures and generate preliminary design schemes; Step 3, conducting preliminary evaluation of the generated schemes, and sending the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary generated schemes, completing iterative fine-tuning and optimization of the schemes; Step 4, outputting the optimized schemes to the user through the output module; Step 5, updating the knowledge graph.

[0030] Based on the above method embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention uses the current status of intersection traffic organization design in step 1 as input to take the parameters of relevant design elements and the traffic problems existing in the relevant elements as system input, so as to provide a data basis for completing subsequent auxiliary decision-making.

[0031] Based on the above method embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention, in step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, specifically includes: Step 2.1: Combining conventional solutions and design experience and specifications for related traffic problems in the knowledge graph, using a deep learning framework to train the auxiliary decision-making model, and then mapping the current status of intersection traffic organization design input in step 1 to the decision model for knowledge reasoning to complete the analysis of optimization design measures; Step 2.2: Organizing the generated decision results to generate a preliminary intersection traffic organization optimization design scheme; The intersection traffic organization optimization design scheme includes: transforming the intersection traffic organization design-related knowledge contained in the knowledge graph into low-dimensional feature vectors and embedding them into the deep learning model for training, so as to obtain the optimization measures and traffic problems and their He designed a relationship model between elements; inputting the current intersection traffic organization design problem and related elements into the relationship model, analyzing and deriving optimization measures, thereby providing auxiliary decision-making for optimization design; the knowledge graph of the intersection traffic organization design domain includes intersection traffic organization design cases, relevant national standards and specifications for intersection traffic organization design, and intersection traffic organization design knowledge in intersection traffic organization design literature, forming a knowledge graph of the intersection traffic organization design domain; the construction of the knowledge graph of the intersection traffic organization design domain includes: analyzing the conceptual and structural levels of intersection traffic organization design knowledge, completing the construction of the pattern layer of intersection traffic organization design domain knowledge; preprocessing the collected design document data; extracting the specific entities and relationships contained in the intersection traffic organization design domain according to the entity and relationship types defined in the pattern layer, and storing the extracted knowledge in the form of a graph database, thereby completing the construction of the knowledge graph.

[0032] Based on the above method embodiments, as an optional embodiment, the human-computer interaction process in step 3 of the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention specifically includes: sending the preliminary evaluation scheme to the human-computer interaction module, comparing and judging the scheme, judging whether there is a scheme that can be directly output, if there is no scheme that can be directly accepted and output, the designer selects the best scheme among the existing preliminary schemes, and fine-tunes the design elements involved in the shortcomings of the scheme, and re-enters it into the system to iteratively optimize the scheme until the scheme meets the output requirements.

[0033] Based on the above method embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention completes the final decision scheme output in step 4, thereby completing the entire decision-making process.

[0034] Based on the above method embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making method provided in this embodiment of the invention includes, in step 5, updating the knowledge graph: treating the experience generated during the auxiliary decision-making process, including scheme fine-tuning, and the generated schemes as entirely new design knowledge, converting and storing them in the knowledge graph, thereby completing the knowledge graph update. The knowledge graph update improves the scientificity and accuracy of the auxiliary decision-making model.

[0035] The knowledge graph-based auxiliary decision-making method for intersection traffic organization design provided in this invention combines the characteristics of intersection traffic organization design knowledge, uses knowledge graphs as the knowledge carrier, and integrates the business logic of intersection traffic organization design to propose an auxiliary decision-making method for intersection traffic organization design based on knowledge graphs in the field of intersection traffic organization design. This method can improve the efficiency of intersection traffic organization design and enhance the quality of intersection traffic organization design decisions.

[0036] This invention provides a knowledge graph-based auxiliary decision-making system for intersection traffic organization design. (See also...) Figure 4 The system includes: a knowledge graph for intersection traffic organization design, used to organize and structure intersection traffic organization design knowledge from cases, relevant national standards and specifications, and literature, forming a knowledge base in graph form; an intersection traffic organization design auxiliary decision-making method module, used to combine business logic, address the shortcomings of current intersection traffic organization design, and, based on the auxiliary decision-making model trained by the knowledge graph, perform knowledge reasoning to propose targeted improvement solutions, thus completing the intersection traffic organization design auxiliary decision-making; an intersection traffic organization design human-computer interaction module, used to meet the system's human-computer interaction functional requirements during the auxiliary decision-making process, whereby designers compare, evaluate, and fine-tune the initially formed solutions, and iteratively optimize the solutions in conjunction with the system; an intersection traffic organization design optimization solution output module, used to output the optimized solution to the user, completing the entire process of intersection traffic organization design auxiliary decision-making; and a central processing module, used to implement the knowledge graph-based intersection traffic organization design auxiliary decision-making method as described in any of the aforementioned method embodiments.

[0037] In another embodiment, a knowledge graph-based auxiliary decision-making system for intersection traffic organization design is disclosed. Starting from the design service requirements in the field of intersection traffic organization design, the system uses a knowledge graph to structure design knowledge, discovers the connections between knowledge, and then combines the business logic of design to construct an optimized design auxiliary decision-making method.

[0038] See Figure 5 The system described in this example includes five core modules: 1. Input module for current status of intersection traffic organization; 2. Knowledge graph for intersection traffic organization design; 3. Decision-making support method module for intersection traffic organization design; 4. Human-computer interaction module for intersection traffic organization design; and 5. Output module for optimized intersection traffic organization scheme.

[0039] See Figure 6 The workflow of the system proposed in this example is as follows: First, the current status of intersection traffic organization design is input into the system. The input includes, but is not limited to, the attribute parameters of intersection traffic organization design elements such as lanes and signs / markings, as well as the representation and causes of current intersection traffic organization design problems. Then, the input is converted into a vector representation and mapped to the intersection traffic organization design auxiliary decision-making method module. Based on the optimization design auxiliary decision-making model trained by the knowledge graph of the intersection traffic organization design domain, optimization measures are predicted, and preliminary design schemes are generated. Next, the generated relevant schemes are initially evaluated, and the schemes that pass the evaluation are sent to the human-computer interaction module, where designers compare and evaluate the initially generated schemes and iteratively optimize the schemes in conjunction with the system. Finally, the optimized scheme is output to the user, and the knowledge graph is updated.

[0040] See Figure 7 The knowledge graph described in this example uses a graph database to extract knowledge from design materials, form knowledge triples, and transform them into a knowledge graph. Figure 7 The aforementioned knowledge graph for intersection traffic organization design mainly includes the following definitions:

[0041] ① Design Element Concept / Class: A collection or general term for a type of element in the field of intersection traffic organization design. A category may include many specific instances. In this invention, intersection traffic organization design elements are divided into: channelization, traffic control measures, traffic management measures, traffic data, traffic problems, and evaluation methods.

[0042] ② Entity: An instance of a "class", such as the entity "left turn lane" under the "channelization" class;

[0043] ③ Attributes: Quantities that describe the characteristics of "classes" and "entities", such as "quantity" being an attribute of "left turn lanes";

[0044] ④ Attribute value: A numerical value or a quantity of a numerical type that describes the "attribute";

[0045] ⑤ Relationships: Quantities that describe the connections between "classes" and "entities", "classes" and "classes", "entities" and "attributes", "attributes" and "entities". For example, the relationship between "left-turn lane" and "channelization class" is "belongs to". The relationship between the channelization class entity "left-turn lane" with a "quantity" attribute value of "1" and the traffic problem class entity "insufficient left-turn capacity" is "leads to".

[0046] Figure 7 This example illustrates a knowledge graph of the traffic organization design domain for some intersections. The graph shows the following: entities such as "left-turn lane", "U-turn lane", "traffic flow", "traffic problems", and "operation status"; the attributes of each entity, such as the attributes of "left-turn lane" entity such as "state", "intersection", "entrance", "lane location", and "lane length"; and the relationships between entities, such as the relationship between "left-turn lane, traffic flow" and "traffic problems" being "caused by", and the relationship between "operation status: state: before optimization" and "operation status: state: after optimization" being "optimization".

[0047] The intersection traffic organization design auxiliary decision-making method module in the system mainly combines business logic, addresses the shortcomings of the current intersection traffic organization design, and relies on an auxiliary decision-making model trained on data provided by a knowledge graph to perform knowledge reasoning and propose targeted improvement solutions, thereby completing the auxiliary decision-making for intersection traffic organization design; see also Figure 8 This example demonstrates an embedding of a knowledge graph and the training of an auxiliary decision-making model. First, the knowledge contained in the knowledge graph of intersection traffic organization design is vectorized to complete the embedding of the knowledge graph. As shown in the figure, a set of design knowledge in the knowledge graph is transformed into a 4-dimensional feature vector, which is then used as a training data for the auxiliary decision-making model. Second, in the model training part, a deep learning framework based on Bi-LSTM+Self-attention is shown in the figure. This framework combines the characteristics of Bi-LSTM, which can determine whether relevant information is effective, and Self-attention, which can highlight the importance of relevant factors of the solution, thereby improving the accuracy of the model in predicting solutions to intersection traffic organization problems.

[0048] See Figure 6This example demonstrates the iterative optimization process of the human-computer interaction process. First, the designer compares and judges the solutions to determine if there is a solution that can be directly output. If there is no acceptable solution that can be directly output, the designer selects the best solution and fine-tunes the design element attributes and parameters involved in the shortcomings of the solution, such as the length, width, and location of the lane. This data is then used as new input to the model for re-prediction, thereby completing the fine-tuning of the solution until the solution is iterated to meet the output requirements.

[0049] See Figure 6 The knowledge graph update described in this example is not limited to storing the solutions generated during the iterative optimization process as new knowledge in the knowledge graph. It can also treat the experience and logic generated during the decision support process, including solution fine-tuning, as entirely new design knowledge, transform it, and store it in the knowledge graph, thereby completing the knowledge graph update. The knowledge graph update also continuously improves the accuracy of the decision support model.

[0050] See Figure 6 and Figure 9 The aforementioned method for generating preliminary evaluation of design schemes is a multi-module comprehensive evaluation method. It can output corresponding evaluation results based on the user's design requirements and priorities, or it can output a comprehensive evaluation result. The evaluation method module mainly includes a safety evaluation module and an efficiency evaluation module. The traffic indicators related to efficiency include:

[0051]

[0052] In the formula: The average vehicle delay is denoted by ti; the actual time it takes for sample vehicle i to pass through the intersection is t. j denoted as , where is the time it takes for vehicles to pass through the intersection in free-flow mode; denoted as n, where n is the effective sample size within the evaluation period.

[0053]

[0054] In the formula: W s w represents the average number of stops. ij G represents the number of stops in the valid sample; ij This represents the number of valid samples.

[0055]

[0056] In the formula: L i Let n be the average queue length of entrance lane i during the evaluation period; n be the number of entrance lanes at the intersection.

[0057] Traffic safety indicators include:

[0058]

[0059] In the formula: P c p represents the phase clearing rate. t (i) represents the number of phases that are cleared in the i-th cycle; p T (i) represents the total number of signal phases in the i-th cycle; n represents the number of cycles within the evaluation period, where n is greater than or equal to 10.

[0060]

[0061] In the formula, R 机-机 Let T be the traffic conflict rate between motor vehicles, T be the number of traffic conflicts between motor vehicles at the intersection per hour, and P be the equivalent traffic volume of motor vehicles.

[0062] The implementation of the various embodiments of this invention is based on programmed processing through a device with processor functionality. Therefore, in practical engineering, the technical solutions and functions of the various embodiments of this invention can be encapsulated into various modules. Based on this reality, and building upon the above embodiments, this invention provides a knowledge graph-based intersection traffic organization design auxiliary decision-making device, which executes the knowledge graph-based intersection traffic organization design auxiliary decision-making method in the above method embodiments. See also... Figure 2 The device includes: a first main module for implementing step 1, inputting the current status of intersection traffic organization design into the system; a second main module for implementing step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, and using knowledge reasoning methods based on the intersection traffic organization design domain knowledge graph to analyze optimization measures and generate preliminary design schemes; a third main module for implementing step 3, conducting preliminary evaluation of the generated schemes, and sending the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary generated schemes, completing iterative fine-tuning and optimization; a fourth main module for implementing step 4, outputting the optimized schemes to the user through the output module; and a fifth main module for implementing step 5, updating the knowledge graph.

[0063] The knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in this embodiment of the invention adopts... Figure 2 Based on several modules in the field of intersection traffic organization design, and taking into account the characteristics of intersection traffic organization design knowledge, this paper proposes an auxiliary decision-making method for intersection traffic organization design based on the knowledge graph of the intersection traffic organization design field. This method can improve the efficiency of intersection traffic organization design and enhance the quality of intersection traffic organization design decisions.

[0064] It should be noted that the apparatus in the device embodiments provided by the present invention can be used not only to implement the methods in the above method embodiments, but also to implement the methods in other method embodiments provided by the present invention. The difference lies only in the setting of corresponding functional modules. Its principle is basically the same as that of the above device embodiments provided by the present invention. As long as those skilled in the art, based on the above device embodiments and referring to the specific technical solutions in other method embodiments, obtain corresponding technical means and technical solutions composed of these technical means by combining technical features, and improve the apparatus in the above device embodiments while ensuring the practicality of the technical solutions, they can obtain corresponding device-type embodiments for implementing the methods in other method-type embodiments. For example:

[0065] Based on the above device embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in this embodiment of the invention further includes: a first sub-module, used to implement the input of the current status of intersection traffic organization design in step 1, and used to take the parameters of relevant design elements and the traffic problems existing in the relevant elements as system input, so as to provide a data basis for completing subsequent auxiliary decision-making.

[0066] Based on the above device embodiments, as an optional embodiment, the intersection traffic organization design auxiliary decision-making device based on knowledge graph provided in this embodiment of the invention further includes: a second sub-module, used to implement the mapping of input content to the intersection traffic organization design auxiliary decision-making method module in step 2, specifically including: step 2.1: combining conventional solutions and design experience and design specifications of relevant traffic problems in the knowledge graph, using a deep learning framework to train the auxiliary decision-making model, and then mapping the current status of intersection traffic organization design input in step 1 to the decision model for knowledge reasoning to complete the analysis of optimization design measures; step 2.2: organizing the generated decision results to generate a preliminary intersection traffic organization optimization design scheme; the intersection traffic organization optimization design scheme includes: converting the intersection traffic organization design-related knowledge contained in the knowledge graph into low-dimensional feature vectors and embedding them into the deep learning model for training to obtain optimization measures and A relationship model between traffic problems and other design elements is constructed. Current intersection traffic organization design problems and related elements are input into the relationship model, and optimization measures are derived to support decision-making for optimization design. The intersection traffic organization design domain knowledge graph includes intersection traffic organization design cases, relevant national standards and specifications for intersection traffic organization design, and intersection traffic organization design knowledge in literature. The construction of the intersection traffic organization design domain knowledge graph includes: analyzing the conceptual and structural levels of intersection traffic organization design knowledge to complete the construction of the schema layer of intersection traffic organization design domain knowledge; preprocessing the collected design documents; extracting specific entities and relationships contained in the intersection traffic organization design domain according to the entity and relationship types defined in the schema layer, and storing the extracted knowledge in the form of a graph database to complete the construction of the knowledge graph.

[0067] Based on the above device embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in this embodiment of the invention further includes: a third sub-module, used to implement the human-computer interaction process in step 3, specifically including: sending the schemes that have passed the preliminary evaluation to the human-computer interaction module, comparing and judging the schemes, judging whether there is a scheme that can be directly output, if there is no scheme that can be directly accepted and output, the designer selects the best scheme among the existing preliminary schemes, and fine-tunes the design elements involved in the shortcomings of the scheme, and re-enters it into the system to iteratively optimize the scheme until the scheme meets the output requirements.

[0068] Based on the above device embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in this embodiment of the invention further includes: a fourth sub-module, used to implement the output of the final decision scheme in step 4, thereby completing the entire decision-making process.

[0069] Based on the above device embodiments, as an optional embodiment, the knowledge graph-based intersection traffic organization design auxiliary decision-making device provided in this embodiment of the invention further includes: a fifth sub-module, used to implement the knowledge graph update in step 5, which includes: treating the experience generated during the auxiliary decision-making process, including scheme fine-tuning, and the generated schemes as new design knowledge, converting and storing them in the knowledge graph, and completing the knowledge graph update. The knowledge graph update improves the scientificity and accuracy of the auxiliary decision-making model.

[0070] The method in this embodiment of the invention is implemented using an electronic device; therefore, it is necessary to introduce the relevant electronic device. For this purpose, this embodiment of the invention provides an electronic device, such as... Figure 3 As shown, the electronic device includes at least one processor, a communications interface, at least one memory, and a communications bus, wherein the at least one processor, the communications interface, and the at least one memory communicate with each other via the communications bus. The at least one processor can invoke logical instructions stored in the at least one memory to execute all or part of the steps of the methods provided in the foregoing method embodiments.

[0071] Furthermore, when the logical instructions in at least one of the aforementioned memories can be implemented as software functional units 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 the present invention, in essence, or the part that contributes to the prior art, or a part 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 personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various method embodiments of the present 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.

[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Based on this understanding, 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 in some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or sometimes in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, 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.

[0075] It should be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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; and these 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.

Claims

1. A knowledge graph-based auxiliary decision-making method for intersection traffic organization design, characterized in that, include: Step 1: Input the current traffic organization design of the intersection into the system; Step 2: Map the input content to the intersection traffic organization design auxiliary decision-making method module, and rely on the knowledge graph of the intersection traffic organization design domain to analyze optimization measures using knowledge reasoning methods to generate a preliminary design scheme; Step 3: Conduct a preliminary evaluation of the generated schemes, and send the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary schemes, completing iterative fine-tuning and optimization; Step 4: Output the optimized scheme to the user through the output module; Step 5: Update the knowledge graph; Step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, specifically includes: Step 2.1: Combining conventional solutions and design experience / standard knowledge of relevant traffic problems in the knowledge graph, a deep learning framework is used to train the auxiliary decision-making model. Then, the current status of intersection traffic organization design input in Step 1 is mapped to the decision model for knowledge reasoning to complete the analysis of optimization design measures; Step 2.2: The generated decision results are organized to generate a preliminary intersection traffic organization optimization design scheme; The intersection traffic organization optimization design scheme includes: transforming the intersection traffic organization design-related knowledge contained in the knowledge graph into low-dimensional feature vectors and embedding them into the deep learning model for training to obtain a relationship model between optimization measures and traffic problems and other design elements; and transforming the current intersection traffic organization design problem and... Relevant elements are input into the relational model, and optimization measures are derived through analysis, thereby providing auxiliary decision-making for optimization design. The knowledge graph of the intersection traffic organization design domain includes intersection traffic organization design cases, relevant national standards and specifications for intersection traffic organization design, and intersection traffic organization design knowledge in literature on intersection traffic organization design. The construction of the knowledge graph of the intersection traffic organization design domain includes: analyzing the conceptual and structural levels of intersection traffic organization design knowledge, and completing the construction of the schema layer of intersection traffic organization design domain knowledge; preprocessing the collected design documents; extracting specific entities and relationships contained in the intersection traffic organization design domain according to the entity and relation types defined in the schema layer, and storing the extracted knowledge in the form of a graph database, thereby completing the construction of the knowledge graph. The human-computer interaction process in step 3 specifically includes: sending the solutions that have passed the preliminary evaluation to the human-computer interaction module, comparing and judging the solutions, determining whether there are any solutions that can be directly output, and if there are no solutions that can be directly accepted and output, the designers select the best solution from the existing preliminary solutions, fine-tune the design elements involved in the shortcomings of the solution, and re-enter the solution into the system for iterative optimization until the solution meets the output requirements.

2. The knowledge graph-based intersection traffic organization design auxiliary decision-making method according to claim 1, characterized in that, The input of the current status of intersection traffic organization design in step 1 is used to take the parameters of relevant design elements and the traffic problems existing in the relevant elements as system input, and provide a data basis for completing subsequent auxiliary decision-making.

3. The knowledge graph-based intersection traffic organization design auxiliary decision-making method according to claim 1, characterized in that, Step 4 completes the output of the final decision-making scheme, thus completing the entire decision-making process.

4. The knowledge graph-based intersection traffic organization design auxiliary decision-making method according to claim 3, characterized in that, Step 5, updating the knowledge graph, includes treating the experience generated during the decision support process, including scheme fine-tuning, and the generated schemes as entirely new design knowledge, transforming and storing them in the knowledge graph, thus completing the knowledge graph update. The knowledge graph update improves the scientificity and accuracy of the decision support model.

5. A knowledge graph-based auxiliary decision-making system for intersection traffic organization design, characterized in that, include: The intersection traffic organization design knowledge graph is used to organize and structure intersection traffic organization design knowledge, including intersection traffic organization design cases, relevant national standards and specifications, and literature, forming a knowledge base represented by a graph structure. The intersection traffic organization design auxiliary decision-making method module, combined with business logic, addresses the shortcomings of current intersection traffic organization designs by using an auxiliary decision-making model trained on data provided by the knowledge graph to perform knowledge reasoning, propose targeted improvement solutions, and complete the intersection traffic organization design auxiliary decision-making. The intersection traffic organization design human-computer interaction module meets the system's human-computer interaction functional requirements during the auxiliary decision-making process. The human-computer interaction includes: designers comparing, evaluating, and fine-tuning preliminary solutions, and iteratively optimizing the solutions in conjunction with the system. The intersection traffic organization design optimization scheme output module is used to output the optimized scheme to the user, completing the entire process of intersection traffic organization design auxiliary decision-making; the central processing module is used to implement the knowledge graph-based intersection traffic organization design auxiliary decision-making method as described in any one of claims 1 to 4.

6. A knowledge graph-based auxiliary decision-making device for intersection traffic organization design, characterized in that, include: The first main module is used to implement step 1, inputting the current traffic organization design of the intersection into the system; The second main module is used to implement step 2, mapping the input content to the intersection traffic organization design auxiliary decision-making method module, and using knowledge reasoning methods based on the knowledge graph of the intersection traffic organization design domain to analyze optimization measures and generate preliminary design schemes. The third main module is used to implement step 3, conducting preliminary evaluation of the generated relevant schemes, and sending the evaluated schemes to the intersection traffic organization design human-computer interaction module, where designers compare and evaluate the preliminary generated schemes, and complete iterative fine-tuning and optimization of the schemes. The fourth main module is used to implement step 4, outputting the optimized schemes to the user through the output module. The fifth main module is used to implement step 5, updating the knowledge graph. The knowledge graph-based intersection traffic organization design auxiliary decision-making device is used to execute the steps in the knowledge graph-based intersection traffic organization design auxiliary decision-making method according to any one of claims 1 to 4.

7. An electronic device, characterized in that, include: At least one processor, at least one memory, and a communication interface; wherein, The processor, memory, and communication interface communicate with each other; The memory stores program instructions that can be executed by the processor, which invokes the program instructions to perform the method described in any one of claims 1 to 4.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method described in any one of claims 1 to 4.

Images