Method, apparatus and electronic device for adding new roads based on driving trajectory mining

Abstract

The present disclosure provides a method, device, electronic device and storage medium for mining new roads based on driving trajectories, which relates to the field of smart transportation technology, and specifically to the field of artificial intelligence technology such as intelligent search, big data and deep learning. The specific implementation plan is: obtain historical driving trajectories; match the historical driving trajectories with the target road network, and determine candidate trajectory segments that do not match the target road network from the historical driving trajectories; cluster the candidate trajectory segments to obtain unmatched target trajectory segments; and determine the location point sequence of the new target roads based on the target trajectory segments. By mining the historical driving trajectories, it is determined whether new target roads appear and the map is updated. Thus, the update of the new roads does not require manual road verification, and the road conditions can be monitored in real time, which improves the timeliness and accuracy of new road mining and reduces costs.

Description

Technical Field

[0001] The present disclosure relates to the field of smart transportation technology, specifically to artificial intelligence technology fields such as intelligent search, big data and deep learning, and more particularly to a method, device, electronic device and storage medium for mining new roads based on driving trajectories. Background Art

[0002] With the popularization of Internet technology, the development of positioning technology, and the popularity of terminal devices such as smart phones, users can easily obtain information such as their current location, navigation planning to their destination, and travel time estimates through apps such as Baidu Maps.

[0003] The traditional method of updating map roads is to collect data on-site using a collection vehicle. After the collection is completed, the collected data is brought back to the data center via an isolated encrypted hard drive. After that, map staff will process the data to identify new additions, redundancies, changes, etc., and use this to create the map. Summary of the Invention

[0004] The present disclosure provides a method, device, electronic device and storage medium for mining new roads based on driving trajectories.

[0005] According to a first aspect of the present disclosure, a method for mining new roads based on driving trajectories is provided, comprising: obtaining historical driving trajectories; performing trajectory matching on the historical driving trajectories with a target road network, and determining, from the historical driving trajectories, candidate trajectory segments that do not match the target road network; clustering the candidate trajectory segments to obtain unmatched target trajectory segments; and determining, based on the target trajectory segments, a sequence of position points for a new target road.

[0006] According to a second aspect of the present disclosure, a device for mining newly added roads based on driving trajectories is provided, comprising: an acquisition module for acquiring historical driving trajectories; a matching module for performing trajectory matching between the historical driving trajectories and a target road network, and determining, from the historical driving trajectories, candidate trajectory segments that do not match the target road network; a clustering module for clustering the candidate trajectory segments to obtain unmatched target trajectory segments; and a determination module for determining a sequence of position points of newly added target roads based on the target trajectory segments.

[0007] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for mining new roads based on driving trajectories as described in the above-mentioned embodiment.

[0008] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program / instruction is stored. The computer instructions are used to enable the computer to execute the method for mining new roads based on driving trajectories as described in the embodiment of the above-mentioned first aspect.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which, when executed by a processor, implements the method for mining new roads based on driving trajectories described in the embodiment of the first aspect.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0012] Figure 1 A flowchart of a method for mining new roads based on driving trajectories provided in an embodiment of the present disclosure;

[0013] Figure 2 A comparison diagram of historical driving trajectories and target road networks for another method for mining new roads based on driving trajectories provided by an embodiment of the present disclosure;

[0014] Figure 3 A schematic flow chart of another method for mining new roads based on driving trajectories provided in an embodiment of the present disclosure;

[0015] Figure 4 A schematic flow chart of another method for mining new roads based on driving trajectories provided in an embodiment of the present disclosure;

[0016] Figure 5 A schematic flow chart of another method for mining new roads based on driving trajectories provided in an embodiment of the present disclosure;

[0017] Figure 6 A schematic diagram of the overall process of a device for mining new roads based on driving trajectories provided in an embodiment of the present disclosure;

[0018] Figure 7 This is a schematic block diagram of the structure of a device for mining new roads based on driving trajectories according to an embodiment of the present disclosure;

[0019] Figure 8 The present invention is a block diagram of an electronic device for a method for mining new roads based on driving trajectories according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] The following describes a method, device, and electronic device for mining new roads based on driving trajectories according to embodiments of the present disclosure with reference to the accompanying drawings.

[0022] The predecessor of smart transportation is the Intelligent Transport System (ITS), a concept proposed in the United States in the early 1990s. The ITS integrates people, vehicles, and roads. It utilizes information technology, data communication and transmission technology, electronic sensing technology, satellite navigation and positioning technology, electronic control technology, computer processing technology, and traffic engineering technology. These technologies are effectively integrated and applied throughout the entire transportation management system, enabling close coordination and harmony among people, vehicles, and roads. This creates a synergistic effect, significantly improving transportation efficiency, ensuring traffic safety, improving the transportation environment, and enhancing energy efficiency. The "people" in the ITS refer to all those involved in the transportation system, including traffic managers, operators, and participants; "vehicles" encompass vehicles of all modes; and "roads" encompass roads and routes for all modes of transportation. "Intelligence" is the fundamental characteristic that distinguishes ITS from traditional transportation systems.

[0023] Deep learning (DL) is a new research direction in machine learning (ML). It was introduced to bring ML closer to its original goal: artificial intelligence. Deep learning studies the inherent laws and representational hierarchies of sample data. The information gained from this learning process is highly helpful in interpreting data such as text, images, and sound. Its ultimate goal is to enable machines to acquire human-like analytical learning capabilities and recognize data such as text, images, and sound. Deep learning is a complex machine learning algorithm that has achieved results in speech and image recognition that far surpass previous technologies.

[0024] Smart search is a new generation search engine that incorporates artificial intelligence technology. In addition to providing traditional quick search and relevance ranking functions, it also offers user role registration, automatic identification of user interests, semantic understanding of content, and intelligent information filtering and push notifications.

[0025] Image processing technology uses computers to analyze images to achieve desired results. It is also known as image processing. Image processing generally refers to digital image processing. A digital image is a large two-dimensional array captured by devices such as industrial cameras, video cameras, and scanners. The elements of this array are called pixels, and their values are called grayscale values. Image processing technology generally includes three components: image compression, enhancement and restoration, and matching, description, and recognition.

[0026] Big data, or massive amounts of data, refers to information so massive that it cannot be captured, managed, processed, and organized into meaningful insights for business decision-making within a reasonable timeframe using mainstream software tools. Research firm Gartner defines "big data" as requiring new processing models to enable stronger decision-making, insight discovery, and process optimization to accommodate massive, rapidly growing, and diverse information assets.

[0027] Current technology traditionally uses data collection vehicles for on-site road map updates. After data collection is complete, the collected data is brought back to the data center via isolated, encrypted hard drives. Mappers then process the data to identify new additions, redundancies, and changes, and use this data to create maps. This entire process is extremely lengthy, taking at least months, or even six months, and is extremely costly. The area that a data collection vehicle can capture in a given period of time is also very limited. Compared to traditional methods, user trajectories offer the advantages of wide coverage, high timeliness, and low cost. By using trajectory mining technology to mine user trajectories, the road update cycle can be shortened to days or even hours, significantly reducing costs while simultaneously covering the entire road network.

[0028] Figure 1 A flowchart of a method for mining new roads based on driving trajectories provided in an embodiment of the present disclosure.

[0029] like Figure 1 As shown, the method for mining new roads based on driving trajectories may include:

[0030] S101, obtaining historical driving trajectories.

[0031] In the disclosed embodiments, a vehicle's historical driving trajectory can be obtained in a variety of ways. Optionally, the vehicle's driving data can be uploaded to a server via electronic map software (Application, APP) installed in the vehicle. The server can then process the uploaded data to determine the vehicle's historical driving trajectory.

[0032] Optionally, the driving data can be uploaded to the road information database and / or traffic management platform through the vehicle's positioning system, and the server can be connected to the road information database and / or traffic management platform to obtain historical driving trajectories from the information database and / or traffic management platform.

[0033] Optionally, the vehicle's driving data may be uploaded to the server via the vehicle's positioning system. Furthermore, the server may process the uploaded data to obtain a historical driving trajectory.

[0034] It should be noted that the acquisition cycle for obtaining historical driving trajectories is not fixed. For example, it can be obtained once every week, once every 6 hours, etc. There is no limitation here and it is set according to actual conditions.

[0035] S102 : performing trajectory matching between the historical driving trajectory and the target road network, and determining candidate trajectory segments that are not matched with the target road network from the historical driving trajectory.

[0036] In the disclosed embodiment, the target road network is the road network information of the area where the historical driving trajectory is located. The target road network can be a provincial road network, a municipal road network, or a partial regional road network, etc., and the specific determination needs to be made based on the actual situation.

[0037] After obtaining the historical driving trajectory, the historical driving trajectory can be matched with the target road network. It can be understood that if there is a mismatch between the historical driving trajectory and the target road network, it can be considered that the vehicle is traveling on a newly added road. If the historical driving trajectory completely matches the target road network, it can be considered that the road the vehicle is traveling on is not a newly added road. For example, Figure 2 As shown, the left side is the historical driving trajectory of the vehicle, and the right side is the target road network. It can be seen that the historical driving trajectory of the vehicle does not match the target road network. It can be considered that the vehicle is driving on a newly added road, and the candidate trajectory segments are obtained.

[0038] S103: Cluster the candidate trajectory segments to obtain unmatched target trajectory segments.

[0039] It is understandable that due to inaccurate point positions, poor signals, etc., there may be multiple candidate matching segments generated by matching the historical driving trajectory with the target road network. The candidate matching segments may be continuous or offset.

[0040] Clustering is the process of dividing a collection of physical or abstract objects into clusters of similar objects. A cluster generated by clustering is a set of data objects that are similar to objects in the same cluster and dissimilar to objects in other clusters.

[0041] In the disclosed embodiments, various methods are available for clustering candidate trajectory segments. These methods include clustering candidate trajectory segments based on regional location, clustering candidate trajectory segments based on trajectory shape and orientation, and so on. These methods are not limited to any specific method and should be determined based on actual circumstances. For example, clustering algorithms may include partitioning methods, hierarchical methods, density-based methods, grid-based methods, and model-based methods.

[0042] In the disclosed embodiments, a cluster may contain multiple trajectory segments. Optionally, the longest of the multiple trajectory segments may be selected as the target trajectory segment. For example, a cluster may contain four trajectory segments, A, B, C, and D. The longest of the four trajectory segments, B, may be selected as the target trajectory segment.

[0043] Alternatively, the correlation between multiple trajectory segments can be calculated and the segment with the highest correlation can be selected as the target trajectory segment. For example, if a cluster contains four trajectory segments A, B, C, and D, then segment C with the highest correlation can be selected as the target trajectory segment.

[0044] S104: Determine a newly added target road position point sequence based on the target trajectory segment.

[0045] A target trajectory segment is composed of multiple target trajectory points, which can be considered as the shape points of the road. In implementation, since point position coefficients may exist during signal acquisition, dense road position points can be obtained by interpolating the target trajectory points of the coefficients.

[0046] In the disclosed embodiment, historical driving trajectories are first acquired, then track-matched with the target road network. Candidate trajectory segments that do not match the target road network are identified from the historical driving trajectories. These candidate trajectory segments are then clustered to obtain unmatched target trajectory segments. Finally, based on the target trajectory segments, a sequence of location points for newly added target roads is determined. By mining historical driving trajectories to determine whether new target roads have appeared and updating the map, the newly added roads can be updated without manual verification, allowing for real-time monitoring of road conditions. This improves the timeliness and accuracy of newly added road mining and reduces costs.

[0047] In the disclosed embodiment, the driving objects uploaded in the historical driving trajectory may be motor vehicles, cycling vehicles, and walking, among which cycling vehicles may include bicycles, motorcycles, and electric bicycles, among others. It is understandable that the historical driving trajectory also includes data of users cycling or walking. Since this solution is mainly aimed at mining and updating the driving roads of motor vehicles, the historical driving trajectory data of cycling or walking is of little reference value and needs to be screened out. Therefore, after obtaining the historical driving trajectory, the driving speed of the driving object can also be determined based on the candidate historical driving trajectory, and then the candidate historical driving trajectory belonging to the vehicle can be extracted from the candidate historical driving trajectory based on the driving speed as the historical driving trajectory. Therefore, by screening the historical driving data and extracting the candidate historical driving trajectory belonging to the vehicle, the reference value of the historical driving data can be improved and the cost of data processing can be reduced.

[0048] Furthermore, after acquiring historical driving trajectories, we can also extract and remove abnormal trajectory points that have drifted from the historical trajectory points. It should be noted that abnormal trajectory points are uploaded due to reasons such as inaccurate positioning or poor signal quality. Abnormal trajectory points have large errors and are not useful as reference points. Therefore, by removing abnormal trajectory points, we can improve the accuracy of historical driving trajectory data and reduce data processing costs.

[0049] In the above embodiment, the candidate trajectory segments are clustered to obtain the unmatched target trajectory segments. Figure 3 To further explain, as shown in the figure, the method includes:

[0050] S301 : Clustering candidate trajectory segments according to a set number of layers to obtain at least one cluster, wherein the cluster includes at least one unmatched candidate trajectory segment.

[0051] In the disclosed embodiment, we can use a hierarchical clustering method to cluster candidate trajectory segments. In the field of sociology, the similarity or distance between network nodes is generally defined by the topological structure of a given network, and then single-link hierarchical clustering or fully-linked hierarchical clustering is used to organize the network nodes into a tree-like hierarchy. Among them, the leaf nodes of the tree represent network nodes, and non-leaf nodes are generally obtained by merging similar or close-distance child nodes. We can set the number of layers in advance and then process it through hierarchical clustering. For example, the number of layers can be set to 3, and it stops when 3 trajectory segments are clustered.

[0052] S302 : Select the longest candidate trajectory segment from the cluster as the target trajectory segment of the cluster.

[0053] The longest candidate trajectory segment in the cluster can be considered as the user's actual driving trajectory on the newly added road and can be used as the target trajectory segment of the cluster.

[0054] In this disclosed embodiment, candidate trajectory segments are first clustered according to a set number of levels to obtain at least one cluster, where each cluster includes at least one unmatched candidate trajectory segment. The longest candidate trajectory segment within each cluster is then selected as the target trajectory segment for that cluster. Thus, by aggregating and filtering historical driving trajectories through hierarchical clustering, the user's driving trajectory on newly added roads can be accurately determined.

[0055] In the above embodiment, the historical driving trajectory is matched with the target road network, and the candidate trajectory segments that do not match the target road network are determined from the historical driving trajectory. Figure 4 To further explain, as shown in the figure, the method includes:

[0056] S401 , performing hidden Markov network matching on the trajectory points on the historical driving trajectory and the current road network to determine the first trajectory point on the historical driving trajectory that exists on the current road network.

[0057] A Hidden Markov Model (HMM) is a statistical model used to describe a Markov relationship process with hidden unknown parameters. The Markov relationship can be described as a distribution that, given a fixed initial state and a constant state transition matrix, eventually reaches a steady state after n cycles.

[0058] In the disclosed embodiment, the operating principle of the hidden Markov model can be as follows: first, any trajectory point in the to-be-matched trajectory is used as the current trajectory point. The road network data is searched for at least one candidate matching road for the current trajectory point. The observation probability from the current trajectory point to each candidate matching road is then calculated. The transition probability from each candidate matching road of the trajectory point preceding the current trajectory point to each candidate matching road of the current trajectory point is also calculated. If all candidate matching roads of the trajectory point preceding the current trajectory point are not connected to all candidate matching roads of the current historical driving trajectory point, and the current trajectory point is a fallback point, the optimal matching road of the trajectory point preceding the current trajectory point is calculated. This process continues until all candidate matching roads of the trajectory point preceding the current trajectory point match the current historical driving trajectory point. This trajectory point is then considered the first trajectory point. Using the hidden Markov model, it is possible to analyze whether a Markov relationship exists between a trajectory point in the historical driving trajectory and the current road network, and to determine the first trajectory point in the historical driving trajectory that exists on the current road network. The first trajectory point is a trajectory point in the historical driving trajectory that has a Markov relationship with the road network.

[0059] S402 : forming candidate trajectory segments based on the remaining second trajectory points on the historical driving trajectory.

[0060] After determining the first trajectory point, the remaining second trajectory point on the historical driving trajectory can be considered as a point where there is no Markov relationship between the trajectory point on the historical driving trajectory and the current road network. This trajectory point can be considered as the trajectory point where the user travels on the newly added target road.

[0061] In this disclosed embodiment, a hidden Markov network matching is first performed on the historical driving trajectory points and the current road network to determine the first trajectory point on the historical driving trajectory that exists on the current road network. Then, candidate trajectory segments are generated based on the remaining second trajectory points on the historical driving trajectory. Thus, by using hidden Markov to analyze the trajectory points on the historical driving trajectory and the current road network, the historical driving trajectory can be filtered through the road network to form accurate candidate trajectory segments, providing a basis for the subsequent generation of target trajectory segments.

[0062] It's important to note that before acquiring historical driving trajectories, it's necessary to determine the target area for mining new roads. Then, the historical driving trajectories for the target area are extracted from the candidate historical driving trajectories. Finally, the road network in the target area is determined as the target road network. Therefore, by determining the target area for mining new roads, the search area can be narrowed, reducing search costs.

[0063] Furthermore, after acquiring the position point sequence, the target road is updated on the map based on the coordinate information of the position points in the position point sequence. This provides users with more travel options and precisely guides vehicles traveling on the target road, significantly enhancing the user experience.

[0064] Furthermore, based on the coordinate information of the location points in the location point sequence, before updating the target road on the map, it is also necessary to obtain the search range of the target trajectory segment and obtain the rail transit roads within the search range on the target road network. In response to the overlap between the rail transit road and the target road, it is determined that the target road is not a new road.

[0065] Rail transit roads, including subways, railways, and light rail, are not displayed in the road network, and their historical travel trajectories are of no reference value for new road excavation. Therefore, these historical travel trajectories need to be screened out. Alternatively, a location point sequence for the rail transit road can be obtained and then compared with the location point sequence of the target road to determine whether the rail transit road and the target road overlap, thereby accurately screening out the rail transit road portion of the historical travel trajectory.

[0066] Therefore, by screening out the parts of the historical driving trajectory that are on rail transit roads, the accuracy of the historical driving trajectory data can be increased and the cost of data processing can be reduced.

[0067] In the above embodiment, after the target road is updated on the map, Figure 5 Explaining further, the method includes:

[0068] S501: Acquire driving image data corresponding to a target trajectory segment.

[0069] In the embodiment of the present disclosure, driving image data can be collected by the vehicle's image collection device. For example, the image collection device can be a vehicle-mounted camera, a vehicle-mounted camera, etc., and no limitation is made here.

[0070] After the vehicle reaches the road corresponding to the target trajectory segment, it can collect driving image data and report it to the server for processing. It should be noted that driving image data can include road condition information, target road environment, and traffic sign information, etc. This is not limited here and is set according to actual circumstances.

[0071] Optionally, the image acquisition device can collect driving data of the vehicle during the entire driving process and report it to the server for processing.

[0072] Optionally, the server may issue an instruction to control the vehicle to capture an image of the target trajectory segment after reaching the target trajectory segment, and report the image to the server for processing.

[0073] It should be noted that the electronic map can be updated by continuously acquiring image data uploaded by vehicles.

[0074] S502 : Identify traffic sign information on the target road based on the driving image data, and mark the traffic sign information at a corresponding position on the electronic map.

[0075] In this disclosed embodiment, the system first acquires driving image data corresponding to the target trajectory segment. Based on this driving image data, it then identifies traffic signs on the target road and marks them at the corresponding locations on the electronic map. After the map is updated, data from passing vehicles is collected to improve the target road information in real time, thereby increasing travel safety and enhancing the user experience.

[0076] Figure 6This is a schematic diagram of the overall process of a method for mining new roads based on driving trajectories according to an embodiment of the present disclosure. As shown in the figure, first, multiple candidate historical driving trajectories are obtained. From the candidate historical driving trajectories, the candidate historical driving trajectories belonging to the vehicle are screened out as the historical driving trajectories for mining new roads. Due to inaccurate point positions, poor signals, and other reasons, trajectory points may drift at some locations. Therefore, in order to ensure the accuracy of mining new roads, it is necessary to extract the drifting abnormal trajectory points from the trajectory points of the historical driving trajectories and eliminate the abnormal trajectory points. Furthermore, the target area for mining new roads is determined, and the road network in the target area is determined as the target road network.

[0077] It should be noted that, in order to reduce the amount of data processing, the area can be determined first, and then the historical driving trajectories belonging to the vehicle can be screened out from the candidate historical trajectories in the area.

[0078] Then the historical driving trajectory is matched with the target road network. If the two are completely matched, the method ends. If the two are not matched, the historical driving trajectory is hierarchically clustered, and the clustering results are filtered. Then, the trajectory matching the rail transit road is removed, and finally a new target road location point sequence is generated. The sequence is processed by the server, the map is updated, and the map is pushed to the user.

[0079] Corresponding to the methods for mining new roads based on driving trajectories provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides a device for mining new roads based on driving trajectories. Since the device for mining new roads based on driving trajectories provided in the embodiment of the present disclosure corresponds to the methods for mining new roads based on driving trajectories provided in the above-mentioned embodiments, the implementation methods of the above-mentioned methods for mining new roads based on driving trajectories are also applicable to the device for mining new roads based on driving trajectories provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0080] Figure 7 The schematic diagram of the structure of a device for mining new roads based on driving trajectories provided by an embodiment of the present disclosure is shown in FIG. As shown in FIG, the device 700 for mining new roads based on driving trajectories includes: an acquisition module 710 , an acquisition module 720 , a clustering module 730 , and a determination module 740 .

[0081] The acquisition module 710 is used to acquire the historical driving trajectory.

[0082] The acquisition module 720 is configured to perform trajectory matching between the historical driving trajectory and the target road network, and determine candidate trajectory segments that are not matched with the target road network from the historical driving trajectory.

[0083] The clustering module 730 is configured to cluster the candidate trajectory segments to obtain unmatched target trajectory segments.

[0084] The determination module 740 is configured to determine a sequence of position points of a newly added target road based on the target trajectory segment.

[0085] In one embodiment of the present disclosure, the clustering module 730 is further configured to: cluster the candidate trajectory segments according to a set number of layers to obtain at least one cluster, wherein the cluster includes at least one unmatched candidate trajectory segment; and select the longest candidate trajectory segment from the cluster as the target trajectory segment of the cluster.

[0086] In one embodiment of the present disclosure, the acquisition module 720 is further used to: perform hidden Markov network matching on the trajectory points on the historical driving trajectory and the current road network to determine the first trajectory point on the historical driving trajectory that exists on the current road network; and form a candidate trajectory segment based on the remaining second trajectory points on the historical driving trajectory.

[0087] In one embodiment of the present disclosure, the acquisition module 710 is further configured to: determine a target area for mining new roads; extract historical driving trajectories of the target area from candidate historical driving trajectories; and determine the road network of the target area as the target road network.

[0088] In one embodiment of the present disclosure, the acquisition module 710 is further configured to: determine a driving speed of the driving object based on the candidate historical driving trajectories; and extract, based on the driving speed, a candidate historical driving trajectory belonging to the vehicle from the candidate historical driving trajectories as the historical driving trajectory.

[0089] In one embodiment of the present disclosure, the determination module 740 is further configured to extract abnormal trajectory points where drift occurs from the trajectory points of the historical driving trajectory, and remove the abnormal trajectory points.

[0090] In one embodiment of the present disclosure, the determination module 740 is further configured to update the target road on the map based on the coordinate information of the position points in the position point sequence.

[0091] In one embodiment of the present disclosure, the determination module 740 is further configured to: obtain driving image data corresponding to the target trajectory segment; identify traffic sign information on the target road based on the driving image data, and mark the traffic sign information at a corresponding location on the electronic map.

[0092] In one embodiment of the present disclosure, the determination module 740 is further used to: obtain a search range for the target trajectory segment; obtain rail transit roads within the search range on the target road network; and in response to the rail transit road and the target road coinciding, determine that the target road is not a newly added road.

[0093] In one embodiment of the present disclosure, the determination module 740 is further configured to: obtain a position point sequence of the rail transit road; and compare the position point sequence of the rail transit road with the position point sequence of the target road to determine whether the rail transit road and the target road overlap.

[0094] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0095] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0096] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0097] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to computer programs / instructions stored in a read-only memory (ROM) 802 or computer programs / instructions loaded from a storage unit 806 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0098] Various components in device 800 are connected to I / O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, etc.; a storage unit 808 such as a magnetic disk, optical disk, etc.; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0099] The computing unit 801 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for mining new roads based on driving trajectories. For example, in some embodiments, the method for mining new roads based on driving trajectories can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 806. In some embodiments, part or all of the computer program / instructions can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program / instructions are loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for mining new roads based on driving trajectories described above can be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for mining new roads based on driving trajectories in any other appropriate manner (for example, by means of firmware).

[0100] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs / instructions that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0102] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0104] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0105] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs / instructions running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0106] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0107] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for mining new roads based on driving trajectories, comprising: Get historical driving trajectory; Performing trajectory matching on the historical driving trajectory and the target road network, and determining candidate trajectory segments that are not matched with the target road network from the historical driving trajectory; Clustering the candidate trajectory segments according to a set number of layers to obtain at least one cluster, wherein the cluster includes at least one unmatched candidate trajectory segment; Selecting the longest candidate trajectory segment from the cluster as the target trajectory segment of the cluster; Determining a new target road position point sequence based on the target trajectory segment; The step of performing trajectory matching on the historical driving trajectory and the target road network, and determining candidate trajectory segments that do not match the target road network from the historical driving trajectory, includes: Performing hidden Markov network matching on the trajectory points on the historical driving trajectory and the current road network to determine the first trajectory point on the historical driving trajectory that exists on the current road network, wherein if all candidate matching roads of the trajectory point before the current trajectory point are not connected to all candidate matching roads of the current historical driving trajectory point, and the current trajectory point is a fallback point, then calculating the optimal matching road of the trajectory point before the current trajectory point, until all candidate matching roads of the previous trajectory point match the current historical driving trajectory point, then the current historical driving trajectory point is the first trajectory point; The candidate trajectory segment is formed based on the remaining second trajectory points on the historical driving trajectory.

2. The method according to claim 1, wherein Before obtaining the historical driving trajectory, the method further includes: Identify target areas for excavating new roads; Extracting the historical driving trajectory of the target area from the candidate historical driving trajectories; The road network of the target area is determined as the target road network.

3. The method according to claim 1, wherein The obtaining of the historical driving trajectory includes: Determine the driving speed of the driving object based on the candidate historical driving trajectory; Based on the driving speed, a candidate historical driving trajectory belonging to the vehicle is extracted from the candidate historical driving trajectories as the historical driving trajectory.

4. The method according to claim 1, wherein The obtaining of the historical driving trajectory includes: Abnormal trajectory points where drift occurs are extracted from the trajectory points of the historical driving trajectory, and the abnormal trajectory points are eliminated.

5. The method according to claim 1, wherein After determining a new target road position point sequence based on the target trajectory segment, the method further includes: The target road is updated on a map based on the coordinate information of the position points in the position point sequence.

6. The method according to claim 5, wherein: After updating the target road on the map, the method further includes: Acquiring driving image data corresponding to the target trajectory segment; Based on the driving image data, traffic sign information on the target road is identified, and the traffic sign information is marked at a corresponding position on an electronic map.

7. The method according to claim 5, wherein: Before updating the target road on the map based on the coordinate information of the position points in the position point sequence, the method further includes: Obtaining a search range for the target trajectory segment; Acquire rail transit roads on the target road network that are within the search range; In response to the rail transit road being coincident with the target road, it is determined that the target road is not a newly added road.

8. The method according to claim 7, wherein: The process of determining whether the rail transit road coincides with the target road includes: Acquire a sequence of position points of the rail transit road; The position point sequence of the rail transit road is compared with the position point sequence of the target road to determine whether the rail transit road and the target road overlap.

9. A device for mining new roads based on driving trajectories, comprising: Acquisition module, used to obtain historical driving trajectories; a matching module, configured to perform trajectory matching between the historical driving trajectory and a target road network, and determine candidate trajectory segments that are not matched with the target road network from the historical driving trajectory; A clustering module, configured to cluster the candidate trajectory segments to obtain unmatched target trajectory segments; a determination module, configured to determine a sequence of position points of a newly added target road based on the target trajectory segment; The clustering module is further used to: Clustering the candidate trajectory segments according to a set number of layers to obtain at least one cluster, wherein the cluster includes at least one unmatched candidate trajectory segment; Selecting the longest candidate trajectory segment from the cluster as the target trajectory segment of the cluster; The matching module is further configured to: Performing hidden Markov network matching on the trajectory points on the historical driving trajectory and the current road network to determine the first trajectory point on the historical driving trajectory that exists on the current road network, wherein if all candidate matching roads of the trajectory point before the current trajectory point are not connected to all candidate matching roads of the current historical driving trajectory point, and the current trajectory point is a fallback point, then calculating the optimal matching road of the trajectory point before the current trajectory point, until all candidate matching roads of the previous trajectory point match the current historical driving trajectory point, then the current historical driving trajectory point is the first trajectory point; The candidate trajectory segment is formed based on the remaining second trajectory points on the historical driving trajectory.

10. The device according to claim 9, wherein The acquisition module is further used to: Identify target areas for excavating new roads; Extracting the historical driving trajectory of the target area from the candidate historical driving trajectories; The road network of the target area is determined as the target road network.

11. The device according to claim 9, wherein The acquisition module is further used to: Determine the driving speed of the driving object based on the candidate historical driving trajectory; Based on the driving speed, a candidate historical driving trajectory belonging to the vehicle is extracted from the candidate historical driving trajectories as the historical driving trajectory.

12. The device according to claim 9, wherein The determining module is further configured to: Abnormal trajectory points where drift occurs are extracted from the trajectory points of the historical driving trajectory, and the abnormal trajectory points are eliminated.

13. The device according to claim 9, wherein The determining module is further configured to: The target road is updated on a map based on the coordinate information of the position points in the position point sequence.

14. The device according to claim 13, wherein The determining module is further configured to: Acquiring driving image data corresponding to the target trajectory segment; Based on the driving image data, traffic sign information on the target road is identified, and the traffic sign information is marked at a corresponding position on an electronic map.

15. The device according to claim 13, wherein The determining module is further configured to: Obtaining a search range for the target trajectory segment; Acquire rail transit roads on the target road network that are within the search range; In response to the rail transit road being coincident with the target road, it is determined that the target road is not a newly added road.

16. The device according to claim 15, wherein The determining module is further configured to: Acquire a sequence of position points of the rail transit road; The position point sequence of the rail transit road is compared with the position point sequence of the target road to determine whether the rail transit road and the target road overlap.

17. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for mining new roads based on driving trajectories according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method for mining new roads based on driving trajectories according to any one of claims 1 to 8.

19. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the step of mining new roads based on driving trajectories in the method of claim 1 is implemented.

Images