Map matching method, device, computer equipment and storage medium

Abstract

The present application relates to a map matching method, apparatus, computer device, and storage medium. According to the distance between the vehicle position and the previous observation point of the vehicle, as well as the navigation device accuracy factor, an evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range is obtained; and according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point, the state matching probability between each candidate road segment and the vehicle position is determined; then according to the state matching probability between each candidate road segment and the vehicle position, the target matching road segment of the vehicle's driving path in the map is determined. This method eliminates the error caused by the instability of the navigation device during the map matching process, making the final map matching result more accurate.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent transportation, and in particular, to a map matching method, apparatus, computer device, and storage medium. Background Art

[0002] With the development of science and technology and society, the problems of road traffic safety and traffic efficiency have become increasingly prominent, and V2X, as a system solution in vehicle-road cooperation, has been more and more widely promoted.

[0003] Map matching, as a basic support function of V2X, has received more and more attention. Map matching in V2X is a technology that: obtains the node information of the road section where the vehicle is located by performing section matching based on vehicle GPS information and map information. Specifically, map matching is to match the longitude, latitude, heading angle, speed, etc. in the vehicle GPS with the upstream and downstream node relationships, node longitude, node latitude, etc. of multiple nodes in the map information to obtain the unique matching road section of the vehicle in the map.

[0004] However, in actual applications, the GPS information is not stable enough, resulting in inaccurate results of the map matching method. Summary of the Invention

[0005] Based on this, it is necessary to provide a map matching method, apparatus, computer device, and storage medium for the above technical problems, which can improve the accuracy of the final map matching result.

[0006] In a first aspect, the embodiments of the present application provide a map matching method, which includes:

[0007] Obtain the evaluation matching probability between the vehicle position and at least one candidate road section in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device accuracy factor;

[0008] Determine the state matching probability between each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the historical matching road section of the previous observation point to each candidate road section, and the historical state matching probability of the historical matching road section of the previous observation point;

[0009] Determine the target matching road section of the vehicle's driving path in the map according to the state matching probability between each candidate road section and the vehicle position.

[0010] In one of the embodiments, the above step of obtaining the evaluation matching probability between the vehicle position and at least one candidate road section in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device accuracy factor, includes:

[0011] Obtain the distribution information of the distance between the vehicle position and the previous observation point, and regularize the dilution of precision of the navigation device;

[0012] Determine the evaluation matching probability of each candidate road section according to the distribution information of the distance between the vehicle position and the previous observation point and the dilution of precision of the navigation device after regularization.

[0013] In one embodiment, the method further includes:

[0014] Obtain the map network topology relationship between the historical matching road section of the previous observation point and each candidate road section;

[0015] Determine the state transition probability from the historical matching road section of the previous observation point to each candidate road section according to the map network topology relationship.

[0016] In one embodiment, the above determining the state transition probability from the historical matching road section of the previous observation point to each candidate road section according to the map network topology relationship includes:

[0017] For any candidate road section:

[0018] If the map network topology relationship is that the candidate road section is the same road section as the historical matching road section, determine that the transition probability is a preset first value;

[0019] If the map network topology relationship is that the candidate road section is the next road section of the historical matching road section, determine that the transition probability is a preset second value.

[0020] In one embodiment, the method further includes:

[0021] Obtain the initial state matching probability values of the initial observation point of the vehicle to each initial candidate road section in the target map search range;

[0022] Determine the historical state matching probability of the historical matching road section of the previous observation point according to the initial state matching probability values.

[0023] In one embodiment, the above obtaining the initial state matching probability values of the initial observation point to each candidate road section in the target map search range includes:

[0024] Determine the projection point ratio evaluation value of each initial candidate road section according to the ratio information of the projection points of the initial observation point in each initial candidate road section;

[0025] Determine the distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section;

[0026] Determine the angle evaluation value of each initial candidate road section according to the included angle information between the driving direction of the initial observation point and the direction of each initial candidate road section;

[0027] Determine the initial state matching probability values of each initial candidate road segment according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate road segment.

[0028] In one embodiment, determining the historical state matching probability of the historical matching road segment of the previous observation point according to the initial state matching probability value includes:

[0029] Taking the state matching probability values of the candidate road segments of the initial observation point as the starting values, and determining the historical state matching probability of the historical matching road segment of the next observation point in sequence according to the observation point order of the vehicle's driving path until the previous observation point of the vehicle position is determined, so as to obtain the historical state matching probability of the historical matching road segment of the previous observation point.

[0030] In one embodiment, determining the target matching road segment of the vehicle's driving path on the map according to the state matching probability between each candidate road segment and the vehicle position includes:

[0031] Determine the sequence road segment composed of the candidate road segment corresponding to the maximum state matching probability value and the vehicle's historical trajectory as the target matching road segment of the vehicle's driving path on the map.

[0032] In a second aspect, an embodiment of the present application provides a map matching device, which includes:

[0033] An acquisition module, configured to acquire the evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device accuracy factor;

[0034] A determination module, configured to determine the state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point;

[0035] A matching module, configured to determine the target matching road segment of the vehicle's driving path on the map according to the state matching probability between each candidate road segment and the vehicle position.

[0036] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method steps of any one of the embodiments in the first aspect are implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method steps of any one of the embodiments in the first aspect are implemented.

[0038] A map matching method, device, computer device, and storage medium provided by an embodiment of the present application obtain an evaluation matching probability between a vehicle position and at least one candidate road segment in a target map search range according to the distance between the vehicle position and the previous observation point of the vehicle and the horizontal dilution of precision (HDOP) of a navigation device; and determine a state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point; then determine a target matching road segment of the driving path of the vehicle in the map according to the state matching probability between each candidate road segment and the vehicle position. In this method, by combining the HDOP of the navigation device and the distance between the vehicle position and the previous observation point of the vehicle, which are two position points of the navigation device, the evaluation matching probability of each candidate road segment is determined. In this way, since the influence brought by the HDOP is considered in the map matching process, that is, the error caused by the instability of the navigation device is eliminated in the map matching process, the final map matching result is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 FIG. is an application environment diagram of a map matching method provided in an embodiment;

[0040] Figure 2 FIG. is a schematic flowchart of a map matching method provided in an embodiment;

[0041] Figure 3 FIG. is a schematic flowchart of a map matching method provided in another embodiment;

[0042] Figure 4 FIG. is a schematic flowchart of a map matching method provided in another embodiment;

[0043] Figure 5 FIG. is a schematic flowchart of a map matching method provided in another embodiment;

[0044] Figure 6 FIG. is a schematic flowchart of a map matching method provided in another embodiment;

[0045] Figure 7 FIG. is a schematic diagram of the projection relationship between a path and a vehicle position provided in an embodiment;

[0046] Figure 8 FIG. is a flowchart of a map matching method provided in an embodiment;

[0047] Figure 9 FIG. is a structural block diagram of a map matching device provided in an embodiment;

[0048] Figure 10Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The map matching method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the processor in the computer device is used to provide computing and control capabilities; the memory includes a non-volatile storage medium and an internal memory; the non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the database of the computer device is used to store relevant data in the map matching process. The network interface of the computer device is used to communicate with other external devices through a network connection. Among them, the computer device can be installed in a vehicle, and it can be, but is not limited to, an in-vehicle navigation device or a personal computer, a laptop computer, a smart phone, a tablet computer, a portable wearable device, etc. with an in-vehicle navigator built in. Of course, the computer device can also be a server, and the server realizes map matching by performing wired or wireless communication with a navigation instrument in the vehicle.

[0051] Next, the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be specifically described through embodiments and in combination with the accompanying drawings. The following several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. It should be noted that when the map matching method provided by the embodiments of the present application is described below, the execution subject is described as a computer device. To make the objectives, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments.

[0052] In one embodiment, as Figure 2 shown, a map matching method is provided. This embodiment relates to the specific process of obtaining the evaluation matching probability of candidate road segments by combining the distance between the current position of the vehicle and the previous observation point and the accuracy factor of the navigation device on the vehicle, and determining the state matching probability between each candidate road segment and the vehicle position based on the evaluation matching probability, the state transition probability from the previous observation to each candidate road segment, and the historical state matching probability of the previous observation point, and finally determining the target matching road segment; this embodiment includes the following steps:

[0053] S101. Obtain the evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device precision factor.

[0054] The vehicle position is the current position point of the vehicle, and the specific information of the current position point can be determined by the navigation device in the vehicle. For example, the longitude, latitude, and heading angle information of the vehicle can be obtained through a GPS navigator.

[0055] The current moment point corresponding to the current position point can be regarded as the current observation point, and the previous observation point is the moment point when the vehicle was last matched with a road segment. For the previous observation point, the road segment matching has been completed, and the position information of the vehicle at the previous observation point can also be obtained in the navigation device. Therefore, the position of the vehicle at the previous observation point is known. Then, the distance between the two can be determined based on the current position point of the vehicle and the position of the vehicle at the previous observation point. Therefore, the distance between the vehicle position (current observation point) and the previous observation point (vehicle position) essentially reflects the change between two GPS sampling points.

[0056] Generally, in the actual application of map matching, due to hardware problems or algorithm problems, the obtained GPS information is not stable enough. Therefore, it is necessary to comprehensively consider multiple vehicle position points to determine the final matching result. And since there must be some connection between the information in a time series, that is, in the sequence of vehicle position points determined by GPS, the connection between each position point is related to the horizontal dilution of precision (HDOP) of GPS. Among them, HDOP is the square root of the sum of the squares of errors such as latitude and longitude. The magnitude of the HDOP value is positively correlated with the GPS positioning error. The larger the HDOP value, the greater the GPS positioning error, and the lower the GPS positioning accuracy. Therefore, the HDOP of GPS for a period of time can affect the final matching result. Based on this, in the embodiments of the present application, the distance between the vehicle position and the previous observation point of the vehicle is combined with the navigation device precision factor to jointly determine the evaluation matching probability between the vehicle position and each candidate road segment, which can make the evaluation matching probability between each candidate road segment and the vehicle position more accurate. This evaluation matching probability is the probability of the preliminary evaluation of each candidate road segment matching the vehicle position.

[0057] Among them, each candidate road segment refers to a road segment within the target map search range, and the target map search range refers to the possible range of the vehicle's current driving path on the map. That is, any road segment within the target map search range may be a matching road segment of the vehicle's current driving path. The target map search range is determined in advance. For example, based on the vehicle's historical driving data (including but not limited to trajectory, driving time, driving speed, etc.) and combined with the vehicle's current driving moment, the vehicle's current preliminary position is determined first, and then the target map search range is determined on the map according to the preliminary position. The embodiments of the present application do not limit the determination method of the target map search range; alternatively, according to the position obtained by the vehicle's GPS positioning, a range is determined with this position as the center, and this range can be used as the target map search range.

[0058] For any candidate road segment, for example, the evaluation matching probability between it and the vehicle position can be determined through a preset neural network model, that is, the distance between the vehicle position and the previous observation point and the accuracy factor of the navigation device are used as input data and input into the trained neural network model, and the output obtained is the evaluation matching probability between the candidate road segment and the vehicle position. Or, the distance from the vehicle position to the previous observation point and the distance from the vehicle position to the candidate road segment can be combined, and the difference between these two distances is combined with the accuracy factor of the navigation device to comprehensively determine the evaluation matching probability from the candidate road segment to the vehicle position. The embodiments of the present application do not limit this. Among them, the accuracy factor of the navigation device can be directly obtained from the navigation device.

[0059] S102. Determine the state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point.

[0060] After obtaining the evaluation matching probability of each candidate road segment, it is also necessary to further obtain the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point.

[0061] In map matching, there is a certain association between the state at time T and the state at time T + 1. For example, the positions at adjacent times are necessarily related to the speed, which conforms to the basic characteristics of the hidden Markov model. For the initial positioning results at different times, there is also a certain probability that the initial positioning result at the previous time transitions from a certain state to a certain state of the initial positioning result at the next time. This probability is the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment. Therefore, this state transition probability is determined from the dimension of the state connection between adjacent observation points and can reflect the possibility of each candidate road segment being the target matching road segment.

[0062] The historical matching section of the previous observation point refers to the final matching section I that has been completed in the previous match. F Therefore, the historical state matching probability of the historical matching section refers to the probability that when the final matching section I has not been determined during the previous map matching. F At that time, for section I F the state matching probability. For section I F the state matching probability, when it has not been determined that I F is the final matching section, it represents the probability value of section I from the dimension of state information (such as distance, included angle, projection information, etc.) being the final matching section. F

[0063] For example, when determining the state matching probability between each candidate section and the vehicle position based on the evaluation matching probability of each candidate section, the state transition probability from the historical matching section of the previous observation point to each candidate section, and the historical state matching probability of the historical matching section of the previous observation point, the product of the three can be used as the state matching probability between each candidate section and the vehicle position, or the sum or weighted sum of the three can be used as the state matching probability between each candidate section and the vehicle position, etc. The embodiments of the present application do not limit this.

[0064] For example, taking the product as an example, let P N (seg i ) represent the state matching probability of candidate section i at the vehicle position (current observation point); P N-1 (seg i ) represent the historical state matching probability of historical matching section i (final matching section) at the previous observation point; P topo (seg i ) represent the state transition probability from the historical matching section of the previous observation point to candidate section i at the vehicle position (current observation point); P cvt (seg i ) represents the evaluation matching probability of candidate section i at the vehicle position; then P N (seg i ) = P N-1 (seg i ) · P topo (seg i ) · P cvt (seg i ).

[0065] S103. Determine the target matching section of the vehicle's driving path on the map according to the state matching probability between each candidate section and the vehicle position.

[0066] ​After determining the state matching probability between each candidate road segment and the vehicle position, based on this, determine the target matching road segment of the vehicle's driving path in the map.

[0067] In one embodiment, the candidate road segment corresponding to the maximum state matching probability value and the sequential road segment formed by the vehicle's historical trajectory are determined as the target matching road segment of the vehicle's driving path in the map.

[0068] After all candidate road segments have been traversed, find the candidate road segment with the largest state matching probability value, and then find the candidate road segment corresponding to this largest state matching probability value as the road segment that best matches the current observation point. Then, the candidate road segment corresponding to the largest state matching probability value and the sequential road segment formed by the historical matching road segments that have been completed in the past are determined as the target matching road segment of the vehicle's driving path in the map. Equivalently, looking at it from the initial observation point to the current observation point, the candidate road segment with the largest state matching probability value at each observation point is the target candidate road segment corresponding to the observation point. In this way, the road segment formed by the target candidate road segments determined corresponding to each observation point can be called the target matching road segment of the vehicle's driving path in the map.

[0069] The embodiment of the present application provides a map matching method. According to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device accuracy factor, obtain the evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range; and according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point, determine the state matching probability between each candidate road segment and the vehicle position; then according to the state matching probability between each candidate road segment and the vehicle position, determine the target matching road segment of the vehicle's driving path in the map. In this method, by combining the navigation device accuracy factor HDOP and the distance between the vehicle position and the previous observation point of the vehicle, which are two navigation device position points, the evaluation matching probability of each candidate road segment is determined. In this way, since the influence brought by HDOP is considered in the map matching process, that is, the error caused by the instability of the navigation device is eliminated during the map matching process, the final map matching result is more accurate.

[0070] Based on the above embodiment, an embodiment is provided below to illustrate the determination process of the evaluation matching probability of each candidate road segment. As Figure 3 shown, in one embodiment, this embodiment includes:

[0071] S201, obtain the distribution information of the distance between the vehicle position and the previous observation point, and perform regularization processing on the navigation device accuracy factor.

[0072] The distribution information of the distance between the vehicle position and the previous observation point can be a Gaussian distribution (normal distribution), etc. For example, a Gaussian distribution is established based on the difference between the distance from the vehicle position to the previous observation point and the distance from the vehicle position to the candidate road segment: d I is the distance from the vehicle position to the previous observation point, and d i is the distance from the vehicle position to candidate road segment i, μ is the expected value of the distribution, usually taking the value of 0, and σ is the standard deviation parameter, which determines the amplitude of the distribution, usually taking the value of 4.07.

[0073] After obtaining the dilution of precision (DOP) of the navigation device, it is regularized to reduce errors. For example, where γ is the regularization parameter, usually taking values from 2 to 6, which is used to control the balance relationship between two different objectives, that is, to balance the objective of fitting training and the objective of keeping the parameter values small.

[0074] S202. Determine the evaluation matching probability of each candidate road segment according to the distribution information of the distance between the vehicle position and the previous observation point and the regularized DOP of the navigation device.

[0075] According to the above distribution information of the distance between the vehicle position and the previous observation point and the regularized DOP of the navigation device, the sum of the two is determined as the evaluation matching probability of the candidate road segment. For example, the evaluation matching probability of candidate road segment i is expressed as P cvt (seg i ), then:

[0076] In this embodiment, by obtaining the distribution information of the distance between the vehicle position and the previous observation point, regularizing the DOP of the navigation device, and then determining the evaluation matching probability of each candidate road segment according to the distribution information of the distance between the vehicle position and the previous observation point and the regularized DOP of the navigation device, in this way, the evaluation matching probability of the candidate road segment is determined according to the HDOP and the distance, that is, the influence of HDOP on the candidate road segment as the final target matching road segment is considered, and when considering HDOP, it is regularized, making its measurement error even smaller, thereby improving the accuracy of the evaluation matching probability.

[0077] The probabilities of the above state transition probability and historical state matching probability are described below through an embodiment. Then in one embodiment, an implementation manner for determining the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment is provided, as Figure 4 shown. This embodiment includes:

[0078] S301. Obtain the map network topology relationship between the historical matching road segment of the previous observation point and each candidate road segment.

[0079] Among them, the map network topology relationship is the connection relationship between each road in the map. For example, information such as the orientation of each road, the intersection points with other roads, the distance, and the physical space distribution. Here, it refers to the topological relationship between the historical matching section determined by the previous observation point and each candidate section of the current observation point. For example, if the historical matching section is section AB, and the candidate sections of the current observation point include section CD and section EF, then the topological relationship between the historical matching section and each candidate section can be that section CD is the downstream section of section AB, and section EF is the upstream section of section AB, etc. In addition to the upstream and downstream sections, it can also be the current section belonging to the historical matching section, and the lanes on the current section, such as the current lane, other lanes, etc. The embodiments of the present application do not limit the topological relationship, and it can also include other connection relationships and spatial distribution relationships.

[0080] Specifically, according to the road relationships stored in the electronic map, as well as the positions of the historical matching section and the candidate sections in the map itself, the map network topology relationship between the historical matching section and each candidate section can be determined.

[0081] S302. According to the map network topology relationship, determine the state transition probability from the historical matching section of the previous observation point to each candidate section.

[0082] After determining the map network topology relationship between the historical matching section of the previous observation point and each candidate section, in combination with this map network topology relationship, determine the state transition probability from the historical matching section of the previous observation point to each candidate section.

[0083] In one implementation, taking any candidate section as an example, the map network topology relationship includes: the candidate section is the same section as the historical matching section, and the candidate section is the next section of the historical matching section. Taking these two relationships as examples for explanation. Then, the method for determining the state transition probability from the historical matching section of the previous observation point to each candidate section according to the map network topology relationship includes:

[0084] If the map network topology relationship is that the candidate section is the same section as the historical matching section, then determine the transition probability as a preset first value; if the map network topology relationship is that the candidate section is the next section of the historical matching section, then determine the transition probability as a preset second value.

[0085] For the candidate section being the same section as the historical matching section, it means that the candidate section and the historical matching section that was successfully matched at the previous observation point are the same section, that is, the vehicle has not yet driven out of the section where it was traveling at the previous observation point; while the candidate section being the next section of the historical matching section means that the vehicle has driven out of the historical matching section of the previous observation point and reached the downstream section.

[0086] Exemplarily, let Ptopo (seg i ) represents the state transition probability of candidate road segment i. Let I represent the historical matching road segment. Then, according to It can be determined that if the candidate road segment is the same road segment as the historical matching road segment, the transition probability is determined to be a preset first value, that is, 0.5. However, if the candidate road segment is the next road segment of the historical matching road segment, the transition probability is determined to be a preset second value, that is, 0.2. And if the topological relationship between the candidate road segment and the historical matching road segment is not one of the above two, its transition probability is determined to be 0, indicating that candidate road segment i cannot be the target matching road segment of the current observation point.

[0087] In this embodiment, the map network topological relationship between the historical matching road segment of the previous observation point and each candidate road segment is obtained. According to the map network topological relationship, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment is determined. Since the map network topological relationship reflects the positional relationship between road segments, and the state transition probability is determined based on the geographical location, the state transition probability can more accurately reflect the possibility of each candidate road segment being the target matching road segment.

[0088] In another embodiment, an implementation manner for determining the historical state matching probability of the historical matching road segment of the previous observation point is provided. As Figure 5 shown, this embodiment includes the following steps:

[0089] S401, obtain the initial state matching probability values of each initial candidate road segment from the initial observation point of the vehicle to the target map search range.

[0090] The initial observation point is the moment when map matching starts. At the initial observation point, each initial candidate road segment has an initial state matching probability value. For example, there are three road segments I1, I2, and I3 in the target map search range, and these three road segments are all initial candidate road segments of the initial observation point. The initial position of the vehicle (the position corresponding to the initial observation point) can also be located to specific position information through the navigation device. Then, according to the initial position of the vehicle and the road segment information (such as direction, position, etc.) of the initial candidate road segments I1, I2, and I3, the matching degrees of the initial candidate road segments I1, I2, and I3 with the initial position of the vehicle can be determined, and this matching degree can be regarded as the initial state probability values of the initial candidate road segments I1, I2, and I3.

[0091] S402, determine the historical state matching probability of the historical matching road segment of the previous observation point according to the initial state matching probability values.

[0092] Based on the initial state matching probability values of each initial candidate road segment that have been determined, determine the historical state probability value of the historical matching road segment of the previous observation point. The previous observation point is defined relative to the current observation point. For example, if the initial observation point is T0 and the current observation point is Tn, then the previous observation point is Tn - 1. Assuming n = 5, the previous observation point is T4. Therefore, after determining the initial state matching probability values of the initial candidate road segments of the initial observation point T0, and then determining them sequentially for the next observation point, the state matching probabilities of each candidate road segment of the previous observation point T4 can be determined.

[0093] Optionally, according to the initial state matching probability values, determine the historical state matching probability of the historical matching road segment of the previous observation point, including: using the state matching probability values of each candidate road segment of the initial observation point as the starting values, and sequentially determining the historical state matching probability of the historical matching road segment of the next observation point according to the order of the observation points of the vehicle's driving path until the previous observation point of the vehicle's position is determined, so as to obtain the historical state matching probability of the historical matching road segment of the previous observation point.

[0094] Let P1 (state matching probability of the Tn observation point) = P2 (state matching probability of the Tn - 1 observation point) * P3 (transition state probability from the Tn - 1 observation point to the Tn observation point) * P4 (evaluation matching probability of the Tn observation point);

[0095] Then when n = 1, substitute the initial state matching probability value P2 of the initial candidate road segment of the initial observation point T0, the transition state probability P3 from the initial observation point T0 to the T1 observation point, and the evaluation matching probability P4 of the T1 observation point into this formula in sequence to determine the state matching probability P1 of the T1 observation point. By analogy, the state matching probability P1 of the T2 observation point can be determined until the state matching probability of the T4 observation point is determined, and then the state matching probability of the previous observation point is obtained, which is the historical state matching probability of the historical matching road segment. It should be noted that when calculating, it is calculated in units of road segments. Each observation point has at least one candidate road segment, so the state matching probability is naturally the state matching probability value of each candidate road segment.

[0096] In this embodiment, obtain the initial state matching probability values of each initial candidate road segment from the initial observation point of the vehicle to the target map search range, and then determine the historical state matching probability of the historical matching road segment of the previous observation point according to the initial state matching probability values; starting from the initial observation point as the starting point, calculate the historical matching road segments from the initial observation point to the previous observation point of the current observation point in sequence. The adjacent observation points are interconnected, so that the historical state matching probability of the historical matching road segment of the previous observation point can be obtained more accurately.

[0097] Such as Figure 6As shown, in one embodiment, the process of obtaining the initial state matching probability values of each candidate road segment from the initial observation point to the target map search range includes:

[0098] S501. Determine the projection point ratio evaluation value of each initial candidate road segment according to the ratio information of the projection points of the initial observation point in each initial candidate road segment.

[0099] The ratio information refers to the proportion of the vehicle's position in the entire road segment. Therefore, the form of the ratio information can be a percentage, a proportion, etc., which is not limited in the embodiments of the present application. Therefore, the ratio information of the projection points of the vehicle's position of the initial observation point in each initial candidate road segment refers to the percentage R of the projection point of the vehicle's position of the initial observation point in the road segment. For example, if a road segment is 10 meters long and the projection point of the vehicle's position of the initial observation point is at 5 meters of the road segment, then the ratio information is 50%. After determining the ratio information, the ratio information can be directly determined as the projection point ratio evaluation value of any road segment i.

[0100] In addition, the projection point of the vehicle's position (in this embodiment, the vehicle position refers to the vehicle position of the initial observation point and will not be repeated) may fall outside the road segment. For example, please refer to Figure 7 As shown, P is the vehicle's position, and P' is the projection point of the vehicle on the road segment AB. For this case, the projection point ratio evaluation value of each initial candidate road segment can be determined according to the projection line segment information. Specifically, Figure 7 In, BP' is the projection line segment. If P' is inside the line segment AB, the length of the projection line segment takes a positive value; otherwise, it takes a negative value, and when it is outside the line segment, the connection line between the projection point and the nearest point on AB is the projection line segment.

[0101] Let the projection line segment information be R i , then Based on this formula, the projection line segment information R of any road segment i in each initial candidate road segment can be determined i , determine the projection line segment information R of these initial candidate road segments i The maximum value R in max , and use the ratio of the projection line segment information R of any road segment i i to the maximum value R max as the projection information of any road segment i Then

[0102] After determining the projection information , the projection information can be directly determined as the projection point ratio evaluation value of any road segment i, that is

[0103] S502. Determine the distance evaluation values of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section.

[0104] Among them, the distance information may be the vertical distance d from the vehicle to each initial candidate road section; for example, if the point where the vehicle is located is P and the road section is L, then the distance information is the vertical distance from point P to road section L. Optionally, the algorithm for obtaining the distance information from the vehicle to each initial candidate road section may be any one of the algorithms using Euclidean distance, Chebyshev distance, Manhattan distance, Fréchet distance, Hausdorff distance, Hamming distance, LCS distance, DTW distance, and the embodiments of the present application do not limit this either.

[0105] Exemplarily, a way to determine the distance evaluation value of each initial candidate road section is as follows: Let the current position of the vehicle be P and any historical position of the vehicle be Q, then QP is the driving direction of the vehicle. A and B are path points on any initial candidate road section, and its direction is from A to B; P' is the projection of P on AB; then P' = A + (B - A) × t, where t is the ratio of the length of AP' to AB, and its calculation formula is Determine the distance D from vehicle P to road section AB according to P' and P i Among them, D i = |P - P i '|, where the subscript i here is the label of any road section, for example, it refers to the label of road section AB here.

[0106] Calculate the distance D from the vehicle to each initial candidate road section according to this method i , and then determine the minimum distance D among the distances from the vehicle to all road sections min , then the distance information from the vehicle to road section i The calculation formula is In this formula, G is an adjustable parameter of the log model. According to the V2X communication distance limit, the usual value of G is 10.

[0107] After determining the distance information from the vehicle to road section i , the distance evaluation value of any road section i is

[0108] S503. Determine the angle evaluation values of each initial candidate road section according to the included angle information between the driving direction of the initial observation point and the direction of each initial candidate road section.

[0109] Among them, the included angle information can reflect the positional relationship between the vehicle and each initial candidate road section. The included angle information refers to the included angle A between the vehicle driving direction and the road section direction. Among them, the method of obtaining the included angle information between the vehicle and each initial candidate road section can be determined through a neural network model or through a geometric algorithm. For example, if it is determined through a neural network model, a neural network model needs to be pre-trained in advance. The input of this neural network model is the current position of the vehicle, the vehicle driving direction, and the coordinate position of the initial candidate road section; the output is the included angle information between the vehicle and each initial candidate road section.

[0110] Optionally, an implementation method for obtaining the included angle information between the vehicle and each initial candidate road section includes: obtaining the supplementary angle value of the included angle of each initial candidate road section according to the included angle formed by the current position of the vehicle and each initial candidate road section; determining the ratio between the supplementary angle value of the included angle of each initial candidate road section and the largest supplementary angle value among the supplementary angle values of each included angle as the included angle information between the vehicle and each initial candidate road section.

[0111] The included angle formed by the current position of the vehicle and each initial candidate road section refers to ∠PAB in the triangle formed by the line segment connecting the two endpoints AB of any initial candidate road section i at the current position point P of the vehicle. i , which can be represented by H' i , that is, H' i is the included angle formed by the vehicle P and the road section AB. According to this included angle, the angle value of the supplementary angle of this included angle needs to be obtained. Then, for each initial candidate road section, the angle value of the supplementary angle of the included angle formed by the vehicle and it needs to be obtained.

[0112] Let H i be the supplementary angle of the included angle formed by the vehicle and the road section AB, then H i = 180 - H' i . Among them, the included angle H' i formed by the vehicle P and the road section AB can be calculated according to the included angle formed by the road section AB and the due north direction and the included angle (heading angle) formed by the vehicle and the due north direction.

[0113] Specifically, let be the included angle formed by the road section AB and the due north direction , ∠Veh be the included angle formed by the vehicle and the due north direction. Among them, the cosine value of obtaining is:

[0114] Then, That is, if the difference from ∠Veh is greater than 180 degrees, then the included angle H' i formed by the vehicle P and the road section AB is 360 degrees minus The difference from ∠Veh; otherwise, the included angle H' formed by vehicle P and road section AB i is the difference from ∠Veh.

[0115] After determining the supplementary angle values of the included angles of each initial candidate road section, the ratio between the supplementary angle value of the included angle of each initial candidate road section and the largest supplementary angle value among all the initial candidate road sections is determined as the included angle information of the vehicle and each initial candidate road section.

[0116] For example, H i is the size of the supplementary angle of the included angle formed by the vehicle and initial candidate road section i, H max is the largest included angle among the included angles of all initial candidate road sections, is the included angle information of initial candidate road section i, then

[0117] Similarly, for any road section i among each initial candidate road section, the included angle information can be calculated in this way, so as to obtain the included angle information of the vehicle and each initial candidate road section.

[0118] After determining the included angle information of any road section i the included angle information can be directly determined as the included angle evaluation value of any road section i, that is

[0119] Since the included angle information itself can also reflect the positional relationship between the vehicle and each initial candidate road section, in the embodiments of the present application, taking the included angle information as one of the factors for the matching evaluation value of each initial candidate road section can greatly increase the accuracy of the matching evaluation value of each initial candidate road section.

[0120] In addition, since the diagonal information can also reflect the distance between the vehicle and each initial candidate road section, in the embodiments of the present application, the diagonal information can also be taken as one of the factors for the matching evaluation value of each initial candidate road section, which can greatly increase the accuracy of the matching evaluation value of each initial candidate road section.

[0121] For example, according to the diagonals formed by the current position of the vehicle and each initial candidate road section, the diagonal angle values of each initial candidate road section can be obtained; the ratio between the diagonal angle value of each initial candidate road section and the largest diagonal angle value among the diagonal angle values is determined as the diagonal information of the vehicle and each initial candidate road section; the diagonal information of the vehicle and each initial candidate road section is determined as the diagonal evaluation value of each initial candidate road section.

[0122] Among them, the diagonal formed by the current position of the vehicle and each initial candidate section is equivalent to the diagonal of the median line of the triangle formed by a point and a line. For example, if the current position of the vehicle is point P, and the two endpoints of any initial candidate section i are A and B, then in the triangle formed by the two endpoints A and B of section i and the vehicle point P, the diagonal of section AB is ∠APB i .

[0123] Exemplarily, taking the initial candidate section i as an example, obtain ∠APB i The angular value A i of can be determined according to cos(∠APB i ), where then where rad To deg represents converting arccos(cos(∠APB i )) into the corresponding value in angular measure units, that is, calculating arccos(cos(∠APB i )) * 180 / π.

[0124] After determining the diagonal angular values of each initial candidate section, the ratio between the diagonal angular value of each initial candidate section and the largest diagonal angular value among all the initial candidate sections is determined as the diagonal information of the vehicle and each initial candidate section. For example, A i The magnitude of the diagonal angular value of the initial candidate section i, A max is the largest diagonal angular value among all the initial candidate sections, represents the diagonal information of the initial candidate section i, then

[0125] After determining the diagonal information of any section i the diagonal information can be directly determined as the diagonal evaluation value of any section i, that is

[0126] S504. Determine the initial state matching probability value of each initial candidate section according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate section.

[0127] After determining the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate section, the initial state matching probability value of each initial candidate section can be determined according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate section.

[0128] Let the initial state matching probability value be denoted as P cond (d i ,A i ,R i |Seg i), where i is any initial candidate road segment, then P cond (d i , A i , R i |Seg i ) = E(d i |Seg i ) + E(H i |Seg i ) + E(R i |Seg i ). Of course, if the diagonal evaluation value E(A i |Seg i ) is also obtained above, then E(A i |Seg i ) can also be added to the initial state matching probability value. This application embodiment does not make a limitation on this.

[0129] In the embodiments of this application, by determining the projection point ratio evaluation value of each initial candidate road segment, the distance evaluation value of each initial candidate road segment, and the included angle evaluation value of each initial candidate road segment; then according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate road segment, the initial state matching probability of each initial candidate road segment is determined. By evaluating the initial state matching probability of each initial candidate road segment, the probability value that each initial candidate road segment may be the target matching road segment can be accurately estimated, so that the initial state matching probability of each final determined initial candidate road segment is more accurate.

[0130] As Figure 8 shown, in one embodiment, a map matching method is further provided. This method includes:

[0131] S1. Obtain the distribution information of the distance between the vehicle position and the previous observation point, and perform regularization processing on the navigation device accuracy factor.

[0132] S2. Determine the evaluation matching probability of each candidate road segment according to the distribution information of the distance between the vehicle position and the previous observation point and the regularized navigation device accuracy factor.

[0133] S3. Obtain the map network topology relationship between the historical matching road segment of the previous observation point and each candidate road segment.

[0134] S4. For any candidate road segment, if the map network topology relationship is that the candidate road segment is the same road segment as the historical matching road segment, then determine that the transition probability is a preset first value; if the map network topology relationship is that the candidate road segment is the next road segment of the historical matching road segment, then determine that the transition probability is a preset second value.

[0135] S5. Determine the projection point ratio evaluation value of each initial candidate road section according to the ratio information of the projection points of the initial observation point in each initial candidate road section; determine the distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section; determine the angle evaluation value of each initial candidate road section according to the included angle information between the driving direction of the initial observation point and the direction of each initial candidate road section.

[0136] S6. Determine the initial state matching probability value of each initial candidate road section according to the projection point ratio evaluation value, distance evaluation value, and angle evaluation value of each initial candidate road section.

[0137] S7. Take the state matching probability value of each candidate road section of the initial observation point as the starting value, and sequentially determine the historical state matching probability of the historical matching road section of the next observation point according to the observation point order of the vehicle's driving path until the previous observation point of the vehicle position is determined, and obtain the historical state matching probability of the historical matching road section of the previous observation point.

[0138] S8. Determine the state matching probability between each candidate road section and the vehicle position according to the evaluation matching probability of each candidate road section, the state transition probability from the historical matching road section of the previous observation point to each candidate road section, and the historical state matching probability of the historical matching road section of the previous observation point.

[0139] S9. Determine the target matching road section of the vehicle's driving path on the map as the sequence road section composed of the candidate road section corresponding to the maximum state matching probability value and the vehicle's historical trajectory.

[0140] In this embodiment, the implementation principles and technical effects of each step are similar to those in the above method embodiment, and will not be elaborated here.

[0141] It should be understood that although the steps in the flowchart of the above embodiment are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowchart of the above embodiment may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0142] In one embodiment, as Figure 9 shown, a map matching device is provided, which includes: an acquisition module 10, a determination module 11, and a matching module 12, where:

[0143] An acquisition module 10, configured to obtain an evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device dilution of precision;

[0144] A determination module 11, configured to determine a state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point;

[0145] A matching module 12, configured to determine a target matching road segment of the driving path of the vehicle in the map according to the state matching probability between each candidate road segment and the vehicle position.

[0146] In one embodiment, the above acquisition module 10 includes:

[0147] A processing unit, configured to obtain distribution information of the distance between the vehicle position and the previous observation point, and perform regularization processing on the navigation device dilution of precision;

[0148] A determination unit, configured to determine the evaluation matching probability of each candidate road segment according to the distribution information of the distance between the vehicle position and the previous observation point and the navigation device dilution of precision after regularization processing.

[0149] In one embodiment, the device further includes:

[0150] A relationship determination module, configured to obtain the map network topology relationship between the historical matching road segment of the previous observation point and each candidate road segment;

[0151] A probability determination module, configured to determine the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment according to the map network topology relationship.

[0152] In one embodiment, the above probability determination module is specifically configured to: for any candidate road segment:

[0153] If the map network topology relationship is that the candidate road segment is the same road segment as the historical matching road segment, determine that the transition probability is a preset first value; if the map network topology relationship is that the candidate road segment is the next road segment of the historical matching road segment, determine that the transition probability is a preset second value.

[0154] In one embodiment, the device further includes:

[0155] An initial probability acquisition module, configured to obtain an initial state matching probability value between the initial observation point of the vehicle and each initial candidate road segment in the target map search range;

[0156] A matching probability determination module, configured to determine the historical state matching probability of the historical matching road section of the previous observation point according to the initial state matching probability value.

[0157] In one embodiment, the above-mentioned initial probability acquisition module includes:

[0158] A first evaluation value unit, configured to determine the projection point ratio evaluation value of each initial candidate road section according to the ratio information of the projection points of the initial observation point in each initial candidate road section;

[0159] A second evaluation value unit, configured to determine the distance evaluation value of each initial candidate road section according to the distance information from the initial observation point to each initial candidate road section;

[0160] A third evaluation value unit, configured to determine the included angle evaluation value of each initial candidate road section according to the included angle information between the driving direction of the initial observation point and the direction of each initial candidate road section;

[0161] An initial probability determination unit, configured to determine the initial state matching probability value of each initial candidate road section according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate road section.

[0162] In one embodiment, the above-mentioned matching probability determination module is specifically configured to use the state matching probability value of each candidate road section of the initial observation point as the starting value, and sequentially determine the historical state matching probability of the historical matching road section of the next observation point according to the observation point order of the vehicle's driving path until the previous observation point of the vehicle position is determined, so as to obtain the historical state matching probability of the historical matching road section of the previous observation point.

[0163] In one embodiment, the above-mentioned matching module 12 is specifically configured to determine the sequence road section composed of the candidate road section corresponding to the maximum state matching probability value and the historical trajectory of the vehicle as the target matching road section of the vehicle's driving path on the map.

[0164] For the specific limitations of the map matching device, reference can be made to the limitations on the map matching method in the above text, which will not be elaborated here. Each module in the above map matching device can be implemented in whole or in part by software, hardware, and their combinations. The above modules can be embedded in the processor in the computer device in hardware form or independent of it, or stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0165] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 10As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a map matching method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0166] Those skilled in the art can understand that Figure 10 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0167] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0168] According to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device accuracy factor, obtain the evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range;

[0169] According to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point, determine the state matching probability between each candidate road segment and the vehicle position;

[0170] According to the state matching probability between each candidate road segment and the vehicle position, determine the target matching road segment of the vehicle's driving path on the map.

[0171] For the computer device provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0172] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented:

[0173] Obtain an evaluation matching probability between the vehicle position and at least one candidate road segment in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle and the navigation device dilution of precision.

[0174] Determine a state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point.

[0175] Determine a target matching road segment of the driving path of the vehicle in the map according to the state matching probability between each candidate road segment and the vehicle position.

[0176] For a computer-readable storage medium provided in the above embodiment, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be elaborated here.

[0177] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. The non-volatile memory can include a read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory. By way of illustration and not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc.

[0178] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0179] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A map matching method, characterized in that, The method includes: Obtaining an evaluation matching probability between the vehicle position and at least one candidate road segment in a target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device dilution of precision; Determining a state matching probability between each candidate road segment and the vehicle position according to the evaluation matching probability of each candidate road segment, the state transition probability from the historical matching road segment of the previous observation point to each candidate road segment, and the historical state matching probability of the historical matching road segment of the previous observation point; Determining a target matching road segment of the driving path of the vehicle in the map according to the state matching probability between each candidate road segment and the vehicle position; Wherein, the obtaining an evaluation matching probability between the vehicle position and at least one candidate road segment in a target map search range according to the distance between the vehicle position and the previous observation point of the vehicle, and the navigation device dilution of precision includes: Obtaining distribution information of the distance between the vehicle position and the previous observation point, and performing regularization processing on the navigation device dilution of precision; Determining the evaluation matching probability of each candidate road segment according to the distribution information of the distance between the vehicle position and the previous observation point and the navigation device dilution of precision after regularization processing.

2. The method according to claim 1, characterized in that, The method further includes: Obtaining a map network topology relationship between the historical matching road segment of the previous observation point and each candidate road segment; Determining a state transition probability from the historical matching road segment of the previous observation point to each candidate road segment according to the map network topology relationship.

3. The method according to claim 2, characterized in that, The determining a state transition probability from the historical matching road segment of the previous observation point to each candidate road segment according to the map network topology relationship includes: For any candidate road segment: If the map network topology relationship is that the candidate road segment is the same road segment as the historical matching road segment, determining the transition probability as a preset first value; If the map network topology relationship is that the candidate road segment is the next road segment of the historical matching road segment, determining the transition probability as a preset second value.

4. The method according to claim 1, characterized in that, The method further includes: Obtaining an initial state matching probability value from the initial observation point of the vehicle to each initial candidate road segment in the target map search range; Determining the historical state matching probability of the historical matching road segment of the previous observation point according to the initial state matching probability value.

5. The method according to claim 4, characterized in that, The obtaining an initial state matching probability value from the initial observation point of the vehicle to each candidate road segment in the target map search range includes: Determining a projection point ratio evaluation value of each initial candidate road segment according to the ratio information of the projection points of the initial observation point in each initial candidate road segment; Determining a distance evaluation value of each initial candidate road segment according to the distance information from the initial observation point to each initial candidate road segment; Determining an included angle evaluation value of each initial candidate road segment according to the included angle information between the driving direction of the initial observation point and the direction of each initial candidate road segment; Determining the initial state matching probability value of each initial candidate road segment according to the projection point ratio evaluation value, distance evaluation value, and included angle evaluation value of each initial candidate road segment.

6. The method according to claim 4, characterized in that, Determining the historical state matching probability of the historical matching section of the previous observation point according to the initial state matching probability value includes: Taking the state matching probability values of the candidate sections of the initial observation point as the starting values, and sequentially determining the historical state matching probability of the historical matching section of the next observation point according to the order of the observation points of the driving path of the vehicle until the previous observation point of the vehicle position is determined, so as to obtain the historical state matching probability of the historical matching section of the previous observation point.

7. The method according to claim 1, characterized in that, Determining the target matching section of the driving path of the vehicle on the map according to the state matching probability between each candidate section and the vehicle position includes: Determining the sequence section composed of the candidate section corresponding to the maximum state matching probability value and the historical trajectory of the vehicle as the target matching section of the driving path of the vehicle on the map.

8. A map matching device, characterized in that, The device includes: An acquisition module, configured to obtain an evaluation matching probability between the vehicle position and at least one candidate section in the target map search range according to the distance between the vehicle position and the previous observation point of the vehicle and the navigation device accuracy factor; A determination module, configured to determine the state matching probability between each candidate section and the vehicle position according to the evaluation matching probability of each candidate section, the state transition probability from the historical matching section of the previous observation point to each candidate section, and the historical state matching probability of the historical matching section of the previous observation point; A matching module, configured to determine the target matching section of the driving path of the vehicle on the map according to the state matching probability between each candidate section and the vehicle position; Wherein, the acquisition module is specifically configured to: obtain the distribution information of the distance between the vehicle position and the previous observation point, and perform regularization processing on the navigation device accuracy factor; determine the evaluation matching probability of each candidate section according to the distribution information of the distance between the vehicle position and the previous observation point and the navigation device accuracy factor after regularization processing.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A storage medium, on which a computer program is stored, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images