WO2020082900A1 - 订单服务安全性检测装置及方法 - Google Patents

订单服务安全性检测装置及方法 Download PDF

Info

Publication number
WO2020082900A1
WO2020082900A1 PCT/CN2019/103945 CN2019103945W WO2020082900A1 WO 2020082900 A1 WO2020082900 A1 WO 2020082900A1 CN 2019103945 W CN2019103945 W CN 2019103945W WO 2020082900 A1 WO2020082900 A1 WO 2020082900A1
Authority
WO
WIPO (PCT)
Prior art keywords
duration
order
service
historical
service provider
Prior art date
Application number
PCT/CN2019/103945
Other languages
English (en)
French (fr)
Inventor
韩福波
刘亚书
Original Assignee
北京嘀嘀无限科技发展有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京嘀嘀无限科技发展有限公司 filed Critical 北京嘀嘀无限科技发展有限公司
Publication of WO2020082900A1 publication Critical patent/WO2020082900A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/01—Customer relationship services
    • G06Q30/012—Providing warranty services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/02—Reservations, e.g. for tickets, services or events
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Definitions

  • the present disclosure relates to the field of information technology, and in particular, to an order service security detection device and method.
  • Online car rental is the abbreviation of online taxi booking. Passengers can make reservations with the driver on the online car rental platform through mobile devices. After taking the order, the driver picks up the passenger at the appointed place to pick up the destination to facilitate passenger travel.
  • online car-hailing (such as taxis, special cars, express trains, tailwinds, etc.) are more common to meet users' more diversified travel needs.
  • the purpose of the present disclosure is to provide an order service security detection device and method, which can detect the security of the order service, and the detection accuracy is better.
  • the present disclosure provides an order service security detection device.
  • the device includes a processor, a storage medium, and a bus.
  • the storage medium stores machine-readable instructions executable by the processor.
  • the processor and all The storage medium communicates via a bus, and the processor executes the machine-readable instructions to perform the following processing:
  • the service safety of the current travel order is determined according to driving stop information and route offset information of the service provider.
  • the device further includes: a communication interface; the communication interface and the processor communicate via a bus;
  • the communication interface is used to receive track point data during the execution of the current travel order reported by the service provider or the service requester.
  • the track point data during the execution of the current travel order reported by the received service provider or service request end is used as the track point data during the current travel order of the service provider.
  • the driving stay information includes staying position information and staying time;
  • the route offset information includes continuous route offset time; for driving stay information and route offset information according to the service provider, determine the For the service security of the current travel order, when the machine-readable instructions are executed by the processor, the following processing is performed: including:
  • the service provider end stays at a position where the secludedness is greater than the secludedness threshold value, and the stayed duration is greater than the first durational threshold value;
  • the duration of the continuous route offset of the service provider is greater than the second duration threshold.
  • any location it is determined according to the following steps whether the location is a location with a secludedness greater than a secludedness threshold, and the machine-readable instructions are executed as follows when executed by the processor:
  • the outlier corresponding to the area is greater than the outlier threshold, it is determined that any one of the locations is a location with an outlier greater than the outlier threshold.
  • the following processing is also performed.
  • the method further includes:
  • the historical abnormal travel order refers to a travel order that receives user complaints
  • any of the maximum stay duration and the remoteness of any sampling trajectory point as a pairing combination to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the pairing combination; the historical travel order coverage corresponding to the pairing combination
  • the quantity refers to the number of historical travel orders whose outliers in a sampling track point are greater than the outliers in the pairing combination, and whose staying time at the sampling track point is greater than the maximum staying time in the pairing combination; the pairing combination corresponds to
  • the historical abnormal order recall rate refers to the historical anomalous travel after a survey, the remoteness of a sampling trajectory point is greater than the remoteness of the pairing combination, and the stay time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the outlier threshold and the first duration threshold are determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination.
  • the outlier threshold and the first duration threshold are determined, and the machine-readable instruction is executed when executed by the processor.
  • the following processing includes:
  • the preset historical travel order coverage selection range and historical abnormal order recall rate selection range select a pairing combination and combine the selected pairing combinations
  • the outlier in is used as the outlier threshold
  • the maximum stay duration in the selected pairing combination is used as the first duration threshold.
  • For each maximum continuous offset duration determine the historical travel order coverage and historical abnormal order recall rate corresponding to the maximum continuous offset duration; where the historical travel order coverage corresponding to the maximum continuous offset duration refers to the corresponding maximum The number of historical travel orders whose continuous offset duration is greater than the current maximum continuous offset duration; the historical abnormal order recall rate corresponding to the maximum continuous offset duration means that after investigation, the corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration The proportion of historical abnormal travel orders with offset time in all historical abnormal travel orders;
  • the second duration threshold is determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration.
  • the machine-readable instruction executed by the processor performs the following processes including: :
  • the selected maximum continuous offset duration is used as the second duration threshold.
  • the duration of the continuous duration of the angle between the current travel direction of the service provider and the reference travel direction being greater than the set angle threshold is determined as the duration of continuous deviation of the route;
  • the reference travel direction refers to the provision from the service The connection direction of the current track point position of the terminal and the destination of the current travel order.
  • the following processing is also performed.
  • the method further includes:
  • the processing strategy corresponding to the determined duration range is executed according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong.
  • a processing strategy corresponding to the determined duration range is executed, and when the machine-readable instruction is executed by the processor, the following processing includes: :
  • duration range belongs to the first duration range, send a preset prompt voice to the service provider and / or service request end;
  • duration range belongs to the second duration range, send a security confirmation request voice waiting for voice feedback to the service provider and / or service request end;
  • duration range belongs to the third duration range, initiate a manual call request to the service provider and / or service request end;
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range.
  • the security confirmation request voice is repeatedly sent until the security confirmation voice is received, or until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold, a manual call request is initiated;
  • the present disclosure also provides an order service security detection method device.
  • the method device includes: a processor, a storage medium, and a bus, the storage medium stores machine-readable instructions executable by the processor, and the processing
  • the processor communicates with the storage medium through a bus, and the processor executes the machine-readable instructions to perform the following processes including:
  • the present disclosure also provides an order service security detection method, which includes:
  • the service safety of the current travel order is determined according to driving stop information and route offset information of the service provider.
  • the driving stay information includes staying location information and staying time;
  • the route offset information includes continuous route offset time; according to the driving stopping information and route offset information of the service provider, determine the current
  • the service security of the travel order may include: when any one of the following conditions is met, determining that there is a problem with the service security of the current travel order:
  • the service provider end stays at a position where the secludedness is greater than the secludedness threshold value, and the stayed duration is greater than the first durational threshold value;
  • the duration of the continuous route offset of the service provider is greater than the second duration threshold.
  • any location it can be determined whether the location is a location with a secludedness greater than a secludedness threshold according to the following steps:
  • the outlier corresponding to the area is greater than the outlier threshold, it is determined that any one of the locations is a location with an outlier greater than the outlier threshold.
  • the method further includes:
  • the remoteness threshold and the first duration threshold may be determined according to the following steps:
  • the historical abnormal travel order refers to a travel order that receives user complaints
  • any of the maximum stay duration and the remoteness of any sampling trajectory point as a pairing combination to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the pairing combination; the historical travel order coverage corresponding to the pairing combination
  • the quantity refers to the number of historical travel orders whose outliers in a sampling track point are greater than the outliers in the pairing combination, and whose staying time at the sampling track point is greater than the maximum staying time in the pairing combination; the pairing combination corresponds to
  • the historical abnormal order recall rate refers to the historical anomalous travel after a survey, the remoteness of a sampling trajectory point is greater than the remoteness of the pairing combination, and the stay time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the outlier threshold and the first duration threshold are determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination.
  • determining the outlier threshold and the first duration threshold according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination may include:
  • the preset historical travel order coverage selection range and historical abnormal order recall rate selection range select a pairing combination and combine the selected pairing combinations
  • the outlier in is used as the outlier threshold
  • the maximum stay duration in the selected pairing combination is used as the first duration threshold.
  • the second duration threshold may be determined according to the following steps:
  • For each maximum continuous offset duration determine the historical travel order coverage and historical abnormal order recall rate corresponding to the maximum continuous offset duration; where the historical travel order coverage corresponding to the maximum continuous offset duration refers to the corresponding maximum The number of historical travel orders whose continuous offset duration is greater than the current maximum continuous offset duration; the historical abnormal order recall rate corresponding to the maximum continuous offset duration means that after investigation, the corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration The proportion of historical abnormal travel orders with offset time in all historical abnormal travel orders;
  • the second duration threshold is determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration.
  • determining the second duration threshold according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration may include:
  • the selected maximum continuous offset duration is used as the second duration threshold.
  • the continuous offset duration of the route may be determined according to the following steps:
  • the duration of the continuous duration of the angle between the current travel direction of the service provider and the reference travel direction being greater than the set angle threshold is determined as the duration of continuous deviation of the route;
  • the reference travel direction refers to the provision from the service The connection direction of the current track point position of the terminal and the destination of the current travel order.
  • the method further includes:
  • the processing strategy corresponding to the determined duration range is executed according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong.
  • execution of a processing strategy corresponding to the determined duration range includes:
  • duration range belongs to the first duration range, send a preset prompt voice to the service provider and / or service request end;
  • duration range belongs to the second duration range, send a security confirmation request voice waiting for voice feedback to the service provider and / or service request end;
  • duration range belongs to the third duration range, initiate a manual call request to the service provider and / or service request end;
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range.
  • the method further includes:
  • the security confirmation request voice is repeatedly sent until the security confirmation voice is received, or until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold, a manual call request is initiated;
  • the present disclosure also provides an order service security detection method, which includes:
  • An embodiment of the present disclosure also provides an order service security detection device.
  • the device includes:
  • Track point acquisition module configured to acquire track point data of the service provider during the current travel order process of the service
  • the information determining module is configured to determine driving stop information and route offset information of the service provider based on the track point data
  • the safety detection module is configured to determine the service safety of the current travel order according to driving stop information and route offset information of the service provider.
  • the driving stop information includes stop position information and stop duration;
  • the route offset information includes continuous route offset duration;
  • the security detection module is specifically configured to: when any one of the following conditions is met, determine that there is a problem with the service security of the current travel order:
  • the service provider end stays at a position where the secludedness is greater than the secludedness threshold value, and the stayed duration is greater than the first durational threshold value;
  • the duration of the continuous route offset of the service provider is greater than the second duration threshold.
  • the security detection module is specifically configured as:
  • the outlier corresponding to the area is greater than the outlier threshold, it is determined that any one of the locations is a location with an outlier greater than the outlier threshold.
  • the device may further include:
  • the remoteness determination module is configured to divide the range of the target geographic area into a plurality of areas of preset sizes; determine the number of orders generated in each divided area; and determine the remoteness of each divided area according to the number of orders degree.
  • the device may further include:
  • the first threshold determination module is configured to separately obtain the maximum stay time of each historical abnormal travel order at each sampling trajectory point and the remoteness of the sampling trajectory point corresponding to the maximum stay time; the historical abnormal travel order refers to the user complaint received Travel orders;
  • any of the maximum stay duration and the remoteness of any sampling trajectory point as a pairing combination to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the pairing combination; the historical travel order coverage corresponding to the pairing combination
  • the quantity refers to the number of historical travel orders whose outliers in a sampling track point are greater than the outliers in the pairing combination, and whose staying time at the sampling track point is greater than the maximum staying time in the pairing combination; the pairing combination corresponds to
  • the historical abnormal order recall rate refers to the historical anomalous travel after a survey, the remoteness of a sampling trajectory point is greater than the remoteness of the pairing combination, and the stay time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the outlier threshold and the first duration threshold are determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination.
  • the first threshold determination module is specifically configured to be based on the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination, as well as the preset historical travel order coverage selection range and historical abnormal order recall Select a pairing combination, and select the outlier in the selected pairing combination as the outlier threshold, and use the maximum stay duration in the selected pairing combination as the first duration threshold.
  • the device may further include:
  • the second threshold determination module is configured to separately obtain the maximum continuous offset duration of each historical abnormal travel order
  • For each maximum continuous offset duration determine the historical travel order coverage and historical abnormal order recall rate corresponding to the maximum continuous offset duration; where the historical travel order coverage corresponding to the maximum continuous offset duration refers to the corresponding maximum The number of historical travel orders whose continuous offset duration is greater than the current maximum continuous offset duration; the historical abnormal order recall rate corresponding to the maximum continuous offset duration means that after investigation, the corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration The proportion of historical abnormal travel orders with offset time in all historical abnormal travel orders;
  • the second duration threshold is determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration.
  • the second threshold determination module is specifically configured to be based on the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration, and the preset historical travel order coverage selection range and history In the selection range of the abnormal order recall rate, a maximum continuous offset duration is selected, and the selected maximum continuous offset duration is used as the second duration threshold.
  • the device may further include:
  • An offset duration determining module configured to determine a continuous duration in which the angle between the current travel direction of the service provider and the reference travel direction is greater than a set angle threshold as the continuous offset duration of the route; the reference travel The direction refers to the connection direction from the current track point position of the service provider and the destination of the current travel order.
  • the device may further include:
  • the processing module is configured to execute a processing strategy corresponding to the determined duration range according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong.
  • processing module is specifically configured as:
  • duration range belongs to the first duration range, send a preset prompt voice to the service provider and / or service request end;
  • duration range belongs to the second duration range, send a security confirmation request voice waiting for voice feedback to the service provider and / or service request end;
  • duration range belongs to the third duration range, initiate a manual call request to the service provider and / or service request end;
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range.
  • processing module is specifically configured as:
  • the security confirmation request voice is repeatedly sent until the security confirmation voice is received, or until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold, a manual call request is initiated;
  • the present disclosure also provides an order service security detection device, which includes:
  • Track point acquisition module configured to acquire track point data of the service provider during the current travel order process of the service
  • An information determination module configured to determine driving stop information of the service provider based on the track point data
  • the safety detection module is configured to determine the service safety of the current travel order according to the driving stop information of the service provider.
  • the present disclosure also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, which is executed by a processor to execute the order service security as described in any one of the first and second aspects Steps of sex testing methods.
  • FIG. 1 shows a flowchart of an order service security detection method provided in Embodiment 1 of the present disclosure
  • FIG. 2 shows a flowchart of an order service security detection method provided by an embodiment of the present disclosure
  • FIG. 3 shows a flowchart of an order service security detection method provided in Embodiment 3 of the present disclosure
  • FIG. 4 shows a flowchart of an order service security detection method provided in Embodiment 4 of the present disclosure
  • FIG. 5 shows an application schematic diagram of an order service security detection method provided in Embodiment 4 of the present disclosure
  • FIG. 6 shows a flowchart of an order service security detection method provided in Embodiment 6 of the present disclosure
  • Embodiment 7 is a schematic structural diagram of an order service security detection device provided in Embodiment 7 of the present disclosure.
  • Embodiment 8 is a schematic structural diagram of an order service security detection device provided in Embodiment 8 of the present disclosure.
  • FIG. 9 shows a schematic structural diagram of an order service security detection device provided in Embodiment 9 of the present disclosure.
  • Vehicles in the transportation system may include taxis, private cars, tailwinds, buses, trains, bullet trains, high-speed railways, subways, or driverless vehicles, etc., or any combination thereof.
  • the present disclosure may also include any service system for providing safety detection of ride-hailing.
  • Applications of the system or method of the present disclosure may include web pages, browser plug-ins, client terminals, customized systems, internal analysis systems, artificial intelligence robots, etc., or any combination thereof.
  • bypassenger “passenger”, “service requester”, “service staff”, “service requester”, “customer”, “passenger terminal” or “service requester” in this disclosure are used interchangeably to refer to the request Or individuals, entities or tools that order services.
  • driver “service provider”, “service provider”, “supplier”, “driver”, “driver terminal” or “service provider” in this disclosure are used interchangeably to refer to Individuals, entities or tools that can provide services.
  • user in this disclosure may refer to an individual, entity, or tool that requests a service, subscribes to a service, provides a service, or facilitates the provision of a service. For example, the user may be a passenger, driver, operator, etc., or any combination thereof.
  • service request and “order” in this disclosure are used interchangeably to refer to requests initiated by passengers, service requesters, drivers, service providers, or suppliers, etc., or any combination thereof. Accepting the "service request” or “order” may be passengers, service requesters, drivers, service providers, or suppliers, etc., or any combination thereof. Service requests can be paid or free.
  • the present application provides an order service security that determines the service security of the current travel order by analyzing and processing driving stop information and route offset information obtained from the track point data of the service provider Detection scheme.
  • the order service security detection method provided by this application can effectively detect the security of order services, and the detection accuracy is good.
  • the following is a detailed description through several embodiments.
  • FIG. 1 it is a flowchart of an order service security detection method provided in Embodiment 1 of the present disclosure.
  • the method may be executed by a background server.
  • the above order service security detection method includes the following steps:
  • the track point data may be obtained from the existing taxi platform.
  • ride-hailing information such as travel start information and travel destination information
  • the travel order in service can also record the track point data of each driving track point during the driving process, such as Time information, position information, speed information, etc. of each track point.
  • the above travel orders can also include other taxi information, such as the type of car information, taxi, express, special car, ride, etc.
  • the position information in the track point data of the driving track points can be determined using positioning technology, and the speed information can be determined using sensor technology.
  • the positioning technology used in this disclosure may be based on Global Positioning System (Global Positioning System, GPS), Global Navigation Satellite System (Global Navigation Satellite System, GLONASS), Compass Navigation System (COMPASS), Galileo Positioning System, Quasi-Zenith Satellite System (QZSS), Wireless Fidelity (WiFi) positioning technology, etc., or any combination thereof.
  • GPS Global Positioning System
  • GLONASS Global Navigation Satellite System
  • Compass Navigation System COMPASS
  • Galileo Positioning System Galileo Positioning System
  • QZSS Quasi-Zenith Satellite System
  • WiFi Wireless Fidelity
  • the positioning device collects position information
  • the position information of the track point can be sent out every preset time interval (such as 1s), so that the background server can obtain the position information of each track point, and can also use
  • the sampling technology adopts the position information of some track points, which is not specifically limited in the embodiments of the present disclosure.
  • the track point data of the starting track point and the ending track point mainly refer to the travel starting point position corresponding to the starting point and the traveling end point position corresponding to the ending point.
  • the position information can also be determined using positioning technology.
  • the user's current position can be automatically positioned as the starting point for travel.
  • the user can select a specific travel starting point location on the map, or manually enter the travel starting point location, such as manually entering the "AA airport" travel starting point location, the above travel ending position is mainly used by the user to select on the map or manually enter the way To determine, not repeat them here.
  • S102 Determine driving stop information and route offset information of the service provider based on the track point data.
  • the embodiments of the present disclosure may use the corresponding track point data to determine driving stop information and route offset information of the service provider.
  • the driving stop information may indicate the stop situation of the service provider at a certain track point, and may include not only the position information of the stop point where the stop point is, but also the length of the stop point at the stop point.
  • the description of the location information has already been explained above, and will not be repeated here.
  • the dwell time of the track point can be determined by the time difference between the time when the position first appears in the track point data and the time when it last appears in the track point data.
  • the above-mentioned driving stop information also includes information on the duration of staying at any place in the remote area.
  • the embodiment of the present disclosure can determine whether the area at any location is a remote area according to the following steps: travel according to each historical travel order Geographical information, determine the area where the number of orders generated within the latest preset time period is lower than the target quantity threshold (such as 100), and use the determined area as a remote area.
  • the route offset information may indicate the driving situation of the service provider, mainly including the duration of continuous route offset.
  • the duration of the continuous offset of the relevant route may be determined by the duration that the angle between the current driving direction and the reference driving direction of the service provider is continuously greater than the set angle threshold.
  • S103 Determine the service safety of the current travel order according to driving stop information and route offset information of the service provider.
  • the current travel environment can be determined whether there is an abnormality in the current travel environment based on the remoteness threshold and the stay duration threshold to determine whether there is a problem with the service security of the current travel order.
  • the current travel environment can also be determined based on the offset duration threshold Is there any abnormality in the driving situation to determine whether there is a problem with the service safety of the current travel order.
  • the embodiment of the present disclosure is to capture the above-mentioned small probability event in time, and determine the staying time of the trajectory point based on the trajectory data.
  • the present The disclosed embodiment can also determine the location information of the track point where the stay is.
  • the location is relatively remote (such as the location's remoteness is greater than the remoteness threshold), and the stay time is too long (such as the location's stay longer than the stay duration threshold), you can basically determine that there is a problem with service security.
  • the stay time is too long (such as the location's stay longer than the stay duration threshold)
  • the route offset information may indicate the driving situation of the service provider, mainly including the duration of continuous route offset.
  • the taxi platform can determine the travel route from the travel start point to the travel end point according to the travel start information and the travel end information selected by the user, even though there may be a certain degree of route deviation due to the influence of the traffic environment during the driving process
  • continuous offsets (such as the continuous offset duration of the route is greater than the offset duration threshold) can basically determine that there is a problem with service security.
  • the embodiments of the present disclosure may determine the outlier corresponding to any position in the area based on the outlier corresponding to the area, so that when any area is an area with an outlier greater than an outlier threshold (a outlying area), it can be considered as within the area
  • Any location of is a location with a remoteness greater than the remoteness threshold (ie, a remote location).
  • pre-saved information indicating whether each area is an area with a secluded degree greater than the set secludedness threshold at this time, according to the area where any location is located, you can directly know whether the location is a secluded degree greater than a secluded
  • the location of the threshold in addition, the pre-stored may be the secludedness and secludedness threshold of each area.
  • the threshold value is compared, and the embodiment of the present disclosure does not specifically limit this.
  • the remoteness of the above-mentioned area may be predetermined.
  • the remoteness of the area can be determined as follows:
  • the target geographic area is first divided into a plurality of areas of a predetermined size, then the number of orders in each divided area is determined, and finally the remoteness of the area is determined according to the number of orders.
  • the number of orders in each area may be determined based on the statistical result of the number of orders located in the area where the departure point is. In order to count the number of orders for each region, you can count the number of historical orders generated in a recent period (such as 7 days). In this way, the remoteness of each area can be determined based on the ratio of the total number of orders within the target geographic area to the number of orders generated in each area, and the smaller the number of orders generated, the greater the corresponding remoteness . In addition, for each region, the embodiments of the present disclosure can also comprehensively consider the order origination time for generating orders in the region, and the influence factors of other regions on the region to determine the remoteness of the region.
  • the embodiments of the present disclosure may divide the area according to a preset size. For example, with respect to the target geographic area of City A, the embodiment of the present disclosure may divide City A into several areas, and the shape of each area may be a quadrilateral, a hexagon, or other polygons.
  • Embodiments of the present disclosure comprehensively consider the knowledge of world geography, and city A can be divided into multiple quadrilateral regions in sequence, and the length of the quadrilateral can be from hundreds of meters to several kilometers.
  • the selected side length is not easy to be too large or too small, and a side length of 120 m may be selected.
  • the embodiments of the present disclosure may use the Geohash encoding algorithm to divide the range of the target geographic area into several rectangular areas, and may also encode each rectangular area (such as hash coding), and use the coding result as corresponding to the rectangular area Identification information. In this way, based on the mapping relationship between each identification information and each outlier, the outlier corresponding to the area where the current track track point is located can be found.
  • the embodiments of the present disclosure may use the historical travel order coverage and the historical abnormal order recall rate to determine the threshold. Described by the following example three
  • Embodiment 3 of the present disclosure provides a threshold determination method.
  • the method specifically includes the following steps:
  • the determination of the threshold value depends on the analysis result of each historical abnormal travel order. That is, the embodiment of the present disclosure may first determine the stay time of the abnormal trajectory point for each historical abnormal travel order. There can be one or more abnormal track points. Generally speaking, there can be one abnormal trajectory point where a malignant event occurs. In this way, the abnormal trajectory point may be the sampling trajectory point with the longest residence time. If there are multiple abnormal trajectory points, the embodiment of the present disclosure may first sort the stay duration of each sampled trajectory point in order from large to small, and select the top-ranked abnormal trajectory point. In order to facilitate the subsequent description, the description will be made with an abnormal track point.
  • the corresponding maximum stay time can be determined for each historical abnormal travel order.
  • each determined maximum stay time and the outlier of the corresponding sampling trajectory point can be paired and combined to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the paired combination.
  • the corresponding target pairing combination can be selected from all pairing combinations to determine the outlier threshold and the first duration threshold.
  • the historical travel order coverage corresponding to the above-mentioned pairing combination means that the outlier of a sampling trajectory point is greater than that in the pairing combination, and the staying time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the number of historical travel orders, that is, the above historical travel order coverage can indicate the number of historical travel orders covered by the pairing combination;
  • the historical abnormal order recall rate corresponding to the above pairing combination refers to the remoteness of a sampling track point after investigation
  • the proportion of historical anomalous travel orders that are greater than the outlier in the paired combination and the duration of stay at the sampling track point is greater than the maximum duration of the paired combination in all historical anomalous travel orders, that is, the above historical anomalies
  • the order recall rate can indicate the historical abnormal travel orders that the current pairing combination can correctly identify account for the proportion of all historical abnormal travel orders.
  • different pairing combinations may be selected for different application requirements to determine the threshold.
  • each historical abnormal travel order corresponds to 1 maximum stay time and corresponding 1 outlier, and the maximum stay time of any two historical abnormal travel orders is different and remote Also different.
  • the corresponding historical travel order coverage and historical abnormal order recall rate are determined. According to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination, as well as the preset historical travel order coverage selection range and historical abnormal order recall rate selection range, select a pairing combination to determine the outlier threshold and the The first duration threshold.
  • the selection range of the historical travel order coverage is mainly related to the service processing capacity of the customer service personnel of the taxi platform
  • the historical abnormal order recall rate is mainly related to the accuracy of the abnormal judgment.
  • the corresponding pairing combination can be selected according to the specific operation strategy of the taxi platform to meet the dual requirements of service processing capability and accuracy of abnormality determination.
  • the embodiments of the present disclosure may use the historical travel order coverage and the historical abnormal order recall rate to determine the threshold. It is described by the following example four.
  • Embodiment 4 of the present disclosure provides a threshold determination method, which specifically includes the following steps:
  • the determination of the threshold here can also depend on the analysis results of various historical abnormal travel orders. That is, the embodiment of the present disclosure may first determine the continuous offset duration for each historical abnormal travel order.
  • the continuous offset duration can be one or multiple. For a continuous offset duration, it can be directly used as the maximum continuous offset duration. If there are multiple continuous offset durations, the embodiments of the present disclosure may first sort the continuous offset durations in order from large to small, and select The top continuous offset duration is regarded as the maximum continuous offset duration.
  • the corresponding maximum continuous offset duration can be determined for each historical abnormal travel order.
  • the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration can be determined.
  • the corresponding target maximum continuous offset duration can be selected from all the maximum continuous offset durations to determine the second duration threshold.
  • the historical travel order coverage corresponding to the maximum continuous offset duration mentioned above refers to the number of historical travel orders whose corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration, that is, the historical travel order coverage can be Indicates the number of historical travel orders covered by the pairing combination;
  • the historical abnormal order recall rate corresponding to the maximum continuous offset duration refers to the historical abnormal travel order whose corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration after investigation
  • the proportion of orders in all historical abnormal travel orders that is, the above-mentioned historical abnormal order recall rate can indicate the current maximum continuous offset duration that can correctly identify the historical abnormal travel orders accounted for the proportion of all historical abnormal travel orders.
  • the selection range of historical travel order coverage and historical abnormal order recall rate can also be selected according to the specific operating strategy of the taxi platform.
  • the continuous duration of the included angle between the current traveling direction and the reference traveling direction of the service providing end being greater than the set included angle threshold may be used as the duration of the continuous route offset.
  • the reference driving direction refers to the connection direction from the current track point position of the service provider and the destination of the current travel order.
  • the set angle threshold can be selected from 0 degrees to 180 degrees. The embodiment of the present disclosure can select 90 degrees as the set angle threshold. If the angle between the current driving direction and the reference driving direction is continuously greater than 90 degrees, It means that the track point continues to travel away from the end point.
  • P0-P5 are the path trajectory points of a historical abnormal travel order
  • S and D correspond to the starting trajectory point and the end trajectory point of the historical abnormal travel order. It can be seen from FIG. 5 that for P0, P1, P3, P4, and P5, the angle between the current driving direction and the reference driving direction at these trajectory points is less than 90 degrees, indicating that these trajectory points are driving near the end point, and For P2, the angle between the current driving direction and the reference driving direction is continuously greater than 90 degrees. If the continuous time to point P4 is greater than the second duration threshold, it can be determined that an offset abnormality has started to occur at the track point P4. That is, there should be a problem with the service security of current travel orders.
  • the embodiments of the present disclosure may execute a processing strategy corresponding to the determined duration range according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong. Next, it will be further described by the following embodiment five.
  • the excessively long stay time and / or the excessively long offset time of the service provider can correspond to corresponding abnormal intervention strategies, and the longer the length of the stay time and / or the continuous offset time of the route belong to, respectively.
  • the embodiments of the present disclosure may adopt exception intervention strategies ranging from light to heavy to perform exception handling to restrict the service behavior of the service provider while ensuring the safety of passengers' cars.
  • abnormal intervention strategies mainly include voice broadcast, security confirmation request voice, and manual call.
  • the duration range belongs to the first duration range
  • a preset prompt voice is sent to the service provider and / or service requesting end
  • the duration range belongs to the second duration range
  • the service provider and / Or the service requesting end sends a security confirmation request voice waiting for voice feedback
  • the time range belongs to the third time duration range
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range. It can be seen that the current intervention duration and / or the continuous offset duration of the route belong to different preset duration ranges that fall into different preset duration ranges, and the abnormal intervention strategies adopted are different.
  • the prompt voice you can use the text to speech (Text ToSpeech, TTS) broadcast method, such as "the current itinerary stays abnormally for 5 minutes, if necessary, you can perform a one-click help function operation, the taxi platform will continue "Follow your itinerary" is broadcast to the service provider or service requester in the form of voice.
  • Text ToSpeech Text ToSpeech, TTS
  • the security confirmation request voice you can use the interactive voice response (Interactive Voice Response, IVR) phone method, such as staying for more than 15 minutes, to the service provider or service requester to connect the security confirmation IVR phone, and wait Feedback security confirmation request voice, if the security confirmation voice is received within the preset time period, continue to monitor, if the security confirmation voice is not received within the preset time period, the security confirmation request voice is repeatedly sent until the security confirmation voice is received Or, until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold (such as 3 times), a manual call request is initiated.
  • IVR Interactive Voice Response
  • the embodiments of the present disclosure start from the current car-hailing environment, comprehensively consider a variety of abnormal influencing factors to determine whether there is an abnormality in service security, and when there is an abnormality in service security, an exception intervention strategy from light to heavy can be used to handle exceptions. Therefore, while restricting the service behavior of the service provider, it also ensures the safety of the passengers.
  • FIG. 6 it is a flowchart of an order service security detection method provided in Embodiment 6 of the present disclosure.
  • the method may be executed by a background server.
  • the above order service security detection method includes the following steps:
  • S602 Determine driving stop information of the service provider based on the track point data
  • S603 Determine the service safety of the current travel order according to the driving stop information of the service provider.
  • the service safety of the current travel order can be determined based on the driving stop information.
  • the driving stop information can indicate the stop situation of the service provider at a certain track point, and can include not only the position information of the stop point where the stop point is located, but also the stay time of the stop point. The description of the location information has already been explained above, and will not be repeated here.
  • the dwell time of the track point can be determined by the time difference between the time when the position first appears in the track point data and the time when it last appears in the track point data.
  • the above-mentioned driving stop information also includes information on the duration of staying at any place in the remote area.
  • the embodiment of the present disclosure can determine whether the area at any location is a remote area according to the following steps: travel according to each historical travel order
  • the address information determines the area where the number of orders generated within the latest preset time period is lower than the target quantity threshold, and uses the determined area as a remote area.
  • the present disclosure also provides an order service security detection device.
  • an order service security detection device For the implementation of the following various devices, reference may be made to the implementation of the method, and repeated descriptions are not repeated.
  • FIG. 7 it is an order service security detection device provided in Embodiment 7 of the present disclosure, and the device includes:
  • the track point obtaining module 701 is configured to obtain track point data of the service provider during the current travel order process of the service;
  • the information determination module 702 is configured to determine driving stop information and route offset information of the service provider based on the track point data;
  • the safety detection module 703 is configured to determine the service safety of the current travel order according to driving stop information and route offset information of the service provider.
  • the driving stop information includes stop position information and stop duration;
  • the route offset information includes continuous route offset duration;
  • the security detection module 703 is specifically configured to: when any one of the following conditions is met, determine that there is a problem with the service security of the current travel order:
  • the service provider end stays at a position where the secludedness is greater than the secludedness threshold value, and the stayed duration is greater than the first durational threshold value;
  • the duration of the continuous route offset of the service provider is greater than the second duration threshold.
  • the security detection module 703 is specifically configured as:
  • the outlier corresponding to the area is greater than the outlier threshold, it is determined that any one of the locations is a location with an outlier greater than the outlier threshold.
  • the device may further include:
  • the remoteness determination module 704 is configured to divide the range of the target geographic area into a plurality of areas of preset sizes; determine the number of orders generated in each divided area; and determine the size of each divided area according to the number of orders Remoteness.
  • the device may further include:
  • the first threshold determination module 705 is configured to separately obtain the maximum stay time of each historical abnormal travel order at each sampling trajectory point and the remoteness of the sampling trajectory point corresponding to the maximum stay time; the historical abnormal travel order refers to receiving a user complaint Of travel orders;
  • any of the maximum stay duration and the remoteness of any sampling trajectory point as a pairing combination to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the pairing combination; the historical travel order coverage corresponding to the pairing combination
  • the quantity refers to the number of historical travel orders whose outliers in a sampling track point are greater than the outliers in the pairing combination, and whose staying time at the sampling track point is greater than the maximum staying time in the pairing combination; the pairing combination corresponds to
  • the historical abnormal order recall rate refers to the historical anomalous travel after a survey, the remoteness of a sampling trajectory point is greater than the remoteness of the pairing combination, and the stay time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the outlier threshold and the first duration threshold are determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination.
  • the first threshold determination module 705 is specifically configured to determine the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination, as well as the preset historical travel order coverage selection range and historical abnormal order Select the range of the recall rate, select a pairing combination, and use the outlier degree in the selected pairing combination as the outlier threshold, and use the maximum stay duration in the selected pairing combination as the first duration threshold.
  • the device may further include:
  • the second threshold determination module 706 is configured to separately obtain the maximum continuous offset duration of each historical abnormal travel order
  • For each maximum continuous offset duration determine the historical travel order coverage and historical abnormal order recall rate corresponding to the maximum continuous offset duration; where the historical travel order coverage corresponding to the maximum continuous offset duration refers to the corresponding maximum The number of historical travel orders whose continuous offset duration is greater than the current maximum continuous offset duration; the historical abnormal order recall rate corresponding to the maximum continuous offset duration means that after investigation, the corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration The proportion of historical abnormal travel orders with offset time in all historical abnormal travel orders;
  • the second duration threshold is determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration.
  • the second threshold determination module 706 is specifically configured to determine the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration, and the preset historical travel order coverage selection range and The historical abnormal order recall rate selection range selects a maximum continuous offset duration, and uses the selected maximum continuous offset duration as the second duration threshold.
  • the device may further include:
  • the offset duration determination module 707 is configured to determine the duration of the continuous duration of the route as the continuous offset duration of the route whose angle between the current driving direction of the service provider and the reference driving direction is continuously greater than the set angle threshold value;
  • the driving direction refers to the connection direction from the current track point position of the service provider and the destination of the current travel order.
  • the device may further include:
  • the processing module 708 is configured to execute a processing strategy corresponding to the determined duration range according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong.
  • processing module 708 is specifically configured as:
  • duration range belongs to the first duration range, send a preset prompt voice to the service provider and / or service request end;
  • duration range belongs to the second duration range, send a security confirmation request voice waiting for voice feedback to the service provider and / or service request end;
  • duration range belongs to the third duration range, initiate a manual call request to the service provider and / or service request end;
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range.
  • processing module 708 is specifically configured as:
  • the security confirmation request voice is repeatedly sent until the security confirmation voice is received, or until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold, a manual call request is initiated;
  • the device includes:
  • the track point obtaining module 801 is configured to obtain the track point data of the service provider during the current travel order process of the service;
  • the information determination module 802 is configured to determine the driving stay information of the service provider based on the track point data;
  • the safety detection module 803 is configured to determine the service safety of the current travel order according to the driving stop information of the service provider.
  • FIG. 9 it is a schematic structural diagram of an order service security detection device provided in Embodiment 9 of the present disclosure, including: a processor 901, a storage medium 902, and a bus 903, where the storage medium stores the processor 901 executable machine-readable instructions.
  • the processor 901 communicates with the storage medium 902 via a bus 903.
  • the processor 901 executes the machine-readable instructions to perform the following processing:
  • the service safety of the current travel order is determined according to driving stop information and route offset information of the service provider.
  • the driving stop information includes stop position information and stop duration;
  • the route offset information includes continuous route offset duration; for
  • the service provider end stays at a position where the secludedness is greater than the secludedness threshold value, and the stayed duration is greater than the first durational threshold value;
  • the duration of the continuous route offset of the service provider is greater than the second duration threshold.
  • any location it is determined according to the following steps whether the location is a location with a secludedness greater than a secludedness threshold, and the machine-readable instructions are executed as follows when executed by the processor:
  • the outlier corresponding to the area is greater than the outlier threshold, it is determined that any one of the locations is a location with an outlier greater than the outlier threshold.
  • the following processing is also performed.
  • the method further includes:
  • the historical abnormal travel order refers to a travel order that receives user complaints
  • any of the maximum stay duration and the remoteness of any sampling trajectory point as a pairing combination to determine the historical travel order coverage and historical abnormal order recall rate corresponding to the pairing combination; the historical travel order coverage corresponding to the pairing combination
  • the quantity refers to the number of historical travel orders whose outliers in a sampling track point are greater than the outliers in the pairing combination, and whose staying time at the sampling track point is greater than the maximum staying time in the pairing combination; the pairing combination corresponds to
  • the historical abnormal order recall rate refers to the historical anomalous travel after a survey, the remoteness of a sampling trajectory point is greater than the remoteness of the pairing combination, and the stay time at the sampling trajectory point is greater than the maximum staying time in the pairing combination
  • the outlier threshold and the first duration threshold are determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each pairing combination.
  • the outlier threshold and the first duration threshold are determined, and the machine-readable instruction is executed when executed by the processor.
  • the following processing includes:
  • the preset historical travel order coverage selection range and historical abnormal order recall rate selection range select a pairing combination and combine the selected pairing combinations
  • the outlier in is used as the outlier threshold
  • the maximum stay duration in the selected pairing combination is used as the first duration threshold.
  • For each maximum continuous offset duration determine the historical travel order coverage and historical abnormal order recall rate corresponding to the maximum continuous offset duration; where the historical travel order coverage corresponding to the maximum continuous offset duration refers to the corresponding maximum The number of historical travel orders whose continuous offset duration is greater than the current maximum continuous offset duration; the historical abnormal order recall rate corresponding to the maximum continuous offset duration means that after investigation, the corresponding maximum continuous offset duration is greater than the current maximum continuous offset duration The proportion of historical abnormal travel orders with offset time in all historical abnormal travel orders;
  • the second duration threshold is determined according to the historical travel order coverage and historical abnormal order recall rate corresponding to each maximum continuous offset duration.
  • the machine-readable instruction executed by the processor performs the following processes including: :
  • the selected maximum continuous offset duration is used as the second duration threshold.
  • the duration of the continuous duration of the angle between the current travel direction of the service provider and the reference travel direction being greater than the set angle threshold is determined as the duration of continuous deviation of the route;
  • the reference travel direction refers to the provision from the service The connection direction of the current track point position of the terminal and the destination of the current travel order.
  • the following processing is also performed.
  • the method further includes:
  • the processing strategy corresponding to the determined duration range is executed according to the duration range to which the stay duration and / or the route continuous offset duration respectively belong.
  • a processing strategy corresponding to the determined duration range is executed, and when the machine-readable instruction is executed by the processor, the following processing includes: :
  • duration range belongs to the first duration range, send a preset prompt voice to the service provider and / or service request end;
  • duration range belongs to the second duration range, send a security confirmation request voice waiting for voice feedback to the service provider and / or service request end;
  • duration range belongs to the third duration range, initiate a manual call request to the service provider and / or service request end;
  • the first duration range, the second duration range and the third duration range do not overlap each other, and the duration in the second duration range is greater than the duration in the first duration range and less than the duration in the third duration range.
  • the security confirmation request voice is repeatedly sent until the security confirmation voice is received, or until the number of times the security confirmation request voice is repeatedly sent is greater than the set threshold, a manual call request is initiated;
  • the present disclosure also provides an order service security detection method device.
  • the method device includes: a processor, a storage medium, and a bus, the storage medium stores machine-readable instructions executable by the processor, and the processing
  • the processor communicates with the storage medium through a bus, and the processor executes the machine-readable instructions to perform the following processes including:
  • the order service safety detection device determines, based on the track point data, whether the service provider has abnormal behaviors when providing travel services (such as long driving stay, excessive route deviation, etc.) to determine the safety of the service Whether it is sex or not, the effective detection of service safety is achieved, and the accuracy of the detection is good, so that it can not only restrict the service behavior of the service provider, but also further ensure the safety of passengers.
  • the device further includes: a communication interface; the communication interface and the processor communicate via a bus;
  • the communication interface is used to receive track point data during the execution of the current travel order reported by the service provider or the service requester.
  • the track point data during the execution of the current travel order reported by the received service provider or service request end is used as the track point data during the current travel order of the service provider.
  • the order service security detection device can receive the track point data reported by the service provider or the service requester through the communication interface.
  • the processor can receive the reported data based on the communication connection relationship with the communication interface Track point data, and determine the track point data as the track point data of the service provider during the current travel order process of the service.
  • both the service provider and the service requester can determine the track point data during the execution of the current travel order through the built-in positioning system.
  • the service provider When the service provider is used as the data reporting terminal, it can determine the latitude and longitude coordinates collected by the built-in positioning system at preset time intervals based on the positioning technology. Each latitude and longitude coordinate corresponds to a track point data, so that the service provider can use the collected trajectory The point data is reported to the order service security testing device in real time so that the device can perform order service security testing.
  • the service requesting end is used as the data reporting end
  • the latitude and longitude coordinates collected by the built-in positioning system at preset time intervals can also be determined based on the positioning technology.
  • Each latitude and longitude coordinate corresponds to a track point data.
  • the collected track point data can be reported to the order service security detection device in real time so that the device can perform order service security detection.
  • the track point data of the service provider during the current travel order process of the service can also be determined, and also based on the binding relationship between the service provider and the vehicle terminal,
  • the track point data reported by the vehicle-mounted terminal is used as the track point data of the service provider.
  • Embodiment 14 of the present disclosure also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and the computer program is executed by a processor to execute the order service security detection method described in any of the above embodiments A step of.
  • the storage medium can be a general-purpose storage medium, such as a removable disk, a hard disk, etc.
  • the above-mentioned order service security detection method can be executed, thereby solving Through the review of the online car-hailing platform, the safety of the travel service can be preliminarily judged, and it cannot respond to the complexity of the current online car-hailing environment. There is no effective guarantee and prevention of passenger safety, and thus the security of the order service is achieved. Carry out effective testing, and the accuracy of testing is better.
  • the computer program product of the order service security detection method provided by the embodiments of the present disclosure includes a computer-readable storage medium storing program codes.
  • the instructions included in the program codes can be used to execute the methods in the foregoing method embodiments. The method embodiments are not repeated here.
  • the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a non-volatile computer-readable storage medium executable by a processor.
  • a computer device which may be a personal computer, a server, or a network device, etc.
  • the foregoing storage media include various media that can store program codes, such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
  • the order service safety detection device and method provided by the present disclosure determine whether the service provider has abnormal behaviors when providing travel services (such as long driving stay, excessive route deviation, etc.) to determine the service
  • the safety of the system has achieved effective detection of service safety, and the accuracy of the detection is good, which can not only restrict the service behavior of the service provider, but also further ensure the safety of passengers.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Traffic Control Systems (AREA)

Abstract

公开了一种订单服务安全性检测装置及方法，涉及信息技术领域，所述方法包括：获取服务提供端在服务当前出行订单过程中的轨迹点数据；基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。实现了对服务安全性的有效检测，且检测的准确性较好，从而不仅能够很好的约束服务提供方的服务行为，还能够进一步确保乘客的用车安全。

Description

订单服务安全性检测装置及方法
相关申请的交叉引用
本公开要求于2018年10月25日提交中国国家知识产权局(CNIPA)的公开号为201811251791.X，名称为“订单服务安全性检测方法及装置、计算机可读存储介质”的中国专利公开的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及信息技术领域，具体而言，涉及一种订单服务安全性检测装置及方法。
背景技术
近些年，由于网约车的便捷性和实用性，网约车规模迅速扩张。网约车即是网络预约出租汽车的简称，乘客可以通过移动设备在网约车平台上与司机进行预约，司机接单后到预约的指定地点接乘客到目的地，以方便乘客出行。目前，网约车(如出租车、专车、快车、顺风车等)比较常见以满足用户更加多样化的出行需求。
尽管司机和相关车辆已经在网约车平台经过了登记与审核，然而，就目前的网约车环境而言，网约车仍具有较大的乘车风险，对于乘客的安全并没有进行有效的保障和预防。
发明内容
本公开的目的在于提供一种订单服务安全性检测装置及方法，能够对订单服务的安全性进行检测，且检测的准确性较好。
本公开提供了一种订单服务安全性检测装置，所述装置包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如下处理：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
一种实施例中，所述装置还包括：通信接口；所述通信接口与所述处理器之间通过总线通信；
所述通信接口，用于接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据。
一种实施例中，对于所述获取服务提供端在服务当前出行订单过程中的轨迹点数据，所述机器可读指令被处理器执行时还执行如下处理：
通过通信接口接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据；
将接收的服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据，作为服务提供端在服务当前出行订单过程中的轨迹点数据。
可选地，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；对于根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性，所述机器可读指令被处理器执行时执行如下处理：包括：
当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
所述服务提供端的路线连续偏移时长大于第二时长阈值。
可选地，对于针对任一位置，根据以下步骤确定该位置是否为偏僻度大于偏僻度阈值的位置，所述机器可读指令被处理器执行时执行如下处理：
确定所述任一位置所在的区域；
若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
可选地，所述方法机器可读指令被处理器执行时还执行如下处理还包括：
将目标地理区域范围划分为多个预设大小的区域；
确定划分出的每个区域内产生的订单数量；
根据所述订单数量，确定划分出的每个区域的偏僻度。
可选地，根据以下步骤对于确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理：
分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
可选地，对于根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理包括：
根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
可选地，对于根据以下步骤确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理：
分别获取每个历史异常出行订单的最大连续偏移时长；
针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
可选地，对于根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理包括：
根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
可选地，根据以下步骤对于确定所述路线连续偏移时长，所述机器可读指令被处理器执行时执行如下处理：
将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
可选地，当确定所述当前出行订单的服务安全存在问题后，所述机器可读指令被处理器执行时还执行如下处理所述方法还包括：
根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
可选地，对于根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略，所述机器可读指令被处理器执行时执行如下处理包括：
若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
可选地，在向所述服务提供端和/或服务请求端发送等待反馈的安全确认请求语音之后，所述机器可读指令被处理器执行时还执行如下处理还包括：
若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
本公开还提供了一种订单服务安全性检测方法装置，所述方法装置包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如下处理包括：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
本公开还提供了一种订单服务安全性检测方法，所述方法包括：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
可选地，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性，可以包括：当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
所述服务提供端的路线连续偏移时长大于第二时长阈值。
可选地，针对任一位置，可以根据以下步骤确定该位置是否为偏僻度大于偏僻度阈值的位置：
确定所述任一位置所在的区域；
若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
可选地，所述方法还包括：
将目标地理区域范围划分为多个预设大小的区域；
确定划分出的每个区域内产生的订单数量；
根据所述订单数量，确定划分出的每个区域的偏僻度。
可选地，可以根据以下步骤确定所述偏僻度阈值和所述第一时长阈值：
分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻 度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
可选地，根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值，可以包括：
根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
可选地，可以根据以下步骤确定所述第二时长阈值：
分别获取每个历史异常出行订单的最大连续偏移时长；
针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
可选地，根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值，可以包括：
根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
可选地，可以根据以下步骤确定所述路线连续偏移时长：
将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
可选地，当确定所述当前出行订单的服务安全存在问题后，所述方法还包括：
根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
可选地，根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略，包括：
若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
可选地，在向所述服务提供端和/或服务请求端发送等待反馈的安全确认请求语音之后，还包括：
若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
本公开还提供了一种订单服务安全性检测方法，所述方法包括：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
本公开实施例还提供了一种订单服务安全性检测装置，所述装置包括：
轨迹点获取模块，配置为获取服务提供端在服务当前出行订单过程中的轨迹点数据；
信息确定模块，配置为基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
安全检测模块，配置为根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
在一些实施例中，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；
所述安全检测模块，具体配置为：当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
所述服务提供端的路线连续偏移时长大于第二时长阈值。
可选地，针对任一位置，所述安全检测模块，具体配置为：
确定所述任一位置所在的区域；
若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
可选地，所述装置还可以包括：
偏僻度确定模块，配置为将目标地理区域范围划分为多个预设大小的区域；确定划分出的每个区域内产生的订单数量；根据所述订单数量，确定划分出的每个区域的偏僻度。
可选地，所述装置还可以包括：
第一阈值确定模块，配置为分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
可选地，所述第一阈值确定模块，具体配置为根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
可选地，所述装置还可以包括：
第二阈值确定模块，配置为分别获取每个历史异常出行订单的最大连续偏移时长；
针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
可选地，所述第二阈值确定模块，具体配置为根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
可选地，所述装置还可以包括：
偏移时长确定模块，配置为将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
可选地，所述装置还可以包括：
处理模块，配置为根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
可选地，所述处理模块，具体配置为：
若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
可选地，所述处理模块，具体配置为：
若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
本公开还提供了一种订单服务安全性检测装置，所述装置包括：
轨迹点获取模块，配置为获取服务提供端在服务当前出行订单过程中的轨迹点数据；
信息确定模块，配置为基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
安全检测模块，配置为根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
本公开还提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如第一方面和第二方面任一所述的订单服务安全性检测方法的步骤。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本公开的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例一所提供的一种订单服务安全性检测方法的流程图；
图2示出了本公开实施例所二提供的一种订单服务安全性检测方法的流程图；
图3示出了本公开实施例三所提供的一种订单服务安全性检测方法的流程图；
图4示出了本公开实施例四所提供的一种订单服务安全性检测方法的流程图；
图5示出了本公开实施例四所提供的一种订单服务安全性检测方法的应用示意图；
图6示出了本公开实施例六所提供的一种订单服务安全性检测方法的流程图；
图7示出了本公开实施例七所提供的一种订单服务安全性检测装置的结构示意图；
图8示出了本公开实施例八所提供的一种订单服务安全性检测装置的结构示意图；
图9示出了本公开实施例九所提供的一种订单服务安全性检测装置的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，应当理解，本公开中附图仅起到说明和描述的目的，并不用于限定本公开的保护范围。另外，应当理解，示意性的附图并未按实物比例绘制。本公开中使用的流程图示出了根据本公开的一些实施例实现的操作。应该理解，流程图的操作可以不按顺序实现，没有逻辑的上下文关系的步骤可以反转顺序或者同时实施。此外，本领域技术人员在本公开内容的指引下，可以向流程图添加一个或多个其他操作，也可以从流程图中移除一个或多个操作。
另外，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围，而是仅仅表示本公开的选定实施例。基于本公开的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
为了使得本领域技术人员能够使用本公开内容，结合特定应用场景“网约车(如专车、快车等)安全性检测”，给出以下实施例。对于本领域技术人员来说，在不脱离本公开的精神和范围的情况下，可以将这里定义的一般原理应用于其他实施例和应用场景。虽然本公开主要围绕网约车安全性检测进行描述，但是应该理解，这仅是一个示例性实施例。本公开可以应用于任何其他交通运输类型。例如，本公开可以应用于不同的运输系统环境，包括陆地，海洋，或航空等，或其任意组合。运输系统的交通工具可以包括出租车、私家车、顺风车、公共汽车、火车、子弹头列车、高速铁路、地铁、或无人驾驶车辆等，或其任意组合。本公开还可以包括用于提供网约车安全性检测的任何服务系统。本公开的系统或方法的应用可以包括网页、浏览器的插件、客户端终端、定制系统、内部分析系统、或人工智能机器人等，或其任意组合。
需要说明的是，本公开实施例中将会用到术语“包括”，用于指出其后所声明的特征的存在，但并不排除增加其它的特征。
本公开中的术语“乘客”、“服务请求方”、“服务人员”、“服务请求方”、“客户”、“乘客终端”或“服务请求端”可互换使用，以指代可以请求或订购服务的个人、实体或工具。本公开中的术语“司机”、“服务提供方”、“服务提供端”、“供应商”、“驾驶员”、“驾驶员终端”或“服务提供端”可互换使用，以指代可以提供服务的个人、实体或工具。本公开中的术语“用户”可以指代请求服务、订购服务、提供服务或促成服务的提供的个人、实体或工具。例如，用户可以是乘客、驾驶员、操作员等，或其任意组合。
本公开中的术语“服务请求”和“订单”可互换使用，以指代由乘客、服务请求方、司机、服务提供端、或供应商等、或其任意组合发起的请求。接受该“服务请求”或“订单”的可以是乘客、服务请求方、司机、服务提供端、或供应商等、或其任意组合。服务请求可以是收费的或免费的。
值得注意的是，在本公开提出之前，相关技术中大多通过司机和相关车辆在网约车平台的审核通过来初步判断出行服务的安全性，无法应对当前网约车环境的复杂性，对于乘客的安全并没有进行有效的保障和预防。为了解决上述相关技术中的问题，本申请提供了一种通过对服务提供端的轨迹点数据进行分析处理得到的驾驶停留信息和路线偏移信息来确定当前出行订单的服务安全性的订单服务安全性检测方案。
本申请提供的订单服务安全性检测方法可以对订单服务的安全性进行有效检测，且检测的准确性较好。下面通过几个实施例进行具体描述。
实施例一
如图1所示，为本公开实施例一提供的一种订单服务安全性检测方法的流程图，该方法可以由后台服务器来执行。上述订单服务安全性检测方法包括如下步骤：
S101、获取服务提供端在服务当前出行订单过程中的轨迹点数据。
这里，轨迹点数据可以是从现有的打车平台获取的。在用户需要打车时，可以在打车平台输入相应的打车信息(如出行起点信息和出行终点信息等)，根据该打车信息能够生成对应的出行订单。处于在服务的出行订单除了可以确定起始轨迹点和终止轨迹点的轨迹点 数据(即出行起点信息和出行终点信息)，还可以记录行驶过程中各行驶轨迹点的轨迹点数据，如行径每个轨迹点的时间信息、位置信息、速度信息等。除此之外，在上述出行订单还可以包括其他打车信息，如用车类型信息，出租车、快车、专车、顺风车等。
值得说明的是，上述行驶轨迹点的轨迹点数据中有关位置信息可以利用定位技术来确定，有关速度信息可以利用传感器技术来确定。针对位置信息而言，本公开中使用的定位技术可以基于全球定位系统(Global Positioning System,GPS)、全球导航卫星系统(Global Navigation Satellite System,GLONASS)，罗盘导航系统(COMPASS)、伽利略定位系统、准天顶卫星系统(Quasi-Zenith Satellite System,QZSS)、无线保真(Wireless Fidelity,WiFi)定位技术等，或其任意组合。一个或多个上述定位系统可以在本公开中互换使用；针对速度信息而言，本公开实施例可以利用设置在行驶车辆上的速度传感器或者其它能够测量行驶车辆的速度的设备来确定，这里不做具体的限制。
另外，上述定位装置在进行位置信息采集时，可以每预设时间间隔(如1s)向外发送一次行径轨迹点的位置信息，这样，上述后台服务器可以获取各轨迹点的位置信息，也可以利用采样技术采取部分轨迹点的位置信息，本公开实施例对此不做具体的限制。
上述起始轨迹点和终止轨迹点的轨迹点数据主要是指与起点对应的出行起点位置以及与终点对应的出行终点位置，同样的，该位置信息也可以利用定位技术确定。如在打车平台可以自动定位用户当前的位置作为出行起点位置。或者，用户可以在地图上选择具体的出行起点位置，或者手动输入出行起点位置，如手动输入“AA机场”这一出行起点位置，上述出行终点位置则主要利用用户在地图上选择或手动输入方式来确定，在此不再赘述。
S102、基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息。
这里，针对每个轨迹点，本公开实施例可以利用相应的轨迹点数据确定服务提供端的驾驶停留信息以及路线偏移信息。
其中，驾驶停留信息可以指示服务提供端在某个轨迹点的停留情况，不仅可以包括停留所处轨迹点的位置信息，还可以包括在停留所处轨迹点的停留时长。有关位置信息的描述已经在前文进行说明，在此不再赘述。有关轨迹点的停留时长则可以由该位置第一次出现在轨迹点数据中的时间，与最后一次出现在轨迹点数据中的时间的时间差来确定。
除此之外，上述驾驶停留信息还包括在偏僻区域中的任一地点停留的时长信息，本公开实施例可以根据以下步骤确定任意地点所处区域是否为偏僻区域：根据各历史出行订单的出行地理信息，确定在最近预设时长内产生的订单数量低于目标数量阈值(如100)的区域，将确定出的区域作为偏僻区域。
另外，路线偏移信息可以指示服务提供端的行驶情况，主要包括路线连续偏移时长。有关路线连续偏移时长可以由服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长来确定。
S103、根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
这里，可以基于偏僻度阈值以及停留时长阈值确定当前出行环境下的停留情况是否存在异常，以判定当前出行订单的服务安全是否存在问题，同理，还可以基于偏移时长阈值确定当前出行环境下的行驶情况是否存在异常，以判定当前出行订单的服务安全是否存在问题。
在当前出行环境下，在某个轨迹点存在停留多发生在交通拥堵、红绿灯等候等情形，而因为恶性事件(如命案、抢劫重伤案、强奸案等)的发生而导致过长时间的停留尽管是小概率事件，但如果发生将会对打车平台和社会带来不良的影响。本公开实施例正是为了及时捕捉上述小概率事件，才根据轨迹点数据确定停留所处轨迹点的停留时长，另外，又为了防止正常出行行为所存在的停留对服务安全性检测的影响，所以本公开实施例还可以确定停留所处轨迹点的位置信息。若该位置较为偏僻(如该位置的偏僻度大于偏僻度阈值)，且停留时间过长(如该位置的停留时长大于停留时长阈值)，则可以基本判定服务安全存在问题。此外，在确定行径的轨迹点处于偏僻区域后，如果停留过长时间，也可以基本判定服务安全存在问题。
另外，路线偏移信息可以指示服务提供端的行驶情况，主要包括路线连续偏移时长。在当前出行环境下，打车平台可以根据用户选取的出行起点信息和出行终点信息确定由出行起点至出行终点的行驶路线，即使在行驶过程中可能会由于交通环境的影响存在一定程度的路线偏移，但连续的偏移(如路线连续偏移时长大于偏移时长阈值)则可以基本判定服务安全存在问题。
本公开实施例可以基于区域对应的偏僻度，确定该区域内任一位置对应的偏僻度，这样，在任一区域为偏僻度大于偏僻度阈值的区域(偏僻区域)时，则可以认为该区域内的任一位置为偏僻度大于偏僻度阈值的位置(即偏僻位置)。
这里，在实际实施中，预先保存的可能是指示各个区域是否为偏僻度大于设定偏僻度阈值的区域的信息，此时根据任一位置所在区域，可以直接知道该位置是否为偏僻度大于偏僻度阈值的位置；此外，预先保存的也可能是各个区域的偏僻度以及偏僻度阈值，此时，可以先根据任一位置所在区域的偏僻度确定该位置的偏僻度，再将其与偏僻度阈值进行比较，本公开实施例对此不做具体的限制。其中，上述区域的偏僻度可以是预先确定的。
接下来通过如下实施例二对区域的偏僻度确定过程进行说明。
实施例二
如图2所示，可以按照如下步骤确定区域的偏僻度：
S201、将目标地理区域范围划分为多个预设大小的区域；
S202、确定划分出的每个区域内产生的订单数量；
S203、根据所述订单数量，确定划分出的每个区域的偏僻度。
这里，首先将目标地理区域范围划分为多个预设大小的区域，然后确定划分出的每个区域内的订单数量，最后根据该订单数量确定该区域的偏僻度。
本公开实施例中，可以是基于对出发地位于该区域内的订单的数量的统计结果确定每个区域内的订单数量。在针对每个区域进行订单数量统计时，可以统计近一段时间(如7天)内产生的历史订单的数量。这样，可以基于目标地理区域范围内的总订单数量与每个区域的产生的订单数量的比值结果确定每个区域的偏僻度，对于产生的订单数量越少的区域，其对应的偏僻度越大。除此之外，针对每个区域而言，本公开实施例还可以综合考虑在该区域产生订单的订单发起时间、以及其它区域对该区域的影响因素等来确定该区域的偏僻度。
其中，在对目标地理区域范围进行划分时，本公开实施例可以按照预设大小进行区域划分。例如，针对A市这一目标地理区域范围而言，本公开实施例可以将A市划分为若干区域，且划分各个区域的形状可以是四边形、六边形或者其他多边形。本公开实施例综合考虑世界地理知识，可以将A市依次划分为多个四边形的区域，该四边形的边长可以是从数百米到数千米。本公开实施例中，为了兼顾数据计算量和划分精确度，选取的边长不易过大也不易过小，可以选用120m的边长。
值得说明的是，本公开实施例可以采用Geohash编码算法将目标地理区域范围划分为若干矩形区域，还可以对每个矩形区域进行编码(如哈希编码)，并将编码结果作为与矩形区域对应的标识信息。这样，便可以基于各标识信息与各偏僻度之间的映射关系，查找与当前行径轨迹点所处区域对应的偏僻度。
考虑到偏僻度阈值以及停留时长阈值(即第一时长阈值)的选取对停留异常判断结果的影响，且阈值选取过大可能会导致真正异常的出行订单无法被检测，而阈值选取过小则可能会导致正常出行订单被误检。为了提升检测准确度和精准度，本公开实施例可以利用历史出行订单覆盖量以及历史异常订单召回率来确定阈值。通过如下实施例三进行描述
实施例三
如图3所示，本公开实施例三提供了一种阈值确定方法，该方法具体包括如下步骤：
S301、分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
S302、将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；
S303、根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
这里，阈值确定依赖于对各历史异常出行订单的分析结果。也即，本公开实施例可以首先针对每个历史异常出行订单确定异常轨迹点的停留时长。异常轨迹点可以为一个，也可以有多个。通常来说，发生恶性事件的异常轨迹点可以为一个。这样，该异常轨迹点可以是停留时长最大的采样轨迹点。如果异常轨迹点为多个，本公开实施例可以先按照由大到小的顺序对各采样轨迹点的停留时长进行排序，选取排名靠前的异常轨迹点。为了便于后续描述，接下来以一个异常轨迹点进行描述。
本公开实施例中，针对每个历史异常出行订单均可以确定对应的最大停留时长。这样，可以将确定的每个最大停留时长和对应的采样轨迹点的偏僻度进行配对组合以确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率。基于所有配对组合对应的历史出行订单覆盖量以及历史异常订单召回率可以从所有配对组合中选取出对应的目标配对组合，从而确定偏僻度阈值和第一时长阈值。
其中，上述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量，也即，上述历史出行订单覆盖量可以指示配对组合覆盖的历史出行订单的数量；上述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比，也即，上述历史异常订单召回率可以指示当前配对组合能够正确识别出的历史异常出行订单占所有历史异常出行订单的订单占比。
本公开实施例中可以针对不同的应用需求选取不同的配对组合确定阈值。假设近一段时间内，历史异常出行订单有5个，每个历史异常出行订单对应1个最大停留时长和对应的1个偏僻度，且任意两个历史异常出行订单的最大停留时长不同、偏僻度也不同。这样，针对每个历史异常出行订单而言，均可以确定有5个配对组合，对5个历史异常出行订单对应的25个配对组合分别确定对应的历史出行订单覆盖量以及历史异常订单召回率。根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合确定偏僻度阈值和所述第一时长阈值。
其中，上述历史出行订单覆盖量的选择范围主要与打车平台的客服人员的服务处理能力有关，而历史异常订单召回率则主要与异常判定的准确度有关。本公开实施例可以根据打车平台的具体运营策略选取对应的配对组合以满足服务处理能力和异常判定准确度的双重要求。
考虑到偏移时长阈值(即第二时长阈值)的选取对偏移异常判断结果的影响，且阈值选取过大可能会导致真正异常的出行订单无法被检测，而阈值选取过小则可能会导致正常出行订单被误检。为了检测检测准确度和精准度，本公开实施例可以利用历史出行订单覆盖量以及历史异常订单召回率来确定阈值。通过如下实施例四进行描述。
实施例四
如图4所示，本公开实施例四提供了一种阈值确定方法，该方法具体包括如下步骤：
S401、分别获取每个历史异常出行订单的最大连续偏移时长；
S402、针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；
S403、根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
同理，这里阈值的确定也可以依赖于对各历史异常出行订单的分析结果。也即，本公开实施例可以首先针对每个历史异常出行订单确定连续偏移时长。连续偏移时长可以为一个，也可以有多个。对于一个连续偏移时长，可以直接将其作为最大连续偏移时长，如果 连续偏移时长为多个，本公开实施例可以先按照由大到小的顺序对各连续偏移时长进行排序，选取排名最靠前的一个连续偏移时长作为最大连续偏移时长。
本公开实施例中，针对每个历史异常出行订单均可以确定对应的最大连续偏移时长。这样，可以确定每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率。基于所有最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率可以从所有最大连续偏移时长中选取出对应的目标最大连续偏移时长，从而确定第二时长阈值。
其中，上述该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量，也即，上述历史出行订单覆盖量能够指示配对组合覆盖的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比，也即，上述历史异常订单召回率能够指示当前最大连续偏移时长能够正确识别出的历史异常出行订单占所有历史异常出行订单的订单占比。
这样，根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长作为第二时长阈值。其中，为了满足服务处理能力和异常判定准确度的双重要求，这里的历史出行订单覆盖量选择范围和历史异常订单召回率也可以根据打车平台的具体运营策略来选取。
在确定当前服务提供端的路线连续偏移时长大于第二时长阈值时，便可以基本确定当前出行订单的服务安全存在问题。本公开实施例可以将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长作为上述路线连续偏移时长。其中，参考行驶方向则是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。设定夹角阈值可以从0度至180度中进行选取，本公开实施例可以选取90度作为该设定夹角阈值，若当前行驶方向与参考行驶方向之间的夹角连续大于90度，则说明轨迹点持续在远离终点方向行驶。
接下来结合图5进一步描述如何根据偏移异常情况来确定服务安全存在问题。
其中，P0-P5为一个历史异常出行订单的行径轨迹点，S和D对应该历史异常出行订单的起始轨迹点和终止轨迹点。由图5可知，针对P0、P1、P3、P4、P5而言，这些轨迹点处当前行驶方向与参考行驶方向之间的夹角小于90度，则说明这些轨迹点在靠近终点方向行驶，而对于P2而言，其当前行驶方向与参考行驶方向之间的夹角连续大于90度，若至P4点连续时间大于第二时长阈值，则可以判定在该轨迹点P4点开始出现偏移异常，也即，当前出行订单的服务安全应该存在问题。
为了应对不同的服务安全异常情况，本公开实施例可以根据停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。接下来通过如下实施例五进一步进行描述。
实施例五
在本公开实施例中，服务提供端的停留时长过长和/或偏移时长过长均可以对应有相应的异常干预策略，且停留时长和/或路线连续偏移时长分别所属的时长范围越大，相应的异常干预策略需要越有力，这主要是考虑到上述时长范围可能直接关系到恶性事件的发生概率。这样，本公开实施例可以采用由轻到重的异常干预策略进行异常处理以在约束服务提供方的服务行为的同时，确保乘客的用车安全。其中，异常干预策略主要包括语音播报、安全确认请求语音、人工呼叫等方式。
这里，若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求。其中，第一时长范围、第二时长范围和第三时长范围互不重叠，且第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围 内的时长。可见，当前停留时长和/或路线连续偏移时长分别所属的时长范围落入的不同预设时长范围，其采用的异常干预策略也不相同。
针对提示语音而言，可以采用从文本到语音(Text To Speech，TTS)播报的方式，如将“当前行程出现异常停留5分钟，如有需要您可进行一键求助功能操作，打车平台将持续关注您的行程动向”以语音的形式播报给服务提供端或服务请求端。
针对安全确认请求语音而言，可以采用互动式语音应答(Interactive Voice Response，IVR)电话的方式，如在停留时长超过15分钟，给服务提供端或服务请求端接通安全确认IVR电话，并等待反馈的安全确认请求语音，如果在预设时长内接收到安全确认语音，则继续监控，如果在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值(如3次)，则发起人工呼叫请求。
针对人工呼叫而言，如在停留时长超过60分钟，直接电话呼叫服务提供端或服务请求端，如果回复安全，则继续监控；如果回复异常，则提供帮助，包括报警、取证、流转等操作；如果未得到回复，则连续拨打，在连续拨打的次数大于设定阈值(如5次)后仍未接通则联系紧急联系人或升级特勤处理。
可见，本公开实施例从当前网约车环境出发，综合考虑多种异常影响因素判定服务安全是否存在异常，并在服务安全存在异常时，能够采用由轻到重的异常干预策略进行异常处理，从而在约束服务提供方的服务行为的同时，还确保乘客的用车安全。
实施例六
如图6所示，为本公开实施例六提供的一种订单服务安全性检测方法的流程图，该方法可以由后台服务器来执行。上述订单服务安全性检测方法包括如下步骤：
S601、获取服务提供端在服务当前出行订单过程中的轨迹点数据；
S602、基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
S603、根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
这里，可以根据驾驶停留信息确定当前出行订单的服务安全性。与本公开实施例一相同的是，驾驶停留信息可以指示服务提供端在某个轨迹点的停留情况，不仅可以包括停留所处轨迹点的位置信息，还可以包括在停留所处轨迹点的停留时长。有关位置信息的描述已经在前文进行说明，在此不再赘述。有关轨迹点的停留时长则可以由该位置第一次出现在轨迹点数据中的时间，与最后一次出现在轨迹点数据中的时间的时间差来确定。
除此之外，上述驾驶停留信息还包括在偏僻区域中的任一地点停留的时长信息，本公开实施例可以根据以下步骤确定任意地点所处区域是否为偏僻区域：根据各历史出行订单的出行地址信息，确定在最近预设时长内产生的订单数量低于目标数量阈值的区域，将确定出的区域作为偏僻区域。
对于轨迹点的获取过程以及根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性在上述实施例一中已经进行了相应的描述，在此不再赘述。
基于上述实施例，本公开还提供了订单服务安全性检测装置，下述各种装置的实施可以参见方法的实施，重复之处不再赘述。
实施例七
如图7所示，为本公开实施例七提供的订单服务安全性检测装置，所述装置包括：
轨迹点获取模块701，配置为获取服务提供端在服务当前出行订单过程中的轨迹点数据；
信息确定模块702，配置为基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
安全检测模块703，配置为根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
在一些实施例中，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；
所述安全检测模块703，具体配置为：当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
所述服务提供端的路线连续偏移时长大于第二时长阈值。
一种实施例中，针对任一位置，所述安全检测模块703，具体配置为：
确定所述任一位置所在的区域；
若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
可选地，所述装置还可以包括：
偏僻度确定模块704，配置为将目标地理区域范围划分为多个预设大小的区域；确定划分出的每个区域内产生的订单数量；根据所述订单数量，确定划分出的每个区域的偏僻度。
可选地，所述装置还可以包括：
第一阈值确定模块705，配置为分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
可选地，所述第一阈值确定模块705，具体配置为根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
可选地，所述装置还可以包括：
第二阈值确定模块706，配置为分别获取每个历史异常出行订单的最大连续偏移时长；
针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
可选地，所述第二阈值确定模块706，具体配置为根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
可选地，所述装置还可以包括：
偏移时长确定模块707，配置为将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
可选地，所述装置还可以包括：
处理模块708，配置为根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
可选地，所述处理模块708，具体配置为：
若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
可选地，所述处理模块708，具体配置为：
若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
实施例八
如图8所示，为本公开实施例八提供的订单服务安全性检测装置，所述装置包括：
轨迹点获取模块801，配置为获取服务提供端在服务当前出行订单过程中的轨迹点数据；
信息确定模块802，配置为基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
安全检测模块803，配置为根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
实施例九
如图9所示，为本公开实施例九所提供的一种订单服务安全性检测装置的结构示意图，包括：处理器901、存储介质902和总线903，所述存储介质存储有所述处理器901可执行的机器可读指令，所述处理器901与所述存储介质902之间通过总线903通信，所述处理器901执行所述机器可读指令，以执行如下处理：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
可选地，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；对于
根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性，所述机器可读指令被处理器执行时执行如下处理：包括：
当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
所述服务提供端的路线连续偏移时长大于第二时长阈值。
可选地，对于针对任一位置，根据以下步骤确定该位置是否为偏僻度大于偏僻度阈值的位置，所述机器可读指令被处理器执行时执行如下处理：
确定所述任一位置所在的区域；
若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
可选地，所述方法机器可读指令被处理器执行时还执行如下处理还包括：
将目标地理区域范围划分为多个预设大小的区域；
确定划分出的每个区域内产生的订单数量；
根据所述订单数量，确定划分出的每个区域的偏僻度。
可选地，根据以下步骤对于确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理：
分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
可选地，对于根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理包括：
根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
可选地，对于根据以下步骤确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理：
分别获取每个历史异常出行订单的最大连续偏移时长；
针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
可选地，对于根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理包括：
根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
可选地，根据以下步骤对于确定所述路线连续偏移时长，所述机器可读指令被处理器执行时执行如下处理：
将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
可选地，当确定所述当前出行订单的服务安全存在问题后，所述机器可读指令被处理器执行时还执行如下处理所述方法还包括：
根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
可选地，对于根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略，所述机器可读指令被处理器执行时执行如下处理包括：
若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
可选地，在向所述服务提供端和/或服务请求端发送等待反馈的安全确认请求语音之后，所述机器可读指令被处理器执行时还执行如下处理还包括：
若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
本公开还提供了一种订单服务安全性检测方法装置，所述方法装置包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如下处理包括：
获取服务提供端在服务当前出行订单过程中的轨迹点数据；
基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
本公开提供的订单服务安全性检测装置，基于轨迹点数据来确定服务提供端在提供出行服务时是否存在异常行为(如驾驶停留时长较长、路线偏移过大等)，以确定服务的安全性与否，实现了对服务安全性的有效检测，且检测的准确性较好，从而不仅能够很好的约束服务提供方的服务行为，还能够进一步确保乘客的用车安全。
一种实施例中，所述装置还包括：通信接口；所述通信接口与所述处理器之间通过总线通信；
所述通信接口，用于接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据。
可选地，对于所述获取服务提供端在服务当前出行订单过程中的轨迹点数据，所述机器可读指令被处理器执行时还执行如下处理：
通过通信接口接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据；
将接收的服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据，作为服务提供端在服务当前出行订单过程中的轨迹点数据。
这里，本申请实施例提供的订单服务安全性检测装置能够通过通信接口接收服务提供端或服务请求端上报的轨迹点数据，这样，处理器可以基于与该通信接口的通信连接关系接收上述上报的轨迹点数据，并将该轨迹点数据确定为服务提供端在服务当前出行订单过程中的轨迹点数据。
本申请实施例中，服务提供端和服务请求端均可以通过内置的定位系统确定在当前出行订单被执行过程中的轨迹点数据。在服务提供端作为数据上报端时，可以基于定位技术确定内置的定位系统按照预设时间间隔所采集的经纬度坐标，每个经纬度坐标对应一个轨迹点数据，这样，服务提供端可以将采集的轨迹点数据实时上报给订单服务安全性检测装置以便该装置进行订单服务安全性检测。同理，在服务请求端作为数据上报端时，也可以基于定位技术确定内置的定位系统按照预设时间间隔所采集的经纬度坐标，每个经纬度坐标对应一个轨迹点数据，在确定该服务请求端与服务提供端对应同一个当前出行订单时，可以将采集的轨迹点数据实时上报给订单服务安全性检测装置以便该装置进行订单服务安全性检测。
在实际应用中，除了可以基于服务提供端和服务请求端上报的轨迹点数据确定服务提供端在服务当前出行订单过程中的轨迹点数据，还可以基于服务提供端与车载终端的绑定关系，将车载终端上报的轨迹点数据作为服务提供端的轨迹点数据。
实施例十
本公开实施例十四还提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行上述任意实施例所述订单服务安全性检测方法的步骤。
具体地，该存储介质能够为通用的存储介质，如移动磁盘、硬盘等，该存储介质上的计算机程序被运行时，能够执行上述订单服务安全性检测方法，从而解决目前通过司机和相关车辆在网约车平台的审核通过来初步判断出行服务的安全性，无法应对当前网约车环境的复杂性，对于乘客的安全并没有进行有效的保障和预防等问题，进而达到对订单服务的安全性进行有效检测，且检测的准确性较好的效果。
本公开实施例所提供的订单服务安全性检测方法的计算机程序产品，包括存储了程序代码的计算机可读存储介质，程序代码包括的指令可用于执行前面方法实施例中的方法，具体实现可参见方法实施例，在此不再赘述。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统和装置的具体工作过程，可以参考方法实施例中的对应过程，本公开中不再赘述。在本公开所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或模块的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上仅为本公开的具体实施例，但本公开的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以权利要求的保护范围为准。
工业实用性
本公开提供的订单服务安全性检测装置及方法，基于轨迹点数据来确定服务提供端在提供出行服务时是否存在异常行为(如驾驶停留时长较长、路线偏移过大等)，以确定服务的安全性与否，实现了对服务安全性的有效检测，且检测的准确性较好，从而不仅能够很好的约束服务提供方的服务行为，还能够进一步确保乘客的用车安全。

Claims (26)

  1. 一种订单服务安全性检测装置，所述装置包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如下处理：
    获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
    根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
  2. 根据权利要求1所述的装置，所述装置还包括：通信接口；所述通信接口与所述处理器之间通过总线通信；
    所述通信接口，用于接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据。
  3. 根据权利要求2所述的装置，对于所述获取服务提供端在服务当前出行订单过程中的轨迹点数据，所述机器可读指令被处理器执行时还执行如下处理：
    通过通信接口接收服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据；
    将接收的服务提供端或服务请求端上报的在当前出行订单被执行过程中的轨迹点数据，作为服务提供端在服务当前出行订单过程中的轨迹点数据。
  4. 根据权利要求1至3任一所述的装置，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；对于根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性，所述机器可读指令被处理器执行时执行如下处理：
    当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
    所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
    所述服务提供端的路线连续偏移时长大于第二时长阈值。
  5. 根据权利要求4所述的装置，对于针对任一位置，确定该位置是否为偏僻度大于偏僻度阈值的位置，所述机器可读指令被处理器执行时执行如下处理：
    确定所述任一位置所在的区域；
    若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
  6. 根据权利要求5所述的装置，所述机器可读指令被处理器执行时还执行如下处理：
    将目标地理区域范围划分为多个预设大小的区域；
    确定划分出的每个区域内产生的订单数量；
    根据所述订单数量，确定划分出的每个区域的偏僻度。
  7. 根据权利要求4至6任一所述的装置，对于确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理：
    分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
    将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
    根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
  8. 根据权利要求7所述的装置，对于根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值，所述机器可读指令被处理器执行时执行如下处理：
    根据每个配对组合对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个配对组合，并将选取的配对组合中的偏僻度作为所述偏僻度阈值，将选取的配对组合中的最大停留时长作为所述第一时长阈值。
  9. 根据权利要求4至8任一所述的装置，对于确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理：
    分别获取每个历史异常出行订单的最大连续偏移时长；
    针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
    根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
  10. 根据权利要求9所述的装置，对于根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值，所述机器可读指令被处理器执行时执行如下处理：
    根据每个最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率，以及预设的历史出行订单覆盖量选择范围和历史异常订单召回率选择范围，选取一个最大连续偏移时长，并将选取的最大连续偏移时长作为所述第二时长阈值。
  11. 根据权利要求4至10任一所述的装置，对于确定所述路线连续偏移时长，所述机器可读指令被处理器执行时执行如下处理：
    将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
  12. 根据权利要求4至11任一所述的装置，当确定所述当前出行订单的服务安全存在问题后，所述机器可读指令被处理器执行时还执行如下处理：
    根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
  13. 根据权利要求12所述的装置，对于根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略，所述机器可读指令被处理器执行时执行如下处理：
    若所述时长范围属于第一时长范围，向所述服务提供端和/或服务请求端发送预设的提示语音；
    若所述时长范围属于第二时长范围，向所述服务提供端和/或服务请求端发送等待语音反馈的安全确认请求语音；
    若所述时长范围属于第三时长范围，向所述服务提供端和/或服务请求端发起人工呼叫请求；
    其中，所述第一时长范围、第二时长范围和第三时长范围互不重叠，且所述第二时长范围内的时长大于第一时长范围内的时长、小于第三时长范围内的时长。
  14. 根据权利要求13所述的装置，在向所述服务提供端和/或服务请求端发送等待反馈的安全确认请求语音之后，所述机器可读指令被处理器执行时还执行如下处理：
    若在预设时长内没有接收到安全确认语音，则重复发送安全确认请求语音，直到接收到安全确认语音，或者直到重复发送安全确认请求语音的次数大于设定阈值，则发起人工呼叫请求；
    若接收到反馈当前存在危险的语音，则发起人工呼叫请求。
  15. 一种订单服务安全性检测装置，所述装置包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如下处理：
    获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
    根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
  16. 一种订单服务安全性检测方法，其特征在于，所述方法包括：
    获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
    根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
  17. 根据权利要求16所述的方法，其特征在于，所述驾驶停留信息包括停留的位置信息和停留时长；所述路线偏移信息包括路线连续偏移时长；
    根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性，包括：当满足以下条件中的任意一种时，确定所述当前出行订单的服务安全存在问题：
    所述服务提供端停留在偏僻度大于偏僻度阈值的位置的停留时长大于第一时长阈值；
    所述服务提供端的路线连续偏移时长大于第二时长阈值。
  18. 根据权利要求17所述的方法，其特征在于，针对任一位置，根据以下步骤确定该位置是否为偏僻度大于偏僻度阈值的位置：
    确定所述任一位置所在的区域；
    若所述区域对应的偏僻度大于偏僻度阈值，则确定所述任一位置为偏僻度大于偏僻度阈值的位置。
  19. 根据权利要求17或18所述的方法，其特征在于，根据以下步骤确定所述偏僻度阈值和所述第一时长阈值：
    分别获取每个历史异常出行订单在各个采样轨迹点的最大停留时长以及最大停留时长对应采样轨迹点的偏僻度；所述历史异常出行订单是指接收到用户投诉的出行订单；
    将任一所述最大停留时长和任一采样轨迹点的偏僻度作为一个配对组合，确定该配对组合对应的历史出行订单覆盖量以及历史异常订单召回率；所述配对组合对应的历史出行订单覆盖量是指在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史出行订单的数量；所述配对组合对应的历史异常订单召回率是指经过调查，在一采样轨迹点的偏僻度大于该配对组合中的偏僻度，且在该采样轨迹点的停留时长大于该配对组合中的最大停留时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
    根据每个配对组合对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述偏僻度阈值和所述第一时长阈值。
  20. 根据权利要求17至19任一所述的方法，其特征在于，根据以下步骤确定所述第二时长阈值：
    分别获取每个历史异常出行订单的最大连续偏移时长；
    针对每个最大连续偏移时长，确定该最大连续偏移时长对应的历史出行订单覆盖量和历史异常订单召回率；其中，该最大连续偏移时长对应的历史出行订单覆盖量是指对应的最大连续偏移时长大于当前该最大连续偏移时长的历史出行订单的数量；该最大连续偏移时长对应的历史异常订单召回率是指经过调查，在对应的最大连续偏移时长大于当前该最大连续偏移时长的历史异常出行订单在所有历史异常出行订单中的订单占比；
    根据每个最大连续偏移时长对应的历史出行订单覆盖量以及历史异常订单召回率，确定所述第二时长阈值。
  21. 根据权利要求17至20任一所述的方法，其特征在于，根据以下步骤确定所述路线连续偏移时长：
    将所述服务提供端的当前行驶方向与参考行驶方向之间的夹角连续大于设定夹角阈值的持续时长确定为所述路线连续偏移时长；所述参考行驶方向是指从所述服务提供端的当前轨迹点位置与所述当前出行订单的目的地的连线方向。
  22. 根据权利要求17至21任一所述的方法，其特征在于，当确定所述当前出行订单的服务安全存在问题后，所述方法还包括：
    根据所述停留时长和/或路线连续偏移时长分别所属的时长范围，执行与确定的时长范围对应的处理策略。
  23. 一种订单服务安全性检测方法，其特征在于，所述方法包括：
    获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
    根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
  24. 一种订单服务安全性检测装置，其特征在于，所述装置包括：
    轨迹点获取模块，用于获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    信息确定模块，用于基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息和路线偏移信息；
    安全检测模块，用于根据所述服务提供端的驾驶停留信息和路线偏移信息，确定所述当前出行订单的服务安全性。
  25. 一种订单服务安全性检测装置，其特征在于，所述装置包括：
    轨迹点获取模块，用于获取服务提供端在服务当前出行订单过程中的轨迹点数据；
    信息确定模块，用于基于所述轨迹点数据，确定所述服务提供端的驾驶停留信息；
    安全检测模块，用于根据所述服务提供端的驾驶停留信息，确定所述当前出行订单的服务安全性。
  26. 一种计算机可读存储介质，其特征在于，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求16至23任一所述的订单服务安全性检测方法的步骤。
PCT/CN2019/103945 2018-10-25 2019-09-02 订单服务安全性检测装置及方法 WO2020082900A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811251791.XA CN111105243B (zh) 2018-10-25 2018-10-25 订单服务安全性检测方法及装置、计算机可读存储介质
CN201811251791.X 2018-10-25

Publications (1)

Publication Number Publication Date
WO2020082900A1 true WO2020082900A1 (zh) 2020-04-30

Family

ID=70331866

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/103945 WO2020082900A1 (zh) 2018-10-25 2019-09-02 订单服务安全性检测装置及方法

Country Status (2)

Country Link
CN (1) CN111105243B (zh)
WO (1) WO2020082900A1 (zh)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111833145A (zh) * 2020-07-02 2020-10-27 北京嘀嘀无限科技发展有限公司 信息显示方法、装置、电子设备和存储介质
CN111860594A (zh) * 2020-06-16 2020-10-30 北京嘀嘀无限科技发展有限公司 绕路订单识别方法、装置、电子设备和可读存储介质
CN112001349A (zh) * 2020-08-31 2020-11-27 杭州海康威视数字技术股份有限公司 数据审核方法、系统及电子设备
CN112053098A (zh) * 2020-09-30 2020-12-08 北京嘀嘀无限科技发展有限公司 订单处理方法、装置、服务器及计算机存储介质
CN112184519A (zh) * 2020-08-18 2021-01-05 汉海信息技术(上海)有限公司 行程监控方法、装置、电子设备及存储介质
CN112328515A (zh) * 2020-11-04 2021-02-05 北京嘀嘀无限科技发展有限公司 设备检测方法及装置
CN112819670A (zh) * 2021-01-08 2021-05-18 北京嘀嘀无限科技发展有限公司 信息处理方法、装置、可读存储介质和电子设备
CN113688679A (zh) * 2021-07-22 2021-11-23 南京视察者智能科技有限公司 一种重点人员防控预警的方法
CN113723858A (zh) * 2021-09-10 2021-11-30 首约科技(北京)有限公司 一种依据供需的网约车排队场景的分析方法

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111260167B (zh) * 2018-11-30 2022-08-30 北京嘀嘀无限科技发展有限公司 订单服务安全性检测方法、装置、电子设备及存储介质
CN111986470B (zh) * 2020-07-20 2022-11-29 汉海信息技术(上海)有限公司 网约车安全监控方法、装置、电子设备及存储介质
CN111967725A (zh) * 2020-07-23 2020-11-20 汉海信息技术(上海)有限公司 输出提示信息的方法、终端、服务器、设备及存储介质
CN112069391B (zh) * 2020-07-23 2024-04-16 江苏运满满同城信息科技有限公司 一种基于Geohash的货物顺路拼车的方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103179503A (zh) * 2011-12-23 2013-06-26 宇龙计算机通信科技(深圳)有限公司 移动终端和提醒方法
CN103530734A (zh) * 2013-10-23 2014-01-22 苏州海客科技有限公司 旅游轨迹非实时监控方法
CN105160880A (zh) * 2015-09-24 2015-12-16 滴滴（中国）科技有限公司 一种车辆载客状态的预估方法及装置
CN108154283A (zh) * 2016-12-06 2018-06-12 北京嘀嘀无限科技发展有限公司 司机驾驶行为分析方法及装置
CN108665698A (zh) * 2018-05-21 2018-10-16 杭州优行科技有限公司 基于轨迹的网约车监管方法及装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103544820B (zh) * 2012-07-11 2015-08-26 张凯杰 出租车的安全监控系统及其方法
CN105243838B (zh) * 2015-11-09 2018-05-04 北京奇虎科技有限公司 车辆行驶安全监控方法和装置、系统
CN105679067B (zh) * 2016-02-22 2019-12-13 腾讯科技（深圳）有限公司 一种信息处理方法、第一终端及服务器
US9952056B2 (en) * 2016-03-11 2018-04-24 Route4Me, Inc. Methods and systems for detecting and verifying route deviations

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103179503A (zh) * 2011-12-23 2013-06-26 宇龙计算机通信科技(深圳)有限公司 移动终端和提醒方法
CN103530734A (zh) * 2013-10-23 2014-01-22 苏州海客科技有限公司 旅游轨迹非实时监控方法
CN105160880A (zh) * 2015-09-24 2015-12-16 滴滴（中国）科技有限公司 一种车辆载客状态的预估方法及装置
CN108154283A (zh) * 2016-12-06 2018-06-12 北京嘀嘀无限科技发展有限公司 司机驾驶行为分析方法及装置
CN108665698A (zh) * 2018-05-21 2018-10-16 杭州优行科技有限公司 基于轨迹的网约车监管方法及装置

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111860594A (zh) * 2020-06-16 2020-10-30 北京嘀嘀无限科技发展有限公司 绕路订单识别方法、装置、电子设备和可读存储介质
CN111833145A (zh) * 2020-07-02 2020-10-27 北京嘀嘀无限科技发展有限公司 信息显示方法、装置、电子设备和存储介质
CN112184519A (zh) * 2020-08-18 2021-01-05 汉海信息技术(上海)有限公司 行程监控方法、装置、电子设备及存储介质
CN112001349B (zh) * 2020-08-31 2023-09-26 杭州海康威视数字技术股份有限公司 数据审核方法、系统及电子设备
CN112001349A (zh) * 2020-08-31 2020-11-27 杭州海康威视数字技术股份有限公司 数据审核方法、系统及电子设备
CN112053098A (zh) * 2020-09-30 2020-12-08 北京嘀嘀无限科技发展有限公司 订单处理方法、装置、服务器及计算机存储介质
CN112053098B (zh) * 2020-09-30 2021-11-02 北京嘀嘀无限科技发展有限公司 订单处理方法、装置、服务器及计算机存储介质
CN112328515A (zh) * 2020-11-04 2021-02-05 北京嘀嘀无限科技发展有限公司 设备检测方法及装置
CN112328515B (zh) * 2020-11-04 2024-05-07 北京嘀嘀无限科技发展有限公司 设备检测方法及装置
CN112819670A (zh) * 2021-01-08 2021-05-18 北京嘀嘀无限科技发展有限公司 信息处理方法、装置、可读存储介质和电子设备
CN113688679B (zh) * 2021-07-22 2024-03-08 南京视察者智能科技有限公司 一种重点人员防控预警的方法
CN113688679A (zh) * 2021-07-22 2021-11-23 南京视察者智能科技有限公司 一种重点人员防控预警的方法
CN113723858A (zh) * 2021-09-10 2021-11-30 首约科技(北京)有限公司 一种依据供需的网约车排队场景的分析方法

Also Published As

Publication number Publication date
CN111105243A (zh) 2020-05-05
CN111105243B (zh) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2020082900A1 (zh) 订单服务安全性检测装置及方法
US11821737B2 (en) Public and ordered transportation trip planning
US11062415B2 (en) Systems and methods for allocating networked vehicle resources in priority environments
CN108765933B (zh) 一种推荐上车点的方法、装置、设备及存储介质
US9024752B2 (en) Traveler hurry status monitor
US10197410B2 (en) Dynamic real-time carpool matching
US20180060989A1 (en) System, method and device for digitally assisted personal mobility management
US9111403B2 (en) Systems and methods for tracking device control and report
CN107421554A (zh) 导航路径确定方法、装置、车载设备和存储介质
EP2708850A1 (en) Method and system for performing travel assistance for a user
CN111260167B (zh) 订单服务安全性检测方法、装置、电子设备及存储介质
KR20150039851A (ko) 공공 교통 네비게이터
CN111147532A (zh) 一种信息分享方法、装置、设备及介质
CN113892275A (zh) 一种定位方法、装置、电子设备及存储介质
CN110730416A (zh) 基于定位数据的车辆安全管理方法和装置
CN110798807A (zh) 用于记录车辆轨迹的方法、装置、计算机设备和介质
JP2003217093A (ja) バスナビゲーションシステム
JP6439251B2 (ja) 車両管理システム及び車両管理方法
KR101626235B1 (ko) 여행자 긴급 상태 모니터
CN104269050A (zh) 一种交通信息处理系统
CN110062040B (zh) 一种救援消息推送方法及装置
CN111651687B (zh) 上车点信息推送方法及装置、下车点信息推送方法及装置
US20210150419A1 (en) Systems and methods for determining rideable vehicle locations
US11800321B2 (en) Server and communication system
CN110363981B (zh) 一种出租车交接方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19875727

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19875727

Country of ref document: EP

Kind code of ref document: A1