Highway maintenance management method and system

Abstract

The invention relates to an expressway maintenance management method and system, and relates to the field of road maintenance, and the method comprises the steps: obtaining humidity change diagrams corresponding to a plurality of positions in a tunnel and vibration change diagrams corresponding to the plurality of positions, the humidity change diagrams and the vibration change diagrams are humidity change diagrams and vibration change diagrams from the last maintenance time to the current time, determining an abnormal risk value of each position based on the humidity change diagrams and the vibration change diagrams, and obtaining historical monitoring videos in the tunnel; the historical monitoring video is a monitoring video from the last maintenance time to the current time, determining the severity of an accident occurring in the tunnel and the position of the accident based on the historical monitoring video, judging whether a road section needing to be maintained exists or not based on the abnormal risk value and the severity of the accident, and if the road section needing to be maintained exists, stopping maintenance. And if yes, outputting the road section to be maintained. The method and the device have the effect of finding the position where the tunnel is about to be damaged or damaged in time.

Description

Technical Field

[0001] The present application relates to the field of road maintenance, and in particular to a highway maintenance management method and system. Background Art

[0002] With the development of the transportation industry and the improvement of the national highway network, more and more highways need to pass through tunnels. Tunnels are usually built on mountains, so the environment inside the tunnel is dark and humid, which is prone to traffic accidents. Traffic accidents may cause damage to the road surface or other facilities in the highway tunnel, and the tunnel may also be affected by geological movements, causing damage to the road surface or other facilities. Therefore, the maintenance of highway tunnel sections has become an important link.

[0003] Due to the dark environment of the tunnel, currently only regular manual inspection and maintenance can be carried out in the tunnel. Often, damage to the road surface or damage to facilities can be discovered and maintained only after it occurs. Therefore, the timeliness is not high, and it is impossible to discover the location of impending damage or destruction in the tunnel and perform repairs in advance. Summary of the invention

[0004] In order to be able to more promptly discover locations in a tunnel where damage or destruction is about to occur, the present application provides a highway maintenance management method and system.

[0005] In the first aspect, the present application provides a highway maintenance management method, which adopts the following technical solution: A highway maintenance management method, comprising: Obtain humidity change graphs corresponding to a plurality of positions in the tunnel and vibration change graphs corresponding to the plurality of positions, wherein the humidity change graphs and the vibration change graphs are humidity change graphs and vibration change graphs from the last maintenance to the current time; Determine the abnormal risk value of each position based on the humidity change graph and the vibration change graph; Obtaining historical surveillance videos in the tunnel, where the historical surveillance videos are surveillance videos from the last maintenance to the current time; Determining the severity of the accident that occurred in the tunnel and the accident location of the accident based on the historical monitoring video; Based on the abnormal risk value and the severity of the accident, it is determined whether there is a road section that needs maintenance. If so, the road section that needs maintenance is output.

[0006] By adopting the above technical solution, the humidity change map and the vibration change map are obtained to facilitate the subsequent analysis of the possibility of abnormalities and damages caused by humidity and vibration to the road surface and facilities in the tunnel. Humidity changes and vibration conditions are key factors affecting whether abnormal risks occur. Therefore, the abnormal risk value of each location can be accurately determined based on the humidity change map and the vibration change map. Traffic accidents in the tunnel may also have an impact on the road surface and facilities. Therefore, historical monitoring videos are obtained. Since the historical monitoring videos record the specific circumstances when the accident occurred, the severity of the accident and the location of the accident can be determined based on the historical monitoring videos. Finally, the abnormal risk value and the severity of the accident are combined to determine whether there is a road surface that needs maintenance. If so, it means that the road surface that needs maintenance may be about to be damaged and abnormal, so the section that needs maintenance is output, so that the staff can promptly know the sections and locations where abnormalities or damage are more likely to occur, which is convenient for timely preventive maintenance.

[0007] In another possible implementation, determining the abnormal risk value of each position based on the humidity change graph and the vibration change graph includes: Determine the humidity variance and humidity average value at each location based on the humidity change graph; Determine a first data segment whose humidity value exceeds a preset humidity threshold, and determine a first proportion of the first data segment in the humidity change graph; Determine a first abnormality score for each location based on the humidity variance, the humidity average, and the first proportion; Determine a second data segment where vibration exists at each position based on the vibration variation graph; Determining the duration, amplitude mean, and amplitude variance of each second data segment; Determine a second anomaly score for each second data segment based on the duration, the amplitude mean, and the amplitude variance; An abnormal risk value for each location is determined based on the first abnormality score and the second abnormality score.

[0008] In another possible implementation manner, determining the abnormal risk value of each position based on the first abnormality score and the second abnormality score includes: determining an average of the second anomaly scores based on the second anomaly scores of each second data segment; determining the number of the second data segments, and determining a third anomaly score for each position with respect to the vibration variation map based on the number and an average value of the second anomaly scores; An abnormal risk value for each location is determined based on the first abnormality score and the third abnormality score.

[0009] In another possible implementation, determining the severity of the accident that occurred in the tunnel based on the historical surveillance video includes: Obtain the time point of the accident, and segment the historical surveillance video based on the time point and the preset duration to obtain sub-videos corresponding to each accident; Analyzing the sub-videos to determine the speed of each vehicle in the accident before the collision, and the collision position on the vehicle; determining a relative speed based on the speed; A score representing the severity of each accident is determined based on the relative speed and the impact position.

[0010] In another possible implementation, judging whether there is a road section requiring maintenance based on the abnormal risk value and the severity of the accident includes: Numbering each location and determining the sum of abnormal risk values ​​of each number interval, wherein the number interval represents a road section between two adjacent locations; Determine the number interval where the accident location is located, and calculate the total score of the severity score and the sum of the abnormal risk values ​​of the locations in the corresponding number interval; Determine whether the sum of the abnormal risk values ​​or the total score of any numbered interval reaches a preset score threshold. If so, determine that the road section of any numbered interval is a road section that needs maintenance.

[0011] In another possible implementation, the method further includes: Input the historical monitoring video into the trained network model to perform traffic flow analysis, and determine the time period when the traffic flow is less than a preset traffic flow threshold; The time period is output.

[0012] In another possible implementation, the method further includes: The corresponding lighting lamps in the road section requiring maintenance are controlled to light up according to preset colors.

[0013] In the second aspect, the present application provides a highway maintenance management system, which adopts the following technical solution: A highway maintenance management system, comprising: A first acquisition module is used to acquire humidity change graphs corresponding to a plurality of positions in the tunnel and vibration change graphs corresponding to the plurality of positions, wherein the humidity change graphs and the vibration change graphs are humidity change graphs and vibration change graphs from the last maintenance to the current time; A first determination module, configured to determine an abnormal risk value of each position based on the humidity change graph and the vibration change graph; The second acquisition module is used to acquire the historical monitoring video in the tunnel, where the historical monitoring video is the monitoring video between the last maintenance and the current time; A second determination module is used to determine the severity of the accident that occurred in the tunnel and the accident location of the accident based on the historical monitoring video; The road section output module is used to determine whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident, and if so, output the road section that needs maintenance.

[0014] By adopting the above technical solution, the first acquisition module obtains the humidity change map and the vibration change map to facilitate the subsequent analysis of the possibility of abnormalities and damages caused by humidity and vibration to the road surface and facilities in the tunnel. Humidity changes and vibration conditions are key factors affecting whether abnormal risks occur. Therefore, the first determination module can accurately determine the abnormal risk value of each location based on the humidity change map and the vibration change map. Traffic accidents in the tunnel may also have an impact on the road surface and facilities. Therefore, the second acquisition module obtains historical monitoring videos. Since the historical monitoring videos record the specific circumstances when the accident occurred, the second determination module can determine the severity of the accident and the location of the accident based on the historical monitoring videos. Finally, the section output module comprehensively determines whether there is a road surface that needs maintenance based on the abnormal risk value and the severity of the accident. If so, it means that the road surface that needs maintenance may be about to be damaged and abnormal. Therefore, the section output module outputs the section that needs maintenance, so that the staff can promptly know the sections and locations where abnormalities or damage are more likely to occur, which is convenient for timely preventive maintenance.

[0015] In another possible implementation, when the first determination module determines the abnormal risk value of each position based on the humidity change graph and the vibration change graph, it is specifically used to: Determine the humidity variance and humidity average value at each location based on the humidity change graph; Determine a first data segment whose humidity value exceeds a preset humidity threshold, and determine a first proportion of the first data segment in the humidity change graph; Determine a first abnormality score for each location based on the humidity variance, the humidity average, and the first proportion; Determine a second data segment where vibration exists at each position based on the vibration variation graph; Determining the duration, amplitude mean, and amplitude variance of each second data segment; Determine a second anomaly score for each second data segment based on the duration, the amplitude mean, and the amplitude variance; An abnormal risk value for each location is determined based on the first abnormality score and the second abnormality score.

[0016] In another possible implementation, when the first determination module determines the abnormal risk value of each position based on the first abnormal score and the second abnormal score, it is specifically configured to: determining an average of the second anomaly scores based on the second anomaly scores of each second data segment; determining the number of the second data segments, and determining a third anomaly score for each position with respect to the vibration variation map based on the number and an average value of the second anomaly scores; An abnormal risk value for each location is determined based on the first abnormality score and the third abnormality score.

[0017] In another possible implementation, when the second determination module determines the severity of the accident that occurred in the tunnel based on the historical monitoring video, it is specifically configured to: Obtain the time point of the accident, and segment the historical surveillance video based on the time point and the preset duration to obtain sub-videos corresponding to each accident; Analyzing the sub-videos to determine the speed of each vehicle in the accident before the collision, and the collision position on the vehicle; determining a relative speed based on the speed; A score representing the severity of each accident is determined based on the relative speed and the impact position.

[0018] In another possible implementation, when the road section output module determines whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident, it is specifically used to: Numbering each location and determining the sum of abnormal risk values ​​of each number interval, wherein the number interval represents a road section between two adjacent locations; Determine the number interval where the accident location is located, and calculate the total score of the severity score and the sum of the abnormal risk values ​​of the locations in the corresponding number interval; Determine whether the sum of the abnormal risk values ​​or the total score of any numbered interval reaches a preset score threshold. If so, determine that the road section of any numbered interval is a road section that needs maintenance.

[0019] In another possible implementation, the system further includes: An analysis module, used for inputting the historical monitoring video into the trained network model to perform traffic flow analysis and determine a time period when the traffic flow is less than a preset traffic flow threshold; The time period output module is used to output the time period.

[0020] In another possible implementation, the system further includes: The control module is used to control the corresponding lighting lamps in the road section that needs maintenance to light up according to preset colors.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute a highway maintenance management method shown in any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, when the computer program is executed in a computer, enables the computer to execute a highway maintenance management method as described in any one of the first aspects.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: Obtaining humidity change graphs and vibration change graphs facilitates subsequent analysis of the possibility of abnormalities and damage caused by humidity and vibration to the road surface and facilities in the tunnel. Humidity changes and vibration conditions are key factors affecting whether abnormal risks occur. Therefore, the abnormal risk value of each location can be accurately determined based on the humidity change graph and vibration change graph. Traffic accidents in tunnels may also have an impact on the road surface and facilities. Therefore, historical monitoring videos are obtained. Since the historical monitoring videos record the specific circumstances when the accident occurred, the severity of the accident and the location of the accident can be determined based on the historical monitoring videos. Finally, the abnormal risk value and the severity of the accident are combined to determine whether there is a road surface that needs maintenance. If so, it means that the road surface that needs maintenance may be about to be damaged and abnormal, so the road section that needs maintenance is output, so that the staff can promptly know the sections and locations where abnormalities or damage are more likely to occur, which facilitates timely preventive maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a highway maintenance management method according to an embodiment of the present application.

[0025] Figure 2 It is a structural schematic diagram of a highway maintenance management system according to an embodiment of the present application.

[0026] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] The present application is further described in detail below in conjunction with the accompanying drawings.

[0028] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0030] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0031] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0032] The embodiment of the present application provides a highway maintenance management method, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited to this. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, and the embodiment of the present application does not limit this. Figure 1 As shown, the method includes step S101, step S102, step S103, step S104 and step S105, wherein: S101, obtaining humidity change graphs corresponding to a plurality of positions in the tunnel and vibration change graphs corresponding to a plurality of positions.

[0033] Among them, the humidity change graph and the vibration change graph are both humidity change graphs and vibration change graphs from the last maintenance to the current time.

[0034] For the embodiment of the present application, the staff can install humidity sensors at multiple locations in the tunnel in advance, and the humidity sensors are connected to the cloud server through wires. Multiple humidity sensors can be set at equal intervals. The humidity sensors collect humidity values ​​at multiple locations in the tunnel and send them to the cloud server, and the cloud server generates a humidity change graph of humidity values ​​changing over time. The electronic device is connected to the cloud server in communication, so the electronic device can obtain the humidity change graph. Excessive humidity in the tunnel may cause some facilities to rust or some electronic devices to age and damage, and affect the road surface.

[0035] Similarly, the staff can install vibration sensors at multiple locations in the tunnel in advance, and the vibration sensors are connected to the cloud server through wires. Multiple vibration sensors can be set at equal intervals, and the vibration sensors can be set at the same location as the humidity sensor. The vibration sensor collects vibration values ​​at multiple locations in the tunnel and sends them to the cloud server, which generates a vibration change graph showing the vibration values ​​changing over time. The electronic device is connected to the cloud server in communication, so the electronic device can obtain the vibration change graph. Drastic vibration changes may be caused by resonance caused by large vehicles or vibrations caused by geological movements, etc. These vibrations may cause cracks in the road surface in the tunnel or damage other facilities.

[0036] The humidity change graph and vibration change graph are both after the last maintenance, so it can be considered that there is no abnormality and no risk in the entire tunnel after the last maintenance.

[0037] S102: Determine the abnormal risk value of each position based on the humidity change graph and the vibration change graph.

[0038] For the embodiments of the present application, since humidity changes and vibration changes are factors that affect whether abnormal risks occur in the tunnel, and the humidity change graph and the vibration change graph both record the specific changes in humidity and vibration, the electronic device can comprehensively determine the abnormal risk value of each location in the tunnel based on the humidity change graph and the vibration change graph, and characterize the risk and possibility of abnormalities occurring at each location through the abnormal risk value.

[0039] S103, obtaining historical surveillance videos in the tunnel.

[0040] Among them, the historical monitoring video is the monitoring video between the last maintenance and the current time.

[0041] For the embodiment of the present application, surveillance cameras are installed at different locations in the tunnel to collect traffic conditions in the tunnel. The surveillance cameras are connected to electronic devices through wires, so that the electronic devices obtain historical surveillance videos from the last maintenance to the current time based on the time point of the last maintenance.

[0042] S104, determining the severity of the accident that occurred in the tunnel and the accident location based on the historical monitoring video.

[0043] For the embodiments of the present application, the impact caused by a car accident in the tunnel may also cause damage to the road surface or other facilities in the tunnel. Therefore, the electronic device determines the accidents that have occurred after the last maintenance and the severity of each accident based on the historical monitoring video. Since the position of the monitoring camera is determined, the accident location of each accident can be determined based on the position of the monitoring camera. Determining the accident location can determine the location where the accident may cause abnormalities to the road surface or facilities in the tunnel. Different severity levels will cause different degrees of damage to the road surface and other facilities in the tunnel. The historical monitoring video records the specific circumstances of each accident, so the electronic device can determine the severity of each accident based on the historical monitoring video.

[0044] S105: Based on the abnormal risk value and the severity of the accident, determine whether there is a road section that needs maintenance. If so, output the road section that needs maintenance.

[0045] For the embodiment of the present application, the abnormal risk value of each location and the severity of the accident are key factors in judging whether each location in the tunnel needs maintenance. Therefore, the electronic device can more accurately and timely determine whether there is a road section that needs maintenance in combination with the abnormal risk value and the severity. After determining the road section that needs maintenance, the electronic device sends the location of the road section that needs maintenance to the terminal device of the staff. Therefore, the staff can know the road section that needs maintenance more promptly and perform preventive early maintenance more promptly, which is more timely.

[0046] In a possible implementation of the embodiment of the present application, in step S102, the abnormal risk value of each position is determined based on the humidity change graph and the vibration change graph, specifically including step S1021 (not shown in the figure), step S1022 (not shown in the figure), step S1023 (not shown in the figure), step S1024 (not shown in the figure), step S1025 (not shown in the figure), step S1026 (not shown in the figure) and step S1027 (not shown in the figure), wherein: S1021, determining the humidity variance and humidity average value of each location based on the humidity change graph.

[0047] For the embodiment of the present application, the electronic device determines the data of each humidity value from the humidity change diagram of each location, and then calculates the humidity variance and humidity average value using the variance calculation formula and the average value calculation formula. The humidity variance represents the severity of the humidity change. The greater the severity of the humidity change, the higher the possibility of abnormality or damage to the road surface or facilities in an environment with drastic humidity changes. Therefore, the greater the variance, the greater the impact on the abnormal risk value. The humidity average value represents the overall humidity level of each location from the last maintenance to the present. The greater the humidity, the greater the impact or damage risk on some facilities, such as electronic devices. Therefore, the greater the humidity average value, the greater the impact on the abnormal risk value.

[0048] S1022, determining a first data segment whose humidity value exceeds a preset humidity threshold, and determining a first proportion of the first data segment in the humidity change graph.

[0049] For the embodiment of the present application, the preset humidity threshold serves as a dividing point for whether the humidity is too high. Exceeding the preset humidity threshold indicates that the risk of damage to some facilities, such as electronic devices, is too high. Therefore, the electronic device determines from the humidity change graph the first data segment in which the humidity value exceeds the preset humidity threshold. The longer the time of the first data segment, the greater the risk of damage to the electronic devices in the tunnel. Therefore, the electronic device determines the proportion of the sum of the time of all the first data segments in the total time length in the humidity change graph, that is, the first proportion.

[0050] S1023: Determine a first abnormality score for each location based on the humidity variance, the humidity average, and the first proportion.

[0051] For the embodiments of the present application, in summary, humidity variance, humidity average and first proportion are all key factors affecting the possibility of abnormalities at each location in terms of humidity, and the degree of influence is different. Therefore, the staff sets different coefficients for the humidity variance, humidity average and first proportion. After the electronic device determines the humidity variance, humidity average and first proportion, it calls the corresponding coefficients for weighted calculation to obtain the first abnormality score for each location. By calculating the first abnormality score and using the score to characterize the possibility of abnormalities caused by humidity at each location more accurately.

[0052] S1024, determining a second data segment where vibration exists at each position based on the vibration variation graph.

[0053] For the embodiment of the present application, when vibration occurs, fluctuation data will appear on the vibration change graph, so the electronic device determines from the vibration change graph that a second data segment of vibration data exists at each position.

[0054] S1025, determining the duration, amplitude average, and amplitude variance of each second data segment.

[0055] For the embodiment of the present application, the longer the second data segment lasts, the greater the possibility of causing damage to the road surface, guardrails, bolts and other facilities in the tunnel, so the electronic device determines the duration of each second data segment. The electronic device calculates the amplitude average value of the vibration data in the second data segment using the average value calculation formula. The larger the amplitude average value, the greater the energy carried by the vibration, and the greater the possibility of causing damage to facilities such as the road surface. The electronic device calculates the amplitude variance of the vibration data in each second data segment using the variance calculation formula. The amplitude variance represents the severity of the amplitude. The larger the variance, the greater the severity, and the greater the possibility of causing damage.

[0056] S1026: Determine a second abnormality score for each second data segment based on the duration, the amplitude average, and the amplitude variance.

[0057] For the embodiments of the present application, in summary, the duration, the average amplitude and the amplitude variance are all key factors in terms of vibration. The vibration generated by each second data segment affects the possibility of abnormalities at each position, and the degree of influence is different. Therefore, the staff sets different coefficients for the duration, the average amplitude and the amplitude variance. After the electronic device determines the duration, the average amplitude and the amplitude variance, it calls the corresponding coefficients for weighted calculation to obtain the second abnormality score for each second data segment. By calculating the second abnormality score and using the score to characterize the possibility of abnormalities on the road surface or facilities in the vibration situation corresponding to each second data segment, it is more accurate.

[0058] S1027: Determine an abnormal risk value for each location based on the first abnormal score and the second abnormal score.

[0059] For the embodiment of the present application, after the electronic device determines the first abnormality score and the second abnormality score, it is more accurate to comprehensively determine the abnormal risk value of abnormal damage at each location by combining the first abnormality score for humidity and the second abnormality score for vibration.

[0060] In a possible implementation of the embodiment of the present application, in step S1027, the abnormal risk value of each position is determined based on the first abnormal score and the second abnormal score, specifically including step S1 (not shown in the figure), step S2 (not shown in the figure) and step S3 (not shown in the figure), wherein: S1, determining an average value of the second anomaly score based on the second anomaly score of each second data segment.

[0061] For the embodiment of the present application, the vibration change graph at each position corresponds to one or more second data segments, so the electronic device uses the average value calculation formula to calculate the average value of the second abnormality scores of all the second data segments, and uses the average value to characterize the possibility of the overall vibration in the vibration change graph at each position causing abnormality or damage.

[0062] S2, determining the number of second data segments, and determining a third abnormality score for each position with respect to the vibration variation graph based on the number and an average value of the second abnormality scores.

[0063] For the embodiment of the present application, a greater number of second data segments at each position indicates a greater number of vibrations that occur, and thus the electronic device counts the second data segments at each position to obtain the number of second data segments.

[0064] In summary, the average value of the second abnormality score and the number of the second data segments are both key factors in determining the likelihood of vibration causing abnormality or damage to each location, and the degree of impact is different. Therefore, the staff sets different coefficients for the average value of the second abnormality score and the number of the second data segments. After the electronic device determines the average value of the second abnormality score and the number of the second data segments, it calls the corresponding coefficients for weighted calculation to obtain the third abnormality score for each location regarding the vibration change graph.

[0065] S3: Determine an abnormal risk value for each location based on the first abnormal score and the third abnormal score.

[0066] For the embodiment of the present application, the humidity and vibration aspects add up to affect the possibility of abnormality at each location, so the electronic device can sum the first abnormality score and the third abnormality score to obtain the abnormality risk value of each location. It is more accurate to analyze and comprehensively determine the abnormality risk value of each location through humidity and vibration.

[0067] In a possible implementation of the embodiment of the present application, the severity of the accident that occurred in the tunnel is determined based on the historical monitoring video in step S104, including step S1041 (not shown in the figure), step S1042 (not shown in the figure), step S1043 (not shown in the figure) and step S1044 (not shown in the figure), wherein: S1041, obtaining the time point when the accident occurred, and segmenting the historical monitoring video based on the time point and the preset duration to obtain sub-videos corresponding to each accident.

[0068] For the embodiment of the present application, after each accident occurs, the staff can mark the time point of the accident on the collected surveillance video, so that the electronic device can obtain the time point of each accident. The preset duration can be 10 seconds (s), 20 seconds, etc. If the preset duration is 10 seconds, the electronic device will segment the historical surveillance video based on the time point of the accident and the preset duration of 10 seconds to obtain a sub-video including 5 seconds before and 5 seconds after the time point of the accident. Sub-videos are used to facilitate subsequent analysis, thereby reducing the amount of data to be analyzed.

[0069] S1042, analyzing the sub-videos to determine the speed of each vehicle before the collision and the collision position on the vehicles.

[0070] For the embodiment of the present application, the electronic device can calculate the displacement of the vehicle by comparing the different positions of the accident vehicle in the video, and can calculate the speed of the vehicle before the collision by combining the timestamp of the monitoring video. Therefore, the electronic device determines the speed of the relevant vehicle involved in the accident before the collision in the above manner. The electronic device determines the frame image at the moment of collision, and inputs the frame image into the trained network model to identify the collision site, so as to determine the collision position on the vehicle, such as the front of the vehicle directly hitting the rear of the vehicle, the front of the vehicle offset collision with the rear of the vehicle, the front of the vehicle hitting the side, etc. Different collision positions produce different vibrations, different degrees of damage to the road section, and different corresponding accident severity, so the electronic device determines the collision position on the vehicle. The more serious the accident, the greater the possibility of abnormality or damage to the road surface or other facilities in the tunnel.

[0071] S1043, determine the relative speed based on the speed.

[0072] For the embodiment of the present application, if the colliding vehicles are traveling in the same direction, the electronic device uses the larger speed minus the smaller speed to obtain the relative speed. If the colliding vehicles are traveling in opposite directions, the electronic device uses the two speeds to add to obtain the relative speed. The greater the relative speed, the greater the energy generated by the collision, and the greater the possibility of abnormality and damage to the road section in the tunnel.

[0073] S1044: Determine a score representing the severity of each accident based on the relative speed and the impact position.

[0074] For the embodiments of the present application, in summary, the magnitude of the relative speed and the impact position on the vehicle are both important factors in characterizing the severity of the accident. Therefore, in order to facilitate the quantitative calculation of the severity, the staff can set different scores for different impact positions, and the relative speed and the impact position are both important factors affecting the severity of the accident. Therefore, the staff sets different coefficients for the relative speed and the impact position. After the electronic device determines the scores corresponding to the relative speed and the impact position, it calls the corresponding coefficients for weighted calculation to obtain the score characterizing the severity of each accident. It is more accurate to comprehensively determine the score characterizing the severity through the relative speed and the impact position.

[0075] In other embodiments, the electronic device can also determine whether each accident collides with the wall in the tunnel. If a collision occurs, the score representing the severity is corrected. For example, a correction score corresponds to a collision. After the score representing the severity is determined, the correction score is added to obtain a corrected score representing the severity, making the score more accurate.

[0076] In a possible implementation of the embodiment of the present application, in step S105, judging whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident specifically includes step S1051 (not shown in the figure), step S1052 (not shown in the figure), and step S1053 (not shown in the figure), wherein: S1051, number each position and determine the total abnormal risk value of each number interval.

[0077] The number interval represents the road section between two adjacent locations.

[0078] For the embodiment of the present application, the staff can store the model or map of the tunnel on the electronic device in advance, and then mark each position where the humidity sensor and the vibration sensor are placed on the model or map and number them, so that each position has an independent number. A road section is formed between adjacent positions. Therefore, the electronic device calculates the sum of the abnormal risk values ​​of each two adjacent positions, that is, the sum of the abnormal risk values ​​of each numbered interval, and the sum can characterize the magnitude of the abnormal risk caused by humidity and vibration to the road section of the numbered interval.

[0079] S1052, determine the number interval where the accident location is located, and calculate the total score of the severity score and the sum of the abnormal risk values ​​of the locations in the corresponding number interval.

[0080] For the embodiment of the present application, the electronic device determines the numbered interval where each accident location is located, and then the electronic device calculates the total score of the score representing the severity and the sum of the abnormal risk values ​​of the numbered interval where it is located. The total score represents the magnitude of the abnormal risk caused to the road section by humidity, vibration, and accidents. If no accidents have occurred in certain numbered intervals, only the sum of the abnormal risk values ​​is used to represent the magnitude of the abnormal risk to the road section. If at least two accidents have occurred in certain numbered intervals, the scores of the abnormality levels of all accidents are accumulated and summed, and then the summed value is summed with the total of the abnormal risk values.

[0081] S1053, determining whether the total of abnormal risk values ​​or the total score of any numbered interval reaches a preset score threshold. If so, determining that the road section of any numbered interval is a road section that needs maintenance.

[0082] For the embodiment of the present application, the preset score threshold is used as the dividing point of whether the abnormal risk is too large. After the electronic device determines the total abnormal risk value or total score of each number interval, the total abnormal risk value or total score is compared with the preset score threshold. If the total abnormal risk value or total score of a certain number interval reaches the preset score threshold, it means that the road section corresponding to the number interval is likely to be abnormal or damaged, so the electronic device determines the road section as a road section that needs maintenance.

[0083] If an accident has occurred within a certain numbered interval, the total score is compared with the preset score threshold. If no accident has occurred, the sum of the abnormal risk values ​​is compared with the preset score threshold.

[0084] In a possible implementation of the embodiment of the present application, step S105 further includes step S106 (not shown in the figure) and step S107 (not shown in the figure), wherein: S106, inputting the historical monitoring video into the trained network model to perform traffic flow analysis, and determining the time period when the traffic flow is less than a preset traffic flow threshold.

[0085] S107, output time period.

[0086] For the embodiment of the present application, the electronic device can input the monitoring video into the trained convolutional neural network model or the recurrent neural network model, so as to analyze and identify the traffic volume of the monitoring video to obtain the time period when the traffic volume is less than the preset traffic volume threshold. The time period is defined according to the length of a day. For example, the time periods defined by two hours are (0:00-2:00], (2:00-4:00]... (22:00-24:00]. The time period when the traffic volume is less than the preset traffic volume threshold indicates that there are few passing vehicles in this time period, and it is suitable to carry out maintenance work in this time period. The electronic device then sends the determined time period to the worker. The terminal device of the staff is used to inform the staff of the time period, so that the staff can perform maintenance within the time period. First, the staff collects a training sample set, one of which can be "a video segment of vehicles passing by on a road, and the corresponding traffic volume is xxx", and then inputs the collected training sample set into the initial network model for supervised training and learning to obtain a trained network model. In other embodiments, after the staff sets all the time periods on the electronic device, the electronic device identifies the number of passing vehicles at each moment in the historical monitoring video, thereby determining the number of vehicles in each time period, and using the number of vehicles to represent the traffic volume.

[0087] In a possible implementation of the embodiment of the present application, step S105 further includes step S108 (not shown in the figure), wherein: S108, controlling the corresponding lighting lamps in the road section that needs maintenance to light up according to a preset color.

[0088] For the embodiment of the present application, the electronic device is connected to the lighting lamps in the tunnel through a wire, the lighting lamps can emit light of multiple colors, and the position of each lighting lamp is stored in the electronic device. Therefore, after the electronic device determines the road section that needs maintenance, it determines the lighting lamps in the road section that needs maintenance according to the interval number corresponding to the road section that needs maintenance, and then the electronic device sends a control signal to the lighting lamps in the road section that needs maintenance, so that the lighting lamps in the road section that needs maintenance emit light of a different color from other lighting lamps, such as red or yellow, thereby warning passing vehicles. When the staff is maintaining the road section that needs maintenance, the lighting lamps light up according to the preset colors. When continuous maintenance is carried out, passing vehicles can pay attention to the personnel performing maintenance in the road section in advance, thereby protecting the safety of the maintenance staff to a certain extent.

[0089] The above embodiment introduces a highway maintenance management method from the perspective of method flow, and the following embodiment introduces a highway maintenance management system from the perspective of a virtual module or a virtual unit. Please refer to the following embodiment for details.

[0090] The present application embodiment provides a highway maintenance management system 20, such as Figure 2 As shown, the highway maintenance management system 20 may specifically include: The first acquisition module 201 is used to obtain humidity change graphs corresponding to multiple positions in the tunnel and vibration change graphs corresponding to multiple positions, where the humidity change graphs and vibration change graphs are humidity change graphs and vibration change graphs from the last maintenance to the current time; A first determination module 202 is used to determine an abnormal risk value of each position based on a humidity change graph and a vibration change graph; The second acquisition module 203 is used to acquire the historical monitoring video in the tunnel, where the historical monitoring video is the monitoring video between the last maintenance and the current time; A second determination module 204 is used to determine the severity of the accident that occurred in the tunnel and the accident location of the accident based on the historical monitoring video; The road section output module 205 is used to determine whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident, and if so, output the road section that needs maintenance.

[0091] The embodiment of the present application discloses a highway maintenance management system 20, wherein the first acquisition module 201 acquires a humidity change map and a vibration change map to facilitate subsequent analysis of the possibility of abnormalities and damages caused by humidity and vibration to the road surface and facilities in the tunnel. Both humidity changes and vibration conditions are key factors affecting whether abnormal risks occur. Therefore, the first determination module 202 can accurately determine the abnormal risk value of each location based on the humidity change map and the vibration change map. Traffic accidents in the tunnel may also have an impact on the road surface and facilities. Therefore, the second acquisition module 203 acquires historical monitoring videos. Since the historical monitoring videos record the specific circumstances when the accident occurred, the second determination module 204 can determine the severity of the accident and the location of the accident based on the historical monitoring videos. Finally, the section output module 205 comprehensively determines whether there is a road surface that needs maintenance based on the abnormal risk value and the severity of the accident. If there is, it means that the road surface that needs maintenance may be about to be damaged and abnormal. Therefore, the section output module 205 outputs the section that needs maintenance, so that the staff can promptly know the sections and locations where abnormalities or damage are more likely to occur, thereby facilitating timely preventive maintenance.

[0092] In a possible implementation of the embodiment of the present application, when the first determination module 202 determines the abnormal risk value of each position based on the humidity change graph and the vibration change graph, it is specifically used to: Based on the humidity variation graph, the humidity variance and humidity average value of each location are determined; Determine a first data segment whose humidity value exceeds a preset humidity threshold, and determine a first proportion of the first data segment in the humidity change graph; Determine a first anomaly score for each location based on the humidity variance, the humidity average, and the first proportion; Determine a second data segment where vibration exists at each position based on the vibration variation graph; Determining the duration, amplitude mean, and amplitude variance of each second data segment; determining a second anomaly score for each second data segment based on the duration, the amplitude mean, and the amplitude variance; An abnormality risk value for each location is determined based on the first anomaly score and the second anomaly score.

[0093] In a possible implementation of the embodiment of the present application, when the first determination module 202 determines the abnormal risk value of each position based on the first abnormal score and the second abnormal score, it is specifically used to: determining an average of the second anomaly scores based on the second anomaly scores of each second data segment; determining the number of the second data segments, and determining a third anomaly score for each position with respect to the vibration variation map based on the number and an average of the second anomaly scores; An abnormal risk value for each location is determined based on the first abnormality score and the third abnormality score.

[0094] In a possible implementation of the embodiment of the present application, when the second determination module 204 determines the severity of an accident that has occurred in the tunnel based on the historical monitoring video, it is specifically configured to: Obtain the time point of the accident, and segment the historical surveillance video based on the time point and the preset duration to obtain the sub-video corresponding to each accident; Analyze the sub-videos to determine the speed of each vehicle in the accident before the collision, and the impact position of the collision on the vehicle; Determine relative speed based on speed; A score representing the severity of each accident is determined based on the relative speed and impact location.

[0095] In a possible implementation of the embodiment of the present application, when the road section output module 205 determines whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident, it is specifically used to: Number each location and determine the total abnormal risk value of each number interval, where the number interval represents the road section between two adjacent locations; Determine the number interval where the accident location is located, and calculate the total score of the severity score and the sum of the abnormal risk values ​​of the locations in the corresponding number interval; Determine whether the sum of abnormal risk values ​​or the total score of any numbered interval reaches the preset score threshold. If so, determine that the road section of any numbered interval is a section that needs maintenance.

[0096] In a possible implementation of the embodiment of the present application, the system 20 further includes: An analysis module is used to input historical surveillance videos into the trained network model to perform traffic flow analysis and determine the time period when the traffic flow is less than a preset traffic flow threshold; The time period output module is used to output the time period.

[0097] In a possible implementation of the embodiment of the present application, the system 20 further includes: The control module is used to control the corresponding lighting lamps in the road section that needs maintenance to light up according to the preset color.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the monitoring system 20 of the intelligent switch cabinet described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0099] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3The electronic device 30 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 30 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 30 does not constitute a limitation on the embodiments of the present application.

[0100] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0101] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0102] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0103] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0104] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0105] The embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer is run on a computer, the computer can execute the corresponding content in the above method embodiment. Compared with the related art, in the embodiment of the present application, the humidity change graph and the vibration change graph are obtained to facilitate the subsequent analysis of the possibility of abnormality and damage caused by humidity and vibration to the road surface and facilities in the tunnel. The humidity change and vibration conditions are both key factors affecting whether abnormal risks occur. Therefore, the abnormal risk value of each position can be accurately determined according to the humidity change graph and the vibration change graph. Traffic accidents in the tunnel may also have an impact on the road surface and facilities. Therefore, historical monitoring videos are obtained. Since the specific circumstances when the accident occurred are recorded in the historical monitoring videos, the severity of the accident and the location of the accident can be determined according to the historical monitoring videos. Finally, the abnormal risk value and the severity of the accident are combined to determine whether there is a road surface that needs maintenance. If there is, it means that the road surface that needs maintenance may be damaged and abnormal, so the road section that needs maintenance is output, so that the staff can promptly know the road sections and locations with high probability of abnormality or damage, which is convenient for timely preventive maintenance.

[0106] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0107] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A highway maintenance management method, characterized in that: include: Obtain humidity change graphs corresponding to a plurality of positions in the tunnel and vibration change graphs corresponding to the plurality of positions, wherein the humidity change graphs and the vibration change graphs are humidity change graphs and vibration change graphs from the last maintenance to the current time; Determine the abnormal risk value of each position based on the humidity change graph and the vibration change graph; Obtaining historical surveillance videos in the tunnel, where the historical surveillance videos are surveillance videos from the last maintenance to the current time; Determining the severity of the accident that occurred in the tunnel and the accident location of the accident based on the historical monitoring video; Based on the abnormal risk value and the severity of the accident, it is determined whether there is a road section that needs maintenance. If so, the road section that needs maintenance is output.

2. A highway maintenance management method according to claim 1, characterized in that: The determining of the abnormal risk value of each position based on the humidity change graph and the vibration change graph includes: Determine the humidity variance and humidity average value at each location based on the humidity change graph; Determine a first data segment whose humidity value exceeds a preset humidity threshold, and determine a first proportion of the first data segment in the humidity change graph; Determine a first abnormality score for each location based on the humidity variance, the humidity average, and the first proportion; Determine a second data segment where vibration exists at each position based on the vibration variation graph; Determining the duration, amplitude mean, and amplitude variance of each second data segment; Determine a second anomaly score for each second data segment based on the duration, the amplitude mean, and the amplitude variance; An abnormal risk value for each location is determined based on the first abnormality score and the second abnormality score.

3. A highway maintenance management method according to claim 2, characterized in that: The determining the abnormal risk value of each position based on the first abnormal score and the second abnormal score includes: determining an average of the second anomaly scores based on the second anomaly scores of each second data segment; determining the number of the second data segments, and determining a third anomaly score for each position with respect to the vibration variation map based on the number and an average value of the second anomaly scores; An abnormal risk value for each location is determined based on the first abnormality score and the third abnormality score.

4. A highway maintenance management method according to claim 1, characterized in that: Determining the severity of the accident that occurred in the tunnel based on the historical monitoring video includes: Obtain the time point of the accident, and segment the historical surveillance video based on the time point and the preset duration to obtain sub-videos corresponding to each accident; Analyzing the sub-videos to determine the speed of each vehicle in the accident before the collision, and the collision position on the vehicle; determining a relative speed based on the speed; A score representing the severity of each accident is determined based on the relative speed and the impact position.

5. A highway maintenance management method according to claim 1, characterized in that: The determining whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident includes: Numbering each location and determining the sum of abnormal risk values ​​of each number interval, wherein the number interval represents a road section between two adjacent locations; Determine the number interval where the accident location is located, and calculate the total score of the severity score and the sum of the abnormal risk values ​​of the locations in the corresponding number interval; Determine whether the sum of the abnormal risk values ​​or the total score of any numbered interval reaches a preset score threshold. If so, determine that the road section of any numbered interval is a road section that needs maintenance.

6. A highway maintenance management method according to claim 1, characterized in that: The method further comprises: Input the historical monitoring video into the trained network model to perform traffic flow analysis, and determine the time period when the traffic flow is less than a preset traffic flow threshold; The time period is output.

7. A highway maintenance management method according to claim 1, characterized in that: The method further comprises: The corresponding lighting lamps in the road section requiring maintenance are controlled to light up according to preset colors.

8. A highway maintenance management system, characterized in that: include: A first acquisition module is used to acquire humidity change graphs corresponding to a plurality of positions in the tunnel and vibration change graphs corresponding to the plurality of positions, wherein the humidity change graphs and the vibration change graphs are humidity change graphs and vibration change graphs from the last maintenance to the current time; A first determination module, used to determine an abnormal risk value of each position based on the humidity change graph and the vibration change graph; The second acquisition module is used to acquire the historical monitoring video in the tunnel, where the historical monitoring video is the monitoring video between the last maintenance and the current time; A second determination module is used to determine the severity of the accident that occurred in the tunnel and the accident location of the accident based on the historical monitoring video; The road section output module is used to determine whether there is a road section that needs maintenance based on the abnormal risk value and the severity of the accident, and if so, output the road section that needs maintenance.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute a highway maintenance management method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute a highway maintenance management method as described in any one of claims 1 to 7.

Images