System and method for calculating total driving time of online car-hailing driver based on multi-account identification

Abstract

The application provides a system and method for calculating the total driving time of a driver of a network car-hailing service based on multi-account identification. For different network car-hailing platforms, driver accounts with the same ID number or the same mobile phone number are determined as the same account. For accounts with different ID numbers and mobile phone numbers, similarity analysis is performed based on the movement trajectory within a certain period of time to determine whether they are the same account. The system receives a driver work time query request and sends a driver work time calculation request within a specific period to several privacy computing access ends. The calculation steps are sent to a time series database. Based on the time series database calculation results sent by each privacy computing access end, the working hours of the same account on different network car-hailing platforms are accumulated to obtain the total working hours of the driver within a specific period. The application realizes the identification of multi-accounts of network car-hailing drivers across platforms, accurately calculates the total driving time of the driver, and protects privacy data and the business secrets of the network car-hailing company through privacy calculation.

Description

Technical Field

[0001] This invention relates to the field of privacy computing technology, and in particular to a system and method for calculating the total driving time of ride-hailing drivers based on multi-account identification. Background Technology

[0002] With societal development, people's travel options have become increasingly diverse, including private cars, subways, and buses. Thanks to the rapid development of the internet, ride-hailing services have also become an increasingly important mode of transportation. However, while providing convenience, ride-hailing services also pose significant risks. For example, to prevent fatigue driving, a single ride-hailing platform typically only allows a specific vehicle to operate continuously for 3-4 hours, or cumulatively for no more than 8 hours. Exceeding these limits will result in no further orders being assigned to that vehicle. However, due to the existence of multiple ride-hailing platforms, drivers can register on multiple platforms. When the operating time limit on one platform is reached and no more orders can be assigned, the driver can switch to another platform. This can lead to drivers being continuously fatigued, endangering not only the personal safety of the driver and passengers but also the safety of pedestrians and other vehicles on the road.

[0003] Due to the independence of each ride-hailing platform, the information of ride-hailing drivers and vehicles is an internal trade secret of each ride-hailing company, making it impossible to effectively control drivers' cross-platform registration behavior.

[0004] If a driver registers using the same personal information, such as a mobile phone number and ID number, on different platforms, it's possible to identify the two accounts as belonging to the same driver. However, if a driver registers using different personal information on different platforms, or uses two different sets of personal information on the same platform, it's impossible to accurately determine the driver's total working hours. Therefore, it's necessary to compare accounts across different platforms to identify multiple accounts belonging to the driver. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention provides a system and method for calculating the total driving time of ride-hailing drivers based on multi-account identification, which identifies multiple accounts of the driver to obtain the driver's accurate working hours.

[0006] To achieve the above objectives, the present invention provides a system for calculating the total driving time of ride-hailing drivers based on multi-account identification, including a privacy computing center and several distributed computing terminals;

[0007] The computing terminal includes a time-series database and a privacy computing access terminal;

[0008] The time-series database synchronizes in real time the platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platform; based on the calculation steps sent by the privacy computing access terminal, it reads the corresponding data and performs calculations.

[0009] After receiving a request to identify driver accounts initiated by the privacy computing center, the privacy computing access terminal reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center; after receiving a time calculation request initiated by the privacy computing center, it forms calculation steps and sends them to the time-series database, reads the calculation results from the time-series database, and sends the calculation results to the privacy computing center.

[0010] The privacy computing center identifies driver accounts with the same ID number or mobile phone number on different ride-hailing platforms as the same account; for accounts with different ID numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if similar, it identifies them as the same account; it receives driver work time query requests and sends driver work time calculation requests for a specific time period to several privacy computing access terminals; based on the calculation results sent by each privacy computing access terminal, it accumulates the work hours of the same account on different ride-hailing platforms to obtain the driver's total work hours within the specific time period.

[0011] Furthermore, the time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate movement trajectories, thus forming account behavior data;

[0012] The privacy computing access terminal receives account behavior data of each account from the time-series database and converts it into intermediate data for transmission to the privacy computing center.

[0013] The privacy computing center receives intermediate data from at least one privacy computing access point and restores it to account behavior data. It then performs similarity analysis on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account.

[0014] Furthermore, the privacy computing center extracts the account's login time, logout time, login location, logout location, and movement trajectory from the account behavior data;

[0015] The method of performing similarity analysis on account behavior data from different accounts to classify different accounts with similarity thresholds as the same account includes at least one of the following steps:

[0016] A similarity analysis is performed between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, the first account and the second account are considered to be the same account.

[0017] A similarity analysis is performed between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered to be the same account.

[0018] A similarity analysis is performed between the login locations of the first account and the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, the first account and the second account are considered to be the same account.

[0019] A similarity analysis is performed between the exit locations of the first account and the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, the first account and the second account are considered to be the same account.

[0020] The similarity analysis of the movement trajectory of the first account and the movement trajectory of the second account is performed. If the similarity of the movement trajectories of the first account and the second account meets the fifth similarity threshold, the first account and the second account are regarded as the same account.

[0021] Furthermore, the method of performing similarity analysis on account behavior data of different accounts to classify different accounts with similarity thresholds as the same account also includes at least one of the following steps:

[0022] The similarity analysis of the logout time of the first account and the login time of the second account is performed. If the similarity of the handover time of the first account and the second account meets the sixth similarity threshold, the first account and the second account are considered to be the same account.

[0023] The similarity analysis is performed between the logout location of the first account and the login location of the second account. If the similarity of the intersection point of the first account and the second account meets the seventh similarity threshold, the first account and the second account are considered to be the same account.

[0024] Furthermore, the first account and the second account are accounts with at least one different ID card number or mobile phone number on the same platform, or the first account and the second account are accounts with at least one different ID card number or mobile phone number on different platforms.

[0025] Furthermore, the calculation of the time-series database includes at least the following steps: obtaining the driver's corresponding number from the calculation steps, reading the start time and end time of each dispatch within a specific time period corresponding to the number, and calculating the working time of each dispatch.

[0026] The working hours obtained from different dispatch and driving data are summed up to obtain the driver's total working hours within a specific time period.

[0027] The second aspect provides a method for calculating the total driving time of ride-hailing drivers based on multi-account recognition, including:

[0028] The time-series database synchronizes platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platforms in real time.

[0029] The privacy computing center initiates a request to identify the driver's account and sends it to each privacy computing access point.

[0030] After receiving the request to identify the driver's account, the privacy computing access terminal reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center.

[0031] The privacy computing center identifies driver accounts with the same ID number or the same mobile phone number on different ride-hailing platforms as the same account; for accounts with different ID numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if they are similar, it identifies them as the same account.

[0032] The privacy computing center receives driver work time query requests and sends driver work time calculation requests for a specific time period to several privacy computing access terminals.

[0033] After receiving a time calculation request initiated by the privacy computing center, the privacy computing access terminal forms calculation steps and sends them to the time series database, and reads the calculation results from the time series database; the time series database, based on the calculation steps sent by the privacy computing access terminal, reads the corresponding data and performs the calculation; the privacy computing access terminal sends the calculation results to the privacy computing center.

[0034] The privacy computing center, based on the calculation results sent by each privacy computing access terminal, accumulates the working hours of the same account on different ride-hailing platforms to obtain the total working hours of the driver within a specific time period.

[0035] Furthermore, the time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate movement trajectories, thus forming account behavior data;

[0036] The privacy computing access terminal receives account behavior data of each account from the time-series database and converts it into intermediate data for transmission to the privacy computing center.

[0037] The privacy computing center receives intermediate data from at least one privacy computing access point and restores it to account behavior data. It then performs similarity analysis on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account.

[0038] Furthermore, the privacy computing center extracts the account's login time, logout time, login location, logout location, and movement trajectory from the account behavior data;

[0039] The method of performing similarity analysis on account behavior data from different accounts to classify different accounts with similarity thresholds as the same account includes at least one of the following steps:

[0040] A similarity analysis is performed between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, the first account and the second account are considered to be the same account.

[0041] A similarity analysis is performed between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered to be the same account.

[0042] A similarity analysis is performed between the login locations of the first account and the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, the first account and the second account are considered to be the same account.

[0043] A similarity analysis is performed between the exit locations of the first account and the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, the first account and the second account are considered to be the same account.

[0044] The similarity analysis of the movement trajectory of the first account and the movement trajectory of the second account is performed. If the similarity of the movement trajectories of the first account and the second account meets the fifth similarity threshold, the first account and the second account are regarded as the same account.

[0045] A third aspect provides an electronic device, including a processor and a memory, wherein the memory is used to store program instructions, and the processor is used to call the program instructions to execute the method for calculating the total driving time of ride-hailing drivers based on multi-account recognition.

[0046] The fourth aspect provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the method for calculating the total driving time of ride-hailing drivers based on multi-account recognition.

[0047] The above-described technical solution of the present invention has the following beneficial technical effects:

[0048] (1) This invention enables cross-platform identification of multiple accounts of ride-hailing drivers, accurately calculates the total driving time of drivers, and protects privacy data and the trade secrets of ride-hailing companies through privacy calculation.

[0049] (2) This invention utilizes the characteristics of fast computation of time-series databases to greatly improve the completion speed of each step of privacy and security computation. Attached Figure Description

[0050] Figure 1 These are schematic diagrams illustrating the structure of a ride-hailing driver total driving time calculation system based on multi-account recognition, provided in some embodiments.

[0051] Figure 2 Here are some implementation examples of a method for calculating the total driving time of ride-hailing drivers based on multi-account identification;

[0052] Figure 3 This is a schematic diagram of the components of an electronic device. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments and the accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of the invention. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0054] In some embodiments, a system for calculating the total driving time of ride-hailing drivers based on multi-account identification is provided, including a privacy computing center and several distributed computing terminals. The computing terminals include a time-series database and a privacy computing access terminal.

[0055] The time-series database synchronizes in real time the platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platform; based on the calculation steps sent by the privacy computing access terminal, it reads the corresponding data and performs calculations.

[0056] Further, the time-series database, according to the calculation steps, receives calculation step i initiated by the privacy computing access terminal; extracts the data required for calculating calculation step i, calls the corresponding function, completes the calculation of calculation step i, and forms a calculation result. The privacy computing access terminal, after receiving a request to identify driver accounts initiated by the privacy computing center, reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center; after receiving a time calculation request initiated by the privacy computing center, it forms a calculation step and sends it to the time-series database, reads the calculation result from the time-series database, and sends the calculation result to the privacy computing center. In one embodiment, to avoid leaking data required by the privacy computing access terminal during the time-series database calculation process, or leaking data required for the time-series database calculation, the privacy computing access terminal uses a privacy computing method to obtain the calculation result from the time-series database, and uses privacy information retrieval (PIR) or privacy set intersection (PSI) methods to obtain the calculation result from the time-series database.

[0057] The privacy computing center identifies driver accounts with the same ID number or mobile phone number on different ride-hailing platforms as the same account; for accounts with different ID numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if similar, it identifies them as the same account; it receives driver work time query requests and sends driver work time calculation requests for a specific time period to several privacy computing access terminals; based on the calculation results sent by each privacy computing access terminal, it accumulates the work hours of the same account on different ride-hailing platforms to obtain the driver's total work hours within the specific time period.

[0058] Specific time periods, such as 24 hours, 12 hours, or 8 hours, are determined based on demand.

[0059] In one embodiment, the time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate a movement trajectory, thus forming account behavior data.

[0060] The privacy computing access terminal forms a computing step to receive account behavior data of each account from the time-series database, convert it into intermediate data, and transmit it to the privacy computing center for similarity analysis.

[0061] The privacy computing center receives intermediate data from at least one privacy computing access point and restores it to account behavior data. It then performs similarity analysis on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account.

[0062] In one embodiment, the calculation of the time-series database includes at least the following steps: obtaining the driver's corresponding ID through the calculation steps; reading the start and end times of each dispatch within a specific time period corresponding to the ID; calculating the working time of each dispatch; and summing the working times obtained from different dispatches and driving data to obtain the driver's total working time within the specific time period.

[0063] In one embodiment, the privacy computing center obtains the time and location information of N drivers logging into and out of the system from each of the privacy computing access terminals. A time-series database calculates the most likely location and time of the exit location. The most likely locations and times calculated by different time-series databases are compared, and the m most similar accounts are selected. Alternatively, in an optional embodiment, this scheme can also obtain the movement trajectories of the m accounts over the past few days, find the same time period of the location by calculating the intersection PSI of the privacy protection set, and compare the locations at the same time. If the overlap rate is greater than a set threshold, the accounts are determined to be the same.

[0064] In an optional embodiment, in addition to analyzing the similarity of movement trajectories of different accounts, this application can also analyze whether the login time, login location, logout time, and logout location of different accounts are similar to determine whether different accounts belong to the same account. Specifically, the privacy computing center extracts the login time, logout time, login location, logout location, and movement trajectory of accounts from account behavior data. Performing similarity analysis on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account includes at least one of the following steps:

[0065] 1. Perform a similarity analysis between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, then the first account and the second account are considered to be the same account.

[0066] 2. Perform a similarity analysis between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered as the same account.

[0067] 3. Perform a similarity analysis between the login location of the first account and the login location of the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, then the first account and the second account will be considered as the same account.

[0068] 4. Perform a similarity analysis between the exit location of the first account and the exit location of the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, then the first account and the second account are considered as the same account.

[0069] 5. Perform a similarity analysis between the movement trajectory of the first account and the movement trajectory of the second account. If the similarity between the movement trajectories of the first account and the second account meets the fifth similarity threshold, then the first account and the second account are considered as the same account.

[0070] If a driver habitually uses two different registered accounts simultaneously, and the movement trajectories monitored by the two different platforms are largely the same, the similarity of the movement trajectories of the two accounts can be used to make a judgment.

[0071] For drivers with multiple accounts, they may use two accounts simultaneously. The login time, login location, logout time, and logout location of the two accounts may be close. Therefore, this application embodiment can analyze whether the login time is close (e.g., the login time difference between different accounts is within ten minutes), whether the login location is close (e.g., the distance is within three kilometers), whether the logout time is close, and whether the logout location is close, thereby determining whether the two accounts are the same account.

[0072] The first similarity threshold (or second similarity threshold) can be set to determine whether the number of similar login (or logout) times within a preset period exceeds a preset number. For example, data from 30 days can be extracted; if two accounts have 10 login times within half an hour of each other, the two accounts can be considered highly similar. The second similarity threshold can be set according to requirements. For example, data from 30 days can be extracted; if two accounts have 15 logout times within half an hour of each other, the two accounts can be considered highly similar.

[0073] The third similarity threshold (or the filamentary similarity threshold) can be set to whether the number of similar login (or logout) locations within a preset time period exceeds a preset number. For example, if 30 days of data are extracted, and two accounts have 13 login locations within 1 km of each other, the two accounts can be considered highly similar. Similarly, if 30 days of data are extracted, and two accounts have 12 logout locations within 1.5 km of each other, the two accounts can be considered highly similar.

[0074] The fifth similarity threshold can be whether the number of similar movement trajectories within a preset time period exceeds a preset number. The similarity of movement trajectories can be determined based on whether the overlap distance of the movement trajectories exceeds the overlap distance threshold.

[0075] There is no restriction on the order of the five steps described above, nor is there any restriction on the choice of steps. You can choose 1 to 5 steps and combine them in the selected order.

[0076] Furthermore, for drivers with multiple accounts, they may not use both accounts simultaneously, but rather use one account followed by another. Therefore, embodiments of this application can also analyze the handover behavior between two accounts to determine the similarity between the accounts. Specifically, in one embodiment, similarity analysis is performed on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account, and the analysis further includes at least one of the following steps:

[0077] 1. Perform a similarity analysis between the logout time of the first account and the login time of the second account. If the similarity between the handover time of the first account and the second account meets the sixth similarity threshold, the first account and the second account are considered to be the same account.

[0078] 2. Perform a similarity analysis between the logout location of the first account and the login location of the second account. If the similarity of the intersection point of the first account and the second account meets the seventh similarity threshold, the first account and the second account will be considered as the same account.

[0079] If a driver chooses to use two accounts alternately, it's common for them to log out of one account and log in to the other. Therefore, it's important to analyze the handover times between the accounts. If there are multiple instances where the logout time of the first account is close to the login time of the second account, the two accounts can be considered highly similar. For example, if, after extracting 30 days of data, the handover times of the two accounts differ by half an hour 10 times, it can be determined that the two accounts are highly similar.

[0080] If a driver chooses to use two accounts alternately, it's common to log out of one account and log in to the other. Therefore, the points of overlap between the different accounts are relatively close. If the logout location of the first account and the login location of the second account are close multiple times, the two accounts can be considered highly similar. For example, if 30 days of data are extracted and the points of overlap between the two accounts are within 1 km 10 times, it can be determined that the two accounts are highly similar.

[0081] In this embodiment, the two steps described above are not restricted in any particular order, nor are the steps themselves limited. One or two steps can be selected and combined in the chosen order.

[0082] Furthermore, the first account and the second account are accounts with at least one different ID card number or mobile phone number on the same platform, or the first account and the second account are accounts with at least one different ID card number or mobile phone number on different platforms.

[0083] In some embodiments, a method for calculating the total driving time of ride-hailing drivers based on multi-account identification is provided, including the following steps:

[0084] The S100 time-series database synchronizes platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platforms in real time.

[0085] This step is executed in real time and has no order restriction with other steps. Figure 2 At least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. Their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0086] In one embodiment, the time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate a movement trajectory, thus forming account behavior data.

[0087] The S200 privacy computing center initiates a request to identify driver accounts, which is then sent to each privacy computing access terminal. Upon receiving the driver account identification request, each privacy computing access terminal reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center.

[0088] In one embodiment, the privacy computing access terminal performs computing steps to receive account behavior data of each account from a time-series database, convert it into intermediate data, and transmit it to the privacy computing center for similarity analysis.

[0089] The privacy computing access point forms computing steps including the computing steps required for the privacy computing request, and obtains the computing results of the time series database by using privacy information retrieval (PIR) or privacy set intersection (PSI).

[0090] The time-series database receives calculation step i initiated by the privacy computing access terminal according to the calculation steps; extracts the data required to calculate calculation step i, calls the corresponding function, completes the calculation of calculation step i, and forms the calculation result.

[0091] The time-series database obtains the driver's corresponding ID through the calculation steps, reads the start and end times of each dispatch within a specific time period corresponding to that ID, and calculates the working time for each dispatch. The time-series database then sums the working times obtained from different dispatches and driving data to obtain the driver's total working time within the specific time period.

[0092] The privacy computing center described in S300 determines that driver accounts with the same ID card number or the same mobile phone number on different ride-hailing platforms are the same account; for accounts with different ID card numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if they are similar, they are determined to be the same account.

[0093] In one embodiment, the privacy computing center receives intermediate data of an account from at least one privacy computing access point and restores it to account behavior data, so as to perform similarity analysis on the account behavior data of different accounts and classify different accounts with similarity that meet the similarity threshold as the same account.

[0094] The privacy computing center extracts login time, logout time, login location, logout location, and movement trajectory from account behavior data. It then performs similarity analysis on the account behavior data of different accounts to classify different accounts with similarity thresholds as the same account, including at least one of the following steps:

[0095] 1. Perform a similarity analysis between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, then the first account and the second account are considered to be the same account.

[0096] 2. Perform a similarity analysis between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered as the same account.

[0097] 3. Perform a similarity analysis between the login location of the first account and the login location of the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, then the first account and the second account will be considered as the same account.

[0098] 4. Perform a similarity analysis between the exit location of the first account and the exit location of the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, then the first account and the second account are considered as the same account.

[0099] 5. Perform a similarity analysis between the movement trajectory of the first account and the movement trajectory of the second account. If the similarity between the movement trajectories of the first account and the second account meets the fifth similarity threshold, then the first account and the second account are considered as the same account.

[0100] There is no restriction on the order of the five steps described above, nor is there any restriction on the choice of steps. You can choose 1 to 5 steps and combine them in the selected order.

[0101] In one embodiment, performing similarity analysis on account behavior data of different accounts to classify different accounts with similarity thresholds as the same account further includes at least one of the following steps:

[0102] 1. Perform a similarity analysis between the logout time of the first account and the login time of the second account. If the similarity between the handover time of the first account and the second account meets the sixth similarity threshold, the first account and the second account are considered to be the same account.

[0103] 2. Perform a similarity analysis between the logout location of the first account and the login location of the second account. If the similarity of the intersection point of the first account and the second account meets the seventh similarity threshold, the first account and the second account will be considered as the same account.

[0104] In this embodiment, the two steps described above are not restricted in any particular order, nor are the steps themselves limited. One or two steps can be selected and combined in the chosen order.

[0105] The method in this embodiment is similar to the data processing flow of the system in the above embodiment. For specific implementation methods, please refer to the specific implementation methods of the above system, which will not be repeated here.

[0106] Furthermore, the first account and the second account are accounts with at least one different ID card number or mobile phone number on the same platform, or the first account and the second account are accounts with at least one different ID card number or mobile phone number on different platforms.

[0107] In one embodiment, the privacy computing center performs similarity analysis based on movement trajectories over a period of time, including:

[0108] Each privacy-preserving computing access point obtains the time and location information of drivers logging into or out of the system N times. A time-series database calculates the most likely location and time of the exit point. The most likely locations and times calculated by different time-series databases are compared, and the m most similar accounts are selected. The movement trajectories of these m accounts over the past few days are obtained. A PSI (Personal Segment Intersection) algorithm is used to find the same time periods between locations. Locations at the same time are compared; if the overlap rate is greater than a set threshold, the accounts are determined to be the same.

[0109] S400 The privacy computing center receives a driver working time query request and sends a driver working time calculation request for a specific time period to several privacy computing access terminals; after receiving the time calculation request initiated by the privacy computing center, the privacy computing access terminal forms calculation steps and sends them to the time series database, and reads the calculation results from the time series database; the time series database, based on the calculation steps sent by the privacy computing access terminal, reads the corresponding data and performs the calculation; the privacy computing access terminal sends the calculation results to the privacy computing center.

[0110] The privacy computing center terminal described in S500, based on the calculation results sent by each privacy computing access terminal, accumulates the working hours of the same account on different ride-hailing platforms to obtain the total working hours of the driver within a specific time period.

[0111] Provide an electronic device, combined with Figure 3 It includes a processor and a memory, the memory being used to store program instructions, and the processor being used to call the program instructions to execute the method for calculating the total driving time of ride-hailing drivers based on multi-account recognition.

[0112] The memory can be read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory can store programs, and when the program stored in the memory is executed by the processor, the processor executes the various steps of the image processing method of this application embodiment. For example, it can execute... Figure 1 The illustrated embodiment is a method for distributed privacy computing.

[0113] The processor may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, used to execute relevant programs to implement the image processing method of the embodiments of this application.

[0114] The processor can also be an integrated circuit chip with signal processing capabilities. In implementation, each step of the image processing method in this application embodiment can be completed by integrated logic circuits in the processor's hardware or by software instructions.

[0115] The aforementioned processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0116] The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads information from the memory and, in conjunction with its hardware, completes the functions required by the units included in the image processing apparatus in the embodiments of this application, or, the image processing method of the method embodiments of this application can be executed... Figure 1 The illustrated embodiment describes a method for calculating the privacy of a ride-hailing driver's total driving time.

[0117] Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the aforementioned method for calculating the total driving time of ride-hailing drivers based on multi-account identification.

[0118] Computer-readable storage media may include, for example, a memory card for a smartphone, a storage component for a tablet computer, a hard disk for a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB storage device, or any combination of the above storage media. A computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0119] In summary, this invention provides a system and method for calculating the total driving time of ride-hailing drivers based on multi-account identification. It identifies driver accounts with the same ID card number or mobile phone number across different ride-hailing platforms as the same account. For accounts with different ID card numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time to determine if they are the same account. The system receives driver working time query requests and sends driver working time calculation requests for a specific time period to several privacy computing access terminals. It then generates calculation steps and sends them to a time-series database. Based on the calculation results from the time-series database sent by each privacy computing access terminal, it sums the working times of the same account across different ride-hailing platforms to obtain the driver's total working time within the specific time period. This invention achieves cross-platform identification of multiple accounts for ride-hailing drivers, accurately calculates the driver's total driving time, and protects privacy data and the trade secrets of ride-hailing companies through privacy computing.

[0120] It should be understood that the specific embodiments described above are merely illustrative or explanatory of the principles of the invention and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of the invention should be included within the protection scope of the invention. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. A system for calculating the total driving time of ride-hailing drivers based on multi-account recognition, characterized in that, This includes a privacy-preserving computing center and several distributed computing endpoints; The computing terminal includes a time-series database and a privacy computing access terminal; The time-series database synchronizes in real time the platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platform. Based on the calculation steps sent by the privacy computing access terminal, read the corresponding data and perform calculations; After receiving a request to identify driver accounts initiated by the privacy computing center, the privacy computing access terminal reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center; after receiving a time calculation request initiated by the privacy computing center, it forms calculation steps and sends them to the time-series database, reads the calculation results from the time-series database, and sends the calculation results to the privacy computing center. The privacy computing center identifies driver accounts with the same ID number or mobile phone number on different ride-hailing platforms as the same account; for accounts with different ID numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if similar, it identifies them as the same account; it receives driver work time query requests and sends driver work time calculation requests for a specific time period to several privacy computing access terminals; based on the calculation results sent by each privacy computing access terminal, it adds up the work time of the same account on different ride-hailing platforms to obtain the total work time of the driver within the specific time period. The privacy computing access terminal receives account behavior data of each account from the time-series database and converts it into intermediate data for transmission to the privacy computing center. The privacy computing center receives intermediate data from at least one privacy computing access point and reconstructs it into account behavior data. It then performs similarity analysis on the account behavior data of different accounts, classifying different accounts with similarity thresholds as the same account. Includes at least one of the following steps: The similarity analysis of the logout time of the first account and the login time of the second account is performed. If the similarity of the handover time of the first account and the second account meets the sixth similarity threshold, the first account and the second account are considered to be the same account. The similarity analysis is performed between the logout location of the first account and the login location of the second account. If the similarity of the intersection point of the first account and the second account meets the seventh similarity threshold, the first account and the second account are considered to be the same account.

2. The system for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 1, characterized in that, The time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate movement trajectories, thus forming the account behavior data.

3. The system for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 2, characterized in that, The privacy computing center extracts the account's login time, logout time, login location, logout location, and movement trajectory from the account behavior data; The method of performing similarity analysis on account behavior data of different accounts to classify different accounts with similarity thresholds as the same account also includes at least one of the following steps: A similarity analysis is performed between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the login locations of the first account and the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the exit locations of the first account and the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, the first account and the second account are considered to be the same account. The similarity analysis of the movement trajectory of the first account and the movement trajectory of the second account is performed. If the similarity of the movement trajectories of the first account and the second account meets the fifth similarity threshold, the first account and the second account are regarded as the same account.

4. The system for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 3, characterized in that, The first account and the second account are accounts with at least one different ID card number or mobile phone number on the same platform, or the first account and the second account are accounts with at least one different ID card number or mobile phone number on different platforms.

5. The system for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 1, characterized in that, The calculation of the time-series database includes at least the following steps: obtaining the driver's corresponding number from the calculation steps, reading the start time and end time of each dispatch within a specific time period corresponding to the number, and calculating the working time of each dispatch. The working hours obtained from different dispatch and driving data are summed up to obtain the driver's total working hours within a specific time period.

6. A method for calculating the total driving time of ride-hailing drivers based on multi-account recognition, characterized in that, include: The time-series database synchronizes platform usage data, driver dispatch data, and driver driving data of the corresponding ride-hailing platforms in real time. The privacy computing center initiates a request to identify the driver's account and sends it to each privacy computing access point. After receiving the request to identify the driver's account, the privacy computing access terminal reads the movement trajectory of each driver over a period of time from the time-series database and sends it to the privacy computing center. The privacy computing center identifies driver accounts with the same ID number or the same mobile phone number on different ride-hailing platforms as the same account; for accounts with different ID numbers and mobile phone numbers, it performs similarity analysis based on movement trajectories over a period of time, and if they are similar, it identifies them as the same account. The privacy computing center receives driver work time query requests and sends driver work time calculation requests for a specific time period to several privacy computing access terminals. After receiving a time calculation request initiated by the privacy computing center, the privacy computing access terminal forms calculation steps and sends them to the time series database, and reads the calculation results from the time series database; the time series database, based on the calculation steps sent by the privacy computing access terminal, reads the corresponding data and performs calculations. The privacy computing access terminal sends the computing result to the privacy computing center terminal; The privacy computing center, based on the calculation results sent by each privacy computing access terminal, accumulates the working hours of the same account on different ride-hailing platforms to obtain the total working hours of the driver within a specific time period. The privacy computing access terminal receives account behavior data of each account from the time-series database and converts it into intermediate data for transmission to the privacy computing center. The privacy computing center receives intermediate data from at least one privacy computing access point and reconstructs it into account behavior data. This data is then used to perform similarity analysis on the account behavior data of different accounts, classifying different accounts with similarity thresholds as the same account. Includes at least one of the following steps: The similarity analysis of the logout time of the first account and the login time of the second account is performed. If the similarity of the handover time of the first account and the second account meets the sixth similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the logout location of the first account and the login location of the second account. If the similarity of the intersection point of the first account and the second account meets the seventh similarity threshold, the first account and the second account are considered to be the same account.

7. The method for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 6, characterized in that, The time-series database calculates the account's daily login time, logout time, login location, and logout location on the platform, and obtains real-time location information from driver driving data to generate movement trajectories, thus forming the account behavior data.

8. The method for calculating the total driving time of ride-hailing drivers based on multi-account recognition according to claim 7, characterized in that, The privacy computing center extracts the account's login time, logout time, login location, logout location, and movement trajectory from the account behavior data; The method of performing similarity analysis on account behavior data of different accounts to classify different accounts with similarity thresholds as the same account also includes at least one of the following steps: A similarity analysis is performed between the login time of the first account and the login time of the second account. If the similarity between the login times of the first account and the second account meets the first similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the exit time of the first account and the exit time of the second account. If the similarity between the exit times of the first account and the second account meets the second similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the login locations of the first account and the second account. If the similarity between the login locations of the first account and the second account meets the third similarity threshold, the first account and the second account are considered to be the same account. A similarity analysis is performed between the exit locations of the first account and the second account. If the similarity between the exit locations of the first account and the second account meets the fourth similarity threshold, the first account and the second account are considered to be the same account. The similarity analysis of the movement trajectory of the first account and the movement trajectory of the second account is performed. If the similarity of the movement trajectories of the first account and the second account meets the fifth similarity threshold, the first account and the second account are regarded as the same account.

9. An electronic device, comprising a processor and a memory, the memory for storing program instructions, the processor for invoking the program instructions to execute the method for calculating the total driving time of a ride-hailing driver based on multi-account identification as described in any one of claims 6-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for calculating the total driving time of ride-hailing drivers based on multi-account recognition as described in any one of claims 6-8.

Images