Urban rail transit junction safety management method and system based on AI perception and medium

Abstract

The invention provides an urban rail transit junction safety management method and system based on AI perception and a medium. The method comprises the steps of obtaining a safety monitoring time point, a passenger flow volume actual value and bearing capacity design data of an urban rail transit hub, obtaining historical passenger flow volume mean value data according to the safety monitoring time point, and performing processing according to the passenger flow volume actual value in combination with the historical passenger flow volume mean value data and the bearing capacity design data. Obtaining a hub passenger flow abnormal parameter corresponding to the safety monitoring time point, comparing the hub passenger flow abnormal parameter with a preset passenger flow early warning threshold, and outputting an early warning response according to a threshold comparison result; according to the method, the passenger flow volume actual value is compared with the historical passenger flow volume mean value data and the bearing capacity design data, the hub passenger flow abnormal parameters are obtained, correction is carried out in combination with the personnel density and the corresponding stagnation duration, and safe and intelligent management of the urban rail transit hub is achieved through dynamic threshold value comparison.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban rail transit, in particular to an urban rail transit hub safety management method, system and medium based on AI perception. BACKGROUND

[0002] Urban rail transit hubs have numerous facilities, complex and variable personnel composition, and current safety management mainly relies on manual inspection or passive monitoring. Although some urban rail transit hubs have introduced intelligent security systems, there are problems such as lack of real-time performance, lack of pertinence and high false alarm rate.

[0003] In view of the above problems, effective technical solutions are currently needed. SUMMARY

[0004] The purpose of the present application is to provide an urban rail transit hub safety management method, system and medium based on AI perception, which can obtain hub passenger flow anomaly parameters by comparing actual passenger flow value with historical passenger flow average value data and carrying capacity design data, and correct them in combination with personnel density and corresponding stagnation time, and realize intelligent safety management of urban rail transit hubs through dynamic threshold comparison.

[0005] The present application also provides an urban rail transit hub safety management method based on AI perception, comprising the following steps: Obtaining a safety monitoring time point, actual passenger flow value and carrying capacity design data of an urban rail transit hub; Obtaining historical passenger flow average value data according to the safety monitoring time point; Processing the actual passenger flow value in combination with the historical passenger flow average value data and the carrying capacity design data to obtain hub passenger flow anomaly parameters corresponding to the safety monitoring time point; Comparing the hub passenger flow anomaly parameters with a preset passenger flow warning threshold, and outputting a warning response according to the threshold comparison result.

[0006] Optionally, in the urban rail transit hub safety management method based on AI perception described in the present application, the processing of the actual passenger flow value in combination with the historical passenger flow average value data and the carrying capacity design data to obtain hub passenger flow anomaly parameters corresponding to the safety monitoring time point comprises: Comparing the actual passenger flow value with the historical passenger flow average value data to obtain a passenger flow over-average rate; Processing the actual passenger flow value and the carrying capacity design data to obtain a passenger flow carrying warning rate; Weighted sum processing of the passenger flow over-average rate and the passenger flow carrying warning rate to obtain hub passenger flow anomaly parameters corresponding to the safety monitoring time point.

[0007] Optionally, in the AI perception-based urban rail transit hub safety management method described in the present application, the hub passenger flow abnormality parameter is compared with a preset passenger flow warning threshold, and a warning response is output according to a threshold comparison result, including: The hub passenger flow abnormality parameter is compared with a preset hub passenger flow reference parameter to obtain a hub passenger flow evaluation relative value; The hub passenger flow evaluation relative value is compared with a preset passenger flow warning threshold; If it is less than or equal to the preset passenger flow warning threshold, no warning response is output; If it is greater than the preset passenger flow warning threshold, a warning response is output.

[0008] Optionally, in the AI perception-based urban rail transit hub safety management method described in the present application, further comprising: Obtaining the personnel density and the corresponding stagnation time length in a preset range of the urban rail transit hub; Processing the personnel density and the preset average personnel density to obtain a personnel over-density rate; Processing the stagnation time length and the preset average stagnation time length to obtain an over-stagnation rate; Weighted mean processing is performed according to the personnel over-density rate and the over-stagnation rate to obtain a hub passenger flow evaluation influence coefficient; The hub passenger flow abnormality parameter is corrected according to the hub passenger flow evaluation influence coefficient to obtain a hub passenger flow abnormality correction parameter.

[0009] Optionally, in the AI perception-based urban rail transit hub safety management method described in the present application, further comprising: Obtaining personnel identity information in a preset range of the urban rail transit hub; Comparing the personnel identity information with identity information in a preset staff database; If the comparison is successful, the stagnation time length is not counted; If the comparison is not successful, the stagnation time length is counted.

[0010] Optionally, in the AI perception-based urban rail transit hub safety management method described in the present application, further comprising: Obtaining a first historical passenger flow mean value in a first preset time period and a second historical passenger flow mean value in a second preset time period; Comparing the first historical passenger flow mean value and the second historical passenger flow mean value to obtain a passenger flow relative value in the first preset time period; Comparing the passenger flow relative value with a preset passenger flow parameter relative value; If it is less than or equal to the preset passenger flow parameter relative value, a first preset passenger flow warning threshold corresponding to the first preset time period is obtained by querying a preset dynamic threshold list; If greater than the preset passenger flow parameter relative value, a first preset time period corresponding second preset passenger flow early warning threshold value is obtained by querying the preset dynamic threshold list.

[0011] In a second aspect, the application provides an AI perception-based urban rail transit hub safety management system, which comprises a memory and a processor, the memory comprising an AI perception-based urban rail transit hub safety management method program, the AI perception-based urban rail transit hub safety management method program being executed by the processor to implement the following steps: Obtaining a safety monitoring time point, an actual passenger flow value, and a carrying capacity design data of the urban rail transit hub; Obtaining historical passenger flow average data according to the safety monitoring time point; Processing the actual passenger flow value in combination with the historical passenger flow average data and the carrying capacity design data to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point; Comparing the hub passenger flow abnormality parameter with a preset passenger flow early warning threshold value, and outputting an early warning response according to the threshold value comparison result.

[0012] Optionally, in the AI perception-based urban rail transit hub safety management system described in the application, the processing of the actual passenger flow value in combination with the historical passenger flow average data and the carrying capacity design data to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point comprises: Comparing the actual passenger flow value with the historical passenger flow average data to obtain a passenger flow over-average rate; Processing the actual passenger flow value and the carrying capacity design data to obtain a passenger flow carrying early warning rate; Weighted sum processing the passenger flow over-average rate and the passenger flow carrying early warning rate to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point.

[0013] Optionally, in the AI perception-based urban rail transit hub safety management system described in the application, the comparison of the hub passenger flow abnormality parameter with a preset passenger flow early warning threshold value according to the threshold value comparison result to output an early warning response comprises: Comparing the hub passenger flow abnormality parameter with a preset hub passenger flow reference parameter to obtain a hub passenger flow evaluation relative value; Comparing the hub passenger flow evaluation relative value with a preset passenger flow early warning threshold value; If less than or equal to the preset passenger flow early warning threshold value, no early warning response is outputted; If greater than the preset passenger flow early warning threshold value, an early warning response is outputted.

[0014] In a third aspect, the present application also provides a computer readable storage medium, wherein an AI perception-based urban rail transit hub safety management method program is stored, and the AI perception-based urban rail transit hub safety management method program is executed by a processor to implement the steps of the AI perception-based urban rail transit hub safety management method according to any one of the above aspects.

[0015] As can be seen from the above, the AI perception-based urban rail transit hub safety management method, system and medium provided by the present application obtain hub passenger flow abnormal parameters by comparing the actual passenger flow value with the historical passenger flow mean value data and the bearing capacity design data, and correct the parameters in combination with the personnel density and the corresponding stagnation time, and then realize intelligent safety management of the urban rail transit hub through dynamic threshold comparison.

[0016] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and achieved by particular structures particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained from these drawings without creative labor.

[0018] Figure 1 The flowchart of the AI perception-based urban rail transit hub safety management method provided by the embodiments of the present application; Figure 2 The flowchart of obtaining the hub passenger flow abnormal parameters corresponding to the safety monitoring time point of the AI perception-based urban rail transit hub safety management method provided by the embodiments of the present application; Figure 3 The flowchart of obtaining the hub passenger flow abnormal correction parameters of the AI perception-based urban rail transit hub safety management method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0020] It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used for differentiation in description, and cannot be understood as indicating or implying relative importance.

[0021] Please refer to Figure 1 , Figure 1 is a flowchart of an AI perception-based urban rail transit hub safety management method in some embodiments of the present application. The AI perception-based urban rail transit hub safety management method is used in a terminal device, such as a computer, a mobile phone terminal, etc. The AI perception-based urban rail transit hub safety management method includes the following steps: S11, acquiring a safety monitoring time point of an urban rail transit hub, an actual value of passenger flow, and design data of carrying capacity; S12, acquiring historical passenger flow average data according to the safety monitoring time point; S13, processing the actual value of passenger flow in combination with the historical passenger flow average data and the design data of carrying capacity to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point; S14, comparing the hub passenger flow abnormality parameter with a preset passenger flow early warning threshold value, and outputting an early warning response according to a threshold value comparison result.

[0022] It should be noted that in order to realize intelligent management of safety in an urban rail transit hub, the influence of passenger flow on safety is primarily considered. First, historical passenger flow average data of the same period in history is determined according to a safety monitoring time point. The difference between the historical passenger flow average data and the design data of carrying capacity and the actual value of passenger flow is comprehensively processed to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point, which is used to evaluate the passenger flow safety situation of the urban rail transit hub at the current time point. Then, the hub passenger flow abnormality parameter is compared with a preset passenger flow early warning threshold value, and an early warning response is output according to a threshold value comparison result. The preset passenger flow early warning threshold value is dynamically adjusted, which reduces the false positive rate under the premise of safety.

[0023] Referring to Figure 2 , Figure 2 is a flowchart of obtaining a hub passenger flow abnormality parameter corresponding to a safety monitoring time point in an AI perception-based urban rail transit hub safety management method in some embodiments of the present application. According to the embodiment of the present application, the hub passenger flow abnormality parameter corresponding to the safety monitoring time point is obtained by processing the actual passenger flow value in combination with the historical passenger flow mean value data and the carrying capacity design data, which comprises: S21, comparing the actual passenger flow value with the historical passenger flow mean value data to obtain a passenger flow over-mean rate; S22, processing the actual passenger flow value and the carrying capacity design data to obtain a passenger flow carrying early warning rate; S23, performing weighted summation processing on the passenger flow over-mean rate and the passenger flow carrying early warning rate to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point.

[0024] It should be noted that, in order to accurately evaluate the passenger flow safety situation of the urban rail transit hub at the current time point, first, the passenger flow over-mean rate is obtained by processing the actual passenger flow value and the historical passenger flow mean value data. The passenger flow over-mean rate is the ratio of the actual passenger flow value to the historical passenger flow mean value data. The larger the passenger flow over-mean rate, the more the current passenger flow, and the higher the safety risk. Then, the passenger flow carrying early warning rate is obtained by processing the actual passenger flow value and the carrying capacity design data. The passenger flow carrying early warning rate is the ratio of the actual passenger flow value to the carrying capacity design data. The larger the passenger flow carrying early warning rate, the higher the safety risk. Finally, the hub passenger flow abnormality parameter corresponding to the safety monitoring time point is obtained by performing weighted summation processing on the obtained passenger flow over-mean rate and passenger flow carrying early warning rate. The corresponding weight value is pre-set by a person skilled in the art according to specific applications and can be dynamically adjusted.

[0025] According to the embodiment of the present application, the hub passenger flow abnormality parameter is compared with a preset passenger flow early warning threshold value, and an early warning response is output according to the threshold value comparison result, which comprises: comparing the hub passenger flow abnormality parameter with a preset hub passenger flow reference parameter to obtain a hub passenger flow evaluation relative value; comparing the hub passenger flow evaluation relative value with a preset passenger flow early warning threshold value; if less than or equal to the preset passenger flow early warning threshold value, no early warning response is output; if greater than the preset passenger flow early warning threshold value, an early warning response is output.

[0026] It should be noted that in order to determine whether the passenger flow is abnormal, the obtained hub passenger flow abnormality parameter is compared with the preset hub passenger flow benchmark parameter to obtain a hub passenger flow evaluation relative value. For example, if the hub passenger flow abnormality parameter is 7 and the preset hub passenger flow benchmark parameter is 10, then 7 / 10=0.7 is the hub passenger flow evaluation relative value. Then, the preset passenger flow early warning threshold is compared with the threshold. In this embodiment, the preset passenger flow early warning threshold is set to (0, 0.65], (0.65, 1], which respectively correspond to no output of the early warning response and output of the early warning response. For example, if the hub passenger flow evaluation relative value is 0.7, which is greater than the preset passenger flow early warning threshold, it indicates that the passenger flow is abnormal, and then the early warning response is output.

[0027] Please refer to Figure 3 , Figure 3 is a flowchart for obtaining a hub passenger flow abnormality correction parameter in an AI perception-based urban rail transit hub safety management method according to some embodiments of the present application. According to the embodiments of the present application, the method further comprises: S31, obtaining a personnel density and a corresponding stagnation time length in a preset range of an urban rail transit hub; S32, processing the personnel density and a preset average personnel density to obtain a personnel over-density rate; S33, processing the stagnation time length and a preset average stagnation time length to obtain an over-stagnation rate; S34, performing weighted mean processing on the personnel over-density rate and the over-stagnation rate to obtain a hub passenger flow evaluation influence coefficient; S35, correcting the hub passenger flow abnormality parameter according to the hub passenger flow evaluation influence coefficient to obtain a hub passenger flow abnormality correction parameter.

[0028] It should be noted that the personnel composition in the urban rail transit hub is complex, and under normal passenger flow conditions, some passengers may be sick or faint, causing personnel gathering or special personnel to stay for a long time. The hub passenger flow abnormal parameter needs to be adjusted according to the above common situations. First, the personnel density and the preset average personnel density are processed to obtain the personnel over-density rate. The personnel density refers to the number of personnel in the preset range, and the personnel over-density rate refers to the ratio of the difference between the personnel density and the preset average personnel density to the preset average personnel density. If the personnel density is not greater than the preset average personnel density, the personnel over-density rate of the preset range is not calculated. If there are multiple positions greater than the preset average personnel density, the personnel over-density rate is processed by averaging. Then, the stagnation time and the preset average stagnation time are processed to obtain the over-stay rate. The stagnation time refers to the total time of passengers entering the urban rail transit hub in the preset range, and the over-stay rate refers to the ratio of the difference between the stagnation time and the preset average stagnation time to the preset average stagnation time. If the stagnation time is not greater than the preset average stagnation time, the over-stay rate of the passenger is not calculated. If there are multiple positions greater than the preset average stagnation time, the over-stay rate is processed by averaging. Then, the obtained personnel over-density rate and over-stay rate are weighted and averaged to obtain the hub passenger flow evaluation influence coefficient. The corresponding weight value can be preset by the person skilled in the art and can be dynamically adjusted. For example, the obtained personnel over-density rate is 0.2, the over-stay rate is 0.3, the personnel over-density rate weight value is 0.2, and the over-stay rate weight value is 0.3. Then, (0.2*0.2+0.3*0.3) / (0.2+0.3)=0.26 is the hub passenger flow evaluation influence coefficient. Finally, the obtained hub passenger flow evaluation influence coefficient is used to correct the hub passenger flow abnormal parameter to obtain the hub passenger flow abnormal correction parameter. For example, the hub passenger flow abnormal parameter is 7, and the hub passenger flow evaluation influence coefficient is 0.26. Then, (1+0.26)*7=8.82 is the hub passenger flow abnormal correction parameter.

[0029] According to the embodiments of the present application, the method further comprises: Obtaining personnel identity information in the urban rail transit hub preset range; Comparing the personnel identity information with the identity information in the preset staff database; If the comparison is successful, the stagnation time is not counted; If the comparison is not successful, the stagnation time is counted.

[0030] It should be noted that in addition to passengers, there are many staff in the urban rail transit hub. They stay in the hub for a long time. If the stagnation time of such personnel is counted, it will affect the accuracy of the hub passenger flow evaluation influence coefficient. Therefore, the present application excludes the personnel whose identity information is successfully compared with the identity information in the preset staff database.

[0031] According to the embodiment of the present application, further comprising: obtaining a first historical passenger flow average value of a first preset time period and a second historical passenger flow average value of a second preset time period; comparing the first historical passenger flow average value and the second historical passenger flow average value to obtain a passenger flow relative value of the first preset time period; comparing the passenger flow relative value with a preset passenger flow parameter relative value; if less than or equal to the preset passenger flow parameter relative value, querying a preset dynamic threshold list to obtain a first preset passenger flow early warning threshold corresponding to the first preset time period; if greater than the preset passenger flow parameter relative value, querying the preset dynamic threshold list to obtain a second preset passenger flow early warning threshold corresponding to the first preset time period.

[0032] It should be noted that the passenger flow of the urban rail transport hub has certain rules, such as larger passenger flow during holidays and rush hours, therefore, if the preset passenger flow early warning threshold is a fixed threshold, early warning will not be timely during low peak and flat peak, and frequent false alarms will occur during peak period, affecting safety management; in order to accurately manage safety, first, a first historical passenger flow average value of a first preset time period and a second historical passenger flow average value of a second preset time period are obtained, wherein the first preset time period is 15 minutes before and after the current time point, a total of 30 minutes, the first historical passenger flow average value is the passenger flow average value of the same first preset time period in the past 5 years, and the second preset time period is the natural day in which the current time point is located, and the second historical passenger flow average value refers to the passenger flow average value of the same second preset time period in the past 5 years, the two are compared to obtain a passenger flow relative value, for example, the first historical passenger flow average value is 500 people, the second historical passenger flow average value is 10,000 people, and 500 / 10,000=0.05 is the passenger flow relative value; then the obtained passenger flow relative value is compared with a preset passenger flow parameter relative value, in the embodiment, the preset passenger flow parameter relative value is set to 0.1, for example, the obtained passenger flow relative value is 0.05, which is less than the preset passenger flow parameter relative value, then a first preset passenger flow early warning threshold corresponding to the first preset time period is obtained by querying a preset dynamic threshold list, wherein the preset dynamic threshold list is preset and adjusted by a person skilled in the art according to the specific passenger flow of the urban rail transport hub.

[0033] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining a signal light changing time, a signal light color and a preset urban rail transport timetable in the urban rail transport hub; extracting a signal light changing demand time and a corresponding preset signal light color according to the preset urban rail transport timetable; processing the signal light changing time and the signal light changing demand time to obtain a signal light changing deviation time; comparing the signal lamp color with a preset signal lamp color, if the colors are the same, determining that the signal lamp is working normally; if less than or equal to the preset time deviation threshold, comparing the signal lamp color with a preset signal lamp color, if the colors are the same, determining that the signal lamp is working normally; if greater than the preset time deviation threshold, determining that the signal lamp is working abnormally, and outputting a warning response.

[0034] It should be noted that the signal lamp in the urban rail transit hub is an important part of guiding the operation of the urban rail transit. Whether the signal lamp changing time and color are accurate needs to be focused on. First, the signal lamp changing time is compared with the signal lamp changing demand time extracted from the preset urban rail transit timetable to obtain the signal lamp changing deviation time, which is the absolute value of the difference between the signal lamp changing time and the signal lamp changing demand time. Then, the signal lamp changing deviation time is compared with a preset time deviation threshold. If greater than the preset time deviation threshold, it indicates that the signal lamp changing time is inaccurate, and a warning response is directly output. If less than or equal to the preset time deviation threshold, it indicates that the signal lamp changing time is accurate. Further, the signal lamp color is compared with a preset signal lamp color. If the colors are the same, it is determined that the signal lamp is working normally. Otherwise, it is determined that the signal lamp is working abnormally, a warning response is output, and timely processing is ensured to ensure the safety of the urban rail transit hub.

[0035] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining water level information, preset warning water level information and preset drainage parameter data of a preset position of the urban rail transit hub; querying a preset water level and water storage amount mapping table according to the water level information and the preset warning water level information to obtain water storage data and preset warning water storage data; obtaining weather forecast information, and extracting predicted precipitation data according to the weather forecast information; comparing the water storage data and the predicted precipitation data with the preset drainage parameter data to obtain a predicted water storage increment; comparing the predicted water storage increment with the preset warning water storage data to obtain a predicted water storage rate; comparing the predicted water storage rate with a preset water storage rate warning threshold; if less than or equal to the preset water storage rate warning threshold, not outputting a warning response; if greater than the preset water storage rate warning threshold, outputting a warning response.

[0036] It should be noted that the urban rail transport hub is located in an underground environment, and the water level should be supervised in real time to prevent safety problems caused by underground seepage or extreme weather rainwater backflow. The obtained water storage data and predicted precipitation data are compared with the preset drainage parameter data to obtain a water storage prediction increment, which is the water storage data plus the predicted precipitation data minus the preset drainage parameter data. If it is not greater than 0, it means that the drainage system can timely remove excess water. If it is greater than 0, it means that the water level will gradually rise. Further compare the water storage prediction increment with the preset warning water storage data to obtain a predicted water storage rate, which is the ratio of the water storage prediction increment to the preset warning water storage data, and compare it with the preset water storage rate warning threshold. In this embodiment, the preset water storage rate warning threshold is set to 0.25. For example, the obtained water storage data is 1, the predicted precipitation data is 2, and the preset drainage parameter data is 2. Then (1+2)-2=1 is the water storage prediction increment, and the preset warning water storage data is 5. Then 1 / 5=0.2 is the predicted water storage rate, which is less than the preset water storage rate warning threshold, so no early warning response is output.

[0037] It is worth mentioning that, according to the embodiment of the application, further comprising: obtaining a first speed at a first preset time point of urban rail transport and a second speed at a second preset time point; comparing the first speed with a preset first required speed to obtain a first speed deviation rate; threshold comparison between the first speed deviation rate and a preset speed deviation rate threshold; if greater than the preset speed deviation rate threshold, output an overspeed early warning response; if less than or equal to the preset speed deviation rate threshold, compare the second speed with a preset second required speed to obtain a second speed deviation rate; threshold comparison between the second speed deviation rate and the preset speed deviation rate threshold; if greater than the preset speed deviation rate threshold, determine that the urban rail transport is running at an overspeed; if less than or equal to the preset speed deviation rate threshold, determine that the urban rail transport is running normally.

[0038] It should be noted that the urban rail transit hub is an urban rail transit stop site, and the stop position is fixed, and the running speed of the urban rail transit hub should be supervised in real time whether it can be accurately stopped at the predetermined position. First, a first speed at a first preset time point and a second speed at a second preset time point are obtained, wherein the first preset time point is a time point corresponding to a position before the urban rail transit enters the urban rail transit hub, and the second preset time point is a time point after the first preset time point by a preset time interval. Then, the obtained first speed is compared with a preset first required speed to obtain a first speed deviation rate, the first speed deviation rate being a ratio of an absolute value of a difference between the first speed and the preset first required speed to the preset first required speed. Finally, the preset speed deviation rate threshold is compared. If the corresponding threshold is exceeded, a warning reminder is directly output. If not, the second speed corresponding to the second time point is monitored, and the monitoring is repeated until the urban rail transit hub is accurately stopped.

[0039] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining position information of a preset range of the urban rail transit hub and corresponding gas concentration growth rate, temperature rise rate and smoke particle concentration rise rate; weighting and summing the gas concentration growth rate, the temperature rise rate and the smoke particle concentration rise rate to obtain a fire condition prediction parameter; comparing the fire condition prediction parameter with a preset fire condition warning threshold; if less than or equal to the preset fire condition warning threshold, no warning is output; if greater than the preset fire condition warning threshold, a warning is output, and distance data of the worker is obtained according to the position information; sorting the distance data in ascending order, and sending the position information to the terminal of the worker with the smallest distance data for display.

[0040] It should be noted that there are many facilities in the urban rail transit hub, and the environment is relatively closed. The growth rate of gas concentration, the temperature increase rate and the smoke particle concentration increase rate are monitored through pre-set sensors, wherein the gas includes carbon monoxide and sulfur dioxide, the growth rate of gas concentration refers to the difference between the gas concentration at the next time point and the gas concentration at the previous time point, and the ratio of the gas concentration at the previous time point, the temperature increase rate refers to the difference between the temperature at the next time point and the temperature at the previous time point, and the ratio of the temperature at the previous time point, and the smoke particle concentration increase rate refers to the difference between the smoke particle concentration at the next time point and the smoke particle concentration at the previous time point, and the ratio of the smoke particle concentration at the previous time point. The obtained gas concentration growth rate, temperature increase rate and smoke particle concentration increase rate are weighted and summed to obtain a fire condition prediction parameter, wherein the corresponding weight value is pre-set by a person skilled in the art according to the specific monitoring environment. Finally, the obtained fire condition prediction parameter is compared with the preset fire condition warning threshold value, and if it is determined that a fire occurs, the nearest staff is found according to the location of the fire occurrence, so as to timely handle.

[0041] The application also discloses an urban rail transit hub safety management system based on AI perception, comprising a memory and a processor, wherein the memory comprises an urban rail transit hub safety management method program based on AI perception, and the urban rail transit hub safety management method program based on AI perception is executed by the processor to realize the following steps: obtaining a safety monitoring time point, an actual passenger flow value and a bearing capacity design data of an urban rail transit hub; obtaining historical passenger flow average data according to the safety monitoring time point; processing the actual passenger flow value in combination with the historical passenger flow average data and the bearing capacity design data to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point; comparing the hub passenger flow abnormality parameter with a preset passenger flow warning threshold value, and outputting a warning response according to the threshold comparison result.

[0042] It should be noted that in order to realize intelligent management of the safety of the urban rail transit hub, the influence of passenger flow on safety is primarily considered. First, historical passenger flow average data of the same period is determined according to the safety monitoring time point. The difference between the historical passenger flow average data and the bearing capacity design data and the actual passenger flow value is comprehensively processed to obtain a hub passenger flow abnormality parameter corresponding to the safety monitoring time point, which is used to evaluate the passenger flow safety of the urban rail transit hub at the current time point. Then, the threshold comparison is performed with the preset passenger flow warning threshold value, and the warning response is output according to the threshold comparison result. The preset passenger flow warning threshold value is dynamically adjusted, which reduces the false positive rate under the premise of safety.

[0043] According to the embodiment of the present application, the hub passenger flow abnormality parameter corresponding to the safety monitoring time point is obtained by processing the actual passenger flow value in combination with the historical average passenger flow value data and the carrying capacity design data, and comprises: The passenger flow over-average rate is obtained by comparing the actual passenger flow value with the historical average passenger flow value data. The passenger flow carrying early warning rate is obtained by processing the actual passenger flow value and the carrying capacity design data. The passenger flow over-average rate and the passenger flow carrying early warning rate are weighted and summed to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point.

[0044] It should be noted that, in order to accurately evaluate the passenger flow safety situation of the urban rail transit hub at the current time point, first, the passenger flow over-average rate is obtained by processing the actual passenger flow value and the historical average passenger flow value data. The passenger flow over-average rate is the ratio of the actual passenger flow value to the historical average passenger flow value data. The larger the passenger flow over-average rate, the more the current passenger flow, and the higher the safety risk. Then, the passenger flow carrying early warning rate is obtained by processing the actual passenger flow value and the carrying capacity design data. The passenger flow carrying early warning rate is the ratio of the actual passenger flow value to the carrying capacity design data. The larger the passenger flow carrying early warning rate, the higher the safety risk. Finally, the passenger flow over-average rate and the passenger flow carrying early warning rate are weighted and summed to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point. The corresponding weight value is preset by the person skilled in the art according to the specific application, and can be dynamically adjusted.

[0045] According to the embodiment of the present application, the hub passenger flow abnormality parameter is compared with the preset passenger flow early warning threshold value, and the early warning response is output according to the threshold value comparison result, comprising: The hub passenger flow evaluation relative value is obtained by comparing the hub passenger flow abnormality parameter with the preset hub passenger flow reference parameter. The hub passenger flow evaluation relative value is compared with the preset passenger flow early warning threshold value. If it is less than or equal to the preset passenger flow early warning threshold value, no early warning response is output. If it is greater than the preset passenger flow early warning threshold value, the early warning response is output.

[0046] It should be noted that in order to determine whether the passenger flow is abnormal, the obtained hub passenger flow abnormality parameter is compared with the preset hub passenger flow benchmark parameter to obtain a hub passenger flow evaluation relative value, for example, the hub passenger flow abnormality parameter is 7, the preset hub passenger flow benchmark parameter is 10, and 7 / 10=0.7 is the hub passenger flow evaluation relative value, and then the preset passenger flow early warning threshold is compared with the threshold, in the embodiment, the preset passenger flow early warning threshold is set to (0, 0.65], (0.65, 1], corresponding to no output of the early warning response and output of the early warning response, for example, the hub passenger flow evaluation relative value is 0.7, which is greater than the preset passenger flow early warning threshold, indicating that the passenger flow is abnormal, and the early warning response is output.

[0047] According to the embodiment of the application, further comprising: Obtaining the personnel density and the corresponding stagnation time length in the preset range of the urban rail transit hub; Processing according to the personnel density and the preset average personnel density to obtain a personnel over-density rate; Processing according to the stagnation time length and the preset average stagnation time length to obtain an over-stagnation rate; Weighted mean processing according to the personnel over-density rate and the over-stagnation rate to obtain a hub passenger flow evaluation influence coefficient; According to the hub passenger flow evaluation influence coefficient, the hub passenger flow abnormality parameter is corrected to obtain a hub passenger flow abnormality correction parameter.

[0048] It should be noted that the personnel composition in the urban rail transit hub is complex, and under normal passenger flow conditions, some passengers may be sick or faint, causing personnel gathering or special personnel to stay for a long time. The hub passenger flow abnormal parameter needs to be adjusted according to the above common situations. First, the personnel density and the preset average personnel density are processed to obtain the personnel over-density rate. The personnel density refers to the number of personnel in the preset range, and the personnel over-density rate refers to the ratio of the difference between the personnel density and the preset average personnel density to the preset average personnel density. If the personnel density is not greater than the preset average personnel density, the personnel over-density rate of the preset range is not calculated. If there are multiple positions greater than the preset average personnel density, the personnel over-density rate is processed by averaging. Then, the stagnation time and the preset average stagnation time are processed to obtain the over-stay rate. The stagnation time refers to the total time of passengers entering the urban rail transit hub in the preset range, and the over-stay rate refers to the ratio of the difference between the stagnation time and the preset average stagnation time to the preset average stagnation time. If the stagnation time is not greater than the preset average stagnation time, the over-stay rate of the passenger is not calculated. If there are multiple positions greater than the preset average stagnation time, the over-stay rate is processed by averaging. Then, the personnel over-density rate and the over-stay rate are weighted and averaged to obtain the hub passenger flow evaluation influence coefficient. The corresponding weight value can be preset by the person skilled in the art and can be dynamically adjusted. For example, the personnel over-density rate is 0.2, the over-stay rate is 0.3, the personnel over-density rate weight value is 0.2, and the over-stay rate weight value is 0.3. Then, (0.2*0.2+0.3*0.3) / (0.2+0.3)=0.26 is the hub passenger flow evaluation influence coefficient. Finally, the hub passenger flow evaluation influence coefficient is used to correct the hub passenger flow abnormal parameter to obtain the hub passenger flow abnormal correction parameter. For example, the hub passenger flow abnormal parameter is 7, and the hub passenger flow evaluation influence coefficient is 0.26. Then, (1+0.26)*7=8.82 is the hub passenger flow abnormal correction parameter.

[0049] According to the embodiments of the present application, the method further comprises: obtaining personnel identity information in the urban rail transit hub preset range; comparing the personnel identity information with the identity information in the preset staff database; if the comparison is successful, the stagnation time is not counted; if the comparison is not successful, the stagnation time is counted.

[0050] It should be noted that in addition to passengers, there are many staff in the urban rail transit hub. They stay in the hub for a long time. If the stagnation time of such personnel is counted, it will affect the accuracy of the hub passenger flow evaluation influence coefficient. Therefore, the present application excludes the personnel whose identity information is successfully compared with the identity information in the preset staff database.

[0051] According to the embodiment of the present application, further comprising: obtaining a first historical passenger flow average value of a first preset time period and a second historical passenger flow average value of a second preset time period; comparing the first historical passenger flow average value and the second historical passenger flow average value to obtain a passenger flow relative value of the first preset time period; comparing the passenger flow relative value with a preset passenger flow parameter relative value; if less than or equal to the preset passenger flow parameter relative value, querying a preset dynamic threshold list to obtain a first preset passenger flow early warning threshold corresponding to the first preset time period; if greater than the preset passenger flow parameter relative value, querying the preset dynamic threshold list to obtain a second preset passenger flow early warning threshold corresponding to the first preset time period.

[0052] It should be noted that the passenger flow of the urban rail transport hub has certain rules, such as larger passenger flow during holidays and rush hours, therefore, if the preset passenger flow early warning threshold is a fixed threshold, early warning will not be timely during low peak and flat peak, and frequent false alarms will occur during peak period, affecting safety management; in order to accurately manage safety, first, a first historical passenger flow average value of a first preset time period and a second historical passenger flow average value of a second preset time period are obtained, wherein the first preset time period is 15 minutes before and after the current time point, a total of 30 minutes, the first historical passenger flow average value is the passenger flow average value of the same first preset time period in the past 5 years, and the second preset time period is the natural day in which the current time point is located, and the second historical passenger flow average value refers to the passenger flow average value of the same second preset time period in the past 5 years, the two are compared to obtain a passenger flow relative value, for example, the first historical passenger flow average value is 500 people, the second historical passenger flow average value is 10,000 people, and 500 / 10,000=0.05 is the passenger flow relative value; then the obtained passenger flow relative value is compared with a preset passenger flow parameter relative value, in the embodiment, the preset passenger flow parameter relative value is set to 0.1, for example, the obtained passenger flow relative value is 0.05, which is less than the preset passenger flow parameter relative value, then a first preset passenger flow early warning threshold corresponding to the first preset time period is obtained by querying a preset dynamic threshold list, wherein the preset dynamic threshold list is preset and adjusted by a person skilled in the art according to the specific passenger flow of the urban rail transport hub.

[0053] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining a signal light changing time, a signal light color and a preset urban rail transport timetable in the urban rail transport hub; extracting a signal light changing demand time and a corresponding preset signal light color according to the preset urban rail transport timetable; processing the signal light changing time and the signal light changing demand time to obtain a signal light changing deviation time; comparing the signal lamp color with a preset signal lamp color, if the colors are the same, determining that the signal lamp is working normally; if less than or equal to the preset time deviation threshold, comparing the signal lamp color with a preset signal lamp color, if the colors are the same, determining that the signal lamp is working normally; if greater than the preset time deviation threshold, determining that the signal light change is abnormal, and outputting a warning response.

[0054] It should be noted that the signal lamp in the urban rail transit hub is an important part of guiding the operation of urban rail transit. Whether the change time and color of the signal lamp are accurate needs to be focused on. First, the signal change deviation time is obtained by comparing the signal change time with the signal change required time extracted from the preset urban rail transit timetable. The signal change deviation time is the absolute value of the difference between the signal change time and the signal change required time. Then, threshold comparison is performed with the preset time deviation threshold. If it is greater than the preset time deviation threshold, it means that the signal change time is inaccurate, and a warning response is directly output. If it is less than or equal to the preset time deviation threshold, it means that the change time is accurate. Further, the signal lamp color is compared with the preset signal lamp color. If the colors are the same, it is determined that the signal lamp is working normally. Otherwise, it is determined that the signal lamp is working abnormally, a warning response is output, and timely processing is ensured to ensure the safety of the urban rail transit hub.

[0055] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining water level information, preset warning water level information and preset drainage parameter data of a preset position of the urban rail transit hub; querying a preset water level and water storage amount mapping table according to the water level information and the preset warning water level information to obtain water storage data and preset warning water storage data; obtaining weather forecast information, and extracting predicted precipitation data according to the weather forecast information; comparing the water storage data and the predicted precipitation data with the preset drainage parameter data to obtain a predicted water storage increment; comparing the predicted water storage increment with the preset warning water storage data to obtain a predicted water storage rate; threshold comparing the predicted water storage rate with a preset water storage rate warning threshold; if less than or equal to the preset water storage rate warning threshold, no warning response is output; if greater than the preset water storage rate warning threshold, a warning response is output.

[0056] It should be noted that the urban rail transport hub is located in an underground environment, and the water level should be supervised in real time to prevent safety problems caused by underground water seepage or extreme weather rainwater backflow. The obtained water storage data and predicted precipitation data are compared with the preset drainage parameter data to obtain a water storage prediction increment, which is the water storage data plus the predicted precipitation data minus the preset drainage parameter data. If it is not greater than 0, it means that the drainage system can timely remove excess water. If it is greater than 0, it means that the water level will gradually rise. Further compare the water storage prediction increment with the preset warning water storage data to obtain a predicted water storage rate, which is the ratio of the water storage prediction increment to the preset warning water storage data, and compare it with the preset water storage rate warning threshold. In the embodiment, the preset water storage rate warning threshold is set to 0.25. For example, the obtained water storage data is 1, the predicted precipitation data is 2, and the preset drainage parameter data is 2. Then (1+2)-2=1 is the water storage prediction increment, and the preset warning water storage data is 5. Then 1 / 5=0.2 is the predicted water storage rate, which is less than the preset water storage rate warning threshold, and no early warning response is output.

[0057] It is worth mentioning that, according to the embodiment of the application, further comprising: obtaining a first speed at a first preset time point of urban rail transport and a second speed at a second preset time point; comparing the first speed with a preset first required speed to obtain a first speed deviation rate; threshold comparison between the first speed deviation rate and a preset speed deviation rate threshold; if greater than the preset speed deviation rate threshold, output an overspeed early warning response; if less than or equal to the preset speed deviation rate threshold, compare the second speed with a preset second required speed to obtain a second speed deviation rate; threshold comparison between the second speed deviation rate and the preset speed deviation rate threshold; if greater than the preset speed deviation rate threshold, determine that the urban rail transport is running at an overspeed; if less than or equal to the preset speed deviation rate threshold, determine that the urban rail transport is running normally.

[0058] It should be noted that the urban rail transit hub is an urban rail transit stop site, and the stop position is fixed, and the running speed of the urban rail transit hub should be supervised in real time whether it can be accurately stopped at the predetermined position. First, a first speed at a first preset time point and a second speed at a second preset time point are obtained, wherein the first preset time point is a time point corresponding to a position before the urban rail transit enters the urban rail transit hub, and the second preset time point is a time point after the first preset time point by a preset time interval. Then, the obtained first speed is compared with a preset first required speed to obtain a first speed deviation rate, the first speed deviation rate being a ratio of an absolute value of a difference between the first speed and the preset first required speed to the preset first required speed. Finally, the preset speed deviation rate threshold is compared. If the corresponding threshold is exceeded, a warning reminder is directly output. If not, the second speed corresponding to the second time point is monitored, and the monitoring is repeated until the urban rail transit hub is accurately stopped.

[0059] It is worth mentioning that, according to the embodiment of the present application, further comprising: obtaining position information of a preset range of the urban rail transit hub and corresponding gas concentration growth rate, temperature rise rate and smoke particle concentration rise rate; weighting and summing the gas concentration growth rate, the temperature rise rate and the smoke particle concentration rise rate to obtain a fire condition prediction parameter; comparing the fire condition prediction parameter with a preset fire condition warning threshold; if less than or equal to the preset fire condition warning threshold, no warning is output; if greater than the preset fire condition warning threshold, a warning is output, and distance data of the worker is obtained according to the position information; sorting the distance data in ascending order, and sending the position information to the terminal of the worker with the smallest distance data.

[0060] It should be noted that there are many facilities in the urban rail transit hub, and the environment is relatively closed, the growth rate of gas concentration, the temperature rise rate and the smoke particle concentration rise rate should be monitored through the preset sensor, wherein the gas includes carbon monoxide and sulfur dioxide, the growth rate of gas concentration refers to the difference between the gas concentration at the next time point and the gas concentration at the previous time point, and the ratio of the gas concentration at the previous time point, the temperature rise rate refers to the difference between the temperature at the next time point and the temperature at the previous time point, and the ratio of the temperature at the previous time point, and the smoke particle concentration rise rate refers to the difference between the smoke particle concentration at the next time point and the smoke particle concentration at the previous time point, and the ratio of the smoke particle concentration at the previous time point, the obtained gas concentration growth rate, temperature rise rate and smoke particle concentration rise rate are weighted and summed to obtain a fire condition prediction parameter, wherein the corresponding weight value is preset by the person skilled in the art according to the specific monitoring environment, and finally, the obtained fire condition prediction parameter is compared with the preset fire condition warning threshold, if it is determined that a fire occurs, the nearest staff is found according to the location of the fire occurrence, so as to be handled in time.

[0061] The third aspect of the present application provides a readable storage medium, wherein an AI perception-based urban rail transit hub safety management method program is stored in the readable storage medium, and when the AI perception-based urban rail transit hub safety management method program is executed by a processor, the steps of the AI perception-based urban rail transit hub safety management method according to any one of the preceding aspects are implemented.

[0062] The AI perception-based urban rail transit hub safety management method, system and medium disclosed in the present application obtain hub passenger flow anomaly parameters by comparing the actual passenger flow value with the historical passenger flow mean value data and the bearing capacity design data, and correct them in combination with the personnel density and the corresponding stagnation time, and then realize intelligent safety management of the urban rail transit hub through dynamic threshold comparison.

[0063] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0064] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0065] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0066] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction-related hardware, and the foregoing program can be stored in a readable storage medium, and when the program is executed, the steps of the method embodiments are executed; and the foregoing storage medium includes mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic discs or optical discs, and various media that can store program codes.

[0067] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes mobile storage devices, ROMs, RAMs, magnetic discs or optical discs, and various media that can store program codes.

Claims

1. The urban rail transit hub safety management method based on AI perception is characterized by: The following steps are involved: Obtain safety monitoring time points, actual passenger flow values, and design capacity data for urban rail transit hubs; Obtain historical passenger flow average data based on the safety monitoring time point; Processing the actual passenger flow value in combination with the historical passenger flow average data and the load capacity design data to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point; The abnormal passenger flow parameters of the hub are compared with the preset passenger flow warning threshold, and a warning response is output according to the threshold comparison result.

2. The urban rail transit hub safety management method based on AI perception according to claim 1 is characterized in that: The processing of the actual passenger flow value in combination with the historical passenger flow average data and the carrying capacity design data to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point includes: Comparing the actual passenger flow value with the historical passenger flow average data to obtain a passenger flow excess rate; Processing the actual passenger flow value and the designed carrying capacity data to obtain a passenger flow carrying warning rate; The passenger flow excess rate and the passenger flow carrying warning rate are weighted and summed to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point.

3. The urban rail transit hub safety management method based on AI perception according to claim 2 is characterized in that: The step of comparing the abnormal hub passenger flow parameter with a preset passenger flow warning threshold and outputting a warning response according to the threshold comparison result includes: Comparing the abnormal hub passenger flow parameters with the preset hub passenger flow benchmark parameters to obtain a relative hub passenger flow evaluation value; Comparing the relative value of the hub passenger flow evaluation with a preset passenger flow warning threshold; If it is less than or equal to the preset passenger flow warning threshold, no warning response is output; If it is greater than the preset passenger flow warning threshold, an early warning response is output.

4. The urban rail transit hub safety management method based on AI perception according to claim 3 is characterized in that: Also includes: Obtain the population density and corresponding stagnation duration within the preset range of the urban rail transit hub; Processing is performed based on the population density and the preset average population density to obtain a population over-density rate; Processing is performed according to the stagnation time and a preset average stagnation time to obtain an excess stop rate; A weighted average is performed based on the overcrowding rate and overparking rate to obtain the hub passenger flow evaluation impact coefficient; The hub passenger flow abnormality parameter is corrected according to the hub passenger flow evaluation influence coefficient to obtain the hub passenger flow abnormality correction parameter.

5. The urban rail transit hub safety management method based on AI perception according to claim 4 is characterized in that: Also includes: Obtain the identity information of people within the preset range of the urban rail transit hub; Comparing the personnel identity information with the identity information in a preset personnel database; If the comparison is successful, the stagnation time will not be counted; If the comparison is unsuccessful, the stagnation time is counted.

6. The AI-based urban rail transit hub safety management method according to claim 5 is characterized in that: Also includes: Obtain a first historical passenger flow average value for a first preset time period and a second historical passenger flow average value for a second preset time period; Comparing the first historical passenger flow average with the second historical passenger flow average to obtain a relative passenger flow value for a first preset time period; Comparing the passenger flow relative value with a preset passenger flow parameter relative value; If it is less than or equal to the preset passenger flow parameter relative value, query the preset dynamic threshold list to obtain the first preset passenger flow warning threshold corresponding to the first preset time period; If it is greater than the preset passenger flow parameter relative value, the preset dynamic threshold list is queried to obtain the second preset passenger flow warning threshold corresponding to the first preset time period.

7. The urban rail transit hub safety management system based on AI perception is characterized by: The system includes a memory and a processor, wherein the memory includes a program of an urban rail transit hub safety management method based on AI perception, and when the program of the urban rail transit hub safety management method based on AI perception is executed by the processor, the following steps are implemented: Obtain safety monitoring time points, actual passenger flow values, and design capacity data for urban rail transit hubs; Obtain historical passenger flow average data based on the safety monitoring time point; Processing the actual passenger flow value in combination with the historical passenger flow average data and the load capacity design data to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point; The abnormal passenger flow parameters of the hub are compared with the preset passenger flow warning threshold, and a warning response is output according to the threshold comparison result.

8. The urban rail transit hub safety management system based on AI perception according to claim 7 is characterized in that: The processing of the actual passenger flow value in combination with the historical passenger flow average data and the carrying capacity design data to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point includes: Comparing the actual passenger flow value with the historical passenger flow average data to obtain a passenger flow excess rate; Processing the actual passenger flow value and the designed carrying capacity data to obtain a passenger flow carrying warning rate; The passenger flow excess rate and the passenger flow carrying warning rate are weighted and summed to obtain the hub passenger flow abnormality parameter corresponding to the safety monitoring time point.

9. The urban rail transit hub safety management system based on AI perception according to claim 8 is characterized in that: The step of comparing the abnormal hub passenger flow parameter with a preset passenger flow warning threshold and outputting a warning response according to the threshold comparison result includes: Comparing the abnormal hub passenger flow parameters with the preset hub passenger flow benchmark parameters to obtain a relative hub passenger flow evaluation value; Comparing the relative value of the hub passenger flow evaluation with a preset passenger flow warning threshold; If it is less than or equal to the preset passenger flow warning threshold, no warning response is output; If it is greater than the preset passenger flow warning threshold, an early warning response is output.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an AI-perception-based urban rail transit hub safety management method program. When the AI-perception-based urban rail transit hub safety management method program is executed by the processor, the steps of the AI-perception-based urban rail transit hub safety management method as described in any one of claims 1 to 6 are implemented.

Images