Traffic situation congestion prediction method, system, computer device and storage medium
By clustering motor vehicle stopping areas and activity types, and combining this with graphical model analysis, accurate prediction of sporadic traffic congestion was achieved. This solves the problem that existing technologies cannot accurately predict sporadic congestion, and improves the precision and accuracy of traffic management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING SINOITS TECH
- Filing Date
- 2023-11-16
- Publication Date
- 2026-05-15
AI Technical Summary
Existing technologies cannot accurately predict sporadic traffic congestion, resulting in insufficient emergency control plans that cannot meet the needs of refined traffic management.
By identifying the areas where motor vehicles stop, clustering activity types, obtaining semantic sequences and performing short-time frame-by-frame clustering, and combining this with graph model analysis, traffic congestion can be predicted.
It enables accurate early warning of occasional traffic congestion, improves the precision of traffic management and the accuracy of prediction, and supports real-time data updates and information push.
Smart Images
Figure CN117542200B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of traffic planning and management technology, and in particular to a method, system, computer equipment, and storage medium for predicting traffic congestion. Background Technology
[0002] With the rapid increase in motor vehicle ownership and the continuous growth in residents' travel demands, urban traffic congestion has worsened. While the rapid development of highways and the initial formation of a highway network have brought convenience to residents, the frequent occurrence of highway congestion significantly diminishes the advantages of highways' "fast and smooth" operation. For traffic managers, highway congestion increases operating costs, complicates coordination and control, and lowers the overall efficiency of the highway network. Therefore, formulating reasonable traffic control policies and developing scientifically sound emergency plans has become a top priority for traffic management departments.
[0003] Traffic congestion can be categorized into recurring and sporadic congestion based on its causes. Recurring congestion occurs when traffic demand exceeds the normal capacity of road infrastructure; current prediction methods are numerous and relatively accurate. Sporadic congestion, on the other hand, is caused by sudden traffic events that temporarily reduce road capacity below the current traffic demand. It is more random and falls under the more challenging category of "unsupervised congestion pattern analysis." Existing methods and systems used by traffic management departments are inaccurate in predicting sporadic congestion, and their emergency control plans are insufficient and unscientific, often leading to long-distance, long-duration, and large-scale congestion. This fails to guarantee the operational efficiency of highways and cannot meet the needs of refined and diversified traffic management models. Summary of the Invention
[0004] The technical problem to be solved by this invention is to address the shortcomings of existing technologies, and specifically provides a method, system, computer equipment, and storage medium for predicting traffic congestion, as detailed below:
[0005] 1) In a first aspect, the present invention provides a method for predicting traffic congestion, the specific technical solution of which is as follows:
[0006] Determine the stopping area for each motor vehicle on the pre-defined road segment;
[0007] Based on the parking area of each motor vehicle, the activity type of each motor vehicle is clustered;
[0008] Based on the activity clustering results of each motor vehicle, a semantic sequence of the activity clusters for each motor vehicle is obtained;
[0009] Based on a preset time window, the semantic sequence of each motor vehicle's activity cluster is divided into short-time frames to obtain the short-time individual motor vehicle activity type semantic sequence for each motor vehicle.
[0010] Cluster the short-term individual vehicle activity type semantic sequences for each vehicle;
[0011] Based on the clustering results of the short-term individual motor vehicle activity type semantic sequence for each motor vehicle, traffic congestion is predicted for the preset road segment.
[0012] The beneficial effects of the traffic congestion prediction method provided by this invention are as follows:
[0013] This invention breaks away from traditional approaches such as unsupervised identification methods that judge congestion behavior based on deviation from normal patterns and supervised identification methods that judge congestion behavior based on similarity to known congestion behavior patterns. It predicts traffic congestion based on vehicle behavior semantic analysis and congestion risk warning, solving the challenge of analyzing and warning of sporadic congestion characterized by "new and unknown" events. This invention addresses the traditional problem that existing technologies cannot accurately determine sporadic congestion.
[0014] Based on the above scheme, the traffic congestion prediction method of the present invention can be further improved as follows.
[0015] Furthermore, the stopping area for each motor vehicle on the pre-defined road segment is determined, including:
[0016] Obtain and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment.
[0017] Furthermore, based on the parking area of each motor vehicle, activity type clustering is performed for each motor vehicle, including:
[0018] A graph model clustering scheme is adopted, and each motor vehicle is clustered by activity type based on its parking area.
[0019] Furthermore, it also includes:
[0020] When the preset traffic congestion result for a pre-defined road segment is congested, an alert will be issued.
[0021] 2) Secondly, the present invention also provides a system for predicting traffic congestion, the specific technical solution of which is as follows:
[0022] It includes a determination module, a first clustering module, a semantic sequence acquisition module, a framing module, a second clustering module, and a congestion prediction module;
[0023] The determination module is used to: determine the stopping area for each motor vehicle on a preset road segment;
[0024] The first clustering module is used to: cluster each motor vehicle by activity type based on the parking area of each motor vehicle;
[0025] The semantic sequence acquisition module is used to: obtain the semantic sequence of each motor vehicle's activity cluster based on the activity clustering results of each motor vehicle;
[0026] The framing module is used to: perform short-time framing on the semantic sequence of each motor vehicle's activity cluster according to a preset time window, so as to obtain a short-time individual motor vehicle activity type semantic sequence for each motor vehicle;
[0027] The second clustering module is used to cluster the short-term individual vehicle activity type semantic sequences for each vehicle.
[0028] The congestion prediction module is used to predict traffic congestion on preset road segments based on the clustering results of the short-term individual vehicle activity type semantic sequence for each vehicle.
[0029] Based on the above scheme, the traffic congestion prediction system of the present invention can be further improved as follows.
[0030] Furthermore, it was determined that the module is specifically used for:
[0031] Obtain and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment.
[0032] Furthermore, the first clustering module is specifically used for:
[0033] A graph model clustering scheme is adopted, and each motor vehicle is clustered by activity type based on its parking area.
[0034] Furthermore, it also includes a reminder module, which is used to issue a reminder when the preset traffic congestion result of a preset road segment is congested.
[0035] 3) In a third aspect, the present invention also provides a computer device, the computer device including a processor coupled to a memory, the memory storing at least one computer program, the at least one computer program being loaded and executed by the processor, so that the computer device implements any of the above-mentioned methods for predicting traffic congestion.
[0036] 4) In a fourth aspect, the present invention also provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above-mentioned methods for predicting traffic congestion.
[0037] It should be noted that the beneficial effects of the technical solutions of the second to fourth aspects of the present invention and their corresponding possible implementations can be found in the above description of the technical effects of the first aspect and its corresponding possible implementations, and will not be repeated here. Attached Figure Description
[0038] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:
[0039] Figure 1 This is a flowchart illustrating a method for predicting traffic congestion according to an embodiment of the present invention.
[0040] Figure 2 This is a schematic diagram of the structure of a traffic congestion prediction system according to an embodiment of the present invention;
[0041] Figure 3 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation
[0042] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
[0043] like Figure 1 As shown, a traffic congestion prediction method according to an embodiment of the present invention includes the following steps:
[0044] S1. Determine the stopping area for each motor vehicle on the preset road segment, specifically:
[0045] Obtain and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment.
[0046] Here, the spatiotemporal trajectory point of the motor vehicle is defined as: p = (lo, la, t), where lo represents the longitude of the motor vehicle, la represents the latitude of the motor vehicle, and t represents the time. Then, at time t... m Time to t n The set of spatiotemporal trajectory points P of the i-th motor vehicle on the preset road segment between time points. i Specifically, it can be expressed as follows: in, Indicates that the i-th motor vehicle is in t m The spatiotemporal trajectory point at a given moment. Indicates the position of the i-th motor vehicle in t m+1 The spatiotemporal trajectory point P at time [time]. n Indicates that the i-th motor vehicle is in t n The spatiotemporal trajectory point at time t can be used to determine the time. m Time to t n The time intervals are divided into multiple time periods, thus determining time m+1, time m+2, etc. The total number of motor vehicles on the preset road segment is K, where i and K are positive integers and i≤K.
[0047] Clustering algorithms are used to determine the center point of the spatiotemporal trajectory point set for each motor vehicle. The stopping area of the i-th motor vehicle can be represented by a center point C. i The activity radius is r i The activity area, C i Let r be the center point of the i-th motor vehicle. i Let P represent the activity radius of the i-th motor vehicle. i The maximum time interval is denoted as the individual's dwell time TL. i =(t m′ , t n′ Let 'e' be the vehicle ID (e.g., license plate number) of an individual stopping point. Then, the stopping area S of the i-th vehicle... i Expressed as:
[0048] S i =(C i r i , t m′ , t n′ ,e}
[0049] Among them, t m′ and t n′ All located at t m Time to t n In a short period of time.
[0050] S2. Based on the parking area of each motor vehicle, cluster the activity types of each motor vehicle, specifically:
[0051] A graph model clustering scheme is adopted, and based on the stopping area of each vehicle, the activity type of each vehicle is clustered. Specifically:
[0052] Let the relationship between samples S be modeled as a graph S = (V, E), where V is a point S i The set of points S, where E represents each point S. i By dividing the graph into disjoint subgraphs (G1, G2, ..., Gr) based on the relationships between them, we can obtain the clustering results of motor vehicle activity types, i.e., minimize the loss function.
[0053] Cut(G1,G2,…,Gr)=Σi∈G1,j∈G2,…k∈Gr wij…k
[0054] Where r represents the category, and w represents the number of sample points S. i The similarity between them.
[0055] S3. Based on the activity clustering results of each motor vehicle, obtain the semantic sequence of the activity clusters for each motor vehicle;
[0056] Semantic information is extracted based on the activity clustering results of individual motor vehicles. Semantic labels are assigned to the location, time, and motor vehicle distribution of r activity types, as follows:
[0057] SP r =(SC, SD, ST, SU, SE)
[0058] Wherein, SC represents the activity type of the individual motor vehicle, SD represents the regional semantic tag (public building, transportation hub, etc.) with the highest regional distribution ratio in the activity type of the individual motor vehicle, ST represents the duration segment with the highest duration distribution ratio in the activity type of the individual motor vehicle, ST represents the duration segment with the highest distribution ratio in the activity type of the individual motor vehicle, and SE represents the number of individual motor vehicles with the highest distribution ratio.
[0059] S4. Based on the preset time window, perform short-time framing on the semantic sequence of each motor vehicle's activity cluster to obtain the short-time individual motor vehicle activity type semantic sequence for each motor vehicle.
[0060] The semantic sequence of motor vehicle activity clustering is processed into n equal-length window sequences by framing, which are called short-time individual motor vehicle activity type semantic sequences, defined as follows:
[0061] TD i =(SP1, SP2, ..., SP) y}
[0062] Where y represents the number of times individual motor vehicle activities are included within the window.
[0063] S5. Cluster the short-term individual motor vehicle activity type semantic sequences for each motor vehicle;
[0064] The semantic sequence TD of the above short-term individual motor vehicle activity types i Clustering is performed, assuming a short-term individual motor vehicle activity type semantic sequence TD. i If we obtain g categories through clustering, we can sort them according to the quantity in each category. The sorting order by quantity is defined as 1, 2, 3, ..., g, and denoted as categories M1, M2, M3, ..., Mg.
[0065] S6. Based on the clustering results of the short-term individual motor vehicle activity type semantic sequence for each motor vehicle, traffic congestion is predicted for the preset road segment.
[0066] Classes M1, M2, M3, ..., Mg that exceed a set traffic congestion threshold are considered likely to experience congestion, and thus a prediction is made. Conversely, classes that do not exceed a certain threshold are considered not to experience congestion.
[0067] Optionally, the above technical solution also includes:
[0068] S7. When the preset traffic congestion result for a preset road segment is congested, issue a reminder.
[0069] The beneficial effects of the traffic congestion prediction method of the present invention are as follows:
[0070] 1) This invention breaks away from traditional approaches such as unsupervised identification methods that judge congestion behavior based on deviation from normal patterns and supervised identification methods that judge congestion behavior based on similarity to known congestion behavior patterns. It predicts traffic congestion based on vehicle behavior semantic analysis and congestion risk warning, solving the challenge of analyzing and warning of sporadic congestion characterized by "new and unknown" events. This invention addresses the traditional problem that existing technologies cannot accurately determine sporadic congestion.
[0071] 2) By monitoring the locations where traffic congestion is predicted to occur, traffic congestion prediction knowledge and data samples can be updated in real time, further improving the accuracy of traffic congestion prediction.
[0072] 3) It can intelligently push alarm information, prediction information, statistical data and other information through the network.
[0073] In the above embodiments, although the steps are numbered S1, S2, etc., they are only specific embodiments given by the present invention. Those skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, which is also within the protection scope of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.
[0074] like Figure 2 As shown, a traffic congestion prediction system 200 according to an embodiment of the present invention includes a determination module 201, a first clustering module 202, a semantic sequence acquisition module 203, a frame segmentation module 204, a second clustering module 205, and a congestion prediction module 206.
[0075] The determining module 201 is used to: determine the stopping area for each motor vehicle on a preset road segment;
[0076] The first clustering module 202 is used to: cluster each motor vehicle by activity type based on the parking area of each motor vehicle;
[0077] The semantic sequence acquisition module 203 is used to: obtain the semantic sequence of the activity cluster of each motor vehicle based on the activity clustering results of each motor vehicle;
[0078] The framing module 204 is used to: perform short-time framing on the semantic sequence of the activity cluster of each motor vehicle according to a preset time window, so as to obtain a short-time individual motor vehicle activity type semantic sequence for each motor vehicle;
[0079] The second clustering module 205 is used to: cluster the short-term individual motor vehicle activity type semantic sequence for each motor vehicle;
[0080] The congestion prediction module 206 is used to predict traffic congestion on preset road segments based on the clustering results of the short-term individual motor vehicle activity type semantic sequence of each motor vehicle.
[0081] Optionally, in the above technical solution, the determining module 201 is specifically used for:
[0082] Obtain and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment.
[0083] Optionally, in the above technical solution, the first clustering module 202 is specifically used for:
[0084] A graph model clustering scheme is adopted, and each motor vehicle is clustered by activity type based on its parking area.
[0085] Optionally, the above technical solution also includes a reminder module, which is used to issue a reminder when the preset traffic congestion result of the preset road segment is congestion.
[0086] It should be noted that the beneficial effects of the traffic congestion prediction system 200 provided in the above embodiments are the same as those of the traffic congestion prediction method described above, and will not be repeated here. Furthermore, the system provided in the above embodiments is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to the actual situation to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, and will not be repeated here.
[0087] like Figure 3 As shown, an embodiment of the present invention provides a computer device 300, which includes a processor 320 coupled to a memory 310. The memory 310 stores at least one computer program 330, which is loaded and executed by the processor 320 to enable the computer device 300 to implement any of the above-mentioned methods for predicting traffic congestion. Specifically:
[0088] The computer device 300 can vary considerably due to differences in configuration or performance. It may include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, which is loaded and executed by the one or more processors 320 to enable the computer device 300 to implement any of the traffic congestion prediction methods provided in the above embodiments. Of course, the computer device 300 may also have wired or wireless network interfaces, a keyboard, and input / output interfaces for input and output. The computer device 300 may also include other components for implementing device functions, which will not be elaborated here.
[0089] An embodiment of the present invention provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to enable a computer to implement any of the above-described methods for predicting traffic congestion.
[0090] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.
[0091] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform any of the above-described methods for predicting traffic congestion.
[0092] It should be noted that the terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and represent a limitation on a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of this application described herein can be implemented in an order other than that shown or described.
[0093] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.
[0094] Any combination of one or more computer-readable media can be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0095] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.
Claims
1. A method for predicting traffic congestion, characterized in that, include: Obtain and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment; The spatiotemporal trajectory points of motor vehicles are defined as follows: , Indicates the longitude of the motor vehicle. Indicates the latitude of the motor vehicle. To indicate the time, then in Time to Between moments, the first on the preset road segment Set of spatiotemporal trajectory points of a motor vehicle Specifically, it can be expressed as follows: ,in, Indicates the first A motor vehicle The spatiotemporal trajectory point at a given moment. Indicates the first Individual motor vehicles The spatiotemporal trajectory point at a given moment. Indicates the first A motor vehicle The spatiotemporal trajectory point at a given moment will Time to The time intervals are divided into multiple time periods, and the total number of motor vehicles on the preset road segment is: K , and K It is a positive integer, and ; Clustering algorithms are used to determine the center point of the spatiotemporal trajectory point set for each motor vehicle, and the 1st... The parking area for each motor vehicle is represented by the center point as... Activity radius is The activity area For the first The center point of each motor vehicle Indicates the first The activity radius of a motor vehicle, taken The longest time interval is denoted as the individual's stay time. If the license plate number of a vehicle at an individual stop is denoted as 𝑒, then the stopping area of the 𝑖th vehicle is... Expressed as: ,in, and All located in Time to Between moments; A graph model clustering scheme is adopted, and each motor vehicle is clustered by activity type based on its parking area; Let the relationship between samples S be modeled as a graph. ,in For point The set, Indicate each point The relationships between the graphs divide the graph into disjoint subgraphs. This yields the clustering results for the activity types of motor vehicles; Based on the activity clustering results of each motor vehicle, a semantic sequence of the activity clusters for each motor vehicle is obtained; Semantic information is extracted based on the activity clustering results of individual motor vehicles. Semantic labels are assigned to the location, time, and motor vehicle distribution of r activity types, as follows: ,in, This indicates the type of activity of the individual's motor vehicle. The semantic tag representing the region with the highest regional distribution proportion among the activity types of this individual's motor vehicles. This indicates the duration segment with the highest proportion of duration distribution among the activity types of this individual motor vehicle. This indicates the duration period during which the activity type of the individual's motor vehicle has the highest distribution proportion. This represents the segment of individual motor vehicles with the highest distribution ratio; Based on a preset time window, the semantic sequence of each motor vehicle's activity cluster is divided into short-time frames to obtain the short-time individual motor vehicle activity type semantic sequence for each motor vehicle. The semantic sequence of motor vehicle activity clustering is processed into n equal-length window sequences by framing, which are called short-time individual motor vehicle activity type semantic sequences, defined as follows: Where, 𝑦 is the number of times individual motor vehicle activities are included within the window; Cluster the short-term individual vehicle activity type semantic sequences for each vehicle; Semantic sequence of short-term individual motor vehicle activity types Clustering is performed, assuming a short-term semantic sequence of individual motor vehicle activity types. Obtained through clustering If there are multiple categories, then sort them according to the quantity in each category, and the sorting by quantity is defined as follows: , denoted as category ; Based on the clustering results of the short-term individual motor vehicle activity type semantic sequence for each motor vehicle, traffic congestion is predicted for the preset road segment; Category Traffic congestion exceeding a set threshold is considered congested, and a prediction is made accordingly; otherwise, it is considered not to be congested.
2. The method for predicting traffic congestion according to claim 1, characterized in that, Also includes: When the preset traffic congestion result for the preset road segment is congested, an alert will be issued.
3. A system for predicting traffic congestion, characterized in that, It includes a determination module, a first clustering module, a semantic sequence acquisition module, a framing module, a second clustering module, and a congestion prediction module; The determining module is used to: acquire and determine the stopping area of each motor vehicle based on the set of spatiotemporal trajectory points of each motor vehicle on the preset road segment; The spatiotemporal trajectory points of motor vehicles are defined as follows: , Indicates the longitude of the motor vehicle. Indicates the latitude of the motor vehicle. To indicate the time, then in Time to Between moments, the first on the preset road segment Set of spatiotemporal trajectory points of a motor vehicle Specifically, it can be expressed as follows: ,in, Indicates the first A motor vehicle The spatiotemporal trajectory point at a given moment. Indicates the first Individual motor vehicles The spatiotemporal trajectory point at a given moment. Indicates the first A motor vehicle The spatiotemporal trajectory point at a given moment will Time to The time intervals are divided into multiple time periods, and the total number of motor vehicles on the preset road segment is: K , and K It is a positive integer, and ; Clustering algorithms are used to determine the center point of the spatiotemporal trajectory point set for each motor vehicle, and the 1st... The parking area for each motor vehicle is represented by the center point as... Activity radius is The activity area For the first The center point of each motor vehicle Indicates the first The activity radius of a motor vehicle, taken The longest time interval is denoted as the individual's stay time. If the license plate number of a vehicle at an individual stop is denoted as 𝑒, then the stopping area of the 𝑖th vehicle is... Expressed as: ,in, and All located in Time to Between moments; The first clustering module is used to: adopt a graph model clustering scheme and cluster each motor vehicle by activity type based on the stopping area of each motor vehicle; Let the relationship between samples S be modeled as a graph. ,in For point The set, Indicate each point The relationships between the graphs divide the graph into disjoint subgraphs. This yields the clustering results for the activity types of motor vehicles; The semantic sequence acquisition module is used to: obtain the semantic sequence of each motor vehicle's activity cluster based on the activity clustering results of each motor vehicle; Semantic information is extracted based on the activity clustering results of individual motor vehicles. Semantic labels are assigned to the location, time, and motor vehicle distribution of r activity types, as follows: ,in, This indicates the type of activity of the individual's motor vehicle. The semantic tag representing the region with the highest regional distribution proportion among the activity types of this individual's motor vehicles. This indicates the duration segment with the highest proportion of duration distribution among the activity types of this individual motor vehicle. This indicates the duration period during which the activity type of the individual's motor vehicle has the highest distribution proportion. This represents the segment of individual motor vehicles with the highest distribution ratio; The framing module is used to: perform short-time framing on the semantic sequence of the activity cluster of each motor vehicle according to a preset time window, so as to obtain a short-time individual motor vehicle activity type semantic sequence for each motor vehicle; The semantic sequence of motor vehicle activity clustering is processed into n equal-length window sequences by framing, which are called short-time individual motor vehicle activity type semantic sequences, defined as follows: Where, 𝑦 is the number of times individual motor vehicle activities are included within the window; The second clustering module is used to: cluster the short-term individual motor vehicle activity type semantic sequences of each motor vehicle; Semantic sequence of short-term individual motor vehicle activity types Clustering is performed, assuming a short-term semantic sequence of individual motor vehicle activity types. Obtained through clustering If there are multiple categories, then sort them according to the quantity in each category, and the sorting by quantity is defined as follows: , denoted as category ; The congestion prediction module is used to: predict traffic congestion on the preset road segment based on the clustering results of the short-term individual motor vehicle activity type semantic sequence of each motor vehicle; Category Traffic congestion exceeding a set threshold is considered congested, and a prediction is made accordingly; otherwise, it is considered not to be congested.
4. The traffic congestion prediction system according to claim 3, characterized in that, It also includes a reminder module, which is used to issue a reminder when the preset traffic congestion result of the preset road segment is congestion.
5. A computer device, characterized in that, The computer device includes a processor coupled to a memory storing at least one computer program, which is loaded and executed by the processor to enable the computer device to implement a method for predicting traffic congestion as described in any one of claims 1 to 2.
6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to enable the computer to implement a method for predicting traffic congestion as described in any one of claims 1 to 2.