CN114396956A

CN114396956A - Navigation method and apparatus, computing device, storage medium, and computer program product

Info

Publication number: CN114396956A
Application number: CN202210106679.7A
Authority: CN
Inventors: 李煌
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-01-28
Filing date: 2022-01-28
Publication date: 2022-04-26

Abstract

The present disclosure provides a navigation method and apparatus, a computing device, a computer-readable storage medium, and a computer program product. The navigation method comprises the following steps: acquiring positioning data, wherein the positioning data comprises a navigation starting point position and map data related to the navigation starting point position; determining at least one alternative road from the map data based on the navigation starting point position; generating picture data based on the positioning data for each alternative road; and determining a navigation starting point road from at least one alternative road based on the picture data. By the navigation method, the accuracy of the navigation starting point road is improved, and the user experience is improved. Some embodiments of the disclosure may be applied to the traffic field and may be applied to relevant scenes such as automatic driving, assisted driving, and the like.

Description

Navigation method and apparatus, computing device, storage medium, and computer program product

Technical Field

The present disclosure relates to the field of computer technology, and more particularly, to a navigation method, a navigation apparatus, a computing device, a computer-readable storage medium, and a computer program product.

Background

With the continuous development of computer technology, the use of navigation applications is becoming more and more widespread in the transportation field. The navigation application may be used to provide route guidance services to a user while walking or driving, and may also be used during travel of an unmanned vehicle, robot, or the like. Generally, when navigation is started, it is necessary to determine a navigation start point road from a navigation start point position. When the navigation start point location is not accurately located or the roads near the navigation start point location are dense, the determined navigation start point road may be deviated. This can affect the accuracy of navigation and cause frustration to users using navigation applications, adversely affecting the user experience.

Disclosure of Invention

In view of the above, the present disclosure provides a navigation method, a navigation apparatus, a computing device, a computer-readable storage medium and a computer program product, which may alleviate, reduce or even eliminate the above-mentioned problems.

According to an aspect of the present disclosure, there is provided a navigation method including: acquiring positioning data, wherein the positioning data comprises a navigation starting point position and map data related to the navigation starting point position; determining at least one alternative road from the map data based on the navigation starting point position; generating picture data based on the positioning data for each alternative road; and determining a navigation starting point road from at least one alternative road based on the picture data.

In some embodiments, the picture data comprises at least one of: the navigation system includes direction information of a navigation starting point position, precision information of the navigation starting point position, road information in a vicinity of the navigation starting point position, and information of an upstream road connected to the alternative road.

In some embodiments, the positioning data further comprises a plurality of historical positions of the navigation object in relation to the navigation start position, and wherein generating the picture data based on the positioning data comprises at least one of: generating a direction channel picture based on the navigation starting point position and the direction information of the plurality of historical positions; generating a precision channel picture based on the navigation starting point position and the precision information of the plurality of historical positions; generating a picture of a channel of an adjacent road based on a plurality of roads in the adjacent area of the navigation starting point position; and generating an upstream road channel picture based on the alternative road and an upstream road communicated with the alternative road.

In some embodiments, generating the direction channel picture based on the navigation start position and the direction information of the plurality of historical positions comprises: determining positions of a plurality of points in the direction channel picture, which correspond to the navigation starting point position and the plurality of historical positions respectively, based on the navigation starting point position and the plurality of historical positions; and determining the gray scales of the corresponding points according to the navigation starting point position and the direction information of the plurality of historical positions.

In some embodiments, determining the grayscales of the corresponding plurality of points according to the navigation start position and the direction information of the plurality of historical positions includes: mapping the navigation starting point position and the directions of the plurality of historical positions into corresponding gray values according to a linear mapping scheme from the directions to the gray values; and determining the gray scale of the corresponding points based on the gray scale values obtained by mapping.

In some embodiments, generating the accuracy channel picture based on the accuracy information of the navigation start position and the plurality of historical positions comprises: determining positions of a plurality of points in the precision channel picture, which correspond to the navigation starting point position and the plurality of historical positions respectively, based on the navigation starting point position and the plurality of historical positions; and determining the gray scales of the corresponding points according to the navigation starting point position and the precision information of the plurality of historical positions.

In some embodiments, determining the grayscales of the plurality of points based on the accuracy information of the navigation start position and the plurality of historical positions comprises: mapping the precision of the navigation starting point position and the plurality of historical positions into corresponding gray values according to a linear mapping scheme from precision to gray; and determining the gray scale of the corresponding points based on the gray scale values obtained by mapping.

In some embodiments, generating the picture of the surrounding road based on at least part of the plurality of roads surrounding the navigation start position includes: determining the positions of a plurality of lines corresponding to at least part of roads in the surrounding road channel picture based on the positions of at least part of roads in the plurality of roads around the navigation starting point position; and determining the gray scales of the corresponding lines according to the driving directions of the roads.

In some embodiments, generating the upstream road channel picture based on the alternative road and an upstream road in communication with the alternative road comprises: determining the positions of at least two lines respectively corresponding to the alternative road and the upstream road communicated with the alternative road in the upstream road channel picture based on the positions of the alternative road and the upstream road communicated with the alternative road; the gradation of the line corresponding to the candidate road and the gradation of the line corresponding to the upstream road are determined to be different gradation values.

In some embodiments, generating the picture data based on the positioning data comprises: and generating picture data by taking the navigation starting point position as the central position of the picture.

In some embodiments, determining at least one alternative road from the map data based on the navigation origin position comprises: for each of at least some of the roads in the map data, determining a degree of correlation of the road with the navigation start position based on at least one of a distance difference and a direction difference between the road and the navigation start position; and determining at least one road in at least part of the roads as the alternative road based on the correlation degree.

In some embodiments, determining the navigation origin road from the at least one alternative road based on the picture data comprises: determining the election probability of each alternative road based on the picture data; and determining the alternative road with the highest election probability as the navigation starting point road in the at least one alternative road.

In some embodiments, determining the election probability of each alternative road based on the picture data includes: for each alternative road, the following steps are performed: extracting picture features from picture data corresponding to the alternative road; determining a numerical value pair used for representing the election probability and the improper election probability of the alternative road based on the picture characteristics; and normalizing the numerical value pairs to obtain the election probability of the alternative road.

In some embodiments, determining the election probability of each alternative road based on the picture data includes: and sequentially inputting the picture data corresponding to each alternative road into a navigation starting point road to determine so as to obtain the election probability of each alternative road, wherein the navigation starting point road determination model is a pre-trained machine learning model.

In some embodiments, the navigation origin road determination model is trained by: acquiring a plurality of groups of sample navigation data, wherein each group of sample navigation data comprises sample positioning data, a sample navigation starting point road and a sample actual starting point road, and the sample positioning data comprises a sample navigation starting point position and map data related to the sample navigation starting point position; generating sample picture data based on the sample navigation starting point road and the sample positioning data for each group of sample navigation data; and training the machine learning model by taking the sample picture data of the sample actual starting point road as a positive sample, and the sample picture data of the sample actual starting point road different from the sample navigation starting point road as a negative sample, so as to maximize the accuracy rate of the machine learning model for determining the input sample picture data as the positive sample or the negative sample.

According to another aspect of the present disclosure, there is provided a navigation device including: an acquisition module configured to acquire positioning data, the positioning data including a navigation start position and map data related to the navigation start position; a first determination module configured to determine at least one alternative road from the map data based on the navigation start point position; a generating module configured to generate picture data based on the positioning data for each alternative road; and the second determination module is configured to determine a navigation starting point road from at least one alternative road based on the picture data.

According to yet another aspect of the present disclosure, there is provided a computing device comprising: a memory configured to store computer-executable instructions; a processor configured to perform the navigation method described according to the preceding aspect when the computer executable instructions are executed by the processor.

According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed, perform the navigation method described according to the preceding aspect.

According to yet another aspect of the disclosure, a computer program product comprising computer instructions which, when executed by a processor, implement the navigation method described according to the preceding aspect.

By the navigation method provided by the disclosure, at least one alternative road can be selected near the navigation starting point position, then, for each alternative road, picture data is generated based on the navigation starting point position in the positioning data and map data related to the navigation starting point position, and then the navigation starting point road is determined in the at least one alternative road by analyzing the picture data. Therefore, in the process of determining the navigation starting point road, various information in the navigation starting point position and the related map data, especially the relationship between the navigation starting point position and the related road, can be considered more fully and comprehensively through means such as picture analysis processing, so that the correct, more practical and more reliable navigation starting point road can be screened from at least one alternative road on the basis of comprehensively considering various information, and the possible deviation and even error of the navigation starting point road determination simply depending on positioning data in the related technology are avoided. This helps to improve the accuracy of the determination of the navigation origin road, and further helps to improve the accuracy of the navigation service, thereby improving the user experience.

These and other aspects of the disclosure will be apparent from and elucidated with reference to the embodiments described hereinafter.

Drawings

Further details, features and advantages of the disclosure are disclosed in the following description of exemplary embodiments, taken in conjunction with the accompanying drawings, in which:

FIG. 1 schematically illustrates an example scenario in which a navigation scheme provided by some embodiments of the present disclosure may be applied;

FIG. 2 schematically illustrates an example navigation interface according to some embodiments of the present disclosure;

FIG. 3 schematically illustrates an example flow diagram of a navigation method according to some embodiments of the present disclosure;

4A-4D schematically illustrate examples of channel pictures according to some embodiments of the present disclosure;

FIG. 5 schematically illustrates an example structure diagram of a convolutional neural network model, according to some embodiments of the present disclosure;

FIG. 6 schematically illustrates an example flow diagram of a method of training a machine learning model according to some embodiments of the present disclosure;

7A-7B schematically illustrate examples of sample navigation data according to some embodiments of the present disclosure;

fig. 8 schematically illustrates an example block diagram of a navigation device in accordance with some embodiments of the present disclosure;

fig. 9 schematically illustrates an example block diagram of a computing device in accordance with some embodiments of the disclosure.

Detailed Description

The technical solutions in the present application will be described clearly and completely with reference to the accompanying drawings in the present application. The described embodiments are only some embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without inventive step, are within the scope of the present application.

Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. 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, automatic driving, intelligent traffic, automatic control and the like.

Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, formal learning, active learning, and the like.

With the research and progress of artificial intelligence technology, the artificial intelligence technology is developed and researched in a plurality of fields, such as common smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, unmanned driving, automatic driving, unmanned aerial vehicles, robots, smart medical services, smart customer service, internet of vehicles, automatic driving, smart traffic and the like.

Before describing embodiments of the present disclosure in detail, some related concepts are explained first.

In an embodiment of the present disclosure, the navigation start position refers to a start position when the user uses the navigation service. The starting position may be the position where the user is located, or may be other positions set by the user. The starting position may be automatically measured or manually input by the user.

In the embodiment of the present disclosure, navigating the starting point road refers to navigating the road used by the starting point in the planned road when the user uses the navigation service.

Some embodiments of the present disclosure may be implemented with a Convolutional Neural Network (CNN). Convolutional neural networks are a class of neural network models designed for processing image data, and can achieve very good results in image recognition applications. Convolutional neural networks are generally composed of an input layer, which may be generally used to receive one-dimensional, two-dimensional, or higher-dimensional arrays, an implicit layer, which generally includes convolutional layers, pooling layers, and fully-connected layers, and may sometimes include other modules such as residual modules, and an output layer, which generally is used to output classification results, which may be implemented by means of a logic function or a normalized exponential function, or the like. The convolutional neural network can be trained through supervised learning or unsupervised learning according to the actual application requirements.

The embodiment of the disclosure can be applied to the Traffic field, and can be applied to related scenes such as Intelligent Traffic System (ITS), automatic driving, auxiliary driving and the like. An Intelligent Transportation System is a comprehensive Transportation System which effectively and comprehensively applies advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operational research, artificial intelligence and the like) to Transportation, service control and vehicle manufacturing and strengthens the relation among vehicles, roads and users, thereby forming a comprehensive Transportation System which ensures safety, improves efficiency, improves environment and saves energy.

Fig. 1 schematically illustrates an example scenario 100 in which navigation schemes provided by embodiments of the present disclosure may be applied.

As shown in FIG. 1, the scenario 100 includes a computing device 110. The navigation solution provided by embodiments of the present disclosure may be deployed at the computing device 110 and used to determine a navigation origin road. The computing devices may include, but are not limited to, cell phones, computers, smart voice interaction devices, smart appliances, vehicle terminals, aircraft, and the like. Embodiments of the present disclosure may be applied in a variety of scenarios, including but not limited to cloud technology, artificial intelligence, smart traffic, assisted driving, and the like.

Illustratively, the user 120 may use the navigation service through the computing device 110. For example, user 120 may input instructions through a user interface provided by computing device 110, such as through related physical or virtual keys, through text, voice, or gesture instructions, etc., to launch a navigation application deployed on computing device 110 and/or server 130, view a navigation route, etc.

The scenario 100 may also include a server 130. Optionally, the navigation solution provided by the embodiments of the present disclosure may also be deployed on the server 130. Alternatively, the navigation solution provided by the embodiments of the present disclosure may also be deployed on a combination of the computing device 110 and the server 130. The present disclosure is not particularly limited in this regard. For example, user 120 may access server 130 through computing device 110 via network 150 in order to obtain services provided by server 130.

The server 130 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 basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like. Further, it should be understood that server 130 is shown by way of example only and that other devices or combinations of devices having computing and storage capabilities may alternatively or additionally be used to provide corresponding services.

Optionally, the computing device 110 and/or the server 130 may be linked with the database 140 via the network 150, for example, to retrieve map data or the like from the database 140. Illustratively, the database 140 may be a stand-alone data storage device or device cluster, or may also be a back-end data storage device or device cluster associated with other online services.

Further, in the present disclosure, the network 150 may be a wired network connected via, for example, a cable, an optical fiber, etc., or may be a wireless network such as 2G, 3G, 4G, 5G, Wi-Fi, bluetooth, ZigBee, Li-Fi, etc., or may be an internal connection line of one or several devices, etc.

FIG. 2 schematically shows an example navigation interface 200 according to an embodiment of the present disclosure. Illustratively, the navigation interface 200 may be presented on a terminal device of the user, such as a mobile phone, a tablet computer, an in-vehicle navigation device, a smart watch, etc., for the user to view the navigation route. For example, the navigation interface 200 may be applied to the scene 100 shown in FIG. 1 and may be presented on a display screen of the computing device 110.

As shown, the navigation interface 200 may include a map display area 210 that may display a map near the current navigation location, such as information about roads, buildings, greenbelts, and the like. An indication 220 indicating the current navigation position may be presented in the map display area 210, where the indication 220 indicates a navigation start position, which may represent a direction of the navigation start position by an arrow, which may be an orientation of a navigation positioning device (e.g., a satellite navigation receiver, etc.). Further, optionally, a logo regarding the direction may be displayed, for example, a logo regarding at least one of east, west, south, and north may be displayed around the logo 220. The arrow at the marker 220 may indicate the direction of travel of the navigation route. The navigation interface 200 may also include a text navigation area 230, which may indicate a navigation route in the form of an arrow, text, a combination of both, or the like. The navigation interface 200 may also include a road status overview strip 240 that may display congestion levels for different segments of the navigation route in different colors, patterns, etc. The navigation interface 200 may also include an information presentation area 250 that may display information regarding the length of the navigation route, expected transit time, expected arrival time, number of route traffic lights, and the like. Further, the navigation interface 200 may alternatively or additionally include other elements or regions depending on the actual application scenario requirements.

It should be understood that the navigation interface 200 is merely exemplary. In fact, different navigation interfaces can be designed according to actual requirements, or navigation routes can be presented in the forms of voice broadcasting, text broadcasting and the like.

In the related art, when determining a navigation starting point road, the road is usually screened by characteristic dimensions such as a distance, a direction relationship, and the like between a navigation starting point position and the road. For example, a plurality of filtering strategies may be used to select a road, and a parameter threshold may be set for each filtering strategy (e.g., distance, direction angle difference, etc.) to determine whether a certain road meets the requirement of navigating the starting point road.

However, the inventors have found that the navigation start position is sometimes inaccurate, i.e. deviates from the true start position, due to an unstable strength of the positioning signal or due to the user equipment itself. Therefore, in the actual use process, the above-described solutions in the related art have the following disadvantages. First, the navigation origin road has low accuracy. Because the navigation starting point is inaccurate in position, misjudgment is easy to occur when the navigation starting point road is determined through a fixed screening strategy. For example, when filtering through the example and direction strategy, the inaccuracy of the navigation starting point position may cause the nearest road with the most matching direction to be not the road where the user actually starts the position. Second, the optimization iteration speed is slow. When a screening strategy is formulated or an existing screening strategy is optimized, experienced personnel are required to formulate or optimize the strategy, and a new strategy needs to be repeatedly tested and compared, so that the upper linear speed or the optimization speed of the navigation function is very slow. Third, the coverage of problems is narrow. When solving the problem of wrong navigation starting point road selection through an optimization screening strategy, multiple mutually-exclusive optimization scenes are often met, for example, when the influence of the direction of the navigation starting point position is expected to be increased in some scenes, a road with a longer distance may be selected, and thus other scenes may be negatively influenced. Therefore, when the problem that the navigation starting point road is not accurately selected is solved, the optimized coverage of the screening strategy is narrow, the problem is difficult to consider in all directions, and the requirements of different scenes are met.

Based on the above considerations, the inventors propose a new navigation method that helps solve or alleviate the above-mentioned deficiencies in the related art.

Fig. 3 schematically illustrates an example flow diagram of a navigation method 300 according to an embodiment of this disclosure. Illustratively, the navigation method 300 may be deployed on the computing device 110 or the server 130 in the scenario 100 shown in FIG. 1, or may be deployed on a combination of both.

At step 310, positioning data can be acquired, which can include a navigation origin position and map data related to the navigation origin position. The navigation starting point position can be described by a two-dimensional coordinate formed by longitude and latitude, a three-dimensional coordinate formed by longitude and latitude and altitude, or a two-dimensional or three-dimensional coordinate in other coordinate systems, or can also be described by a relative position with a road, an intersection, a landmark address and the like, and the like. The map data relating to the navigation origin position may direct map data within a range near the navigation origin position, for example, within a range of a preset distance threshold from the navigation origin position, such as within a range of 10 meters, 20 meters, 50 meters, 100 meters, 200 meters, 300 meters, or the like from the navigation origin position. It should be understood that the preset distance threshold may be set manually or automatically depending on the needs of a particular application. Alternatively, the map data related to the navigation start point position may also refer to map data within a range of a rural, county, prefecture, or provincial administrative area including the navigation start point position, or may also refer to map data of a full range including the navigation start point position, or the like. The map data may include road information and may include other relevant information, such as one or more of building information, green belt information, water area information, utility information, and the like.

Alternatively, the positioning data may be locally generated or obtained from an external device, or may be partially locally generated and partially obtained from an external device. Illustratively, in the scenario 100 shown in fig. 1, if the navigation method 300 is deployed on a computing device 110 of a user 120, the navigation origin position may be generated by the computing device 110, and the map data related to the navigation origin position may be stored locally or may be obtained from a server 130 or database 140 via a network; if the navigation method 300 is deployed on the server 130, the navigation origin position may be received from the computing device 110 via a network, and the map data associated with the navigation origin position may be stored locally or may be obtained from an external device, such as the database 140, via a network.

For example, the navigation start position may be determined in various ways. For example, the navigation origin position may be determined by means of a satellite navigation system such as the Global Positioning System (GPS), the GLONASS satellite navigation system (GLONASS), the GALILEO satellite navigation system (GALILEO) and the beidou satellite navigation system (BDS). In such an example, a navigation object (e.g., a vehicle, a mobile terminal, a robot, etc.) may be equipped with a satellite signal receiver that may receive satellite signals and determine a position of the navigation object from the received satellite signals. Alternatively, the navigation origin position may be determined by means of other navigation solutions, for example by means of a combination of one or more of a telecommunications base station, a WiFi signal, a Zigbee signal, a high precision map, a vehicle sensor system comprising accelerometers, wheel encoders, etc. Alternatively, the navigation start position may be manually set by the user.

At step 320, at least one alternative road may be determined from the map data based on the navigation origin position. For example, all or a part of the roads in the acquired map data related to the navigation start point position may be used as the alternative roads. For example, roads in a certain vicinity of the navigation start position may be used as the candidate roads, such as roads in a range of 10 meters, 20 meters, 50 meters, 100 meters, 200 meters or other distances around the navigation start position; alternatively, a preset number of roads closer to the navigation start position may be determined as the alternative roads, such as 3, 5, 8, 10, 15 or another number of roads closer to the navigation start position; or, a road in which the difference between the road driving direction and the direction of the navigation starting point position is within a certain preset angle range may be used as the alternative road, or a preset number of roads in which the difference between the road driving direction and the direction of the navigation starting point position is smaller may be used as the alternative road, and similarly, the preset angle range or the preset number may be set according to actual requirements; alternatively, alternate links may be determined according to other mechanisms or fusing two or more mechanisms.

At step 330, picture data may be generated based on the positioning data for each alternative road. Illustratively, single-channel or multi-channel picture data may be generated based on the positioning data, wherein the multi-channel picture may comprise a plurality of color channels (such as RGB pictures) or a plurality of custom channels. For example, a single-channel grayscale picture or a multi-channel color picture may be generated based on all or part of information in the map data related to the navigation start point position, and the navigation start point position and the alternative road may be marked in the generated picture by a preset form, for example, the navigation start point position may be marked by dot-like identification of a preset shape and/or color, and the alternative road may be marked by a preset color, pattern, line type, or the like. Alternatively, the picture data may be generated by other mechanisms such that the picture data may reflect at least information about the navigation origin position and the alternative road, and may optionally reflect information of at least one other road and other optional information.

In step 340, a navigation start road may be determined from the at least one alternative road based on the picture data. The navigation start point road may be determined based on the picture data by means of various image analysis means. For example, each channel in the single-channel or multi-channel picture data may include a plurality of pixel points, each pixel point may have a corresponding gray value, and thus, each channel in the single-channel or multi-channel picture data may be represented as a matrix, and each element in the matrix may be a gray value of the corresponding pixel point. Such data may be analyzed by various data analysis means to determine which alternative road is best suited as the navigation origin road. For example, the picture data may also be preprocessed by cropping, filtering, etc., so as to better determine the navigation starting point road based on the picture data.

Through the navigation method 300, in the process of determining the navigation starting point road, the conversion from the positioning data to the picture data can be realized, and the navigation starting point position and various information in the related map data can be considered more fully and comprehensively by means of picture analysis means, so that the correct navigation starting point road can be obtained by screening from at least one alternative road on the basis of fusing various factors. This helps to improve the accuracy of the determined navigation origin road, and further helps to improve the quality of navigation services, thereby improving user experience.

In some embodiments, the picture data generated in step 330 may include at least one of: the navigation system includes direction information of a navigation starting point position, precision information of the navigation starting point position, road information in a vicinity of the navigation starting point position, and information of an upstream road connected to the alternative road. Illustratively, the direction information and/or the accuracy information of the navigation position may be characterized in the picture data in the form of a shape, a color feature, or the like. The road information within the vicinity of the navigation origin position may include one or more of location information, driving direction information, or other attribute information of the road, wherein the vicinity may guide an area within a preset threshold distance range near the navigation origin position, such as an area within 10 meters, 20 meters, 50 meters, 100 meters, 200 meters, or other distance range around the navigation origin position. The information of the upstream road in communication with the alternative road may include one or more of position information, driving direction information, or other attribute information of the upstream road, where the upstream road may refer to a road that may be driven into and directly connected to the alternative road. There may be 1, 2 or more upstream roads in communication with one alternative road. Similarly, for example, the road information in the vicinity of the navigation start point position and/or the information of the upstream road communicating with the alternative road may be characterized in the picture data by the form of a shape, a color feature, or the like.

By including one or more of direction information of the navigation start point position, precision information of the navigation start point position, road information in the vicinity of the navigation start point position, and information of an upstream road communicating with the alternative road in the picture data, it is helpful to improve the accuracy of the navigation start point position. Specifically, the direction information of the navigation starting point position can reflect the current orientation of the navigation object, which is helpful for judging the possible driving direction of the navigation object, and is further helpful for screening a proper navigation starting point road; the accuracy information of the navigation starting point position can reflect the accuracy degree of the navigation starting point position, which can be used as reference information when the navigation starting point road is screened, for example, to adjust the dependence degree of the navigation starting point road on the navigation starting point position; the road information in the vicinity of the navigation starting point position can reflect the overall road distribution situation near the navigation starting point position, which is helpful for comprehensively considering the distribution situation of other roads nearby when determining the navigation starting point road; the information of the upstream road connected to the alternative road may reflect a road that may be driven into the alternative road, which contributes to reducing the probability of misselection of the navigation origin road when the history track of the navigation object is combined.

The picture data may alternatively or additionally include other information according to actual application requirements. Further, it is to be understood that the above-described picture data may include multi-channel pictures, wherein each channel picture may reflect only one of the above-described various information. Different information can be respectively highlighted in each channel picture, and the analysis efficiency and the analysis effect of the picture data are improved. Alternatively, the various information may be embodied in a mono picture, or one of the multi-channel pictures may embody two or more kinds of the various information, depending on the specific setting.

In some embodiments, the positioning data may further comprise a plurality of historical positions of the navigation object associated with the navigation origin position. The plurality of historical locations may be stored locally or retrieved from an external device. The history position of the navigation object related to the navigation start position may refer to a position acquired within a time period before the time when the navigation object is at the navigation start position, or may refer to a preset number of positions acquired before the navigation start position, or may also refer to a position within a distance range acquired before the navigation object is at the navigation start position. For example, the plurality of historical positions may be a series of positioning points obtained by a satellite navigation system such as GPS, GLONASS, GALILEO, BDS, which may play a role of assisting in the determination of the navigation origin road. For example, the plurality of historical positions may be positions acquired before the current time or a period of time before the navigation object stops moving last time, such as positions acquired in the previous 50s, 60s, 70s, 80s or other periods of time, or such as 50, 60, 70, 80 or other numbers of positions acquired before the navigation start position, and so on. Alternatively, the plurality of history positions may be continuously acquired positions, or may be positions obtained by sampling continuously acquired positions. In some embodiments, the process of generating picture data based on the positioning data may include generating at least one of: a direction channel picture, a precision channel picture, an adjacent channel picture, and an upstream channel picture. In addition, the generated picture data may optionally include other forms of channel pictures.

Fig. 4A-4D schematically show a direction channel picture 400A, a precision channel picture 400B, an adjacent lane channel picture 400C, and an upstream lane channel picture 400D, respectively, according to an embodiment of the invention. It should be understood that the coordinate information of the left and lower sides of each channel picture in fig. 4A to 4D is shown only for ease of understanding, and the actually generated channel pictures may not include such coordinate information. 4A-4D do not show gray scale information, various points or lines therein may have gray scales, and the gray scale values thereof may be determined according to various embodiments in the following description.

In some embodiments, a direction channel picture 400A as shown in fig. 4A may be generated based on the navigation start position and the direction information of the plurality of historical positions.

In some embodiments, the direction channel picture may be generated based on the navigation start position and the direction information of the plurality of historical positions by: determining positions of a plurality of points in the direction channel picture, which correspond to the navigation starting point position and the plurality of historical positions respectively, based on the navigation starting point position and the plurality of historical positions; and determining the gray scales of the corresponding points according to the navigation starting point position and the direction information of the plurality of historical positions. For example, the obtained navigation starting point position and each of the plurality of historical positions may be mapped to a position of a corresponding pixel point in the direction channel picture according to a preset scale. For example, as shown in fig. 4A, the navigation start position may be mapped to a pixel point 411 at (100 ), i.e., a central pixel point of the direction channel picture, and the plurality of history positions may be mapped to a series of pixel points 412 marked by a dashed box. Alternatively, each location may be represented by one or a group of pixel points.

The gray levels of the pixel point 411 corresponding to the navigation start position and the pixel point 412 corresponding to the plurality of history positions may be determined according to the direction information thereof. For example, when using GPS positioning, the acquired GPS positioning may carry a corresponding direction angle value, which may serve as direction information of the navigation start position and the historical position. The direction angle value may be referenced to a preset direction, for example, to the true north direction. In some embodiments, the gray scale for each point may be determined by: mapping the navigation starting point position and the directions of the plurality of historical positions into corresponding gray values according to a linear mapping scheme from the directions to the gray values; and determining the gray scale of the corresponding points based on the gray scale values obtained by mapping. A linear mapping scheme from direction to gray scale may map a direction angle of 0 to 360 degrees (or-180 to 180 degrees or other range) to a gray scale value of 0 to 255, or to a gray scale value interval between 0 and 255, e.g. to a gray scale value interval [36,216] or other gray scale value interval. The gray values outside the gray value interval can be reserved for other purposes, such as the background gray of the direction channel picture, the corresponding gray of the position not carrying the direction information, and the like.

Alternatively, the above linear mapping scheme from direction to grayscale can be described by the following mapping function:

wherein the content of the first and second substances,

in order to be the direction angle,

and

the maximum and minimum of the direction angle, respectively, can be 360 and 0, respectively,

in order to set the upper limit of the gray scale,

for example, the set lower gray scale limit may be 216 and 36, respectively. Alternatively, if there is a position that does not carry direction information in the starting point navigation position and the plurality of history positions, the gray scale of the corresponding point may be set to a preset fixed gray scale value, for example, to 255 or another value.

In addition, in the direction channel picture, pixel points corresponding to the navigation starting point position and adjacent positions in the plurality of historical positions can be connected through line segments, so that the traveling track of the navigation object can be displayed more clearly. Here, the adjacent position refers to a position adjacent in acquisition time. The grey scale of the connecting line segment between adjacent positions may be determined as a preset fixed grey scale value, which may be a grey scale value outside the grey scale value interval involved in the direction-to-grey scale linear mapping scheme.

In some embodiments, the precision channel picture 400B as shown in fig. 4B may be generated based on the precision information of the navigation start position and the plurality of historical positions.

In some embodiments, the precision channel picture may be generated based on the precision information of the navigation start position and the plurality of historical positions by: determining positions of a plurality of points in the precision channel picture, which correspond to the navigation starting point position and the plurality of historical positions respectively, based on the navigation starting point position and the plurality of historical positions; and determining the gray scales of the corresponding points according to the navigation starting point position and the precision information of the plurality of historical positions. Similar to the aforementioned direction channel picture, for example, the acquired navigation starting point position and the plurality of historical positions may be mapped to positions of corresponding pixel points in the direction channel picture according to a preset scale. For example, as shown in fig. 4B, the navigation start position may be mapped to a pixel 421 at (100 ), i.e., a central pixel of the direction channel picture, and the plurality of history positions may be mapped to a series of pixels 422 marked by a dashed box. Alternatively, each location may be represented by one or a group of pixel points.

The gray levels of the pixel 421 corresponding to the navigation start position and the pixel 422 corresponding to the plurality of history positions may be determined according to the accuracy information thereof. For example, when using GPS positioning, the acquired GPS positioning may carry a corresponding accuracy factor, which may be used as accuracy information of the navigation starting point position and the historical position. The accuracy factor may be derived by the GPS receiver based on the strength of the satellite signals, the relative positions of the GPS receiver and the satellites, and other factors. In some embodiments, the gray scale for each point may be determined by: mapping the precision of the navigation starting point position and the plurality of historical positions into corresponding gray values according to a linear mapping scheme from precision to gray; and determining the gray scale of the corresponding points based on the gray scale values obtained by mapping. A linear mapping scheme from precision to grey scale may map the precision interval to grey scale values of 0 to 255, or to grey scale value intervals between 0 and 255, for example to grey scale value interval [36,216] or other grey scale value intervals. The gray values outside the gray value interval can be reserved for other purposes, such as the background gray of the precision channel picture, the corresponding gray of the position not carrying the precision information, and the like. The above-mentioned precision interval may comprise all possible precisions, or only a part of the possible precisions. For example, the above-mentioned precision interval may be set to [0,250], and the precision exceeding 250 is directly set to 250. After the precision reaches a certain height, the accurate navigation initial position can be accurately represented, so that higher precision can be uniformly replaced by a certain precision value to save computing resources, and the gray level difference of the precision in a low precision range after mapping is enlarged, thereby being beneficial to improving the image processing effect and improving the accuracy of the finally determined navigation starting point road.

Alternatively, the above-described linear mapping scheme from precision to grayscale can be described by the following mapping function:

wherein, acc is a precision value,

and

the maximum and minimum values of the precision value, respectively, may be, for example, 250 and 0, respectively (the precision value exceeding 250 may be directly set to 250),

in order to set the upper limit of the gray scale,

for example, 216 and 36 may be respectively set as the set lower gray limit. Alternatively, if there is a position that does not carry precision information in the starting point navigation position and the plurality of historical positions, the gray scale of the corresponding point may be set to a preset fixed gray scale value, for example, to 255 or another value.

Further, similarly to what has been described with respect to the direction channel picture, in the precision channel picture, the pixel points corresponding to the navigation start position and the adjacent position in the plurality of history positions may also be connected by a line segment so as to more clearly display the travel trajectory of the navigation object.

In some embodiments, the adjacent road lane picture 400C as shown in fig. 4C may be generated based on a plurality of roads within the vicinity of the navigation start point position.

In some embodiments, the surrounding road-to-road picture may be generated based on at least part of the plurality of roads surrounding the navigation start position by: determining the positions of a plurality of lines corresponding to at least part of roads in the surrounding road channel picture based on the positions of at least part of the roads in the surrounding navigation starting point position; and determining the gray scales of the corresponding lines according to the driving directions of the roads. For example, the positions of a plurality of lines in the picture of surrounding road channels may be determined based on roads within a vicinity of the navigation start point position, where each line corresponds to one road. For example, as shown in fig. 4C, roads within a vicinity of the navigation start point position may be mapped as a plurality of lines 431 in the adjacent road-to-road picture 400C. The road in the vicinity may be a road within a distance range of 10 meters, 20 meters, 50 meters, 100 meters, 200 meters, 300 meters, or other distance range from the navigation start point position, or may be a road that falls wholly or partially within the drawing area. For example, the positions of the respective shape points may be determined in the surrounding road channel picture based on the positions of the shape points of at least some of the plurality of roads surrounding the navigation start point position, and then the shape points may be connected to determine the positions of the lines corresponding to the respective roads. Alternatively, the positions of a plurality of lines corresponding to the road in the picture of the surrounding road channels may be determined in other manners, for example, the positions of preset nodes in the road may be used for determination.

The gradation of a line corresponding to at least a part of the plurality of roads around the navigation start point position may be determined according to the traveling direction of the corresponding road. For example, a driving direction at a point on a road closest to the navigation initial position may be determined as the driving direction of the road; or, the average driving direction at a point on the road where the distance from the navigation initial position is less than the preset threshold may be determined as the driving direction of the road; and so on. In some embodiments, the gray scale of each line may be determined by: according to a linear mapping scheme from the driving direction to the gray level, mapping the form direction of the road into the corresponding gray level value; and determining the gray levels of the corresponding lines based on the gray levels obtained by mapping. The linear mapping scheme from driving direction to grayscale may map a driving direction angle of 0 to 360 degrees (or-180 to 180 degrees or other range) to a grayscale value of 0 to 255, or to a grayscale value interval between 0 and 255, e.g. to a grayscale value interval [36,216] or other grayscale value interval. The linear mapping scheme from the driving direction to the grayscales can be described by a mapping function similar to the linear mapping scheme from the direction to the grayscales, which is not described herein, but the upper grayscale limit and the lower grayscale limit in the two linear mapping schemes can be set identically or differently according to actual needs.

In some embodiments, an upstream road channel picture 400D as shown in fig. 4D may be generated based on the alternative road and the upstream road in communication with the alternative road.

In some embodiments, the upstream road channel picture may be generated based on the alternative road and an upstream road in communication with the alternative road by: determining the positions of at least two lines respectively corresponding to the alternative road and an upstream road communicated with the alternative road in the upstream road channel picture based on the positions of at least part of roads in a plurality of roads around the navigation starting point position; the gradation of the line corresponding to the candidate road and the gradation of the line corresponding to the upstream road are determined to be different gradation values. For example, the location of the corresponding line may be determined based on the alternative road and the corresponding upstream road according to a process similar to that described with respect to FIG. 4C. For example, as shown in fig. 4C, the alternative road may be mapped to a line marked with a dashed box 441 in the upstream road map 400C, and the upstream road may be mapped to a line marked with a dashed box 442. The gradations of the line corresponding to the alternative road and the upstream road may be determined to be different preset fixed values, for example, the gradation of the line corresponding to the alternative road may be determined to be 112, and the gradation of the line corresponding to the upstream road may be determined to be 45. Alternatively, the gradation preset fixed value may be set to other values.

In some embodiments, the picture data may be generated with the navigation start position as the center position of the picture. For example, each of the channel pictures shown in fig. 4A-4D may each have the navigation start position as the center position of the channel picture. This helps to more comprehensively embody trajectory information, road information, and the like in various directions around the navigation start point position. Furthermore, when the picture data includes a plurality of channel pictures, it also helps to synchronize the display areas of the respective channel pictures. Therefore, the processing efficiency and the processing effect of the picture data can be further improved, and the navigation starting point road can be determined more quickly and accurately. Alternatively, the navigation starting point position may be set at other positions in the picture. In addition, the scale of each channel picture can be kept consistent, so that the displayed space range of each channel picture is kept consistent.

It should be appreciated that in each of the channel pictures described with reference to fig. 4A-4D, incomplete mapping of partial roads or historical locations may occur due to limitations in picture size and scale. For example, among the acquired plurality of historical positions, only part of the historical positions may be embodied in the direction channel picture and the precision channel picture; in the surrounding road passage picture, only part of the road sections of one or more roads may be represented; in the upstream road channel picture, only a partial section of the alternative road or the upstream road may be able to be embodied, or even the upstream road may not be able to be embodied; and so on.

Also, other forms of channel pictures than the one described with reference to fig. 4A-4D may be used instead or in addition. For example, a channel picture may be generated based on at least some of the roads around the navigation start point position and the alternative roads to reflect the relationship between the surrounding roads and the alternative roads; generating a channel picture based on the navigation starting point position and the position and/or the direction of the alternative road to embody the relationship between the navigation starting point position and the alternative road; and so on.

In some embodiments, step 320 shown in FIG. 3 may be implemented by: for each of at least some of the roads in the map data, determining a degree of correlation of the road with the navigation start position based on at least one of a distance difference and a direction difference between the road and the navigation start position; and determining at least one road in at least part of the roads as the alternative road based on the correlation degree. For example, a distance between the navigation start position and at least a portion of a road in the map data may be determined, which may be the shortest distance from the navigation start position to a point on the road. And, alternatively or additionally, a direction difference may be determined between the direction of the navigation start position and the direction of travel of at least a portion of the roads in the map data, the direction of travel of a road may refer to the direction of travel at the point closest in distance to the navigation start position, and the direction difference may refer to the difference in direction angle between the two. Determining roads with distances smaller than a preset threshold and/or direction differences smaller than the preset threshold as alternative roads; alternatively, the two and optionally other metrics may be combined into a single correlation value, and the road whose correlation value satisfies the threshold condition is determined as the alternative road; alternatively, the roads may be sorted according to the distance and/or direction difference or according to the correlation value, and a preset number of roads ranked in the front (i.e., the distance is small and/or the direction difference is small, or the correlation is high) may be determined as the candidate roads. Through the steps, at least one suitable alternative road can be conveniently determined. In addition, the preliminary screening is carried out on the roads near the navigation starting point position, so that the determination efficiency of the navigation starting point road is improved.

In some embodiments, step 340 illustrated in FIG. 3 may be implemented by: determining the election probability of each alternative road based on the picture data; and determining the alternative road with the highest election probability as the navigation starting point road in the at least one alternative road. For example, the election probability of the corresponding alternative road may be determined based on the picture data through various picture data analysis means. For example, a machine learning model or other data feature analysis means may be employed.

In some embodiments, the election probability of each alternative road may be determined based on the picture data by: for each alternative road, the following steps are performed: extracting picture features from picture data corresponding to the alternative road; determining a numerical value pair used for representing the election probability and the improper election probability of the alternative road based on the picture characteristics; and normalizing the numerical value pairs to obtain the election probability of the alternative road. Illustratively, this process may be implemented by machine learning models, or by other means of picture data analysis.

In some embodiments, the election probability of each alternative road may be determined based on the picture data by: and sequentially inputting the picture data corresponding to each alternative road into a navigation starting point road determination model to obtain the election probability of each alternative road, wherein the navigation starting point road determination model is a pre-trained machine learning model. Alternatively, the machine learning model may be a variety of existing or self-designed models, such as a general convolutional neural network model, a VGG model, a Resnet model, and the like. By means of the machine learning model, on one hand, the relation among the navigation starting point position, the historical position and the related road can be learned from the space dimension, so that the alternative road can be correctly screened, and the accuracy of the determined navigation starting point road is higher. On the other hand, the machine learning model can learn a plurality of complex conditions which cannot be judged by the manually specified rule strategies, so that the defects of low function optimization iteration speed and high strategy formulation experience requirement in the related technology can be avoided, the calculation complexity is effectively reduced, the working efficiency is improved, the network resources are saved, and the network resource scheduling is optimized.

Illustratively, the machine learning model may be a convolutional neural network model. For example, the election probability of each alternative road may be determined based on the picture data by means of the convolutional neural network model 500 shown in fig. 5. As shown in FIG. 5, the convolutional neural network model 500 includes three

convolutional layers

502, 504, 506 and three fully-connected

layers

508, 509, 510. Illustratively, convolution layers 502, 504, and 506 may each employ a 3 x 3 convolution kernel, and the step sizes may each be 2. Each convolutional layer may be followed by a

pooling layer

503, 505, or 507. Illustratively, pooling

layers

503, 505, and 507 may each employ 2 x 2 pooling windows. For example, the image data generated in the foregoing step 330 may be input to the input layer 501 of the neural network model 500, wherein the input image data may include four channel images described with respect to fig. 4A-4D, and the pixels thereof may be preset to 200 × 200, or other channel numbers and/or pixel values may also be preset according to specific requirements. Subsequently, the input image data can be processed by the convolutional layer, the pooling layer and the full-link layer, feature extraction is performed, and two output values are finally obtained, wherein the two output values can be used for representing the election probability and the improper election probability of the alternative road. Finally, the two output values may be normalized, for example by means of a softmax function, to obtain the final classification result. The classification result may include two values, which are the election probability and the improper selection probability of the alternative road, respectively. The higher the election probability is, the more suitable the corresponding alternative road is as the navigation starting point road.

Through experiments, when the election probability of an alternative road is determined based on picture data, the relation between accuracy and efficiency can be well balanced through the convolutional neural network model 500 described with reference to fig. 5, and the expected accuracy can be met while the processing speed is high, so that the model can well adapt to the performance requirements of online use. However, it will be appreciated by those skilled in the art that the convolutional neural network model described with respect to fig. 5 is merely exemplary, and that other types of machine learning models may be employed to determine the election probability of an alternative road based on picture data. Alternatively, in the case of using a convolutional neural network model, different network structures may be used, such as different numbers of convolutional layers, pooling layers, full-link layers, or different sizes of convolutional cores, pooling windows, the number of full-link layer units, or different channel numbers, etc. In other words, the above values can be adjusted according to the actual application requirements.

In some embodiments, the machine learning model described above may be pre-trained by a training method 600 as shown in fig. 6 to obtain a navigation origin road determination model.

At step 610, a plurality of sets of sample navigation data may be acquired, each set of sample navigation data may include sample positioning data, sample navigation start point roads, and sample actual start point roads, and the sample positioning data may include a sample navigation start point position and map data related to the sample navigation start point position. For example, the sample navigation data may be obtained based on log data related to a navigation start road selection process in historical navigation. For example, a plurality of sets of sample navigation data may be obtained by combining the navigation history log data and the user real track, where the sample positioning data and the sample navigation start road may be obtained from the navigation history log data, the sample navigation start road may be a navigation start road determined in the history navigation process, and the sample actual start road may be determined according to the user real track, and the sample actual start road is a start road actually selected by the user. If the sample navigation starting point road in the navigation history log data is consistent with the sample actual starting point road determined by the user real track, the determined sample navigation starting point road can be considered to be correct, otherwise, the determined sample navigation starting point road can be considered to be wrong. Alternatively, a large amount of sample navigation data may be collected in order to improve the training effect.

Illustratively, fig. 7A and 7B schematically show two sets of sample navigation data. As shown in fig. 7A, in the sample navigation data 700A, a sample navigation start point position 711 and map data related to the sample navigation start point position 711 are presented, and a sample navigation start point road 713 and a user real trajectory 714 are also presented. In addition, the sample navigation data 700A also presents an optional plurality of sample historical locations 712, which are similar to the plurality of historical locations described previously. As can be seen, in the sample navigation data 700A, the sample navigation origin road 713 and the sample actual origin road obtained from the user real trajectory 714 are coincident, and therefore, the sample navigation origin road 713 may be considered to be correct. As shown in fig. 7B, in the sample navigation data 700B, a sample navigation start position 721 and map data related to the sample navigation start position 721 are presented, and a navigation start road 723 and a sample actual start road 724 are also presented. In addition, the sample navigation data 700B also presents an optional plurality of sample historical locations 722, which are similar to the historical locations described previously. As can be seen, in the sample navigation data 700B, the sample navigation start point road 723 and the sample actual start point road obtained from the user real trajectory 724 are inconsistent, and therefore, the sample navigation start point road 723 may be considered as erroneous.

At step 620, sample picture data may be generated for each set of sample navigation data based on the sample navigation origin road and the sample positioning data. This step may be implemented according to various embodiments described with respect to step 330 of fig. 3, where the correlation step is performed with the sample navigation origin road in place of the alternate road. The generated sample picture data may constitute a data set used in the model training process.

In step 630, the machine learning model may be trained by taking sample picture data of the sample actual starting point road that is the same as the sample navigation starting point road as a positive sample and taking sample picture data of the sample actual starting point road that is different from the sample navigation starting point road as a negative sample, so as to maximize the accuracy rate of the machine learning model in determining that the input sample picture data is a positive sample or a negative sample. For example, the generated sets of sample navigation data may be sequentially input to a machine learning model to be trained, and then a selection probability of the sample navigation start point road may be determined based on an output of the machine learning model, which may be regarded as a probability that the corresponding sample navigation data is a positive sample. Illustratively, the labels of the positive and negative examples are set to 1 and 0, respectively, so that the accuracy of the machine learning model can be measured by comparing the winning probability obtained based on the output of the machine learning model with the difference of the labels. For example, a loss function may be constructed according to the difference between the elected probability obtained based on the output of the machine learning model and the label, and various model parameters may be adjusted during the training process to minimize the loss function.

In some embodiments, the data set formed by the sample picture data may be split, and 70% of the sample picture data may be randomly extracted as a training data set, 10% as a verification data set, and 20% as a testing data set. The training data set may be used to train the model, the validation data set may be used to validate whether the model is trained, and the test data set may be used to test the model effect. Therefore, through the training, verifying and testing processes, the training effect of the model can be effectively guaranteed, and the trained model can be reliably and accurately used for determining the navigation starting point road. Alternatively, the data set may be split according to other proportions.

Fig. 8 schematically illustrates an example block diagram of a navigation device 800, in accordance with some embodiments of the present disclosure. As shown in fig. 8, the navigation device 800 includes an acquisition module 810, a first determination module 820, a generation module 830, and a second determination module 840. Illustratively, the navigation device 1000 may be deployed on the computing device 110, the server 130, or a combination of both, shown in fig. 1.

In particular, the obtaining module 810 may be configured to obtain positioning data, the positioning data comprising a navigation origin position and map data related to the navigation origin position; the first determination module 820 may be configured to determine at least one alternative road from the map data based on the navigation origin position; the generating module 830 may be configured to generate picture data based on the positioning data for each alternative road; the second determination module 840 may be configured to determine the navigation origin road from the at least one alternative road based on the picture data.

It is understood that the navigation device 800 may be implemented in software, hardware, or a combination of software and hardware. Several different modules may be implemented in the same software or hardware configuration, or one module may be implemented by several different software or hardware configurations.

Furthermore, the navigation device 800 may be used to implement the navigation method 300 described above, the relevant details of which have been described in detail above and, for the sake of brevity, will not be repeated here. The navigation device 800 may have the same features and advantages as described in relation to the previous method.

Fig. 9 schematically illustrates an example block diagram of a computing device 900 in accordance with some embodiments of this disclosure. For example, it may represent the computing device 110 or server 130 of fig. 1, or other computing device that may be used to deploy the navigation apparatus 800 provided by the present disclosure.

As shown, the example computing device 900 includes a processing system 901, one or more computer-readable media 902, and one or more I/O interfaces 903 communicatively coupled to each other. Although not shown, the computing device 900 may also include a system bus or other data and command transfer system that couples the various components to one another. A system bus can include any one or combination of different bus structures, such as a memory bus or memory controller, a peripheral bus, a universal serial bus, and/or a processor or local bus that utilizes any of a variety of bus architectures, or that also includes data lines, such as control and data lines.

Processing system 901 represents functionality to perform one or more operations using hardware. Thus, the processing system 901 is illustrated as including hardware elements 904 that may be configured as processors, functional blocks, and so forth. This may include implementing an application specific integrated circuit or other logic device formed using one or more semiconductors in hardware. Hardware element 904 is not limited by the materials from which it is formed or the processing mechanisms employed therein. For example, a processor may be comprised of semiconductor(s) and/or transistors (e.g., electronic Integrated Circuits (ICs)). In such a context, processor-executable instructions may be electronically-executable instructions.

The computer-readable medium 902 is illustrated as including a memory/storage 905. Memory/storage 905 represents memory/storage associated with one or more computer-readable media. The memory/storage 905 may include volatile storage media (such as Random Access Memory (RAM)) and/or nonvolatile storage media (such as Read Only Memory (ROM), flash memory, optical disks, magnetic disks, and so forth). The memory/storage 905 may include fixed media (e.g., RAM, ROM, a fixed hard drive, etc.) as well as removable media (e.g., flash memory, a removable hard drive, an optical disk, and so forth). Illustratively, the memory/storage 905 may be used to store various map data, navigation data, and the like mentioned in the above embodiments. The computer-readable medium 902 may be configured in various other ways as further described below.

One or more input/output interfaces 903 represent functionality that allows a user to enter commands and information to computing device 900, and also allows information to be presented to the user and/or sent to other components or devices using various input/output devices. Examples of input devices include a keyboard, a cursor control device (e.g., a mouse), a microphone (e.g., for voice input), a scanner, touch functionality (e.g., capacitive or other sensors configured to detect physical touch), a camera (e.g., motion that does not involve touch may be detected as gestures using visible or invisible wavelengths such as infrared frequencies), a network card, a receiver, and so forth. Examples of output devices include a display device, speakers, printer, haptic response device, network card, transmitter, and so forth. For example, in the above-described embodiments, the user may be allowed to perform various interactive operations through the input device, such as launching a navigation application, inputting navigation start and/or end positions, and the like, and viewing a navigation route through the output device.

Computing device 900 also includes a navigation application 906. The navigation application 906 may be stored as computer program instructions in the memory/storage 905. The navigation application 906, along with the processing system 901 and the like, may implement all of the functionality of the various modules of the navigation device 800 described with respect to fig. 8.

Various techniques may be described herein in the general context of software, hardware, elements, or program modules. Generally, these modules include routines, programs, objects, elements, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The terms "module," "functionality," and the like, as used herein generally represent software, firmware, hardware, or a combination thereof. The features of the techniques described herein are platform-independent, meaning that the techniques may be implemented on a variety of computing platforms having a variety of processors.

An implementation of the described modules and techniques may be stored on or transmitted across some form of computer readable media. Computer readable media can include a variety of media that can be accessed by computing device 900. By way of example, and not limitation, computer-readable media may comprise "computer-readable storage media" and "computer-readable signal media".

"computer-readable storage medium" refers to a medium and/or device, and/or a tangible storage apparatus, capable of persistently storing information, as opposed to mere signal transmission, carrier wave, or signal per se. Accordingly, computer-readable storage media refers to non-signal bearing media. Computer-readable storage media include hardware such as volatile and nonvolatile, removable and non-removable media and/or storage devices implemented in a method or technology suitable for storage of information such as computer-readable instructions, data structures, program modules, logic elements/circuits or other data. Examples of computer readable storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical storage, hard disks, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or other storage devices, tangible media, or an article of manufacture suitable for storing the desired information and accessible by a computer.

"computer-readable signal medium" refers to a signal-bearing medium configured to transmit instructions to the hardware of computing device 900, such as via a network. Signal media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave, data signal or other transport mechanism. Signal media also includes any information delivery media. By way of example, and not limitation, signal media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media.

As previously described, hardware elements 901 and computer-readable media 902 represent instructions, modules, programmable device logic, and/or fixed device logic implemented in hardware form that may be used in some embodiments to implement at least some aspects of the techniques described herein. The hardware elements may include integrated circuits or systems-on-chips, Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs), Complex Programmable Logic Devices (CPLDs), and other implementations in silicon or components of other hardware devices. In this context, a hardware element may serve as a processing device that performs program tasks defined by instructions, modules, and/or logic embodied by the hardware element, as well as a hardware device for storing instructions for execution, such as the computer-readable storage medium described previously.

Combinations of the foregoing may also be used to implement the various techniques and modules described herein. Thus, software, hardware, or program modules and other program modules may be implemented as one or more instructions and/or logic embodied on some form of computer-readable storage medium and/or by one or more hardware elements 901. Computing device 900 may be configured to implement particular instructions and/or functions corresponding to software and/or hardware modules. Thus, implementing modules as modules executable by computing device 900 as software may be implemented at least partially in hardware, for example, using computer-readable storage media of a processing system and/or hardware elements 901. The instructions and/or functions may be executed/operable by, for example, one or more computing devices 900 and/or processing systems 901 to implement the techniques, modules, and examples described herein.

The techniques described herein may be supported by these various configurations of computing device 900 and are not limited to specific examples of the techniques described herein.

It will be appreciated that embodiments of the disclosure have been described with reference to different functional units for clarity. However, it will be apparent that the functionality of each functional unit may be implemented in a single unit, in a plurality of units or as part of other functional units without departing from the disclosure. For example, functionality illustrated to be performed by a single unit may be performed by a plurality of different units. Thus, references to specific functional units are only to be seen as references to suitable units for providing the described functionality rather than indicative of a strict logical or physical structure or organization. Thus, the present disclosure may be implemented in a single unit or may be physically and functionally distributed between different units and circuits.

The present disclosure provides a computer-readable storage medium having stored thereon computer-readable instructions, which when executed, implement the above-described navigation method.

The present disclosure provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computing device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to cause the computing device to perform the navigation method provided in the various embodiments described above.

Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed subject matter, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

It is to be understood that in particular embodiments of the present disclosure, navigation positioning data, navigation history log data, etc. of the user are involved. When embodiments of the present disclosure involving such data are deployed in a particular product or technology, user permission or consent needs to be obtained, and the collection, use, and processing of the relevant data needs to comply with relevant laws and regulations and standards in the relevant countries and regions.

Claims

1. A navigation method, comprising:

acquiring positioning data, wherein the positioning data comprises a navigation starting point position and map data related to the navigation starting point position;

determining at least one alternative road from the map data based on the navigation start point position;

generating picture data based on the positioning data for each alternative road;

and determining a navigation starting point road from the at least one alternative road based on the picture data.

2. The navigation method of claim 1, wherein the picture data comprises at least one of: the navigation system includes direction information of a navigation starting point position, precision information of the navigation starting point position, road information in a vicinity of the navigation starting point position, and information of an upstream road connected to the alternative road.

3. A navigation method according to claim 1 or 2, wherein said positioning data further comprises a plurality of historical positions of a navigation object related to said navigation start position, and wherein said generating picture data based on said positioning data comprises at least one of:

generating a direction channel picture based on the navigation starting point position and the direction information of the plurality of historical positions;

generating a precision channel picture based on the navigation starting point position and the precision information of the plurality of historical positions;

generating a picture of adjacent road channels based on a plurality of roads in the adjacent area of the navigation starting point position;

and generating an upstream road channel picture based on the alternative road and an upstream road communicated with the alternative road.

4. The navigation method of claim 3, wherein the generating a direction channel picture based on the navigation start position and the direction information of the plurality of historical positions comprises:

determining positions of a plurality of points in the direction channel picture, which correspond to the navigation start point position and the plurality of historical positions, respectively, based on the navigation start point position and the plurality of historical positions;

and determining the gray scales of the corresponding points according to the navigation starting point position and the direction information of the plurality of historical positions.

5. The navigation method of claim 4, wherein the determining the gray scale of the corresponding plurality of points according to the navigation start position and the direction information of the plurality of historical positions comprises:

mapping the navigation starting point position and the directions of the plurality of historical positions into corresponding gray values according to a linear mapping scheme from the directions to the gray values;

and determining the gray scale of the corresponding points based on the gray scale values obtained by mapping.

6. The navigation method of claim 3, wherein the generating an accuracy channel picture based on the accuracy information of the navigation origin position and the plurality of historical positions comprises:

determining positions of a plurality of points in the precision channel picture, which correspond to the navigation starting point position and the plurality of historical positions respectively, based on the navigation starting point position and the plurality of historical positions;

and determining the gray scales of the corresponding points according to the navigation starting point position and the precision information of the plurality of historical positions.

7. The navigation method of claim 6, wherein the determining the grayscales of the plurality of points according to the accuracy information of the navigation start position and the plurality of historical positions comprises:

mapping the navigation starting point position and the accuracies of the plurality of historical positions into corresponding gray values according to a linear mapping scheme from accuracy to gray;

8. The navigation method of claim 3, wherein the generating a surrounding road channel picture based on at least a portion of a plurality of roads surrounding the navigation start point location comprises:

determining positions of a plurality of lines corresponding to at least part of roads in the surrounding road channel picture based on the positions of at least part of the roads in the surrounding navigation starting point position;

and determining the gray scales of the corresponding lines according to the driving directions of the roads.

9. The navigation method according to claim 3, wherein the generating an upstream road channel picture based on the alternative road and an upstream road communicated with the alternative road comprises:

determining the positions of at least two lines respectively corresponding to the alternative road and an upstream road communicated with the alternative road in the upstream road channel picture based on the positions of the alternative road and the upstream road communicated with the alternative road;

the gradation of the line corresponding to the candidate road and the gradation of the line corresponding to the upstream road are determined to be different gradation values.

10. The navigation method of claim 2, wherein the generating picture data based on the positioning data comprises:

and generating the picture data by taking the navigation starting point position as the central position of the picture.

11. The navigation method of claim 1, wherein the determining at least one alternative road from the map data based on the navigation origin position comprises:

for each of at least some of the roads in the map data, determining a degree of correlation of the road with the navigation start position based on at least one of a distance difference and a direction difference between the road and the navigation start position;

and determining at least one road in the at least part of roads as an alternative road based on the correlation degree.

12. The navigation method of claim 1, wherein the determining a navigation origin road from the at least one alternative road based on the picture data comprises:

determining the election probability of each alternative road based on the picture data;

and determining the candidate road with the highest election probability as the navigation starting point road in the at least one candidate road.

13. The navigation method of claim 12, wherein the determining, based on the picture data, the electing probability for each alternative road comprises:

for each alternative road, the following steps are performed:

extracting picture features from picture data corresponding to the alternative road;

determining a numerical value pair used for representing the election probability and the improper election probability of the alternative road based on the picture characteristics;

and normalizing the numerical value pair to obtain the election probability of the alternative road.

14. The navigation method of claim 12, wherein the determining, based on the picture data, the electing probability for each alternative road comprises:

and sequentially inputting the picture data corresponding to each alternative road into a navigation starting point road determination model to obtain the election probability of each alternative road, wherein the navigation starting point road determination model is a pre-trained machine learning model.

15. The navigation method according to claim 14, wherein the navigation origin road determination model is trained by:

acquiring a plurality of groups of sample navigation data, wherein each group of sample navigation data comprises sample positioning data, a sample navigation starting point road and a sample actual starting point road, and the sample positioning data comprises a sample navigation starting point position and map data related to the sample navigation starting point position;

generating sample picture data based on the sample navigation starting point road and the sample positioning data for each group of sample navigation data;

and training the machine learning model by taking the sample picture data of the sample actual starting point road as a positive sample, and the sample picture data of the sample actual starting point road different from the sample navigation starting point road as a negative sample, so as to maximize the accuracy rate of the machine learning model for determining the input sample picture data as the positive sample or the negative sample.

16. A navigation device, comprising:

an acquisition module configured to acquire positioning data, the positioning data including a navigation start position and map data related to the navigation start position;

a first determination module configured to determine at least one alternative road from the map data based on the navigation origin position;

a generating module configured to generate picture data based on the positioning data for each alternative road;

a second determination module configured to determine a navigation origin road from the at least one candidate road based on the picture data.

17. A computing device, comprising:

a memory configured to store computer-executable instructions;

a processor configured to perform the method of any one of claims 1 to 15 when the computer-executable instructions are executed by the processor.

18. A computer-readable storage medium storing computer-executable instructions that, when executed, perform the method of any one of claims 1 to 15.

19. A computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 15.