Traveling road section matching method, device and equipment of train and storage medium

Abstract

The invention provides a train driving road section matching method, device and equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining the positioning data of a train positioning point at a current observation moment, and determining a candidate road section set matched with the train positioning point in a train road network based on the positioning data of the train positioning point; for each candidate road section, obtaining a target observation probability and a target transition probability of the candidate road section matched with the train positioning point; under the condition that a train positioning point arrives at a key control point of a road section, the target observation probability and the target transition probability of a candidate road section and the target observation probability and the target transition probability of the candidate road section of the train positioning point at each observation moment from a starting observation moment to a current observation moment are applied to a Viterbi algorithm. And determining a target candidate road section matched with the train positioning point. According to the method, the accuracy and reliability of train section matching in a complex and changeable line environment in a heavy haul railway traffic road network are improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for matching a train driving section. Background Art

[0002] Map matching is one of the important steps in the positioning algorithm. It is used to match the actual collected positioning data with the pre-built map to determine the specific location of the location point on the map. Map matching has a wide range of applications in vehicle navigation, traffic management, logistics and transportation, and can help analyze vehicle driving paths, predict traffic congestion, and optimize route planning. Through map matching, the accuracy and reliability of location data can be improved. The map matching process can help improve the accuracy and reliability of positioning, especially when using positioning technologies such as GPS. The basic idea of ​​map matching is to find the best match by comparing the similarity between location data and map data.

[0003] At present, map matching positioning algorithms are mostly used in urban road networks to improve the accuracy and reliability of vehicle navigation and traffic management. However, due to the complexity and particularity of heavy-duty railway transportation networks, such as the fixed nature of railway lines, the high density of railway lines, and various changes on railway lines (such as curves, slopes, switches, etc.), when existing map matching technology is applied to this scenario, there may be insufficient recognition and matching accuracy of railway lines, and it is difficult to adapt to the complex curves and slope changes of railway lines; the positioning accuracy of trains in complex areas such as railway intersections and shunting yards is not high. Summary of the invention

[0004] The present invention provides a train driving section matching method, device, equipment and storage medium, which are used to solve the defects of the train driving section matching method in the prior art.

[0005] The present invention provides a method for matching a driving section of a train, the method comprising: Obtain the positioning data of the train positioning point at the current observation time; Based on the positioning data of the train positioning point at the current observation time, determining a set of candidate sections in the train road network that matches the train positioning point at the current observation time; For each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtaining a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; In the case that the train positioning point at the current observation time reaches the key control point of the section, the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, are applied to the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of a turning point, a turning point, a tunnel starting point and end point, a bridge starting point and end point, and a kilometer mark.

[0006] According to a train driving section matching method provided by the present invention, the target observation probability of the candidate section matched by the train positioning point at the current observation time is obtained in the following manner: Determining a first observation probability of the candidate section based on the distance between the train positioning point and the candidate section at the current observation time; Determining a second observation probability of the candidate section based on a direction vector of the train positioning point at the current observation time and a direction vector of the candidate section; Based on the first observation probability and the second observation probability of the candidate road segment, a target observation probability of the candidate road segment is determined.

[0007] According to a train driving section matching method provided by the present invention, the target transition probability of the candidate section matched by the train positioning point at the current observation time is obtained by the following method: Determine a first transition probability of the candidate section based on a distance between a train positioning point at a current observation time and a train positioning point at a previous observation time, and a distance between a projection point of the train positioning point at the current observation time in the candidate section and the train positioning point at the previous observation time; Determine a second transition probability of the candidate section based on a direction vector between a projection point of a train location point at a current observation time in the candidate section and a starting line point of the candidate section and a direction vector of the candidate section; Based on the first transition probability and the second transition probability of the candidate road segment, a target transition probability of the candidate road segment is determined.

[0008] According to a method for matching a driving section of a train provided by the present invention, the method of determining a candidate section set for matching a train positioning point at the current observation time in a train road network based on the positioning data of the train positioning point at the current observation time comprises: Obtaining a grid index table and a section data table matching a train road network, wherein the train road network includes the longitude and latitude of the first and last line points of each section and the point numbers of the first and last line points, the grid index table includes the grid mileage range and section identification corresponding to each grid, and the section data table includes the longitude and latitude and point numbers of the first and last line points corresponding to each section identification; Based on the positioning data of the train positioning point at the current observation time, the grid index table and the section data table are queried to determine a set of candidate sections that match the train positioning point at the current observation time in the train road network.

[0009] A method for matching a train driving section provided by the present invention further includes: Determine the distance between the train positioning point at the current observation time and the section key control point of the candidate section based on the longitude and latitude in the positioning data of the train positioning point at the current observation time and the longitude and latitude of the section key control point of the candidate section matched by the train positioning point at the current observation time; When the distance is less than or equal to the distance threshold, determining that the train positioning point at the current observation time has arrived at the key control point of the section; When the distance is greater than the distance threshold, it is determined that the train positioning point at the current observation time has not reached the key control point of the section.

[0010] A method for matching a train driving section provided by the present invention further includes: When the train positioning point at the current observation time has not reached the key control point of the section, the target candidate section that matches the train positioning point at the current observation time in the candidate section set is determined based on the target observation probability and the target transfer probability of the candidate section.

[0011] The present invention also provides a train driving section matching device, the device comprising: The first driving section matching module is used to obtain the positioning data of the train positioning point at the current observation time; A second driving section matching module is used to determine a candidate section set matching the train positioning point at the current observation time in the train road network based on the positioning data of the train positioning point at the current observation time; A third driving section matching module is used to obtain, for each candidate section in the candidate section set matched by the train positioning point at the current observation time, a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; The fourth driving route section matching module is used to apply the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set when the train positioning point at the current observation time reaches the key control point of the section, based on the target observation probability and the target transfer probability of the candidate section, and the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, wherein the key control point of the section includes at least one of the entry point, exit point, tunnel starting point and end point, bridge starting point and end point, and kilometer mark.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for matching a train driving section as described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for matching the driving section of a train as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned train driving section matching methods.

[0015] The method, device, equipment and storage medium for matching a driving section of a train provided by the present invention include obtaining positioning data of a train positioning point at a current observation time, determining a candidate section set in a train road network that matches the train positioning point at the current observation time based on the positioning data of the train positioning point at the current observation time; obtaining a target observation probability and a target transfer probability of the candidate section that matches the train positioning point at the current observation time for each candidate section in the candidate section set that matches the train positioning point at the current observation time; when the train positioning point at the current observation time reaches a key control point of the section, applying a Viterbi algorithm based on the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, to determine a target candidate section in the candidate section set that matches the train positioning point at the current observation time, wherein the key control point of the section includes at least one of an in-curve point, an out-curve point, a tunnel start point and an end point, a bridge start point and an end point, and a kilometer mark. In this way, the present invention accurately obtains train positioning data, determines the candidate section set based on these data, and then combines the target observation probability and target transfer probability of the train positioning point on the candidate section at the current and historical observation times, and uses the Viterbi algorithm to comprehensively consider all observation data when the train arrives at the key control point of the section, so as to more accurately match the target candidate section of the train at the current observation time. It not only improves the accuracy and reliability of driving section matching in the complex and changeable line environment of the heavy-duty railway transportation network. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a schematic diagram of a scenario of a line error between an actual line provided by the present invention and a track line formed by DTM data points; Figure 2 It is a flow chart of the method for matching the driving route section of a train provided by the present invention; Figure 3 It is a schematic diagram of a scene of grid index division of a train road network of a heavy-haul railway provided by the present invention; Figure 4 It is a structural schematic diagram of a train driving section matching device provided by the present invention; Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] It should be noted that the electronic map of the heavy-haul railway in the embodiment of the present invention is constructed based on the data mode of the Digital Terrain Models (DTM), and the map data is obtained and the database is constructed by measuring the track line of the heavy-haul railway. DTM is a digital description form with spatial position (X, Y) and terrain attribute (Z) features, which is mainly used to express the surface morphological attributes of the terrain, where the attribute information (Z value) can include terrain features such as elevation, slope and slope aspect.

[0020] Combined with the actual operation of the train, in order to ensure the safety of train operation, the track line of heavy-duty railways usually does not have sharp turns, and the minimum curve radius of the track line R ≥ 200m. Assuming that the distance between DTM data points is small, the track line is represented by any two consecutive DTM data points, and the track line of the train operation is approximately represented by a straight line. Therefore, there is an inherent deviation d between the actual line and the track line composed of DTM data points, such as Figure 1 shown.

[0021] From the above analysis, it can be seen that the accuracy of the electronic map data points of the heavy-haul railway has a crucial impact on the subsequent map matching results. Therefore, in this embodiment, the acquisition plan of the electronic map data points of the heavy-haul railway is divided into five steps, namely, first using RTK (real-time dynamic carrier phase difference technology) to collect common special points in the heavy-haul railway, such as stations (stations or stops along the railway), the starting point and end point of the tunnel (a tunnel is a special section of the railway that passes through a mountain or underground structure, and its starting point and end point are the key positions for the train to enter and leave the tunnel), the starting point and end point of the bridge (a bridge is a railway crossing The structure of rivers, lakes or other obstacles, whose starting and ending points are the key positions for trains to get on and off the bridge), kilometer markers (kilometer markers are special points along the railway used to mark distances, usually set in integer kilometers) and other key points are marked; then the VINS-Fusion method that combines visual information and inertial measurement unit data is used to draw the route map; then the starting point and key points measured by RTK are combined with the route map and posture data drawn by VINS-Fusion, with 1m as the distance between two points, the longitude and latitude of each point in the electronic map are calculated.

[0022] Specifically, in the embodiment of the present invention, the electronic map of the heavy-haul railway adopts the DTM data point format, the spatial position characteristics (X, Y) include the relative horizontal coordinate (x) and relative vertical coordinate (y) of the map, and the terrain attribute characteristics (Z) include longitude, latitude, relative displacement (drift) from the previous point and accumulated mileage.

[0023] Figure 2 FIG. 1 is a flow chart of a method for matching a train driving section provided by the present invention. Figure 2 As shown, the method includes: Step 210, obtaining the positioning data of the train positioning point at the current observation time; Specifically, the positioning data of the train positioning point can be obtained by installing a GPS receiver on the train, and the receiver can receive signals from multiple GPS satellites.

[0024] Here, the positioning data includes timestamp, longitude, latitude, speed and travel direction, etc. Among them, the travel direction of the train positioning point at the current observation time can be determined according to the longitude and latitude of the train positioning point at the current observation time and the longitude and latitude of the train positioning point at the previous observation time.

[0025] Step 220, based on the positioning data of the train positioning point at the current observation time, determine a set of candidate sections in the train road network that matches the train positioning point at the current observation time; Here, the train road network is constructed based on the electronic map data points of the heavy-haul railway mentioned above, which will not be described in detail here.

[0026] The train road network is represented by a directed graph G(V, E), A set of route points in an electronic map representing a heavy-haul railway, each of which includes the latitude and longitude of the point and a point number; Represents a set of road segments in an electronic map. Each road segment contains the latitude and longitude of the first and last route points and the point numbers of the first and last route points.

[0027] In one example, the candidate sections close to the train can be found in the train road network according to the longitude and latitude of the train, and the candidate sections that match the train's movement state can be further screened out in combination with the train's travel direction. For example, if the train is traveling eastward, the candidate section should be a railway line extending eastward.

[0028] Step 230, for each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtain a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; Preferably, in this embodiment, a Hidden Markov Model (HMM) is used to obtain the target observation probability and the target transfer probability of the candidate road section matched by the train positioning point at the current observation time.

[0029] It should be understood that the Hidden Markov Model is a statistical model used to describe a Markov process with hidden unknown parameters. It consists of two main components: hidden state and observation. In this embodiment, the hidden state is regarded as the actual position of the candidate road section matched by the train positioning point in the train road network, and the observation is the positioning data of the train positioning point (such as longitude, latitude, speed, etc.).

[0030] Specifically, the target observation probability of the candidate section matched by the train positioning point at the current observation time refers to the probability that the train positioning point appears on this candidate section at the current observation time. In practical applications, it can be calculated by the distance between the train positioning point and the candidate section.

[0031] Specifically, the target transfer probability of the candidate section matched by the train positioning point at the current observation time refers to the probability that the train transfers from the section at the previous observation time to the candidate section at the current observation time. In practical applications, it can be calculated by the distance between the train positioning point at the previous observation time and the train positioning point at the current observation time, and the distance between the projection points of the train positioning point at the previous observation time and the train positioning point at the current observation time on the candidate section.

[0032] Step 240, when the train positioning point at the current observation time reaches the key control point of the section, based on the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the train positioning point of the candidate section at each observation time between the starting observation time and the current observation time, the Viterbi algorithm is applied to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of an entry point, an exit point, a tunnel starting point and an end point, a bridge starting point and an end point, and a kilometer mark.

[0033] It should be understood that the key control points of the road section in this embodiment are specific locations on the road section that are crucial for train positioning and navigation. These points may include the entry point (the location of entering the curve), the exit point (the location of leaving the curve), the starting point and end point of the tunnel, the starting point and end point of the bridge, and the kilometer mark (a key point for marking the distance).

[0034] The Viterbi algorithm is a dynamic programming algorithm used to find the most likely sequence of hidden states (i.e. the most likely path for a train to travel), given a series of observations (i.e. the positioning data of the train at different observation times).

[0035] Specifically, starting from the starting state A of the observation sequence (i.e., the train positioning point at the starting observation time), the joint probability of each candidate section reaching the first state C (the next observation time) is calculated. This joint probability is obtained by multiplying the target observation probability of the candidate section under state C with the target transition probability, and then the candidate section with the largest joint probability is selected as the target candidate section of state C.

[0036] Next, for the second state D (the next observation time), calculate the joint probability of each candidate segment from the starting state A to state D. This joint probability is obtained by multiplying the joint probability of the target candidate segment in the previous state C with the target observation probability and target transition probability of the candidate segment in state D, and then select the candidate segment with the largest joint probability as the target candidate segment in state D.

[0037] After that, all observation moments are traversed from the front to the back, and the steps of the second state D are repeated until the final state E (current observation moment) is traversed. In the final state E (current observation moment), the candidate road segment with the largest joint probability is found as the target candidate road segment of the final state E (current observation moment).

[0038] The train driving section matching method proposed in this embodiment can more accurately match the target candidate section of the train at the current observation time by accurately obtaining the train positioning data and determining the candidate section set based on these data, and then combining the target observation probability and target transfer probability of the train positioning point on the candidate section at the current and historical observation times, especially when the train arrives at the key control point of the section, using the Viterbi algorithm to comprehensively consider all observation data. This not only improves the accuracy and reliability of driving section matching in the complex and changeable line environment of the heavy-duty railway transportation network.

[0039] It should be noted that each implementation method of the present application can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0040] In some embodiments, it also includes: Determine the distance between the train positioning point at the current observation time and the section key control point of the candidate section based on the longitude and latitude in the positioning data of the train positioning point at the current observation time and the longitude and latitude of the section key control point of the candidate section matched by the train positioning point at the current observation time; When the distance is less than or equal to the distance threshold, determining that the train positioning point at the current observation time has arrived at the key control point of the section; When the distance is greater than the distance threshold, it is determined that the train positioning point at the current observation time has not reached the key control point of the section.

[0041] In this embodiment, after obtaining the candidate road section matched by the train positioning point at the current observation time, the distance between the train positioning point and the key control point of the road section in the candidate road section will be calculated, and a distance threshold will be pre-set according to the positioning accuracy of the train, the characteristics of the railway line and the safety requirements. If the distance between the train positioning point and the key control point of the road section is less than or equal to the distance threshold, it is considered that the train has arrived at the key control point of the road section.

[0042] In some embodiments, the determining, based on the positioning data of the train positioning point at the current observation time, a set of candidate sections matching the train positioning point at the current observation time in the train road network includes: Obtaining a grid index table and a section data table matching a train road network, wherein the train road network includes the longitude and latitude of the first and last line points of each section and the point numbers of the first and last line points, the grid index table includes the grid mileage range and section identification corresponding to each grid, and the section data table includes the longitude and latitude and point numbers of the first and last line points corresponding to each section identification; Based on the positioning data of the train positioning point at the current observation time, the grid index table and the section data table are queried to determine a set of candidate sections that match the train positioning point at the current observation time in the train road network.

[0043] Here, the grid index table is used to quickly locate the grid where the train is located, thereby narrowing the scope of subsequent searches. The grid index table is a database table that divides the train road network into multiple grids and assigns a unique identifier to each grid. Each grid records the mileage range it covers and the road segment identifier associated with it.

[0044] The segment data table contains detailed information about all segments in the train road network, including the latitude and longitude data and point numbers of the first and last line points of each segment. The segment identifier is used to establish an association between the grid index table and the segment data table.

[0045] Specifically, the longitude and latitude in the positioning data of the train positioning point at the current observation time are used to search in the grid index table to determine the grid where the train is located and its adjacent grids. Once the grid where the train is located and its adjacent grids are determined, the section data table will be further queried to extract all sections in these grids as candidate sections.

[0046] It should be noted that in this embodiment, when the train road network is divided into multiple grids, reference Figure 3 As shown, the road segments are divided into kilometer markers to improve indexing efficiency. Kilometer markers (or mile markers) are marks used to identify specific locations, usually in kilometers. For example, a kilometer marker may indicate that the distance from the starting point of the route to the point is 5.2 kilometers.

[0047] Specifically, the starting point and the end point of the railway line, as well as the total length of the entire line, can be determined, and then the railway line can be divided into multiple continuous grids according to the kilometer mark. For example, each 1 kilometer or 2 kilometers can be a grid, and each grid will be assigned a unique grid identifier, and the section information and grid distance range associated with the grid.

[0048] The train driving section matching method proposed in this embodiment constructs a grid index table divided step by step by kilometer marks in the train road network in the above manner, thereby improving indexing efficiency, especially when processing a large amount of real-time positioning data, which can significantly improve response speed and processing capacity.

[0049] In some embodiments, the target observation probability of the candidate section matched by the train location point at the current observation time is obtained by: Determining a first observation probability of the candidate section based on the distance between the train positioning point and the candidate section at the current observation time; Determining a second observation probability of the candidate section based on a direction vector of the train positioning point at the current observation time and a direction vector of the candidate section; Based on the first observation probability and the second observation probability of the candidate road segment, a target observation probability of the candidate road segment is determined.

[0050] In this embodiment, when obtaining the target observation probability of the candidate section matching the train positioning point at the current observation time, not only the distance factor between the train positioning point and the candidate section is considered, but also the direction factor between the train positioning point and the candidate section is considered.

[0051] Specifically, the following formula is used to calculate the current observation time under the distance factor: t The train positioning point Candidate sections The first observation probability : ; in, It is the train positioning point and candidate segments The distance between is the standard deviation of the observation noise positioning error, which can usually be taken as 10m.

[0052] Use the following formula to calculate the current observation time under the direction factor t The train positioning point Candidate sections The second observation probability : ; in, It is the train positioning point Direction vector and candidate road segments The cosine value between the direction vectors can reflect the size of the angle θ between the two direction vectors.

[0053] Finally, refer to the following formula to synthesize the first observation probability and the second observation probability , and obtain the target observation probability of the candidate road segment : ; The train driving section matching method proposed in this embodiment improves the accuracy and reliability of driving section matching in the complex and changeable line environment of the heavy-duty railway transportation network by comprehensively considering the distance factor and the direction factor in the target observation probability.

[0054] In some embodiments, the target transition probability of the candidate section matched by the train location point at the current observation time is obtained by: Determine a first transition probability of the candidate section based on a distance between a train positioning point at a current observation time and a train positioning point at a previous observation time, and a distance between a projection point of the train positioning point at the current observation time in the candidate section and the train positioning point at the previous observation time; Determine a second transition probability of the candidate section based on a direction vector between a projection point of a train location point at a current observation time in the candidate section and a starting line point of the candidate section and a direction vector of the candidate section; Based on the first transition probability and the second transition probability of the candidate road segment, a target transition probability of the candidate road segment is determined.

[0055] Similarly, in this embodiment, when obtaining the target transfer probability of the candidate section matched by the train positioning point at the current observation time, not only the distance factor but also the direction factor is considered.

[0056] Specifically, the following formula is used to calculate the current observation time under the distance factor: t The train positioning point Candidate sections The first transition probability : ; in, is the train location point at the current observation time t In the candidate section The projection point on Indicates the train location at the last observation time (t-1) The train location at the current observation time The Euclidean distance between Indicates the train location at the last observation time (t-1) and the train location point at the current observation time t In the candidate section Projection point on The Euclidean distance between .

[0057] Next, determine the current observation time under the direction factor t The train positioning point Candidate sections The second transition probability .

[0058] Specifically, compare whether the direction vector between the projection point of the train positioning point in the candidate section at the current observation time and the starting line point of the candidate section is the same as the direction vector of the candidate section. If they are the same, the second transition probability , otherwise, the second transition probability .

[0059] Finally, refer to the following formula to synthesize the first transition probability and the second transition probability , and obtain the target observation probability of the candidate road segment : ; The train driving section matching method proposed in this embodiment improves the accuracy and reliability of driving section matching in the complex and changeable line environment of the heavy-duty railway transportation network by comprehensively considering the distance factor and the direction factor in the target transfer probability.

[0060] In some embodiments, it also includes: When the train positioning point at the current observation time has not reached the key control point of the section, the target candidate section that matches the train positioning point at the current observation time in the candidate section set is determined based on the target observation probability and the target transfer probability of the candidate section.

[0061] Specifically, when the train positioning point does not reach the key control point of the section, a comprehensive probability is calculated for each candidate section by combining the product of the target observation probability and the target transition probability. Among all the candidate sections, the candidate section with the highest comprehensive probability is selected as the target candidate section.

[0062] Based on any of the above embodiments, the present invention further provides a train driving section matching device, Figure 4 is a schematic diagram of the structure of the train driving section matching device provided by the present invention, such as Figure 4 As shown, the device comprises: The first driving section matching module 410 is used to obtain the positioning data of the train positioning point at the current observation time; A second driving section matching module 420 is used to determine a candidate section set matching the train positioning point at the current observation time in the train road network based on the positioning data of the train positioning point at the current observation time; The third driving section matching module 430 is used to obtain, for each candidate section in the candidate section set matched by the train positioning point at the current observation time, a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; The fourth driving route section matching module 440 is used to apply the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set when the train positioning point at the current observation time reaches the key control point of the section, based on the target observation probability and the target transfer probability of the candidate section, and the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, wherein the key control point of the section includes at least one of the entry point, exit point, tunnel starting point and end point, bridge starting point and end point, and kilometer mark.

[0063] The device provided by the embodiment of the present invention can more accurately match the target candidate section of the train at the current observation time by accurately acquiring the train positioning data and determining the candidate section set based on the data, and then combining the target observation probability and target transfer probability of the train positioning point on the candidate section at the current and historical observation times, and taking all the observation data into consideration by using the Viterbi algorithm, especially when the train arrives at the key control point of the section. This not only improves the accuracy and reliability of the driving section matching in the complex and changeable line environment of the heavy-duty railway transportation network.

[0064] The train driving route section matching device described in this embodiment and the train driving route section matching method provided by the present invention described above can correspond to each other and will not be described in detail here.

[0065] Figure 5An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the train driving section matching method, which includes: Obtain the positioning data of the train positioning point at the current observation time; Based on the positioning data of the train positioning point at the current observation time, determining a set of candidate sections in the train road network that matches the train positioning point at the current observation time; For each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtaining a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; In the case that the train positioning point at the current observation time reaches the key control point of the section, the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, are applied to the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of a turning point, a turning point, a tunnel starting point and end point, a bridge starting point and end point, and a kilometer mark.

[0066] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0067] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the train driving section matching method provided by the above methods, the method includes: Obtain the positioning data of the train positioning point at the current observation time; Based on the positioning data of the train positioning point at the current observation time, determining a set of candidate sections in the train road network that matches the train positioning point at the current observation time; For each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtaining a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; In the case that the train positioning point at the current observation time reaches the key control point of the section, the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, are applied to the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of a turning point, a turning point, a tunnel starting point and end point, a bridge starting point and end point, and a kilometer mark.

[0068] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for matching the driving sections of a train provided by the above methods is implemented, and the method comprises: Obtain the positioning data of the train positioning point at the current observation time; Based on the positioning data of the train positioning point at the current observation time, determining a set of candidate sections in the train road network that matches the train positioning point at the current observation time; For each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtaining a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; In the case that the train positioning point at the current observation time reaches the key control point of the section, the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, are applied to the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of a turning point, a turning point, a tunnel starting point and end point, a bridge starting point and end point, and a kilometer mark.

[0069] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0071] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical coding feature diagrams therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for matching a train driving section, characterized in that: The method comprises: Obtain the positioning data of the train positioning point at the current observation time; Based on the positioning data of the train positioning point at the current observation time, determining a set of candidate sections in the train road network that matches the train positioning point at the current observation time; For each candidate section in the candidate section set matched by the train positioning point at the current observation time, obtaining a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; In the case that the train positioning point at the current observation time reaches the key control point of the section, the target observation probability and the target transfer probability of the candidate section, as well as the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, are applied to the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set, wherein the key control point of the section includes at least one of a turning point, a turning point, a tunnel starting point and end point, a bridge starting point and end point, and a kilometer mark.

2. The train driving section matching method according to claim 1, characterized in that: The target observation probability of the candidate section matched by the train positioning point at the current observation time is obtained in the following way: Determining a first observation probability of the candidate section based on the distance between the train positioning point and the candidate section at the current observation time; Determining a second observation probability of the candidate section based on a direction vector of the train positioning point at the current observation time and a direction vector of the candidate section; Based on the first observation probability and the second observation probability of the candidate road segment, a target observation probability of the candidate road segment is determined.

3. The train driving section matching method according to claim 1, characterized in that: The target transition probability of the candidate section matched by the train location point at the current observation time is obtained in the following way: Determine a first transition probability of the candidate section based on a distance between a train positioning point at a current observation time and a train positioning point at a previous observation time, and a distance between a projection point of the train positioning point at the current observation time in the candidate section and the train positioning point at the previous observation time; Determine a second transition probability of the candidate section based on a direction vector between a projection point of a train location point at a current observation time in the candidate section and a starting line point of the candidate section and a direction vector of the candidate section; Based on the first transition probability and the second transition probability of the candidate road segment, a target transition probability of the candidate road segment is determined.

4. The train driving section matching method according to claim 1, characterized in that: The determining, based on the positioning data of the train positioning point at the current observation time, a set of candidate sections matching the train positioning point at the current observation time in the train road network comprises: Obtaining a grid index table and a section data table matching a train road network, wherein the train road network includes the longitude and latitude of the first and last line points of each section and the point numbers of the first and last line points, the grid index table includes the grid mileage range and section identification corresponding to each grid, and the section data table includes the longitude and latitude and point numbers of the first and last line points corresponding to each section identification; Based on the positioning data of the train positioning point at the current observation time, the grid index table and the section data table are queried to determine a set of candidate sections that match the train positioning point at the current observation time in the train road network.

5. The train driving section matching method according to claim 1, characterized in that: Also includes: Determine the distance between the train positioning point at the current observation time and the section key control point of the candidate section based on the longitude and latitude in the positioning data of the train positioning point at the current observation time and the longitude and latitude of the section key control point of the candidate section matched by the train positioning point at the current observation time; When the distance is less than or equal to the distance threshold, determining that the train positioning point at the current observation time has arrived at the key control point of the section; When the distance is greater than the distance threshold, it is determined that the train positioning point at the current observation time has not reached the key control point of the section.

6. The train driving section matching method according to claim 1, characterized in that: Also includes: When the train positioning point at the current observation time has not reached the key control point of the section, the target candidate section that matches the train positioning point at the current observation time in the candidate section set is determined based on the target observation probability and the target transfer probability of the candidate section.

7. A train driving section matching device, characterized in that: The device comprises: The first driving section matching module is used to obtain the positioning data of the train positioning point at the current observation time; A second driving section matching module is used to determine a candidate section set matching the train positioning point at the current observation time in the train road network based on the positioning data of the train positioning point at the current observation time; A third driving section matching module is used to obtain, for each candidate section in the candidate section set matched by the train positioning point at the current observation time, a target observation probability and a target transfer probability of the candidate section matched by the train positioning point at the current observation time; The fourth driving route section matching module is used to apply the Viterbi algorithm to determine the target candidate section that matches the train positioning point at the current observation time in the candidate section set when the train positioning point at the current observation time reaches the key control point of the section, based on the target observation probability and the target transfer probability of the candidate section, and the target observation probability and the target transfer probability of the candidate section of the train positioning point at each observation time between the starting observation time and the current observation time, wherein the key control point of the section includes at least one of the entry point, exit point, tunnel starting point and end point, bridge starting point and end point, and kilometer mark.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the train driving section matching method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for matching the driving route section of a train as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for matching the driving route section of a train as described in any one of claims 1 to 6 is implemented.

Images