Scheduling method and system for online car-hailing motorcade, electronic equipment and medium

Abstract

The invention provides an online car-hailing fleet scheduling method and system, an electronic device and a medium, and the method comprises the steps: obtaining image information in a first region and image information in a second region through constructing a driver driving behavior action database and a passenger behavior action database according to a vehicle-mounted camera; and collecting driver action images in the first area and passenger action images and face images in the second area, determining the number of travel passengers, and judging whether passenger behaviors are abnormal or not based on a passenger behavior action data model, the standard of the driving behavior of the driver in the first area is judged based on the driver driving behavior action data model, whether the passenger behavior is abnormal or not is judged based on the passenger behavior action data model, the binding relation between the digital virtual key and the vehicle to which the digital virtual key belongs is established, and the user permission function is set; and sending an alarm to the platform, and sending an early warning notification to the user terminal.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and specifically relates to a dispatching method, system, electronic equipment and medium for an online car-hailing fleet. Background Art

[0002] The current dispatch method for online ride-hailing fleets on the market is mainly based on factors such as order volume. It has a low level of intelligence and is unable to monitor the driver's driving behavior and the passenger's riding behavior in real time. When the driver's driving behavior or the passenger's behavior is abnormal, it is impossible to notify the application platform in time for dispatch, resulting in low passenger satisfaction and easily causing accidents that cannot be handled in a timely manner. Summary of the invention

[0003] In order to overcome the shortcomings of the prior art, the present invention provides a dispatching method, system, electronic device and medium for an online car-hailing fleet, so as to solve the problem in the prior art that the online car-hailing fleet dispatching cannot monitor the abnormal behaviors of drivers and passengers in real time.

[0004] One embodiment of the present invention provides a method for dispatching a fleet of online ride-hailing vehicles, comprising the following steps:

[0005] Create a binding relationship between the digital virtual key and the vehicle to which it belongs, set up the driver's authority function, integrate the digital virtual key with the vehicle rental system, and collect and store vehicle rental period information;

[0006] The image information in the first area is obtained according to the on-board camera, and the first area includes the driver. The action images of the driver in the first area are collected and uploaded to a preset action database. The standardization of the driving behavior of the driver in the first area is judged based on the driver action data model that has been pre-trained for the driver's driving behavior. The driving behavior information data of the driver is received and stored in the cloud. The image information in the second area is obtained according to the on-board camera, and the passenger action images and face images in the second area are collected and uploaded to the preset action database. Based on the preset passenger behavior action data model, the number of traveling passengers is determined, and whether the passenger behavior is abnormal is judged. The passenger behavior action information data is received and stored in the cloud. The data is compared with the preset action data model. When an abnormal situation occurs, an alarm is issued to the platform, and an early warning notification is sent to the user terminal. The platform constructs a scheduling model through alarm analysis, and formulates a scheduling strategy according to the scheduling model.

[0007] Furthermore, it also includes a preset action database construction process: according to the on-board camera, collecting the driver's standard driving behavior video in the first area, and evenly extracting image frames from the video, marking the driver's shoulder angle coordinate points and hand position coordinate points; uploading the marked image frames in the first area to the driver's driving behavior action database and storing them; according to the on-board camera, collecting abnormal passenger behavior data in the second area, including passenger behavior action image information and face images, evenly extracting image frames from the video, marking the passenger's head coordinate position and joint angle position; uploading the marked image frames to the passenger behavior action database and storing them.

[0008] Furthermore, the driver action data model construction process includes: preprocessing the image frame data stored in the driver's driving behavior action database, and extracting a first feature vector set in the processed data center; based on the first feature vector set, constructing a deep learning model for action recognition; real-time monitoring of the driver's driving behavior, and outputting real-time feedback based on the driver's driving behavior recognition model.

[0009] Furthermore, the process of constructing the preset passenger behavior action data model includes: preprocessing the image frame data stored in the passenger behavior action database, and extracting a second feature vector set in the processed data center; based on the second feature vector set, using the passenger behavior action database, and adopting an action recognition method based on time series analysis to establish a passenger behavior action recognition model; real-time monitoring of passenger behavior actions, and outputting real-time feedback based on the passenger behavior action recognition model.

[0010] Furthermore, the digital virtual key includes an API interface, a digital key management module and a digital key control module. The digital virtual key is connected to the online car-hailing control platform and the vehicle user terminal through the API interface, and user permissions are set according to the user information issued by the digital key management module.

[0011] Furthermore, a training sample set is obtained, which includes a driving behavior information data sample set and a passenger behavior action information data sample set; a random forest model is established, and the random forest model is trained according to the training set to adjust the model; and the scheduling strategy is formulated according to the adjusted model results.

[0012] The present invention also includes a dispatching system for an online car-hailing fleet, comprising the following modules: a digital virtual key module: creating a binding relationship between a digital virtual key and the vehicle to which it belongs, establishing the authority function of the driver, the digital virtual key and the vehicle rental system are integrated, and the vehicle rental period information is collected and stored; a first control module: obtaining image information in a first area according to a vehicle-mounted camera, the first area including the driver, collecting the driver's action image in the first area and uploading it to a preset action database, judging the standardization of the driver's driving behavior in the first area based on a driver's action data model pre-trained for the driver's driving behavior, and receiving and storing the driver's driving behavior information data in the cloud; a second control module: obtaining image information in a second area according to a vehicle-mounted camera, collecting passenger action images and face images in the second area, and uploading them to the preset action database, determining the number of traveling passengers based on the preset passenger behavior action data model, judging whether the passenger behavior is abnormal, and receiving and storing the passenger's behavior action information data in the cloud; an early warning module: comparing with the preset action data model, when an abnormal situation occurs, issuing an alarm to the platform, and sending an early warning notification to the user terminal, the platform constructs a dispatching model through alarm analysis, and formulates a dispatching strategy according to the dispatching model.

[0013] Furthermore, the first control module collects standard driving behavior video of the driver in the first area according to the on-board camera, and evenly extracts image frames from the video, marks the driver's shoulder angle coordinate points and the driver's hand position coordinate points, and uploads the marked image frames to the driver's driving behavior action database for storage; collects abnormal passenger behavior data in the second area according to the on-board camera, including passenger behavior action image information and passenger audio information, evenly extracts image frames from the video, marks the passenger's head coordinate position and joint angle position, and uploads the marked image frames to the passenger behavior action database for storage.

[0014] Furthermore, the warning module includes a modeling unit, a warning unit and a transmission unit; the modeling unit obtains a training sample set according to the first control module and the second control module, and the training sample set includes a driving behavior information data sample set and a passenger behavior action information data sample set; establishes a random forest model, trains the random forest model according to the training set, and adjusts the model; formulates the scheduling strategy according to the optimized model results.

[0015] The dispatch model construction process needs to interpret the important features and decision paths output by the random forest model, understand which driving behaviors and passenger actions have a significant impact on dispatch decisions, and formulate specific dispatch strategies based on the model results. For example, if the model finds that sudden movements of passengers are associated with an increased risk of traffic accidents, it can automatically adjust the vehicle speed or issue a warning when such behavior is detected, integrate the dispatch strategy into the vehicle control system, and continuously monitor its effects, and adjust and optimize as needed.

[0016] The present invention also includes an electronic device, including one or more processors; a storage device, on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement a method for dispatching an online car-hailing fleet.

[0017] The present invention also includes a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in a method for dispatching an online car-hailing fleet is implemented.

[0018] The above embodiments provide a method, system, electronic device and medium for dispatching an online car-hailing fleet, which have the following beneficial effects:

[0019] 1. By centralizing the driving information of online car-hailing fleet drivers through the platform, the constraints on online car-hailing drivers and the ability to integrate information can be improved.

[0020] 2. Use digital virtual keys to achieve the elimination of physical keys and key authorization while effectively controlling vehicle dispatch and maintenance;

[0021] 3. Through deep learning, a behavior recognition model is built based on the training set to accurately evaluate the behavioral habits of car drivers and determine whether the passenger behavior is abnormal, and then upload it to the cloud for effective risk control.

[0022] 4. Through the early warning unit, the platform collects the alarm conditions of problem vehicles in real time and dispatches them in a timely manner, effectively improving the dispatch efficiency of the online car-hailing fleet and improving the convenience of passenger travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0024] Figure 1 A working step diagram of a method for dispatching online car-hailing vehicles provided in the first embodiment of the present invention;

[0025] Figure 2 A diagram showing the steps for constructing a preset action database in the first embodiment of the present invention;

[0026] Figure 3 A block diagram of an online car-hailing dispatching system provided for the second embodiment of the present invention;

[0027] Figure 4 A schematic diagram of the hardware structure of an online car-hailing fleet dispatching device provided in one embodiment of the present application of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0030] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of the features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0031] One of the embodiments of the present invention provides a dispatching method for an online car-hailing fleet, comprising the following steps: creating a binding relationship between a digital virtual key and the vehicle to which it belongs, establishing the driver's authority function, integrating the digital virtual key with a vehicle rental system, and collecting and storing vehicle rental period information; acquiring image information in a first area according to a vehicle-mounted camera, the first area including the driver, collecting the driver's action image in the first area and uploading it to a preset action database, judging the standardization of the driver's driving behavior in the first area based on a driver's action data model pre-trained for the driver's driving behavior, and receiving and storing the driver's driving behavior information data in the cloud; acquiring image information in a second area according to the vehicle-mounted camera, collecting passenger action images and face images in the second area, and uploading them to the preset action database, determining the number of traveling passengers based on the preset passenger behavior action data model, judging whether the passenger behavior is abnormal, and receiving and storing the passenger's behavior action information data in the cloud; comparing with the preset action data model, and when an abnormal situation occurs, issuing an alarm to the platform, and sending an early warning notification to the user terminal, the platform constructs a dispatching model through alarm analysis, and formulates a dispatching strategy based on the dispatching model.

[0032] Furthermore, it also includes a preset action database construction process: according to the on-board camera, collecting the driver's standard driving behavior video in the first area, and evenly extracting image frames from the video, marking the driver's shoulder angle coordinate points and hand position coordinate points; uploading the marked image frames in the first area to the driver's driving behavior action database and storing them; according to the on-board camera, collecting abnormal passenger behavior data in the second area, including passenger behavior action image information and face images, evenly extracting image frames from the video, marking the passenger's head coordinate position and joint angle position; uploading the marked image frames to the passenger behavior action database and storing them.

[0033] In an embodiment, the first area includes the cab position, and the coordinate points of the driver's shoulder angle and the driver's hands position are collected and marked. Generally, the driver's shoulders should be kept horizontal when driving. If the shoulders are tilted, whether the driver is fatigued driving is identified based on whether the shoulder angle inclination exceeds the shoulder angle inclination value in normal driving posture.

[0034] Furthermore, the driver action data model construction process includes: preprocessing the image frame data stored in the driver's driving behavior action database, and extracting a first feature vector set in the processed data center; based on the first feature vector set, constructing a deep learning model for action recognition; real-time monitoring of the driver's driving behavior, and outputting real-time feedback based on the driver's driving behavior recognition model.

[0035] When taking an online ride-hailing car, the passenger's behavior is also a criterion for judging whether vehicle dispatch is required. In some cases, the passenger's special behavior will affect the driver's driving safety, such as grabbing the steering wheel, interfering with the driver's vision or operation, and other abnormal behaviors. When an abnormal situation is identified, it will be handled in a timely manner through the early warning notification platform.

[0036] Furthermore, based on the extracted feature vectors, a deep learning model that can accurately identify driving behavior is trained, and a suitable deep learning model architecture is selected according to the task requirements. In some embodiments, the deep learning model includes a CNN model, and the architecture of the model is designed, including an input layer, a hidden layer (and an output layer; the model is trained using a labeled data set. During the training process, the performance of the model is optimized by adjusting hyperparameters (such as learning rate, batch size, number of iterations, etc.) and optimization algorithms (such as SGD, Adam, etc.), and the accuracy, recall rate, F1 score and other indicators of the model are evaluated using a validation set or a test set to ensure that the model has good performance.

[0037] The process of constructing the preset passenger behavior action data model includes: preprocessing the image frame data stored in the passenger behavior action database, and extracting a second feature vector set in the processed data center; based on the second feature vector set, using the passenger behavior action database, and adopting an action recognition method based on time series analysis to establish a passenger behavior action recognition model; real-time monitoring of passenger behavior actions, and outputting real-time feedback according to the passenger behavior action recognition model.

[0038] Furthermore, based on the extracted feature vectors, the passenger behavior action database is used to establish a model using the action recognition method of time series analysis. The time series analysis method is selected: Since passenger behavior actions are usually time-series (that is, the actions change continuously over time), models suitable for processing time series data such as RNN, LSTM or GRU can be used. Design a model architecture that includes a feature input layer, a time series processing layer (such as an LSTM layer), a fully connected layer, and an output layer. Use the labeled data in the passenger behavior action database to train the model. During the training process, the feature vector sequence is used as input, and the corresponding passenger behavior action label is used as output. Optimize the performance of the model by adjusting the model parameters and optimization algorithms. Use the validation set or test set to evaluate the model's accuracy, recall rate, F1 score and other indicators to ensure that the model can accurately identify various passenger behaviors.

[0039] Furthermore, the digital virtual key includes an API interface, a digital key management module and a digital key control module. The digital virtual key is connected to the online car-hailing control platform and the vehicle user terminal through the API interface, and user permissions are set according to the user information issued by the digital key management module.

[0040] The API interface is a bridge for the digital virtual key to communicate with external systems (such as the online car-hailing control platform and the user terminal of the vehicle). Through the API interface, the digital virtual key can receive and send instructions to achieve signal connection and data exchange with the online car-hailing control platform and the user terminal. The digital key management module is responsible for the storage and management of user information, including the driver's identity information, permission settings, etc. Through the digital key management module, the administrator can flexibly set and modify user permissions to ensure that only authorized users can use the digital virtual key to control the vehicle. The digital key control module is the core part of the digital virtual key. It is responsible for receiving instructions from the online car-hailing control platform or user terminal, and controlling the vehicle to perform corresponding operations (such as unlocking, starting, shutting down, etc.). It interacts with the control system inside the vehicle through wireless communication technology to realize the function of remotely controlling the vehicle.

[0041] In some embodiments, the digital virtual key manages the vehicle and the driver by establishing a mobile device terminal app. In this embodiment, the rental system is integrated and managed. The car rental company provides a one-stop service through the digital virtual key App. Customers can book vehicles online and obtain the digital key of the vehicle through the App. They can go directly to the designated location to unlock and pick up the car without going to the physical store to handle the formalities. The car rental company can flexibly set the rental period in the App according to customer needs, including hourly, daily or weekly billing, to provide customers with more personalized car rental solutions. When the rental period is about to end, the App will automatically send a reminder notification to the customer to ensure that the customer returns the car on time. At the same time, the App also supports online settlement functions, and customers can quickly complete the payment of the rental fee through the bound payment account. The car rental company can also monitor the vehicle's location, fuel level, battery power and other status information in real time through the digital virtual key system to ensure the safety and normal operation of the vehicle.

[0042] Furthermore, a training sample set is obtained, which includes a driving behavior information data sample set and a passenger behavior action information data sample set; a random forest model is established, and the random forest model is trained according to the training set to adjust the model; and the scheduling strategy is formulated according to the adjusted model results.

[0043] Embodiment 2

[0044] The present invention also includes an embodiment, a dispatching system for an online car-hailing fleet, comprising the following modules: a database module: constructing a driver's driving behavior action database and a passenger behavior action database; a first control module: acquiring image information in a first area according to a vehicle-mounted camera, collecting driver action images in the first area, judging the standardization of the driver's driving behavior in the first area based on a driver's driving behavior action data model, and receiving and storing the driver's driving behavior information data in the cloud; a second control module: acquiring image information in a second area according to a vehicle-mounted camera, collecting passenger action images and face images in the second area, determining the number of traveling passengers, judging whether the passenger behavior is abnormal based on the passenger behavior action data model, and receiving and storing the passenger's behavior action information data in the cloud; a digital virtual key module: creating a binding relationship between a digital virtual key and the vehicle to which it belongs, and establishing a user authority function; an early warning module: when an abnormal situation occurs, an alarm is issued to the platform, and an early warning notification is sent to the user terminal. The platform constructs a dispatching model through alarm analysis, and formulates a dispatching strategy based on the dispatching model.

[0045] Furthermore, the first control module collects standard driving behavior video of the driver in the first area according to the on-board camera, and evenly extracts image frames from the video, marks the driver's shoulder angle coordinate points and the driver's hand position coordinate points, and uploads the marked image frames to the driver's driving behavior action database for storage; collects abnormal passenger behavior data in the second area according to the on-board camera, including passenger behavior action image information and passenger audio information, evenly extracts image frames from the video, marks the passenger's head coordinate position and joint angle position, and uploads the marked image frames to the passenger behavior action database for storage.

[0046] The early warning module transmits the early warning notification to the user's mobile terminal and the vehicle rental company through network transmission. The rental company evaluates and determines the specific situation of the current vehicle based on the early warning information, and makes timely scheduling arrangements. The user's mobile terminal includes the driver's mobile terminal and the passenger's application platform information reception. Once an abnormal situation occurs, the alarm is synchronized to the two receiving terminals. If the rental company cannot arrange the timely dispatch of the abnormal vehicle in time, the passenger will make a judgment and deal with it in time based on the early warning information sent by the application platform.

[0047] The present invention also includes an electronic device, including one or more processors; a storage device, on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement a method for dispatching an online car-hailing fleet.

[0048] The present invention also includes a computer-readable medium storing a computer program, wherein when the computer program is executed by a processor, the method described in a method for dispatching an online car-hailing fleet is implemented.

[0049] In the embodiment provided by the present invention, the driving information of the drivers of the online car-hailing fleet is centralized by the platform, so as to improve the restraint and information integration capabilities on the drivers of the online car-hailing fleet, use digital virtual keys to achieve physical key removal and key authorization, and effectively manage vehicle scheduling and vehicle maintenance. Through deep learning, a behavior recognition model is constructed according to the training set to accurately evaluate the behavioral habits of the drivers and determine whether the passenger behavior is abnormal, and upload it to the cloud for effective risk control. Through the early warning unit, the platform collects the alarm conditions of problem vehicles in real time and dispatches them in time, effectively improving the scheduling efficiency of the online car-hailing fleet and improving the convenience of passenger travel.

[0050] refer to Figure 4 , Figure 4 A schematic diagram of the hardware structure of an online car-hailing dispatching device provided in one embodiment of the present application.

[0051] The device 5 includes a processor 51, a memory 54, an input device 52, and an output device 53. The processor 51, the memory 54, the input device 52, and the output device 53 are coupled via a connector, and the connector includes various interfaces, transmission lines, or buses, etc., which are not limited in the embodiments of the present application. It should be understood that in various embodiments of the present application, coupling refers to mutual connection in a specific manner, including direct connection or indirect connection through other devices, for example, through various interfaces, transmission lines, buses, etc.

[0052] The processor 51 may be one or more graphics processing units (GPUs). When the processor 51 is a GPU, the GPU may be a single-core GPU or a multi-core GPU. Optionally, the processor 51 may be a processor group consisting of multiple GPUs, and the multiple processors are coupled to each other via one or more buses. Optionally, the processor may also be other types of processors, etc., which are not limited in the embodiments of the present application.

[0053] The memory 54 can be used to store computer program instructions and various computer program codes including the program code for executing the program code of the present application. Optionally, the memory includes but is not limited to random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read only memory (CD-ROM), which is used for related instructions and data.

[0054] The input device 52 is used to input data and / or signals, and the output device 53 is used to output data and / or signals. The output device 53 and the input device 22 may be independent devices or an integrated device.

[0055] It is understandable that in the embodiment of the present application, the memory 54 can not only be used to store related instructions, and the embodiment of the present application does not limit the specific data stored in the memory.

[0056] Understandably, Figure 4 Only a simplified design of the device of the online car-hailing dispatching method is shown. In practical applications, the device may also include other necessary components, including but not limited to any number of input / output devices, processors, memories, etc., and all devices that can implement the embodiments of the present application are within the scope of protection of the present application.

[0057] In a third aspect, the present application provides a terminal, comprising a touch screen, a memory, a transceiver, one or more processors, multiple applications, and one or more programs; wherein the one or more programs are stored in the memory, and the transceiver is used to transmit or receive wireless signals; when the one or more processors execute the one or more programs, the terminal implements the case analysis method as described above.

[0058] In a fourth aspect, the present application provides a server, comprising a memory, a transceiver, one or more processors, multiple applications, and one or more programs; wherein the one or more programs are stored in the memory, and the transceiver is used to transmit or receive wireless signals; when the one or more processors execute the one or more programs, the server implements the case analysis method as described above.

[0059] In a fifth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the case analysis method as described above.

[0060] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0061] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present application have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0062] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0063] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or 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.

[0064] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0065] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0066] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.

Claims

1. A method for dispatching a fleet of online ride-hailing vehicles. It is characterized in that The following steps are involved: Create a binding relationship between the digital virtual key and the vehicle to which it belongs, set up the driver's authority function, integrate the digital virtual key with the vehicle rental system, and collect and store vehicle rental period information; Acquire image information in a first area according to the vehicle-mounted camera, the first area includes a driver, collect action images of the driver in the first area and upload them to a preset action database, judge the standard of the driving behavior of the driver in the first area based on a pre-trained driver action data model of the driver's driving behavior, and receive and store the driving behavior information data of the driver in the cloud; Acquire image information in the second area according to the on-board camera, collect passenger action images and face images in the second area, upload them to the preset action database, determine the number of traveling passengers based on the preset passenger action data model, determine whether the passenger behavior is abnormal, and receive and store the passenger action information data in the cloud; The system compares the data with the preset action data model. When an abnormal situation occurs, an alarm is issued to the platform and an early warning notification is sent to the user terminal. The platform analyzes the alarm, builds a scheduling model, and formulates a scheduling strategy based on the scheduling model.

2. A method for dispatching a fleet of online car-hailing vehicles as claimed in claim 1, It is characterized in that It also includes the preset action database construction process: According to the vehicle-mounted camera, a standard driving behavior video of the driver in the first area is collected, and image frames are evenly extracted from the video, and the coordinate points of the driver's shoulder angle and the coordinate points of the hands position are marked; Uploading the marked image frames in the first area to the preset action database and storing them; According to the on-board camera, the abnormal behavior data of passengers in the second area are collected, including passenger behavior action image information and face images, image frames are evenly extracted from the video, and the coordinate position of the passenger's head and the angle position of the joints are annotated; The image frames marked in the second area are uploaded to the preset action database and stored.

3. A method for dispatching a network-hailing vehicle fleet as claimed in claim 1, It is characterized in that The driver action data model construction process includes: Preprocessing the data stored in the driver's driving behavior action database, and extracting a first feature vector set from the processed data; Constructing a deep learning model for action recognition based on the first feature vector set; Monitor the driver's driving behavior in real time and output real-time feedback based on the driver's driving behavior recognition model.

4. A method for dispatching a fleet of online car-hailing vehicles as claimed in claim 1, It is characterized in that The process of constructing the preset passenger behavior action data model includes: Preprocessing the image frame data stored in the passenger behavior action database, and extracting a second feature vector set from the processed data; According to the second feature vector set, using the passenger behavior action database, a passenger behavior action recognition model is established by adopting an action recognition method based on time series analysis; Monitor passenger behavior in real time and output real-time feedback based on the passenger behavior recognition model.

5. A method for dispatching a network-hailing vehicle fleet as claimed in claim 1, It is characterized in that The digital virtual key includes an API interface, a digital key management module and a digital key control module. The digital virtual key is connected to the online car-hailing control platform and the vehicle user terminal through the API interface, and user permissions are set according to the user information issued by the digital key management module.

6. A method for dispatching a network-hailing vehicle fleet as claimed in claim 1, It is characterized in that The construction of the scheduling model comprises the following steps: Acquire a training sample set, the training sample set including a driving behavior information data sample set and a passenger behavior action information data sample set; Establishing a random forest model, training the random forest model according to the training set, and adjusting the model; According to the adjusted model results, the scheduling strategy is formulated.

7. A dispatching system for online car-hailing fleets, It is characterized in that Includes the following modules: Digital virtual key module: creates a binding relationship between the digital virtual key and the vehicle to which it belongs, establishes the driver's authority function, and integrates the digital virtual key with the vehicle rental system to collect and store vehicle rental period information; The first control module is configured to obtain image information in a first area according to the vehicle-mounted camera, the first area includes the driver, collect action images of the driver in the first area and upload them to a preset action database, judge the standard of the driving behavior of the driver in the first area based on a pre-trained driver action data model of the driver's driving behavior, and receive and store the driving behavior information data of the driver in the cloud; The second control module is used to obtain image information in the second area according to the vehicle-mounted camera, collect passenger action images and face images in the second area, upload them to the preset action database, determine the number of traveling passengers based on the preset passenger action data model, determine whether the passenger behavior is abnormal, and receive and store the passenger action information data in the cloud; Early warning module: compares with the preset action data model. When an abnormal situation occurs, an alarm is issued to the platform and an early warning notification is sent to the user terminal. The platform analyzes the alarm, builds a scheduling model, and formulates a scheduling strategy based on the scheduling model.

8. A dispatching system for an online car-hailing fleet as claimed in claim 7, It is characterized in that The first control module collects a standard driving behavior video of a driver in a first area according to a vehicle-mounted camera, evenly extracts image frames from the video, marks the coordinate points of the driver's shoulder angle and the coordinate points of the driver's hands, and uploads the marked image frames to the driver's driving behavior action database for storage; According to the on-board camera, the abnormal behavior data of passengers in the second area are collected, including passenger behavior and action image information and passenger audio information, image frames are evenly extracted from the video, the passenger head coordinate position and joint angle position are annotated, and the annotated image frames are uploaded to the passenger behavior and action database and stored.

9. A dispatching system for an online car-hailing fleet as claimed in claim 7, It is characterized in that The early warning module includes a modeling unit, an early warning unit and a transmission unit The modeling unit obtains a training sample set according to the first control module and the second control module, the training sample set including a driving behavior information data sample set and a passenger behavior action information data sample set; establishes a random forest model, trains the random forest model according to the training set, and adjusts the model; According to the optimized model results, the scheduling strategy is formulated.

10. An electronic device, It is characterized in that one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

Images