A method, an electronic device, and a storage medium for detecting abnormal behaviors of a driver

Abstract

The present invention provides a method for detecting abnormal behaviors of a driver, an electronic device, and a storage medium, relating to the technical field of abnormal behavior detection. The method determines a first duration from a departure location to an initial intersection, a second duration from the initial intersection to a destination location, and a third duration from the departure location to the initial intersection and then from the initial intersection to the destination location based on an estimated driving duration and an estimated parking duration, obtains a target path according to the A* algorithm, the first duration, the second duration, and the third duration, and determines whether there are abnormal behaviors of the driver during the process of driving the target vehicle from the departure location to the destination location according to the actual driving duration of the driver driving the target vehicle from the departure location to the destination location and the estimated driving duration of the driver driving the target vehicle from the departure location to the destination location along the target path, which is beneficial to improving the accuracy of the result of detecting whether there are abnormal behaviors of the driver during the process of driving the target vehicle from the departure location to the destination location.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal behavior detection, and particularly to a method for detecting abnormal behavior of a driver, an electronic device, and a storage medium. Background Art

[0002] In the prior art, most of the methods for detecting whether there is abnormal behavior of a driver during the process of driving a target vehicle from a starting point to a destination are as follows: obtaining the optimal path from the starting point to the destination according to the A* algorithm, obtaining the estimated vehicle passing duration according to the vehicle driving distance corresponding to the optimal path and the average vehicle speed of all vehicles passing through the optimal path within a preset time period, and determining whether there is abnormal behavior of the driver during the process of driving the target vehicle from the starting point to the destination according to the actual passing duration of the target vehicle along the optimal path from the starting point to the destination and the estimated vehicle passing duration.

[0003] However, the above method also has the following technical problems:

[0004] When using the A* algorithm to obtain the optimal path in the prior art, only the road distance of the path or the driving duration of the vehicle is used to determine the actual cost and the heuristic cost, ignoring the parking duration of the vehicle in the path. Therefore, the accuracy of the optimal path obtained by the above method is relatively low. Consequently, the accuracy of the result of detecting whether there is abnormal behavior of the driver during the process of driving the target vehicle from the starting point to the destination according to the above method is also relatively low. Summary of the Invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is as follows:

[0006] According to a first aspect of the present invention, there is provided a method for detecting abnormal behavior of a driver, which is used to detect whether there is abnormal behavior of the driver during the process of driving a target vehicle from a starting point to a destination. The method includes the following steps:

[0007] S1. Taking the sum of the first duration from the starting point to the initial intersection and the second duration from the initial intersection to the destination as the third duration from the starting point to the initial intersection and then from the initial intersection to the destination. Among them, taking the sum of the estimated driving duration from the starting point to the initial intersection and the estimated parking duration from the starting point to the initial intersection as the first duration from the starting point to the initial intersection, and taking the sum of the estimated driving duration from the initial intersection to the destination and the estimated parking duration from the initial intersection to the destination as the second duration from the initial intersection to the destination. The initial intersection is the intersection in the initial path, and the initial path is the path from the starting point to the destination.

[0008] S2. Using the A* algorithm to calculate the first duration, the second duration, and the third duration to obtain the target path B from the starting point to the destination.

[0009] S3. Obtain the actual driving duration C of the driver's current driving target vehicle from the departure location to the destination location.

[0010] S4. When C ≤ D, it is determined that the driver has no abnormal behavior during the process of driving the target vehicle from the departure location to the destination location. When C > D, it is determined that the driver has abnormal behavior during the process of driving the target vehicle from the departure location to the destination location, where D is the estimated driving duration for the driver to drive the target vehicle from the departure location to the destination location along B.

[0011] According to the second aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing a computer program, which is loaded and executed by a processor to implement the foregoing method.

[0012] According to the third aspect of the present invention, there is provided an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where the processor implements the foregoing method when executing the computer program.

[0013] The present invention has at least the following beneficial effects:

[0014] The present invention provides a method for detecting abnormal behavior of a driver, an electronic device, and a storage medium. The method takes the sum of the estimated driving duration from the departure location to the initial intersection and the estimated parking duration from the departure location to the initial intersection as the first duration from the departure location to the initial intersection, takes the sum of the estimated driving duration from the initial intersection to the destination location and the estimated parking duration from the initial intersection to the destination location as the second duration from the initial intersection to the destination location, and takes the sum of the first duration from the departure location to the initial intersection and the second duration from the initial intersection to the destination location as the third duration from the departure location to the initial intersection and then from the initial intersection to the destination location. The A* algorithm is used to calculate the first duration, the second duration, and the third duration to obtain the target path from the departure location to the destination location, obtain the actual driving duration of the driver's current driving target vehicle from the departure location to the destination location, and determine whether the driver has abnormal behavior during the process of driving the target vehicle from the departure location to the destination location according to the actual driving duration and the estimated driving duration for the driver to drive the target vehicle from the departure location to the destination location along the target path, which is beneficial to improving the accuracy of the obtained target path, and further beneficial to improving the accuracy of the result of detecting whether the driver has abnormal behavior during the process of driving the target vehicle from the departure location to the destination location. Description of the Drawings

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of a method for detecting abnormal behaviors of a driver provided by an embodiment of the present invention. Specific embodiments

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0018] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar tasks and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0019] The embodiments of the present invention provide a method for detecting abnormal behaviors of a driver. The method is used to detect whether there are abnormal behaviors of the driver during the process of driving a target vehicle from a starting point to a destination. The method includes the following steps, as Figure 1 shown:

[0020] S1. Take the sum of the first duration from the starting point to the initial intersection and the second duration from the initial intersection to the destination point as the third duration from the starting point to the initial intersection and then from the initial intersection to the destination point. Among them, take the sum of the estimated driving duration from the starting point to the initial intersection and the estimated parking duration from the starting point to the initial intersection as the first duration from the starting point to the initial intersection, and take the sum of the estimated driving duration from the initial intersection to the destination point and the estimated parking duration from the initial intersection to the destination point as the second duration from the initial intersection to the destination point. The initial intersection is the intersection in the initial path, and the initial path is the path from the starting point to the destination point. Those skilled in the art know that those skilled in the art can obtain the estimated driving duration from the starting point to the initial intersection and the estimated driving duration from the initial intersection to the destination point from the map application program, which will not be elaborated here.

[0021] Specifically, in step S1, the following sub-steps S11 - S14 are further included:

[0022] S11. Obtain the initial road segment ID list E = {E1, E2, ……, E i , ……, E m}, E i = {E i1 , E i2 , ……, E ij , ……, E in(i)}, E i is the initial road segment ID list corresponding to the i-th initial path, the value range of i is from 1 to m, m is the number of initial paths, and E ij is the j-th initial road segment ID corresponding to the i-th initial path, the value of j ranges from 1 to n(i), and n(i) is the number of initial road segment IDs corresponding to the i-th initial path.

[0023] Specifically, the initial road segment ID is the unique identity identifier of the initial road segment.

[0024] Specifically, the i-th initial path includes n(i) - 1 initial intersections.

[0025] Specifically, when j = 1, the initial road segment corresponding to E ij is the road segment between the starting point and the first initial intersection in the i-th initial path. When 1 < j < n(i), the initial road segment corresponding to E ij is the road segment between the (j - 1)-th initial intersection and the j-th initial intersection in the i-th initial path. When j = n(i), E ijis the road section between the (n(i)-1)-th initial intersection and the destination in the i-th initial path; for example, if n(i)=5, there are 5 initial road sections and 4 initial intersections in the i-th initial path, and the value range of j is from 1 to 4. When j = 1, E ij The corresponding initial road section is the 1st initial road section in the i-th initial path, that is, the road section between the starting point and the 1st initial intersection in the i-th initial path. When j = 2, E ij The corresponding initial road section is the 2nd initial road section in the i-th initial path, that is, the road section between the 1st initial intersection and the 2nd initial intersection in the i-th initial path. When j = 3, E ij The corresponding initial road section is the 3rd initial road section in the i-th initial path, that is, the road section between the 2nd initial intersection and the 3rd initial intersection in the i-th initial path. When j = 4, E ij The corresponding initial road section is the 4th initial road section in the i-th initial path, that is, the road section between the 3rd initial intersection and the 4th initial intersection in the i-th initial path. When j = 5, E ij The corresponding initial road section is the 5th initial road section in the i-th initial path, that is, the road section between the 4th initial intersection and the destination in the i-th initial path.

[0026] S12. Obtain the initial parking area ID list F = {F1, F2, ……, F r , ……, F s}, where F r is the r-th initial parking area ID, the value range of r is from 1 to s, s is the number of initial parking area IDs, the initial parking area ID is the unique identity of the initial parking area, and the initial parking area is the geographical area where parking is allowed within the target geographical area, which can be understood as: the geographical area where the parking facilities around commercial places such as shopping malls and restaurants are located within the target geographical area, and the target geographical area is the rectangular geographical area covered by all initial paths.

[0027] S13. Obtain the first average parking duration T ij corresponding to E ij .

[0028] Specifically, step S13 also includes the following sub-steps S131 - S136:

[0029] S131. Obtain the road vertical distance G r between the initial parking area corresponding to F ij and the initial road section corresponding to E r ij , where the road vertical distance G r ijF r The center point of the corresponding initial parking area to E ij The vertical distance of the center line of the corresponding initial road segment, where the center line of the initial road segment is a straight line passing through the center point of the initial road segment and parallel to the straight line where the roadside of the initial road segment is located.

[0030] S132, according to G r ij Get E ij Corresponding intermediate parking area ID list Z ij ={Z 1 ij , Z 2 ij , ..., Z x ij , ..., Z p(ij) ij}, Z x ij For E ij The corresponding intermediate parking area ID of the xth intermediate parking area, x ranges from 1 to p(ij), p(ij) is E ij The number of corresponding intermediate parking areas, where G r ij F r When the minimum value of the road vertical distance between the initial parking area corresponding to the initial road segment ID and the initial road segment ID corresponding to all initial road segment IDs is reached, E ij The center line of the corresponding initial section to F r The straight-line distance of the center point of the corresponding initial parking area is G r ij The point is E ij The center point of the corresponding middle parking area is G r ij as the radius of the intermediate parking area to obtain the intermediate parking area.

[0031] S133, obtain the target vehicle at Z x ij The total number of historical parking times H in the corresponding intermediate parking area x ij and the historical average parking time T x ij , where H x ij is the target vehicle in Z during the historical period x ij The total number of parking times in the corresponding intermediate parking area, T x ij is the target vehicle in Z during the historical period x ijThe total parking duration within the corresponding intermediate parking area is divided by H x ij to obtain the quotient; for example: if the target vehicle parked in the Z x ij corresponding intermediate parking area a total of 5 times during the historical time period, and the 5 parking durations are 20 minutes, 30 minutes, 10 minutes, 50 minutes, and 60 minutes respectively, then H x ij is 5, and the total parking duration of the target vehicle in the Z x ij corresponding intermediate parking area during the historical time period is 170 minutes, and T x ij is 34 minutes; those skilled in the art know that the length of the historical time period is set by those skilled in the art according to actual needs and will not be elaborated here.

[0032] S134. Perform normalization processing on H x ij and T x ij to obtain the normalized value H x ij corresponding to H 0x ij and the normalized value T x ij corresponding to T 0x ij , where those skilled in the art know that any normalization method in the prior art falls within the protection scope of the present invention and will not be elaborated here.

[0033] S135. Obtain the second average parking duration list L 0x ij corresponding to the key parking area of E 0x ij from H ij and T ij ={L 1 ij , L 2 ij , ……, L y ij , ……, L q(ij) ij}, where L y ij is the second average parking duration corresponding to the y-th key parking area of E ij , and the value of y ranges from 1 to q(ij), where q(ij) is the number of key parking areas corresponding to E ij . Among them, when H 0x ij +T 0xij When it is greater than TL, set Z x ij as E ij the corresponding key parking area and set T x ij as the second average parking duration corresponding to the key parking area. TL is a preset stay score. Those skilled in the art know that the preset stay score is set by those skilled in the art according to actual needs and will not be elaborated here.

[0034] S136. According to L y ij Obtain T ij , T ij meets the following conditions:

[0035] T ij =∑ q(ij) y=1 L y ij .

[0036] Through the above steps, obtain the road vertical distance between the initial parking area and the initial road segment, obtain the intermediate parking area corresponding to the initial road segment ID based on the road vertical distance, obtain the second average parking duration corresponding to the key parking area of the initial road segment ID according to the historical total parking times and historical average parking durations of the target vehicle in the intermediate parking area, and obtain the first average parking duration corresponding to the initial road segment ID according to the second average parking duration, which is beneficial to improving the accuracy of obtaining the first average duration. Furthermore, it is beneficial to improve the accuracy of obtaining the estimated parking duration from the departure location to the initial intersection and the estimated parking duration from the initial intersection to the destination location.

[0037] S14. When j≠n(i), obtain the estimated parking duration U ij from the departure location to the j-th initial intersection in the i-th initial path and the estimated parking duration V ij from the j-th initial intersection to the destination location in the i-th initial path according to T ij , where U ij meets the following conditions:

[0038] U ij =T i1 +T i2 +……+T ia +……+T ij , where T ia is the first average parking duration corresponding to E ia , E ia is the a-th initial road segment ID corresponding to the i-th initial path, and the value range of a is from 1 to j;

[0039] Vij Meet the following conditions:

[0040] V ij =T i(j+1) +T i(j+2) +……+T ib +……+T in(i) , where T ib is the first average parking duration corresponding to E ib , E ib is the b-th initial section ID corresponding to the i-th initial path, and the value range of b is from j + 1 to n(i); for example: if n(i) = 5 and j = 3, the estimated parking duration U from the starting point to the 3rd initial intersection in the i-th initial path i3 =T i1 +T i2 +T i3 , the estimated parking duration V from the 3rd initial intersection to the destination in the i-th initial path i3 =T i4 +T i5 .

[0041] Through the above steps, based on the initial section ID list and the initial parking area ID list, the first average parking duration corresponding to the initial section ID is obtained, and based on the first average duration, the estimated parking duration from the starting point to the initial intersection and the estimated parking duration from the initial intersection to the destination are obtained, which is beneficial to improving the accuracy of obtaining the estimated parking duration from the starting point to the initial intersection and the estimated parking duration from the initial intersection to the destination. Based on the estimated travel duration and the estimated parking duration, the first duration from the starting point to the initial intersection, the second duration from the initial intersection to the destination, and the third duration from the starting point to the initial intersection and then from the initial intersection to the destination are determined, and the target path is obtained according to the A* algorithm, the first duration, the second duration, and the third duration, which is beneficial to improving the accuracy of the obtained target path.

[0042] S2. Use the A* algorithm to calculate the first duration, the second duration, and the third duration to obtain the target path B from the starting point to the destination, where the target path is the path obtained by using the A* algorithm to calculate the first duration, the second duration, and the third duration; it can be understood that: taking the first duration as the actual cost in the A* algorithm, taking the second duration as the heuristic cost in the A* algorithm, and taking the third duration as the total cost in the A* algorithm and performing calculations to obtain the target path from the starting point to the destination.

[0043] Specifically, the alias of the A* algorithm is the A search algorithm.

[0044] S3. Obtain the actual driving duration C of the driver's current driving target vehicle from the departure location to the destination location.

[0045] S4. When C ≤ D, it is determined that the driver has no abnormal behavior during the process of driving the target vehicle from the departure location to the destination location; when C > D, it is determined that the driver has abnormal behavior during the process of driving the target vehicle from the departure location to the destination location, where D is the estimated driving duration for the driver to drive the target vehicle from the departure location to the destination location along B.

[0046] Specifically, the abnormal behavior includes detouring behavior and non-essential stopping behavior. Non-essential stopping behavior can be understood as the behavior of stopping when there is no need to stop.

[0047] Specifically, step S4 further includes the following sub-steps S41 - S45:

[0048] S41. Obtain E ij The corresponding average passing duration R ij , R ij Is equal to the length of the road section corresponding to E ij Divided by the average vehicle speed of E ij The corresponding road section length is the length of the initial road section corresponding to E ij The corresponding average vehicle speed is the average value of the vehicle speeds of all vehicles passing through the initial road section corresponding to E on the same day. ij The corresponding road section length is the length of the initial road section corresponding to E ij The corresponding average vehicle speed is the average value of the vehicle speeds of all vehicles passing through the initial road section corresponding to E on the same day. ij The corresponding average vehicle speed is the average value of the vehicle speeds of all vehicles passing through the initial road section corresponding to E on the same day.

[0049] S42. If the total parking duration of the target vehicle in the y-th key parking area corresponding to E within the historical time slice is 0, then the historical time slice is used as the non-stopping time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period, and the length of the time slice in the historical time period is 1 day. ij The corresponding total parking duration in the y-th key parking area is 0, then the historical time slice is used as the non-stopping time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period, and the length of the time slice in the historical time period is 1 day. ij The corresponding total parking duration in the y-th key parking area is 0, then the historical time slice is used as the non-stopping time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period, and the length of the time slice in the historical time period is 1 day.

[0050] S43. Obtain the parking weight value W of the target vehicle when parking in the y-th key parking area corresponding to E ij The corresponding parking weight value W of the target vehicle when parking in the y-th key parking area corresponding to E y ij , W y ij Is equal to the number of non-stopping time slices corresponding to the y-th key parking area corresponding to E divided by the number of historical time slices. ij The corresponding parking weight value W of the target vehicle when parking in the y-th key parking area corresponding to E is equal to the number of non-stopping time slices corresponding to the y-th key parking area corresponding to E divided by the number of historical time slices.

[0051] S44. According to R ij , W y ij And L y ij Obtain E iThe corresponding estimated travel time TX i , TX i meets the following conditions:

[0052] TX i =∑ n(i) j=1 (R ij +∑ q(ij) y=1 W y ij ×L y ij ).

[0053] S45. When the target path is the same as the initial path corresponding to E i , determine D = TX i .

[0054] Through the above steps, the average travel duration corresponding to the initial section ID and the parking weight value of the target vehicle parked in the key parking area corresponding to the initial section ID are obtained. Based on the average travel duration corresponding to the initial section ID, the parking weight value of the target vehicle parked in the key parking area corresponding to the initial section ID, and the second average parking duration corresponding to the key parking area of the initial section ID, the estimated travel time corresponding to the initial path is obtained. The estimated travel time corresponding to the initial path that is the same as the target path is used as the estimated travel duration for the driver to drive the target vehicle from the departure location to the destination along the target path, which is beneficial to improving the accuracy of the estimated travel duration. According to the actual travel duration of the driver currently driving the target vehicle from the departure location to the destination and the estimated travel duration of the driver driving the target vehicle from the departure location to the destination along the target path, it is determined whether there is any abnormal behavior of the driver during the process of driving the target vehicle from the departure location to the destination, which is beneficial to improving the accuracy of the result of detecting whether there is any abnormal behavior of the driver during the process of driving the target vehicle from the departure location to the destination.

[0055] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store a computer program related to a method in the method embodiment. The computer program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0056] An embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method provided in the above embodiment is implemented.

[0057] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product runs on an electronic device, the program code is used to cause the electronic device to execute the steps in the methods according to various exemplary embodiments of the present invention described above in this specification.

[0058] The present invention provides a method for detecting abnormal behavior of a driver, an electronic device, and a storage medium. The method takes the sum of the estimated driving duration from the starting point to the initial intersection and the estimated parking duration from the starting point to the initial intersection as the first duration from the starting point to the initial intersection, takes the sum of the estimated driving duration from the initial intersection to the destination and the estimated parking duration from the initial intersection to the destination as the second duration from the initial intersection to the destination, and takes the sum of the first duration from the starting point to the initial intersection and the second duration from the initial intersection to the destination as the third duration from the starting point to the initial intersection and then from the initial intersection to the destination. The A* algorithm is used to calculate the first duration, the second duration, and the third duration to obtain the target path from the starting point to the destination. The actual driving duration of the driver driving the target vehicle from the starting point to the destination is obtained, and it is determined whether there is abnormal behavior of the driver during the process of driving the target vehicle from the starting point to the destination according to the actual driving duration and the estimated driving duration of the driver driving the target vehicle along the target path from the starting point to the destination. This is beneficial to improving the accuracy of the obtained target path, and further beneficial to improving the accuracy of the result of detecting whether there is abnormal behavior of the driver during the process of driving the target vehicle from the starting point to the destination.

[0059] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are only for illustration and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for detecting abnormal behavior of a driver, which is used to detect whether there is abnormal behavior of the driver during the process of driving a target vehicle from a starting point to a destination point, and is characterized in that, The method includes the following steps: S1. Take the sum of the first duration from the departure location to the initial intersection and the second duration from the initial intersection to the destination location as the third duration from the departure location to the initial intersection and then from the initial intersection to the destination location. Among them, take the sum of the estimated driving duration from the departure location to the initial intersection and the estimated parking duration from the departure location to the initial intersection as the first duration from the departure location to the initial intersection, and take the sum of the estimated driving duration from the initial intersection to the destination location and the estimated parking duration from the initial intersection to the destination location as the second duration from the initial intersection to the destination location. The initial intersection is the intersection in the initial path, and the initial path is the path from the departure location to the destination location. Obtain the estimated driving duration from the departure location to the initial intersection and the estimated driving duration from the initial intersection to the destination location from the map application. In step S1, it further includes the following sub-steps S11 - S14: S11. Obtain the initial road segment ID list E = {E1, E2, ……, E i , ……, E m}, E i = {E i1 , E i2 , ……, E ij , ……, E in(i)}, E i is the initial road segment ID list corresponding to the i-th initial path, where the value range of i is from 1 to m, and m is the number of initial paths. E ij is the j-th initial road segment ID corresponding to the i-th initial path, where the value of j is from 1 to n(i), and n(i) is the number of initial road segment IDs corresponding to the i-th initial path; S12. Obtain the list of initial parking area IDs \(F = \{F_1, F_2, \ldots, F r , \ldots, F s \}\), where \(F r \) is the \(r\)-th initial parking area ID, \(r\) ranges from 1 to \(s\), \(s\) is the number of initial parking area IDs, and the initial parking area is the geographical area where parking is permitted within the target geographical area, and the target geographical area is the rectangular geographical area covered by all the initial paths; S13. Obtain E based on F and E ij The corresponding first average parking duration T ij ; S14. When j ≠ n(i), according to T ij Obtain the estimated parking duration U from the departure location to the j-th initial intersection in the i-th initial path ij and the estimated parking duration V from the j-th initial intersection to the destination location in the i-th initial path ij , where U ij meets the following conditions: U ij =T i1 +T i2 +……+T ia +……+T ij ,where T ia is the first average parking duration corresponding to E ia ,E ia is the a-th initial road section ID corresponding to the i-th initial path, and the value range of a is from 1 to j; V ij Meet the following conditions: V ij = T i(j+1) + T i(j+2) + …… + T ib + …… + T in(i) , where T ib is the first average parking duration corresponding to E ib and E ib is the ID of the b-th initial road segment corresponding to the i-th initial path, and the value range of b is from j + 1 to n(i); S2. Use the A* algorithm to calculate the first duration, the second duration, and the third duration to obtain the target path B from the departure location to the destination location. Take the first duration as the actual cost in the A* algorithm, take the second duration as the heuristic cost in the A* algorithm, and take the third duration as the total cost in the A* algorithm and calculate to obtain the target path from the departure location to the destination location; S3. Obtain the actual driving duration C of the driver currently driving the target vehicle from the departure location to the destination location; S4. When C ≤ D, determine that there is no abnormal behavior of the driver during the process of driving the target vehicle from the departure location to the destination location. When C > D, determine that there is abnormal behavior of the driver during the process of driving the target vehicle from the departure location to the destination location. Among them, D is the estimated driving duration for the driver to drive the target vehicle from the departure location to the destination location along B.

2. The abnormal behavior detection method for a driver according to claim 1, characterized in that, The i-th initial path includes n(i) - 1 initial intersections.

3. The abnormal behavior detection method for a driver according to claim 2, characterized in that When j = 1, E ij The corresponding initial road segment is the road segment between the starting point and the first initial intersection in the i-th initial path. When 1 < j < n(i), E ij The corresponding initial road segment is the road segment between the (j - 1)-th initial intersection and the j-th initial intersection in the i-th initial path. When j = n(i), E ij Is the road segment between the (n(i) - 1)-th initial intersection and the destination in the i-th initial path.

4. The abnormal behavior detection method for a driver according to claim 1, characterized in that, In step S13, it further includes the following sub-steps S131 - S136: S131. Obtain F r The vertical distance G between the corresponding initial parking area and the initial road section of E ij where the vertical distance G of the road r ij is the vertical distance from the center point of the initial parking area corresponding to F to the center line of the initial road section of E r ij for F r and the center line of the initial road section is a straight line passing through the center point of the initial road section and parallel to the straight line where the roadside of the initial road section is located; ij ​ S132. Obtain E according to G r ij to obtain the corresponding intermediate parking area ID list Z ij ={Z ij 1 ij , Z 2 ij , ……, Z x ij , ……, Z p (ij) ij x}, where Z ij ij is the intermediate parking area ID of the x-th intermediate parking area corresponding to E, and the value range of x is from 1 to p(ij), and p(ij) is the number of intermediate parking areas corresponding to E. Among them, when G ij r ij is the minimum value among the road vertical distances between the initial parking area corresponding to F r and all the initial road segments corresponding to the initial road segment IDs, the point with the straight-line distance from the center line of the initial road segment corresponding to E ij to the center point of the initial parking area corresponding to F r being G r ij is used as the center point of the intermediate parking area corresponding to E, and G ij r ij is used as the radius of the intermediate parking area to obtain the intermediate parking area;​​​​ S133. Obtain the total historical parking times H x ij and the historical average parking duration T x ij in the corresponding intermediate parking area of the target vehicle, where x ij H x ij is the total parking times of the target vehicle in the corresponding intermediate parking area within the historical time period, and T x ij is the quotient obtained by dividing the total parking duration of the target vehicle in the corresponding intermediate parking area within the historical time period by H x ij ; x ij x ij ​​ S134. Normalize H x ij and T x ij to obtain the normalized values H x ij corresponding to H 0x ij and T x ij corresponding to the normalized value T 0x ij ; S135. Obtain the second average parking duration list L corresponding to the key parking area corresponding to E according to H 0x ij and T 0x ij Obtain E ij The second average parking duration list L corresponding to the corresponding key parking area ij ={L 1 ij ,L 2 ij ,……,L y ij ,……,L q(ij) ij},where L y ij is the second average parking duration corresponding to the y-th key parking area corresponding to E, and the value of y ranges from 1 to q(ij), where q(ij) is the number of key parking areas corresponding to E. Among them, when H ij ij 0x +T ij 0x ij > TL, take Z x ij as the key parking area corresponding to E and take T ij x ij as the second average parking duration corresponding to the key parking area. TL is a preset stay score value;​​​ S136. According to L y ij Obtain T ij , T ij meets the following conditions: T ij =∑ q(ij) y=1 L y ij 。 5. The method for detecting abnormal behavior of a driver according to claim 4, characterized in that In step S4, it further includes the following sub-steps S41 - S45: S41. Obtain E ij The corresponding average passing time R ij , R ij is equal to E ij divided by the corresponding average vehicle speed of E ij , where the corresponding road segment length is the length of the initial road segment corresponding to E ij , and the corresponding average vehicle speed is the average value of the vehicle speeds of all vehicles passing through the initial road segment corresponding to E on the same day; ij The corresponding road segment length is the length of the initial road segment corresponding to E ij The corresponding average vehicle speed is the average value of the vehicle speeds of all vehicles passing through the initial road segment corresponding to E on the same day ij ; S42. If the total parking duration of the target vehicle in the y-th key parking area corresponding to E within the historical time slice is 0, then use the historical time slice as the non-staying time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period; ij If the total parking duration of the target vehicle in the y-th key parking area corresponding to E within the historical time slice is 0, then use the historical time slice as the non-staying time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period; ij If the total parking duration of the target vehicle in the y-th key parking area corresponding to E within the historical time slice is 0, then use the historical time slice as the non-staying time slice corresponding to the y-th key parking area corresponding to E. The historical time slice is a time slice in the historical time period; S43. Obtain the parking weight value W of the target vehicle when parking in the y-th key parking area corresponding to E ij where W y ij equals the number of non-stay time slices corresponding to the y-th key parking area corresponding to E divided by the number of historical time slices; y ij is equal to E ij ​ S44. Obtain the estimated travel time TX corresponding to R ij , W y ij and L y ij and obtain E i The corresponding estimated travel time TX i , TX i meets the following conditions: TX i =∑ n(i) j=1 (R ij +∑ q(ij) y=1 W y ij ×L y ij ); S45. When the target path is the same as the initial path corresponding to E i determine D = TX i .

6. The method for detecting abnormal behavior of a driver according to claim 5, wherein, The length of the time slice in the historical time period is 1 day.

7. The abnormal behavior detection method for a driver according to claim 1, characterized in that, Abnormal behavior includes detouring behavior and unnecessary staying behavior.

8. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is loaded and executed by a processor to implement the driver's abnormal behavior detection method as described in any one of claims 1 - 7.

9. An electronic device, comprising: A processor, a memory, and a computer program stored on the memory and executable on the processor, wherein the processor implements the driver's abnormal behavior detection method as described in any one of claims 1 - 7 when executing the computer program.

Images