Rail transit protection area automatic patrol method and device based on artificial intelligence

Abstract

The invention discloses an automatic patrol method and device for a rail transit protection area based on artificial intelligence, and relates to the field of maintenance and management of the rail transit protection area, key patrol sub-areas generating negative correlation close signals are sorted according to the periodic jam frequency, a same patrol sub-area sequence is obtained, and in the same patrol sub-area sequence, the negative correlation close signals are obtained; and for each key patrol subarea, finding out a blocking time period with the least blocking frequency in a historical period, marking the patrol frequency corresponding to the time period as a patrol basis value, and summing the patrol basis values corresponding to all the key patrol subareas to obtain a mean value so as to obtain a final patrol frequency. A relatively reasonable frequency reference is provided for patrol work in the rail protection area, blind patrol is avoided, and the problem of how to reasonably allocate patrol resources according to blockage and patrol association conditions of different key patrol sub-areas in the rail traffic protection area is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of maintenance and management of rail transit protection areas, and in particular to an automatic inspection method and device for rail transit protection areas based on artificial intelligence. Background Art

[0002] During the operation of rail transit, drainage pipes within the rail protection zone are crucial to ensure the normal operation of the track. However, the traditional inspection method of rail transit protection zones often relies on manual experience and has many disadvantages, such as unreasonable allocation of inspection resources, inability to adjust the inspection frequency in time according to actual conditions, and difficulty in discovering potential blockage problems in advance.

[0003] In the prior art, as the scope of rail transit protection zones continues to expand, there is a lack of quantitative analysis of the correlation between the number of inspections and the number of congestion times, and it is impossible to adjust the inspection strategy in a targeted manner according to the actual conditions of different areas, which easily leads to a waste of inspection resources or inadequate inspections. Therefore, this application identifies key inspection sub-areas, analyzes the changes in the number of congestion times in key inspection sub-areas during historical periods, reflects the law of congestion changes in key inspection sub-areas, arranges inspection work reasonably, extracts the historical number of inspections in key inspection sub-areas in multiple congestion periods from the inspection log, constructs a patrol number change curve, and compares it with the changes in the number of congestion times in existing key inspection sub-areas. The combined comparative analysis of the curves reflects the close correlation between the number of inspections and the number of congestion in the historical period, which is conducive to optimizing the inspection strategy and adjusting the inspection frequency of key inspection sub-areas in a targeted manner. For each key inspection sub-area, find out the congestion period with the least congestion in the historical period, sum and average the inspection basis values ​​corresponding to all key inspection sub-areas, and get the final inspection frequency. This provides a more reasonable frequency reference for the inspection work in the rail protection area, avoids blind inspections, and solves the problem of how to reasonably allocate inspection resources in the rail transit protection area according to the congestion and inspection correlation of different key inspection sub-areas. Summary of the invention

[0004] The object of the present invention is to provide an artificial intelligence-based automatic inspection method and device for a rail transit protection zone to solve at least one of the above-mentioned problems of the prior art.

[0005] In the first aspect, an automatic inspection method for a rail transit protection zone based on artificial intelligence comprises: Step 1: Extract the drainage pipeline drawings along the route through the panoramic navigation system, generate the pipeline inspection area, analyze the blockage data of the pipeline inspection area in the historical period, and obtain the key inspection sub-area; Step 2: Analyze the changes in the number of congestion times in multiple key inspection sub-areas in the historical period to obtain the number of change data, quantify the number of change data, and obtain a linear change signal; Step 3: Based on the linear change signal, extract the historical inspection data of multiple key inspection sub-areas from the inspection log, perform correlation analysis on the historical inspection data and the congestion data, and obtain a negative correlation signal; Step 4: Summarize the key inspection sub-areas that generate negative correlation signals, obtain the same inspection sub-area sequence, obtain the inspection frequency, and complete the inspection work of the key inspection sub-areas in the same inspection sub-area sequence.

[0006] Beneficial effects of the present invention: 1. The present invention obtains the frequency mean of the pipeline sub-area in the historical period, identifies the key inspection sub-area, analyzes the change of the number of blockages in the key inspection sub-area in the historical period, obtains the number of change data, quantifies the number of change data, and obtains the linear value of the blockage change, so as to reflect the blockage change law in the key inspection sub-area through the linear value of the blockage change, so as to reasonably arrange the inspection work; 2. The present invention extracts the historical inspection times of key inspection sub-areas in multiple congestion periods from the inspection log, constructs an inspection times change curve, and compares and analyzes it with the congestion times change curve of the existing key inspection sub-areas. The proportion of negative correlation periods in all historical periods and the discrete degree of the slope ratio of the inspection sub-curve and the congestion sub-curve in the negative correlation period reflect the close correlation between the inspection times and the congestion times in the historical period, which is conducive to optimizing the inspection strategy and adjusting the inspection frequency of key inspection sub-areas in a targeted manner. 3. The present invention sorts the key inspection sub-areas that generate negatively correlated close signals according to the periodic congestion frequency to obtain a sequence of the same inspection sub-areas. Within the sequence of the same inspection sub-areas, for each key inspection sub-area, find the congestion period with the least congestion in the historical period, mark the number of inspections corresponding to the period as the inspection basis value, sum and average the inspection basis values ​​corresponding to all key inspection sub-areas, and obtain the final inspection frequency, which provides a more reasonable frequency reference for the inspection work in the rail protection area, avoids blind inspections, and solves the problem of how to reasonably allocate inspection resources according to the congestion and inspection correlation of different key inspection sub-areas in the rail transit protection area. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 It is a flow chart of an automatic inspection method of a rail transit protection zone based on artificial intelligence of the present invention; Figure 2 It is a schematic diagram of an automatic patrol system for rail transit protection areas based on artificial intelligence of the present invention; Figure 3 The present invention is a schematic diagram of an automatic patrol device for a rail transit protection zone based on artificial intelligence. DETAILED DESCRIPTION

[0009] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0010] Embodiment 1 Figure 1 A flowchart of an artificial intelligence-based automatic patrol method for a rail transit protection zone provided in Embodiment 1 of the present invention. The embodiment of the present invention can be applied to reflect the congestion change law in a key patrol sub-area through the linear value of congestion change. The artificial intelligence-based automatic patrol method for a rail transit protection zone can be executed by an artificial intelligence-based automatic patrol system for a rail transit protection zone. The artificial intelligence-based automatic patrol system for a rail transit protection zone can be implemented by software and / or hardware. The artificial intelligence-based automatic patrol system for a rail transit protection zone can be configured in an artificial intelligence-based automatic patrol device for a rail transit protection zone. Optionally, an artificial intelligence-based automatic patrol device for a rail transit protection zone can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc. The embodiment of the present invention does not limit this.

[0011] like Figure 1 As shown, an embodiment of the present invention provides an automatic inspection method for a rail transit protection zone based on artificial intelligence, which specifically includes the following steps: Step 1: Import the design drawings of the drainage pipelines along the railway protection area into the panoramic navigation system, generate the pipeline inspection area, obtain the blockage data of the pipeline inspection area in the historical period, where the blockage data includes the blockage frequency, and compare it with the blockage frequency threshold to obtain the key inspection sub-area; In some embodiments, the design drawings of the drainage pipe are converted by image conversion in the panoramic navigation system to obtain the inspection pipe area; Divide the pipeline inspection area into a number of pipeline sub-areas of equal area; Divide the historical cycle into several historical periods with equal time intervals; Obtain the number of blockages in the pipeline sub-area during the historical period, and perform summation and mean calculation to obtain the periodic blockage frequency; The periodic blocking frequency is compared with the periodic blocking frequency threshold as follows: If the periodic blocking frequency is greater than or equal to the periodic blocking frequency threshold, it means that the analyzed pipeline sub-area has a high blocking frequency in the historical period, and it is marked as a key inspection sub-area; If the periodic blocking frequency is less than the periodic blocking frequency threshold, it means that the analyzed pipeline sub-area has a low blocking frequency in the historical period, and it is marked as a non-key inspection sub-area; Step 2: Analyze the changes in the number of congestion times in multiple key inspection sub-areas in the historical period to obtain the number of change data, where the number of change data includes the number of linear overlaps and the linear proximity value, quantify the number of change data, obtain the congestion change linear value, and compare it with the congestion change linear threshold. If the congestion change linear value is greater than or equal to the congestion change linear threshold, a linear change signal is generated; In some embodiments, a key inspection sub-area is arbitrarily selected; For the key inspection sub-areas, the historical periods where congestion occurred are marked as congestion periods; Mark the historical periods without congestion as non-congestion periods; A two-dimensional coordinate system is established, in which the x-axis represents time and the y-axis represents the number of congestion times. The number of congestion times in the key inspection sub-area during all congestion periods is substituted into the two-dimensional coordinate system to obtain a congestion times change curve; Connect the coordinates of the two endpoints of the congestion frequency variation curve to obtain a fitted congestion reference line; It should be noted that the coordinates of the two end points of the congestion frequency variation curve are not on the same horizontal line; Substitute the coordinates of the two endpoints of the congestion frequency change curve into the slope formula to obtain the slope corresponding to the fitted congestion reference line, and combine the coordinates of the two endpoints of the congestion frequency change curve to obtain the fitted congestion reference equation: ,in, denoted as the blocking reference slope, and b as a constant; Remove the two end point coordinates of the blocking times variation curve; Substitute the remaining endpoint X coordinates on the congestion frequency curve into the fitting congestion reference equation to obtain the fitting reference coordinates ( , ),in, It represents the Y coordinate on the fitted blockage reference line, x represents the X coordinate on the blockage number change curve, and e is the total number of X coordinates of the remaining endpoints on the aperture change curve; Exemplarily, endpoints with the same X coordinate are combined to obtain multiple groups of different Y combinations; It should be noted that the X coordinates of the endpoints in different Y combinations are the same, but the Y coordinates are different; Pick any different Y combination; Subtract the two different Y coordinates in different Y combinations, take the absolute value, and get the difference of different Y combinations; The difference of different Y combinations is calculated by Euclidean calculation formula to obtain the linear approximation value; The congestion frequency variation curve is divided into a number of congestion sub-curves of equal length, and the partial congestion sub-curves that overlap with the fitting comparison line are obtained, and the number of partial congestion sub-curves is counted, and the ratio is calculated with the total number of congestion sub-curves divided in the congestion frequency variation curve to obtain the number of linear overlaps; It should be noted that the congestion frequency change curve is divided according to each congestion period; The linear value of the blockage change is obtained by calculating the ratio of the linear overlap number to the linear proximity value; It can be explained that the meaning of the congestion change linear value is: a quantification of the closeness of the linear relationship between the congestion number change curve and the fitted congestion reference line, which comprehensively considers the two factors of curve fluctuation degree and local overlap. The number of linear overlaps reflects the overlap of the congestion number change curve with the fitted congestion reference line in the local interval, and the linear proximity value reflects the degree of deviation of the curve from the fitted congestion reference line. Combining the two, the congestion change linear value is obtained, which is conducive to identifying the congestion change law in the key inspection sub-area, so as to reasonably arrange the inspection work; The congestion change linear value is compared with the congestion change linear threshold value, and the process is as follows: If the congestion change linear value is greater than or equal to the congestion change linear threshold, it means that the difference between the congestion number change curve and the fitted congestion reference line is large, and the local overlap degree is high, and a linear change signal is generated; If the congestion change linear value is less than the congestion change linear threshold, it means that the difference between the congestion number change curve and the fitted congestion reference line is small, and the local overlap is low, generating a nonlinear change signal; Based on the nonlinear change signal, the number of times the key inspection area is blocked during the blocking period is obtained, and the number of times the maximum blocking occurs during the blocking period is extracted as the inspection frequency of the key inspection area; The specific implementation plan of the embodiment of the present invention is: by obtaining the frequency mean of the pipeline sub-area in the historical period, the key inspection sub-area is identified, the change of the number of blockages in the key inspection sub-area in the historical period is analyzed to obtain the number change data, the number change data is quantified to obtain the linear value of the blockage change, and the linear value of the blockage change is used to reflect the blockage change law in the key inspection sub-area, so as to reasonably arrange the inspection work.

[0012] Embodiment 2 The embodiment of the present invention provides an automatic inspection method for a rail transit protection zone based on artificial intelligence, which specifically includes the following steps: Step 3: Based on the linear change signal, historical inspection data of multiple key inspection sub-areas in multiple congestion periods are extracted through inspection logs, where the historical inspection data includes the number of historical inspections. The historical inspection data is correlated with the congestion data to obtain a correlation closeness value, which is compared with the correlation closeness threshold. If the correlation closeness value is greater than or equal to the correlation closeness threshold, a negative correlation closeness signal is generated. In some embodiments, a key inspection sub-area is arbitrarily selected; With the x-axis representing time and the y-axis representing the number of inspections, a two-dimensional coordinate system is established to obtain the historical number of inspections of the key inspection sub-areas in multiple congestion periods and substitute it into the two-dimensional coordinate system to obtain the inspection number change curve; Compare and analyze the inspection frequency change curve with the congestion frequency change curve. The process is as follows: The inspection frequency variation curve is divided in the same way as the congestion frequency variation curve, to obtain a number of inspection sub-curves, wherein the number of inspection sub-curves is the same as the number of congestion sub-curves; Randomly select a patrol sub-curve and obtain the slope of the patrol sub-curve; At the same time, a congestion sub-curve in the same congestion period as the patrol sub-curve is obtained, and the slope of the congestion sub-curve is obtained; Compare the slope of the inspection sub-curve with the slope of the blocking sub-curve. The process is as follows: If the slope of the inspection sub-curve is of the same sign as the slope of the congestion sub-curve, it means that the number of inspections during the analyzed congestion period needs to be increased; If the slope of the inspection sub-curve is different from the slope of the congestion sub-curve in terms of positive and negative, it means that the number of congestion decreases with the increase in the number of inspections during the analyzed congestion period, and the analyzed congestion period is marked as a negative correlation period; Count the number of negatively correlated periods and calculate the ratio with the total number of historical periods in the historical cycle to obtain the number of negative correlations; Extract the slope of the inspection sub-curve and the slope of the blocking sub-curve in the negative correlation period, and calculate the ratio to obtain the negative correlation coefficient; The variance of the negative correlation coefficient is calculated to obtain the negative correlation closeness value; The ratio of the number of negative correlations to the negative correlation closeness value is calculated to obtain the unit closeness value; The unit density values ​​corresponding to all key inspection sub-areas are summed and averaged to obtain the correlation density value; It can be understood that the meaning of the correlation closeness value is: it is used to measure the correlation closeness between the number of inspections and the number of congestion in the historical period, by combining the proportion of negative correlation periods in all historical periods (reflected by the negative correlation quantity) and the discreteness of the slope ratio of the inspection sub-curve and the congestion sub-curve in the negative correlation period (reflected by the negative correlation closeness value). Specifically, a higher negative correlation quantity indicates that in more periods, increasing the number of inspections is effective in reducing the number of congestion, and a smaller negative correlation closeness value indicates that in the negative correlation period, the ratio of the slope of the inspection sub-curve to the slope of the congestion sub-curve is relatively stable; The close association value is compared with the close association threshold, and the process is as follows; If the correlation closeness value is greater than or equal to the correlation closeness threshold, it means that the negative correlation period accounts for a high proportion of the total period, and the negative correlation between the number of inspections and the number of congestion is relatively close, generating a negative correlation closeness signal; If the correlation closeness value is less than the correlation closeness threshold, it means that the negative correlation period accounts for a high proportion of the total period, and the negative correlation between the number of inspections and the number of congestion is not close, generating a non-negative correlation closeness signal; The specific implementation plan of the embodiment of the present invention is: extract the historical inspection times of key inspection sub-areas in multiple congestion time periods from the inspection log, construct an inspection times change curve, and compare and analyze it with the congestion times change curve of the existing key inspection sub-areas. The proportion of negative correlation time periods in all historical time periods and the discrete degree of the slope ratio of the inspection sub-curve and the congestion sub-curve in the negative correlation time period reflect the close correlation between the inspection times and the congestion times in the historical period, which is conducive to optimizing the inspection strategy and adjusting the inspection frequency of key inspection sub-areas in a targeted manner.

[0013] Embodiment 3 Step 4: Summarize the key inspection sub-areas that generate negative correlation signals to obtain a sequence of the same inspection sub-areas. Based on the sequence of the same inspection sub-areas, obtain the inspection frequency and complete the inspection of the key inspection sub-areas in the sequence of the same inspection sub-areas. In some embodiments, the key inspection sub-areas generating the negative correlation close signal are sorted according to the periodic congestion frequency to obtain a sequence of the same inspection sub-areas; In the same inspection sub-area series, randomly select a key inspection sub-area; Obtain the congestion period with the least congestion in the key inspection sub-area during the historical period and mark it as the period with the least congestion; Mark the number of inspections corresponding to the period with the least congestion as the inspection basis value; The inspection basis values ​​corresponding to all key inspection sub-areas are summed and averaged to obtain the inspection frequency; The obtained patrol frequency provides a more reasonable frequency reference for patrol work in the rail protection area, avoiding blind patrols and solving the problem of how to reasonably allocate patrol resources according to the congestion and patrol correlation of different key patrol sub-areas in the rail transit protection area; The specific implementation plan of the embodiment of the present invention is: the key patrol sub-areas that generate negatively correlated close signals are sorted according to the periodic congestion frequency to obtain a sequence of the same patrol sub-areas. Within the sequence of the same patrol sub-areas, for each key patrol sub-area, the congestion period with the least number of congestion in the historical period is found, and the number of patrols corresponding to the period is marked as the patrol basis value. The patrol basis values ​​corresponding to all key patrol sub-areas are summed and averaged to obtain the final patrol frequency, which provides a more reasonable frequency reference for the patrol work in the rail protection area, avoids blind patrols, and solves the problem of how to reasonably allocate patrol resources in the rail transit protection area according to the congestion and patrol correlation of different key patrol sub-areas.

[0014] Embodiment 4 like Figure 2 The embodiment of the present invention provides an automatic inspection system for a rail transit protection zone based on artificial intelligence, comprising: Key inspection screening module: Extract the drainage pipeline drawings along the route through the panoramic navigation system to generate inspection pipeline areas, analyze the blockage data of the inspection pipeline areas in the historical period, and obtain key inspection sub-areas; Congestion linear analysis module: Analyze the changes in the number of congestion times in the key inspection sub-areas in the historical period, obtain the number of change data, quantify the number of change data, and obtain a linear change signal; Close correlation analysis module: Based on the linear change signal, the historical inspection data of multiple key inspection sub-areas are extracted from the inspection log, and the historical inspection data is correlated with the congestion data to obtain a negative correlation signal; Inspection strategy adjustment module: summarize the key inspection sub-areas that generate negative correlation signals, obtain the same inspection sub-area sequence, obtain the inspection frequency, and complete the inspection work of the key inspection sub-areas in the same inspection sub-area sequence.

[0015] Embodiment 5 Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, an automatic inspection method for a rail transit protection zone based on artificial intelligence as described in any one of the above methods is implemented.

[0016] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0017] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0018] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0019] Embodiment 6 An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, an automatic inspection method for a rail transit protection zone based on artificial intelligence as described in any one of the above methods is implemented.

[0020] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0021] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0022] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0023] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0024] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0025] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0026] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An automatic inspection method for rail transit protection areas based on artificial intelligence, characterized in that: The following steps are involved: Obtain the pipeline inspection area, analyze the blockage data of the pipeline inspection area in the historical period, and obtain the key inspection sub-area; Analyze the changes in the number of congestion times in multiple key inspection sub-areas during the historical period, obtain the linear proximity value and the number of linear overlaps, perform quantitative processing, and generate a linear change signal; Extract historical inspection data of multiple key inspection sub-areas, perform correlation analysis on the historical inspection data and the congestion data, obtain the unit density value, and compare it with the unit density threshold to generate a negative correlation density signal; The key inspection sub-areas with close negative correlation signals are summarized to obtain the sequence of the same inspection sub-areas, obtain the inspection frequency, and complete the inspection work of the key inspection sub-areas in the sequence of the same inspection sub-areas.

2. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The key inspection sub-areas are obtained as follows: Divide the pipeline inspection area into a number of pipeline sub-areas of equal area; Obtain the congestion frequency of pipeline sub-areas in the historical period; record pipeline sub-areas that exceed the congestion frequency threshold as key inspection sub-areas.

3. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The analysis process of the linear approximation value is: Randomly select a key inspection sub-area; Mark the historical periods where congestion occurred as congestion periods; Construct a curve of the number of congestion changes over time; Connect the coordinates of the two endpoints of the congestion frequency variation curve to obtain a fitted congestion reference line, and obtain the slope to obtain a fitted congestion reference equation; Remove the two endpoint coordinates of the congestion frequency change curve, and substitute the remaining endpoint X coordinates into the fitting congestion reference equation to obtain the fitting reference coordinates; Combine two different Y coordinates corresponding to the endpoints and the X coordinates to obtain multiple groups of different Y combinations; Randomly select a different Y combination, make a difference between two different Y coordinates, take the absolute value, and calculate the difference of different Y combinations using the Euclidean calculation formula to obtain the linear approximation value.

4. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The analysis process of the number of linear coincidences is: The congestion frequency variation curve is divided into several congestion sub-curves of equal length, and the partial congestion sub-curves that overlap with the fitting comparison line are obtained. The proportion of the partial congestion sub-curves is counted to obtain the linear overlap number.

5. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The linear change signal generation process is as follows: The linear value of the blockage change is obtained by calculating the ratio of the linear overlap number to the linear proximity value; If the congestion change linear value is greater than or equal to the congestion change linear threshold, a linear change signal is generated.

6. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The historical inspection data and congestion data are correlated and analyzed. The process is as follows: Randomly select key inspection sub-areas; Construct a patrol frequency variation curve and divide it into several patrol sub-curves; Get the slope of any patrol sub-curve; At the same time, the slope of a congestion sub-curve in the same congestion period as the patrol sub-curve is obtained; If the slope of the inspection sub-curve is different from the slope of the congestion sub-curve in terms of positive and negative sign, the congestion period under analysis will be recorded as a negative correlation period.

7. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 6 is characterized in that: The analysis process of the unit compactness value is as follows: Count the percentage of negatively correlated periods; Extract the slope of the inspection sub-curve and the slope of the blocking sub-curve in the negative correlation period, and calculate the ratio to obtain the negative correlation coefficient; The variance of the negative correlation coefficient is calculated to obtain the negative correlation closeness value; The ratio of the number of negative correlations to the negative correlation closeness value is calculated to obtain the unit closeness value.

8. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 7 is characterized in that: The process of generating a negative correlation close signal is as follows: The unit density values ​​corresponding to all key inspection sub-areas are summed and averaged to obtain the correlation density value; If the correlation closeness value is greater than or equal to the correlation closeness threshold, a negative correlation closeness signal is generated.

9. The method for automatic inspection of rail transit protection areas based on artificial intelligence according to claim 1 is characterized in that: The sequence of sub-areas with the same inspection is obtained by induction, and the inspection frequency is obtained. The process is as follows: According to the periodic blocking frequency, the key inspection sub-areas with close negative correlation signals are summarized to obtain the same inspection sub-area sequence, and a key inspection sub-area is randomly selected; The congestion period with the least number of congestion is recorded as the least congestion period, and the corresponding number of inspections is used as the inspection basis value; The inspection basis values ​​corresponding to all key inspection sub-areas are summed and averaged to obtain the inspection frequency.

10. An automatic inspection device for rail transit protection areas based on artificial intelligence, characterized in that: The device includes: Key inspection screening module: obtain the inspection pipeline area, analyze the blockage data of the inspection pipeline area in the historical period, and obtain the key inspection sub-area; Congestion linear analysis module: Analyze the changes in the number of congestion times in multiple key inspection sub-areas in the historical period, obtain the linear proximity value and the number of linear overlaps, perform quantitative processing, and generate a linear change signal; Correlation closeness analysis module: extracts historical inspection data of multiple key inspection sub-areas, performs correlation analysis on the historical inspection data and the congestion data, obtains the unit closeness value, and compares it with the unit closeness threshold to generate a negative correlation closeness signal; Inspection strategy adjustment module: summarize the key inspection sub-areas with close negative correlation signals, obtain the sequence of the same inspection sub-areas, obtain the inspection frequency, and complete the inspection work of the key inspection sub-areas in the sequence of the same inspection sub-areas.

Images