CN112595333A

CN112595333A - Road navigation data processing method and device, electronic equipment and storage medium

Info

Publication number: CN112595333A
Application number: CN202011455256.3A
Authority: CN
Inventors: 刘春�
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-12-10
Filing date: 2020-12-10
Publication date: 2021-04-02
Anticipated expiration: 2040-12-10
Also published as: CN112595333B

Abstract

The embodiment of the application provides a method and a device for processing road navigation data, electronic equipment and a storage medium, and relates to the technical fields of artificial intelligence, maps and the like. The method comprises the following steps: acquiring road data in a target range of an electronic map, wherein the road data comprises a first shape point set, a second shape point set and a track point set, and the map precision of at least one first shape point in the first shape point set is lower than that of at least one second shape point in the second shape point set; obtaining a first set comprising a plurality of first point pairs based on the road data; obtaining a second set containing a plurality of second point pairs based on the road data; performing iterative optimization on the first set based on the second set and the cost function until a preset first end condition is met to obtain an optimized set; and determining corresponding road navigation data based on the first shape point and the second shape point in each point pair in the optimized set, thereby improving the road matching efficiency.

Description

Road navigation data processing method and device, electronic equipment and storage medium

Technical Field

The present application relates to the technical field of artificial intelligence, maps, and the like, and in particular, to a method and an apparatus for processing road navigation data, an electronic device, and a storage medium.

Background

Road navigation information is generally required for assisting driving when a vehicle is driven, and the road navigation information can be obtained by matching detailed lane information described based on a high-precision map (the precision of a road is high) with road information provided by a common map (the precision of the road is low). At present, when detailed lane information described by a high-precision map is matched with road information provided by a common map, the detailed lane information is mainly realized by directly using a hidden markov model.

However, the inventor researches and finds that the hidden markov model is a local model, is not suitable for overlong map matching and is easy to generate the problem of matching fracture, so that the matching length of roads is required to be limited in practical application, and because a high-precision map is a complex road network and does not directly reflect road tracks, a starting point needs to be manually specified during matching to form a simulated road track, and then the simulated road track is matched with road information provided by a common map, so that the matching efficiency is low.

Disclosure of Invention

The application relates to a method and a device for processing road navigation data, electronic equipment and a storage medium, which can improve road matching efficiency.

In one aspect, an embodiment of the present application provides a method for processing road navigation data, where the method includes:

acquiring road data in a target range of an electronic map, wherein the road data comprises a first shape point set, a second shape point set and a track point set, and the map precision of at least one first shape point in the first shape point set is lower than that of at least one second shape point in the second shape point set;

obtaining a first set containing a plurality of first point pairs based on road data, wherein each first point pair comprises a first shape point, a second shape point and a track point in the track point set, and each first shape point is at least contained in one first point pair;

obtaining a second set containing a plurality of second point pairs based on the road data, wherein each second point pair comprises a first shape point and an associated point of the first shape point, and the associated point comprises a second shape point and a track point which are positioned in the set range of the first shape point;

performing iterative optimization on the first set based on the second set and a cost function until a preset first end condition is met to obtain an optimized set, wherein the value of the cost function represents the matching degree between each point pair in the first point pair;

determining road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set

On the other hand, an embodiment of the present application provides a processing apparatus for road navigation data, the apparatus includes:

the data acquisition module is used for acquiring road data in the target range of the electronic map, wherein the road data comprises a first shape point set, a second shape point set and a track point set, and the map precision of at least one first shape point in the first shape point set is lower than that of at least one second shape point in the second shape point set;

the first set determining module is used for obtaining a first set containing a plurality of first point pairs based on the road data, wherein each first point pair comprises a first shape point, a second shape point and a track point in the track point set, and each first shape point is at least contained in one first point pair;

the second set determining module is used for obtaining a second set containing a plurality of second point pairs based on the road data, wherein each second point pair comprises a first shape point and an associated point of the first shape point, and the associated point comprises a second shape point and a track point which are positioned in a set range of the first shape point;

the optimization module is used for performing iterative optimization on the first set based on the second set and a cost function until a preset first end condition is met to obtain an optimized set, wherein the value of the cost function represents the matching degree between each point pair in the first point pair;

and the road navigation data determining module is used for determining road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set.

In another aspect, an embodiment of the present application provides an electronic device, including a processor and a memory: the memory is configured to store a computer program which, when executed by the processor, causes the processor to perform the method of processing road navigation data as described above.

In still another aspect, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, which when run on a computer, enables the computer to execute the method for processing road navigation data described above.

The technical scheme provided by the embodiment of the application has the following beneficial effects:

in the embodiment of the application, when determining the road navigation data, the obtained reason data comprises first shape points with low map precision (namely, a common map), second shape points with high map precision (namely, a high-precision map) and track points of a track measured in advance, assistance can be performed based on the track points, the problem of road matching between the original common map and the high-precision map is converted into the problem of three-point matching, and the matching uniqueness of each first point pair in the obtained first set can be ensured; furthermore, a second set comprising a plurality of second point pairs can be obtained based on second shape points and track points within a first shape point setting range, then iterative optimization can be carried out on the obtained first set based on the second set and a cost function, and road navigation data can be determined based on the optimized set, so that the problems that too long roads cannot be matched and the like when a hidden Markov model is singly used and matching is carried out can be effectively avoided, correct pairing relation can be searched more effectively, the calculation efficiency is improved, accurate road navigation data can be determined in a shorter time, and the road data within the target range of the electronic map is matched, namely tile operation is adopted, the electronic map can be divided into different operation tasks, and the different operation tasks can be processed in parallel, the processing efficiency is further improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.

Fig. 1 is a schematic flowchart of a method for processing road navigation data according to an embodiment of the present disclosure;

FIG. 2a is a schematic diagram of a first shape point and a second shape point in a first set of point pairs provided by an embodiment of the present application;

FIG. 2b is a schematic diagram of pairs of points in a first set according to an embodiment of the present application;

FIG. 2c is a schematic diagram of pairs of points in an optimized set according to an embodiment of the present application;

fig. 3 is a schematic view of a scenario provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a road included in a target range according to an embodiment of the present disclosure;

fig. 5 is a schematic flowchart of another road navigation data processing method according to an embodiment of the present application;

fig. 6 is a schematic diagram of values of a cost function provided in an embodiment of the present application;

FIG. 7 is a diagram illustrating first shape points and second shape points in an optimized set according to an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a device for processing road navigation data according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.

As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

In application scenarios of advanced driving assistance, smart driving, and automatic driving, it is generally required to perform driving assistance based on road navigation information obtained by matching detailed lane geometric information described by a high-precision map with road information provided by a general map, and when a vehicle acquires the road navigation information, the vehicle may acquire the road navigation information in real time through a high-precision map ECU (Electronic Control Unit) and a general map ECU (Electronic Control Unit), respectively, through an in-vehicle application. The detailed lane geometric information described by the high-precision map is used for accurately positioning the vehicle and judging the road conditions, the road information provided by the common map provides basic road navigation information, and when the two types of information are accurately matched, the detailed lane geometric information described by the high-precision map and the road information provided by the common map need to be matched according to geometric distance, topological relation, road attributes and the like.

At present, when detailed lane information described by a high-precision map is matched with road information provided by a common map, the detailed lane information is mainly directly realized by using a hidden markov model, but when the hidden markov model is adopted to directly match the road, the following problems exist:

(1) because the hidden Markov model is a local model, when the road is matched for a long time, the problem of matching fracture is easy to occur, so that the matching length of the road needs to be limited in practical application; (2) the influence of the initial state is large, and once the matching of the initial state is wrong, the whole matching is easy to fail; (3) because the high-precision map is a complex road network and does not directly reflect the road track, the starting point needs to be manually appointed when matching is carried out, the simulated road track is formed, and then matching is carried out based on the simulated road track and the road information provided by the common map, so that the matching efficiency is low.

Based on this, embodiments of the present application provide a method and an apparatus for processing road navigation data, an electronic device, and a storage medium, which are intended to solve some or all of the above technical problems. The method and the device can be realized based on an artificial intelligence technology, and particularly relate to an automatic driving technology in the artificial intelligence technology.

Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.

The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning, an automatic driving technology and the like. The automatic driving technology generally comprises technologies such as high-precision maps, environment perception, behavior decision, path planning, motion control and the like, and has wide application prospects.

Optionally, the data processing and/or computing involved in the embodiments of the present application may be implemented by a cloud computing method. Among them, cloud computing (cloud computing) is a computing mode that distributes computing tasks over a resource pool formed by a large number of computers, so that various application systems can acquire computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the "cloud" appear to the user as being infinitely expandable and available at any time, available on demand, expandable at any time, and paid for on-demand. As a basic capability provider of cloud computing, a cloud computing resource pool (called as a cloud Platform in general, an Infrastructure as a Service) Platform is established, and multiple types of virtual resources are deployed in the resource pool for selective use by external clients, the cloud computing resource pool mainly includes a computing device (including an operating system, for a virtualized machine), a storage device, and a network device, and is divided according to logical functions, a PaaS (Platform as a Service) layer may be deployed on an IaaS (Infrastructure as a Service) layer, a SaaS (Software as a Service) layer may be deployed on the PaaS layer, or the SaaS may be directly deployed on the IaaS layer, the PaaS may be a Platform running on Software, such as a web database, a container, and the like, as business Software of various websites, a web portal, and the like, SaaS and PaaS are upper layers relative to IaaS.

The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.

The terms referred to in this application will first be introduced and explained:

hidden Markov Model (HMM): a statistical model for analyzing system internal states or modes through data observation.

Random Geometry model (Stochastic Geometry): a mathematical model for researching the mode (pattern) of the geometric objects arranged in the space is suitable for researching the spatial distribution of the geometric objects in the natural and artificial environments.

High Definition Map (HD Map): lane-level maps with accuracy on the centimeter level.

Electronic Horizon (EH): refers to local map information that is some distance ahead of the vehicle during travel.

Markov Chain Monte Carlo (Markov Chain Monte Carlo, MCMC): the general term of a group of random optimization methods in statistics can be used for the optimization of high-dimensional complex objective functions/cost functions.

Fig. 1 is a flowchart illustrating a method for processing road navigation data, which may be executed by a server or a terminal device, provided in an embodiment of the present application. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services. The terminal device may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart car terminal, etc., but is not limited thereto. The terminal device and the server may be directly or indirectly connected through wired or wireless communication, and the application is not limited herein.

In the embodiment of the present application, an execution subject is taken as an example of a vehicle-mounted terminal, and as shown in fig. 1, the method may include:

step S101, road data in the target range of the electronic map is obtained, the road data comprises a first shape point set, a second shape point set and a track point set, and the map precision of at least one first shape point in the first shape point set is lower than that of at least one second shape point in the second shape point set.

The target range may refer to any specified area range within the electronic map range, or may refer to an area range of one map sheet, which is not limited in the embodiment of the present application. Alternatively, the target range may be determined based on the actual position of the vehicle.

Optionally, in this embodiment of the application, a first shape point set, a second shape point set, and a track point set of each road in a target range may be obtained, where a shape point refers to a point that outlines a shape of a road, and specifically may be position information such as coordinates of a line shape point. The first shape point refers to a shape point constituting each road in a target range in an electronic map (hereinafter referred to as a general map) with lower accuracy, the second shape point refers to a shape point constituting each road in a target range in an electronic map (hereinafter referred to as a high-accuracy map) with higher accuracy, and the track point refers to a track point of each road measured in advance in the target range.

In one example, the road data in the target range of the electronic map may be acquired sequentially according to a traveling direction (e.g., the forward direction of the vehicle is taken as the traveling direction, which may be determined according to the position of the vehicle acquired in real time), such as a plurality of roads in the target range in a common map, and the first shape point of the traveling direction is M_i(i is 1, …, m, m represents the m-th), coexists in the m first shape points, and the second shape point of the plurality of roads in the target range in the high-precision map in the traveling direction is N_j(j is 1, …, n, n represents the nth), coexists in the n second shape points, and all track points of each road measured in advance in the target range are P_k(k 1, …, p, p denotes the p-th trace point), and coexist in p trace points.

Step S102, obtaining a first set containing a plurality of first point pairs based on road data, wherein each first point pair comprises a first shape point, a second shape point and a track point in the track point set, and each first shape point is at least contained in one first point pair.

Optionally, after the road data is acquired, the acquired first shape points, second shape points and track points may be combined to obtain first point pairs. Each first point pair only comprises one first shape point, one second shape point and one track point, and each first shape point at least appears in one first point pair.

Step S103, based on the road data, obtaining a second set containing a plurality of second point pairs, wherein each second point pair comprises a first shape point and an associated point of the first shape point, and the associated point comprises a second shape point and a track point which are located in the set range of the first shape point.

Alternatively, a set range may be preset, and at this time, for each first shape point, each second shape point and each trace point located in the set range of the first shape point may be determined, and then, based on the determined first shape points, and each second shape point and each trace point located in the set range of each first shape point, the second shape point and each trace point, a second set including a plurality of second point pairs is obtained.

In an alternative embodiment of the present application, obtaining a second set including a plurality of second point pairs based on the road data includes:

and for each first shape point, combining the first shape point, each second shape point located in a set range of the first shape point and each track point to obtain each second point pair corresponding to the first shape point and comprising all combination modes of one first shape point, one second shape point and one track point, wherein the second set comprises each second point pair corresponding to each first shape point.

As an optional embodiment, for each first shape point, the first shape point may be combined with each second shape point in the set range to obtain each combined point pair, and for each combined point pair, each combined point pair is combined with each track point in the set range at will to obtain each second point pair corresponding to all the combined modes of the first shape point; at this time, the second point pairs corresponding to each first shape point may be combined into a second set, and each second point pair includes a first shape point, a second shape point and a track point.

Optionally, after the second set is obtained, in order to improve the accuracy of the data and improve the processing efficiency, the second point pairs in the second set may be subjected to deduplication processing to obtain a second set subjected to deduplication processing, and subsequent processing may be performed based on the second set subjected to deduplication processing. The deduplication processing refers to performing deduplication processing on a second point pair including the same first shape point, second shape point and track point in the second point pair. For example, assuming that the first shape points, the second shape points, and the track points included in the two second point pairs are all the same, the two second point pairs may be removed from one and remain one.

And step S104, performing iterative optimization on the first set based on the second set and the cost function until a preset first end condition is met to obtain an optimized set, wherein the value of the cost function represents the matching degree between each point pair in the first point pair.

Optionally, for the obtained first set, iterative optimization may be performed on the first set based on the cost function and the determined second set until a preset first end condition is met, so that the matching degree of each first point pair in the set after iterative optimization meets the requirement. The first end condition may be configured in advance, for example, a preset number of iterations is reached and/or a value of the cost function is smaller than a preset threshold. The value of the cost function indicates the matching degree between each point pair in the first point pair, and when the matching degree is higher, the road described by the first shape point and the second shape point in the first point pair is more similar.

In an optional embodiment of the present application, iteratively optimizing the first set based on the second set and the cost function until a preset first end condition is met includes:

repeatedly performing the following operations based on the second set and the cost function until a first end condition is satisfied:

calculating a first value of a cost function based on each point pair in the first set;

replacing a first point pair in the first set with a second point pair containing the same first shape point as the first point pair to obtain a third set;

calculating a second value of the cost function based on each point pair in the third set;

and determining a current suboptimal target set from the first set and the third set based on the first value and the second value, and updating the first set into the target set.

As an optional embodiment, when optimizing the first set each time based on the second set and the cost function, a first value of the cost function may be calculated based on each point pair in the first set, a second point pair is randomly selected from the second set, the selected second point pair is replaced with a first point pair containing the same first shape point in the target set, and at this time, the target set of the replaced point pair is the third set. Further, a second value of the cost function may be calculated based on each point pair in the obtained third set, then a target set is determined from the first set and the third set according to the obtained first value of the cost function and the obtained second value of the cost function, then the first set is updated to the target set, the first value of the cost function is calculated based on each point pair in the updated first set (i.e., the target set), then a second point pair is randomly selected from the second set, the selected second point pair and a first point pair containing the same first shape point in the updated first set (i.e., the target set) are replaced, and at this time, the target set of the replaced point pair is the third set. Further, a second value of the cost function may be calculated based on each point pair in the obtained third set, then, according to the obtained first value of the cost function and the obtained second value of the cost function, the target set is determined again from the updated first set (i.e., the target set) and the third set, the first set is updated again to the target set determined in the current iteration, and the above operations are repeatedly performed until the first end condition is satisfied.

In an alternative embodiment of the present application, determining a current sub-optimized target set from the first set and the third set based on the first value and the second value includes:

if the second value is less than or equal to the first value, determining the third set as a target set;

and if the second value is greater than or equal to the first value, determining the acceptance probability corresponding to the third set according to the first value, the second value and the iterative optimization times, and determining a target set from the first set and the third set according to the acceptance probability.

Optionally, when determining the current sub-optimized target set from the first set and the third set based on the first value and the second value, the determination may be performed according to a magnitude relationship between the first value and the second value. If the second value is less than or equal to the first value (less than the first value), the third set may be determined as the target set, and if the second value is greater than the first value (greater than the first value or equal to the first value), the acceptance probability corresponding to the third set needs to be determined according to the first value, the second value, and the number of times that the iterative optimization has been performed, and then the target set is determined from the first set and the third set based on the determined acceptance probability. Wherein the reception probability characterizes a probability that the third set can be the target set.

In an example, assuming that a first value of the cost function calculated based on each point pair in the first set is 4.58, and a second value of the cost function calculated based on each point pair in the third set is 5, it can be seen that the second value is greater than the first value, at this time, an acceptance probability corresponding to the third set can be determined according to the first value, the second value, and the current iterative optimization times, and then a target set is determined from the first set and the third set based on the determined acceptance probability; accordingly, if the second value of the cost function calculated based on each point pair in the third set is 4, and the second value is smaller than the first value, the target set may be determined to be the third set.

As an alternative, when determining the target set from the first set and the third set according to the determined acceptance probability, a random probability value may be randomly generated, and then the target set may be determined from the first set and the third set according to the magnitude relationship between the acceptance probability and the random probability value. For example, the third set may be determined as the target set when the acceptance probability is greater than or equal to the random probability value, whereas the first set may be determined as the target set when the acceptance probability is less than the random probability value.

In an optional embodiment of the present application, determining, according to the first value, the second value, and the number of times that the iterative optimization has been performed, an acceptance probability corresponding to the third set includes:

and determining the acceptance probability corresponding to the third set through a simulated annealing algorithm according to the first value, the second value and the iterative optimization times.

The simulated annealing algorithm is an optimization algorithm which can effectively avoid trapping in a serial structure which is locally minimum and finally tends to global optimum by endowing a search process with time-varying probability jump performance which finally tends to zero. The Markov chain Monte Carlo of the simulated annealing algorithm is an effective method for optimizing a complex nonlinear non-convex problem, an initial value of a solution can be set, then the value of the solution is iteratively and randomly disturbed, the increase or decrease of a cost function is measured, if the value of the solution is decreased, the random disturbance is accepted, if the value of the solution is increased, the random disturbance is accepted according to a small probability, and along with continuous iteration, the small acceptance probability can be further reduced.

Optionally, when determining the acceptance probability corresponding to the third set according to the first value, the second value, and the current iterative optimization times, the acceptance probability may be determined by the following formula (1):

exp ((U0-U1)/T) formula (1)

Where P represents the probability of acceptance, U0 represents a first value, U1 represents a second value, and T represents temperature, where T can be characterized by the following equation (2):

T＝T0*(alpha)^Nformula (2)

Where T0 represents the initial temperature (which may be a preset value), alpha represents the attenuation coefficient, and N represents the number of times the optimization has been iterated.

Optionally, when the first value, the second value, and the current iterative optimization frequency are obtained, the iterative optimization frequency may be substituted into the formula (2) to obtain a temperature value corresponding to the current iteration, the first value, the second value, and the temperature value corresponding to the current iteration are substituted into the formula (1) to obtain a reception probability, and a target set is determined from the first set and the third set according to a size relationship between the reception probability and a randomly generated random probability.

In an alternative embodiment of the present application, calculating the first value of the cost function based on each point pair in the first set includes:

for each point pair of the first set, determining a first distance between a first shape point and a track point in the point pair, and a second distance between a second shape point and the track point;

determining a spatial distribution confidence between each point pair in the first set;

and obtaining a first value of the cost function based on the first distance and the second distance corresponding to each point pair in the first set and the spatial distribution confidence coefficient.

The method mainly comprises two parts of determining a value of a distance confidence coefficient and determining a value of a space confidence coefficient respectively when determining a value of a cost function, wherein generally, when the distance corresponding to a point pair is shorter, the distance confidence coefficient of the point pair is higher, and the matching degree of a first shape point, a second shape point and a track point in the point pair is higher and more reasonable; the spatial confidence degrees correspond to the irrational spatial distribution among the point pairs, and the spatial distribution confidence degrees among the point pairs can be used for representing, and when the spatial distribution confidence degree is higher, the more irrational spatial distribution among the point pairs is represented.

Optionally, when determining the value of the distance confidence, for each point pair in the first set, a first distance between a first shape point and a track point in the point pair and a second distance between a second shape point and the track point may be determined, and the first distance and the second distance are added to serve as the distance confidence of the point pair; accordingly, when the distance confidence of the first set is obtained, the sum of the distance confidence of each point pair in the first set may be used as the value of the distance confidence. Further, after determining the confidence of the spatial distribution between each point pair in the first set, the first value of the cost function may be obtained based on the value of the confidence of the spatial distribution and the value of the confidence of the distance.

In an alternative embodiment of the present application, determining the confidence of the spatial distribution between each point pair in the target set includes:

for each pair of points of the first set, determining a connection between a first shape point and a second shape point in the pair of points;

determining a first number of point pairs in which connecting lines intersect among the point pairs of the first set;

determining a second number of point pairs comprising at least one same road point in each point pair of the first set, wherein the road point is a first shape point, a second shape point or a track point;

a confidence in the spatial distribution between pairs of points in the first set is determined based on the first number and the second number.

Optionally, when determining the confidence of spatial distribution between each point pair in the first set, a first number and a second number corresponding to the first set may be determined, and the confidence of spatial distribution between each point pair in the first set may be determined based on the first number and the second number corresponding to the first set.

When determining the first number corresponding to the first set, for each point pair of the first set, a connecting line between the first shape point and the second shape point in each point pair may be determined, and then the first number of point pairs where the connecting line intersects with each other in each point pair of the first set is determined. Since the first shape point and the second shape point are acquired based on the traveling direction at the time of acquisition, when there is a line intersection between two point pairs, it is described that the first shape point (or the second shape point) of the two point pairs is not sequentially matched based on the traveling direction.

As an example, fig. 2a is a schematic diagram of a first shape point and a second shape point in each point pair in the first set, as shown in the diagram, three triangles in the diagram respectively represent three first shape points a 1-A3, and three rectangles respectively represent three second shape points B1-B3, wherein the first shape point a1 and the second shape point B1 are contained in one point pair, the first shape point a2 and the second shape point B2 are contained in one point pair, the first shape point A3 and the second shape point B3 are contained in one point pair, and the connecting lines between the three point pairs are as shown in fig. 2a, when there is a crossing of the connecting lines of the three point pairs, the second number may be added by 3.

The first shape point, the second shape point or the track point of the first set may be referred to as a road point, and at this time, for any road point of the target set, if the road point appears in a plurality of point pairs, it is indicated that the road point has a plurality of mapping relationships, at this time, the number of point pairs including the road point may be counted as a second number corresponding to the road point, which is dependent on the second number corresponding to the road point, and after the second number corresponding to each road point is obtained, the sum of the second numbers corresponding to each road point is taken as the second number corresponding to the first set.

As an example, fig. 2B is a schematic diagram of each point pair in the first set, as shown in the figure, 4 triangles in the diagram respectively represent 4 first shape points a 1-a 4, 4 rectangles respectively represent 4 second shape points B1-B4, 4 circles respectively represent 4 track points C1-C4, and the relationship between each point pair in the target set is as shown in fig. 2B. At this time, for the track point C2, the track point C2 respectively forms a pair of points with three first shape points a1 to A3, and a pair of points with two second shape points B1 to B3, for the track point C2, there may be a case where 6(2 × 3 ═ 6) point pairs include the track point C2 at most, and if the first set includes the 6 cases, the second number corresponding to the track point C2 is 6.

In an optional embodiment of the present application, obtaining a first value of the cost function based on a first distance and a second distance corresponding to each point pair in the first set and the spatial distribution confidence includes:

determining the sum of the first distance and the second distance corresponding to each point pair in the first set, and taking the obtained sum as a distance confidence coefficient;

acquiring weights corresponding to the first quantity and the second quantity, and performing weighted summation processing on the first quantity and the second quantity according to the weights corresponding to the first quantity and the second quantity to obtain a spatial distribution confidence coefficient;

and obtaining a first value of the cost function according to the distance confidence coefficient and the space distribution confidence coefficient.

Optionally, after obtaining the first distance and the second distance corresponding to each point pair in the first set, the first distance and the second distance corresponding to each point pair may be summed, and the obtained sum value is used as a distance confidence in the first value of the cost function, then the weight corresponding to the first quantity and the weight corresponding to the second quantity may be obtained, and the first quantity and the second quantity are subjected to weighted summation processing according to the weight corresponding to the first quantity and the weight corresponding to the second quantity to obtain a spatial distribution confidence in the first value of the cost function, and the first value of the cost function is obtained according to the obtained distance confidence and the spatial distribution confidence, for example, the distance confidence and the spatial distribution confidence are added to obtain the first value of the cost function.

The weight values corresponding to the first quantity and the second quantity represent the importance degrees of the first quantity and the second quantity when the values of the cost functions are determined, the values of the weights can be configured in advance according to actual requirements, and the embodiment of the application is not limited.

In an alternative embodiment of the present application, the cost function can be represented by formula (3) to formula (5):

u ═ Udata + Uprior equation (3)

Udata ═ Σ { norm (pHD, pTRK) + norm (pSD, pTRK) } formula (4)

Uprior ═ w1 × n _ cross + w2 × n _ multiple formula (5)

Wherein U represents a value of the cost function, Udata represents a distance confidence, Uprior represents a spatial distribution confidence, pHD represents a second shape point, pTRK represents a trajectory point, pSD represents a first shape point, norm (pHD, pTRK) represents a second distance between the second shape point and the trajectory point in any one of the pairs of points in the target set, norm (pSD, pTRK) represents a first distance between the first shape point and the trajectory point in any one of the pairs of points in the target set, Σ { norm (pHD, pTRK) + norm (pSD, pTRK) } represents a sum of the first distance and the second distance of all the pairs of points in the target set, n _ cross represents a first number, n _ multiple represents a second number, w1 represents a weight corresponding to the first number, and w1 represents a weight corresponding to the second number.

Optionally, when calculating the first value of the cost function based on each point pair in the first set, a first distance between a first shape point and a track point in each point pair in the first set and a second distance between a second shape point and a track point may be substituted into formula (4) to obtain a value of the first set corresponding to the distance confidence, a first number and a second number corresponding to the first set are substituted into formula (5) to obtain a value of the first set corresponding to the spatial distribution confidence, and finally, the first value of the cost function is obtained based on formula (3), the value of the first set corresponding to the distance confidence, and the value of the first set corresponding to the spatial distribution confidence.

Step S105, determining road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set.

Optionally, for each point pair in the optimized set, each first shape point, each second shape point, or each track point only appears in one point pair, and connecting lines of each point pair do not intersect.

For example, as shown in fig. 2C, which is a schematic diagram of each point pair in the optimized set, as shown in the figure, 4 triangles in the diagram respectively represent 4 first shape points a 1-a 4, 4 rectangles respectively represent three second shape points B1-B4, and 4 circles respectively represent 4 track points C1-C4. Wherein the first shape point a1, the track point C1 and the second shape point B1 are contained in one point pair, the first shape point a2, the track point C2 and the second shape point B2 are contained in one point pair, the first shape point A3, the track point C3 and the second shape point B3 are contained in one point pair, the first shape point a4, the track point C4 and the second shape point B4 are contained in one point pair, arrows between circles indicate the travel direction of the track, and it can be seen from the figure that the pairs of points in the optimized set are all one-to-one mapping, and each of the first shape point, the second shape point or the track point appears only in one point pair, as the first shape point a1 only forms a point pair with the track point C2 and the second shape point B2, there is no one-to-many or-to-many-to-one point pair, and there is no intersection between the connecting lines of the pairs of points.

Optionally, after the optimized set is obtained, road navigation information may be generated according to the first shape point and the second shape point in each point pair in the optimized set, for example, the road navigation information may specifically include a name of a road, a traveling direction of the road, road construction information, and the like; further, the driver can perform vehicle driving according to the road navigation information.

In an alternative embodiment of the present application, the target range is determined based on a location at which the target vehicle is located, the method further comprising:

providing the road navigation data to a driver of the target vehicle to cause the driver to drive the vehicle in accordance with the road navigation data; or the like, or, alternatively,

movement of the target vehicle is controlled according to the road navigation data.

Alternatively, when the vehicle is driven by a driver, the road navigation data may be displayed to the driver through a display screen of the in-vehicle terminal (or a display screen of another terminal) (or provided to the user through voice broadcast), so that the driver may drive the vehicle according to the displayed road navigation data. Of course, in practical applications, there may also be situations of autonomous driving, where the vehicle may be autonomously driven directly on the basis of road navigation data. It is understood that the electronic map target range is determined based on the position information of the vehicle, and the electronic horizon of the vehicle position may be generally used as the target range, and in order to ensure that the navigation data is more accurate, an area formed by a certain distance in front of the vehicle and a certain distance behind the vehicle, such as an area formed by 150 meters in front of the vehicle and 50 meters behind the vehicle, may also be used as the target range.

In the embodiment of the application, when determining the road navigation data, the obtained reason data comprises first shape points with low map precision (namely, a common map), second shape points with high map precision (namely, a high-precision map) and track points of a track measured in advance, assistance can be performed based on the track points, the problem of road matching between the original common map and the high-precision map is converted into the problem of three-point matching, and the matching uniqueness in the obtained first set can be ensured; furthermore, a second set comprising a plurality of second point pairs can be obtained based on second shape points and track points within a first shape point setting range, then iterative optimization can be carried out on the obtained first set based on the second set and a cost function, and road navigation data can be determined based on the optimized set, so that the problems that too long roads cannot be matched and the like when a hidden Markov model is singly used and matching is carried out can be effectively avoided, correct pairing relation can be searched more effectively, the calculation efficiency is improved, accurate road navigation data can be determined in a shorter time, and the road data within the target range of the electronic map is matched, namely tile operation is adopted, the electronic map can be divided into different operation tasks, and the different operation tasks can be processed in parallel, the processing efficiency is further improved.

In an optional embodiment of the present application, determining road navigation data corresponding to the target range based on each point pair in the optimized set includes:

taking the distance between a first shape point and a second shape point in each point pair in the optimized set as an emission probability matrix of a Hidden Markov Model (HMM), and taking the matching degree between the first shape point and the second shape point in each point pair in the optimized set as a state transition probability matrix of the HMM;

adjusting the first shape point corresponding to the second shape point in each point pair based on the emission probability matrix and the state transition probability matrix to obtain each adjusted point pair;

and determining road navigation data corresponding to the target range based on the first shape point and the second shape point in the adjusted point pairs.

Alternatively, for each point pair in the optimized set, a distance between the first shape point and the second shape point in each point pair may be determined, and the distance between the first shape point and the second shape point in each point pair may be taken as an element value in the emission probability matrix of the HMM, and a degree of matching between the first shape point and the second shape point in each point pair (when the degree of matching is higher, the two shape points are more similar) may be determined, and the degree of matching between the first shape point and the second shape point in each point pair may be taken as an element value in the state transition probability matrix of the HMM. Alternatively, the distance between the first shape point and the second shape point and the matching degree between the first shape point and the second shape point may be obtained based on different calculation manners.

Further, each second shape point in the optimized set may be regarded as an observation sequence of the HMM, and a target first shape point corresponding to each second shape point is determined from each first shape point in the optimized set by using a viterbi algorithm according to the emission probability matrix and the state transition probability matrix. For any second shape point in the optimized set, if it is determined that the target first shape point corresponding to the second shape point is the first shape point (i.e. the original first shape point) in the point pair to which the second shape point belongs, it indicates that the pairing of the second shape point in the optimized set is reasonable, and at this time, the first shape point corresponding to the second shape point may not be adjusted; on the contrary, if it is determined that the target first shape point corresponding to the second shape point is not the first shape point in the point pair to which the second shape point belongs, it indicates that the pairing of the second shape point in the optimized set is not reasonable, and at this time, the first shape point corresponding to the second shape point may be adjusted to the target first shape point, so as to obtain each adjusted point pair; accordingly, the road navigation data corresponding to the target range may be determined based on the first shape point and the second shape point in the adjusted point pairs.

For example, for two point pairs in the optimized set, one of the point pairs includes a first shape point 1, a second shape point 1, and a track point 1, and the other of the point pairs includes a first shape point 2, a second shape point 2, and a track point 2, if the target first shape point determined by the second shape point 1 is the first shape point 2, the resulting point pair for the first shape point 2 may include the second shape point 1, the track point 1, and the first shape point 2.

In an optional embodiment of the present application, further optimization and adjustment may be performed on the pairing condition of each point pair in the optimized set based on an HMM algorithm, so as to further improve the accuracy of the determined road navigation data.

In an optional embodiment of the present application, determining road navigation data corresponding to the target range based on the first shape point and the second shape point in the adjusted point pairs includes:

performing iterative optimization on each adjusted point pair based on the second set and the cost function until a preset second end condition is met;

and determining road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair at the end.

As an optional implementation manner, for each adjusted point pair, iterative optimization may be performed on each adjusted point pair based on the determined second set and the cost function until a preset second end condition is met, and then, based on each point pair at the end, road navigation data corresponding to the target range is determined. The second ending condition may be configured in advance, for example, the preset number of iterations or the value of the cost function is smaller than a preset threshold, and the like, and based on the determined second set and the cost function, the principle and the process of performing iterative optimization on each adjusted point pair are the same as those of performing iterative optimization on the first set based on the second set and the cost function, and specific description may be given to the description of performing iterative optimization on the first set based on the second set and the cost function, which is not described herein again.

It can be understood that the method provided by the embodiment of the application can be applied to auxiliary driving, automatic driving and other applicable scenes. As shown in fig. 3, the general road navigation information, the detailed high-precision road information and the road surrounding facility information at a certain distance (e.g. 200 m) ahead of the vehicle can be acquired by means of a general electronic horizon and a high-precision electronic horizon, and are respectively output to the vehicle in real time through the high-precision map ECU and the general map ECU by the vehicle-mounted application, and the correlation controller in the vehicle application can determine the correlation between the general road navigation information and the detailed high-precision road information (i.e. the correlation between the high-precision map and the general navigation map), and finally form road navigation data to be provided to the driver, thereby assisting the driver in driving the vehicle based on the road navigation data. The general road navigation information is used for adjusting aspects such as safe driving assistance, navigation, comfort level or energy saving (navigation/safety assistance/comfort/energy saving application in the figure), and the high-precision road navigation information is used for adjusting aspects such as positioning/control application.

In order to better understand the method provided by the embodiment of the present application, the method is described in detail below with reference to a specific application scenario. In the present example, the electronic map target range is 200 meters ahead of the vehicle, and the electronic map target range includes roads as shown in fig. 4, in which bold black lines represent high-precision trajectories composed of track points, black lines represent roads (composed of first shape points) in the ordinary map, and broken lines represent roads (composed of second shape points) in the high-precision map. Further, the method may perform road matching on each road in the high-precision map and each road in the ordinary map to obtain the road navigation data, which may be specifically as shown in fig. 5:

step S501, determining a first set { w } containing a plurality of first point pairs;

optionally, the first shape point of each road in the ordinary map may be acquired as M according to the traveling direction_i(i is 1, …, m), and the second shape point of each road in the high-precision map is N_j(j is 1, …, n), and each track point of the high-precision track is P_k(k-1, …, p). Furthermore, m second shape points can be extracted from the n second shape points, m track points are extracted from the p track points, three-point pairing is performed on the basis of the extracted m second shape points, the m first shape points and the m track points, and a first set { w } containing a plurality of first point pairs is obtained, wherein each first point pair packetThe first shape point, the second shape point and the track point are included, and each first shape point is at least contained in one first point pair.

In the embodiment of the application, the high-precision track is adopted to match the high-precision map and the common map, and the high-precision track has the constraint of the traveling direction and the traveling distance, so that the high-precision track is adopted to match the high-precision map and the common map, no divergence can be caused, and the complexity of matching the road network and the road network is reduced.

Step S502, determining a second set { S } containing a plurality of second point pairs;

optionally, for each first shape point, determining each second shape point and each track point within the set range of the first shape point, and then combining the first shape point with each second shape point and each track point within the set range of the first shape point in all possible ways to obtain each second point pair corresponding to the first shape point, where each second point pair includes one first shape point, one second shape point, and one track point; further, second point pairs corresponding to the first shape points form a second set { S }.

Step S503, selecting a second point pair from the second set { S }, and replacing the second point pair with a first point pair in the first set { w }, so as to obtain a third set;

optionally, a second point pair may be randomly selected from the second set { S }, replaced with a first point pair comprising the same first shape points in the first set { w }, and the replaced first set may be used as the third set.

Step S504, determining the value of the cost function based on the first set and the third set respectively, and determining a target set according to the change of the value of the cost function;

specifically, a first value of the cost function may be calculated based on each point pair in the first set, and a second value of the cost function may be calculated based on each point pair in the third set, if the first value is greater than the second value, the first set is used as a target set, and if the first value is not greater than the second value, an acceptance probability corresponding to the third set is determined according to the first value, the second value, and the number of times of iterative optimization, and the target set is determined according to the determined acceptance probability.

Optionally, when determining the acceptance probability corresponding to the third set, the acceptance probability may be determined by a simulated annealing algorithm, and at this time, relevant parameters corresponding to the simulated annealing algorithm, such as an initial temperature, an attenuation coefficient, and the like, may be obtained; further, temperature information corresponding to current sub-optimization can be determined based on the obtained initial temperature, the obtained attenuation coefficient and the number of times of iterative optimization, then receiving probability is obtained based on the determined temperature information, the first value and the second value, and a target set is determined according to the size relation between the receiving probability and the randomly generated random probability. The third set may be determined as the target set if the acceptance probability is greater than the random probability value, whereas the first set may be determined as the target set if the acceptance probability is less than or equal to the random probability value

Step S505, determining whether the number of times of iterative optimization has reached a preset number of iterations, if so, executing step S507, otherwise, executing step S506;

step S506, updating the first set into a target set, and returning to execute the step S503;

step S507, finishing iterative optimization to obtain an optimized set;

step S508, adjusting each point pair in the optimized set based on a hidden Markov model algorithm to obtain each adjusted point pair;

alternatively, a third distance between the first shape point and the second shape point in each point pair in the optimized set may be used as the emission probability matrix of the HMM, and a fourth distance between the first shape point and the second shape point in each point pair in the optimized set may be used as the state transition probability matrix of the HMM; further, for each second shape point in the optimized set, a corresponding target first shape point may be determined from each first shape point in the optimized set by using a viterbi algorithm according to the emission probability matrix and the state transition probability matrix, and then the first shape points corresponding to the second shape points in each point pair in the optimized set may be adjusted to obtain adjusted point pairs.

Step S509, performing iterative optimization on each adjusted point pair based on the second set and the cost function;

optionally, when performing iterative optimization on each adjusted point pair based on the second set and the cost function, the optimization may be performed in the manner in step S503 and step S504, which may specifically refer to the description in step S503 and step S504, and is not described herein again.

Step S510, determining whether the number of times of iterative optimization has reached a preset number of iterations, if so, executing step S511, otherwise, returning to execute step S509;

step S511, finishing the iterative optimization to obtain each point pair when finishing, and determining road navigation data according to each point pair when finishing;

optionally, in the iterative optimization process, the value of the cost function obtained in each optimization may be as shown in fig. 6 (in fig. 6, the abscissa represents the number of iterations, and the ordinate represents the value of the cost function), and as can be seen from fig. 6, in the optimization iteration process, the value of the cost function gradually becomes smaller, and when the number of iterations has reached the preset number of iterations, the value of the cost function generally converges.

As an example, a schematic diagram of the first shape point and the second shape point in each point pair at the end of optimization is shown in fig. 7, in which fig. 7, a triangle represents the first shape point (i.e., the shape point forming the road in the ordinary map), and a rectangle represents the second shape point (i.e., the shape point forming the road in the high-precision map), and based on fig. 7, it can be seen that each first shape point (or second shape point) appears only in one point pair, and there is no intersection in the connecting line between the first shape point and the second shape point in each point pair.

Step S512, providing the road navigation data to a driver so that the driver drives the vehicle according to the road navigation data; or, automatically driving the vehicle according to the road navigation data.

In the embodiment of the application, as the mixed model of the random geometric model and the hidden Markov model is adopted for road matching, global random optimization is carried out on road data, maps with any length can be matched, and as the global random optimization is adopted, the initial state can be any condition without designation, and high-precision tracks are used for auxiliary matching, so that the matching uniqueness is ensured, and the matching efficiency can be greatly improved. Furthermore, in the embodiment of the application, common maps and high-precision maps among arbitrary graph data can be matched, the matching quality and the production efficiency are improved, and at the moment, a map user can randomly select a product combination of the high-precision maps and the common maps in the market, so that the optimal system application is achieved.

An embodiment of the present application provides a processing apparatus for road navigation data, as shown in fig. 8, the processing apparatus 60 for road navigation data may include: a data acquisition module 601, a first set determination module 602, a second set determination module 603, an optimization module 604, and a road navigation data determination module 605, wherein,

the data acquisition module 601 is configured to acquire road data in a target range of an electronic map, where the road data includes a first shape point set, a second shape point set, and a track point set, and a map accuracy of at least one first shape point in the first shape point set is lower than a map accuracy of at least one second shape point in the second shape point set;

a first set determining module 602, configured to obtain a first set including a plurality of first point pairs based on road data, where each first point pair includes a first shape point, a second shape point, and a track point in the track point set, and each first shape point is at least included in one first point pair;

a second set determining module 603, configured to obtain a second set including a plurality of second point pairs based on the road data, where each second point pair includes a first shape point and an associated point of the first shape point, and the associated point includes a second shape point and a track point located in a set range of the first shape point;

an optimization module 604, configured to perform iterative optimization on the first set based on the second set and a cost function until a preset first end condition is met, so as to obtain an optimized set, where a value of the cost function represents a matching degree between each point pair in the first point pair;

and a road navigation data determining module 605, configured to determine road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set.

Optionally, when the second set determining module obtains a second set including a plurality of second point pairs based on the road data, the second set determining module is specifically configured to:

Optionally, the optimization module performs iterative optimization on the first set based on the second set and the cost function until a preset first end condition is met, and is specifically configured to:

and determining a target set from the target set and the third set after the last optimization based on the first value and the second value.

Optionally, when the optimization module determines the target set from the first set and the third set based on the first value and the second value, the optimization module is specifically configured to:

Optionally, when determining the acceptance probability corresponding to the third set according to the first value, the second value, and the number of times of iterative optimization, the optimization module is configured to:

Optionally, the optimization module, when calculating the first value of the cost function based on each point pair in the first set, has a function for:

Optionally, the optimization module, when determining the confidence of the spatial distribution between each point pair in the first set, has a module for:

determining a second number of point pairs comprising at least one same road point in each point pair of the first set, wherein the road point is at least one of a first shape point, a second shape point or a track point;

and determining the confidence of the spatial distribution between each point pair in the target set according to the first quantity and the second quantity.

Optionally, when obtaining the first value of the cost function based on the first distance and the second distance corresponding to each point pair in the first set and the spatial distribution confidence, the optimization module is configured to:

Optionally, the road navigation data determining module is specifically configured to, when determining the road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set:

Optionally, the road navigation data determining module, when determining the road navigation data corresponding to the target range based on the first shape point and the second shape point in the adjusted point pair, is configured to:

Optionally, the target range is determined based on a location where the target vehicle is located, and the apparatus further comprises a data providing module for:

providing the road navigation data to a driver of the target vehicle to enable the driver user to drive the vehicle in accordance with the road navigation data; or the like, or, alternatively,

The processing device for road navigation data according to the embodiment of the present application can execute the processing method for road navigation data according to the embodiment of the present application, and the implementation principles thereof are similar, and are not repeated here.

The processing means of the road navigation data may be a computer program (comprising program code) running in a computer device, for example the processing means of the road navigation data is an application software; the apparatus may be used to perform the corresponding steps in the methods provided by the embodiments of the present application.

In some embodiments, the processing Device of the road navigation data provided by the embodiments of the present Application may be implemented by combining hardware and software, and as an example, the processing Device of the road navigation data provided by the embodiments of the present Application may be a processor in the form of a hardware decoding processor, which is programmed to execute the processing method of the road navigation data provided by the embodiments of the present Application, for example, the processor in the form of the hardware decoding processor may employ one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.

In other embodiments, the processing device for road navigation data provided in the embodiments of the present application may be implemented in software, and fig. 8 illustrates the processing device 60 for road navigation data stored in a memory, which may be software in the form of programs and plug-ins, and includes a series of modules, including a data acquisition module 601, a first set determination module 602, a second set determination module 603, an optimization module 604, and a road navigation data determination module 605; the data acquisition module 601, the first set determination module 602, the second set determination module 603, the optimization module 604, and the road navigation data determination module 605 are used to implement the road navigation data processing method provided in the embodiment of the present application.

An embodiment of the present application provides an electronic device, as shown in fig. 9, an electronic device 2000 shown in fig. 9 includes: a processor 2001 and a memory 2003. Wherein the processor 2001 is coupled to a memory 2003, such as via a bus 2002. Optionally, the electronic device 2000 may also include a transceiver 2004. It should be noted that the transceiver 2004 is not limited to one in practical applications, and the structure of the electronic device 2000 is not limited to the embodiment of the present application.

The processor 2001 is applied in the embodiment of the present application to implement the functions of the modules shown in fig. 8.

The processor 2001 may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 2001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs and microprocessors, and the like.

Bus 2002 may include a path that conveys information between the aforementioned components. The bus 2002 may be a PCI bus or an EISA bus, etc. The bus 2002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 9, but this does not indicate only one bus or one type of bus.

The memory 2003 may be, but is not limited to, ROM or other types of static storage devices that can store static information and computer programs, RAM or other types of dynamic storage devices that can store information and computer programs, EEPROM, CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store a desired computer program or in the form of a data structure and that can be accessed by a computer.

The memory 2003 is used for storing computer programs for executing the application programs of the present scheme and is controlled in execution by the processor 2001. The processor 2001 is used to execute a computer program of an application program stored in the memory 2003 to realize the actions of the road navigation data processing apparatus provided in the embodiment shown in fig. 8.

An embodiment of the present application provides an electronic device, including a processor and a memory: the memory is configured to store a computer program which, when executed by the processor, causes the processor to perform any of the methods of the above embodiments.

The present application provides a computer-readable storage medium for storing a computer program, which, when executed on a computer, enables the computer to perform any one of the above-mentioned methods.

According to an aspect of the application, a computer program product or computer program is provided, comprising computer instructions, the computer instructions being stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the method provided in the various alternative implementations described above.

The terms and implementation principles related to a computer-readable storage medium in the present application may specifically refer to a method for processing road navigation data in the embodiment of the present application, and are not described herein again.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

The foregoing is only a partial embodiment of the present application, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present application, and these modifications and decorations should also be regarded as the protection scope of the present application.

Claims

1. A method for processing road navigation data is characterized by comprising the following steps:

obtaining a first set containing a plurality of first point pairs based on the road data, wherein each first point pair comprises a first shape point, a second shape point and a track point in the track point set, and each first shape point is at least contained in one first point pair;

obtaining a second set containing a plurality of second point pairs based on the road data, wherein each second point pair comprises a first shape point and associated points of the first shape point, and the associated points comprise a second shape point and a track point which are located in a set range of the first shape point;

and determining road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set.

2. The method of claim 1, wherein obtaining a second set comprising a plurality of second point pairs based on the road data comprises:

and for each first shape point, combining the first shape point, each second shape point located in the set range of the first shape point and each track point to obtain each second point pair corresponding to the first shape point and comprising all combination modes of one first shape point, one second shape point and one track point, wherein the second set comprises each second point pair corresponding to each first shape point.

3. The method according to claim 1, wherein the iteratively optimizing the first set based on the second set and a cost function until a preset first end condition is satisfied comprises:

calculating a first value of the cost function based on each point pair in the first set;

determining a target set from the first set and the third set based on the first value and the second value, updating the first set to the target set.

4. The method of claim 3, wherein determining a target set from the first set and the third set based on the first value and the second value comprises:

determining the third set as the target set if the second value is less than or equal to the first value;

if the second value is greater than or equal to the first value, determining an acceptance probability corresponding to the third set according to the first value, the second value and the iterative optimization times, and determining the target set from the first set and the third set according to the acceptance probability.

5. The method of claim 4, wherein determining the acceptance probability corresponding to the third set according to the first value, the second value, and the number of times that the iterative optimization has been performed comprises:

6. The method of claim 3, wherein computing the first value of the cost function based on the pairs of points in the first set comprises:

for each point pair of the first set, determining a first distance between a first shape point and a track point in the point pair, and a second distance between a second shape point and a track point;

determining a spatial distribution confidence between pairs of points in the first set;

and obtaining a first value of the cost function based on the first distance and the second distance corresponding to each point pair in the first set and the spatial distribution confidence.

7. The method of claim 6, wherein determining the confidence in the spatial distribution between the pairs of points in the first set comprises:

for each point pair of the first set, determining a line between a first shape point and a second shape point in the point pair;

determining a first number of pairs of points in the first set where there is a line crossing;

and determining the confidence of the spatial distribution between each point pair in the first set according to the first quantity and the second quantity.

8. The method according to claim 7, wherein obtaining the first value of the cost function based on the first distance and the second distance corresponding to each point pair in the first set and the confidence of the spatial distribution comprises:

determining the sum of the first distance and the second distance corresponding to each point pair in the first set, and taking the obtained sum as the distance confidence;

acquiring weights corresponding to the first quantity and the second quantity, and performing weighted summation processing on the first quantity and the second quantity according to the weights corresponding to the first quantity and the second quantity to obtain the confidence degree of the spatial distribution;

and obtaining a first value of the cost function according to the distance confidence coefficient and the spatial distribution confidence coefficient.

9. The method of claim 1, wherein determining the road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set comprises:

taking the distance between a first shape point and a second shape point in each point pair in the optimized set as a launching probability matrix of a Hidden Markov Model (HMM), and taking the matching degree between the first shape point and the second shape point in each point pair in the optimized set as a state transition probability matrix of the HMM;

adjusting first shape points corresponding to second shape points in each point pair based on the emission probability matrix and the state transition probability matrix to obtain each adjusted point pair;

10. The method of claim 9, wherein determining the road navigation data corresponding to the target range based on the first shape point and the second shape point in the adjusted point pairs comprises:

11. The method of claim 1, wherein the target range is determined based on a location at which a target vehicle is located, the method further comprising:

and controlling the movement of the target vehicle according to the road navigation data.

12. A device for processing road navigation data, comprising:

a second set determining module, configured to obtain a second set including a plurality of second point pairs based on the road data, where each of the second point pairs includes a first shape point and associated points of the first shape point, and the associated points include a second shape point and a track point within a set range of the first shape point;

and the road navigation data determining module is used for determining the road navigation data corresponding to the target range based on the first shape point and the second shape point in each point pair in the optimized set.

13. An electronic device, comprising a processor and a memory:

the memory is configured to store a computer program which, when executed by the processor, causes the processor to perform the method of any of claims 1-11.

14. The electronic device according to claim 13, wherein the electronic device is a vehicle-mounted terminal.

15. A computer-readable storage medium, for storing a computer program which, when run on a computer, causes the computer to perform the method of any of claims 1-11.