Online car-hailing safety monitoring method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for monitoring the safety of online ride-hailing vehicles. The method comprises: when it is determined that the trip of an online ride-hailing vehicle order has ended and the track of one of the driver and the passenger is missing, obtaining the track of the other of the driver and the passenger in real time as a target track; performing feature analysis on the target track to obtain at least one track feature; based on the track feature, judging whether the driver and the passenger have not separated after the trip has ended, so as to monitor the safety of the driver and the passenger. In this way, even if the track of one of the drivers is missing, it is possible to judge whether the driver and the passenger have not separated after the trip has ended, so as to monitor the safety of the driver and the passenger, thereby reducing safety risks.

Description

Technical Field

[0001] The present application relates to the technical field of online car-hailing, and in particular to an online car-hailing safety monitoring method, device, equipment and storage medium. Background Art

[0002] Online car-hailing is a service for booking taxis online, which brings great convenience to people's travel. While online car-hailing brings convenience to people, there are also many safety hazards. Among them, 80% of cases occur after the trip. Therefore, it is crucial for online car-hailing platforms to be able to determine whether the driver and passengers have not separated after the trip. After determining that the driver and passengers have not separated after the trip, timely intervention can be made to reduce safety risks.

[0003] In the related art, one strategy for determining whether the driver and the passenger have not separated after the trip is to match the track points of the driver and the passenger, and then determine whether the driver and the passenger have not separated after the trip. Based on this, the tracks of both the driver and the passenger need to exist, but in actual applications, the tracks may be missing due to various reasons, which will cause the strategy to fail and make it impossible to determine whether the driver and the passenger have not separated after the trip, which poses a high safety risk. Summary of the invention

[0004] The purpose of this application is to provide a method, device, equipment and storage medium for monitoring the safety of online ride-hailing vehicles, so as to solve the problem in the related art that due to the lack of the driver's or passenger's trajectory, it is impossible to determine whether the driver and the passenger have not separated after the trip, resulting in a high safety risk.

[0005] The purpose of this application is achieved through the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for monitoring the safety of an online car-hailing service, comprising:

[0007] When it is determined that the trip of the online car-hailing order has ended and the trajectory of one of the driver and the passenger is missing, the trajectory of the other driver and the passenger is obtained in real time as the target trajectory;

[0008] Performing feature analysis on the target trajectory to obtain at least one trajectory feature;

[0009] At least based on the trajectory characteristics, it is determined whether the driver and passengers are still together after the trip is completed, so as to monitor the safety of the driver and passengers.

[0010] In one embodiment, determining whether the driver and the passenger are still connected after the trip is completed based at least on the trajectory characteristics includes:

[0011] Determine whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result;

[0012] Based at least on the first determination result, it is determined whether the driver and the passenger are not separated after the trip is completed.

[0013] In one embodiment, it further includes:

[0014] Acquire environmental information reflecting the situation inside the vehicle in real time;

[0015] Performing feature analysis on the environmental information to obtain at least one environmental feature;

[0016] At least based on the trajectory characteristics, determining whether the driver and passenger are still together after the trip is completed includes:

[0017] Based on trajectory characteristics and environmental characteristics, determine whether the driver and passenger are still together after the trip.

[0018] In one implementation, based on the trajectory characteristics and the environmental characteristics, determining whether the driver and the passenger are still connected after the trip is completed includes:

[0019] Determine whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result;

[0020] Determine whether the environmental feature exists in the abnormal environmental feature set to obtain a second determination result;

[0021] Based on the first judgment result and the second judgment result, it is determined whether the driver and the passenger are still connected after the trip is completed.

[0022] In one embodiment, if the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination but continues to drive, and / or the driver stays at a location for more than a first preset time; and / or,

[0023] If the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger speed exceeds the walking speed limit, and / or the passenger stays at the missing part of the driver's trajectory for more than a second preset time.

[0024] In one embodiment, the abnormal environment feature set includes abnormal voice features and / or abnormal image features;

[0025] Abnormal image features include: multiple people in the car image after the trip, and / or the driver is not in the main driving seat;

[0026] Abnormal voice features include: after the trip, there are multiple voiceprints in the voice in the car, and / or there is a female voiceprint, and / or there is no sound of opening and closing the car door.

[0027] In one embodiment, it further includes:

[0028] In the case where the trip is determined to be over and both the driver and the passenger's tracks are missing, it is determined that the driver and the passenger have not separated after the trip is completed.

[0029] In one embodiment, it further includes:

[0030] If the driver and passenger are not separated after the trip, the driver side is triggered to send a deterrent signal, and / or the passenger side is triggered to feedback information about the passenger's safety.

[0031] In one embodiment, it further includes:

[0032] If the passenger is unsafe, a customer service ticket is created and assigned to a safety specialist to allow the safety specialist to intervene.

[0033] In one embodiment, it further includes:

[0034] Obtaining driver and passenger characteristics;

[0035] Create customer service tickets and assign them to security specialists, including:

[0036] Determine the safety risk level based on the characteristics of the driver and passengers;

[0037] Create a customer service ticket corresponding to the security risk level and assign it to a security specialist corresponding to the security risk level.

[0038] In one embodiment, it further includes:

[0039] If the passenger terminal does not provide feedback on the passenger's safety status, an outbound call is initiated to the passenger terminal to obtain the passenger's safety status information.

[0040] In a second aspect, an embodiment of the present application provides a safety monitoring device for an online car-hailing service, comprising:

[0041] A first acquisition module is used to acquire the trajectory of the driver and the passenger in real time as the target trajectory when it is determined that the trip of the online car-hailing order has ended and the trajectory of one of the driver and the passenger is missing;

[0042] A first analysis module, used for performing feature analysis on a target trajectory to obtain at least one trajectory feature;

[0043] The judgment module is used to judge whether the driver and the passenger are not separated after the trip is completed based on at least the trajectory characteristics, so as to monitor the safety of the driver and the passenger.

[0044] In one implementation, the determination module is specifically configured to:

[0045] Determine whether the trajectory feature exists in the abnormal trajectory feature set, and obtain a first determination result;

[0046] Based at least on the first determination result, it is determined whether the driver and the passenger are not separated after the trip is completed.

[0047] In one embodiment, it further includes:

[0048] The second acquisition module is used to acquire the collected environmental information reflecting the situation inside the vehicle in real time;

[0049] A second analysis module, used for performing feature analysis on the environmental information to obtain at least one environmental feature;

[0050] The judgment module is specifically used for:

[0051] Based on trajectory characteristics and environmental characteristics, determine whether the driver and passenger are still together after the trip.

[0052] In one implementation, the determination module is specifically configured to:

[0053] Determine whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result;

[0054] Determine whether the environmental feature exists in the abnormal environmental feature set to obtain a second determination result;

[0055] Based on the first judgment result and the second judgment result, it is determined whether the driver and the passenger are still connected after the trip is completed.

[0056] In one embodiment, if the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination but continues to drive, and / or the driver stays at a location for more than a first preset time; and / or,

[0057] If the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger speed exceeds the walking speed limit, and / or the passenger stays at the missing part of the driver's trajectory for more than a second preset time.

[0058] In one embodiment, the abnormal environment feature set includes abnormal voice features and / or abnormal image features;

[0059] Abnormal image features include at least: after the trip, there are multiple people in the car image, and / or the driver is not in the main driving seat;

[0060] Abnormal voice features include at least: after the trip, there are multiple voiceprints in the voice in the car, and / or there is a female voiceprint, and / or there is no sound of opening and closing the car door.

[0061] In one embodiment, it further includes:

[0062] The determination module is used to determine that the driver and the passenger are not separated after the trip is completed when it is determined that the trip is completed and the tracks of both the driver and the passenger are missing.

[0063] In one embodiment, it further includes:

[0064] The trigger module is used to trigger the driver to send a deterrent signal and / or trigger the passenger to feedback the passenger's safety information when the driver and passenger are not separated after the trip.

[0065] In one embodiment, it further includes:

[0066] Create a module to create a customer service ticket and assign it to a safety officer to intervene if a passenger is unsafe.

[0067] In one embodiment, it further includes:

[0068] The third acquisition module is used to acquire the characteristics of the driver and passengers;

[0069] Create modules specifically for:

[0070] Determine the safety risk level based on the characteristics of the driver and passengers;

[0071] Create a customer service ticket corresponding to the security risk level and assign it to a security specialist corresponding to the security risk level.

[0072] In one embodiment, it further includes:

[0073] The outbound call module is used to initiate an outbound call to the passenger terminal to obtain the passenger's safety status information if the passenger terminal does not feedback the passenger's safety status information.

[0074] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any method of the first aspect when executing the computer program.

[0075] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any method of the first aspect.

[0076] The advantages or beneficial effects of the above technical solution include at least: when the trajectory of one of the driver and passenger is missing, the trajectory of the other after the trip can be obtained in real time and feature analysis can be performed, and based on the trajectory features, it can be judged whether the driver and passenger have not separated after the trip. In this way, even if the trajectory of one of them is missing, it can be judged whether the driver and passenger have not separated after the trip, so as to monitor the safety of the driver and passengers. Compared with related technologies, it does not strongly rely on the situation where the driver and passenger have simultaneous trajectories, and can maximize the protection of the driver and passengers after the trip, reduce the occurrence of high-risk events, and thus reduce safety risks.

[0077] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0079] Figure 1 is a flowchart of an exemplary online car-hailing safety monitoring method provided in an embodiment of the present application;

[0080] Figure 2 is a flowchart of an exemplary online car-hailing safety monitoring method provided in an embodiment of the present application;

[0081] Figure 3 is a schematic diagram of an exemplary online car-hailing safety monitoring method provided in an embodiment of the present application;

[0082] Figure 4 is a flowchart of an exemplary online car-hailing safety monitoring method provided in an embodiment of the present application;

[0083] Figure 5 is a structural schematic diagram of an exemplary online car-hailing safety monitoring device provided in an embodiment of the present application;

[0084] Figure 6 is a structural schematic diagram of an exemplary online car-hailing safety monitoring device provided in an embodiment of the present application;

[0085] Figure 7 It is a structural diagram of an exemplary electronic device used to implement a method for safety monitoring of online ride-hailing vehicles provided in an embodiment of the present application. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0087] Online car-hailing is a service for booking taxis online, which brings great convenience to people's travel. While online car-hailing brings convenience to people, there are also many safety hazards. Among them, 80% of cases occur after the trip. Therefore, it is crucial for online car-hailing platforms to be able to determine whether the driver and passengers have not separated after the trip. After determining that the driver and passengers have not separated after the trip, timely intervention can be made to reduce safety risks.

[0088] In the related art, one strategy for determining whether the driver and the passenger have not separated after the trip is to match the track points of the driver and the passenger, and then determine whether the driver and the passenger have not separated after the trip. Based on this, the tracks of both the driver and the passenger need to exist, but in actual applications, the tracks may be missing due to various reasons, which will lead to the failure of the strategy and the inability to determine whether the driver and the passenger have not separated after the trip, which poses a high safety risk.

[0089] Generally, there are several reasons for missing tracks:

[0090] 1. The subjective actions of the driver on the driver side or the passenger on the passenger side (such as exiting the client, etc.) lead to the missing track.

[0091] 2. When abnormal monitoring is performed after the trip, the link for real-time trajectory acquisition is as follows: the driver / passenger end reports the trajectory -> the back-end driver application programming interface (RAPI, Rider Application Programming Interface) / passenger application programming interface (CAPI, Consumer Application Programming Interface) stores the reported trajectory in real time -> the location-based service (LBS, Location Based Service) transmits the stored trajectory in real time -> the data group parses the transmitted trajectory -> the algorithm side obtains the analyzed trajectory information and calculates to determine whether the driver and passenger are not separated after the trip -> the engineering side applies the judgment result of the algorithm side. In short, the driver / passenger end reports the trajectory, the back-end RAPI / CAPI stores the trajectory in real time, the LBS transmits the real-time trajectory, the data group analyzes the data, the algorithm side applies the trajectory calculation, and the engineering side applies the result. Here, the back-end RAPI / CAPI, LBS, data group, algorithm side, and engineering side all belong to the service side corresponding to the driver and passenger ends. It can be seen from this that when abnormal monitoring is performed after the trip, the link for real-time trajectory acquisition is too long, and the trajectory may be missing due to a problem in an upstream link.

[0092] In order to solve the above technical problems, the embodiments of the present application provide an exemplary online car-hailing safety monitoring method, which is applied to the server and is introduced in detail below.

[0093] Figure 1 : is a flow chart of a method for monitoring the safety of online ride-hailing vehicles provided in an embodiment of the present application. Figure 1 As shown, the online car-hailing safety monitoring method includes at least the following steps:

[0094] Step 101: When it is determined that the trip of the online car-hailing order has ended and the trajectory of one of the driver and the passenger is missing, the trajectory of the other of the driver and the passenger is obtained in real time as the target trajectory.

[0095] Step 102: Perform feature analysis on the target trajectory to obtain at least one trajectory feature.

[0096] Step 103: Based on the trajectory characteristics, determine whether the driver and passengers are still together after the trip to monitor the safety of the driver and passengers.

[0097] The end of the trip can be when the driver ends the order, that is, the driver clicks on the destination on the driver side, or when the driver arrives within the destination but does not end the order, or when the driver and passenger cancel the order. Correspondingly, after the trip ends, it can be when the driver ends the order, when the driver arrives within the destination but does not end the order, or when the driver and passenger cancel the order. Here, the target trajectory is the trajectory after the trip ends.

[0098] In this solution, when the trajectory of one of the driver and passenger is missing, the trajectory of the other after the trip can be obtained in real time and feature analysis can be performed. Based on the trajectory features, it can be determined whether the driver and passenger have not separated after the trip. In this way, even if the trajectory of one of them is missing, it can be determined whether the driver and passenger have not separated after the trip, so as to monitor the safety of the driver and passengers. Compared with related technologies, it does not strongly rely on the situation where the driver and passenger have simultaneous trajectories, and can maximize the protection of the driver and passengers after the trip, reduce the occurrence of high-risk events, and thus reduce safety risks.

[0099] In addition, this solution can also avoid the situation in the above related technologies where the link for real-time trajectory acquisition is too long, a problem occurs in one link, resulting in the loss of trajectory and the failure of the overall strategy, as well as the loss of trajectory due to exiting the client, thereby reducing security risks.

[0100] In one embodiment, in step 103, based on the trajectory features, it is determined whether the driver and the passenger are still together after the trip. The specific implementation method may include: determining whether the trajectory features exist in the abnormal trajectory feature set to obtain a first judgment result; based on the first judgment result, determining whether the driver and the passenger are still together after the trip.

[0101] The behavior of the driver and passenger not being separated on the trajectory after the trip will show certain abnormalities. In practical applications, the characteristics of the trajectory of the driver and passenger not being separated after the trip can be analyzed, and the abnormal behaviors of the driver and passenger not being separated on the trajectory after the trip can be counted to obtain abnormal trajectory characteristics, and finally obtain an abnormal trajectory feature set.

[0102] In this embodiment, since the abnormal trajectory feature set is obtained based on the trajectory characteristics of the driver and passenger not separating after the trip ends, by judging whether the analyzed trajectory features belong to the features in the abnormal trajectory feature set, it is possible to accurately judge whether the driver and passenger are not separating after the trip ends.

[0103] It should be noted that, since the analyzed trajectory features include at least one trajectory feature, the above determination of whether the driver and the passenger have not separated after the trip is completed based on the first judgment result can be specifically: as long as there is a trajectory feature in the abnormal trajectory feature set, it is determined that the driver and the passenger have not separated after the trip. Of course, it can also be determined that the driver and the passenger have not separated after the trip is completed if multiple trajectory features exist in the abnormal trajectory feature set.

[0104] After the trip, the driver and passenger are not separated, mainly including two scenarios: the driver and passenger drive together or the driver and passenger park together. In practical applications, the abnormal features of the driver and passenger driving together and the driver and passenger park together can be mined to determine whether the driver and passenger are not separated after the trip. Based on the role characteristics of the driver and passenger, the abnormal features of the two are also different, which are introduced below.

[0105] After the passenger's trip is over, he or she will generally exit the client. At this time, the passenger's trajectory will be missing, and the driver's trajectory can be used as the target trajectory. If the target trajectory is the driver's trajectory, the abnormal trajectory feature set may include: after the trip is over, the driver does not stop at the destination and continues to drive, and / or the driver stays at a location for more than a first preset time. The specific value of the first preset time can be set according to actual conditions and is not specifically limited here.

[0106] In actual applications, after the trip is over, the driver does not stop at the destination but continues to drive, that is, the driver passes the destination without stopping after the trip is over. This is a relatively dangerous signal. Therefore, this is an abnormal trajectory feature that needs to be focused on and can be set in the abnormal trajectory feature set. In addition, after the trip is over, if the driver stays at a location for more than the first preset time, that is, the driver stays at a location for a long time, a safety incident may also occur. Therefore, this can also be used as an abnormal trajectory feature that needs attention and can be set in the abnormal trajectory feature set. In addition, other abnormal trajectory features can also be set, which are not listed here one by one.

[0107] Accordingly, when performing feature analysis on the driver's trajectory, the dwell time of each trajectory point can be specifically analyzed. Then, judging whether the trajectory feature exists in the abnormal trajectory feature set to obtain the first judgment result can specifically include:

[0108] If the abnormal trajectory feature set includes that after the trip ends, the driver stays at a location for more than a first preset time, it can be determined whether the stay time at the location of the analyzed trajectory point exceeds the first preset time. If so, it is determined that the current trajectory feature exists in the abnormal trajectory feature set; otherwise, it is determined that the current trajectory feature does not exist in the abnormal trajectory feature set.

[0109] If the abnormal trajectory feature set includes that after the trip, the driver did not stop at the destination but continued to drive, it can be determined whether the dwell time at the location of the analyzed trajectory point is less than the third preset time. If so, it is considered that after the trip, the driver did not stop at the destination but continued to drive, and it is determined that the current trajectory feature exists in the abnormal trajectory feature set. Otherwise, it is determined that the current trajectory feature does not exist in the abnormal trajectory feature set. Among them, the third preset time is a smaller value, and the specific value can be set according to the actual situation, and is not specifically limited here.

[0110] Some criminal drivers close the client or shut down the computer to commit crimes, or there is a problem with the link to obtain the trajectory, etc., the driver's trajectory will be missing. In this case, the passenger's trajectory can be used as the target trajectory. If the target trajectory is the passenger's trajectory, the abnormal trajectory feature set may include: after the trip, the passenger's speed exceeds the walking speed limit, and / or the passenger stays at the location where the driver's trajectory is missing for more than a second preset time. Among them, the specific value of the second preset time can be set according to actual conditions, and is not specifically limited here.

[0111] In actual application, under normal circumstances, after passengers get off at the destination, they usually walk a distance. At this time, the speed shown by the trajectory after the trip is a normal walking speed. However, when an abnormality occurs, the passenger fails to get off after arriving at the destination, but is carried by the driver to continue driving. Since the speed is much greater than the walking speed, the speed shown by the trajectory after the trip will be abnormal. At this time, the passenger speed exceeds the limit of human walking speed. It can be considered that this situation is more dangerous. Therefore, it can be used as an abnormal trajectory feature that needs attention and can be set in the abnormal trajectory feature set. In addition, if the passenger stays at the missing position of the driver's trajectory for more than the second preset time, that is, the passenger stays at the position where the driver's trajectory disappears for a long time, this may be caused by some criminal drivers closing the client or shutting down the computer to commit crimes. This is a more dangerous signal. Therefore, it can be used as an abnormal trajectory feature that needs attention and is set in the abnormal trajectory feature set. In addition, other abnormal trajectory features can also be set, which are not listed one by one here.

[0112] Correspondingly, when performing feature analysis on passenger trajectories, the trajectory characteristics such as the dwell time at each trajectory point, the trajectory speed, etc. can be specifically analyzed.

[0113] If the abnormal trajectory feature set includes that the passenger speed exceeds the walking speed limit after the trip ends, the analyzed trajectory feature may be the speed of the trajectory, and determining whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result may specifically include: determining whether the speed of the analyzed trajectory exceeds the walking speed limit; if so, determining that the current trajectory feature exists in the abnormal trajectory feature set; otherwise, determining that the current trajectory feature does not exist in the abnormal trajectory feature set.

[0114] If the abnormal trajectory feature set includes that the time the passenger stays at the location where the driver's trajectory is missing exceeds a second preset time, the analyzed trajectory feature may be the residence time at the location of the trajectory point, and whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first judgment result may specifically include: determining whether the location of the trajectory point is consistent with the location where the driver's trajectory is missing and whether the residence time exceeds the second preset time; if so, determining that the current trajectory feature exists in the abnormal trajectory feature set; otherwise, determining that the current trajectory feature does not exist in the abnormal trajectory feature set.

[0115] It should be noted that the trajectory after the above trip can be the trajectory within a preset time period after the trip, because, for passengers, the trajectory information belongs to the user's privacy and cannot be obtained for a long time.

[0116] The above-listed several main abnormal trajectory characteristics of the driver and passenger not being separated after the trip are used to accurately determine whether the driver and passenger are not separated after the trip.

[0117] In order to further improve the accuracy of judging whether the driver and passengers have not separated after the end of the trip, it is also possible to comprehensively judge whether the driver and passengers have not separated after the end of the trip based on the trajectory and in combination with other information, such as the situation inside the car, etc. Based on this, in one embodiment, the above online car-hailing safety monitoring method may also include: obtaining environmental information reflecting the situation inside the car in real time; performing feature analysis on the environmental information to obtain at least one environmental feature. Correspondingly, in the above step 103, based on the trajectory features, judging whether the driver and passengers have not separated after the end of the trip, the specific implementation method may include: judging whether the driver and passengers have not separated after the end of the trip based on the trajectory features and the environmental features. In this way, by combining the trajectory features and the environmental features, it is possible to more accurately judge whether the driver and passengers have not separated after the end of the trip, thereby further reducing safety risks.

[0118] Specifically, based on the trajectory characteristics and environmental characteristics, it is determined whether the driver and passenger are still together after the trip. The implementation method may include: determining whether the trajectory characteristics exist in a set of abnormal trajectory characteristics to obtain a first judgment result; determining whether the environmental characteristics exist in a set of abnormal environmental characteristics to obtain a second judgment result; based on the first judgment result and the second judgment result, determining whether the driver and passenger are still together after the trip.

[0119] In practical applications, as mentioned above, based on the trajectory characteristics of the driver and passenger not separated after the trip, an abnormal trajectory feature set can be obtained. Similarly, the driver and passenger not separated after the trip will show certain abnormal behaviors in the vehicle situation reflected by the environmental information. The vehicle situation after the driver and passenger are not separated after the trip can be analyzed, and the abnormal behaviors of the driver and passenger not separated in the vehicle after the trip can be counted to obtain abnormal environmental features, and finally an abnormal environmental feature set can be obtained.

[0120] In this embodiment, since the abnormal trajectory feature set and the abnormal environment feature set are both obtained based on the characteristic that the driver and the passenger have not separated after the trip, by judging whether the analyzed trajectory features belong to the features in the abnormal trajectory feature set, and by judging whether the analyzed environment features belong to the features in the abnormal environment feature set, by combining the judgment results of the two, it is possible to accurately judge whether the driver and the passenger have not separated after the trip.

[0121] It should be noted that, since the analyzed trajectory features include at least one trajectory feature, and the analyzed environmental features also include at least one environmental feature, the above determination of whether the driver and the passenger have not separated after the trip is based on the first judgment result and the second judgment result can be specifically: as long as there is a trajectory feature in the abnormal trajectory feature set and as long as there is an environmental feature in the abnormal environmental feature set, it can be determined that the driver and the passenger have not separated after the trip. Of course, it can also be that multiple trajectory features exist in the abnormal trajectory feature set and multiple environmental features exist in the abnormal environmental feature set, and it is determined that the driver and the passenger have not separated after the trip. It can also be that multiple trajectory features exist in the abnormal trajectory feature set and one environmental feature exists in the abnormal environmental feature set, and it is determined that the driver and the passenger have not separated after the trip. It can also be that one trajectory feature exists in the abnormal trajectory feature set and multiple environmental features exist in the abnormal environmental feature set, and it is determined that the driver and the passenger have not separated after the trip.

[0122] The environmental information collected above may include voice information and / or image information. In actual applications, the driver can turn on recording, obtain voice information and report it to the server. A vehicle-mounted video terminal is generally installed in the vehicle. After turning it on, it can record video, obtain video image information and report it to the server.

[0123] Accordingly, the environmental features may include voice features and / or image features. The abnormal environmental feature set may include abnormal voice features and / or abnormal image features.

[0124] Among them, abnormal image features may include but are not limited to: after the trip is completed, there are multiple people in the car image, and / or the driver is not in the main driving seat.

[0125] In actual applications, during a trip, there are usually drivers and passengers in the car. After the passengers get off at the destination, there is only the driver in the car. If there are still multiple people in the car image after the trip, it may be that the passengers have not gotten off the car, that is, the driver and passengers are not separated. This is an abnormal feature that needs attention and can be set in the abnormal environment feature set. In addition, the driver usually sits in the main driving seat. If the driver is not in the main driving seat in the car image after the trip, but in the back seat, it may be that the driver is committing a crime. Therefore, this is also an abnormal feature that needs attention and can be set in the abnormal environment feature set.

[0126] Abnormal voice features may include, but are not limited to: after the trip, there are multiple voiceprints in the voice in the car, and / or there is a female voiceprint, and / or there is no sound of opening and closing the car door.

[0127] In addition to images, the voiceprints in the speech can also be used to analyze whether there are multiple people in the car after the trip. Therefore, the feature of multiple voiceprints in the voice in the car can be set in the abnormal environment feature set. In addition, if there is a female voiceprint in the car after the trip, it is also a sensitive signal. In order to avoid harm to the driver and passengers, this feature needs to be set in the abnormal environment feature set. Under normal circumstances, after arriving at the destination, there will be the sound of doors opening and closing when passengers get off the car. However, if the driver passes the destination without stopping and continues to drive, the passengers cannot get off, and there will be no sound of doors opening and closing in the car. Therefore, the absence of door opening and closing sounds can also be set as an abnormal environment feature in the abnormal environment feature set.

[0128] Correspondingly, when performing feature analysis on environmental information, specifically, voiceprint information in speech and / or person feature information in images may be analyzed.

[0129] Among them, the voiceprint information may include the number of voiceprints, whether there is a female voiceprint, whether there is a sound of opening and closing the car door, etc.

[0130] Personnel characteristic information may include the number of people in the car, the seating status of people in the car, etc.

[0131] If the abnormal environmental feature set includes that there are multiple people in the image inside the car after the trip, the analyzed environmental feature can be the number of people in the image inside the car, and it is determined whether the environmental feature exists in the abnormal environmental feature set to obtain a second judgment result. The specific implementation method may include: determining whether the analyzed number of people in the image inside the car is greater than or equal to 2, and if so, determining that the current environmental feature exists in the abnormal environmental feature set; otherwise, determining that the current environmental feature does not exist in the abnormal environmental feature set.

[0132] If the abnormal trajectory feature set includes that the driver is not in the main driving seat after the trip, the analyzed environmental feature may be the seating status of the people in the car, and it is determined whether the environmental feature exists in the abnormal environmental feature set to obtain a second judgment result. The specific implementation method may include: determining whether the analyzed seating status of the people in the car is that the main driving seat is unmanned; if so, determining that the current environmental feature exists in the abnormal environmental feature set; otherwise, determining that the current environmental feature does not exist in the abnormal environmental feature set.

[0133] If the abnormal trajectory feature set includes multiple voiceprints in the in-car voice after the trip, the analyzed environmental feature can be the number of voiceprints in the voice, and it is determined whether the environmental feature exists in the abnormal environmental feature set to obtain a second judgment result. The specific implementation method may include: determining whether the number of analyzed voiceprints is greater than or equal to 2, if so, determining that the current environmental feature exists in the abnormal environmental feature set, otherwise, determining that the current environmental feature does not exist in the abnormal environmental feature set.

[0134] If the abnormal trajectory feature set includes that there is a female voiceprint in the voice in the car after the trip, the analyzed environmental feature can be whether there is a female voiceprint in the voice, and it is judged whether the environmental feature exists in the abnormal environmental feature set to obtain a second judgment result. The specific implementation method may include: judging whether there is a female voiceprint in the analyzed voiceprint, and if so, determining that the current environmental feature exists in the abnormal environmental feature set; otherwise, determining that the current environmental feature does not exist in the abnormal environmental feature set.

[0135] If the abnormal trajectory feature set includes whether there is a door opening and closing sound in the voice in the car after the trip ends, the analyzed environmental feature may be whether there is a door opening and closing sound in the voice, and whether the environmental feature exists in the abnormal environmental feature set to obtain a second judgment result. The specific implementation method may include: judging whether there is a door opening and closing sound in the analyzed voiceprint, and if not, determining that the current environmental feature exists in the abnormal environmental feature set; otherwise, determining that the current environmental feature does not exist in the abnormal environmental feature set.

[0136] The above-listed several main abnormal voice features and abnormal image features of the driver and passenger not being separated after the trip are used to accurately determine whether the driver and passenger are not separated after the trip.

[0137] In one embodiment, when it is determined that the trip is over and both the driver and the passenger's tracks are missing, it is determined that the driver and the passenger have not separated after the trip. In practical applications, when determining that both the driver and the passenger's tracks are missing, signal interference issues such as tunnels can be ruled out first. In this way, if both tracks are missing, this may be a situation where the driver is controlling the passenger's mobile phone, which is a high-risk signal, and it can be directly considered that the driver and the passenger have not separated after the trip, thereby improving passenger safety.

[0138] It should be noted that when it is determined that the trip has ended and the trajectories of the driver and the passenger exist at the same time, the trajectory points of the driver and the passenger can be directly matched. If the distance between the driver's trajectory point and the passenger's trajectory point is lower than the threshold distance, the two trajectory points are determined to be together, and the trajectory point is regarded as a dangerous point. The proportion of dangerous points of all reported real-time trajectory points during the monitoring time is calculated, and based on the proportion, it is determined whether the driver and the passenger have not separated after the trip. If the proportion reaches the threshold proportion, it is determined that the driver and the passenger have not separated after the trip. Among them, the monitoring time refers to the time period from the end of the trip to the current moment.

[0139] In one embodiment, the above online car-hailing safety monitoring method may also include: triggering the driver side to send a deterrent signal when the driver and passenger are not separated after the trip, and / or triggering the passenger side to feedback information on the passenger's safety status.

[0140] In actual applications, if the server determines that the driver and passenger have not separated after the trip, it can trigger high-risk intervention to improve passenger safety. For the driver, the server can trigger the driver to send a deterrent signal in the form of voice broadcast or alarm to prevent him from performing dangerous behaviors. For the passenger, the server can trigger a pop-up window on the passenger side, so that the passenger can operate on the pop-up window to feedback his own safety information. Of course, other methods can also be used to make the passenger feedback safety information.

[0141] In this way, when the driver and passenger have not separated after the trip, the service end can automatically trigger the driver end to deter the driver, and can also automatically trigger the passenger end to remind the passenger to actively feedback safety information through the client to improve passenger safety.

[0142] Furthermore, if the passenger terminal does not provide feedback on the passenger's safety status, an outbound call is initiated to the passenger terminal to obtain the passenger's safety status information. In practical applications, an interactive voice response (IVR) outbound call can be initiated. In this way, if the passenger does not actively provide feedback on the safety status through the passenger terminal, this may be caused by the passenger being unable to provide feedback due to the dangerous behavior being carried out. At this time, the service terminal can also actively call the passenger to confirm whether it is safe, thereby further improving safety.

[0143] In one embodiment, the above online car-hailing safety monitoring method may further include: if the passenger is unsafe, creating a customer service ticket and assigning it to a safety specialist so that the safety specialist can intervene. In this way, when there is a safety issue with the passenger, a customer service ticket can be automatically and quickly created immediately, and the safety specialist can intervene in time to improve the safety of the passenger.

[0144] Furthermore, the above online car-hailing safety monitoring method may also include: obtaining driver and passenger characteristics. Accordingly, creating a customer service ticket and assigning it to a safety specialist, and its specific implementation method may include: determining the safety risk level based on the driver and passenger characteristics; creating a customer service ticket corresponding to the safety risk level, and assigning it to a safety specialist corresponding to the safety risk level.

[0145] The above driver and passenger characteristics are driver profile characteristics and passenger profile characteristics. Driver profile characteristics may include whether the driver has a bad record. Drivers with bad records may be risky drivers who threaten the safety of passengers. Passenger profile characteristics may include whether the passenger's starting point is a restaurant or other place. Passengers whose starting point is a restaurant or other place may be drunk and may be risky passengers who may pose a safety threat.

[0146] In actual applications, the safety risk level can be divided according to actual conditions. For example, based on the characteristics of the driver and the passenger, if it is determined that one of them is at risk, the safety risk level is determined to be high, otherwise, the safety risk level is determined to be normal.

[0147] When creating a customer service ticket, if the security risk level is high, you can create a high-level customer service ticket and assign it to a professional security specialist. If the security risk level is normal, you can create a normal customer service ticket and assign it to a normal security specialist.

[0148] In this way, for ordinary customer service tickets with low risks, ordinary security specialists will perform ordinary level intervention, such as manual outbound call intervention or video linking passengers. For high-level customer service tickets, professionals will perform more advanced intervention, such as calling the police, etc., thereby improving passenger safety through reasonable intervention.

[0149] The following takes a specific application scenario as an example to introduce in more detail a method for monitoring the safety of online ride-hailing vehicles provided in an embodiment of the present application.

[0150] In this embodiment, it mainly includes two processes: judging whether the driver and the passenger are not separated after the trip is completed and applying.

[0151] The process of judging whether the driver and passenger have not separated after the trip:

[0152] like Figure 2 As shown, the system architecture involved in this process includes the passenger side, the driver side, the in-vehicle video terminal installed in the car, and the server side (ie, the back end). Here, the server side architecture can at least include the back-end RAPI, the back-end CAPI, LBS, AI side recognition module, data group, and algorithm side.

[0153] The driver and passenger are not separated after the trip, including two scenarios: the driver and passenger drive together or the driver and passenger stop together. For the identification (i.e. judgment) solution of the driver and passenger not separating after the trip, it is necessary to mine the abnormal features of driving together and stopping together to realize abnormal feature recognition. Starting from the driver and passenger features, trajectory features, voice features, and image features, it is comprehensively judged whether the driver and passenger are still together after the trip. The specific solutions are as follows:

[0154] Step 1: Get the trajectory. Figure 2 As shown in the figure, the specific process includes: driver-side / passenger-side trajectory reporting, back-end RAPI / CAPI trajectory real-time storage, LBS real-time trajectory transparent transmission, data group data analysis, and algorithm-side acquisition of the analyzed trajectory information.

[0155] like Figure 2 and Figure 3As shown, if both the driver and the passenger have trajectories, the driver and passenger trajectories can be used to determine whether the driver and the passenger have not separated. After the algorithm side obtains the parsed trajectory information from the data group, it performs trajectory application calculation: match the driver and passenger trajectory points. If the distance between the driver's trajectory point and the passenger's trajectory point is lower than the threshold distance, it is determined that the two trajectory points are together, and the trajectory point is regarded as a dangerous point. The proportion of dangerous points of all reported real-time trajectory points during the monitoring time is calculated. Based on the proportion, it is determined whether the driver and the passenger have not separated after the trip. If the proportion reaches the threshold proportion, it is determined that the driver and the passenger have not separated after the trip.

[0156] If the track of one of the driver and passenger is missing, the track of the other can be used to determine the location and execute steps 3 to 6.

[0157] Step 3: Obtain voice features. Figure 2 As shown, the specific process includes: the driver-side recording reports, the back-end RAPI stores the driver-side recording in real time, the AI-side recognition module performs AI voiceprint detection on the recording, and the algorithm side obtains the detected voiceprint information, that is, the voice features.

[0158] Step 4: Obtain image features. Figure 2 As shown in the figure, the specific process includes: the vehicle video terminal reports, the back-end RAPI stores the vehicle image information in real time, the AI ​​side recognition module performs AI image recognition on the vehicle image information, and the algorithm side obtains the recognized vehicle image information, that is, the image features.

[0159] Step 5: Figure 2 and Figure 3 As shown, the driver has a track but the passenger has no track: the algorithm side performs trajectory, voice, and image application calculations. Specifically, the algorithm side uses the trajectory information to perform feature analysis to obtain trajectory features, and then obtains voice features and image features. Combined with the trajectory features, voice features, and image features, it comprehensively determines whether the driver and passenger are still together after the trip.

[0160] Less than 30% of the orders have passenger tracks within a period of time (e.g., within 2 minutes) after the trip ends. Passenger tracks are often missing, so the driver's track is the main factor in determining the result. However, it is normal for the driver to drive or stay after the trip ends, so voice and image features are introduced to improve recognition accuracy. Figure 2 and Figure 3 As shown, if the driver stays in one location for a long time after the trip, and there is still a female voiceprint in the car or more than two people appear in the image inside the car, it can be considered to a certain extent that the driver and the passengers have not separated; if the driver passes the destination without stopping after the trip (i.e., passes without stopping), and there is no sound of opening and closing doors in the car or more than two people appear in the image inside the car (i.e., multiple people in the image), it can be judged that the passenger has not got off the car and the driver and the passengers have not separated.

[0161] Step 6: Figure 2 and Figure 3 As shown, the driver has no track but the passenger has a track: the algorithm side performs track and image application calculations. Specifically, the algorithm side uses the track information to perform feature analysis to obtain track features. For example, when the passenger speed exceeds the human walking speed limit, or the passenger stays at the point where the driver's track disappears, combined with the image features, it is determined that the driver and passenger have not separated after the trip.

[0162] Some criminal drivers will exit the driver terminal or turn off the device to commit crimes, so it is impossible to obtain the driver's trajectory and in-car recordings. In this case, it is necessary to start with the passenger trajectory and the video images of the in-car video terminal, such as Figure 3 As shown, if the passenger's speed exceeds the normal human walking speed limit (i.e., the passenger's speed is abnormal) or the passenger stays for a long time at the place where the driver's track disappears, and combined with image features, such as the presence of images of other people in the car besides the driver (i.e., there are multiple people in the image), it can be determined that the passenger has not got off the car and the driver and passenger have not separated.

[0163] If there are no tracks for the driver and passengers, the algorithm will use the track information to determine whether the driver and passengers have not separated after the trip. Then, execute step seven: After confirming that the tracks disappear at the same time and eliminating signal problems such as tunnels, it is possible that the driver is controlling the passenger's mobile phone. This is a high-risk signal, and it is directly determined that the driver and passengers have not separated after the trip.

[0164] In this way, the algorithm side will make a comprehensive judgment based on trajectory features, voice features and image features, and transmit the judgment result that the driver and passenger have not been separated after the trip to the engineering side. The engineering side will conduct technical interactions with the driver side, passenger side and customer service side, apply the results and implement intervention.

[0165] Judgment result application process:

[0166] like Figure 4 As shown, the system architecture involved in this process includes the passenger side, the driver side and the service side. Here, the architecture of the service side may at least include the algorithm side, the engineering side and the customer service side.

[0167] The engineering end uses the algorithm to determine that the driver and passenger have not separated after the trip, triggering high-risk intervention, deterring the driver (including broadcasting and sirens), and triggering a pop-up window on the passenger side. If the passenger does not click on the pop-up window to provide feedback on his or her safety situation, the engineering end will trigger the IVR voice automatic outbound call again to confirm the safety situation information with the passenger. If the passenger feedbacks that there is a safety issue, a customer service ticket will be created immediately, and a safety specialist will intervene manually through an outbound call or video contact to ensure the safety of the driver and passengers.

[0168] In this way, the safety protection of the driver and passengers after the trip is no longer strongly dependent on the situation where both the driver and passengers have tracks. When the track of one party is missing or all is missing due to the personal behavior of the driver and passengers or the technical reasons of the service platform, it can be comprehensively judged from the single-party track features and voice features and image features to determine whether the driver and passengers have not separated after the trip, thus achieving all-round safety monitoring. After the engineering side intervenes and transforms, the driver is deterred and the passenger is reminded. When the passenger does not feedback the safety situation of the platform itself, an artificial customer service work order will be immediately created and handed over to the security team for manual handling, and the safety situation will be confirmed with the driver and passengers to reduce the occurrence of sexual incidents.

[0169] Figure 5 Schematic diagram of an exemplary online car-hailing safety monitoring device according to an embodiment of the present application. Figure 5 As shown, the online car-hailing safety monitoring device 500 includes:

[0170] A first acquisition module 501 is used to acquire the trajectory of the driver and the passenger in real time as a target trajectory when it is determined that the trip of the online car-hailing order has ended and the trajectory of one of the driver and the passenger is missing;

[0171] A first analysis module 502, configured to perform feature analysis on a target trajectory to obtain at least one trajectory feature;

[0172] The judgment module 503 is used to judge whether the driver and the passenger are still together after the trip based on the trajectory characteristics, so as to monitor the safety of the driver and the passenger.

[0173] In one implementation, the determination module 503 is specifically configured to:

[0174] Determine whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result;

[0175] Based at least on the first determination result, it is determined whether the driver and the passenger are not separated after the trip is completed.

[0176] In one embodiment, Figure 6 As shown, it also includes:

[0177] The second acquisition module 504 is used to acquire environmental information reflecting the situation inside the vehicle in real time;

[0178] The second analysis module 505 is used to perform feature analysis on the environmental information to obtain at least one environmental feature;

[0179] The judgment module 503 is specifically used for:

[0180] Based on trajectory characteristics and environmental characteristics, determine whether the driver and passenger are still together after the trip.

[0181] In one implementation, the determination module 503 is specifically configured to:

[0182] Determine whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result;

[0183] Determine whether the environmental feature exists in the abnormal environmental feature set to obtain a second determination result;

[0184] Based on the first judgment result and the second judgment result, it is determined whether the driver and the passenger are still connected after the trip is completed.

[0185] In one embodiment, if the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination but continues to drive, and / or the driver stays at a location for more than a first preset time; and / or,

[0186] If the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger speed exceeds the walking speed limit, and / or the passenger stays at the missing part of the driver's trajectory for more than a second preset time.

[0187] In one embodiment, the abnormal environment feature set includes abnormal voice features and / or abnormal image features;

[0188] Abnormal image features include: multiple people in the car image after the trip, and / or the driver is not in the main driving seat;

[0189] Abnormal voice features include: after the trip, there are multiple voiceprints in the voice in the car, and / or there is a female voiceprint, and / or there is no sound of opening and closing the car door.

[0190] In one embodiment, Figure 6 As shown, it also includes:

[0191] The determination module 506 is used to determine that the driver and the passenger are not separated after the trip is completed when it is determined that the trip is completed and the tracks of both the driver and the passenger are missing.

[0192] In one embodiment, Figure 6 As shown, it also includes:

[0193] The trigger module 507 is used to trigger the driver to send a deterrent signal and / or trigger the passenger to feedback the passenger's safety information when the driver and the passenger are not separated after the trip.

[0194] In one embodiment, Figure 6 As shown, it also includes:

[0195] A creation module 508 is used to create a customer service ticket and assign it to a safety specialist if the passenger is unsafe, so that the safety specialist can intervene.

[0196] In one embodiment, Figure 6 As shown, it also includes:

[0197] The third acquisition module 509 is used to acquire the characteristics of the driver and passengers;

[0198] Create module 508, specifically for:

[0199] Determine the safety risk level based on the characteristics of the driver and passengers;

[0200] Create a customer service ticket corresponding to the security risk level and assign it to a security specialist corresponding to the security risk level.

[0201] In one embodiment, Figure 6 As shown, it also includes:

[0202] The outbound calling module 510 is used to initiate an outbound call to the passenger terminal to obtain the passenger's safety information if the passenger terminal does not feedback the passenger's safety information.

[0203] The functions of each module in each device in the embodiments of the present application can be found in the corresponding description in the above-mentioned online car-hailing safety monitoring method embodiment, and will not be repeated here.

[0204] An embodiment of the present application also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for monitoring the safety of an online car-hailing service as in any of the above embodiments is implemented.

[0205] Figure 7 is a schematic diagram of the structure of an exemplary electronic device provided in an embodiment of the present application. Figure 7 As shown, the electronic device may include: a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704. The processor 701 may call a computer program in the memory 703 to execute the online car-hailing safety monitoring method in any of the above embodiments.

[0206] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the online car-hailing safety monitoring method as in any of the above embodiments is implemented.

[0207] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0208] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0209] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0210] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0211] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0212] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0213] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0214] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for monitoring the safety of online ride-hailing vehicles, characterized in that: include: When it is determined that the trip of the online ride-hailing order has ended and the trajectory of one of the driver and the passenger is missing, the trajectory of the other driver and the passenger is obtained in real time as the target trajectory; Performing feature analysis on the target trajectory to obtain at least one trajectory feature; Based on the trajectory characteristics, determining whether the driver and passenger have not separated after the trip is completed to monitor the safety of the driver and passengers; The determining, based on the trajectory characteristics, whether the driver and passenger are still together after the trip ends includes: Determining whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result; Determining, based on the first judgment result, whether the driver and passenger have not separated after the trip is completed; If the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination and continues driving, and / or the driver stays at a location for longer than a first preset time; and / or, if the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger's speed exceeds the walking speed limit, and / or the passenger stays at a location where the driver's trajectory is missing for longer than a second preset time.

2. The method according to claim 1, characterized in that Also includes: Obtain environmental information reflecting the situation inside the vehicle in real time; Performing feature analysis on the environmental information to obtain at least one environmental feature; The determining, based on the trajectory characteristics, whether the driver and passenger are still together after the trip ends includes: Based on the trajectory characteristics and the environmental characteristics, determining whether the driver and passenger are still together after the trip is completed; The determining, based on the trajectory feature and the environmental feature, whether the driver and passenger are not separated after the trip ends, includes: determining whether the trajectory feature exists in a set of abnormal trajectory features to obtain a first determination result; Determining whether the environmental feature exists in the abnormal environmental feature set to obtain a second determination result; determining whether the driver and passenger have not separated after the trip is completed based on the first judgment result and the second judgment result; The abnormal environment feature set includes abnormal voice features and / or abnormal image features; The abnormal image features include: after the trip is completed, there are multiple people in the car image, and / or the driver is not in the main driving seat; The abnormal voice features include: after the trip ends, the voice in the car has multiple voiceprints, and / or a female voiceprint, and / or no door opening and closing sounds; If the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination and continues driving, and / or the driver stays at a location for longer than a first preset time; and / or, if the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger's speed exceeds the walking speed limit, and / or the passenger stays at a location where the driver's trajectory is missing for longer than a second preset time.

3. The method according to claim 1, characterized in that Also includes: When it is determined that the trip is finished and both the driver and the passenger's tracks are missing, it is determined that the driver and the passenger are not separated after the trip is finished.

4. The method according to claim 1 or 3, characterized in that Also includes: In the event that the driver and passenger are not separated after the trip, the driver side is triggered to send a deterrent signal, and / or the passenger side is triggered to feedback information about the passenger's safety.

5. The method according to claim 4, characterized in that Also includes: If the passenger is unsafe, a customer service ticket is created and assigned to a safety officer to enable said safety officer to intervene.

6. The method according to claim 5, characterized in that Also includes: Obtain driver and passenger characteristics; Creating a customer service ticket and assigning it to a security specialist includes: Determining a safety risk level based on the driver and passenger characteristics; A customer service ticket corresponding to the security risk level is created and assigned to a security specialist corresponding to the security risk level.

7. The method according to claim 6, characterized in that Also includes: If the passenger terminal does not feedback the passenger's safety information, initiate an outbound call to the passenger terminal to obtain the passenger's safety information.

8. A safety monitoring device for online car-hailing, characterized in that: include: A first acquisition module is configured to, when it is determined that the trip of the online ride-hailing order has ended and the trajectory of one of the driver and the passenger is missing, acquire the trajectory of the other driver and the passenger in real time as a target trajectory; a first analysis module, configured to perform feature analysis on the target trajectory to obtain at least one trajectory feature; a determination module, configured to determine, based at least on the trajectory characteristics, whether the driver and passenger have not separated after the trip is completed, so as to monitor the safety of the driver and passenger; The judgment module is specifically used to: Determining whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result; Determining, based on the first judgment result, whether the driver and passenger have not separated after the trip is completed; If the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination and continues driving, and / or the driver stays at a location for longer than a first preset time; and / or, if the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger's speed exceeds the walking speed limit, and / or the passenger stays at a location where the driver's trajectory is missing for longer than a second preset time.

9. The device according to claim 8, characterized in that Also includes: The second acquisition module is used to obtain environmental information reflecting the situation inside the vehicle in real time; a second analysis module, configured to perform feature analysis on the environmental information to obtain at least one environmental feature; The judgment module is specifically used to: Based on the trajectory characteristics and the environmental characteristics, determining whether the driver and passenger are still together after the trip is completed; The judgment module is specifically used to: Determining whether the trajectory feature exists in the abnormal trajectory feature set to obtain a first determination result; Determining whether the environmental feature exists in the abnormal environmental feature set to obtain a second determination result; determining whether the driver and passenger have not separated after the trip is completed based on the first judgment result and the second judgment result; The abnormal environment feature set includes abnormal voice features and / or abnormal image features; The abnormal image features include: after the trip is completed, there are multiple people in the car image, and / or the driver is not in the main driving seat; The abnormal voice features include: after the trip ends, the voice in the car has multiple voiceprints, and / or a female voiceprint, and / or no door opening and closing sounds; If the target trajectory is a driver trajectory, the abnormal trajectory feature set includes: after the trip ends, the driver does not stop at the destination and continues driving, and / or the driver stays at a location for longer than a first preset time; and / or, if the target trajectory is a passenger trajectory, the abnormal trajectory feature set includes: after the trip ends, the passenger's speed exceeds the walking speed limit, and / or the passenger stays at a location where the driver's trajectory is missing for longer than a second preset time.

10. The device according to claim 9, characterized in that Also includes: The determination module is used to determine that the driver and the passenger are not separated after the trip is completed when it is determined that the trip is completed and the tracks of both the driver and the passenger are missing.

11. The device according to claim 8 or 10, characterized in that Also includes: The trigger module is used to trigger the driver side to send a deterrent signal and / or trigger the passenger side to feedback passenger safety information when the driver and passenger are not separated after the trip is completed.

12. The device according to claim 11, characterized in that Also includes: Create a module that creates a customer service ticket and assigns it to a safety officer to intervene if a passenger is unsafe.

13. The device according to claim 12, characterized in that Also includes: The third acquisition module is used to obtain driver and passenger characteristics; The creation module is specifically used to: Determining a safety risk level based on the driver and passenger characteristics; A customer service ticket corresponding to the security risk level is created and assigned to a security specialist corresponding to the security risk level.

14. The device according to claim 11, characterized in that Also includes: The outbound call module is used to initiate an outbound call to the passenger terminal to obtain the passenger's safety information if the passenger terminal does not feedback the passenger's safety information.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images