CN114880416A - Road network map processing method, device, computer equipment and storage medium - Google Patents

Abstract

The present application relates to a road network map processing method, device, computer equipment and storage medium. The method includes: acquiring a two-dimensional road network map; extracting plane features of each road section unit in the two-dimensional road network map; predicting the elevation of each road section unit according to the extracted plane features of each road section unit and a pre-trained road elevation model data; wherein, the road elevation model is a model used to represent the relationship between the plane features of the road segment unit and the elevation data; the two-dimensional road network map is converted into a three-dimensional road network map according to the predicted elevation data. The method can improve the three-dimensional visualization efficiency of the elevation status of each road in the road network map.

Description

Road network map processing method, device, computer equipment and storage medium

technical field

The present application relates to the field of computer technology, and in particular, to a road network map processing method, device, computer equipment and storage medium.

Background technique

With the development of computer technology, intelligent driving has been applied in different business scenarios. However, various road conditions emerge in an endless stream, so a more intuitive and visualized 3D road network map is required.

However, the road information is complex and interlaced, and it is difficult to accurately collect the elevation data of each road in the road network (including viaducts, overpasses, etc.) The situation is displayed in a 3D visualization.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a road network map processing method, device, computer equipment and storage medium that can improve the three-dimensional visualization efficiency of the elevation conditions of each road in the road network map in view of the above technical problems.

A road network map processing method, comprising:

Obtain a 2D road network map;

Extract the plane feature of each road section unit in the two-dimensional road network map;

According to the extracted plane features of each road segment unit and the pre-trained road elevation model, the elevation data of each road segment unit is predicted; wherein, the road elevation model is a model used to characterize the relationship between the plane feature of the road segment unit and the elevation data;

The two-dimensional road network map is converted into a three-dimensional road network map according to the predicted elevation data.

In one embodiment, the training method of the road elevation model includes:

Obtain a sample 2D road network map;

Extracting plane features for each sample road segment unit in the sample two-dimensional road network map;

Obtain the actual road condition data corresponding to the sample two-dimensional road network map;

The road elevation model is trained according to the plane features of each sample road segment unit and the actual road condition data.

In one embodiment, the road elevation model is trained according to the plane features of each sample road segment unit and actual road condition data, including:

Generate the current elevation data of each sample road segment unit according to the preset elevation value range;

Scoring each current elevation data based on actual road condition data;

The road elevation model is trained based on the scores of each current elevation data.

In one embodiment, the road elevation model is trained according to the scores of each current elevation data, including:

Associating each sample road segment unit with a score greater than a preset threshold with its current elevation data;

Adjust the current elevation data of each sample road segment unit whose score is less than the preset threshold, and use the adjusted data as the current elevation data, and enter the step of scoring each current elevation data according to the actual road condition data.

In one embodiment, the actual road condition data includes at least one of lamination relationship data between sample road segment units and gradient data of each sample road segment unit.

In one embodiment, the predicted elevation data includes at least one of elevation values for road segment units, elevation range values for road segment units, relative elevation values between road segment units, and relative elevation range values between road segment units.

In one embodiment, the method further includes:

Display the 3D road network map on the display interface;

In response to the adjustment operation on the elevation data of the specified road segment unit in the three-dimensional road network map, the adjusted elevation data is returned to the road elevation model for model optimization.

A road network map processing device comprising:

A two-dimensional map acquisition module for acquiring a two-dimensional road network map;

The plane feature extraction module is used to extract plane features for each road section unit in the two-dimensional road network map;

The elevation data prediction module is used to predict the elevation data of each road segment unit according to the extracted plane features of each road segment unit and the pre-trained road elevation model; wherein, the road elevation model is used to characterize the plane feature of the road segment unit and the elevation data. A model of the relationship between the

The three-dimensional map generation module is used to convert the two-dimensional road network map into a three-dimensional road network map according to the predicted elevation data.

A computer device includes a memory, a processor and a computer program stored in the memory and running on the processor, the processor implements the steps of the above-mentioned road network map processing method when the processor executes the computer program.

A computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, implements the steps of the above-mentioned road network map processing method.

The above-mentioned road network map processing method, device, computer equipment and storage medium, through the feature extraction of the data of the two-dimensional road network map, and based on the pre-trained road elevation model to obtain the elevation corresponding to each road section unit in the two-dimensional road network map The two-dimensional road network map is converted into a three-dimensional visualization map according to the obtained elevation data, so that the three-dimensional visualization efficiency of the elevation status of each road in the two-dimensional plane road network map can be improved.

Description of drawings

1 is a schematic flowchart of a method for processing a road network map in one embodiment;

2 is a schematic flowchart of steps of training a road elevation model in one embodiment;

Fig. 3 is a structural block diagram of a road network map processing apparatus in one embodiment;

Fig. 4 is the structural block diagram of the elevation model training module in an application example;

FIG. 5 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

In one embodiment, the road network map processing method provided in this application can be applied to a terminal. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, vehicle-mounted terminals, terminal servers, portable wearable devices, and the like. Specifically, the terminal obtains a two-dimensional road network map; extracts plane features of each road section unit in the two-dimensional road network map; predicts the elevation data of each road section unit according to the extracted plane features of each road section unit and the pre-trained road elevation model ; wherein, the road elevation model is a model used to characterize the relationship between the plane features of the road segment unit and the elevation data; the two-dimensional road network map is converted into a three-dimensional road network map according to the predicted elevation data.

In one embodiment, as shown in FIG. 1 , a method for processing a road network map is provided, which is described by taking the method applied to a terminal as an example, including the following steps:

Step S102: Obtain a two-dimensional road network map.

The two-dimensional road network map refers to a map including two-dimensional plane road network data. A road network refers to a road network composed of multiple roads interlaced. A road may be divided into at least one road segment unit, and the two-dimensional road network map may include two-dimensional data of at least one road segment unit of the at least one road. The roads here include but are not limited to urban roads, expressways, auxiliary roads, viaducts, overpasses, and the like.

Specifically, the terminal may acquire the two-dimensional road network map data corresponding to the road network within the specified range in real time or periodically.

Step S104 : extracting plane features for each road section unit in the two-dimensional road network map.

Among them, the plane feature refers to the two-dimensional plane data identified from the two-dimensional road network map data, that is, the two-dimensional feature data that can characterize the attributes of each road section unit, for example, may include the lamination relationship data between each road section unit. , the inclination data of each road section unit, the start position and end position data of each road section unit, etc.

Specifically, according to the acquired two-dimensional road network map, the terminal uses each road section unit in the two-dimensional road network map as a feature extraction unit, and performs feature extraction based on the two-dimensional plane data of each road section unit respectively, and obtains the plane corresponding to each road section unit. feature.

Step S106: Predict the elevation data of each road segment unit according to the extracted plane features of each road segment unit and the pre-trained road elevation model; wherein, the road elevation model is used to characterize the relationship between the plane feature of the road segment unit and the elevation data. Model.

The road elevation model refers to a pre-trained prediction model for outputting elevation data, and the road elevation model can represent the relationship between the plane features of each road segment unit in the two-dimensional road network map and the elevation data of each road segment unit. Elevation data refers to the data representing the distance from a certain road section unit to the target base along the vertical line direction.

Exemplarily, the elevation data may include at least one of an elevation value of each road segment unit, an elevation range value of each road segment unit, a relative elevation value between each road segment unit, and a relative elevation range value between each road segment unit.

Specifically, the terminal can call the pre-trained road elevation model from the memory or database, and use the extracted plane features of each road segment unit as the input parameters of the road elevation model, and obtain the output parameters predicted and output by the road elevation model, that is, , the elevation data corresponding to each road segment unit respectively.

Step S108: Convert the two-dimensional road network map into a three-dimensional road network map according to the predicted elevation data.

The three-dimensional road network map refers to a three-dimensional visualization map including three-dimensional spatial road network data. The three-dimensional road network map can present three-dimensionally the elevation status of each road segment unit of each road and the interval between them.

Specifically, after obtaining the elevation data of each road segment unit predicted and output based on the road elevation model, the terminal performs 3D modeling based on the 2D road network map data and the elevation data corresponding to each road segment unit, thereby obtaining a 3D spatial road network map.

The above-mentioned road network map processing method obtains the elevation data corresponding to each road segment unit in the two-dimensional road network map based on the feature extraction of the data of the two-dimensional road network map, and obtains the elevation data corresponding to each road section unit in the two-dimensional road network map based on the pre-trained road elevation model. Converting the two-dimensional road network map into a three-dimensional visualization map can improve the three-dimensional visualization efficiency of the elevation status of each road in the two-dimensional plane road network map. Especially for road conditions with an elevation concept, such as viaducts and overpasses, the height information can be displayed more realistically and clearly in the 3D map, providing more reliable, closer to the real, and more beautiful 3D visual road network data for intelligent driving.

In one embodiment, reference may be made to FIG. 2 , which shows a schematic flowchart of the steps of training a road elevation model in one embodiment. The training method of the road elevation model can include:

S1: Obtain a sample two-dimensional road network map.

S2: Extracting plane features for each sample road segment unit in the sample two-dimensional road network map.

S3: Obtain actual road condition data corresponding to the sample two-dimensional road network map.

S4: Train the road elevation model according to the plane features of each sample road segment unit and the actual road condition data.

In this embodiment, any one or more two-dimensional road network maps generated historically may be used as samples to train the road elevation model. The sample two-dimensional road network map includes two-dimensional data of at least one sample road segment unit of at least one road. The actual road condition data of the sample two-dimensional road network map refers to the actual measured real data of each road section unit in the road network corresponding to the sample two-dimensional road network map. Exemplarily, the actual road condition data may include lamination relationship data between each road segment unit, gradient data of each road segment unit, and the like.

Specifically, the terminal can select any one or more two-dimensional road network maps generated historically as training samples, and can retrieve the actual road condition data corresponding to the sample two-dimensional road network map by requesting a third-party application service, etc. The plane feature of each sample road segment unit is used as the model input variable, and the actual road condition data corresponding to each sample road segment unit is used as the model target variable, and the road elevation model is trained by means of machine learning.

In one embodiment, referring to FIG. 2 , the road elevation model is trained according to the plane features of each sample road segment unit and the actual road condition data, including:

S41: Generate current elevation data of each sample road segment unit according to a preset elevation value range.

S42: Scoring each current elevation data according to the actual road condition data.

S43: Train the road elevation model according to the scores of each current elevation data.

In this embodiment, the operator can set the upper limit value and the lower limit value of the elevation value range according to business requirements. Specifically, the terminal randomly generates at least one elevation value or an elevation range value within the preset elevation value range corresponding to each sample road segment unit as the current elevation data corresponding to the road segment unit, and the terminal generates according to the current elevation data of each sample road segment unit. Three-dimensional modeling is performed, and according to the actual road condition data corresponding to each sample road section unit, it is judged whether the currently built three-dimensional model conforms to the real road conditions, so as to score the current elevation data corresponding to each sample road section unit. The terminal can further adjust the elevation data according to the scoring results, so as to obtain a model capable of generating road elevation data that meets the requirements.

In one embodiment, the road elevation model is trained according to the scores of each current elevation data, including:

S431: Associate each sample road segment unit with a score greater than a preset threshold with its current elevation data.

S432: Adjust the current elevation data of each sample road segment unit whose score is less than the preset threshold, and use the adjusted data as the current elevation data, and enter the step of scoring each current elevation data according to the actual road condition data (S42).

In this embodiment, the current elevation data with a score greater than the preset threshold indicates that it is close to or conforms to the real road conditions, and the current elevation data with a score less than the preset threshold indicates that it does not conform to the real road conditions. Specifically, the terminal can filter out the sample road segment units whose scores are less than the preset threshold according to the current elevation data score, and adjust and optimize the selected sample road segment units by modifying the value of the elevation data or narrowing the range of the value of the elevation data. its corresponding elevation data. For a sample road segment unit with a score greater than a preset threshold, the current elevation data of the sample road segment unit can be directly retained, and the association between the current elevation data and the plane feature of the sample road segment unit is completed.

Through this embodiment, the sample road segment units that need to be adjusted can be dynamically screened according to the score of the elevation data, and the sample road segment units whose scores are greater than the preset threshold do not need to be repeatedly processed, thereby reducing the amount of data processing. Targeted training and adjustment for the unit.

Further, the current elevation data of each sample road segment unit whose score is less than the preset threshold is adjusted, and the adjusted elevation data is used again as the current elevation data to enter the scoring step. Through the continuous cycle of scoring, screening, and adjustment, the optimal road elevation model can be obtained when the elevation data of all sample road sections meet the expected requirements.

In one embodiment, the method further includes: displaying the three-dimensional road network map on the display interface; in response to the adjustment operation on the elevation data of the specified road segment unit in the three-dimensional road network map, returning the adjusted elevation data to the road elevation model for model optimization.

In this embodiment, the terminal can display the converted three-dimensional road network map through a display device such as a display screen, and supports data modification and fine-tuning interacted with the user. Afterwards, the adjusted data can be further fed back to the road elevation model as model optimization data, so as to realize model optimization.

It should be understood that although the steps in the flowcharts of FIGS. 1-2 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 1-2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times. These sub-steps or stages are not necessarily completed at the same time. The order of execution of the steps is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of sub-steps or stages of other steps.

In one embodiment, as shown in FIG. 3, a road network map processing device is provided, including: a two-dimensional map acquisition module 310, a plane feature extraction module 320, an elevation data prediction module 330, and a three-dimensional map generation module 340, wherein :

A two-dimensional map acquisition module 310, configured to acquire a two-dimensional road network map;

a plane feature extraction module 320, configured to perform plane feature extraction on each road segment unit in the two-dimensional road network map;

The elevation data prediction module 330 is used for predicting the elevation data of each of the road segment units according to the extracted plane features of each of the road segment units and the pre-trained road elevation model; wherein, the road elevation model is used to characterize the road segment unit. A model of the relationship between the plane features and the elevation data;

The three-dimensional map generation module 340 is configured to convert the two-dimensional road network map into a three-dimensional road network map according to each of the predicted elevation data.

In one embodiment, an elevation model training module 350 is further included, and the elevation model training module 350 is used to obtain a sample two-dimensional road network map; perform plane feature extraction on each sample road segment unit in the sample two-dimensional road network map; obtain a sample two-dimensional road network map The actual road condition data corresponding to the road network map; the road elevation model is trained according to the plane features of each sample road segment unit and the actual road condition data.

In one embodiment, the elevation model training module 350 generates current elevation data of each sample road segment unit according to a preset elevation value range; scores each current elevation data according to actual road condition data; The road elevation model is trained.

In one embodiment, the elevation model training module 350 associates each sample road segment unit with a score greater than a preset threshold with its current elevation data; adjusts the current elevation data of each sample road segment unit whose score is less than a preset threshold, and adjusts the adjusted As the current elevation data, enter the step of scoring each current elevation data according to the actual road condition data.

In one embodiment, the three-dimensional map generation module 340 is further configured to display the three-dimensional road network map on the display interface; in response to the adjustment operation on the elevation data of the specified road segment unit in the three-dimensional road network map, the adjusted elevation data Return the road elevation model for model optimization.

For the specific limitation of the road network map processing apparatus, please refer to the above limitation on the road network map processing method, which will not be repeated here. Each module in the above-mentioned road network map processing apparatus may be implemented in whole or in part by software, hardware and combinations thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

Hereinafter, the road network map processing method of the present application will be further described with reference to an application example. Referring to FIG. 4 , FIG. 4 shows a structural block diagram of an elevation model training module of an application example. The elevation model training module 350 may include a training component 3502 , an evaluation component 3504 and a loop adjustment component 3506 .

More specifically, the training module 350 based on the elevation model can implement the following steps:

Step 1: The training component 3502 obtains a sample two-dimensional road network map, the sample two-dimensional map includes a plurality of roads, and each road is divided into at least one sample road segment unit. The training component 3502 generates a three-dimensional road network map representing the three-dimensional elevation between road segments according to the plane features of each sample road segment unit according to each sample road segment unit in the sample two-dimensional road network map. , the elevation data of each sample road segment unit is randomly given within the preset elevation value range.

Step 2: The loop adjustment component 3506 inputs the elevation data of each sample road segment unit output by the training component 3502 into the evaluation component 3504 for scoring.

Step 3: The evaluation component 3504 evaluates the three-dimensional road network map according to the actual road condition data corresponding to the input two-dimensional road network map (for example, including the lamination relationship between each sample road segment unit, the gradient value of each sample road segment unit, etc.) The elevation data of each sample road segment unit in the

Step 4: The loop adjustment component 3506 feeds the scoring result back to the training component 3502. Wherein, the higher the elevation data score is, the closer the three-dimensional visualization of the sample road segment unit is to the real situation, and the training component 3502 retains its elevation data.

Step 5: The training component 3502 adjusts the parameters of the initially generated three-dimensional road network map according to the scoring result returned by the loop adjustment component 3506 . During adjustment, the elevation data of the sample road segment units whose scores are greater than the threshold are kept unchanged, and the elevation data of the sample road segment units whose scores do not reach the threshold are optimized or adjusted.

Step 6: Input the adjusted elevation data of the sample road segment unit into the evaluation component 3504 again for scoring. And so on, until the elevation data scores of all sample road segment units meet the preset requirements.

Step 7: According to the above steps 1 to 6, a trained road elevation model is obtained.

Step 8: The elevation data prediction module 330 uses the trained road elevation model to predict the elevation data of each road segment unit in any one or more target two-dimensional road network maps to be converted, and generates the target two-dimensional road map through the three-dimensional map generation module 340. The web map is converted into a 3D visual map.

In an embodiment, a computer device is also provided, the computer device may be a terminal, and the internal structure diagram thereof may be as shown in FIG. 5 . The computer equipment includes a processor, memory, a network interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for processing a road network map is realized. The display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment , or an external keyboard, trackpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 5 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the following steps are implemented: acquiring a two-dimensional road network map ; Perform plane feature extraction on each road section unit in the two-dimensional road network map; according to the extracted plane features of each road section unit and the pre-trained road elevation model, predict the elevation data of each road section unit; wherein, the road elevation model is used to represent The model of the relationship between the plane features of the road section unit and the elevation data; the two-dimensional road network map is converted into a three-dimensional road network map according to the predicted elevation data.

In one embodiment, the processor also implements the step of training the road elevation model when executing the computer program, and specifically implements the following steps: acquiring a sample two-dimensional road network map; performing plane feature extraction on each sample road segment unit in the sample two-dimensional road network map ; Obtain the actual road condition data corresponding to the sample two-dimensional road network map; train the road elevation model according to the plane features of each sample road segment unit and the actual road condition data.

In one embodiment, when the processor executes the computer program to implement the training of the road elevation model according to the plane features of each sample road segment unit and the actual road condition data, the following steps are specifically implemented: generating each sample road segment according to a preset elevation value range The current elevation data of the unit; each current elevation data is scored according to the actual road condition data; the road elevation model is trained according to the score of each current elevation data.

In one embodiment, when the processor executes the computer program to implement the training of the road elevation model according to the scores of each current elevation data, the following steps are specifically implemented: associating each sample road segment unit with a score greater than a preset threshold with its current elevation data; The current elevation data of each sample road segment unit whose score is less than the preset threshold is adjusted, and the adjusted data is used as the current elevation data, and the step of scoring each current elevation data according to the actual road condition data is entered.

In one embodiment, the processor further implements the following steps when executing the computer program: displaying the three-dimensional road network map on the display interface; The elevation data is returned to the road elevation model for model optimization.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: acquiring a two-dimensional road network map; The unit performs plane feature extraction; according to the extracted plane features of each road section unit and the pre-trained road elevation model, the elevation data of each road section unit is predicted; wherein, the road elevation model is used to characterize the plane feature of the road section unit and the elevation data. The model of the relationship; according to the predicted elevation data, the two-dimensional road network map is converted into a three-dimensional road network map.

In one embodiment, when the computer program is executed by the processor, it also implements the step of training the road elevation model, and specifically implements the following steps: obtaining a sample two-dimensional road network map; Extraction; obtain the actual road condition data corresponding to the sample two-dimensional road network map; train the road elevation model according to the plane features of each sample road segment unit and the actual road condition data.

In one embodiment, when the computer program is executed by the processor to implement the training of the road elevation model according to the plane features of each sample road segment unit and the actual road condition data, the following steps are specifically implemented: generating each sample according to a preset elevation value range The current elevation data of the road segment unit; each current elevation data is scored according to the actual road condition data; the road elevation model is trained according to the score of each current elevation data.

In one embodiment, when the computer program is executed by the processor to implement the training of the road elevation model according to the score of each current elevation data, the following steps are specifically implemented: associating each sample road segment unit with a score greater than a preset threshold with its current elevation data; Adjust the current elevation data of each sample road segment unit whose score is less than the preset threshold, and use the adjusted data as the current elevation data, and enter the step of scoring each current elevation data according to the actual road condition data.

In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: displaying the three-dimensional road network map on the display interface; The elevation data is returned to the road elevation model for model optimization.

Those of ordinary skill in the art can understand that all or part of the process in the method for implementing the above embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer readable In the storage medium, when the computer program is executed, it may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Road (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

The technical features of the above embodiments can be combined arbitrarily. In order to simplify the description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, all It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (10)

1. A road network map processing method, the method comprising: Obtain a 2D road network map; performing plane feature extraction on each road section unit in the two-dimensional road network map; According to the extracted plane features of each of the road section units and the pre-trained road elevation model, the elevation data of each of the road section units is predicted; wherein, the road elevation model is used to represent the plane feature of the road section unit and the elevation data between A model of the relationship; The two-dimensional road network map is converted into a three-dimensional road network map according to each of the predicted elevation data. 2. The method according to claim 1, wherein the training method of the road elevation model comprises: Obtain a sample 2D road network map; performing plane feature extraction on each sample road segment unit in the sample two-dimensional road network map; obtaining actual road condition data corresponding to the sample two-dimensional road network map; The road elevation model is trained according to the plane features of each of the sample road segment units and the actual road condition data. 3. The method according to claim 2, wherein the training of the road elevation model according to the plane features of each of the sample road segment units and the actual road condition data comprises: generating current elevation data of each of the sample road segment units according to a preset elevation value range; scoring each of the current elevation data according to the actual road condition data; The road elevation model is trained according to the scores of each of the current elevation data. 4. The method according to claim 3, wherein the training of the road elevation model according to the score of each of the current elevation data comprises: associating each of the sample road segment units with a score greater than a preset threshold with its current elevation data; Adjust the current elevation data of each of the sample road segment units whose scores are less than a preset threshold, and use the adjusted data as the current elevation data, and enter the process of performing the analysis of each of the current elevation data according to the actual road condition data. Steps for scoring. 5 . The method according to claim 2 , wherein the actual road condition data comprises at least one of lamination relationship data between each of the sample road segment units and slope data of each of the sample road segment units. 6 . kind. 6 . The method of claim 1 , wherein the predicted elevation data includes elevation values of road segment units, elevation range values of road segment units, relative elevation values between road segment units, and relative elevation values between road segment units. 7 . At least one of the elevation range values. 7. The method according to any one of claims 1 to 6, wherein the method further comprises: displaying the three-dimensional road network map on the display interface; In response to an adjustment operation on the elevation data of the designated road segment unit in the three-dimensional road network map, the adjusted elevation data is returned to the road elevation model for model optimization. 8. A road network map processing device, wherein the device comprises: A two-dimensional map acquisition module for acquiring a two-dimensional road network map; a plane feature extraction module, used for extracting plane features for each road section unit in the two-dimensional road network map; The elevation data prediction module is used to predict the elevation data of each of the road segment units according to the extracted plane features of each of the road segment units and the pre-trained road elevation model; wherein, the road elevation model is used to characterize the road segment unit. A model of the relationship between planar features and elevation data; A three-dimensional map generation module is configured to convert the two-dimensional road network map into a three-dimensional road network map according to each of the predicted elevation data. 9. A computer device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor implements any of claims 1 to 7 when the processor executes the computer program. A step of the method. 10. A computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images