Traffic condition identification method, device, server, storage medium and program product

Abstract

The disclosed embodiments relate to a traffic condition identification method, apparatus, server, storage medium, and program product. The method comprises obtaining positioning information of vehicles on a target road section within a target historical period before the current moment; generating multiple driving trajectory maps based on the obtained positioning information; and identifying the multiple driving trajectory maps using a pre-established traffic condition identification model to obtain traffic condition identification results, wherein the traffic condition identification results include whether the target road section is congested or the estimated time to pass the target road section. The method comprises: Using this method can improve the accuracy of traffic condition identification.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the technical field of traffic condition identification, and in particular to a traffic condition identification method, device, server, storage medium, and program product. Background Art

[0002] With the development of Internet technology, Internet-based travel services have emerged, bringing great convenience to people's work and life. Typically, travel services will identify the traffic conditions of the target road section and avoid congested sections.

[0003] Currently, traffic conditions are mostly identified by manually setting rules to determine the driving characteristics of each vehicle in the customer's travel route, such as whether the vehicle stops and the length of time it stops. The average speed of the vehicles in the customer's travel route is then calculated based on the driving characteristics of the vehicles, and congestion is then determined based on the average speed of the vehicles.

[0004] However, it is impossible to manually summarize all driving characteristics, and some deep features have not been discovered, so the accuracy of traffic condition recognition needs to be improved. Summary of the Invention

[0005] The embodiments of the present disclosure provide a traffic condition identification method, device, server, storage medium, and program product, which can be used to improve the accuracy of traffic condition identification.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for identifying traffic conditions, the method comprising:

[0007] Obtain the positioning information of vehicles on the target road section within the target historical period before the current moment;

[0008] generating a plurality of driving trajectory maps according to the acquired positioning information;

[0009] The multiple driving trajectory graphs are identified using a pre-established traffic condition identification model to obtain a traffic condition identification result; wherein the traffic condition identification result includes whether the target road section is congested or the estimated passing time of the target road section.

[0010] In a second aspect, an embodiment of the present disclosure provides a traffic condition recognition device, the device comprising:

[0011] A positioning information acquisition module is used to obtain the positioning information of vehicles in the target road section within the target historical period before the current moment;

[0012] A trajectory map generating module, configured to generate a plurality of driving trajectory maps according to the acquired positioning information;

[0013] A condition recognition module is used to use a pre-established traffic condition recognition model to recognize the multiple driving trajectory graphs to obtain a traffic condition recognition result; wherein the traffic condition recognition result includes whether the target road section is congested or the estimated passing time of the target road section.

[0014] In a third aspect, an embodiment of the present disclosure provides a server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0016] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which implements the method described in the first aspect when executed by a processor.

[0017] The traffic condition identification method, device, server, storage medium, and program product provided by the disclosed embodiments involve a server acquiring the positioning information of vehicles on a target road section within a target historical period prior to the current moment; generating multiple driving trajectory maps based on the acquired positioning information; and utilizing a pre-established traffic condition identification model to identify the multiple driving trajectory maps, thereby obtaining traffic condition identification results. Through the disclosed embodiments, after the server organizes the positioning information into driving trajectory maps, the traffic condition identification model directly identifies the traffic condition. This process eliminates manual summarization of driving characteristics and allows the traffic condition identification model to uncover deeper features within the positioning information, thereby improving the accuracy of traffic condition identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A diagram showing an application environment of a traffic condition recognition method according to an embodiment;

[0019] Figure 2 1 is a flow chart of a traffic condition identification method according to an embodiment;

[0020] Figure 3 A schematic diagram of a flow chart of steps for generating multiple driving trajectory maps in one embodiment;

[0021] Figure 4 A schematic diagram of time period division in one embodiment;

[0022] Figure 5 A schematic diagram of a driving trajectory diagram in one embodiment;

[0023] Figure 6A schematic diagram of a flow chart of steps for identifying multiple driving trajectory images using a traffic condition recognition model in one embodiment;

[0024] Figure 7 This is one of the structural block diagrams of a traffic condition identification device in one embodiment;

[0025] Figure 8 This is a second structural block diagram of a traffic condition identification device in one embodiment;

[0026] Figure 9 FIG. 1 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure more clear, the embodiments of the present disclosure are further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present disclosure and are not intended to limit the embodiments of the present disclosure.

[0028] First of all, before specifically introducing the technical solutions of the embodiments of the present disclosure, the technical background or technical evolution context on which the embodiments of the present disclosure are based is introduced. Under normal circumstances, the method of identifying traffic conditions is mostly to determine the driving characteristics of each vehicle in the customer's travel path based on manually set rules, such as whether to stop, the length of parking, etc., and then calculate the average speed of the vehicles in the customer's travel path based on the driving characteristics of the vehicles, and then judge whether there is congestion based on the average speed of the vehicles. However, through long-term research and development and the collection, demonstration and verification of experimental data, the applicant found that it is impossible to summarize all driving characteristics manually, some deep features have not been discovered, and the accuracy of traffic condition recognition still has room for improvement. In addition, it should be noted that the applicant has put in a lot of creative work to determine that deep information has not been discovered in the above-mentioned identification method, the accuracy of traffic condition recognition can be further improved, and the technical solutions introduced in the following embodiments.

[0029] The following describes the technical solutions involved in the embodiments of the present disclosure in conjunction with the scenarios to which the embodiments of the present disclosure are applied.

[0030] The traffic condition recognition method provided by the embodiment of the present disclosure can be applied to Figure 1In the application environment shown. The application environment includes a user terminal 102 and a server 104; wherein the user terminal 102 communicates with the server 104 via a network. The user terminal 102 sends a traffic condition identification request to the server 104. The server 104 identifies the traffic condition of the target road section based on the traffic condition identification request. After obtaining the traffic condition identification result, the server 104 feeds the traffic condition identification result back to the user terminal 102; the user terminal 102 can display the traffic condition identification result in a map interface. The above-mentioned user terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, portable wearable devices, and in-vehicle devices. The server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0031] In one embodiment, Figure 2 As shown, a traffic condition recognition method is provided, which is applied to Figure 1 The following steps are used as an example to illustrate the server in the example:

[0032] Step 201: Obtain positioning information of vehicles in a target road section within a target historical period before the current moment.

[0033] The vehicle's positioning information may be obtained by positioning the vehicle using a GPS (Global Positioning System), and the positioning information may include at least one of position coordinates, speed, and angular velocity.

[0034] When the server needs to identify the traffic conditions of the target road section, it determines a preset period before the current moment as the target historical period. Then, the server obtains the positioning information of vehicles traveling on the target road section during the target historical period.

[0035] For example, the 20 minutes between the current moment is determined as the target historical period, and the positioning information of the vehicles traveling on the target road section within these 20 minutes is obtained. In practical applications, other methods can also be used to determine the target historical period, and the present disclosure embodiment does not limit this.

[0036] Step 202: Generate multiple driving trajectory maps based on the acquired positioning information.

[0037] After obtaining multiple pieces of positioning information, the server divides the pieces of positioning information into multiple sets of positioning information. The division process may include: evenly dividing the target historical period into multiple sub-historical periods, with the end time of the previous sub-historical period serving as the start time of the next sub-historical period, and forming a positioning information set from the multiple pieces of positioning information corresponding to each sub-historical period.

[0038] For example, if the target historical period is 20 minutes and is evenly divided into 10 sub-historical periods, the multiple positioning information corresponding to the first 2 minutes will constitute positioning information set 1, and the multiple positioning information corresponding to the second 2 minutes will constitute positioning information set 2. This process can be repeated and multiple positioning information sets can be obtained. In actual applications, other methods can also be used to obtain positioning information sets, and this embodiment of the disclosure is not limited thereto.

[0039] After obtaining multiple positioning information sets, a driving trajectory map is generated for each positioning information set to obtain multiple driving trajectory maps.

[0040] Step 203: Use the pre-established traffic condition recognition model to recognize the multiple driving trajectory graphs to obtain traffic condition recognition results.

[0041] The traffic condition recognition result includes whether the target road section is congested or the estimated passing time of the target road section.

[0042] A traffic condition recognition model is pre-established in the server. After obtaining multiple driving trajectory maps, the server uses the traffic condition recognition model to identify the multiple driving trajectory maps. Based on the relationship between different positioning information in each driving trajectory map, the server obtains traffic condition recognition results such as whether the target road section is congested or the estimated time to pass the target road section.

[0043] In the aforementioned traffic condition identification method, the server obtains the positioning information of vehicles on a target road section within a target historical period prior to the current moment; generates multiple driving trajectory maps based on the acquired positioning information; and uses a pre-established traffic condition identification model to identify the multiple driving trajectory maps to obtain traffic condition identification results. With the disclosed embodiments, after the server organizes the positioning information into driving trajectory maps, the traffic condition identification model directly identifies the traffic condition. This process eliminates manual analysis of driving characteristics and allows the traffic condition identification model to uncover deeper features within the positioning information, thereby improving the accuracy of traffic condition identification.

[0044] In one embodiment, Figure 3 As shown, the step of generating multiple driving trajectory maps based on the acquired positioning information may include:

[0045] Step 301: Divide the target historical period into multiple sub-historical periods.

[0046] In order to make full use of the positioning information within the target historical period, when dividing the sub-historical periods, the duration of each sub-historical period is equal, and the end times of each adjacent sub-historical period are separated by a preset time.

[0047] like Figure 4As shown, sub-historical period 1 is equal in length to sub-historical period 2, sub-historical period 3, and so on, and sub-historical period n. The end time of sub-historical period 1 is 1 minute away from the end time of sub-historical period 2, and the end time of sub-historical period 2 is 1 minute away from the end time of sub-historical period 3. ... The end time of sub-historical period n-1 is 1 minute away from the end time of sub-historical period n, and the end time of sub-historical period n is the current time. The present embodiment does not limit the number of sub-historical periods, their duration, or the preset time interval between their end times, and these can be set according to actual circumstances.

[0048] Step 302: Generate a driving trajectory map corresponding to each sub-historical period based on the positioning information in each sub-historical period.

[0049] The driving trajectory graph includes the driving trajectory lines of multiple vehicles in the sub-historical period. Figure 5 As shown in the figure, the horizontal axis of the driving trajectory diagram is length (the distance between the vehicle and the end point of the target road section), and the vertical axis is time. The driving trajectory line can represent the length of time the vehicle is at the same location. For example, Figure 5 The circled driving trajectory indicates that the vehicle remained approximately 200 meters from the target segment's end point for a significant period of time. As can be seen, the longer a vehicle remains in the same location, the slower it is moving. This means that the probability of congestion at that location increases, and the estimated time to pass the target segment increases. Therefore, using the driving trajectory graph to represent the speed of each vehicle within the target segment facilitates traffic condition identification using subsequent traffic condition recognition models.

[0050] After the server divides the historical period into multiple sub-periods, it generates a corresponding driving trajectory map based on the positioning information within each sub-period. The process of generating the driving trajectory map may include: generating a driving trajectory line corresponding to each vehicle based on the positioning information of each vehicle within the sub-period; and generating a driving trajectory map corresponding to the sub-period based on the driving trajectory lines of multiple vehicles within the sub-period.

[0051] For example, based on the positioning information of vehicle 1 in sub-historical period 1, the driving trajectory line corresponding to vehicle 1 is generated... Based on the positioning information of vehicle m in sub-historical period 1, the driving trajectory line corresponding to vehicle m is generated; based on the driving trajectory lines corresponding to vehicle 1... and the driving trajectory lines corresponding to vehicle n, the driving trajectory map corresponding to sub-historical period 1 is drawn.

[0052] In the above-mentioned step of generating multiple driving trajectory maps based on the acquired positioning information, the server divides the target historical period into multiple sub-historical periods; and based on the positioning information within each sub-historical period, generates a driving trajectory map corresponding to each sub-historical period. Through the disclosed embodiment, the server divides the target historical period into multiple overlapping sub-historical periods, making full use of the positioning information within the target historical period. Moreover, the generated multiple driving trajectory maps have a natural temporal relationship, so that the subsequent traffic condition recognition model can identify traffic conditions based on the driving trajectory maps.

[0053] In one embodiment, Figure 6 As shown, the above step of using the pre-established traffic condition recognition model to recognize multiple driving trajectory graphs to obtain traffic condition recognition results may include:

[0054] Step 401: assemble multiple driving trajectory graphs into a trajectory graph sequence according to the temporal relationship of the sub-historical periods.

[0055] When the target historical period is divided into multiple sub-historical periods, the multiple sub-historical periods have a time sequence relationship. For example, the end time of sub-historical period 1 is earlier than the end time of sub-historical period 2, and the end time of sub-historical period 2 is earlier than the end time of sub-historical period 3.

[0056] After obtaining the driving trajectory graph corresponding to each sub-historical period, the server organizes the multiple driving trajectory graphs into a trajectory graph sequence according to the temporal relationship between the sub-historical periods. In this way, the multiple driving trajectory graphs in the trajectory graph sequence also have a temporal relationship.

[0057] Step 402: Input the trajectory graph sequence into the traffic condition recognition model to obtain the traffic condition recognition result output by the traffic condition recognition model.

[0058] After obtaining the trajectory map sequence, the server inputs the trajectory map sequence into the traffic condition recognition model. The traffic condition recognition model recognizes the positioning information in each driving trajectory map respectively and recognizes the temporal relationship between multiple driving trajectory maps; finally, the traffic condition recognition model outputs the traffic condition recognition result.

[0059] In one embodiment, the traffic condition recognition model includes a road condition recognition model. The above-mentioned step of inputting the trajectory map sequence into the traffic condition recognition model to obtain the traffic condition recognition result output by the traffic condition recognition model may include: inputting the trajectory map sequence into the road condition recognition model, the road condition recognition model extracting feature information from each driving trajectory map, and outputting the road condition recognition result based on the temporal relationship between the extracted multiple feature information; wherein, the road condition recognition result is used to characterize whether the target road section is congested.

[0060] In practical applications, the road condition recognition model extracts feature information from the driving trajectory map to generate a road condition feature map. Afterwards, the road condition recognition model determines whether the target road section is congested based on the temporal relationship between multiple road condition feature maps.

[0061] The above-mentioned road condition recognition model can be implemented using a classification neural network model. The portion that extracts feature information can be implemented using a CNN (Convolutional Neural Network), and the portion that obtains traffic condition recognition results based on temporal relationships can be implemented using an RNN (Recurrent Neural Network). The present disclosure does not limit the structure of the road condition recognition model and can be configured according to actual circumstances.

[0062] In one embodiment, the traffic condition recognition model includes a time recognition model. The above-mentioned step of inputting the trajectory map sequence into the traffic condition recognition model to obtain the traffic condition recognition result output by the traffic condition recognition model may include: inputting the trajectory map sequence into the time recognition model, the time recognition model extracting feature information from each driving trajectory map, and outputting a time recognition result based on the temporal relationship between the extracted multiple feature information; the time recognition result is used to represent the expected passing time of the target road section.

[0063] In practical applications, the time recognition model extracts feature information from the driving trajectory graph to generate a time feature graph. Afterwards, the time recognition model determines the estimated passing time of the target road section based on the temporal relationship between multiple time feature graphs.

[0064] The above-mentioned time recognition model can be implemented by using a regression model. The embodiment of the present disclosure does not limit the implementation method of the time recognition model, and it can be set according to actual conditions.

[0065] In the aforementioned step of using a pre-established traffic condition recognition model to identify multiple driving trajectory images and obtain traffic condition recognition results, the server organizes the multiple driving trajectory images into a trajectory image sequence based on the temporal relationship of the sub-historical periods, inputs the trajectory image sequence into the traffic condition recognition model, and obtains the traffic condition recognition results output by the traffic condition recognition model. Through the disclosed embodiments, using the traffic condition recognition model to identify traffic conditions can uncover deep features in positioning information, thereby improving the accuracy of traffic condition recognition.

[0066] In one embodiment, before obtaining the positioning information of the vehicle in the target road section within the target historical period before the current moment, the method may further include: receiving a traffic condition identification request sent by a user terminal; wherein the traffic condition identification request includes the target road section.

[0067] In practice, when a user needs to know the traffic conditions of a target road segment, they can enter their destination in their terminal. The terminal then determines the target road segment based on their location and destination. The terminal then sends a traffic condition identification request to the server, including the target road segment in the request.

[0068] Correspondingly, the server receives a traffic condition identification request from the user terminal and parses the request to identify the target road segment. Next, the server obtains the positioning information of vehicles on the target road segment within the target historical period before the current moment. Based on this positioning information, the server generates multiple driving trajectory maps and uses a pre-established traffic condition identification model to identify these multiple driving trajectory maps, generating traffic condition identification results.

[0069] Next, the server sends the traffic condition identification result to the user terminal, so that the user terminal can display the traffic condition identification result in a map interface.

[0070] In one embodiment, the traffic condition identification result includes whether the target road section is congested. The user terminal can display a colored earthworm map on the map interface based on whether the target road section is congested. For example, if the target road section is very congested, the target road section will be displayed in red; if the target road section is moderately congested, the target road section will be displayed in yellow; if the target road section is not congested, the target road section will be displayed in green.

[0071] In one embodiment, the traffic condition identification result includes an estimated time to pass the target road section, and the user terminal can display the estimated time to pass the target road section in the map interface. For example, the user terminal can display the estimated time to pass the target road section as 30 minutes, or display the estimated time to pass the target road section as 5 minutes.

[0072] The embodiment of the present disclosure does not limit how the user terminal displays the traffic condition recognition results, and can be set according to actual conditions.

[0073] In the above embodiment, the server receives a traffic condition identification request from a user terminal, uses the traffic condition identification model to obtain a traffic condition identification result, and then feeds the traffic condition identification result back to the user terminal. The user terminal can then display the traffic condition identification result accordingly, allowing the user to understand the traffic conditions of the target road section and plan their driving route in advance.

[0074] It should be understood that although Figures 2 to 6 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figures 2 to 6At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0075] In one embodiment, Figure 7 As shown, a traffic condition recognition device is provided, comprising:

[0076] Positioning information acquisition module 501, used to obtain the positioning information of vehicles in the target road section within the target historical period before the current moment;

[0077] A trajectory map generating module 502 is used to generate a plurality of driving trajectory maps according to the acquired positioning information;

[0078] The condition recognition module 503 is used to use a pre-established traffic condition recognition model to recognize multiple driving trajectory graphs to obtain traffic condition recognition results; wherein the traffic condition recognition results include whether the target road section is congested or the estimated passing time of the target road section.

[0079] In one embodiment, the trajectory map generating module 502 includes:

[0080] The time period division submodule is used to divide the target historical period into multiple sub-historical periods; wherein the duration of each sub-historical period is equal, and the end time of each adjacent sub-historical period is separated by a preset time;

[0081] The trajectory map generation submodule is used to generate a driving trajectory map corresponding to each sub-historical period based on the positioning information in each sub-historical period; wherein the driving trajectory map includes the driving trajectory lines of multiple vehicles.

[0082] In one embodiment, the above-mentioned trajectory map generation submodule is specifically used to generate the driving trajectory line corresponding to each vehicle based on the positioning information of each vehicle in the sub-historical period; and generate the driving trajectory map corresponding to the sub-historical period based on the driving trajectory lines of multiple vehicles in the sub-historical period.

[0083] In one embodiment, the situation identification module 503 includes:

[0084] A sequence generation submodule is used to combine multiple driving trajectory graphs into a trajectory graph sequence according to the temporal relationship between multiple sub-historical periods;

[0085] The recognition submodule is used to input the trajectory map sequence into the traffic condition recognition model to obtain the traffic condition recognition result output by the traffic condition recognition model.

[0086] In one embodiment, the traffic condition recognition model includes a road condition recognition model. The above-mentioned recognition submodule is specifically used to input the trajectory map sequence into the road condition recognition model. The road condition recognition model extracts the feature information in each driving trajectory map and outputs the road condition recognition result based on the temporal relationship between the extracted multiple feature information; the road condition recognition result is used to characterize whether the target road section is congested.

[0087] In one embodiment, the traffic condition recognition model includes a time recognition model. The above-mentioned recognition submodule is specifically used to input the trajectory map sequence into the time recognition model. The time recognition model extracts the feature information in each driving trajectory map and outputs the time recognition result based on the temporal relationship between the extracted multiple feature information; the time recognition result is used to represent the expected passing time of the target road section.

[0088] In one embodiment, Figure 8 As shown, the device also includes:

[0089] The request receiving module 504 is configured to receive a traffic condition identification request sent by a user terminal; wherein the traffic condition identification request includes a target road segment;

[0090] The result sending module 505 is used to send the traffic condition identification result to the user terminal so that the user terminal can display the traffic condition identification result in a map interface.

[0091] The specific definitions of the traffic condition recognition device can be found in the definitions of the traffic condition recognition method above and will not be repeated here. Each module in the aforementioned traffic condition recognition device may be implemented in whole or in part through software, hardware, or a combination thereof. Each of the aforementioned modules may be embedded in or independent of a server processor in hardware form, or stored in memory within an electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0092] Figure 9 FIG1 is a block diagram of a server 1400 according to an exemplary embodiment. Figure 9 Server 1400 includes a processing component 1420, which further includes one or more processors and memory resources represented by memory 1422 for storing instructions or computer programs, such as applications, that are executable by processing component 1420. The applications stored in memory 1422 may include one or more modules, each corresponding to a set of instructions. Furthermore, processing component 1420 is configured to execute the instructions to perform the aforementioned method for traffic condition identification.

[0093] The server 1400 may also include a power supply component 1424 configured to perform power management for the device 1400, a wired or wireless network interface 1426 configured to connect the device 1400 to a network, and an input / output (I / O) interface 1428. The server 1400 may operate based on an operating system stored in the memory 1422, such as Windows XP, Mac OS X, Unix, Linux, FreeBSD, or the like.

[0094] In an exemplary embodiment, a storage medium including instructions is also provided, such as memory 1422 including instructions, which can be executed by a processor of server 1400 to perform the above method. The storage medium can be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0095] In an exemplary embodiment, a computer program product is also provided. When executed by a processor, the computer program can implement the above-described method. The computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, they can implement part or all of the above-described method in whole or in part according to the processes or functions described in the embodiments of the present disclosure.

[0096] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the embodiments of the present disclosure may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0097] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above-described embodiments merely represent several implementation methods of the embodiments of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that a person of ordinary skill in the art can make several modifications and improvements without departing from the concept of the embodiments of the present disclosure, all of which fall within the scope of protection of the embodiments of the present disclosure. Therefore, the scope of protection of the patent for the embodiments of the present disclosure shall be based on the appended claims.

Claims

1. A traffic condition recognition method, characterized in that: The method comprises: Obtain the positioning information of vehicles on the target road section within the target historical period before the current moment; generating a plurality of driving trajectory maps according to the acquired positioning information; Using a pre-established traffic condition recognition model to recognize the multiple driving trajectory graphs, and obtaining a traffic condition recognition result; The traffic condition recognition model includes a road condition recognition model and a time recognition model; the traffic condition recognition result includes whether the target road section is congested or the estimated passing time of the target road section; the traffic condition recognition result obtained by using the pre-established traffic condition recognition model to recognize the multiple driving trajectory graphs includes: Combining the plurality of driving trajectory graphs into a trajectory graph sequence according to the temporal relationship between the plurality of sub-historical periods divided by the target historical period; Inputting the trajectory map sequence into the road condition recognition model, the road condition recognition model extracting characteristic information from the driving trajectory map to generate a road condition characteristic map, and determining whether the target road section is congested based on the temporal relationship between the plurality of road condition characteristic maps; The trajectory map sequence is input into the time recognition model, the time recognition model extracts characteristic information from the driving trajectory map to generate a time characteristic map, and determines the estimated travel time of the target road section according to the temporal relationship between multiple time characteristic maps.

2. The method according to claim 1, characterized in that The method of generating a plurality of driving trajectory diagrams according to the acquired positioning information includes: Divide the target historical period into multiple sub-historical periods; wherein the duration of each sub-historical period is equal, and the end time of each two adjacent sub-historical periods is separated by a preset time; A driving trajectory map corresponding to each sub-historical period is generated according to the positioning information in each sub-historical period; wherein the driving trajectory map includes driving trajectory lines of multiple vehicles.

3. The method according to claim 2, characterized in that Generating a driving trajectory map corresponding to each sub-historical period according to the positioning information in each sub-historical period includes: Generate a driving trajectory line corresponding to each vehicle according to the positioning information of each vehicle in the sub-historical period; A driving trajectory map corresponding to the sub-historical period is generated based on the driving trajectory lines of multiple vehicles in the sub-historical period.

4. The method according to claim 1, wherein Before acquiring the positioning information of the vehicle in the target road section within the target historical period before the current moment, the method further includes: receiving a traffic condition identification request sent by a user terminal; wherein the traffic condition identification request includes the target road section; Correspondingly, after identifying the plurality of driving trajectory graphs using the pre-established traffic condition recognition model to obtain a traffic condition recognition result, the method further includes: The traffic condition identification result is sent to the user terminal so that the user terminal can display the traffic condition identification result in a map interface.

5. A traffic condition recognition device, characterized in that: The device comprises: A positioning information acquisition module is used to obtain the positioning information of vehicles in the target road section within the target historical period before the current moment; A trajectory map generating module, configured to generate a plurality of driving trajectory maps according to the acquired positioning information; A condition recognition module, configured to recognize the plurality of driving trajectory images using a pre-established traffic condition recognition model to obtain a traffic condition recognition result; The traffic condition recognition model includes a road condition recognition model and a time recognition model, and the traffic condition recognition result includes whether the target road section is congested or the estimated passing time of the target road section; the condition recognition module includes: A sequence generation submodule, configured to combine the plurality of driving trajectory graphs into a trajectory graph sequence according to a temporal relationship between a plurality of sub-historical time periods; An identification submodule, configured to input the trajectory map sequence into the road condition identification model, wherein the road condition identification model extracts characteristic information from the driving trajectory map to generate a road condition characteristic map, and determines whether a target road section is congested based on a temporal relationship between a plurality of the road condition characteristic maps; The recognition submodule is further configured to input the trajectory map sequence into the time recognition model, the time recognition model extracts characteristic information from the driving trajectory map to generate a time characteristic map, and determines the estimated travel time of the target road section based on the temporal relationship between the multiple time characteristic maps.

6. The device according to claim 5, characterized in that The trajectory map generation module includes: A time period division submodule, configured to divide the target historical period into a plurality of sub-historical periods; wherein the duration of each sub-historical period is equal, and the end times of two adjacent sub-historical periods are separated by a preset time period; The trajectory map generating submodule is used to generate a driving trajectory map corresponding to each sub-historical period according to the positioning information in each sub-historical period; wherein the driving trajectory map includes the driving trajectory lines of multiple vehicles.

7. The device according to claim 6, characterized in that The trajectory map generation submodule is specifically used to generate the driving trajectory line corresponding to each vehicle according to the positioning information of each vehicle in the sub-historical period; and generate the driving trajectory map corresponding to the sub-historical period according to the driving trajectory lines of multiple vehicles in the sub-historical period.

8. The device according to claim 5, characterized in that The device further comprises: a request receiving module, configured to receive a traffic condition identification request sent by a user terminal; wherein the traffic condition identification request includes the target road section; The result sending module is used to send the traffic condition identification result to the user terminal so that the user terminal can display the traffic condition identification result in a map interface.

9. A server comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images