Traffic congestion tracing methods, devices, electronic equipment and storage media

Abstract

This disclosure relates to the field of data processing technology, particularly to the fields of intelligent transportation, traffic management, and traffic information processing, specifically to a method, device, electronic device, and storage medium for tracing traffic congestion sources. The specific implementation scheme is as follows: A pending road segment and at least two reference road segments related to the pending road segment are determined from the target road network; wherein, the reference road segments are the road segments from which traffic flow can flow into the pending road segment; the congestion contagion distance between the pending road segment and the reference road segments is obtained within a target time period; the congestion time difference between the first congestion time of the pending road segment and the second congestion time of the reference road segment within the target time period is calculated; if the correlation between the congestion contagion distance and the congestion time difference meets a preset correlation requirement, the pending road segment is determined as the congestion source of the target road network within the target time period. Using this disclosure can improve the accuracy of congestion source determination.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, particularly to the fields of intelligent transportation, traffic management, and traffic information processing, and specifically to a method, device, electronic device, and storage medium for tracing traffic congestion. Background Technology

[0002] With the acceleration of urbanization, the demand for transportation is constantly increasing, leading to increasingly serious urban traffic congestion. Therefore, identifying the source of congestion plays a crucial role in urban traffic management. Currently, the source of congestion is usually determined based on mobile phone signaling.

[0003] However, based on mobile phone signaling, it is only possible to roughly identify a large area as the source of congestion, but not to pinpoint the source of congestion with precision. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for tracing the source of traffic congestion.

[0005] According to one aspect of this disclosure, a method for tracing the source of traffic congestion is provided, comprising:

[0006] Identify undetermined road segments from the target road network, and at least two reference road segments related to the undetermined road segments; wherein, the reference road segments are the road segments into which traffic flow can flow from the undetermined road segments;

[0007] Obtain the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period;

[0008] Calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period;

[0009] If the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirements, the undetermined road segment is identified as the source of congestion in the target road network during the target time period.

[0010] According to another aspect of this disclosure, a traffic congestion tracing device is provided, comprising:

[0011] The road segment determination unit is used to determine the undetermined road segment and at least two reference road segments related to the undetermined road segment from the target road network; wherein, the reference road segments are the road segments into which the traffic flow of the undetermined road segment can flow.

[0012] The transmission distance acquisition unit is used to acquire the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period;

[0013] The time difference calculation unit is used to calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period.

[0014] The congestion source identification unit is used to identify the undetermined road segment as the congestion source of the target road network within the target time period, provided that the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirements.

[0015] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor;

[0017] The memory that is communicatively connected to the at least one processor;

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described in the present disclosure.

[0019] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the methods according to embodiments of this disclosure.

[0020] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements any of the methods according to embodiments of this disclosure.

[0021] Using this disclosure can improve the accuracy of identifying congestion sources.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a schematic diagram illustrating the changing trend of congestion status as provided in an embodiment of the present disclosure;

[0025] Figure 2 This is another schematic diagram illustrating the changing trend of congestion status provided in this embodiment of the disclosure;

[0026] Figure 3 A flowchart illustrating a traffic congestion tracing method provided in this embodiment of the present disclosure;

[0027] Figure 4 A schematic diagram illustrating the principle of creating a target road network according to an embodiment of this disclosure;

[0028] Figure 5 A schematic diagram of the structural information of a target road network provided in an embodiment of this disclosure;

[0029] Figure 6 A schematic diagram of a spatial adjacency matrix provided in an embodiment of this disclosure;

[0030] Figure 7 A schematic diagram of a distance adjacency matrix provided in an embodiment of this disclosure;

[0031] Figure 8 A traffic flow relationship representation diagram provided in this embodiment of the disclosure;

[0032] Figure 9A , Figure 9B , Figure 9C and Figure 9D This is a schematic diagram illustrating the effects of four correlation analysis methods provided in the embodiments of this disclosure;

[0033] Figure 10 A schematic diagram illustrating a traffic congestion tracing method provided in this embodiment of the present disclosure;

[0034] Figure 11 A schematic structural block diagram of a traffic congestion tracing device provided in this disclosure embodiment;

[0035] Figure 12 This is a schematic structural block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0036] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0037] As described in the background section, currently, congestion sources are typically identified based on mobile phone signaling. However, relying on mobile phone signaling can only roughly identify a large area as a congestion source, and cannot pinpoint the exact source of congestion.

[0038] The inventors discovered that the trend of traffic network congestion over time is similar to the spread of a virus in an infectious disease mechanism: it first appears sporadically, then gradually infects adjacent road sections, reaches a peak, and then gradually dissipates. Please refer to [link / reference]. Figure 1On a certain morning, around 6:00 AM, sporadic traffic congestion appeared on the road network. After 6:00 AM, the congestion on these existing sections gradually spread to adjacent sections, reaching its peak at 9:00 AM, and then gradually dissipating after 9:00 AM. Similarly, please combine this with... Figure 2 In the afternoon of that day, sporadic traffic congestion reappeared on the road network at 3:00 PM. After 3:00 PM, the congestion on existing road sections gradually spread to adjacent road sections, reaching its peak at 6:00 PM, and then gradually dissipating after 6:00 PM. Based on this, it can be understood that the congestion status of the road network usually exhibits a high degree of spatial correlation; that is, the closer the road section is to the source of congestion, the faster the congestion spreads and the earlier congestion occurs. At the same time, the congestion status of the road network also has a strong temporal correlation; for example, congestion is more severe during the morning and evening rush hours.

[0039] Based on the above research, this disclosure provides a method for tracing the source of traffic congestion, which can be applied to electronic devices. The following will be combined with... Figure 3 The flowchart shown illustrates a traffic congestion tracing method provided in this embodiment of the disclosure. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order.

[0040] Step S301: Determine the undetermined road segment and at least two reference road segments related to the undetermined road segment from the target road network; wherein, the reference road segments are the road segments into which the traffic flow of the undetermined road segment can flow.

[0041] Step S302: Obtain the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period;

[0042] Step S303: Calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period;

[0043] Step S304: If the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirements, the undetermined road segment is determined as the source of congestion in the target road network during the target time period.

[0044] The target road network can be used to characterize the traffic road network of a target area, which can be a city area, a district / county area, or any designated area. Furthermore, please combine this with... Figure 4In geographic coordinate systems, latitude and longitude coordinates are typically used to represent the location of points, string of points to represent the location of lines, and surfaces to represent the location of regions. Therefore, to obtain road segment-level road representations, in this embodiment of the disclosure, the intersection of the coordinate information of the string of points constituting a road segment and the location of the target region in the geographic coordinate system can be obtained based on a geographic database, thus obtaining the traffic network of the target region as the target road network. A road segment can be a driving section between two adjacent road nodes, and road nodes are typically equipped with traffic indicator devices such as traffic lights, pedestrian crossings, and stop signs.

[0045] The undetermined road segments can be any designated road segment in the target road network, or they can be selected from the target road network according to preset filtering conditions. For example, road segments in the target road network whose congestion start time is earlier than the source tracing cutoff time can be determined as undetermined road segments. The source tracing cutoff time can be the end time of the target time period. In addition, in this embodiment of the disclosure, the target time period can be a time period before the arrival of a preset peak period and whose duration is a preset duration threshold. The preset duration threshold can be preset, for example, it can be set to 30 minutes (min), 1 hour (h), 2 hours, etc. The preset duration threshold can also be set according to the number of road segments in the target road network, and this embodiment of the disclosure does not limit this. In a specific example, the preset duration threshold can be positively correlated with the number of road segments in the target road network.

[0046] After determining the undetermined road segment from the target road network, at least two reference road segments related to the undetermined road segment can be further determined from the target road network based on the structural information of the target road network. The reference road segments are road segments from which traffic flow can flow into the undetermined road segment; for example, they can be road segments from which traffic flow can flow directly into the undetermined road segment, or road segments from which traffic flow can flow indirectly into the undetermined road segment. Furthermore, in this embodiment, at least two reference road segments related to the undetermined road segment can be determined from the target road network according to a target order. The target order can be used to limit the range of reference road segments. For example, if the target order is 1, all road segments from the target road network that are first-order related (adjacent) to the undetermined road segment can be determined as reference road segments. As another example, if the target order is 3, all road segments from the target road network that are third-order related (intervened by two road segments) to the undetermined road segment can be determined as reference road segments. The target order can be preset or set according to the number of road segments in the target road network; this embodiment does not impose any restrictions on this. In a specific example, the target order can be positively correlated with the number of road segments in the target road network.

[0047] After identifying the undetermined road segment and at least two reference road segments related to it from the target road network, the congestion spread distance between the undetermined road segment and the reference road segments within the target time period can be obtained. This congestion spread distance is not a conventional physical distance, but rather an effective spread distance used to characterize the spread of congestion from the undetermined road segment to the reference road segments. The smaller the congestion spread distance, the faster the congestion spreads, and the earlier congestion will occur.

[0048] In this embodiment of the disclosure, it is also necessary to calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period. In one specific example, the first congestion time can be the starting congestion time of the undetermined road segment within the target time period, and correspondingly, the second congestion time can also be the starting congestion time of the reference road segment within the target time period. In another specific example, the first congestion time can be the time of severe congestion of the undetermined road segment within the target time period, and correspondingly, the second congestion time can also be the time of severe congestion of the reference road segment within the target time period.

[0049] The congestion spread distance and congestion time difference corresponding to each reference road segment are obtained and grouped into a set of relevant parameters. After obtaining at least two sets of relevant parameters, a correlation analysis can be performed on the congestion spread distance and congestion time difference to obtain the correlation degree between them. If the correlation degree between the congestion spread distance and congestion time difference meets a preset correlation requirement, the road segment to be identified as the congestion source of the target road network within the target time period. The preset correlation requirement can be that the congestion spread distance and congestion time difference are significantly positively correlated.

[0050] The traffic congestion source tracing method provided in this disclosure can determine a pending road segment and at least two reference road segments related to the pending road segment from the target road network. Then, it can obtain the congestion contagion distance between the pending road segment and the reference road segments within the target time period, calculate the congestion time difference between the first congestion time of the pending road segment and the second congestion time of the reference road segment within the target time period, and determine the pending road segment as the source of congestion in the target road network within the target time period if the correlation between the congestion contagion distance and the congestion time difference meets the preset correlation requirements. In this process, on the one hand, the granularity of traffic congestion source tracing is reduced to the road segment level. On the other hand, based on the congestion contagion characteristics of the traffic network (congestion status usually exhibits a high degree of spatial correlation, that is, the closer the road segment is to the congestion source, the faster the congestion status spreads and the earlier the congestion status will appear), the spatiotemporal characteristics of traffic congestion are deeply explored by calculating the correlation between congestion contagion distance and congestion time difference, and limiting the reference time period for congestion source tracing to the target time period. Therefore, compared with the existing technology, the accuracy of congestion source determination can be improved.

[0051] In some alternative implementations, the traffic congestion tracing method may also include the following steps:

[0052] Determine the preset peak periods;

[0053] Obtain the start time of the preset peak period;

[0054] The target time period is determined based on the start time of the preset peak period.

[0055] The preset peak period can be a peak period with high traffic demand, such as the morning peak period, the evening peak period, or other designated peak periods. This disclosure does not limit this.

[0056] After determining the preset peak period, the start time of the preset peak period can be obtained, and then the target period can be determined based on the start time of the preset peak period. In a specific example, the start time of the preset peak period can be used as the end time of the target period. For example, if the preset peak period is the morning peak period, and the morning peak period is 07:00~09:00, then 07:00 can be used as the end time of the target period, and the target period can be 06:00~07:00. As another example, if the preset peak period is the evening peak period, and the evening peak period is 17:00~19:00, then 17:00 can be used as the end time of the target period, and the target period can be 16:00~17:00.

[0057] Through the above steps, in this embodiment of the disclosure, a preset peak period can be determined, the start time of the preset peak period can be obtained, and a target period can be determined based on the start time of the preset peak period. Since the target period is determined automatically, the automation level of the traffic congestion tracing method can be improved. Furthermore, it is understood that in this embodiment of the disclosure, the preset peak period can be a peak period with high traffic demand, and the target period is strongly correlated with the preset peak period. Therefore, the correlation between the traffic congestion tracing method and the preset peak period can be enhanced, thereby improving the usability value of the traffic congestion tracing method.

[0058] Furthermore, as mentioned above, in this embodiment of the disclosure, road segments in the target road network whose initial congestion time is earlier than the source tracing cutoff time can be identified as pending road segments. Based on this, in some optional implementations, "identifying pending road segments from the target road network" may include the following steps:

[0059] Road segments in the target road network whose initial congestion time is earlier than the source tracing cutoff time are designated as pending road segments; where the source tracing cutoff time is the end time of the target time period.

[0060] The source tracing cutoff time can be the end time of the target time period, and the end time of the target time period can be the start time of the preset peak period. Based on this, it can be understood that in this embodiment of the disclosure, a target number of road segments in the target road network that have already experienced congestion before the arrival of the preset peak period can be determined as undetermined road segments. In a specific example, a target number of road segments in the target road network that have already experienced congestion before the arrival of the preset peak period and have the earliest start time of congestion can be determined as undetermined road segments. The target number can be preset or set according to the number of road segments in the target road network; this embodiment of the disclosure does not impose any restrictions on this. In a specific example, the target number can be positively correlated with the number of road segments in the target road network.

[0061] In this embodiment of the disclosure, for each road segment, the starting time of congestion can be determined based on the congestion index of that road segment. The congestion index can be a conceptual value used to characterize whether a road segment is smooth or congested, and it can be obtained based on pre-constructed congestion data.

[0062] Congestion data can be generated in the following ways:

[0063] Determine the statistical period for the congestion index. For example, using 5 minutes (min) as the statistical period, the 24 hours of a day can be divided into 288 statistical periods.

[0064] Calculate and store the congestion index for each road segment within any given statistical period to generate congestion data information.

[0065] Within a certain statistical period, the congestion index of each road segment can be the ratio of the traffic flow speed of that road segment during that statistical period to the traffic flow speed of that road segment when there is no obstruction at night.

[0066] The congestion data may also include the statistical date, as well as the start and end times of each statistical period within that date.

[0067] In a specific example, the statistical period is 5 minutes, and the start time of statistical period 1 is 00:00, the end time of statistical period 1 is 00:05, the start time of statistical period 2 is 00:05, the end time of statistical period 1 is 00:10, the start time of statistical period 3 is 00:10, the end time of statistical period 1 is 00:15, and so on. Finally, on the statistical date of April 20, 2023, the congestion data information shown in Table 1 can be obtained.

[0068] Table 1

[0069]

[0070] It should be noted that in this embodiment of the disclosure, the congestion data information may also have other data structures that are different from those shown in Table 1, which will not be elaborated here.

[0071] In this embodiment of the disclosure, for each road segment, the starting time of congestion can be determined based on the congestion index of that road segment. For example, the statistical period corresponding to the first congestion index among multiple congestion indices of that road segment that is greater than a first congestion threshold before the source tracing cutoff time can be determined as the target period, and the starting time of the target period can be determined as the starting time of congestion for that road segment. The first congestion threshold can be set according to actual application requirements, and this embodiment of the disclosure does not impose any restrictions on it.

[0072] Since road segments in the target road network whose initial congestion time is earlier than the source tracing deadline are usually the most likely sources of congestion in the target road network during the target time period, through the above steps, in this embodiment of the disclosure, road segments in the target road network whose initial congestion time is earlier than the source tracing deadline can be directly identified as undetermined road segments, thereby achieving relatively accurate selection of undetermined road segments and improving the efficiency of determining congestion sources.

[0073] Furthermore, as mentioned above, in this embodiment of the disclosure, the first congestion time is the initial congestion time of the undetermined road segment within the target time period, and the second congestion time is the initial congestion time of the reference road segment within the target time period; or, the first congestion time is the severe congestion time of the undetermined road segment within the target time period, and the second congestion time is the severe congestion time of the reference road segment within the target time period.

[0074] In this embodiment of the disclosure, after obtaining congestion data information, the first congestion time of the undetermined road segment within the target time period can be determined based on the congestion data information, and the second congestion time of the reference road segment within the target time period can be determined.

[0075] In a specific example, the first congestion time is the initial congestion time of the undetermined road segment within the target time period, and the second congestion time is the initial congestion time of the reference road segment within the target time period. Therefore, the statistical period corresponding to the first congestion index among multiple congestion indices of the undetermined road segment within the target time period that is greater than the first congestion threshold can be determined as the first period, and the start time of the first period can be determined as the initial congestion time of the undetermined road segment, i.e., the first congestion time. Similarly, the statistical period corresponding to the first congestion index among multiple congestion indices of the reference road segment within the target time period that is greater than the second congestion threshold can be determined as the second period, and the start time of the second period can be determined as the initial congestion time of the reference road segment, i.e., the second congestion time. The first and second congestion thresholds can be set according to actual application needs, and this embodiment does not impose any limitations on them. Furthermore, in this embodiment, the second congestion threshold can be less than or equal to the first congestion threshold.

[0076] In another specific example, the first congestion time is the time of severe congestion for the undetermined road segment within the target time period, and the second congestion time is the time of severe congestion for the reference road segment within the target time period. Therefore, the statistical period corresponding to the largest congestion index among multiple congestion indices for the undetermined road segment within the target time period can be determined as the third period, and the start time of the third period can be determined as the time of severe congestion for the undetermined road segment, i.e., the first congestion time. Similarly, the statistical period corresponding to the largest congestion index among multiple congestion indices for the reference road segment within the target time period can be determined as the fourth period, and the start time of the fourth period can be determined as the time of severe congestion for the reference road segment, i.e., the second congestion time.

[0077] Since the first congestion time is the starting time of congestion for the undetermined road segment within the target time period, and the second congestion time is the starting time of congestion for the reference road segment within the target time period; or, the first congestion time is the time of severe congestion for the undetermined road segment within the target time period, and the second congestion time is the time of severe congestion for the reference road segment within the target time period, there is a high degree of correspondence between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period. This can improve the reliability of the congestion time difference and further improve the accuracy of determining the source of congestion.

[0078] In some optional implementations, "obtaining the congestion contagion distance between the target road segment and the reference road segment within the target time period" may include the following steps:

[0079] Identify at least one candidate path from the target road network that is related to the reference road segment; wherein, the candidate path is the path that traffic flows through when it flows into the undetermined road segment and out of the reference road segment;

[0080] Obtain the effective path infection distance of candidate paths within the target time period to obtain at least one effective path infection distance;

[0081] The minimum effective path transmission distance among at least one effective path transmission distance is determined as the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period.

[0082] For each reference road segment, if the traffic flow of the undetermined road segment can directly flow into the reference road segment, only one candidate path related to the reference road segment can be determined from the target road network. The starting point of the candidate path is the undetermined road segment, and the ending point of the candidate path is the reference road segment.

[0083] For each reference road segment, if the traffic flow of the undetermined road segment can indirectly flow into the reference road segment, it is possible to determine only one candidate path related to the reference road segment from the target road network, with the starting point of the candidate path being the undetermined road segment and the ending point of the candidate path being the reference road segment. Alternatively, it is possible to determine at least two candidate paths related to the reference road segment from the target road network, with the starting point of the candidate path being the undetermined road segment and the ending point of the candidate path being the reference road segment.

[0084] For each reference road segment, after determining at least one candidate path related to the reference road segment from the target road network, the effective path transmission distance of each candidate path within the target time period can be obtained to obtain at least one effective path transmission distance. Then, the effective path transmission distance with the smallest value among the at least one effective path transmission distance is determined as the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period.

[0085] Please combine Figure 5 Suppose that the undetermined road segment is determined to be segment 1 from the target road network and the target order is 3. Therefore, the reference road segments related to the undetermined road segment include segment 4, segment 5, segment 6, segment 7, segment 8, segment 9 and segment 10.

[0086] Among them, the traffic flow of road segment 1 can directly flow into road segment 4. Only one candidate path related to road segment 4 can be determined from the target road network, that is, road segment 1 → road segment 4. Therefore, the effective path transmission distance of the candidate path (road segment 1 → road segment 4) can be directly determined as the congestion transmission distance between road segment 1 and road segment 4 within the target time period.

[0087] Traffic flow from segment 1 can indirectly flow into segment 6, and only one candidate path related to segment 6 can be determined from the target road network, namely, segment 1 → segment 5 → segment 6. Therefore, the effective path transmission distance of the candidate path (segment 1 → segment 5 → segment 6) can be directly determined as the congestion transmission distance between segment 1 and segment 6 within the target time period.

[0088] Traffic flow from segment 1 can indirectly flow into segment 7, and two candidate paths related to segment 7 can be determined from the target road network, namely, segment 1→segment 4→segment 7 and segment 1→segment 5→segment 6→segment 7. Therefore, the effective path infection distance with the smallest value between the effective path infection distance of the candidate path (segment 1→segment 4→segment 7) and the effective path infection distance of the candidate path (segment 1→segment 5→segment 6→segment 7) can be determined as the congestion infection distance between segment 1 and segment 7 within the target time period.

[0089] Based on the structural information of the target road network, traffic flow may take more than one candidate path when flowing into the undetermined road segment and out of the reference road segment, and each candidate path corresponds to an effective path contagion distance. Therefore, considering the actual driving scenario, it can be determined that the effective path contagion distance with the smallest value is the most valuable for reference. Based on this, through the above steps, in this embodiment of the disclosure, for each reference road segment, after determining at least one candidate path related to the reference road segment from the target road network, the effective path contagion distance of the candidate path within the target time period is obtained to obtain at least one effective path contagion distance. Then, the effective path contagion distance with the smallest value among the at least one effective path contagion distance is determined as the congestion contagion distance between the undetermined road segment and the reference road segment within the target time period, thereby improving the reliability of the congestion contagion distance and further improving the accuracy of congestion source determination.

[0090] In some optional implementations, "obtaining the effective path transmission distance of candidate paths within the target time period" may include the following steps:

[0091] The effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period is obtained and used as the target road segment infection distance.

[0092] When the number of infection distances for a target road segment is one, the infection distance for the target road segment is determined as the effective path infection distance for candidate paths within the target time period;

[0093] If the number of infection distances of the target road segment is at least two, the sum of the infection distances of the at least two target road segments is determined as the effective path infection distance of the candidate path within the target time period.

[0094] As mentioned earlier, for each candidate path, it may only include two adjacent target road segments. In this case, the effective road segment infection distance of these two adjacent target road segments in the candidate path within the target time period is obtained and used as the target road segment infection distance. The target road segment infection distance can then be determined as the effective path infection distance of the candidate path within the target time period.

[0095] For each candidate path, it may also include at least three adjacent target road segments. In this case, the effective road segment infection distance of any two adjacent target road segments in the candidate path within the target time period is obtained as the target road segment infection distance. After obtaining at least two target road segment infection distances, the sum of the at least two target road segment infection distances can be determined as the effective path infection distance of the candidate path within the target time period.

[0096] Continue with Figure 5Taking the target road network shown as an example, the undetermined road segment is segment 1 and the target order is 3. Therefore, the reference road segments related to the undetermined road segment include segment 4, segment 5, segment 6, segment 7, segment 8, segment 9 and segment 10.

[0097] Among them, the candidate path (segment 1 → segment 4) only includes two adjacent target segments. Therefore, after obtaining the effective segment infection distance between segment 1 and segment 4 within the target time period, and using it as the target segment infection distance, the target segment infection distance can be determined as the effective path infection distance of the candidate path (segment 1 → segment 4) within the target time period.

[0098] The candidate path (segment 1 → segment 5 → segment 6) includes three adjacent target segments. Therefore, after obtaining the effective segment infection distance between segment 1 and segment 5 within the target time period as the target segment infection distance, and obtaining the effective segment infection distance between segment 5 and segment 6 within the target time period as the target segment infection distance, the sum of these two target segment infection distances can be determined as the effective path infection distance of the candidate path (segment 1 → segment 5 → segment 6) within the target time period.

[0099] Through the above steps, in this embodiment of the disclosure, the effective road segment infection distance between any two adjacent target road segments in the candidate path within the target time period can be obtained as the target road segment infection distance. Then, when the number of target road segment infection distances is one, the target road segment infection distance is determined as the effective path infection distance of the candidate path within the target time period. When the number of target road segment infection distances is at least two, the sum of the at least two target road segment infection distances is determined as the effective path infection distance of the candidate path within the target time period. This refines the effective path infection distance into an integration of target road segment infection distances, which can improve the reliability of the effective path infection distance and further improve the accuracy of congestion source determination.

[0100] In some optional implementations, "obtaining the effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period" may include the following steps:

[0101] From the distance adjacency matrix, query the effective segment infection distance between any two adjacent target segments in the candidate path within the target time period.

[0102] The distance adjacency matrix can be pre-constructed to characterize the effective segment contagion distance of any group of road segments in the target road network. Each group of road segments can include two adjacent road segments with a flow-direction relationship. For example, the target road network is as follows: Figure 5As shown, the distance adjacency matrix can be used to characterize the effective road segment contagion distance for road segment groups (road segment 1 & road segment 4), road segment contagion distance for road segment groups (road segment 4 & road segment 7), road segment contagion distance for road segment groups (road segment 7 & road segment 8), and so on.

[0103] Through the above steps, in this embodiment of the disclosure, the effective road segment transmission distance between any two adjacent target road segments in the candidate paths within the target time period can be queried from the distance adjacency matrix. On the one hand, this improves the efficiency of obtaining the effective road segment transmission distance; on the other hand, regardless of which road segment is determined as a candidate road segment from the target road network, the effective road segment transmission distance can be queried through the distance adjacency matrix without real-time calculation. Therefore, it enhances the flexibility of traffic congestion source tracing.

[0104] In some alternative implementations, the traffic congestion tracing method may also include:

[0105] Create a spatial adjacency matrix, which is used to represent the flow direction relationship between any two adjacent road segments in the target road network;

[0106] Based on the spatial adjacency matrix, multiple road segment groups are determined; each road segment group includes two adjacent road segments with a flow direction relationship of permissible flow.

[0107] Obtain the effective transmission distance of road segment groups within the target time period;

[0108] Based on the effective road segment infection distance of the road segment group within the target time period, the spatial adjacency matrix is ​​updated to obtain the distance adjacency matrix.

[0109] The spatial adjacency matrix is ​​used to represent the flow relationship between any two adjacent road segments in the target road network. For example, if the flow relationship between two adjacent road segments is flowable, the marked position of the two adjacent road segments can be assigned a value of 1 in the preset matrix skeleton; otherwise, the marked position can be assigned a value of 0 or an empty value.

[0110] After creating the spatial adjacency matrix, multiple road segment groups can be identified based on it. Each road segment group includes two adjacent road segments with a flow relationship of permissible direction. Subsequently, the effective road segment spread distance for each road segment group within the target time period is obtained. Then, based on the effective road segment spread distance of the road segment groups within the target time period, the spatial adjacency matrix is ​​updated to obtain a distance adjacency matrix, which is used to characterize the effective road segment spread distance of each road segment group in the target road network within the target time period.

[0111] Continue with Figure 5 Taking the target road network shown as an example, the undetermined road segment is segment 1 and the target order is 3. Therefore, the reference road segments related to the undetermined road segment include segment 4, segment 5, segment 6, segment 7, segment 8, segment 9 and segment 10.

[0112] In this system, road segments 1 and 2 are adjacent road segments, and the flow direction between them is non-flowing; therefore, the marked positions of road segments 1 and 2 can be assigned null values. Similarly, road segments 1 and 3 are adjacent road segments, and the flow direction between them is non-flowing; therefore, the marked positions of road segments 1 and 3 can be assigned null values. Road segments 1 and 4 are adjacent road segments, and the flow direction between them is flowable; therefore, the marked positions of road segments 1 and 4 can be assigned the value 1… Finally, a system like this can be created… Figure 6 The spatial adjacency matrix is ​​shown.

[0113] Next, obtain the effective transmission distance for each road segment group within the target time period. For example, obtain the effective transmission distance for road segment group (road segment 1 & road segment 4), road segment group (road segment 4 & road segment 7), road segment group (road segment 7 & road segment 8), etc.

[0114] Then, based on the effective segment infection distance of each segment group within the target time period, the spatial adjacency matrix is ​​updated to obtain, as follows: Figure 7 The distance adjacency matrix is ​​shown.

[0115] Through the above steps, in this embodiment of the disclosure, a spatial adjacency matrix can be created. Based on the spatial adjacency matrix, multiple road segment groups can be determined, and the effective road segment transmission distance of the road segment groups within the target time period can be obtained. Based on the effective road segment transmission distance of the road segment groups within the target time period, the spatial adjacency matrix is ​​updated to obtain a distance adjacency matrix. In this process, the creation of the distance adjacency matrix is ​​phased; specifically, the spatial adjacency matrix is ​​created first, and then the distance adjacency matrix is ​​obtained based on the spatial adjacency matrix, thereby improving the reliability of the distance adjacency matrix and further improving the accuracy of congestion source identification.

[0116] In some optional implementations, "obtaining the effective road segment transmission distance for a road segment group within a target time period" may include the following steps:

[0117] Obtain the first traffic flow; where the first traffic flow is the traffic flow from the first road segment to the second road segment in the road segment group during the target time period;

[0118] Obtain the second traffic flow; where the second traffic flow is the total traffic flow flowing out of the first road segment during the target time period;

[0119] Based on the first and second traffic flows, the effective transmission distance of the road segment group within the target time period is calculated.

[0120] The first traffic flow refers to the traffic flow from the first road segment to the second road segment within the road segment group during the target time period, while the second traffic flow refers to the total traffic flow flowing out of the first road segment during the target time period. Both the first and second traffic flows can be obtained from traffic video data collected by video surveillance equipment such as checkpoint cameras, electronic police systems, and integrated checkpoint electronic police devices, which will not be elaborated upon here.

[0121] After obtaining the first and second traffic flow data, the effective transmission distance of the road segment group within the target time period can be calculated based on these data. In a specific example, this process can be implemented using the following calculation logic:

[0122]

[0123]

[0124] Where, d AX P represents the effective transmission distance of road segment groups within the target time period. AX F1 represents the ratio of the first traffic flow to the second traffic flow, where F1 is the first traffic flow and F2 is the second traffic flow.

[0125] Based on the above calculation logic, it can be understood that the effective transmission distance between the first and second road segments within the target time period is negatively correlated with the ratio of the first traffic flow to the second traffic flow within the target time period. That is, if most of the traffic flowing out of the first road segment flows to the second road segment within the target time period, the ratio P of the first traffic flow to the second traffic flow will be negatively correlated. AX The effective transmission distance d between the first and second road segments is relatively large. AX A smaller ratio (P1) indicates a faster spread of congestion from the first road segment to the second road segment; conversely, if only a small portion of the traffic flowing out of the first road segment flows into the second road segment during the target time period, the ratio P1 of the first traffic flow to the second traffic flow is lower. AX The effective transmission distance d between the first and second road segments is relatively small. AX A larger value indicates that the congestion spreads slowly from the first road segment to the second road segment.

[0126] Continue with Figure 5 Taking the target road network shown as an example, the undetermined road segment is segment 1 and the target order is 3. Therefore, the reference road segments related to the undetermined road segment include segment 4, segment 5, segment 6, segment 7, segment 8, segment 9 and segment 10.

[0127] In the road segment group (segment 1 & segment 4), the total traffic flow out of segment 1 during the target time period is 100, and the traffic flow from segment 1 to segment 4 during the target time period is 40. Therefore, based on the above calculation logic, the effective road segment transmission distance of the road segment group (segment 1 & segment 4) during the target time period can be obtained as 1.4. In the road segment group (segment 1 & segment 5), the total traffic flow out of segment 1 during the target time period is 100, and the traffic flow from segment 1 to segment 4 during the target time period is 40. The traffic flow is 60. Therefore, based on the above calculation logic, the effective road segment transmission distance for the road segment group (road segment 1 & road segment 5) within the target time period is 1.22. In the road segment group (road segment 2 & road segment 4), the total traffic flow out of road segment 1 within the target time period is 100, and the traffic flow from road segment 2 to road segment 4 within the target time period is 100. Therefore, based on the above calculation logic, the effective road segment transmission distance for the road segment group (road segment 2 & road segment 4) within the target time period is 1…

[0128] Within the target time period, each group of road segments in the target road network has the following characteristics: Figure 8 Given the traffic flow relationship shown, the final result can be obtained as follows: Figure 7 The distance adjacency matrix shown is used to characterize the effective segment infection distance of each segment group in the target road network within the target time period.

[0129] Through the above steps, in this embodiment of the disclosure, a first traffic flow and a second traffic flow can be obtained. The first traffic flow is the traffic flow from the first road segment to the second road segment in the road segment group during the target time period, and the second traffic flow is the total traffic flow flowing out of the first road segment during the target time period. Subsequently, based on the first and second traffic flows, the effective road segment transmission distance of the road segment group during the target time period is calculated. This process allows for in-depth analysis of the correlation between the effective road segment transmission distance and traffic flow between road segments, thereby providing a more refined reflection of the actual causes of congestion on a particular road and further improving the accuracy of identifying the source of congestion.

[0130] In this embodiment of the disclosure, in addition to querying the effective road segment infection distance between any two adjacent target road segments in the candidate path within the target time period from the distance adjacency matrix, the effective road segment infection distance between any two adjacent target road segments in the candidate path within the target time period can also be obtained by direct calculation. Based on this, in some optional implementations, "obtaining the effective road segment infection distance between any two adjacent target road segments in the candidate path within the target time period" may include the following steps:

[0131] Obtain the third traffic flow; where the third traffic flow is the traffic flow from the first target road segment to the second target road segment among two adjacent target road segments during the target time period;

[0132] The fourth traffic flow is obtained; where the fourth traffic flow is the total traffic flow flowing out of the first target road segment during the target time period.

[0133] Based on the third and fourth traffic flow rates, the effective transmission distance between two adjacent target road segments is calculated.

[0134] The above steps can be found in the description of "Obtaining the effective transmission distance of road segments within the target time period", and will not be repeated here.

[0135] Through the above steps, in this embodiment, the third and fourth traffic flows can be directly obtained. The third traffic flow is the traffic flow from the first target road segment to the second target road segment within the target time period, and the fourth traffic flow is the total traffic flow flowing out of the first target road segment within the target time period. Subsequently, based on the third and fourth traffic flows, the effective road segment transmission distance between the two adjacent target road segments is calculated. On the one hand, this allows for in-depth analysis of the correlation between the effective road segment transmission distance and traffic flow between road segments, thus providing a more refined reflection of the actual causes of congestion on a particular road and further improving the accuracy of congestion source identification. On the other hand, since the process of creating the distance adjacency matrix is ​​omitted, the amount of data computation for traffic congestion tracing can be reduced, saving computing resources for electronic devices.

[0136] In some optional implementations, "determining that the correlation between congestion transmission distance and congestion time difference meets a preset correlation requirement" may include the following steps:

[0137] If the correlation between congestion transmission distance and congestion time difference is greater than the preset correlation value, then the correlation between congestion transmission distance and congestion time difference is determined to meet the preset correlation requirement.

[0138] In a specific example, a correlation analysis can be performed between congestion transmission distance and congestion time difference. For instance, the Pearson correlation coefficient between congestion transmission distance and congestion time difference can be calculated as the correlation between them. Subsequently, if the correlation between congestion transmission distance and congestion time difference is greater than a preset correlation value, it is determined that the correlation between congestion transmission distance and congestion time difference meets the preset correlation requirement. The preset correlation value can be set according to actual application needs; for example, it can be set to 0.95, and this embodiment does not limit this.

[0139] Continue with Figure 5 Taking the target road network shown as an example, the undetermined road segment is segment 1 and the target order is 3. Therefore, the reference road segments related to the undetermined road segment include segment 4, segment 5, segment 6, segment 7, segment 8, segment 9 and segment 10.

[0140] Assume that the congestion contagion distance between road segment 1 and any reference road segment, and the congestion time difference between the first congestion time of road segment 1 in the target time period and the second congestion time of any reference road segment in the target time period are as shown in Table 2.

[0141] Table 2

[0142]

[0143] Therefore, the congestion contagion distance of 1.4 and the congestion time difference T between road segment 1 and road segment 4 can be used as the basis for determining the degree of congestion spread. 14 As a set of correlation analysis data, the congestion contagion distance of 1.22 and the congestion time difference T between road segment 1 and road segment 5 are used. 15 As a set of correlation analysis data, the congestion contagion distance of 2.92 and the congestion time difference T between road segment 1 and road segment 6 were used. 16 As a set of correlation analysis data... In the end, 7 sets of correlation analysis data were obtained. Based on these 7 sets of correlation analysis data, the Pearson correlation coefficient between congestion transmission distance and congestion time difference was calculated as the correlation between congestion transmission distance and congestion time difference.

[0144] Through the above steps, in this embodiment of the disclosure, if the correlation between the congestion transmission distance and the congestion time difference is greater than a preset correlation value, it can be determined that the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirement, thereby ensuring that the congestion transmission distance and the congestion time difference have a strong correlation, so as to further improve the accuracy of determining the source of congestion.

[0145] Please combine Figure 9A , Figure 9B and Figure 9C The results were obtained by performing correlation analysis on the Euclidean distance, driving path distance, and traffic merging / emerging ratio between the target road segment and the reference road segment within the target time period, with the congestion time difference. Clearly, the correlations between the Euclidean distance, driving path distance, and traffic merging / emerging ratio with the congestion time difference are not significant.

[0146] See also Figure 9D This involves performing a correlation analysis between the congestion spread distance and the congestion time difference between a potential road segment and a reference road segment within a target time period. The analysis results clearly show a strong positive correlation between the congestion spread distance and the congestion time difference. Furthermore, if the correlation between the congestion spread distance and the congestion time difference exceeds a preset correlation value, the correlation between the congestion spread distance and the congestion time difference can be determined to meet the preset correlation requirement, and the potential road segment can be identified as the congestion source of the target road network within the target time period.

[0147] Please see Figure 10 This is a schematic diagram of a traffic congestion tracing method provided in an embodiment of this disclosure.

[0148] As previously described, the traffic congestion tracing method provided in this disclosure is applied to electronic devices. Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital processors, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices.

[0149] Electronic devices can be used for:

[0150] Identify undetermined road segments from the target road network, and at least two reference road segments related to the undetermined road segments; wherein, the reference road segments are the road segments into which traffic flow can flow from the undetermined road segments;

[0151] Obtain the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period;

[0152] Calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period;

[0153] If the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirements, the undetermined road segment is identified as the source of congestion in the target road network during the target time period.

[0154] It should be noted that, in the embodiments disclosed herein, Figure 10 The schematic diagrams shown are for illustrative purposes only and are not restrictive. Those skilled in the art can use them as a basis for their own interpretation. Figure 10 The examples may be modified in various obvious ways and / or substitutions, and the resulting technical solutions still fall within the scope of the disclosure of the embodiments of this disclosure.

[0155] To better implement traffic congestion tracing methods, this disclosure also provides a traffic congestion tracing device, which can be integrated into an electronic device. The following will be combined with... Figure 11 The schematic diagram shown illustrates a traffic congestion tracing device 1100 provided in the disclosed embodiment.

[0156] The road segment determination unit 1101 is used to determine a road segment to be determined from the target road network, and at least two reference road segments related to the road segment to be determined; wherein, the reference road segments are the road segments into which the traffic flow of the road segment to be determined can flow.

[0157] The transmission distance acquisition unit 1102 is used to acquire the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period;

[0158] The time difference calculation unit 1103 is used to calculate the congestion time difference between the first congestion time of the undetermined road segment in the target time period and the second congestion time of the reference road segment in the target time period.

[0159] The congestion source identification unit 1104 is used to identify the undetermined road segment as the congestion source of the target road network within the target time period, provided that the correlation between the congestion transmission distance and the congestion time difference meets the preset correlation requirements.

[0160] In some optional implementations, the infection distance acquisition unit 1102 is used for:

[0161] Identify at least one candidate path from the target road network that is related to the reference road segment; wherein, the candidate path is the path that traffic flows through when it flows into the undetermined road segment and out of the reference road segment;

[0162] Obtain the effective path infection distance of candidate paths within the target time period to obtain at least one effective path infection distance;

[0163] The minimum effective path transmission distance among at least one effective path transmission distance is determined as the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period.

[0164] In some optional implementations, the infection distance acquisition unit 1102 is used for:

[0165] Obtain the effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period, and use it as the target road segment infection distance;

[0166] When the number of infection distances for a target road segment is one, the infection distance for the target road segment is determined as the effective path infection distance for candidate paths within the target time period;

[0167] If the number of infection distances of the target road segment is at least two, the sum of the infection distances of the at least two target road segments is determined as the effective path infection distance of the candidate path within the target time period.

[0168] In some optional implementations, the infection distance acquisition unit 1102 is used for:

[0169] From the distance adjacency matrix, query the effective segment infection distance between any two adjacent target segments in the candidate paths within the target time period.

[0170] In some alternative implementations, the traffic congestion tracing device 1100 further includes a matrix creation unit for:

[0171] Create a spatial adjacency matrix, which is used to represent the flow direction relationship between any two adjacent road segments in the target road network;

[0172] Based on the spatial adjacency matrix, multiple road segment groups are determined; each road segment group includes two adjacent road segments with a flow direction relationship of permissible flow.

[0173] Obtain the effective transmission distance of road segment groups within the target time period;

[0174] Based on the effective road segment infection distance of the road segment group within the target time period, the spatial adjacency matrix is ​​updated to obtain the distance adjacency matrix.

[0175] In some optional implementations, the matrix creation unit is used for:

[0176] Obtain the first traffic flow; where the first traffic flow is the traffic flow from the first road segment to the second road segment in the road segment group during the target time period;

[0177] Obtain the second traffic flow; where the second traffic flow is the total traffic flow flowing out of the first road segment during the target time period;

[0178] Based on the first and second traffic flows, the effective transmission distance of the road segment group within the target time period is calculated.

[0179] In some optional implementations, the infection distance acquisition unit 1102 is used for:

[0180] Obtain the third traffic flow; where the third traffic flow is the traffic flow from the first target road segment to the second target road segment among two adjacent target road segments during the target time period;

[0181] The fourth traffic flow is obtained; where the fourth traffic flow is the total traffic flow flowing out of the first target road segment during the target time period.

[0182] Based on the third and fourth traffic flow rates, the effective transmission distance between two adjacent target road segments is calculated.

[0183] In some alternative implementations, the traffic congestion tracing device 1100 further includes a time period determination unit for:

[0184] Determine the preset peak periods;

[0185] Obtain the start time of the preset peak period;

[0186] The target time period is determined based on the start time of the preset peak period.

[0187] In some alternative implementations, the road segment determination unit 1101 is used for:

[0188] Road segments in the target road network whose initial congestion time is earlier than the source tracing cutoff time are designated as pending road segments; where the source tracing cutoff time is the end time of the target time period.

[0189] In some alternative implementations, the first congestion time is the start time of congestion for the undetermined road segment within the target time period, and the second congestion time is the start time of congestion for the reference road segment within the target time period;

[0190] Alternatively, the first congestion time is the time of severe congestion for the undetermined road segment within the target time period, and the second congestion time is the time of severe congestion for the reference road segment within the target time period.

[0191] In some alternative implementations, the congestion source determination unit 1104 is used to:

[0192] If the correlation between congestion transmission distance and congestion time difference is greater than the preset correlation value, then the correlation between congestion transmission distance and congestion time difference is determined to meet the preset correlation requirement.

[0193] The specific functions and examples of each unit of the traffic congestion tracing device 1100 in this embodiment can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0194] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0195] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0196] Figure 12 A schematic block diagram of an example electronic device 1200 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0197] like Figure 12As shown, device 1200 includes a computing unit 1201, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 1202 or a computer program loaded from storage unit 1208 into random access memory (RAM) 1203. The RAM 1203 may also store various programs and data required for the operation of device 1200. The computing unit 1201, ROM 1202, and RAM 1203 are interconnected via bus 1204. An input / output (I / O) interface 1205 is also connected to bus 1204.

[0198] Multiple components in device 1200 are connected to I / O interface 1205, including: input unit 1206, such as keyboard, mouse, etc.; output unit 1207, such as various types of monitors, speakers, etc.; storage unit 1208, such as disk, optical disk, etc.; and communication unit 1209, such as network card, modem, wireless transceiver, etc. Communication unit 1209 allows device 1200 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0199] The computing unit 1201 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1201 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 1201 performs the various methods and processes described above, such as a traffic congestion tracing method. For example, in some embodiments, the traffic congestion tracing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1208. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1200 via ROM 1202 and / or communication unit 1209. When the computer program is loaded into RAM 1203 and executed by the computing unit 1201, one or more steps of the traffic congestion tracing method described above may be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured to perform a traffic congestion tracing method by any other suitable means (e.g., by means of firmware).

[0200] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0201] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0202] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM) or flash memory, optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0203] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) monitor or a liquid crystal display (LCD)); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0204] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0205] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0206] This disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute a traffic congestion tracing method.

[0207] This disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements a traffic congestion tracing method.

[0208] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein. Furthermore, in this disclosure, relational terms such as "first," "second," and "third" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0209] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for tracing the source of traffic congestion, comprising: Identify undetermined road segments from the target road network, and at least two reference road segments related to the undetermined road segments; wherein the reference road segments are the road segments into which traffic flow can flow to the undetermined road segments; Obtain the congestion spread distance between the undetermined road segment and the reference road segment within the target time period; wherein, the congestion spread distance is used to characterize the effective spread distance required for the congestion state to spread from the undetermined road segment to the reference road segment, and the smaller the congestion spread distance, the faster the congestion state spreads; Calculate the congestion time difference between the first congestion time of the undetermined road segment within the target time period and the second congestion time of the reference road segment within the target time period; If the correlation between the congestion spread distance and the congestion time difference meets the preset correlation requirement, the undetermined road segment is determined as the congestion source of the target road network in the target time period.

2. The method according to claim 1, wherein, The acquisition of the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period includes: Determine at least one candidate path from the target road network that is related to the reference road segment; wherein the candidate path is the path taken by traffic flow when it flows into the undetermined road segment and out of the reference road segment; Obtain the effective path infection distance of the candidate path within the target time period to obtain at least one effective path infection distance; The effective path transmission distance with the smallest value among the at least one effective path transmission distance is determined as the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period.

3. The method according to claim 2, wherein, The step of obtaining the effective path transmission distance of the candidate path within the target time period includes: The effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period is obtained and used as the target road segment infection distance. When the number of infection distances of the target road segment is one, the infection distance of the target road segment is determined as the effective path infection distance of the candidate path within the target time period; When the number of infection distances of the target road segment is at least two, the sum of the infection distances of the at least two target road segments is determined as the effective path infection distance of the candidate path within the target time period.

4. The method according to claim 3, wherein, The step of obtaining the effective segment infection distance between any two adjacent target segments in the candidate path within the target time period includes: From the distance adjacency matrix, query the effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period.

5. The method according to claim 4, further comprising: Create a spatial adjacency matrix, which is used to characterize the flow direction relationship between any two adjacent road segments in the target road network; Based on the spatial adjacency matrix, multiple road segment groups are determined; wherein each road segment group includes two adjacent road segments with a flow direction relationship of flowability. Obtain the effective transmission distance of the road segment group within the target time period; Based on the effective road segment infection distance of the road segment group within the target time period, the spatial adjacency matrix is ​​updated to obtain the distance adjacency matrix.

6. The method according to claim 5, wherein, The step of obtaining the effective road segment transmission distance of the road segment group within the target time period includes: Obtain the first traffic flow; wherein, the first traffic flow is the traffic flow from the first road segment to the second road segment in the road segment group during the target time period; Obtain the second traffic flow; wherein, the second traffic flow is the total traffic flow flowing out of the first road segment during the target time period; Based on the first traffic flow and the second traffic flow, the effective road segment transmission distance of the road segment group within the target time period is calculated.

7. The method according to claim 3, wherein, The step of obtaining the effective segment infection distance between any two adjacent target segments in the candidate path within the target time period includes: Obtain the third traffic flow; wherein, the third traffic flow is the traffic flow from the first target road segment to the second target road segment during the target time period; The fourth traffic flow is obtained; wherein, the fourth traffic flow is the total traffic flow flowing out of the first target road segment during the target time period; Based on the third and fourth traffic flows, the effective road segment transmission distance between the two adjacent target road segments is calculated.

8. The method according to any one of claims 1 to 7, further comprising: Determine the preset peak periods; Obtain the start time of the preset peak period; The target time period is determined based on the start time of the preset peak period.

9. The method according to any one of claims 1 to 7, wherein, The process of determining the undetermined road segment from the target road network includes: The road segments in the target road network whose initial congestion time is earlier than the source tracing cutoff time are identified as the undetermined road segments; wherein, the source tracing cutoff time is the end time of the target time period.

10. The method according to any one of claims 1 to 7, wherein, The first congestion time is the start time of congestion for the undetermined road segment within the target time period, and the second congestion time is the start time of congestion for the reference road segment within the target time period; Alternatively, the first congestion time is the time of severe congestion for the undetermined road segment within the target time period, and the second congestion time is the time of severe congestion for the reference road segment within the target time period.

11. The method according to any one of claims 1 to 7, wherein, Determining that the correlation between the congestion transmission distance and the congestion time difference meets a preset correlation requirement includes: If the correlation between the congestion transmission distance and the congestion time difference is greater than a preset correlation value, then the correlation between the congestion transmission distance and the congestion time difference is determined to meet the preset correlation requirement.

12. A traffic congestion tracing device, comprising: A road segment determination unit is used to determine a road segment to be determined from a target road network, and at least two reference road segments related to the road segment to be determined; wherein the reference road segments are road segments into which traffic flow can flow to the road segment to be determined. The congestion transmission distance acquisition unit is used to acquire the congestion transmission distance between the undetermined road segment and the reference road segment within a target time period; wherein, the congestion transmission distance is used to characterize the effective transmission distance used for the congestion state to spread from the undetermined road segment to the reference road segment, and the smaller the congestion transmission distance, the faster the congestion state spreads; The time difference calculation unit is used to calculate the congestion time difference between the first congestion time of the undetermined road segment in the target time period and the second congestion time of the reference road segment in the target time period; The congestion source determination unit is used to determine the undetermined road segment as the congestion source of the target road network in the target time period when the correlation between the congestion contagion distance and the congestion time difference meets the preset correlation requirements.

13. The apparatus according to claim 12, wherein, The infection distance acquisition unit is used for: Determine at least one candidate path from the target road network that is related to the reference road segment; wherein the candidate path is the path taken by traffic flow when it flows into the undetermined road segment and out of the reference road segment; Obtain the effective path infection distance of the candidate path within the target time period to obtain at least one effective path infection distance; The effective path transmission distance with the smallest value among the at least one effective path transmission distance is determined as the congestion transmission distance between the undetermined road segment and the reference road segment within the target time period.

14. The apparatus according to claim 13, wherein, The infection distance acquisition unit is used for: The effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period is obtained and used as the target road segment infection distance. When the number of infection distances of the target road segment is one, the infection distance of the target road segment is determined as the effective path infection distance of the candidate path within the target time period; When the number of infection distances of the target road segment is at least two, the sum of the infection distances of the at least two target road segments is determined as the effective path infection distance of the candidate path within the target time period.

15. The apparatus according to claim 14, wherein, The infection distance acquisition unit is used for: From the distance adjacency matrix, query the effective segment infection distance between any two adjacent target road segments in the candidate path within the target time period.

16. The apparatus of claim 15, further comprising a matrix creation unit, configured to: Create a spatial adjacency matrix, which is used to characterize the flow direction relationship between any two adjacent road segments in the target road network; Based on the spatial adjacency matrix, multiple road segment groups are determined; among them... Each road segment group includes two adjacent road segments with a flow direction relationship of permissible flow; Obtain the effective transmission distance of the road segment group within the target time period; Based on the effective road segment infection distance of the road segment group within the target time period, the spatial adjacency matrix is ​​updated to obtain the distance adjacency matrix.

17. The apparatus according to claim 16, wherein, The matrix creation unit is used for: Obtain the first traffic flow; wherein, the first traffic flow is the traffic flow from the first road segment to the second road segment in the road segment group during the target time period; Obtain the second traffic flow; wherein, the second traffic flow is the total traffic flow flowing out of the first road segment during the target time period; Based on the first traffic flow and the second traffic flow, the effective road segment transmission distance of the road segment group within the target time period is calculated.

18. The apparatus according to claim 14, wherein, The infection distance acquisition unit is used for: Obtain the third traffic flow; wherein, the third traffic flow is the traffic flow from the first target road segment to the second target road segment during the target time period; The fourth traffic flow is obtained; wherein, the fourth traffic flow is the total traffic flow flowing out of the first target road segment during the target time period; Based on the third and fourth traffic flows, the effective road segment transmission distance between the two adjacent target road segments is calculated.

19. The apparatus according to any one of claims 12 to 18, further comprising a time period determination unit, used for: Determine the preset peak periods; Obtain the start time of the preset peak period; The target time period is determined based on the start time of the preset peak period.

20. The apparatus according to any one of claims 12 to 18, wherein, The road segment determination unit is used for: The road segments in the target road network whose initial congestion time is earlier than the source tracing cutoff time are identified as the undetermined road segments; wherein, the source tracing cutoff time is the end time of the target time period.

21. The apparatus according to any one of claims 12 to 18, wherein, The first congestion time is the start time of congestion for the undetermined road segment within the target time period, and the second congestion time is the start time of congestion for the reference road segment within the target time period; Alternatively, the first congestion time is the time of severe congestion for the undetermined road segment within the target time period, and the second congestion time is the time of severe congestion for the reference road segment within the target time period.

22. The apparatus according to any one of claims 12 to 18, wherein, The congestion source identification unit is used for: If the correlation between the congestion transmission distance and the congestion time difference is greater than a preset correlation value, then the correlation between the congestion transmission distance and the congestion time difference is determined to meet the preset correlation requirement.

23. An electronic device, comprising: At least one processor; A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 11.

25. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images