A positioning method and apparatus, an electronic device, and a storage medium

Abstract

The application provides a positioning method and device, electronic equipment and storage medium, relates to the technical field of information processing, and can automatically locate the area where the abnormal preset behavior occurs. The method comprises the following steps: acquiring vehicle trajectory data to be analyzed; determining an analysis collection point in the vehicle trajectory data to be analyzed; for any analysis collection point, judging whether the analysis collection point is abnormal according to the position of the analysis collection point and the position of the existing preset behavior occurrence location; and positioning the abnormal preset behavior occurrence location based on the abnormal analysis collection point.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of information processing, and particularly relates to a positioning method and device, electronic equipment and storage medium. BACKGROUND

[0002] At present, in addition to some regular live pig processing enterprises, there are also some irregular live pig processing points (which can be called abnormal preset behavior occurrence places). In order to eliminate these abnormal preset behavior occurrence places, these abnormal preset behavior occurrence places need to be found out first, and then effective means can be used to close these abnormal preset behavior occurrence places. Thus, the number of abnormal preset behavior occurrence places can be effectively reduced.

[0003] However, since the abnormal preset behavior occurrence places are often very concealed, it is difficult to find them out. At present, the problem of being unable to automatically find out the abnormal preset behavior occurrence places still exists. SUMMARY

[0004] The present application provides a positioning method and device, electronic equipment and storage medium, which can automatically locate the area where the abnormal preset behavior occurrence place is located.

[0005] To achieve the above technical purposes, the present application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a positioning method, which comprises: first acquiring vehicle trajectory data to be analyzed; then determining an analysis collection point in the vehicle trajectory data to be analyzed; then, for any analysis collection point, judging whether the analysis collection point is abnormal according to the position of the analysis collection point and the position of the existing preset behavior occurrence place; and finally, based on the abnormal analysis collection point, positioning the abnormal preset behavior occurrence place.

[0007] The analysis collection point comprises a first collection point and / or a second collection point. One first collection point represents a round-trip critical point of one driving trajectory. One second collection point represents a target collection point in the change from transporting a target object to not transporting a target object or in the change from not transporting a target object to transporting a target object in one driving trajectory. The target collection point comprises a collection point of transporting a target object and / or a collection point of not transporting a target object.

[0008] It can be understood that the method provided by the embodiments of the present application first acquires vehicle trajectory data to be analyzed, and then determines a to-be-analyzed collection point in the vehicle trajectory data to be analyzed. The to-be-analyzed collection point can include a first collection point and / or a second collection point. One first collection point represents a round trip critical point of one driving trajectory, and the periphery of the round trip critical point of the driving trajectory can have an abnormal preset behavior occurrence location. One second collection point represents a target collection point in which a target object transported by a vehicle in one driving trajectory changes. Since the target object transported by the vehicle changes at the second collection point, it can be known that the vehicle can load or unload the target object near the second collection point, that is, the periphery of the second collection point can also have an abnormal preset behavior occurrence location. Therefore, for any to-be-analyzed collection point (that is, any first collection point or any second collection point), whether the to-be-analyzed collection point is abnormal can be determined according to the position of the to-be-analyzed collection point and the position of an existing preset behavior occurrence location.

[0009] The distance between the position of the to-be-analyzed collection point and the position of the existing preset behavior occurrence location can reflect whether there is an unknown abnormal preset behavior occurrence location in the periphery of the to-be-analyzed collection point. For example, the to-be-analyzed collection point is far away from an existing normal preset behavior occurrence location, and the vehicle to be analyzed still goes to the to-be-analyzed collection point, so the possibility that there is an abnormal preset behavior occurrence location in the periphery of the to-be-analyzed collection point is very high. For another example, the to-be-analyzed collection point is close to an existing abnormal preset behavior occurrence location, and the vehicle to be analyzed still goes to the to-be-analyzed collection point, so the possibility that the abnormal preset behavior occurrence location close to the to-be-analyzed collection point is still in a working state is very high, that is, the possibility that there is an abnormal preset behavior occurrence location in the periphery of the to-be-analyzed collection point is very high. Therefore, according to the distance between the to-be-analyzed collection point and the existing preset behavior occurrence location, whether there is an abnormal preset behavior occurrence location in the periphery of the to-be-analyzed collection point can be determined.

[0010] Further, according to the position of the to-be-analyzed collection point in the periphery of which there is an abnormal preset behavior occurrence location, a region in which there is an abnormal preset behavior occurrence location can be determined. In this way, the region in which the abnormal preset behavior occurrence location is located is automatically positioned.

[0011] In a possible implementation, the determining whether the to-be-analyzed collection point is abnormal according to the position of the to-be-analyzed collection point and the position of the existing preset behavior occurrence location includes: determining a first distance according to the position of the to-be-analyzed collection point and the position of at least one normal preset behavior occurrence location in the existing preset behavior occurrence locations; determining a second distance according to the position of the to-be-analyzed collection point and the position of at least one abnormal preset behavior occurrence location in the existing preset behavior occurrence locations; and determining that the to-be-analyzed collection point is abnormal if at least one of the first distance is greater than a first distance threshold and the second distance is less than the first distance threshold is met.

[0012] The first distance is a distance between the to-be-analyzed collection point and a closest normal preset behavior occurrence location in the at least one normal preset behavior occurrence location. The second distance is a distance between the to-be-analyzed collection point and a closest abnormal preset behavior occurrence location in the at least one abnormal preset behavior occurrence location.

[0013] In this design, if the distance (that is, the first distance) between the to-be-analyzed collection point and the closest existing normal preset behavior occurrence location is greater than the first distance threshold, it indicates that the distance between the to-be-analyzed collection point and the closest existing normal preset behavior occurrence location is relatively far. If a vehicle that is likely to transport the target object appears on the to-be-analyzed collection point in this case, it can be determined that the possibility that an abnormal preset behavior occurrence location exists around the to-be-analyzed collection point is high. Therefore, the electronic device can determine that the to-be-analyzed collection point is abnormal, so as to use the to-be-analyzed collection point to locate the abnormal preset behavior occurrence location.

[0014] Secondly, if the distance (that is, the second distance) between the to-be-analyzed collection point and the closest existing abnormal preset behavior occurrence location is less than the first distance threshold, it indicates that the distance between the to-be-analyzed collection point and the closest existing abnormal preset behavior occurrence location is relatively close. If a vehicle that is likely to transport the target object appears on the to-be-analyzed collection point in this case, it can be determined that the possibility that the closest existing abnormal preset behavior occurrence location to the to-be-analyzed collection point is still in a working state is high, that is, the possibility that an abnormal preset behavior occurrence location exists around the to-be-analyzed collection point is high. Therefore, the electronic device can determine that the to-be-analyzed collection point is abnormal, so as to use the to-be-analyzed collection point to locate the abnormal preset behavior occurrence location.

[0015] In another possible implementation, the above abnormality-based to-be-analyzed collection point locates the preset behavior occurrence place of the abnormality, including: obtaining target vehicle information, and determining whether a first vehicle conforming to the target vehicle information appears on the abnormality-based to-be-analyzed collection point according to the target vehicle information and an image collected by the abnormality-based to-be-analyzed collection point; wherein the target vehicle information represents information of a vehicle that has a possibility of transporting a target object; if the first vehicle appears on the abnormality-based to-be-analyzed collection point, at least a first feature is counted according to trajectory data of the first vehicle appearing on the abnormality-based to-be-analyzed collection point; the first feature includes at least one of a travel feature of the first vehicle appearing on the abnormality-based to-be-analyzed collection point and a vehicle feature of the first vehicle appearing on the abnormality-based to-be-analyzed collection point; and the preset behavior occurrence place of the abnormality is located according to the first feature.

[0016] In another possible implementation, the above at least counting the first feature according to the trajectory data of the first vehicle appearing on the abnormality-based to-be-analyzed collection point includes: obtaining first trajectory data from the trajectory data of the first vehicle appearing on the abnormality-based to-be-analyzed collection point; the first trajectory data includes the abnormality-based to-be-analyzed collection point; and at least one of a total number of vehicles, a total number of vehicle types, a total number of vehicle return frequencies, and a third distance is counted according to the obtained first trajectory data.

[0017] The third distance represents a distance between a residence address of a person to which the vehicle belongs and the abnormality-based to-be-analyzed collection point; the total number of vehicles, the total number of vehicle types, and the total number of vehicle return frequencies belong to the travel feature; and the third distance belongs to the vehicle feature.

[0018] In another possible implementation, the above locating the preset behavior occurrence place of the abnormality according to the first feature includes: determining whether the abnormality-based to-be-analyzed collection point has a preset behavior occurrence place in a surrounding area according to the first feature; if the abnormality-based to-be-analyzed collection point has the preset behavior occurrence place in the surrounding area, at least one fourth distance corresponding to at least one person to which a vehicle belongs is obtained for the first vehicle appearing on the abnormality-based to-be-analyzed collection point; if any fourth distance is less than or equal to a second distance threshold, a residence address of a person to which a vehicle corresponding to the any fourth distance belongs is determined as the preset behavior occurrence place of the abnormality; and if all the at least one fourth distance is greater than the second distance threshold, the preset behavior occurrence place of the abnormality is determined according to a position of the abnormality-based to-be-analyzed collection point.

[0019] Each fourth distance is a distance between a residence address of a person to which a vehicle corresponding to the fourth distance belongs and the abnormality-based to-be-analyzed collection point.

[0020] In another possible implementation manner, the method further includes: determining a neighboring collection point corresponding to the collection point to be analyzed, and determining the neighboring collection point as the collection point to be analyzed; and a distance between the neighboring collection point and the collection point to be analyzed is less than the third distance threshold.

[0021] In the design manner, in order to avoid exposing the abnormal preset behavior occurrence position, the vehicle for the abnormal preset behavior does not drive to the abnormal preset behavior occurrence position in the process of transporting the target object, but drives to a safe position at a distance from the abnormal preset behavior occurrence position, and then transports the target object between the safe position and the abnormal preset behavior occurrence position by using other manners. Therefore, after the electronic device determines the collection point to be analyzed, the electronic device can further acquire a collection point adjacent to the collection point to be analyzed, to update the collection point to be analyzed. Thus, more abnormal collection points to be analyzed can be found, and omission of the abnormal collection points to be analyzed can be reduced.

[0022] In a second aspect, the present application provides a positioning device. The positioning device includes various modules for executing the method in the first aspect and any possible implementation manner thereof.

[0023] In a third aspect, the present application provides an electronic device including a memory and a processor. The memory and the processor are coupled. The memory is configured to store computer program code including computer instructions. When the processor executes the computer instructions, the electronic device performs the positioning method in the first aspect and any possible implementation manner thereof.

[0024] In a fourth aspect, the present application provides a chip system applied to the positioning device. The chip system includes one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected through a line. The interface circuit is configured to receive a signal from a memory of the positioning device and send a signal to the processor. The signal includes computer instructions stored in the memory. When the processor executes the computer instructions, the electronic device performs the positioning method in the first aspect and any possible implementation manner thereof.

[0025] In a fifth aspect, the present application provides a computer readable storage medium storing computer instructions. When the computer instructions run on an electronic device, the electronic device performs the positioning method in the first aspect and any possible implementation manner thereof.

[0026] In a sixth aspect, the present application provides a computer program product including computer instructions. When the computer instructions run on an electronic device, the electronic device performs the positioning method in the first aspect and any possible implementation manner thereof.

[0027] The detailed description of the second aspect to the sixth aspect and various implementation manners thereof in the present application can refer to the detailed description in the first aspect and various implementation manners thereof; and the beneficial effects of the second aspect to the sixth aspect and various implementation manners thereof can refer to the beneficial effect analysis in the first aspect and various implementation manners thereof, which will not be repeated here.

[0028] These aspects or other aspects of the present application will be more apparent in the following description. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 An implementation environment involved in a positioning method provided by an embodiment of the present application Figure 1 ;

[0030] Figure 2 An implementation environment involved in a positioning method provided by an embodiment of the present application Figure 2 ;

[0031] Figure 3 An implementation environment involved in a positioning method provided by an embodiment of the present application Figure 3 ;

[0032] Figure 4 A flow of a positioning method provided by an embodiment of the present application Figure 1 ;

[0033] Figure 5 A schematic diagram of a first collection point corresponding to a vehicle driving track provided by an embodiment of the present application

[0034] Figure 6A A schematic diagram of a distance between a first collection point and an existing preset behavior occurrence place provided by an embodiment of the present application Figure 1 ;

[0035] Figure 6B A schematic diagram of a distance between a first collection point and an existing preset behavior occurrence place provided by an embodiment of the present application Figure 2 ;

[0036] Figure 7 A flow of a positioning method provided by an embodiment of the present application Figure 2 ;

[0037] Figure 8 A schematic diagram of a region of a preset behavior occurrence place where an anomaly exists provided by an embodiment of the present application

[0038] Figure 9 A structural schematic diagram of a positioning device provided by an embodiment of the present application

[0039] Figure 10 A structural schematic diagram of an electronic device provided by an embodiment of the present application Detailed Implementation

[0040] Hereinafter, the terms "first," "second," and "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first," "second," or "third," etc., may explicitly or implicitly include one or more of that feature.

[0041] To address the problem of not being able to automatically locate the area where abnormal preset behaviors occur, this application provides a location method that first acquires vehicle trajectory data to be analyzed, and then determines the collection points to be analyzed within the vehicle trajectory data. These collection points may include a first collection point and / or a second collection point. A first collection point represents a round-trip critical point of a driving trajectory; the area surrounding a round-trip critical point of a driving trajectory may contain locations where abnormal preset behaviors occur. A second collection point represents a target collection point where the target object transported by the vehicle in the driving trajectory is changing; the area surrounding this target collection point may also contain locations where abnormal preset behaviors occur. Therefore, for any collection point to be analyzed (i.e., any first collection point or any second collection point), based on the location of the collection point to be analyzed and the location of existing locations where preset behaviors occur, it can be determined whether the collection point to be analyzed is abnormal.

[0042] The distance between the location of the data collection point to be analyzed and the location of existing preset behavior occurrences can reflect whether there are unknown abnormal preset behavior occurrences in the vicinity of the data collection point. For example, if the data collection point to be analyzed is far from existing normal preset behavior occurrences, and the vehicle to be analyzed still travels to the data collection point, then there is a high probability that there are abnormal preset behavior occurrences in the vicinity of the data collection point. Conversely, if the data collection point to be analyzed is close to existing abnormal preset behavior occurrences, and the vehicle to be analyzed still travels to the data collection point, then there is a high probability that the abnormal preset behavior occurrence near the data collection point is still active, meaning there is a high probability that there are abnormal preset behavior occurrences in the vicinity of the data collection point. Therefore, based on the distance between the data collection point to be analyzed and existing preset behavior occurrences, it is possible to determine whether there are abnormal preset behavior occurrences in the vicinity of the data collection point.

[0043] Secondly, the embodiment of the present application can also analyze the type of the vehicle appearing at the to-be-analyzed collection point, the return frequency of the same vehicle, the residential address of the personnel to which the vehicle belongs, and the like, based on the images collected by the plurality of collection points, the to-be-analyzed vehicle information, the vehicle registration information, the residential personnel information, and the like, to more accurately determine whether there is an abnormal preset behavior occurrence location around the to-be-analyzed collection point. Further, according to the position of the to-be-analyzed collection point around which there is an abnormal preset behavior occurrence location, the area of the abnormal preset behavior occurrence location can be determined. In this way, the area in which the abnormal preset behavior occurrence location is located is automatically positioned.

[0044] The to-be-analyzed vehicle information can be the information (such as the vehicle type, the license plate number, and the like) of the vehicle associated with the preset personnel. The preset personnel is the personnel related to the preset behavior, for example, the personnel related to the preset behavior, the personnel in the relationship circle of the personnel related to the preset behavior (for example, the family members or friends of the personnel related to the preset behavior). The personnel related to the preset behavior can include the personnel performing the preset behavior, the personnel transporting the target object, and the personnel exchanging the target object. The target object is the processing object of the preset behavior, for example, a pig.

[0045] The vehicle registration information can include the vehicle information and the identity information of the personnel to which the vehicle belongs. The residential personnel information can include the identity information of the personnel and the residential address of the personnel.

[0046] The implementation manners of the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0047] Please refer to Figure 1 which shows the implementation environment schematic diagram involved in the positioning method provided by the embodiment of the present application. As shown in Figure 1 The implementation environment can include a server 100, a terminal 110, and an image collection module 120 arranged at a plurality of collection points. The plurality of collection points can include a road portal, a vehicle speed monitoring point, and the like.

[0048] The server 100 can acquire the images collected by the image collection module 120 at each collection point. The server 100 can acquire the to-be-analyzed vehicle trajectory data according to the images collected by the plurality of collection points. The to-be-analyzed vehicle trajectory data can include one or more trajectory data of each vehicle in the plurality of vehicles. Each trajectory data represents a driving track composed of the positions of the plurality of collection points. The driving track refers to the track of the vehicle from a starting point to a destination and then back to the starting point. The destination is the return critical point of the driving track.

[0049] The server 100 can also acquire the position of the existing preset behavior occurrence location, the to-be-analyzed vehicle information, the vehicle registration information, the residential personnel information, and the like.

[0050] Specifically, as shown in Figure 2 The terminal 110 can receive a first operation input by a user, the first operation being used to indicate a target area and a preset behavior, etc. Then, the terminal 110 can acquire, from the server 100, images collected by a plurality of collection points in the target area, vehicle information used by a person associated with the preset behavior in the target area (which can be referred to as to-be-analyzed vehicle information), vehicle registration information, resident information in the target area, etc., in response to the first operation. The terminal 110 can determine a region where the preset behavior occurs abnormally according to the images, the to-be-analyzed vehicle information, the vehicle registration information, the resident information, etc. Then, the terminal 110 can output the region where the preset behavior occurs abnormally. For example, the terminal 110 can display the region where the preset behavior occurs abnormally on a display screen.

[0051] Alternatively, as shown in Figure 3 The terminal 110 can send the target area and the preset behavior, etc., to the server 100 in response to the first operation. The server 100 can acquire images collected by at least one collection point in the target area, vehicle information used by a person associated with the preset behavior in the target area, vehicle registration information, resident information in the target area, etc. Then, the server 100 can determine a region where the preset behavior occurs abnormally according to the images, the to-be-analyzed vehicle information, the vehicle registration information, the resident information, etc. The server 100 can send the region where the preset behavior occurs abnormally to the terminal 110. The terminal 110 can output the region where the preset behavior occurs abnormally.

[0052] For example, the terminal 110 in the embodiments of the present application can be a mobile phone, a tablet computer, a desktop computer, a laptop computer, a notebook computer, a netbook, etc. The embodiments of the present application do not specially limit the specific form of the terminal 110.

[0053] It should be noted that the positioning method provided by the embodiments of the present application can be applied to the server 100, the terminal 110, or both the server 100 and the terminal 110. The server 100 and the terminal 110 can be collectively referred to as an electronic device. The subject performing the positioning method provided by the embodiments of the present application can also be a positioning apparatus. The positioning apparatus can be an electronic device; or the apparatus can be an application program (APP) installed in the electronic device and providing a positioning function of a region where a preset behavior occurs abnormally; or the apparatus can be a central processing unit (CPU) in the electronic device; or the apparatus can be a control module in the electronic device for executing the positioning method.

[0054] The positioning method provided by the embodiments of the present application is described in detail below by taking an electronic device as an example.

[0055] Specifically, refer to Figure 4 a flowchart of the positioning method provided by the embodiments of the present application. As shown in the figure, Figure 4 the method can include steps 401-404.

[0056] Step 401: The electronic device acquires vehicle trajectory data to be analyzed.

[0057] The electronic device can acquire vehicle trajectory data to be analyzed for some vehicles that have a possibility of abnormal preset behavior.

[0058] In an implementation manner, since the vehicle indicated by the vehicle information to be analyzed is a vehicle used by a person related to the preset behavior, it is known that the vehicle indicated by the vehicle information to be analyzed has a possibility of abnormal preset behavior. Therefore, the electronic device can acquire trajectory data of the vehicle by using images collected by multiple collection points for the vehicle indicated by the vehicle information to be analyzed. Specifically, step 401 can include S11-S12.

[0059] S11: The electronic device acquires images collected by multiple collection points and vehicle information to be analyzed; the vehicle information to be analyzed refers to information of a vehicle associated with a preset person.

[0060] The electronic device can receive images collected by image collection modules on multiple collection points. The electronic device can also collect vehicle information to be analyzed.

[0061] Details of the vehicle information to be analyzed can be found in the above detailed description of the vehicle information to be analyzed.

[0062] The vehicle information to be analyzed can include license plate number, vehicle type, vehicle transportation object, information of a person to whom the vehicle belongs, and the like. The vehicle information to be analyzed can be obtained by a relevant person in advance.

[0063] For example, the electronic device acquires a target area input by a user, and can acquire images collected by multiple collection points in the target area and vehicle information to be analyzed in the target area.

[0064] S12: The electronic device acquires trajectory data of a vehicle associated with a preset person by using the images and the vehicle information to be analyzed.

[0065] The above vehicle trajectory data to be analyzed can include trajectory data of a vehicle associated with a preset person.

[0066] Exemplarily, the electronic device can determine, for each vehicle associated with the preset person, images including the vehicle from the images collected from the plurality of collection points according to the vehicle information of the vehicle. The electronic device can further determine one trajectory data of the vehicle according to each set of images collected successively in time from the images including the vehicle.

[0067] Each trajectory data can include the positions of the plurality of collection points and the travel times of the vehicle at the plurality of collection points. The travel time of the vehicle at each collection point can refer to the collection time at which the image including the vehicle is collected at the collection point.

[0068] Further, the vehicle for the abnormal preset behavior has a greater possibility of traveling at night than during the day in order to avoid being discovered. Therefore, the electronic device can further select, as the vehicle trajectory data to be analyzed, the trajectory data of the vehicle meeting the travel condition (e.g., traveling at night) from the vehicle trajectory data. In this way, the amount of data of the vehicle trajectory data to be analyzed can be reduced, and the vehicles in the vehicle trajectory data to be analyzed can be guaranteed to be the vehicles with a greater possibility of being for the abnormal preset behavior.

[0069] Specifically, step 401 can further include S13 after S12.

[0070] S13, the electronic device obtains, from the trajectory data of the vehicle associated with the preset person, the trajectory data of the vehicle meeting the travel condition.

[0071] The vehicle trajectory data to be analyzed can include the trajectory data of the vehicle meeting the travel condition.

[0072] The travel condition can be used to represent the vehicle traveling at night. For example, the travel condition can include at least one of the following: traveling at least twice in a first time period of the night, traveling in a second time period in the first time period, the number of travels at night being greater than the number of travels during the day, regularly traveling at night.

[0073] The at least twice traveling in the first time period of the night can refer to traveling at least twice in the first time period of the night on the same day, or refer to traveling in the first time period of the night within at least two days.

[0074] For example, the first time period of the night can be from 0:00 to 5:00. The second time period can be a period of time around 3:00. The number of travels at night can be the number of travels of the vehicle from 19:00 to 7:00, and the number of travels during the day can be the number of travels of the vehicle from 7:00 to 19:00.

[0075] In some embodiments, the electronic device can determine that the trajectory data of each vehicle associated with the preset person meets the travel condition according to the travel time in the trajectory data of each vehicle associated with the preset person. In turn, the electronic device can obtain the trajectory data of all vehicles meeting the travel condition.

[0076] In some embodiments, the electronic device can determine that the trajectory data of each vehicle associated with the preset person meets the travel condition according to the travel time in the trajectory data of each vehicle associated with the preset person. In turn, the electronic device can obtain the trajectory data of all vehicles meeting the travel condition.

[0077] In another implementation, although the vehicle indicated by the vehicle information to be analyzed is a vehicle used by the person related to the preset behavior, it is unclear whether the vehicle is currently used in the preset behavior or in an abnormal preset behavior. Therefore, the electronic device can identify the images collected by the plurality of collection points to obtain the information of the vehicle transporting the target object (which can be referred to as the vehicle information of the vehicle transporting the target object). The vehicle transporting the target object identified by the image is the vehicle currently used in the preset behavior. Compared with the vehicle represented by the vehicle information to be analyzed, the vehicle transporting the target object is more likely to be currently used in an abnormal preset behavior. The electronic device can further obtain the trajectory data of the vehicle transporting the target object by using the images collected by the plurality of collection points.

[0078] Specifically, step 401 can include S21-S23.

[0079] S21, the electronic device obtains images collected by a plurality of collection points.

[0080] S22, the electronic device identifies the images to obtain the information of the vehicle transporting the target object (which can be referred to as the vehicle information of the vehicle transporting the target object).

[0081] S23, the electronic device extracts the trajectory data of the vehicle transporting the target object according to the vehicle information of the vehicle transporting the target object by using the images.

[0082] In some embodiments, the vehicle trajectory data to be analyzed can include the trajectory data of the vehicle transporting the target object.

[0083] Further, step 401 can further include S24 after S23.

[0084] S24, the electronic device obtains the trajectory data of the vehicle meeting the travel condition from the trajectory data of the vehicle transporting the target object.

[0085] It should be noted that the specific process of S24 can be referred to the above detailed description of S13, and details are not described herein.

[0086] At step 402, the electronic device determines the to-be-analyzed collection point in the to-be-analyzed vehicle trajectory data.

[0087] The electronic device can determine the to-be-analyzed collection point in the to-be-analyzed vehicle trajectory data for each trajectory data. Further, the electronic device can obtain one or more to-be-analyzed collection points. The to-be-analyzed collection point in each trajectory data can include a first collection point and / or a second collection point.

[0088] The first collection point represents a round-trip critical point of a trajectory. The trajectory is the trajectory of the vehicle indicated by the to-be-analyzed vehicle trajectory data. The trajectory can be referred to the above detailed description of the trajectory represented by each trajectory data.

[0089] For example, as shown in FIG. 4, a trajectory of a vehicle includes collection points A, B, C, C, and B arranged in time sequence. For the trajectory, the electronic device can determine that the first collection point corresponding to the trajectory is collection point C. Figure 5 The second collection point represents a target collection point in the change from transporting a target object to not transporting a target object or the change from not transporting a target object to transporting a target object. The target collection point includes a collection point of transporting a target object and / or a collection point of not transporting a target object.

[0090] At step 403, the electronic device determines whether the to-be-analyzed collection point is abnormal according to the location of the to-be-analyzed collection point and the location of the existing preset behavior occurrence location.

[0091] The electronic device can determine the distance between the to-be-analyzed collection point and the existing preset behavior occurrence location, and determine whether the to-be-analyzed collection point is abnormal. If the to-be-analyzed collection point is abnormal, the electronic device can use the to-be-analyzed collection point to find the abnormal preset behavior occurrence location. If the to-be-analyzed collection point is normal, the electronic device does not use the to-be-analyzed collection point to find the abnormal preset behavior occurrence location, and can determine whether the next to-be-analyzed collection point is abnormal.

[0092] In some embodiments, the location of the existing preset behavior occurrence place can be statistically pre-determined. The existing preset behavior occurrence place includes at least one of at least one normal preset behavior occurrence place and at least one abnormal preset behavior occurrence place. The at least one normal preset behavior occurrence place and the at least one abnormal preset behavior occurrence place are both existing. The abnormal preset behavior occurrence place can refer to a preset behavior occurrence place that does not meet the working condition of the preset behavior.

[0093] Further, the electronic device can determine a distance (which can be referred to as a first distance) between the to-be-analyzed collection point and a nearest one of the at least one existing normal preset behavior occurrence place according to the location of the to-be-analyzed collection point and the location of the at least one normal preset behavior occurrence place. The electronic device can also determine a distance (which can be referred to as a second distance) between the to-be-analyzed collection point and a nearest one of the at least one abnormal preset behavior occurrence place according to the location of the to-be-analyzed collection point and the location of the at least one abnormal preset behavior occurrence place. Then, if at least one of the first distance is greater than a first distance threshold D leg and the second distance is less than the first distance threshold D leg is satisfied, the electronic device can determine that the to-be-analyzed collection point is abnormal.

[0094] The first distance threshold D leg may be determined according to the density and the number of the plurality of collection points provided with the image collection module.

[0095] For example, in a case where the number of the plurality of collection points provided with the image collection module is large and the density is high, the first distance threshold D leg may be set to be small.

[0096] For another example, in a case where the number of the plurality of collection points provided with the image collection module is small and the density is low, the first distance threshold D leg may be set to be large.

[0097] It can be understood that, in a case where the number of the plurality of collection points provided with the image collection module is large and the density is high, the existing normal preset behavior occurrence place has a large probability of being close to the location of part of the collection points, and the existing abnormal preset behavior occurrence place also has a large probability of being close to the location of part of the collection points. Therefore, the first distance threshold D leg for determining the distance between the to-be-analyzed collection point and the normal preset behavior occurrence place and determining the distance between the to-be-analyzed collection point and the abnormal preset behavior occurrence place can be set to be small.

[0098] It should be noted that if the existing preset behavior locations include normal preset behavior locations, the electronic device can determine a first distance. If the existing preset behavior locations include abnormal preset behavior locations, the electronic device can determine a second distance.

[0099] For example, such as Figure 6A As shown, the data collection point to be analyzed corresponding to a driving trajectory is represented by a black star. The electronic device can determine that the distance between the data collection point to be analyzed and the location of its nearest existing abnormal preset behavior is greater than a first distance threshold D. leg If so, it can be determined that the data collection point to be analyzed is normal.

[0100] Or, such as Figure 6B As shown, the electronic device can determine that the distance between the data collection point to be analyzed and its nearest existing normal preset behavior location is greater than a first distance threshold D. leg If so, it can be determined that the data collection point to be analyzed is abnormal.

[0101] For example, for Figure 5 The image shows a vehicle's driving trajectory, and the corresponding data collection point to be analyzed is data collection point C. The electronic device determines the distance d between data collection point C and its nearest known location of normal, pre-defined behavior. C Greater than the first distance threshold D leg If so, it can be determined that the sampling point C is abnormal.

[0102] In this embodiment, to avoid exposing the location of the abnormal preset behavior, some vehicles used for abnormal preset behaviors will not travel to the location of the abnormal preset behavior during the transportation of the target object. Instead, they will travel to a safe location at a certain distance from the location of the abnormal preset behavior and then use other methods to transport the target object between the safe location and the location of the abnormal preset behavior. Therefore, after step 402, the electronic device can acquire collection points adjacent to the collection point to be analyzed determined in step 402 to update the collection point to be analyzed. Then, the electronic device can execute step 403 for the updated collection point to be analyzed.

[0103] Specifically, the electronic device can determine the adjacent sampling points corresponding to the sampling point to be analyzed, and identify the adjacent sampling points as the sampling points to be analyzed. The distance between the adjacent sampling point and its corresponding sampling point to be analyzed is less than a third distance threshold.

[0104] The electronic device can acquire adjacent acquisition points corresponding to each acquisition point to be analyzed from multiple acquisition points equipped with image acquisition modules.

[0105] Step 404: The electronic device locates the location of the abnormal preset behavior based on the abnormal data collection points to be analyzed.

[0106] The electronic device can locate the abnormal preset behavior occurrence location directly based on the location of the abnormal to-be-analyzed collection point.

[0107] Alternatively, the electronic device can analyze the vehicle features and / or driving features of the vehicle traveling at the abnormal to-be-analyzed collection point, using the to-be-analyzed vehicle information, images collected at the abnormal to-be-analyzed collection point, and the like, for each abnormal to-be-analyzed collection point. Then, the electronic device can determine whether the abnormal preset behavior occurrence location exists in the periphery of the abnormal to-be-analyzed collection point according to the vehicle features and / or driving features. Finally, the electronic device can locate the abnormal preset behavior occurrence location based on the abnormal to-be-analyzed collection point in the periphery of which the abnormal preset behavior occurrence location exists.

[0108] In some embodiments, the specific process of step 404 is described by taking the electronic device to continue to determine whether the abnormal preset behavior occurrence location exists in the periphery of the abnormal to-be-analyzed collection point as an example. Specifically, referring to Figure 7 , step 404 can include steps 701-703.

[0109] In step 701, the electronic device obtains target vehicle information, and determines whether a first vehicle conforming to the target vehicle information appears at the abnormal to-be-analyzed collection point according to the target vehicle information and images collected at the abnormal to-be-analyzed collection point. The target vehicle information represents information of a vehicle that has a possibility of transporting a target object.

[0110] The electronic device can perform vehicle recognition on the images collected at each abnormal to-be-analyzed collection point, determine the vehicle information appearing at the abnormal to-be-analyzed collection point, and then determine whether the vehicle information appearing at the abnormal to-be-analyzed collection point includes the target vehicle information. Then, if the vehicle information appearing at the abnormal to-be-analyzed collection point includes the target vehicle information, it is determined that the first vehicle appears at the abnormal to-be-analyzed collection point. If the vehicle information appearing at the abnormal to-be-analyzed collection point does not include the target vehicle information, it is determined that the first vehicle does not appear at the abnormal to-be-analyzed collection point.

[0111] The information of the first vehicle belongs to both the vehicle information appearing at the to-be-analyzed collection point and the target vehicle information. The target vehicle information can include vehicle identification (such as license plate number, license plate type, and license plate color) and the like.

[0112] In some embodiments, the vehicle information to be analyzed can include at least one of a vehicle type and a vehicle transported object. In turn, the electronic device can determine, for each of the vehicle information to be analyzed, that the vehicle information belongs to the target vehicle information and the vehicle represented by the vehicle information belongs to the first vehicle, if the vehicle type in the vehicle information is the target vehicle type and / or the vehicle transported object in the vehicle information is the target object.

[0113] The target vehicle type can refer to a vehicle type capable of transporting the target object. For example, a truck (e.g., a small or medium-sized truck), a fence truck (including a regular fence truck and / or a modified fence truck), and the like.

[0114] In other embodiments, the electronic device can obtain all images collected by a plurality of collection points provided with an image collection module; and identify the vehicle transporting the target object from all images to obtain the target vehicle information. The target vehicle information is the vehicle transporting the target object.

[0115] The electronic device can use a preset identification model to identify the vehicle and the target object in each image to obtain the vehicle information of the vehicle transporting the target object in the image, or determine that the image does not include the vehicle transporting the target object.

[0116] The preset identification model can be obtained by pre-training an initial model using a sample image marked with a vehicle and a target object. The initial model can be a deep learning model, a machine learning model, or the like.

[0117] In other embodiments, the electronic device can determine whether the first vehicle conforming to the target vehicle information appears multiple times at the abnormal collection point to be analyzed. If the first vehicle conforming to the target vehicle information appears multiple times at the abnormal collection point to be analyzed, step 702 can be performed. If the first vehicle conforming to the target vehicle information does not appear at the abnormal collection point to be analyzed, or the first vehicle conforming to the target vehicle information appears once at the abnormal collection point to be analyzed, the electronic device can not perform step 702.

[0118] The first vehicle conforming to the target vehicle information appearing multiple times at the abnormal collection point to be analyzed can include that the same first vehicle conforming to the target vehicle information appears multiple times at the abnormal collection point to be analyzed, and / or different first vehicles conforming to the target vehicle information appear at the abnormal collection point to be analyzed.

[0119] If the first vehicle appears at the abnormal collection point to be analyzed, the electronic device can at least count the first feature according to the trajectory data of the first vehicle appearing at the abnormal collection point to be analyzed.

[0120] The first feature includes at least one of the travel characteristics of the first vehicle appearing at the abnormal data collection point to be analyzed, and the vehicle characteristics of the first vehicle appearing at the abnormal data collection point to be analyzed.

[0121] The electronic device can first acquire first trajectory data from the trajectory data of the first vehicle appearing at the abnormal data collection point to be analyzed; the first trajectory data includes the abnormal data collection point to be analyzed. Then, the electronic device can, based on the acquired first trajectory data, count at least one of the following: total number of vehicles, total number of vehicle types, total number of vehicle round-trip frequencies, and third distance. The total number of vehicles, total number of vehicle types, and total number of vehicle round-trip frequencies belong to the aforementioned travel characteristics. The third distance belongs to the aforementioned vehicle characteristics.

[0122] The total number of vehicles can refer to the total number of all first vehicles appearing at an abnormal data collection point to be analyzed. The total number of vehicle types can refer to the total number of vehicle types of the first vehicles appearing at an abnormal data collection point to be analyzed. The vehicle round-trip frequency can include the sum of the frequencies of all first vehicles appearing at an abnormal data collection point to and from that abnormal data collection point.

[0123] The third distance represents the distance between the residential address of the person to whom the vehicle belongs and the abnormal data collection point to be analyzed. For example, the electronic device can obtain a fourth distance for each first vehicle appearing at an abnormal data collection point to be analyzed; this fourth distance is the distance between the residential address of the person to whom the first vehicle belongs and the abnormal data collection point to be analyzed. Then, the electronic device can determine the maximum value among all the obtained fourth distances as the third distance; or, determine the average value of all the obtained fourth distances as the third distance.

[0124] For example, the electronic device can obtain information about the occupant of a first vehicle appearing at an abnormal data collection point from the vehicle information to be analyzed; then, based on the occupant information, it can obtain the occupant's residential address from the resident information. The electronic device then calculates a third distance corresponding to the first vehicle based on the location of the abnormal data collection point and the occupant's address. The vehicle information and resident information can be from the same area.

[0125] Step 703: The electronic device locates the location of the abnormal preset behavior based on the first feature.

[0126] The electronic device can first determine whether there are any pre-defined locations of abnormal behavior in the vicinity of the abnormal data collection point to be analyzed, based on the first feature. Then, the electronic device can locate the location of the abnormal pre-defined behavior based on the presence of such locations and the abnormal data collection point to be analyzed in the vicinity.

[0127] In some embodiments, the electronic device may set a first threshold corresponding to the total number of vehicles, a second threshold corresponding to the total number of vehicle types, a third threshold corresponding to the total number of vehicle round trips, and a fourth threshold corresponding to the third distance. Then, the electronic device can determine whether there is a preset location of abnormal behavior around the abnormal data collection point to be analyzed based on at least one of the total number of vehicles, the total number of vehicle types, the total number of vehicle round trips, and the third distance and their corresponding thresholds.

[0128] For example, the electronic device can acquire some thresholds and weights for determining whether there are preset locations of abnormal behavior around the analysis point to be analyzed, as shown in Table 1 below. Then, the electronic device can set the first parameter F1 corresponding to the total number of vehicles to 1 when the total number of vehicles is greater than the first threshold; and set the first parameter F1 corresponding to the total number of vehicles to 0 when the total number of vehicles is less than the first threshold. Similarly, the electronic device sets the second parameter F2 corresponding to the total number of vehicle types to 1 when the total number of vehicle types is greater than the second threshold; and sets the second parameter F2 corresponding to the total number of vehicle types to 0 when the total number of vehicle round trips is less than the second threshold. The electronic device sets the third parameter F3 corresponding to the total number of vehicle round trips to 1 when the total number of vehicle round trips is greater than the third threshold; and sets the third parameter F3 corresponding to the total number of vehicle round trips to 0 when the total number of vehicle round trips is less than the third threshold. The electronic device sets the fourth parameter F4 corresponding to the third distance to 1 when the third distance is greater than the fourth threshold; and sets the fourth parameter F4 corresponding to the third distance to 0 when the third distance is less than the fourth threshold.

[0129] Table 1

[0130]

[0131] Then, the electronic device can substitute the first parameter F1, the second parameter F2, the third parameter F3, the fourth parameter F4, the first weight W1, the second weight W2, the third weight W3, and the fourth weight W4 into the confidence calculation formula to obtain the confidence level of the abnormal sampling point to be analyzed. If the confidence level is greater than the fifth threshold, the electronic device can determine that there is a pre-defined location of abnormal behavior in the vicinity of the abnormal sampling point to be analyzed; if the confidence level is less than the fifth threshold, the electronic device can determine that there is no pre-defined location of abnormal behavior in the vicinity of the abnormal sampling point to be analyzed. The confidence calculation formula is shown in Equation (1) below.

[0132]

[0133] Here, Confidence is the confidence level of the data collection point to be analyzed for this anomaly. n is the total number of data points collected by the electronic device for the vehicles representing the transportation target at the data collection point to be analyzed for this anomaly (e.g., if the electronic device counts the total number of vehicles, the total number of vehicle types, the total number of vehicle round trips, and the third distance, then n = 4). α i This is the weighting adjustment factor. α i When = 1, it means that the weight of the i-th data point in the statistics of the electronic device is a fixed value.

[0134] For example, the electronic device can input at least one of the following into a machine learning model: the total number of vehicles, the total number of vehicle types, the total number of vehicle round trips, and a third distance, and output a judgment result. This judgment result indicates whether the abnormal data collection point being analyzed corresponds to a preset location where abnormal behavior occurs or a preset location where abnormal behavior does not occur. The machine learning model may include decision trees, random forests, etc.

[0135] Furthermore, when there are pre-defined locations of abnormal behavior in the vicinity of an abnormal data collection point to be analyzed, the electronic device can acquire at least one fourth distance corresponding to at least one person belonging to at least one vehicle appearing at the abnormal data collection point to be analyzed; wherein, each fourth distance is the distance between the residential address of the person belonging to the corresponding vehicle and the abnormal data collection point to be analyzed. If any fourth distance is less than a second distance threshold, then the residential address of the person belonging to the vehicle corresponding to that fourth distance is determined to be the location of the pre-defined abnormal behavior. If at least one fourth distance is greater than the second distance threshold, then the location of the pre-defined abnormal behavior is determined based on the location of the abnormal data collection point to be analyzed.

[0136] For example, for an abnormal data collection point to be analyzed in a predetermined location where abnormal behavior is expected to occur, the electronic device can define a region corresponding to the abnormal data collection point, with the location of the abnormal data collection point as the center and a predetermined length as the radius. Furthermore, the electronic device can determine that the region corresponding to the abnormal data collection point belongs to the predetermined location where abnormal behavior is expected to occur.

[0137] For example, when an electronic device detects an abnormal data collection point and at least one fourth distance is greater than a second distance threshold, it can determine the location of this abnormal data collection point to identify the location of a preset abnormal behavior. Furthermore, the electronic device can obtain multiple abnormal data collection points for determining the location of the preset abnormal behavior.

[0138] In this scenario, the electronic device can divide the multiple abnormal data collection points into at least one set. The distance between any two abnormal data collection points within each set is less than a fourth distance threshold. Then, for each set, the electronic device can determine an overlapping region (which can be called the overlapping region corresponding to that set) based on the regions corresponding to all the abnormal data collection points within that set. Furthermore, the electronic device can determine that the location of the pre-defined abnormal behavior includes the overlapping region corresponding to at least one set.

[0139] In this process, the electronic device uses the location of each collection point in the set as the center and a preset length as the radius to determine a region corresponding to that collection point. The overlapping region corresponding to each set can be the region contained in the regions corresponding to all abnormal collection points to be analyzed in that set, or the overlapping region corresponding to each combination can include the region contained in the regions corresponding to all abnormal collection points to be analyzed in that set.

[0140] Specifically, such as Figure 8 As shown, the electronic device determines a set including abnormal data collection points D, E, and F. Then, the electronic device can determine that the regions corresponding to data collection points D, E, and F all contain an overlapping region. This overlapping region belongs to the area where the preset abnormal behavior occurred.

[0141] For example, this fourth distance threshold can be in the range of 3-5 kilometers (km).

[0142] For example, suppose the area where an abnormal, pre-defined behavior occurs has entrances and exits in four directions: east, south, west, and north. Each of these four entrances and exits is equipped with an image acquisition module, meaning they are all acquisition points. If the electronic device determines that these four entrances and exits are abnormal acquisition points to be analyzed, and that these four entrances and exits belong to a set, then the electronic device can determine an overlapping area based on the areas corresponding to these four entrances and exits. This overlapping area is very likely the area where the abnormal, pre-defined behavior occurred.

[0143] It should be noted that the specific process by which the electronic device locates the location of the abnormal preset behavior based directly on the location of the abnormal data collection point to be analyzed can be found in the detailed description of the electronic device determining the location of the abnormal preset behavior for an abnormal data collection point with an abnormal preset behavior occurrence location in the surrounding area. This application embodiment will not repeat the details here.

[0144] It should be noted that in the embodiments of this application, "greater than" can be used to mean "greater than" or "greater than or equal to".

[0145] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0146] This application also provides a positioning device. For example... Figure 9 The diagram shown is a structural schematic of a positioning device 900 provided in an embodiment of this application. The positioning device 900 may include: a data acquisition module 901, an anomaly judgment module 902, and an anomaly positioning module 903.

[0147] The data acquisition module 901 is used to acquire vehicle trajectory data to be analyzed. The anomaly judgment module 902 is used to: determine the collection points to be analyzed in the vehicle trajectory data; and for any collection point to be analyzed, determine whether the collection point is abnormal based on its location and the location of existing preset behavior occurrences. The anomaly location module 903 is used to locate the location of the abnormal preset behavior occurrence based on the abnormal collection points to be analyzed.

[0148] The data collection points to be analyzed include a first data collection point and / or a second data collection point; a first data collection point represents the round-trip critical point of a driving trajectory. A second data collection point represents the target data collection point in a driving trajectory during the change of a vehicle from transporting a target object to transporting no target object, or the change of a vehicle from transporting no target object to transporting a target object; target data collection points include data collection points transporting target objects and / or data collection points without transporting target objects. A driving trajectory is the driving trajectory of the vehicle indicated by the vehicle trajectory data to be analyzed.

[0149] In one possible implementation, the anomaly detection module 902 is specifically configured to: determine a first distance based on the location of the data collection point to be analyzed and the location of at least one normal preset behavior occurrence among the existing preset behavior occurrence locations; the first distance is the distance between the data collection point to be analyzed and the nearest normal preset behavior occurrence among the at least one normal preset behavior occurrence locations; determine a second distance based on the location of the first data collection point and the location of at least one abnormal preset behavior occurrence among the existing preset behavior occurrence locations; the second distance is the distance between the data collection point to be analyzed and the nearest abnormal preset behavior occurrence among the at least one abnormal preset behavior occurrence locations; if at least one of the first distance being greater than a first distance threshold and the second distance being less than the first distance threshold is satisfied, then the data collection point to be analyzed is determined to be abnormal.

[0150] In another possible implementation, the anomaly localization module 903 is specifically used to: acquire target vehicle information, and determine whether a first vehicle matching the target vehicle information appears at the abnormal data collection point based on the target vehicle information and the image collected at the abnormal data collection point; wherein, the target vehicle information represents information about vehicles that have the potential to transport target objects; if a first vehicle appears at the abnormal data collection point, then at least based on the trajectory data of the first vehicle appearing at the abnormal data collection point, a first feature is statistically analyzed; the first feature includes at least one of the travel characteristics of the first vehicle appearing at the abnormal data collection point and the vehicle characteristics of the first vehicle appearing at the abnormal data collection point; and based on the first feature, locate the location of the abnormal preset behavior.

[0151] In another possible implementation, the anomaly localization module 903 is specifically used to: obtain first trajectory data from the trajectory data of the first vehicle appearing at the abnormal collection point to be analyzed; the first trajectory data includes the abnormal collection point to be analyzed; based on the obtained first trajectory data, at least one of the following is calculated: total number of vehicles, total number of vehicle types, total number of vehicle round trips, and third distance; wherein, the third distance represents the distance between the residential address of the person to whom the vehicle belongs and the abnormal collection point to be analyzed; the total number of vehicles, the total number of vehicle types, and the total number of vehicle round trips belong to travel characteristics; the third distance belongs to vehicle characteristics.

[0152] In another possible implementation, the anomaly localization module 903 is specifically used to: determine, based on the first feature, whether there is an abnormal preset behavior occurrence location in the vicinity of the abnormal data collection point to be analyzed; if there is an abnormal preset behavior occurrence location in the vicinity of the abnormal data collection point to be analyzed, for the first vehicle appearing at the abnormal data collection point to be analyzed, obtain at least one fourth distance corresponding to at least one person belonging to at least one vehicle; wherein, each fourth distance is the distance between the residential address of the person belonging to the corresponding vehicle and the abnormal data collection point to be analyzed; if any fourth distance is less than or equal to a second distance threshold, then determine that the residential address of the person belonging to the vehicle corresponding to any fourth distance is an abnormal preset behavior occurrence location; if at least one fourth distance is greater than the second distance threshold, then determine the abnormal preset behavior occurrence location based on the location of the abnormal data collection point to be analyzed.

[0153] In another possible implementation, the anomaly detection module 902 is also used to determine the adjacent collection points corresponding to the collection point to be analyzed, and to determine the adjacent collection points as collection points to be analyzed; the distance between the adjacent collection point and its corresponding collection point to be analyzed is less than the third distance threshold.

[0154] Of course, the positioning device 900 provided in this application embodiment includes, but is not limited to, the above-described modules.

[0155] Another embodiment of this application also provides an electronic device. For example... Figure 10 As shown, the electronic device 1000 includes a memory 1001 and a processor 1002; the memory 1001 and the processor 1002 are coupled; the memory 1001 is used to store computer program code, which includes computer instructions. When the processor 1002 executes the computer instructions, the electronic device 1000 performs each step of the method flow shown in the above method embodiment.

[0156] In actual implementation, the data acquisition module 901, the anomaly detection module 902, and the anomaly location module 903 can be composed of... Figure 10 The processor 1002 shown calls the computer program code in the memory 1001 to implement this. The specific execution process can be found in the description of the positioning method section above, and will not be repeated here.

[0157] Another embodiment of this application provides a computer-readable storage medium storing computer instructions that, when executed on an electronic device, cause the electronic device to perform each step of the method flow shown in the above method embodiment.

[0158] Another embodiment of this application provides a chip system applied to an electronic device. The chip system includes one or more interface circuits and one or more processors. The interface circuits and processors are interconnected via lines. The interface circuits are used to receive signals from the electronic device's memory and send the signals to the processors, the signals including computer instructions stored in the memory. When the processor of the electronic device executes the computer instructions, the electronic device performs each step of the method flow shown in the above method embodiments.

[0159] In another embodiment of this application, a computer program product is also provided, which includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the various steps of the method flow shown in the above method embodiments.

[0160] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs).

[0161] The above description is merely a specific embodiment of this application. Any variations or substitutions conceived by those skilled in the art based on the specific embodiments provided in this application should be covered within the protection scope of this application.

Claims

1. A positioning method, characterized by, The method comprises: acquiring vehicle trajectory data to be analyzed; determining an analysis collection point in the vehicle trajectory data to be analyzed; wherein the analysis collection point comprises a first collection point and / or a second collection point; one first collection point represents a round-trip critical point of a driving trajectory; one second collection point represents a target collection point in a change from transporting a target object to not transporting a target object or a change from not transporting a target object to transporting a target object in a driving trajectory, the target collection point comprising a collection point of transporting a target object and / or a collection point of not transporting a target object; the periphery of one first / second collection point has a possibility of a preset behavior occurrence location with an anomaly; for any analysis collection point, determining whether the analysis collection point is abnormal according to the position of the analysis collection point and the position of an existing preset behavior occurrence location; based on the abnormal analysis collection point, positioning an abnormal preset behavior occurrence location; the method further comprises: determining a first distance according to the position of the analysis collection point and the position of at least one normal preset behavior occurrence location in the existing preset behavior occurrence locations; the first distance is the distance between the analysis collection point and the closest normal preset behavior occurrence location in the at least one normal preset behavior occurrence location; determining a second distance according to the position of the first collection point and the position of at least one abnormal preset behavior occurrence location in the existing preset behavior occurrence locations; the second distance is the distance between the analysis collection point and the closest abnormal preset behavior occurrence location in the at least one abnormal preset behavior occurrence location; if at least one of the first distance is greater than a first distance threshold and the second distance is less than the first distance threshold is satisfied, determining that the analysis collection point is abnormal; the method further comprises: statistically determining a first feature according to the trajectory data of a first vehicle appearing on the abnormal analysis collection point; the first vehicle represents a vehicle with a possibility of transporting the target object; the first feature comprises at least one of a travel feature and a vehicle feature of the first vehicle; determining a confidence degree that the abnormal preset behavior occurrence location exists in the periphery of the abnormal analysis collection point according to the first feature; in a case where it is determined that the abnormal preset behavior occurrence location exists in the periphery of the abnormal analysis collection point according to the confidence degree, based on the abnormal analysis collection point, positioning the abnormal preset behavior occurrence location.

2. The method of claim 1, wherein, the method further comprises: Obtaining target vehicle information, and determining whether a first vehicle conforming to the target vehicle information appears on the abnormal analysis collection point according to the target vehicle information and an image collected at the abnormal analysis collection point.

3. The method of claim 1, wherein, The first feature is counted according to trajectory data of the first vehicle appearing on the abnormal analysis collection point, including: First trajectory data is obtained from the trajectory data of the first vehicle appearing on the abnormal analysis collection point, and the first trajectory data includes the abnormal analysis collection point. At least one of a total number of vehicles, a total number of vehicle types, a total number of vehicle return frequencies, and a third distance is counted according to the obtained first trajectory data, wherein the third distance represents a distance between a residence address of a person to whom the vehicle belongs and the abnormal analysis collection point; the total number of vehicles, the total number of vehicle types, and the total number of vehicle return frequencies belong to the travel feature; and the third distance belongs to the vehicle feature.

4. The method of claim 1, wherein, In a case where the abnormal preset behavior occurrence place exists in the periphery of the abnormal analysis collection point according to the confidence, the abnormal preset behavior occurrence place is located based on the abnormal analysis collection point, including: In a case where the abnormal preset behavior occurrence place exists in the periphery of the abnormal analysis collection point, at least one fourth distance corresponding to at least one person to whom a vehicle belongs is obtained for the first vehicle appearing on the abnormal analysis collection point, wherein each fourth distance is a distance between a residence address of the corresponding person to whom the vehicle belongs and the abnormal analysis collection point; If any fourth distance is less than or equal to a second distance threshold, it is determined that the residence address of the person to whom the vehicle corresponding to the any fourth distance belongs is the abnormal preset behavior occurrence place; If all the at least one fourth distance is greater than the second distance threshold, the abnormal preset behavior occurrence place is determined according to a position of the abnormal analysis collection point.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: A neighboring collection point corresponding to the analysis collection point is determined, and the neighboring collection point is determined as the analysis collection point; a distance between the neighboring collection point and the corresponding analysis collection point is less than a third distance threshold.

6. A positioning device, characterized by The positioning device includes: A data acquisition module is configured to acquire vehicle trajectory data for analysis. Anomaly judgment module, used for determining a to-be-analyzed collection point in the to-be-analyzed vehicle trajectory data; wherein the to-be-analyzed collection point includes a first collection point and / or a second collection point; one first collection point represents a round-trip critical point of one driving trajectory; one second collection point represents a target collection point in a change from transporting a target object to not transporting a target object or a change from not transporting a target object to transporting a target object in one driving trajectory, and the target collection point includes a collection point of transporting a target object and / or a collection point of not transporting a target object; a periphery of one first / second collection point has a possibility of existing an abnormal preset behavior occurrence place; For any to-be-analyzed collection point, whether the to-be-analyzed collection point is abnormal is judged according to a position of the to-be-analyzed collection point and a position of an existing preset behavior occurrence place; Anomaly positioning module, used for positioning an abnormal preset behavior occurrence place based on an abnormal to-be-analyzed collection point; the anomaly judgment module is specifically used for determining a first distance according to a position of the to-be-analyzed collection point and a position of at least one normal preset behavior occurrence place in the existing preset behavior occurrence place; the first distance is a distance between the to-be-analyzed collection point and a normal preset behavior occurrence place closest in distance in the at least one normal preset behavior occurrence place; determining a second distance according to the position of the first collection point and a position of at least one abnormal preset behavior occurrence place in the existing preset behavior occurrence place; the second distance is a distance between the to-be-analyzed collection point and an abnormal preset behavior occurrence place closest in distance in the at least one abnormal preset behavior occurrence place; if at least one of the first distance is greater than a first distance threshold and the second distance is less than the first distance threshold is satisfied, it is determined that the to-be-analyzed collection point is abnormal; The anomaly positioning module is specifically used for counting a first feature according to trajectory data of a first vehicle appearing on the abnormal to-be-analyzed collection point; the first vehicle represents a vehicle with a possibility of transporting the target object; the first feature includes at least one of a travel feature and a vehicle feature of the first vehicle; determining a confidence degree that a periphery of the abnormal to-be-analyzed collection point exists the abnormal preset behavior occurrence place according to the first feature; in a case where it is determined that the periphery of the abnormal to-be-analyzed collection point exists the abnormal preset behavior occurrence place according to the confidence degree, positioning the abnormal preset behavior occurrence place based on the abnormal to-be-analyzed collection point.

7. The positioning apparatus according to claim 6, wherein The anomaly positioning module is further used for: acquiring target vehicle information, and judging whether a first vehicle conforming to the target vehicle information appears on the abnormal to-be-analyzed collection point according to the target vehicle information and an image collected by the abnormal to-be-analyzed collection point; wherein the target vehicle information represents information of a vehicle with a possibility of transporting the target object; The anomaly positioning module is specifically used for: Obtain first trajectory data from the trajectory data of the first vehicle appearing at the abnormal analysis collection point; the first trajectory data includes the abnormal analysis collection point; At least according to the obtained first trajectory data, at least one of the total number of vehicles, the total number of vehicle types, the total number of vehicle return frequencies, and the third distance is counted; wherein the third distance represents the distance between the residence address of the vehicle owner and the abnormal analysis collection point; the total number of vehicles, the total number of vehicle types and the total number of vehicle return frequencies belong to the travel characteristics; the third distance belongs to the vehicle characteristics; The abnormal positioning module is specifically used for: In the case that the abnormal preset behavior occurrence place exists in the periphery of the abnormal analysis collection point, for the first vehicle appearing at the abnormal analysis collection point, at least one fourth distance corresponding to at least one vehicle owner is obtained; wherein each fourth distance is the distance between the residence address of its corresponding vehicle owner and the abnormal analysis collection point; If any fourth distance is less than or equal to the second distance threshold, it is determined that the residence address of the vehicle owner corresponding to the any fourth distance is the abnormal preset behavior occurrence place; If the at least one fourth distance is greater than the second distance threshold, the abnormal preset behavior occurrence place is determined according to the position of the abnormal analysis collection point; The abnormal judgment module is also used to determine the adjacent collection point corresponding to the analysis collection point, and determine the adjacent collection point as the analysis collection point; the distance between the adjacent collection point and its corresponding analysis collection point is less than the third distance threshold.

8. An electronic device, comprising: The electronic device includes a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program code, the computer program code includes computer instructions; Wherein, when the processor executes the computer instructions, the electronic device executes the positioning method as claimed in any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, when the computer instructions run on the electronic device, the electronic device executes the positioning method as claimed in any one of claims 1-5.

Images