Road congestion identification method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides a road congestion identification method and device, electronic equipment and a readable storage medium, and the method comprises the steps: determining a vehicle number change value based on a target number corresponding to target vehicles in a target road image and a first number corresponding to first vehicles in a first road image; determining the vehicle similarity between each target vehicle and each first vehicle based on the target vehicle feature corresponding to each target vehicle and the first vehicle feature corresponding to each first vehicle; and determining a road congestion index based on the vehicle similarity, the vehicle number change value and the congestion evaluation coefficient corresponding to each vehicle similarity. In this way, the road congestion degree is accurately evaluated based on the vehicle number change value and the vehicle similarity, and the recognition dimensions of road congestion recognition are enriched. And meanwhile, on the basis of judging whether the road is congested or not, the content of congestion identification is refined, important reference information is provided for traffic management and planning, and the traffic management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and in particular to a method, device, electronic device and readable storage medium for identifying road congestion. Background Art

[0002] With the acceleration of urbanization and the continuous growth of traffic demand, existing traffic congestion assessment methods mainly rely on sensor data, video surveillance and other means to make judgments. For example, the electronic toll collection (ETC) gantry system on the highway collects time-series traffic data in real time, and uses the ETL (including extraction, transformation, and loading) method to process the collected time-series traffic data to obtain the number of vehicles corresponding to the current road section.

[0003] However, these methods can only simply divide the road into two basic levels: smooth and congested, based on the number of vehicles corresponding to the current road section, that is, to judge whether the current road is congested. Due to the lack of specific congestion data and analysis, the efficiency of traffic management is low. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present invention provides a method, device, electronic device and readable storage medium for identifying road congestion.

[0005] In a first aspect, the present invention provides a method for identifying road congestion, the method comprising:

[0006] Determining a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section;

[0007] Determining vehicle similarities between each of the target vehicles and each of the first vehicles based on target vehicle features corresponding to each of the target vehicles and first vehicle features corresponding to each of the first vehicles;

[0008] A road congestion index is determined based on the vehicle similarities, the vehicle quantity change values, and the congestion assessment coefficients corresponding to the vehicle similarities; wherein the road congestion index is used to characterize the degree of road congestion on the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

[0009] Optionally, determining a road congestion index based on the vehicle similarities, the vehicle quantity change value, and a congestion assessment coefficient corresponding to each vehicle similarity includes:

[0010] For any of the vehicle similarities, based on the vehicle similarity and a preset corresponding relationship, determining a congestion assessment coefficient corresponding to the vehicle similarity;

[0011] Determining a first congestion index based on the vehicle quantity change value and a first preset weight;

[0012] Determining a second congestion index based on the sum of the products of each of the vehicle similarities and the congestion assessment coefficients corresponding to each of the vehicle similarities, the sum of the congestion assessment coefficients corresponding to each of the vehicle similarities, and a second preset weight; the sum of the first preset weight and the second preset weight is 1;

[0013] The road congestion index is determined based on the first congestion index and the second congestion index.

[0014] Optionally, the method further comprises:

[0015] According to a preset recognition frequency, a road image collected by a target acquisition device is acquired in real time as the target road image; the target acquisition device is used to collect images for the target road section at each target time interval;

[0016] Based on the target acquisition time corresponding to the target road image, a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target time length is determined.

[0017] Optionally, the method further comprises:

[0018] Performing image recognition on the target road image to obtain the target number corresponding to the target vehicles contained in the target road image;

[0019] Extracting features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle; the target vehicle features include vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle;

[0020] Based on the image identifier corresponding to the first road image, a first quantity and a first vehicle feature corresponding to the first road image pre-stored in a target database are acquired.

[0021] Optionally, the method further comprises:

[0022] When the number of vehicles contained in the preset number of road images continuously collected by the target collection device is less than the first preset threshold, adjusting the preset recognition frequency to the first frequency;

[0023] When the number of vehicles contained in the preset number of road images continuously collected by the target collection device is greater than a second preset threshold, the preset recognition frequency is adjusted to a second frequency; the second frequency is higher than the first frequency.

[0024] Optionally, after extracting features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle, the method further includes:

[0025] storing the target quantity and the target vehicle characteristics in a target cache;

[0026] When the preset conditions are met, the target quantity and target vehicle characteristics corresponding to the target road image stored in the target cache are transferred to the target database; the target database stores the vehicle quantity and vehicle characteristics corresponding to the historical road image collected by the target acquisition device.

[0027] In a second aspect, the present invention provides a device for identifying road congestion, the device comprising:

[0028] A first determination module is used to determine a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section;

[0029] A second determination module, configured to determine a vehicle similarity between each of the target vehicles and each of the first vehicles based on a target vehicle feature corresponding to each of the target vehicles and a first vehicle feature corresponding to each of the first vehicles;

[0030] The third determination module is used to determine a road congestion index based on the vehicle similarity, the vehicle quantity change value and the congestion assessment coefficient corresponding to each vehicle similarity; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

[0031] Optionally, the third determining module includes:

[0032] A first determination submodule, configured to determine, for any of the vehicle similarities, a congestion assessment coefficient corresponding to the vehicle similarity based on the vehicle similarity and a preset corresponding relationship;

[0033] A second determination submodule, configured to determine a first congestion index based on the vehicle quantity change value and a first preset weight;

[0034] A third determination submodule is used to determine a second congestion index based on the sum of the products of each vehicle similarity and the congestion assessment coefficient corresponding to each vehicle similarity, the sum of the congestion assessment coefficients corresponding to each vehicle similarity, and a second preset weight; the sum of the first preset weight and the second preset weight is 1;

[0035] The fourth determination submodule is used to determine the road congestion index based on the first congestion index and the second congestion index.

[0036] Optionally, the device further comprises:

[0037] A first acquisition module is used to acquire, in real time according to a preset recognition frequency, a road image acquired by a target acquisition device as the target road image; the target acquisition device is used to acquire images for the target road section at each target time interval;

[0038] The fifth determination submodule is configured to determine, based on the target acquisition time corresponding to the target road image, a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target duration.

[0039] Optionally, the device further comprises:

[0040] A first recognition module is used to perform image recognition on the target road image to obtain the target number corresponding to the target vehicles contained in the target road image;

[0041] A first extraction module is used to extract features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle; the target vehicle features include vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle;

[0042] The second acquisition module is used to acquire a first quantity and a first vehicle feature corresponding to the first road image pre-stored in a target database based on an image identifier corresponding to the first road image.

[0043] Optionally, the device further comprises:

[0044] A first adjustment module, configured to adjust the preset recognition frequency to a first frequency when the number of vehicles contained in the preset number of road images continuously collected by the target collection device is less than a first preset threshold;

[0045] The second adjustment module is used to adjust the preset recognition frequency to a second frequency when the number of vehicles contained in the preset number of road images continuously collected by the target collection device is greater than a second preset threshold; the second frequency is higher than the first frequency.

[0046] Optionally, the device further comprises:

[0047] A first storage module, used for storing the target quantity and the target vehicle characteristics into a target cache;

[0048] The second storage module is used to transfer the target quantity and target vehicle characteristics corresponding to the target road image stored in the target cache to the target database when the preset conditions are met; the target database stores the vehicle quantity and vehicle characteristics corresponding to the historical road images collected by the target acquisition device.

[0049] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for identifying road congestion described in any one of the first aspects above is implemented.

[0050] In a fourth aspect, the present invention provides a readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the steps in the method for identifying road congestion in any one of the embodiments of the first aspect above.

[0051] In an embodiment of the present invention, a vehicle quantity change value is determined based on a target quantity corresponding to a target vehicle contained in a target road image and a first quantity corresponding to a first vehicle contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section; based on target vehicle features corresponding to each target vehicle and first vehicle features corresponding to each first vehicle, a vehicle similarity between each target vehicle and each first vehicle is determined; based on vehicle similarity, a vehicle quantity change value and a congestion assessment coefficient corresponding to each vehicle similarity, a road congestion index is determined; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image. In this way, by determining the vehicle quantity change value and vehicle similarity corresponding to two road images acquired at different acquisition times, the correlation between vehicle flow and distribution and traffic conditions between two image acquisition intervals can be accurately and comprehensively reflected. At the same time, by determining the road congestion index based on the vehicle quantity change value and vehicle similarity, the road congestion degree can be truly and accurately reflected based on the two dimensions of vehicle quantity change value and vehicle similarity, enriching the recognition dimension of road congestion recognition to reflect a more realistic recognition result. Furthermore, based on determining whether a road is congested, the embodiment of the present invention further refines the content of congestion identification, that is, provides information on the degree of road congestion, provides important reference information for traffic management and planning, and improves traffic management efficiency to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 is a flowchart of a method for identifying road congestion provided by an embodiment of the present invention;

[0054] Figure 2 is a system architecture diagram of a road congestion identification system provided by an embodiment of the present invention;

[0055] Figure 3 is a flowchart of specific steps of a road congestion identification method provided by an embodiment of the present invention;

[0056] Figure 4 is a structural diagram of a road congestion identification device provided by an embodiment of the present invention;

[0057] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] Figure 1 is a flowchart of a method for identifying road congestion provided by an embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0060] Step 101: determine a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section.

[0061] In an embodiment of the present invention, a target road image and a first road image corresponding to a target road section are obtained. The target road image and the first road image may be road images obtained by performing image acquisition at different acquisition times on the target road section by a target acquisition device, and the first acquisition time corresponding to the first road image may be before the target acquisition time corresponding to the target road image. The target acquisition device may be deployed on a road section where traffic status monitoring is required, and the target acquisition device may obtain a road image corresponding to the target road section through image acquisition. The road image is used to characterize the real-time road condition information of the target road section at the image acquisition time.

[0062] It can be understood that the target road image and the first road image can be road images acquired by the target acquisition device at any two different acquisition times. Accordingly, the road congestion index obtained by road congestion identification based on the target road image and the first road image is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image. In other words, the road congestion degree of the target road section in different time periods can be determined by changing the time interval between the target acquisition time and the first acquisition time.

[0063] The target number corresponding to the target vehicles contained in the target road image and the first number corresponding to the first vehicles contained in the first road image are obtained. When the target acquisition device acquires images of the target road section, the road image will include vehicles in the target road section area. Therefore, the target number corresponding to the target vehicles contained in the target road image and the first number corresponding to the first vehicles contained in the first road image can be obtained.

[0064] Based on the target number and the first number, the vehicle number change value is determined. Specifically, the first number can be subtracted from the target number, and the difference can be determined as the vehicle number change value. Among them, the vehicle number change value is used to characterize the change in the number of vehicles on the target road section between the time intervals of two image acquisitions. According to actual traffic scenarios, when congestion begins to appear on the road, it can be observed that the number of vehicles gradually increases, and the vehicles gradually accumulate in the congested section; when the road congestion lasts for a certain period of time, it can be observed that the number of vehicles remains basically unchanged or slightly increases, because the number of new vehicles entering and leaving is similar, but overall they are in a high-density stagnant state. Therefore, the vehicle congestion of the target road section can be analyzed based on the change in the number of vehicles on the target road section between the time intervals of two image acquisitions.

[0065] Step 102: Determine the vehicle similarity corresponding to each of the target vehicles based on the target vehicle features corresponding to each of the target vehicles and the first vehicle features corresponding to each of the first vehicles.

[0066] In an embodiment of the present invention, target vehicle features corresponding to each target vehicle in the target road image and first vehicle features corresponding to each first vehicle in the first road image are obtained. The target road image is feature extracted using a large model algorithm to obtain target vehicle features corresponding to the target vehicles contained in the target road image; the first road image is feature extracted to obtain first vehicle features corresponding to the first vehicles contained in the first road image. The vehicle features may be vehicle feature vectors, which may include vehicle color, vehicle type (e.g., bus, truck, car, etc.), vehicle identification (e.g., vehicle model series), license plate number, license plate color, and vehicle brand, etc. corresponding to the vehicle.

[0067] Based on the target vehicle features corresponding to each target vehicle and the first vehicle features corresponding to each first vehicle, the vehicle similarity corresponding to each target vehicle is determined. Specifically, the vehicle features obtained by feature extraction can be feature vectors, and the target vehicle features are cross-compared with the first vehicle features to obtain the vehicle similarity corresponding to each target vehicle. Among them, the vehicle similarity corresponding to the target vehicle is used to characterize the matching degree between the target vehicle and the first vehicle. According to the actual traffic scene, when the road is congested, the vehicles on the road travel slowly or even stagnate. Therefore, if the road is congested and the vehicles travel slowly, their positions and states may not change much in a short time. Then, the target acquisition device is used to collect images at two different acquisition times before and after. The vehicles contained in the two road images have similarities, and even when the vehicles are stagnant, the vehicles contained in the two road images can be completely consistent. Based on this, the congestion of the road between the time intervals of the two image acquisitions can be reflected according to the degree of similarity of the vehicles in the road images collected before and after. Specifically, the higher the vehicle similarity corresponding to the target vehicle, the higher the possibility that the target vehicle travels slowly between the time intervals of the two image acquisitions, and accordingly, the higher the possibility that the target road section has congestion.

[0068] In the embodiment of the present invention, for any target vehicle and the first vehicle, the similarity value between the target vehicle feature of the target vehicle and the first vehicle feature corresponding to the first vehicle is calculated, and the similarity value is determined as the vehicle similarity between the target vehicle and the first vehicle. Based on the vehicle similarity corresponding to any target vehicle and each first vehicle, it can be determined whether there is a vehicle similar to (matching) the target vehicle in the first road image, and then the road congestion situation is determined. That is, when the highest vehicle similarity corresponding to the target vehicle and each first vehicle is greater than a preset similarity threshold, it can be determined that the first road image contains a vehicle similar to the target vehicle. Further, if the highest vehicle similarity corresponding to the target vehicle is greater than the preset similarity threshold, it can be characterized that the target vehicle moves slowly between two image acquisition intervals. It can be understood that the similarity measurement method between the target vehicle feature and each first vehicle feature can include cosine similarity, Euclidean distance, dot product, etc., and the embodiment of the present invention does not limit the similarity measurement method.

[0069] For example, assuming that the target road image contains two target vehicles, and the corresponding target vehicle features are a1 and a2, and the first road image contains three first vehicles, and the corresponding first vehicle features are b1, b2, and b3, then the vehicle similarity x1 is calculated based on a1 and b1, the vehicle similarity x2 is calculated based on a1 and b2, the vehicle similarity x3 is calculated based on a1 and b3, the vehicle similarity x4 is calculated based on a2 and b1, the vehicle similarity x5 is calculated based on a2 and b2, and the vehicle similarity x6 is calculated based on a2 and b3. Then, a vehicle similarity array [x1, x2, ..., x6] is obtained as the vehicle matching result between the target road image and the first road image.

[0070] Step 103: determine a road congestion index based on the vehicle similarities, the vehicle quantity change value, and the congestion assessment coefficients corresponding to each of the vehicle similarities; wherein the road congestion index is used to characterize the degree of road congestion of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

[0071] In the embodiment of the present invention, corresponding congestion assessment coefficients are defined in advance for different similarity ranges, and a preset correspondence relationship between similarity and congestion assessment coefficient is obtained. After determining the vehicle similarity, based on each vehicle similarity, the congestion assessment coefficient corresponding to the vehicle similarity is determined according to the preset correspondence relationship as the congestion assessment coefficient corresponding to the vehicle similarity. The congestion assessment coefficient can be used as the weight of the target vehicle, and can be dynamically determined according to the value of the similarity. Since the vehicle similarity can reflect the road congestion situation of the target road section, in order to accurately quantify this correspondence, the congestion assessment coefficient can be used for weighted processing. If the vehicle similarity is relatively high, it can be considered that the vehicle corresponding to the vehicle similarity is basically not moving in the gap between two image acquisitions, and accordingly, the higher the congestion assessment coefficient defined for it is; if the vehicle similarity is relatively low, it can be considered that the vehicle corresponding to the vehicle similarity has moved outside the image acquisition area in the gap between two image acquisitions, and accordingly, the lower the congestion assessment coefficient defined for it is.

[0072] Based on the vehicle similarity, the change value of the number of vehicles and the congestion assessment coefficient corresponding to each vehicle similarity, a road congestion index is determined. The road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image. The road congestion index can be a value between 0 and 1, and the larger the value of the road congestion index, the more serious the road congestion degree of the target road section.

[0073] In a possible implementation, after obtaining the road congestion index, the road congestion index can be entered into a data table in a MySQL database in real time, such as a congestion_indexes table. The input information may include a sequence code (id) corresponding to the target road section, a device code (camera_id) corresponding to the target acquisition device, an image acquisition time corresponding to the target road image, i.e., the target acquisition time (timestamp timestamp), and a road congestion index (congestion_index) and other related fields.

[0074] Furthermore, the target road section can be identified and judged in real time. After obtaining the real-time road congestion index, Node.js can be used with the Express framework to complete the interface implementation of database data processing. The front end uses React.js combined with the ECharts chart library for interface display, which intuitively presents the congestion situation of the target road section to which the corresponding target collection device belongs. For example, a Web-based visualization interface can be used to display the detection results to complete the visualization of the congestion situation of the target road section.

[0075] Optionally, step 103 may include the following steps:

[0076] Step 201: for any of the vehicle similarities, based on the vehicle similarity and a preset corresponding relationship, determine a congestion assessment coefficient corresponding to the vehicle similarity.

[0077] In the embodiment of the present invention, for any vehicle similarity, a congestion assessment coefficient corresponding to the vehicle similarity is searched according to a preset corresponding relationship.

[0078] For example, the vehicle similarity x i and congestion assessment coefficient w i The preset correspondence relationship may include when x i ∈(0.9, 1], w i =10; when x i ∈(0.8, 0.9), w i =9; when x i ∈(0.7, 0.8), w i =8; when x i ∈(0.6, 0.7), w i =7; when x i ∈(0.5, 0.6), w i =6; when x i ∈(0.4, 0.5), w i =5; when x i ∈(0.3, 0.4), w i =4; when x i ∈(0.2, 0.3), w i =3; when x i ∈(0.1, 0.2), w i =2; when x i ∈[0,0.1), w i =1.

[0079] Step 202: Determine a first congestion index based on the vehicle quantity change value and a first preset weight.

[0080] In an embodiment of the present invention, a first congestion index is determined based on the change in the number of vehicles and a first preset weight. The first congestion index is used to characterize the impact of the change in the number of vehicles on the road congestion condition. The first preset weight can be pre-set and can be set as a constant or variable according to the specific situation, and is specifically set according to actual needs.

[0081] Step 203: Determine a second congestion index based on the sum of the products of each vehicle similarity and the congestion assessment coefficient corresponding to each vehicle similarity, the sum of the congestion assessment coefficients corresponding to each vehicle similarity, and a second preset weight; the sum of the first preset weight and the second preset weight is 1.

[0082] In the embodiment of the present invention, a weighted average calculation is performed on the vehicle similarity and the congestion assessment coefficient corresponding to the vehicle similarity. Specifically, the product of each vehicle similarity and the congestion assessment coefficient corresponding to each vehicle similarity is determined, and the sum of the product results is multiplied by the second preset weight, and then divided by the sum of the congestion assessment coefficients corresponding to the vehicle similarity to obtain the second congestion index. The second congestion index is used to characterize the impact of the similarity of vehicles in two road images on the road congestion condition. The sum of the first preset weight and the second preset weight is 1.

[0083] Step 204: Determine the road congestion index based on the first congestion index and the second congestion index.

[0084] In the embodiment of the present invention, the sum of the first congestion index and the second congestion index is calculated as the road congestion index.

[0085] Exemplarily, the road congestion index can be obtained based on the following formula:

[0086]

[0087] Among them, P is used to represent the road congestion index, n is used to represent the change value of the number of vehicles, k is used to represent the first preset weight, and x is used to represent the first preset weight. i is used to characterize the similarity of the i-th vehicle, where i is determined based on the target number corresponding to the target vehicle in the target road image and the first number corresponding to the first vehicle in the first road image, and w i Used to characterize the congestion assessment coefficient corresponding to the i-th vehicle similarity.

[0088] In the embodiment of the present invention, by determining the congestion assessment coefficient corresponding to different vehicle similarities, the influence of vehicle similarity on the congestion assessment can be dynamically adjusted to reflect the importance of different similarities on the congestion assessment. At the same time, the congestion assessment is performed based on two dimensions, namely the dimension of vehicle quantity change and the dimension of vehicle similarity, which can avoid the one-sidedness of single-dimensional assessment. And by setting the first preset weight and the second preset weight, the subjectivity of the subjective weighting method can be reduced, the objectivity of the road congestion assessment can be improved, and the road congestion index can be made more accurate and true.

[0089] In summary, in the embodiment of the present invention, the vehicle quantity change value is determined based on the target quantity corresponding to the target vehicles contained in the target road image and the first quantity corresponding to the first vehicles contained in the first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for the target road section; based on the target vehicle features corresponding to each target vehicle and the first vehicle features corresponding to each first vehicle, the vehicle similarity between each target vehicle and each first vehicle is determined; based on the vehicle similarity, the vehicle quantity change value and the congestion assessment coefficient corresponding to each vehicle similarity, the road congestion index is determined; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image. In this way, by determining the vehicle quantity change value and the vehicle similarity corresponding to the two road images acquired at different acquisition times, the correlation between the vehicle flow and distribution and the traffic conditions between the two image acquisition intervals can be accurately and comprehensively reflected. At the same time, the road congestion index is determined based on the vehicle quantity change value and the vehicle similarity, which can truly and accurately reflect the road congestion degree based on the two dimensions of the vehicle quantity change value and the vehicle similarity, enriching the recognition dimension of road congestion recognition to reflect a more realistic recognition result. Furthermore, based on determining whether a road is congested, the embodiment of the present invention further refines the content of congestion identification, that is, provides information on the degree of road congestion, provides important reference information for traffic management and planning, and improves traffic management efficiency to a certain extent.

[0090] Optionally, the embodiment of the present invention may further include the following steps:

[0091] Step 301: Acquire a road image acquired by a target acquisition device in real time according to a preset recognition frequency as the target road image; the target acquisition device is used to acquire images for the target road section at each target time interval.

[0092] In the embodiment of the present invention, an initial recognition frequency is pre-set as a preset recognition frequency, and the preset recognition frequency is used to characterize the frequency of congestion recognition and judgment on the target road section. For example, the preset recognition frequency may be the same as the shooting frequency of the target acquisition device, that is, the target acquisition device performs a congestion recognition and judgment every time it collects a road image. Any value may also be set according to demand, such as once every 10 minutes, once every hour, etc., and the embodiment of the present invention does not impose any limitation on this.

[0093] The target acquisition device performs real-time image acquisition for the target road section at each target time interval, and obtains the road image collected by the target acquisition device in real time according to the preset recognition frequency as the target road image. Among them, the time interval for the target acquisition device to acquire images, that is, the target time, can be determined based on the average vehicle speed of the target road section. For example, the higher the average vehicle speed of the target road section, the smaller the target time can be; the lower the average vehicle speed of the target road section, the larger the target time can be. Exemplarily, after acquiring the road image, the target acquisition device can store the road image in a storage server and record the storage address of the road image in the storage server. In the case where congestion identification and judgment needs to be performed based on the road image, the storage address corresponding to the road image in the storage server is obtained. For example, the road image can be stored in ceph storage, and the storage address of the road image is recorded, and the storage address is pushed to the congestion identification and judgment platform through kafka for processing.

[0094] Step 302: Based on the target acquisition time corresponding to the target road image, determine a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target duration.

[0095] In the embodiment of the present invention, the target acquisition time corresponding to the target road image is obtained, and based on the target acquisition time, a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target time length is obtained. Since the time interval for the target acquisition device to acquire images is the target time length, it is equivalent to acquiring the road image acquired by the target acquisition device in the last image acquisition based on the target acquisition time corresponding to the target road image as the first road image. That is to say, according to the preset recognition frequency, a road image acquired by the target acquisition device is acquired in real time, the road image is used as the target road image, and the road image acquired by the target acquisition device in the last image acquisition is determined as the first road image.

[0096] In an embodiment of the present invention, by acquiring a target road image and determining a first road image in real time according to a preset recognition frequency, the frequency of road congestion recognition can be adjusted by the preset recognition frequency to flexibly identify and evaluate the road congestion situation of the target road section.

[0097] Optionally, the embodiment of the present invention may further include the following steps:

[0098] Step 401: When the number of vehicles contained in a preset number of road images continuously collected by the target collection device is less than a first preset threshold, adjust the preset recognition frequency to a first frequency.

[0099] In the embodiment of the present invention, the number of vehicles is identified for each road image collected by the target acquisition device. When the number of vehicles contained in the preset number of road images continuously collected by the target acquisition device is less than the first preset threshold, it indicates that the current traffic volume of the target road section is small and the possibility of road congestion is low. Therefore, in order to save algorithm resources, the preset identification frequency can be adjusted to the first frequency, wherein the first preset threshold can be set according to actual needs, and the embodiment of the present invention does not limit this. The frequency of the first frequency is lower than the initial identification frequency. In other words, the frequency of road congestion identification based on the target road image and the first road image can be reduced.

[0100] Step 402: When the number of vehicles contained in the preset number of road images continuously collected by the target collection device is greater than a second preset threshold, adjust the preset recognition frequency to a second frequency; the second frequency is higher than the first frequency.

[0101] In an embodiment of the present invention, when the number of vehicles contained in a preset number of road images continuously collected by the target acquisition device is greater than the second preset threshold, it indicates that the current traffic volume of the target road section is large and the possibility of road congestion is high. Therefore, in order to identify the road congestion phenomenon more quickly, the preset recognition frequency can be adjusted to the second frequency, wherein the second preset threshold can be set according to actual needs, and the embodiment of the present invention does not limit this. The second frequency can be higher than the first frequency. In other words, the frequency of road congestion recognition based on the target road image and the first road image can be increased so as to identify the road congestion phenomenon in real time and obtain the road congestion index.

[0102] In the embodiment of the present invention, by flexibly adjusting the recognition frequency according to the number of vehicles on the target road section, it is ensured that the road congestion phenomenon can be recognized more accurately and quickly while saving algorithm resources.

[0103] Optionally, the embodiment of the present invention may further include the following steps:

[0104] Step 501: Perform image recognition on the target road image to obtain the target quantity corresponding to the target vehicles contained in the target road image.

[0105] In the embodiment of the present invention, an image recognition algorithm is used to perform image recognition on the target road to obtain the number of targets corresponding to the target vehicles contained in the target road image. Exemplarily, a traditional algorithm such as template matching and edge detection or a target detection algorithm based on deep learning can be used to identify the target vehicles contained in the target road image, and based on the result of the target detection, the number of targets in the image is counted to obtain the number of targets.

[0106] Step 502: extract features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle; the target vehicle features include vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle.

[0107] In the embodiment of the present invention, based on the pre-trained feature extraction algorithm, feature extraction is performed on each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle. The target vehicle features include but are not limited to the vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle.

[0108] Step 503: Based on the image identifier corresponding to the first road image, obtain a first quantity and a first vehicle feature corresponding to the first road image pre-stored in a target database.

[0109] In the embodiment of the present invention, after the target acquisition device acquires each road image, it performs image recognition and feature extraction on the road image to obtain the number of vehicles and vehicle features corresponding to the road image. The number of vehicles and vehicle features can be stored in the target database in correspondence with the image identification of the road image.

[0110] After determining the first road image, based on the image identifier corresponding to the first road image, the number of vehicles and the vehicle characteristics corresponding to the image identifier stored in the target database are obtained as the first number and the first vehicle characteristics corresponding to the first road image.

[0111] In an embodiment of the present invention, by performing image recognition and feature extraction on a target road image acquired in real time, acquiring a target quantity and target vehicle features in real time, and searching a target database to acquire a pre-stored first quantity and first vehicle features, the processing efficiency of road congestion identification can be improved.

[0112] Optionally, the embodiment of the present invention may further include the following steps:

[0113] Step 601: Store the target quantity and the target vehicle characteristics into a target cache.

[0114] Step 602: When a preset condition is met, the number of vehicles and vehicle characteristics corresponding to the road image stored in the target cache are transferred to a target database; the target database stores the number of vehicles and vehicle characteristics corresponding to the historical road image collected by the target collection device.

[0115] In the embodiment of the present invention, each time a target road image is acquired in real time, image recognition and feature extraction are performed on the target road image to obtain the target quantity and target vehicle features, the target quantity and target vehicle features are stored in the target cache. The target cache may be a Redis cache.

[0116] When the preset conditions are met, the number of vehicles and vehicle features corresponding to the road image stored in the target cache are transferred to the target database. In this way, the number of vehicles and vehicle features corresponding to all historical road images collected by the target acquisition device can be stored in the target database. The preset conditions can be set according to the needs. For example, it can be set to transfer the number of vehicles and vehicle features corresponding to the road image stored in the target cache to the target database every time the target duration is reached. In this case, it is equivalent to storing the number of vehicles and vehicle features corresponding to the road image in the target cache after the target acquisition device collects the road image. After the latest road image is obtained, the number of vehicles and vehicle features originally stored in the target cache will be transferred to the target database. In this way, in the process of road congestion identification, the target number and target vehicle features corresponding to the target road image can be obtained from the target cache, and the first number and first vehicle features corresponding to the first road image can be retrieved and obtained from the target database.

[0117] In an embodiment of the present invention, by transferring the number of vehicles and vehicle characteristics corresponding to the historical road images collected by the target acquisition device to the target database, it can facilitate subsequent long-term data analysis and mining based on the number of vehicles and vehicle characteristics corresponding to the historical road images.

[0118] For example, Figure 2A system architecture diagram of a road congestion identification system is provided. The system includes a client, a large model platform, and a target acquisition device (such as a vehicle checkpoint platform / checkpoint device). The client creates a large model task (such as a road congestion identification task) for the large model application. After receiving the large model task, the large model application sends the large model task to the large model scheduling module and subscribes to the checkpoint snapshot to the access service. In the process of road congestion identification, the access service obtains the real-time collected target road image from the vehicle checkpoint platform / checkpoint device, and pushes the road image to the large model scheduling module through kafka. The large model scheduling model calls the large model inference module to perform feature extraction and image recognition on the target road image, obtains the target number and target vehicle features, and stores the target number and target vehicle features in the target cache (i.e., Redis cache). The first number and the first vehicle features corresponding to the first target image are retrieved in the target database (i.e., Milvus database). The target number and the target vehicle features are obtained from the Redis cache, and the first number and the first vehicle features are obtained from the target database. Based on the target number, the target vehicle features, the first number and the first vehicle features, the road congestion index is determined. The road congestion index and related information are stored in the MySQL database.

[0119] Figure 3 A flowchart of the specific steps of a road congestion identification method is provided, such as Figure 3 As shown, step S1: collect vehicle snapshot images. Specifically, the front end (such as the target acquisition device) can collect road images and perform edge analysis to obtain vehicle snapshot images (i.e., target road images). S2: Extract the target number of vehicles and target vehicle features. Specifically, the target road image is subjected to image recognition and feature extraction through a large model analysis algorithm to obtain the target number and target vehicle features. S3: Cross-matching of targets and features. Specifically, a large model comparison algorithm is used to calculate the net change in the number of vehicles (i.e., the change in the number of vehicles) based on the number of vehicles in the two road images, and the similarity is calculated by cross-comparison based on the vehicle features of the two road images, and the change in the number of vehicles and the similarity are stored in a feature vector library (e.g., a Redis cache). S4: Calculate the congestion index. Specifically, a multivariate analysis algorithm is used to confirm the road congestion index based on the change in the number of vehicles and the similarity, and the road congestion index and related information are stored in an index database (e.g., a MySQL database). S5: Congestion trend analysis and presentation. Specifically, the front end can use React.js combined with the ECharts chart library for interface display, which can intuitively present the congestion situation of the target road section to which the corresponding target collection device belongs, facilitating congestion trend analysis.

[0120] Figure 4 is a schematic diagram of the structure of a device for identifying road congestion provided by an embodiment of the present invention, such as Figure 4 As shown, the device may specifically include:

[0121] A first determination module 701 is used to determine a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section;

[0122] A second determination module 702, configured to determine a vehicle similarity between each of the target vehicles and each of the first vehicles based on a target vehicle feature corresponding to each of the target vehicles and a first vehicle feature corresponding to each of the first vehicles;

[0123] The third determination module 703 is used to determine a road congestion index based on the vehicle similarities, the vehicle quantity change value and the congestion assessment coefficient corresponding to each vehicle similarity; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

[0124] The embodiment of the present invention provides a road congestion recognition device, which determines a vehicle quantity change value based on a target quantity corresponding to a target vehicle contained in a target road image and a first quantity corresponding to a first vehicle contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section; based on target vehicle features corresponding to each target vehicle and first vehicle features corresponding to each first vehicle, determines a vehicle similarity between each target vehicle and each first vehicle; based on vehicle similarity, the vehicle quantity change value and a congestion assessment coefficient corresponding to each vehicle similarity, determines a road congestion index; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image. In this way, by determining the vehicle quantity change value and vehicle similarity corresponding to two road images acquired at different acquisition times, the correlation between vehicle flow and distribution and traffic conditions between two image acquisition intervals can be accurately and comprehensively reflected. At the same time, the road congestion index is determined based on the change value of the number of vehicles and the similarity of vehicles, which can truly and accurately reflect the degree of road congestion based on the two dimensions of the change value of the number of vehicles and the similarity of vehicles, enriching the recognition dimension of road congestion identification to reflect more realistic recognition results. Furthermore, on the basis of judging whether a road is congested, the embodiment of the present invention further refines the content of congestion identification, that is, provides information on the degree of road congestion, provides important reference information for traffic management and planning, and improves traffic management efficiency to a certain extent.

[0125] Optionally, the third determining module 703 includes:

[0126] A first determination submodule, configured to determine, for any of the vehicle similarities, a congestion assessment coefficient corresponding to the vehicle similarity based on the vehicle similarity and a preset corresponding relationship;

[0127] A second determination submodule, configured to determine a first congestion index based on the vehicle quantity change value and a first preset weight;

[0128] A third determination submodule is used to determine a second congestion index based on the sum of the products of each vehicle similarity and the congestion assessment coefficient corresponding to each vehicle similarity, the sum of the congestion assessment coefficients corresponding to each vehicle similarity, and a second preset weight; the sum of the first preset weight and the second preset weight is 1;

[0129] The fourth determination submodule is used to determine the road congestion index based on the first congestion index and the second congestion index.

[0130] Optionally, the device further comprises:

[0131] A first acquisition module is used to acquire, in real time according to a preset recognition frequency, a road image acquired by a target acquisition device as the target road image; the target acquisition device is used to acquire images for the target road section at each target time interval;

[0132] The fifth determination submodule is configured to determine, based on the target acquisition time corresponding to the target road image, a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target duration.

[0133] Optionally, the device further comprises:

[0134] A first recognition module is used to perform image recognition on the target road image to obtain the target number corresponding to the target vehicles contained in the target road image;

[0135] A first extraction module is used to extract features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle; the target vehicle features include vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle;

[0136] The second acquisition module is used to acquire a first quantity and a first vehicle feature corresponding to the first road image pre-stored in a target database based on an image identifier corresponding to the first road image.

[0137] Optionally, the device further comprises:

[0138] A first adjustment module, configured to adjust the preset recognition frequency to a first frequency when the number of vehicles contained in the preset number of road images continuously collected by the target collection device is less than a first preset threshold;

[0139] The second adjustment module is used to adjust the preset recognition frequency to a second frequency when the number of vehicles contained in the preset number of road images continuously collected by the target collection device is greater than a second preset threshold; the second frequency is higher than the first frequency.

[0140] Optionally, the device further comprises:

[0141] A first storage module, used for storing the target quantity and the target vehicle characteristics into a target cache;

[0142] The second storage module is used to transfer the target quantity and target vehicle characteristics corresponding to the target road image stored in the target cache to the target database when the preset conditions are met; the target database stores the vehicle quantity and vehicle characteristics corresponding to the historical road images collected by the target acquisition device.

[0143] The present invention also provides an electronic device, see Figure 5 , including: a processor 801, a memory 802, and a computer program 8021 stored in the memory and executable on the processor, wherein when the processor executes the program, the method for identifying road congestion of the aforementioned embodiment is implemented.

[0144] The present invention also provides a readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the road congestion identification method of the aforementioned embodiment.

[0145] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0146] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0147] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0148] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0149] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0150] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0151] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0152] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0153] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0154] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0155] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for identifying road congestion, characterized in that: The method comprises: Determining a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section; Determining vehicle similarities between each of the target vehicles and each of the first vehicles based on target vehicle features corresponding to each of the target vehicles and first vehicle features corresponding to each of the first vehicles; A road congestion index is determined based on the vehicle similarities, the vehicle quantity change values, and the congestion assessment coefficients corresponding to the vehicle similarities; wherein the road congestion index is used to characterize the degree of road congestion on the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

2. The method according to claim 1, characterized in that The determining of the road congestion index based on the vehicle similarities, the vehicle quantity change value and the congestion assessment coefficient corresponding to each of the vehicle similarities comprises: For any of the vehicle similarities, based on the vehicle similarity and a preset corresponding relationship, determining a congestion assessment coefficient corresponding to the vehicle similarity; Determining a first congestion index based on the vehicle quantity change value and a first preset weight; Determining a second congestion index based on the sum of the products of each of the vehicle similarities and the congestion assessment coefficients corresponding to each of the vehicle similarities, the sum of the congestion assessment coefficients corresponding to each of the vehicle similarities, and a second preset weight; the sum of the first preset weight and the second preset weight is 1; The road congestion index is determined based on the first congestion index and the second congestion index.

3. The method according to claim 1, characterized in that The method further comprises: According to a preset recognition frequency, a road image collected by a target acquisition device is acquired in real time as the target road image; the target acquisition device is used to collect images for the target road section at each target time interval; Based on the target acquisition time corresponding to the target road image, a first road image whose acquisition time is before the target acquisition time and whose time interval with the target acquisition time is the target time length is determined.

4. The method according to claim 1, characterized in that: The method further comprises: Performing image recognition on the target road image to obtain the target number corresponding to the target vehicles contained in the target road image; Extracting features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle; the target vehicle features include vehicle color, vehicle type, vehicle identification and vehicle brand corresponding to the target vehicle; Based on the image identifier corresponding to the first road image, a first quantity and a first vehicle feature corresponding to the first road image pre-stored in a target database are acquired.

5. The method according to claim 3, characterized in that: The method further comprises: When the number of vehicles contained in the preset number of road images continuously collected by the target collection device is less than the first preset threshold, adjusting the preset recognition frequency to the first frequency; When the number of vehicles contained in the preset number of road images continuously collected by the target collection device is greater than a second preset threshold, the preset recognition frequency is adjusted to a second frequency; the second frequency is higher than the first frequency.

6. The method according to claim 3, characterized in that: After extracting features of each target vehicle contained in the target road image to obtain target vehicle features corresponding to each target vehicle, the method further includes: storing the target quantity and the target vehicle characteristics in a target cache; When the preset conditions are met, the target quantity and target vehicle characteristics corresponding to the target road image stored in the target cache are transferred to the target database; the target database stores the vehicle quantity and vehicle characteristics corresponding to the historical road image collected by the target acquisition device.

7. A device for identifying road congestion, characterized in that: The device comprises: A first determination module is used to determine a vehicle quantity change value based on a target quantity corresponding to target vehicles contained in a target road image and a first quantity corresponding to first vehicles contained in a first road image; the target road image and the first road image are obtained by performing image acquisition at different acquisition times for a target road section; A second determination module, configured to determine a vehicle similarity between each of the target vehicles and each of the first vehicles based on a target vehicle feature corresponding to each of the target vehicles and a first vehicle feature corresponding to each of the first vehicles; The third determination module is used to determine a road congestion index based on the vehicle similarity, the vehicle quantity change value and the congestion assessment coefficient corresponding to each vehicle similarity; wherein the road congestion index is used to characterize the road congestion degree of the target road section between the target acquisition time corresponding to the target road image and the first acquisition time corresponding to the first road image.

8. The device according to claim 7, characterized in that The third determining module comprises: A first determination submodule, configured to determine, for any of the vehicle similarities, a congestion assessment coefficient corresponding to the vehicle similarity based on the vehicle similarity and a preset corresponding relationship; A second determination submodule, configured to determine a first congestion index based on the vehicle quantity change value and a first preset weight; A third determination submodule is used to determine a second congestion index based on the sum of the products of each of the vehicle similarities and the congestion assessment coefficients corresponding to each of the vehicle similarities, the sum of the congestion assessment coefficients corresponding to each of the vehicle similarities, and a second preset weight; the sum of the first preset weight and the second preset weight is 1; The fourth determination submodule is used to determine the road congestion index based on the first congestion index and the second congestion index.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for identifying road congestion as claimed in any one of claims 1 to 6 is implemented.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for identifying road congestion as described in any one of claims 1-6.

Images