A traffic construction path recommendation method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a traffic construction path recommendation method and device, electronic equipment and a storage medium, wherein the method comprises: obtaining a starting administrative region and a terminal administrative region of a traffic construction path; performing grid labeling processing on the starting administrative region and the terminal administrative region to obtain grid labeled administrative regions; determining a grid region transfer action from a current grid labeled administrative region to a next grid labeled administrative region according to an advantage function or a state probability transfer matrix of the grid labeled administrative regions; wherein the grid region transfer action is for avoiding a target avoidance grid region between the starting administrative region and the terminal administrative region; and constructing a recommended traffic construction path according to the grid region transfer actions of the grid labeled administrative regions. The technical solution of the embodiments of the present application can improve the recommendation efficiency, accuracy, intelligence and reliability of the traffic construction path.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of route recommendation technology, and in particular to a method, apparatus, electronic device and storage medium for recommending routes in transportation construction. Background Technology

[0002] Transportation construction is an industry that has a comprehensive and leading impact on national economic development, and route planning plays a crucial role in the construction effect.

[0003] Currently, using computer-aided methods to plan transportation construction routes using map base data is a common practice. Typically, manual analysis of map data is performed offline using tools such as ArcGIS (a map-making infrastructure) or PostgreSQL (a feature-rich free software object-relational database management system). Based on the offline analysis results of the layers, transportation construction routes are drawn based on work experience. For example, based on the map-drawing experience of the staff, a transportation construction route might be recommended to avoid nature reserves along the way.

[0004] In the process of realizing this invention, the inventors discovered the following defects in the prior art: when manual offline data analysis is performed by processing basic map data to recommend and draw traffic construction routes, the data processing is time-consuming and the accuracy is low, resulting in low efficiency, accuracy and reliability of traffic construction route recommendations. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for recommending transportation construction routes, which can improve the efficiency, accuracy, intelligence, and reliability of transportation construction route recommendations.

[0006] According to one aspect of the present invention, a method for recommending transportation construction routes is provided, comprising:

[0007] Obtain the starting and ending administrative regions of the transportation construction route;

[0008] The starting and ending administrative regions are subjected to grid labeling to obtain grid-labeled administrative regions.

[0009] The grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region is determined based on the advantage function or the state probability transition matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region;

[0010] Recommended transportation construction paths are constructed based on the grid area transfer actions of each grid-labeled administrative region.

[0011] According to another aspect of the present invention, a traffic construction route recommendation device is provided, comprising:

[0012] The administrative region acquisition module is used to obtain the starting and ending administrative regions of the transportation construction route;

[0013] The grid-labeled administrative region acquisition module is used to perform grid-labeling processing on the starting administrative region and the ending administrative region to obtain grid-labeled administrative regions.

[0014] The grid region transfer action determination module is used to determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the advantage function or the state probability transfer matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region;

[0015] The recommended transportation construction path construction module is used to construct recommended transportation construction paths based on the grid area transfer actions of each grid-labeled administrative region.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the traffic construction route recommendation method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the traffic construction route recommendation method according to any embodiment of the present invention.

[0021] This invention, through grid labeling of the starting and ending administrative regions of the acquired transportation construction routes, yields grid-labeled administrative regions. Based on a dominance function or the state probability transition matrix of these grid-labeled administrative regions, it determines the grid region transfer actions from the current grid-labeled administrative region to the next, avoiding target-avoiding grid regions. This allows for the construction of recommended transportation construction routes based on the grid region transfer actions of each grid-labeled administrative region. This addresses the low efficiency and accuracy issues of current manual offline analysis of map data for recommending transportation construction routes, improving the efficiency, accuracy, intelligence, and reliability of transportation construction route recommendations.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a traffic construction route recommendation method provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a traffic construction route recommendation method provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a flowchart illustrating a traffic construction route recommendation method provided in Embodiment 2 of the present invention;

[0027] Figure 4 This is a schematic diagram of a traffic construction route recommendation device provided in Embodiment 3 of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0031] Currently, layer data is stored in PostgreSQL (PgSQL) or Oracle, supplemented by the Post-GIS plugin (an extension of the object-relational database system PostgreSQL, providing rich spatial information services). PgSQL is a free and open-source relational database. Compared to the popular MySQL database, PgSQL has absolute advantages in reliability, data integrity, and scalability. PgSQL is a powerful open-source object-relational database system that combines many features for secure storage and scaling of the most complex data workloads. PgSQL supports most SQL (Structured Query Language) tags. ArcGIS provides users with a scalable and comprehensive GIS (Geographic Information System) platform. ArcObjects (ArcMap) provides a similar solution. TM ArcCatalog TM and ArcScene TM The development platform (AO) contains a wide range of programmable components, from fine-grained objects (such as individual geometric objects) to coarse-grained objects, such as map objects that interact with existing ArcMap (a user desktop component) documents. These objects provide developers with comprehensive GIS functionality.

[0032] In related technologies, relevant personnel need to conduct offline data analysis on the basic map data using the aforementioned techniques, and combine this with their personal experience to recommend and draw traffic construction routes. Data processing is time-consuming and has low accuracy, resulting in low efficiency, accuracy, and reliability in recommending traffic construction routes.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a traffic construction route recommendation method provided in Embodiment 1 of the present invention. This embodiment can be applied to the situation where traffic construction routes are automatically recommended based on map data and state probability transition matrix. The method can be executed by a traffic construction route recommendation device, which can be implemented by software and / or hardware, and can generally be integrated into an electronic device. The electronic device can be a terminal device or a server device. The embodiments of the present invention do not limit the specific device type of the electronic device.

[0035] Correspondingly, such as Figure 1 As shown, the method includes the following operations:

[0036] S110. Obtain the starting and ending administrative regions of the transportation construction route.

[0037] The transportation construction route can be a road that needs to be planned and constructed. Road types can include, but are not limited to, expressways, national highways, and rural roads, such as the planned expressway from Guangzhou to Shenzhen. This embodiment of the invention does not limit the route planning type of the transportation construction route. The starting administrative region can be the administrative region where the starting point of the planned transportation construction route is located. The ending administrative region can be the administrative region where the ending point of the planned transportation construction route is located.

[0038] S120. Perform grid labeling on the starting administrative region and the ending administrative region to obtain grid-labeled administrative regions.

[0039] Among them, grid labeling is a process that divides administrative regions into grid areas and adds labels to the resulting grid areas. Grid-labeled administrative regions can be grid areas with labels.

[0040] Accordingly, after obtaining the starting and ending administrative regions of the transportation construction route, the administrative regions and ending regions can be processed into grid-labeled administrative regions. Grid-labeled administrative regions can extract and assemble natural resources using normalized labeled grids, thereby refining the processing of the starting and ending administrative regions involved.

[0041] S130. Determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the advantage function or the state probability transition matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region.

[0042] The dominance function can be used to determine whether there are target avoidance grid areas in the surrounding grid-labeled administrative regions of the current grid-labeled administrative region. The state probability transition matrix can be used to record the probability of a grid-labeled administrative region moving to a surrounding grid-labeled administrative region. A grid area transfer action is the action of moving from one grid-labeled administrative region to another. A target avoidance grid area can be a grid area that overlaps with or intersects with the land type or land use area type that needs to be avoided. For example, a target avoidance grid area can be an area type that requires detour planning, such as a nature reserve, ecological park area, or military land. As long as there is a detour requirement, it is acceptable. This embodiment of the invention does not limit the specific content of the detour required by the target avoidance grid area.

[0043] S140. Construct recommended transportation construction paths based on the grid area transfer actions of each grid-labeled administrative region.

[0044] Among them, the recommended transportation construction path is the transportation construction path generated by linking the selected grid-labeled administrative regions based on the grid area transfer actions, and it can be a grid sequence path type.

[0045] Correspondingly, after obtaining the grid-labeled administrative regions, the grid area transfer actions from one grid-labeled administrative region to the next grid-labeled administrative region can be calculated sequentially based on the grid-labeled administrative regions. The grid area transfer actions from each grid-labeled administrative region to the next grid-labeled administrative region are then linked together, and the grid-labeled administrative regions selected by executing the grid area transfer actions are finally connected to form a recommended transportation construction path in the form of a grid sequence.

[0046] Specifically, the grid area transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region can be determined based on the advantage function or the state probability transition matrix of the grid-labeled administrative region. The principle for determining this grid area transfer action is to avoid the target avoidance grid area between the starting administrative region and the ending administrative region as much as possible, so as to meet the planning requirements of the transportation construction path.

[0047] Therefore, the above-mentioned transportation construction route recommendation method does not require human intervention. By using the state probability transition matrix to control the target avoidance grid areas such as nature reserves along the route, it can achieve intelligent and automated recommendation of transportation construction routes, ensuring the accuracy of transportation construction route recommendation, and improving the recommendation efficiency, intelligence and reliability of route recommendation.

[0048] This invention, through grid labeling of the starting and ending administrative regions of the acquired transportation construction routes, yields grid-labeled administrative regions. Based on a dominance function or the state probability transition matrix of these grid-labeled administrative regions, it determines the grid region transfer actions from the current grid-labeled administrative region to the next, avoiding target-avoiding grid regions. This allows for the construction of recommended transportation construction routes based on the grid region transfer actions of each grid-labeled administrative region. This addresses the low efficiency and accuracy issues of current manual offline analysis of map data for recommending transportation construction routes, improving the efficiency, accuracy, intelligence, and reliability of transportation construction route recommendations.

[0049] Example 2

[0050] Figure 2 This is a flowchart of a traffic construction route recommendation method provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and is further specified. In this embodiment, various specific optional implementation methods are given for grid labeling processing, grid administrative region clustering processing, determining grid region transition actions, updating the state probability transition matrix, and constructing recommended traffic construction routes. Correspondingly, as Figure 2 As shown, the method in this embodiment may include:

[0051] S210, Obtain the starting and ending administrative regions of the transportation construction route.

[0052] S220. The circumscribed rectangular region formed by the starting administrative region and the ending administrative region is gridded to obtain a gridded administrative region.

[0053] The gridding process involves dividing the circumscribed rectangular region into multiple grids. The grid administrative regions are the individual grid regions obtained by performing gridding on the circumscribed rectangular region.

[0054] In a specific example, assuming the starting and ending latitudes of the administrative region are 30°N-40°N and the starting and ending longitudes are 20°E-40°E, and the ending latitudes of the administrative region are 45°N-50°N and the starting and ending longitudes are 30°E-50°E, then the starting and ending latitudes of the circumscribed rectangular region formed by the starting and ending administrative regions are 30°N-50°N and the starting and ending longitudes are 20°E-50°E. Accordingly, the circumscribed rectangular region can be gridded according to a set grid resolution. For example, if the grid resolution is set to 150m*150m, the circumscribed rectangular region can be divided into multiple gridded administrative regions with a 150m*150m grid resolution.

[0055] In an optional embodiment of the present invention, after performing gridding processing on the starting administrative region and the ending administrative region to obtain gridded administrative regions, the method may further include: selecting starting area gridded administrative regions covered by the starting administrative region and ending area gridded administrative regions covered by the ending administrative region from each of the gridded administrative regions; performing clustering processing on the starting area gridded administrative regions and the ending area gridded administrative regions respectively to obtain a set number of clustered starting gridded administrative regions and clustered ending gridded administrative regions; selecting a central gridded administrative region from each of the clustered starting gridded administrative regions as a starting central gridded administrative region; and selecting a central gridded administrative region from each of the clustered ending gridded administrative regions as a ending central gridded administrative region.

[0056] In this invention, the starting area grid administrative region can be any grid administrative region covered by the starting administrative region, and the ending area grid administrative region can be any grid administrative region covered by the ending administrative region. The clustering starting grid administrative region can be several major categories of grid administrative regions obtained by clustering the starting area grid administrative regions, with each clustering starting grid administrative region representing one category of starting area grid administrative regions. The clustering ending grid administrative region can be several major categories of grid administrative regions obtained by clustering the ending area grid administrative regions, with each clustering ending grid administrative region representing one category of ending area grid administrative regions. The number of clustering starting and ending grid administrative regions can be set according to actual needs, such as 9 for both. This embodiment of the invention does not limit the specific value of the set number. The central grid administrative region is the grid administrative region located at the center of a certain category of grid administrative regions. Correspondingly, the starting central grid administrative region is the grid administrative region located at the center of each clustering starting grid administrative region, and the ending central grid administrative region is the grid administrative region located at the center of each clustering ending grid administrative region.

[0057] In this embodiment of the invention, after the gridding process of the outlying rectangular region is completed, the obtained grid administrative regions can be further clustered to group similar grid administrative regions into one category, facilitating analysis and calculation of a certain category of grid administrative regions. Specifically, starting area grid administrative regions covered by the starting administrative region and ending area grid administrative regions covered by the ending administrative region can be selected from the grid administrative regions. Clustering processing is then performed on the starting area grid administrative regions and the ending area grid administrative regions respectively. The starting area grid administrative regions can be clustered into a certain number of clustered starting area grid administrative regions, such as 9 categories, and the ending area grid administrative regions can be clustered into a certain number of clustered ending area grid administrative regions, such as 9 categories. Furthermore, a central grid administrative region is selected from each clustered starting area grid administrative region and a central grid administrative region is selected from each clustered ending area grid administrative region.

[0058] In a specific example, assuming the starting administrative region is Guangzhou and the ending administrative region is Shenzhen, the circumscribed rectangular area formed by the starting and ending latitude and longitude of the Guangzhou and Shenzhen administrative divisions is gridded using a grid resolution of 150m*150m (parameter adjustable), resulting in a gridded administrative region, denoted as GRID_GD. Further, the gridded administrative regions covered by Guangzhou and Shenzhen are selected, and these selected gridded administrative regions are clustered into nine major clusters according to the aforementioned administrative divisions. The starting and ending gridded administrative regions are denoted as follows: Guangzhou: GRID_G1, GRID_G2, GRID_G3, GRID_G4, GRID_G5, GRID_G6, GRID_G7, GRID_G8, and GRID_G9; and Shenzhen: GRID_S1, GRID_S2, GRID_S3, GRID_S4, GRID_S5, GRID_S6, GRID_S7, GRID_S8, and GRID_S9. After clustering is complete, you can iterate through GRID_G1-GRID_G9, extracting the central grid administrative regions from each GRID_G1-GRID_G9, and denoting them as GRID_GD_G1-GRID_GD_G9. For example, for GRID_G1, extract the central grid administrative region as the starting central grid administrative region GRID_GD_G1. Similarly, iterate through GRID_S1-GRID_S9, extracting the central grid administrative regions from each GRID_S1-GRID_GD_S9, and denoting them as GRID_GD_S1-GRID_GD_S9.

[0059] S230. Add multi-dimensional labels to each of the grid administrative regions to obtain the grid-labeled administrative regions.

[0060] The multi-dimensional labels may include, but are not limited to, map patch overlay labels, socio-economic labels, natural resource management data labels, and multi-angle evaluation labels.

[0061] After the above operations are completed, multi-dimensional labels can be added to each grid administrative region to obtain grid-labeled administrative regions. At this point, the normalization grid processing operation for administrative regions and termination regions is complete.

[0062] Among them, overlay labels can be related labels for overlay data of overlay patches between different grid administrative regions. For example, overlay labels can include, but are not limited to, geographic attribute information on patches and polygon areas of intersecting and overlaying grid parts. Socio-economic labels can be related labels reflecting the socio-economic attributes of the grid administrative region. For example, socio-economic labels can include, but are not limited to, AOI (Area of ​​Interest, also called information surface, refers to regional geographic entities in map data), population profiles, and passenger flow data (including passenger volume and direction). Natural resource management data labels can be related labels for the natural resource management attributes of the grid administrative region. For example, natural resource management data labels can include, but are not limited to, administrative divisions, ecological protection red lines, nature reserves, permanent basic farmland data, geological disaster-prone zones, general cultivated land data, coastal zone protection and utilization planning vectors, and urban development boundaries. Multi-angle evaluation labels can be related labels added to the grid administrative region from multiple other perspectives. For example, multi-angle evaluation labels can include, but are not limited to, label types for perspectives such as population benefits, urban benefits, land benefits, and transportation benefits. The aforementioned diverse label types can provide rich and multi-dimensional reference information for subsequent calculations of grid area transfer actions used to avoid target avoidance grid areas, thereby improving the rationality of recommended traffic construction paths.

[0063] S240. Each of the aforementioned starting center grid administrative regions shall be used as the starting point region of the transportation construction path, and each of the aforementioned ending center grid administrative regions shall be used as the ending point region of the transportation construction path.

[0064] S250. Starting from the starting area of ​​the transportation construction path as the current grid-labeled administrative region, perform parallel traversal calculations. Determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the dominance function or the state probability transition matrix of the grid-labeled administrative region, until the calculation reaches the endpoint associated region of the transportation construction path.

[0065] The endpoint associated region includes the grid administrative region within the cluster termination grid administrative region where the endpoint region is located.

[0066] Specifically, when calculating the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region, each starting center grid administrative region can be used as the starting point region of the transportation construction path. Parallel traversal calculations can then be performed starting from the starting point region as the current grid-labeled administrative region. The grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region is determined based on the dominance function or the state probability transition matrix of the grid-labeled administrative region, until the endpoint region of the transportation construction path is reached. For each starting point region, the termination condition for the traversal calculation can be set according to actual needs. For example, the termination condition can be that the optimal endpoint region is calculated within the cluster of the endpoint region, using the endpoint region as the boundary. Alternatively, a computational power constraint can be added to the termination condition. After traversing to the endpoint center grid administrative region, the calculation can be expanded once to the nine grid administrative regions near the endpoint center grid administrative region to calculate the optimal endpoint region from these nine grid administrative regions.

[0067] Continuing with the example above, for the initial central grid administrative regions GRID_GD_G1-GRID_GD_G9 in Guangzhou, each can be used as the starting point region for the transportation construction path. Parallel traversal calculations can then begin from the starting point region of the transportation construction path as the current grid-labeled administrative region. Specifically, taking the first initial central grid administrative region GRID_GD_G1 as an example, parallel traversal calculations begin with GRID_GD_G1 as the current grid-labeled administrative region. Based on the dominance function or the state probability transition matrix of the grid-labeled administrative region, the grid region transition action from the current grid-labeled administrative region to the next grid-labeled administrative region is determined, until the calculation reaches the endpoint associated region of the transportation construction path, such as a certain grid administrative region GRID_GD_S1_SS6 within the cluster termination grid administrative region of GRID_GD_S1 (representing the grid administrative region with identifier SS6 of GRID_GD_S1). Similarly, the above traversal calculation work can be performed in parallel for GRID_GD_G2-GRID_GD_G9.

[0068] It is understandable that when the grid area transfer action is performed to move the current grid-labeled administrative area to the next grid-labeled administrative area, the next grid-labeled administrative area will be automatically updated to the current grid-labeled administrative area.

[0069] Accordingly, step S250 may specifically include the following operations:

[0070] S251. Determine whether there is a target avoidance grid area in the surrounding grid-labeled administrative areas based on the advantage function. If yes, execute S252; otherwise, execute S253.

[0071] Among them, the surrounding grid-labeled administrative regions can be the adjacent grid-labeled administrative regions around the current grid-labeled administrative region, such as the surrounding 9-grid distributed grid-labeled administrative regions, etc.

[0072] S252. Determine the grid region transfer action from the surrounding grid-labeled administrative regions based on the advantage function.

[0073] Specifically, during the traversal and calculation of grid region transfer actions, if the dominant function determines that there are target avoidance grid regions in the surrounding grid regions of the current grid-labeled administrative region, then the grid region transfer action can be directly determined from the surrounding grid regions based on the dominant function. The dominant function can comprehensively consider multiple path planning factors, and the grid region transfer action determined from the surrounding grid regions can maximize the achievement of bypassing the current grid region to the next grid region, thus satisfying the requirements of path planning.

[0074] Optionally, the target avoidance grid area can be a single type of grid area, such as a nature reserve, or it can include multiple different types of grid areas, such as nature reserves and military land, etc. The embodiments of the present invention do not limit this.

[0075] S253. Determine the grid region transfer action from the surrounding grid-labeled administrative regions based on the state probability transition matrix.

[0076] The state probability transition matrix consists of matrix elements representing the transition probability values ​​from the current grid-labeled administrative region to the next grid-labeled administrative region. These transition probability values ​​represent the probability of moving from the current grid-labeled administrative region to the next grid-labeled administrative region.

[0077] In a specific example, discrete transition actions are set for each grid-labeled administrative region. For example, four discrete transition actions (ACTION, denoted as A) can be set: up, down, left, and right. The state includes the number of horizontal grids (denoted as W) and the number of vertical grids (denoted as H) within the circumscribed rectangle formed by the starting and ending administrative regions. Then, the number of states in the state probability transition matrix can be denoted as S = W * H. Correspondingly, the state probability transition matrix can be designed as a tensor of W * H * A, where A = [a0, a1, a2, a3], where a0 represents moving up from the current grid-labeled administrative region, a1 represents moving right from the current grid-labeled administrative region, a2 represents moving down from the current grid-labeled administrative region, and a3 represents moving left from the current grid-labeled administrative region.

[0078] Specifically, during the process of traversing and calculating the transfer action of the grid region, if it is determined from the advantage function that there is no target avoidance grid region in the surrounding grid-labeled administrative regions of the current grid-labeled administrative region, then there is no need to use the advantage function to bypass the target avoidance grid region. The grid region transfer action can be determined from the surrounding grid-labeled administrative regions based on the state probability transition matrix.

[0079] The above technical solution uses a dominance function and an established state probability transition matrix to control the areas that need to be bypassed along the way, enabling intelligent recommendation of traffic construction routes.

[0080] In an optional embodiment of the present invention, determining the grid region transfer action from the surrounding grid-labeled administrative regions based on the state probability transition matrix may include: when the state probability transition matrix is ​​determined to be an initial matrix, randomly selecting a preset direction transfer action as the grid region transfer action from a preset direction transfer action set according to the surrounding grid-labeled administrative regions; when the state probability transition matrix is ​​determined to be an iterative update matrix, selecting the preset direction transfer action with the highest transfer probability value from the preset direction transfer actions set according to the surrounding grid-labeled administrative regions as the grid region transfer action.

[0081] The initial matrix, also known as the state probability transition matrix in the initial state, contains default transition probability values ​​for each matrix parameter, such as 0. The preset direction transition action can be a preset type of transition action that allows movement from one grid-labeled administrative region to another, such as upward, downward, leftward, or rightward transition actions. The iterative update matrix, in the non-initial state, contains updated transition probability values ​​for each matrix parameter.

[0082] Specifically, when determining the grid region transfer action from the surrounding grid-labeled administrative regions based on the state probability transition matrix, the matrix type of the state probability transition matrix can be determined first. If the state probability transition matrix is ​​determined to be an initial matrix, it indicates that the current state probability transition matrix is ​​in its initial state. In this case, one of the preset direction transfer actions set by the surrounding grid-labeled administrative regions can be randomly selected as the grid region transfer action. The advantage of this setting is that it allows the experience pool to store some experience data. If the state probability transition matrix is ​​determined to be an iterative update matrix, it indicates that the current state probability transition matrix is ​​not in its initial state. In this case, the preset direction transfer action with the highest transfer probability value set by the surrounding grid-labeled administrative regions can be selected as the grid region transfer action to achieve optimal path planning.

[0083] In an optional embodiment of the present invention, after determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the advantage function, the method may further include: executing the grid region transfer action on the current grid-labeled administrative region to enter the next grid-labeled administrative region, thereby obtaining the next action execution state; calculating a first action incentive score based on the execution process of the grid region transfer action, the occupancy status of the target avoidance grid region, and the associated incentive function parameters; updating the state probability transition matrix based on the first action incentive score, the grid region transfer action, the previous action execution state, and the next action execution state; and further ... and further, after determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the advantage function, the method may further include: executing the grid region transfer action on the current grid-labeled administrative region to enter the next grid-labeled administrative region, thereby obtaining the next action execution state; and further, after determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the advantage function, the method may further include: executing the grid region transfer action on the current grid-labeled administrative region to enter the next grid-labeled administrative region, thereby obtaining the next action execution state; and further, after determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the advantage function, the method may further include: executing the grid After determining the grid area transfer action from the surrounding grid-labeled administrative regions, the probability transition matrix may further include: executing the grid area transfer action on the current grid-labeled administrative region to enter the next grid-labeled administrative region, thereby obtaining the next action execution state; calculating a second action incentive score based on the associated incentive function parameters; and updating the state probability transition matrix based on the second action incentive score, the grid area transfer action, the previous action execution state, and the next action execution state; wherein the associated incentive function parameters include socio-economic label parameters, natural resource management data label parameters, multi-angle evaluation label parameters, and endpoint region parameters.

[0084] The associated excitation function parameters can be relevant parameters used to calculate the excitation score. The first action excitation score can be the excitation score calculated for the determined grid area transfer action after the grid area transfer action is determined based on the dominance function. The previous action execution state can be the execution direction of the previous grid area transfer action, that is, the direction of the recommended traffic path after the previous grid area transfer action is completed. The next action execution state can be the execution direction of the current grid area transfer action, that is, the direction of the recommended traffic path after the current grid area transfer action is completed. The second action excitation score can be the excitation score calculated for the determined grid area transfer action after the grid area transfer action is determined based on the state probability transition matrix.

[0085] Accordingly, after determining the grid area transfer action, the grid area transfer action can be executed for the current grid-labeled administrative area to enter the next grid-labeled administrative area, obtain the execution status of the next action, and obtain the corresponding incentive score based on the feedback of the incentive mechanism. After obtaining the incentive score, the state probability transition matrix can be updated based on the incentive score. Specifically, empirical learning can be performed based on the calculated incentive score, grid area transfer action, the execution status of the previous action, and the execution status of the next action, and the state probability transition matrix can be updated based on the learning results.

[0086] It should be noted that the calculation method for the incentive score differs depending on the method used to determine the grid region transfer action. Specifically, if the grid region transfer action is calculated based on the dominance function, the first action incentive score needs to be calculated based on the occupation of the grid region transfer action and the target avoidance grid region, as well as the associated incentive function parameters. If the grid region transfer action is calculated based on the state probability transition matrix, meaning that there is no occupation of the target avoidance grid region during the execution of the grid region transfer action, the second action incentive score can be calculated based on the associated incentive function parameters.

[0087] Specifically, the associated incentive function parameters may include, but are not limited to, socio-economic label parameters, natural resource management data label parameters, multi-angle evaluation label parameters, and endpoint region parameters. Socio-economic label parameters can be incentive function parameters generated based on socio-economic labels; natural resource management data label parameters can be incentive function parameters generated based on natural resource management data labels; multi-angle evaluation label parameters can be incentive function parameters generated based on multi-angle evaluation labels; and endpoint region parameters can be incentive function parameters that set incentive scores based on the administrative region of the terminating central grid.

[0088] In summary, the incentive function can be constructed based on the occupation parameter (i.e., the execution process of the grid area transfer action and the occupation status of the target's avoidance of the grid area), socio-economic label parameters, natural resource management data label parameters, multi-angle evaluation label parameters, and endpoint area parameters. Different parameters can be assigned corresponding weight values, with the occupation parameter having the highest weight. The weight values ​​of other parameters can be set according to actual needs. It is understandable that the higher the occupation ratio, the lower the incentive score calculated using the occupation parameter, which can even be negative. After the grid area transfer action is calculated based on the dominance function, the occupation parameter value is not 0. Therefore, the first action incentive score can be calculated based on the execution process of the grid area transfer action, the target's avoidance of the grid area's occupation status, and the associated incentive function parameters. After the grid area transfer action is calculated based on the state probability transition matrix, the occupation parameter value is 0. Therefore, the second action incentive score is actually calculated based on the associated incentive function parameters.

[0089] S260. Construct recommended transportation construction paths based on the grid area transfer actions of each grid-labeled administrative region.

[0090] In an optional embodiment of the present invention, the step of constructing a recommended traffic construction path based on the grid area transfer actions of each of the grid-labeled administrative regions may include: when the grid area transfer action is determined from the surrounding grid-labeled administrative regions of the current grid-labeled administrative region according to the state probability transfer matrix, determining a target area transfer action from the grid area transfer action and random transfer actions according to the preset action execution probability of the grid area transfer action; and constructing the recommended traffic construction path based on the target area transfer action.

[0091] The action execution probability can be the probability of executing a grid area transfer action. A random transfer action can be a transfer action executed randomly through a low-probability event. The target area transfer action can be the transfer action ultimately determined for transferring from the current grid-labeled administrative area to the next grid-labeled administrative area.

[0092] In this embodiment of the invention, to prevent the recommended traffic construction path from getting trapped in a local optimum and to fully explore the state spaces of various grid paths to obtain a relatively better solution space, an action execution probability can be set for grid area transfer actions, for example, it can be set to 0.99. Correspondingly, after determining the grid area transfer action, the probability of a random transfer action can be determined based on the action execution probability of the grid area transfer action, such as 0.01, and an action is randomly executed based on the probability of the random transfer action to enter the next action execution state. That is, the final executed transfer action may be a grid area transfer action determined by the dominance function or the state probability transition matrix, or it may be a random transfer action randomly determined based on the probability of the random transfer action. Finally, the recommended traffic construction path will be constructed based on the grid area transfer action or the random transfer action as the target area transfer action.

[0093] To more clearly illustrate the technical solution provided by the embodiments of the present invention, a specific example is given, using Guangzhou as the starting administrative region and Shenzhen as the ending administrative region, to specifically explain the traffic construction route recommendation method. Guangzhou and Shenzhen can be used as inputs, and the output is the recommended traffic construction route (grid sequence route) that needs to be bypassed along the way. Figure 3 This is a flowchart illustrating a traffic construction route recommendation method provided in Embodiment 2 of the present invention, as shown below. Figure 3 As shown, the traffic construction route recommendation method provided in this embodiment of the invention may specifically include the following operations:

[0094] (1) Determine the circumscribed rectangular area based on the starting and ending latitude and longitude of the combination of Guangzhou and Shenzhen administrative divisions. Grid the circumscribed rectangular area using a grid resolution of 150m*150m (adjustable parameter) to obtain the gridded administrative area; denoted as GRID_GD.

[0095] (2) After the grid is completed, the grid administrative regions involved in Guangzhou and Shenzhen are selected. These selected grid administrative regions are clustered into 9 major categories of cluster starting grid administrative regions and cluster ending grid administrative regions. The cluster starting grid administrative regions of Guangzhou are: GRID_G1, GRID_G2, GRID_G3, GRID_G4, GRID_G5, GRID_G6, GRID_G7, GRID_G8 and GRID_G9; the cluster ending grid administrative regions of Shenzhen are: GRID_S1, GRID_S2, GRID_S3, GRID_S4, GRID_S5, GRID_S6, GRID_S7, GRID_S8 and GRID_S9.

[0096] (3) Iterate through GRID_G1-GRID_G9 in sequence; extract the central grid administrative region from GRID_G1-GRID_GD_G1-GRID_GD_G9 in sequence; at the same time, extract the central grid administrative region from GRID_S1-GRID_S9 in sequence, and record it as GRID_GD_S1-GRID_GD_S9.

[0097] (4) Grid Labeling: Add multi-dimensional labels to the grid administrative regions of GRID_GD; multi-dimensional labels may include: overlay labels: geographic attribute information on the patches and the polygon area of ​​each overlapping grid part as labels; socio-economic labels: AOI, population profile and passenger flow data (passenger flow, passenger flow direction) and other labels; natural resource management data labels: administrative division, ecological protection red line, nature reserve, permanent basic farmland data, geological disaster hazard zoning, general cultivated land data, coastal zone protection and utilization planning vector and urban development boundary and other labels; multi-angle evaluation labels: population benefits, urban benefits, land benefits and transportation benefits and other labels.

[0098] (5) Algorithm model design: The fifth step of the operation is performed in parallel on the nine central grid administrative regions of Guangzhou. That is, the nine grids of GRID_GD_G1-GRID_GD_G9 are input into the algorithm model. The endpoint of each recommended traffic construction path output by the algorithm model will eventually land in the central grid administrative region of Shenzhen or other grid administrative regions of the cluster termination grid administrative region where the central grid administrative region is located.

[0099] The algorithm's calculation process is as follows: If there are grid-labeled administrative regions near the current grid-labeled administrative region that overlap or intersect with a nature reserve, the dominant function is used to determine the grid region transfer action to better bypass the nature reserve. Otherwise, the state of the state probability transition matrix is ​​assessed. If the state of the state probability transition matrix is ​​determined to be the initial state, an action is randomly selected as the grid region transfer action to store some experience data in the experience pool; otherwise, the action with the highest probability transition is selected as the grid region transfer action. After determining the grid region transfer action, it can be executed to enter the next state, and the incentive score obtained from the incentive mechanism is obtained. Then, based on the previous state, the currently executed action, the incentive score, and the next state, experience learning is performed to calculate and update the state probability transition matrix.

[0100] (6) To prevent the grid path from being in a local optimum, a greedy strategy can be adopted for action execution decision-making. If the grid region transfer action is determined according to the state probability transition matrix, the decision-making process executes the grid region transfer action with a probability of 0.99 and randomly executes an action to enter the next state with a probability of 0.01. This allows for a thorough exploration of the state spaces of various grid paths, thereby obtaining a relatively better solution space. Here, 0.01 is a hyperparameter that can be dynamically configured and adjusted.

[0101] In the above scheme, the state probability transition matrix is ​​designed as follows: each grid administrative region is given four discrete ACTIONs (denoted as A) of up, down, left, and right. The state has the number of horizontal grids (denoted as W) and the number of vertical grids (denoted as H) of the circumscribed rectangular region. Then the number of states in the state probability transition matrix is ​​denoted as S = W * H. Accordingly, the state probability transition matrix is ​​designed as a tensor of W * H * A; where A = [a0, a1, a2, a3].

[0102] In the above scheme, the incentive mechanism design can be specifically as follows: Incentive scores are set based on whether overlapping or encroachment relationships occur with nature reserves during the grid area transfer process for the current grid-labeled administrative region. The larger the overlapping area, the lower the incentive score. Secondly, socio-economic label parameters, natural resource management data label parameters, and multi-dimensional evaluation label parameters such as population benefits, urban benefits, land benefits, and transportation benefits can all be used to set incentive scores. Finally, incentive scores can also be set based on the termination grid points of transportation construction paths (e.g., GRID_GD_S1-GRID_GD_S9), with different termination grid points corresponding to different incentive scores.

[0103] It should be noted that the labeling system on the grid-labeled administrative region obtained through the above steps can determine whether there is an overlap or encroachment relationship with nature reserves.

[0104] In summary, the algorithm model takes the start and end points of the transportation construction route, as well as necessary points along the way, as input, and outputs a recommended transportation construction route assuming that nature reserves need to be bypassed along the route. The core idea of ​​this scheme is to learn the state probability transition matrix of each grid (default resolution is 150m*150m) through trial and error using the algorithm model. Each grid can be assigned four discrete ACTIONs (denoted as A): up, down, left, and right. All grid probability transition matrices are initialized to 0. Through continuous trial and error random walks in each grid, the A value for each step is obtained. The incentive score obtained from executing this A is calculated using A, and this incentive score is used to update the value of the state probability transition matrix. In the assessment stage of transportation construction routes such as highways, the above scheme can identify nature reserves along the route and provide recommended transportation construction routes based on the provided construction direction, thereby assisting government departments in land development planning.

[0105] It should be noted that any arrangement or combination of the technical features in the above embodiments also falls within the protection scope of this invention.

[0106] Example 3

[0107] Figure 4 This is a schematic diagram of a traffic construction route recommendation device provided in Embodiment 3 of the present invention, as shown below. Figure 4 As shown, the device includes: an administrative region acquisition module 310, a grid-labeled administrative region acquisition module 320, a grid region transfer action determination module 330, and a recommended traffic construction route construction module 340, wherein:

[0108] The administrative region acquisition module 310 is used to acquire the starting and ending administrative regions of the transportation construction route;

[0109] The grid-labeled administrative region acquisition module 320 is used to perform grid-labeling processing on the starting administrative region and the ending administrative region to obtain grid-labeled administrative regions.

[0110] The grid region transfer action determination module 330 is used to determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the advantage function or the state probability transfer matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region;

[0111] The recommended transportation construction path construction module 340 is used to construct recommended transportation construction paths based on the grid area transfer actions of each grid-labeled administrative region.

[0112] This invention, through grid labeling of the starting and ending administrative regions of the acquired transportation construction routes, yields grid-labeled administrative regions. Based on a dominance function or the state probability transition matrix of these grid-labeled administrative regions, it determines the grid region transfer actions from the current grid-labeled administrative region to the next, avoiding target-avoiding grid regions. This allows for the construction of recommended transportation construction routes based on the grid region transfer actions of each grid-labeled administrative region. This addresses the low efficiency and accuracy issues of current manual offline analysis of map data for recommending transportation construction routes, improving the efficiency, accuracy, intelligence, and reliability of transportation construction route recommendations.

[0113] Optionally, the grid-labeled administrative region acquisition module 320 is specifically used for: performing grid processing on the circumscribed rectangular area formed by the starting administrative region and the ending administrative region to obtain a grid administrative region; adding multi-dimensional labels to each of the grid administrative regions to obtain the grid-labeled administrative region; wherein, the multi-dimensional labels include map patch overlay labels, socio-economic labels, natural resource management data labels, and multi-angle evaluation labels.

[0114] Optionally, the transportation construction route recommendation device may further include a regional clustering module, used for: selecting, from each of the grid administrative regions, the starting area grid administrative regions covered by the starting administrative region and the ending area grid administrative regions covered by the ending administrative region; performing clustering processing on the starting area grid administrative regions and the ending area grid administrative regions respectively to obtain a set number of clustered starting grid administrative regions and clustered ending grid administrative regions; selecting a central grid administrative region from each of the clustered starting grid administrative regions as the starting central grid administrative region; and selecting a central grid administrative region from each of the clustered ending grid administrative regions as the ending central grid administrative region.

[0115] Optionally, the grid region transfer action determination module 330 is specifically used to: take each of the starting center grid administrative regions as the starting point region of the transportation construction path, and each of the ending center grid administrative regions as the ending point region of the transportation construction path; start parallel traversal calculation from the starting point region of the transportation construction path as the current grid-labeled administrative region, determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region according to the dominance function or the state probability transition matrix of the grid-labeled administrative region, until the endpoint associated region of the endpoint region of the transportation construction path is calculated; wherein, the endpoint associated region includes the grid administrative regions within the clustered endpoint grid administrative region where the endpoint region is located.

[0116] Optionally, the grid region transfer action determination module 330 is specifically used for: during the traversal calculation of the grid region transfer action, if the target avoidance grid region exists in the surrounding grid-labeled administrative regions determined by the dominance function, determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the dominance function; and during the traversal calculation of the grid region transfer action, if the target avoidance grid region does not exist in the surrounding grid-labeled administrative regions determined by the dominance function, determining the grid region transfer action from the surrounding grid-labeled administrative regions according to the state probability transition matrix; wherein, the matrix elements of the state probability transition matrix are the transition probability values ​​of the current grid-labeled administrative region transferring to the next grid-labeled administrative region.

[0117] Optionally, the grid region transfer action determination module 330 is specifically used for: when the state probability transfer matrix is ​​determined to be an initial matrix, randomly selecting a preset direction transfer action as the grid region transfer action from the preset direction transfer actions set according to the surrounding grid-labeled administrative regions; when the state probability transfer matrix is ​​determined to be an iterative update matrix, selecting the preset direction transfer action with the largest transfer probability value from the preset direction transfer actions set according to the surrounding grid-labeled administrative regions as the grid region transfer action.

[0118] Optionally, the transportation construction route recommendation device may further include a state probability transition matrix update module, used for: executing the grid area transfer action for the current grid-labeled administrative area transfer to enter the next grid-labeled administrative area, and obtaining the next action execution state; calculating a first action incentive score based on the execution process of the grid area transfer action, the occupation status of the target avoidance grid area, and the associated incentive function parameters; updating the state probability transition matrix based on the first action incentive score, the grid area transfer action, the previous action execution state, and the next action execution state; executing the grid area transfer action for the current grid-labeled administrative area transfer to enter the next grid-labeled administrative area, and obtaining the next action execution state; calculating a second action incentive score based on the associated incentive function parameters; updating the state probability transition matrix based on the second action incentive score, the grid area transfer action, the previous action execution state, and the next action execution state; wherein, the associated incentive function parameters include socio-economic label parameters, natural resource management data label parameters, multi-angle evaluation label parameters, and destination area parameters.

[0119] Optionally, the recommended traffic construction path construction module 340 is specifically used for: determining the grid area transfer action from the surrounding grid-labeled administrative regions according to the state probability transition matrix, determining the target area transfer action from the grid area transfer action and random transfer action according to the preset action execution probability of the grid area transfer action; and constructing the recommended traffic construction path according to the target area transfer action.

[0120] The aforementioned traffic construction route recommendation device can execute the traffic construction route recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the traffic construction route recommendation method provided in any embodiment of the present invention.

[0121] Since the traffic construction route recommendation device described above is an apparatus capable of executing the traffic construction route recommendation method in the embodiments of the present invention, those skilled in the art can understand the specific implementation methods and various variations of the traffic construction route recommendation device in this embodiment based on the traffic construction route recommendation method described in the embodiments of the present invention. Therefore, how this traffic construction route recommendation device implements the traffic construction route recommendation method in the embodiments of the present invention will not be described in detail here. Any apparatus used by those skilled in the art to implement the traffic construction route recommendation method in the embodiments of the present invention falls within the scope of protection of this application.

[0122] Example 4

[0123] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0124] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0125] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0126] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as traffic construction route recommendation methods.

[0127] In some embodiments, the traffic construction route recommendation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the traffic construction route recommendation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the traffic construction route recommendation method by any other suitable means (e.g., by means of firmware).

[0128] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0129] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0130] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0131] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0132] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0133] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

Claims

1. A method for recommending transportation construction routes, characterized in that, include: Obtain the starting and ending administrative regions of the transportation construction route; The starting and ending administrative regions are subjected to grid labeling to obtain grid-labeled administrative regions. The grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region is determined based on the advantage function or the state probability transition matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region; Based on the grid area transfer actions of each grid-labeled administrative region, a recommended transportation construction path is constructed. The step of determining the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the dominance function or the state probability transition matrix of the grid-labeled administrative region includes: During the process of traversing and calculating the grid region transfer action, if it is determined from the surrounding grid region labeled with administrative tags that the target avoidance grid region exists based on the advantage function, the grid region transfer action is determined from the surrounding grid region labeled with administrative tags based on the advantage function. During the process of traversing and calculating the grid region transfer action, if it is determined from the surrounding grid region labeled with administrative tags that the target avoidance grid region does not exist according to the advantage function, the grid region transfer action is determined from the surrounding grid region labeled with administrative tags according to the state probability transition matrix. The matrix elements of the state probability transition matrix are the transition probability values ​​of the current grid-labeled administrative region to the next grid-labeled administrative region. Determining the grid region transfer action from the surrounding grid-labeled administrative regions based on the state probability transition matrix includes: When the state probability transition matrix is ​​determined to be the initial matrix, a preset direction transition action is randomly selected from the preset direction transition actions set according to the surrounding grid-labeled administrative regions as the grid region transition action; If the state probability transition matrix is ​​determined to be an iterative update matrix, the preset direction transition action with the highest transition probability value is selected from the preset direction transition actions set according to the surrounding grid-labeled administrative regions as the grid region transition action.

2. The method according to claim 1, characterized in that, The step of performing grid-labeling processing on the starting administrative region and the ending administrative region to obtain grid-labeled administrative regions includes: The circumscribed rectangular region formed by the starting administrative region and the ending administrative region is gridded to obtain a gridded administrative region. Add multi-dimensional labels to each of the grid administrative regions to obtain the grid-labeled administrative regions; The multi-dimensional labels include map patch overlay labels, socio-economic labels, natural resource management data labels, and multi-angle evaluation labels.

3. The method according to claim 2, characterized in that, After performing gridding processing on the starting administrative region and the ending administrative region to obtain the gridded administrative region, the method further includes: From each of the aforementioned grid administrative regions, select the starting area grid administrative regions covered by the starting administrative region and the ending area grid administrative regions covered by the ending administrative region; Clustering is performed on the starting region grid administrative region and the ending region grid administrative region respectively to obtain a set number of clustering starting grid administrative regions and clustering ending grid administrative regions; For each cluster's initial grid administrative region, a central grid administrative region is selected as the initial central grid administrative region; For each cluster termination grid administrative region, the central grid administrative region is selected as the termination central grid administrative region.

4. The method according to claim 3, characterized in that, The step of determining the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the dominance function or the state probability transition matrix of the grid-labeled administrative region includes: Each of the aforementioned starting center grid administrative regions shall be regarded as the starting point region of the transportation construction path, and each of the aforementioned ending center grid administrative regions shall be regarded as the ending point region of the transportation construction path. Starting from the starting area of ​​the transportation construction path as the current grid-labeled administrative region, parallel traversal calculation is performed. Based on the advantage function or the state probability transition matrix of the grid-labeled administrative region, the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region is determined until the endpoint associated region of the end area of ​​the transportation construction path is calculated. The endpoint associated region includes the grid administrative region within the cluster termination grid administrative region where the endpoint region is located.

5. The method according to claim 4, characterized in that, After determining the grid region transfer action from the surrounding grid-labeled administrative regions based on the advantage function, the method further includes: The grid region transfer action is executed on the current grid-labeled administrative region to enter the next grid-labeled administrative region, and the execution status of the next action is obtained; The first action incentive score is calculated based on the execution process of the grid area transfer action, the occupancy status of the target avoidance grid area, and the associated incentive function parameters; The state probability transition matrix is ​​updated based on the first action incentive score, the grid region transition action, the execution state of the previous action, and the execution state of the next action. After determining the grid region transition action from the surrounding grid-labeled administrative regions based on the state probability transition matrix, the method further includes: The grid region transfer action is executed on the current grid-labeled administrative region to enter the next grid-labeled administrative region, and the execution status of the next action is obtained; Calculate the second action incentive score based on the parameters of the associated incentive function; The state probability transition matrix is ​​updated based on the second action incentive score, the grid region transition action, the previous action execution state, and the next action execution state; The parameters of the associated incentive function include socio-economic label parameters, natural resource management data label parameters, multi-angle evaluation label parameters, and endpoint region parameters.

6. The method according to claim 1, characterized in that, The process of constructing recommended transportation construction routes based on the grid area transfer actions of each of the grid-labeled administrative regions includes: When the grid region transfer action is determined from the surrounding grid-labeled administrative regions of the current grid-labeled administrative region according to the state probability transfer matrix, the target region transfer action is determined from the grid region transfer action and the random transfer action according to the preset action execution probability of the grid region transfer action; The recommended transportation construction path is constructed based on the target area transfer actions.

7. A traffic construction route recommendation device, characterized in that, include: The administrative region acquisition module is used to obtain the starting and ending administrative regions of the transportation construction route; The grid-labeled administrative region acquisition module is used to perform grid-labeling processing on the starting administrative region and the ending administrative region to obtain grid-labeled administrative regions. The grid region transfer action determination module is used to determine the grid region transfer action from the current grid-labeled administrative region to the next grid-labeled administrative region based on the advantage function or the state probability transfer matrix of the grid-labeled administrative region; wherein, the grid region transfer action is used to avoid the target avoidance grid region between the starting administrative region and the ending administrative region; The recommended transportation construction path construction module is used to construct recommended transportation construction paths based on the grid area transfer actions of each grid-labeled administrative region. The grid region transfer action determination module is specifically used for: during the traversal and calculation of the grid region transfer action, if the target avoidance grid region exists in the surrounding grid region labeled with administrative regions based on the advantage function, determining the grid region transfer action from the surrounding grid region labeled with administrative regions based on the advantage function; and during the traversal and calculation of the grid region transfer action, if the target avoidance grid region does not exist in the surrounding grid region labeled with administrative regions based on the advantage function, determining the grid region transfer action from the surrounding grid region labeled with administrative regions based on the state probability transition matrix; wherein, the matrix elements of the state probability transition matrix are the transition probability values ​​from the current grid region labeled with administrative regions to the next grid region labeled with administrative regions. The grid region transfer action determination module is specifically used for: when the state probability transfer matrix is ​​determined to be an initial matrix, randomly selecting a preset direction transfer action as the grid region transfer action from the preset direction transfer actions set according to the surrounding grid-labeled administrative regions; when the state probability transfer matrix is ​​determined to be an iterative update matrix, selecting the preset direction transfer action with the largest transfer probability value as the grid region transfer action from the preset direction transfer actions set according to the surrounding grid-labeled administrative regions.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the traffic construction route recommendation method according to any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the traffic construction route recommendation method according to any one of claims 1-6.

Images