Management and control method and device based on multi-dimensional task

Abstract

The invention relates to the technical field of task processing, and discloses a management and control method and device based on a multi-dimensional task, and the method comprises the steps: obtaining target task information; wherein the target task information comprises any one of certificate processing task information, driving identification task information and road test task information; determining a task processing result corresponding to the target task information according to the target task information; and determining a task solution corresponding to the task processing result according to the task processing result.

Description

Technical Field

[0001] The present invention relates to the field of task processing technology, and in particular to a management and control method and device based on multi-dimensional tasks. Background Art

[0002] Currently, online ride-hailing platforms rely primarily on manual management to notify and review users, which is reflected in the following aspects:

[0003] User Notice: For new drivers, especially novice drivers, the platform typically organizes offline training or provides online documentation to help them familiarize themselves with platform rules, service processes, and safety regulations. Route simulation exams, a crucial step in assessing a driver's driving ability and route familiarity, have traditionally been conducted through centralized offline exams or simple online documentation.

[0004] User Verification: Before a driver leaves the vehicle, the platform must conduct a rigorous review of vehicle information (such as model, condition, and license plate number) and driver identity (such as driver's license and ID card) to ensure the legality and compliance of the service. This process often relies on manual verification of images, which is inefficient and prone to errors.

[0005] However, manual notification and review tasks are time-consuming and inefficient, making it difficult to meet the needs of online ride-hailing platforms for rapid response and efficient operation. Summary of the Invention

[0006] In view of this, the present invention provides a multi-dimensional task-based management and control method and device.

[0007] In a first aspect, the present invention provides a management and control method based on multi-dimensional tasks, the method comprising: obtaining target task information; wherein the target task information comprises: any one of document processing task information, driving recognition task information and road test task information; according to the target task information, determining the task processing result corresponding to the target task information; according to the task processing result, determining the task solution measures corresponding to the task processing result.

[0008] The multi-dimensional task-based management and control method provided in this embodiment can determine the task processing results corresponding to different target task information without manual review or notification, thereby improving processing efficiency and meeting the needs of online car-hailing platforms for rapid response and efficient operation.

[0009] In one possible implementation, the target task information includes document processing task information, and the task processing result corresponding to the target task information is determined based on the target task information, including: determining the image data uploaded by the user based on the target task information; identifying the image data to determine the text information corresponding to the image data; determining the target key information from the text information, wherein the target key information includes at least one of: name, document number, document validity period, and permitted vehicle type; comparing the target key information with the historical association information stored in a preset database to determine the task processing result corresponding to the target task information, wherein the task processing result indicates whether the target key information and the historical association information are consistent.

[0010] The multi-dimensional task-based management and control method provided in this embodiment eliminates the need for manual operations, from determining image data to identifying text information, and then extracting and comparing key information. For example, when processing the registration information of a large number of online ride-hailing drivers, the ID photos uploaded by each driver can be quickly processed, greatly reducing processing time and improving work efficiency.

[0011] In one possible implementation, based on the task processing result, the task solution measures corresponding to the task processing result are determined, including: when the task processing result indicates that the target key information and the historical association information are inconsistent, the task processing result is sent to the user's terminal device so that the user can re-upload new image data; or, the target key information is sent to the management page for display so that the target key information can be manually reviewed.

[0012] This embodiment provides a multi-dimensional task-based management and control method. When task processing results indicate a discrepancy between target key information and historically associated information, users are promptly notified via their terminal devices. This allows users to immediately learn of issues with uploaded image data without having to wait or proactively check the review status, improving the timeliness of information acquisition.

[0013] Furthermore, by sending the target key information to the management page for manual review, the reviewer's expertise and experience can be used to reconfirm the system's automated comparison results. Manual review can identify details or special circumstances that the system might have overlooked, thereby improving review accuracy. For example, in some cases, the system may not accurately recognize a handwritten ID number, but a manual reviewer can make a judgment based on handwriting characteristics and contextual information.

[0014] In one possible implementation, the target task information includes driving identification task information, and the task processing result corresponding to the target task information is determined based on the target task information, including: determining the user's driving behavior data based on the target task information; using a behavior level determination model to obtain a task processing result based on the user's driving behavior data; wherein the task processing result indicates the driving behavior level corresponding to the driving behavior data.

[0015] The multi-dimensional task-based control method provided in this embodiment automatically analyzes driving behavior data using a behavior grading model, eliminating the need for manual intervention and significantly improving processing efficiency. Furthermore, the system can process large amounts of driving data in real time or in batches, quickly generating driving behavior grading results, making it suitable for large-scale online ride-hailing platforms.

[0016] In one possible implementation, based on the task processing result, a task solution measure corresponding to the task processing result is determined, including: when the driving behavior level is greater than the level threshold, determining the training scenario information corresponding to the driving behavior data, wherein the training scenario information includes: at least one of safety knowledge course information and simulated accident drill information; determining the user's training evaluation result for the training scenario information; based on the training evaluation result, generating a training modification suggestion corresponding to the training evaluation result, and sending the training modification suggestion to the user's terminal device.

[0017] The multi-dimensional task-based management and control method provided in this embodiment matches targeted training scenario information according to the driver's specific driving behavior data (such as sudden braking, speeding, fatigue driving, etc.). Compared with the traditional training method in related technologies that uses unified training content for all drivers, this application focuses on the driver's weak links and improves training efficiency.

[0018] In one possible implementation, the target task information includes road test task information, wherein determining, based on the target task information, a task processing result corresponding to the target task information includes: determining, based on the road test task information, road test behavior data of the user, wherein the road test behavior data; obtaining, based on the road test behavior data, a task processing result using a behavior anomaly determination model, wherein the task processing result indicates whether the road test behavior data of the user has an anomaly;

[0019] Based on the task processing results, determine the task solution measures corresponding to the task processing results, including: when there is an abnormality in the user's road test behavior data, determine the type of the user's road test behavior data; based on the type of the user's road test behavior data, determine the task solution measures corresponding to the type of the user's road test behavior data.

[0020] The multi-dimensional task-based control method provided in this embodiment collects road test behavior data (such as speeding, sudden braking, and turn signal use), covering the entire driving process and avoiding the limitations of a single indicator. Furthermore, it utilizes a behavioral anomaly identification model and automatically identifies abnormal behavior through algorithms (such as threshold judgment and cluster analysis), reducing manual misjudgment.

[0021] In one possible implementation, the method further includes: utilizing a behavior score determination model to determine the user's behavior score based on the road test behavior data.

[0022] The multi-dimensional task-based control method provided in this embodiment quantifies scores through multi-dimensional behavioral data (such as the number of speeding times, turn signal usage rate, and sudden braking frequency) to avoid deviations from human subjective judgment.

[0023] In the second aspect, the present invention provides a management and control device based on multi-dimensional tasks, which includes: an acquisition module for acquiring target task information; wherein the target task information includes: any one of document processing task information, driving recognition task information and road test task information; a first determination module for determining the task processing result corresponding to the target task information based on the target task information; and a second determination module for determining the task solution measures corresponding to the task processing result based on the task processing result.

[0024] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the multi-dimensional task-based management and control method of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0025] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the multi-dimensional task-based management and control method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0026] In a fifth aspect, the present invention provides a computer program product comprising computer instructions, which are used to enable a computer to execute the multi-dimensional task-based management and control method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 is a flowchart of a multi-dimensional task-based management and control method according to an embodiment of the present invention;

[0029] Figure 2 is a schematic diagram of a multi-dimensional task-based management and control method according to an embodiment of the present invention;

[0030] Figure 3 is a schematic diagram of another multi-dimensional task-based management and control method according to an embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of another multi-dimensional task-based management and control method according to an embodiment of the present invention;

[0032] Figure 5 is a structural block diagram of a multi-dimensional task-based control device according to an embodiment of the present invention;

[0033] Figure 6 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0035] According to an embodiment of the present invention, an embodiment of a management and control method based on multi-dimensional tasks is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] In this embodiment, a multi-dimensional task-based management and control method is provided, which can be used for computer equipment, such as computers, servers, etc. Figure 1 FIG is a flow chart of a multi-dimensional task-based management and control method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0037] Step S101, obtaining target task information; wherein the target task information includes: any one of: document processing task information, driving recognition task information and road test task information.

[0038] Target task information can indicate the data set associated with a specific task to be processed. Different task types correspond to different information contents. Target task information can include document processing task information, driver recognition task information, and road test task information.

[0039] Document processing tasks can include various documents submitted by drivers, such as driver's licenses, vehicle registration certificates, and online ride-hailing driver qualification certificates, which are needed by online ride-hailing platforms. This information includes details such as the certificate number, validity period, and issuing authority, and is used to verify whether the driver is legally qualified to engage in online ride-hailing services.

[0040] Driving identification task information can be collected through in-vehicle equipment or applications on the driver's mobile phone. Driver behavior data during driving, such as driving speed, braking frequency, number of sharp turns, etc. This data is used to assess the driver's driving habits and safety awareness.

[0041] Road test task information can be for newly joined online ride-hailing drivers. The platform may arrange a simulated road test or an actual road test to record the driver's performance information during the test, such as route planning ability, compliance with traffic rules, ability to deal with emergencies, etc.

[0042] As an example, a user can upload an ID image to an application server (such as an online car-hailing platform), and the target task can be determined as a ID processing task, and the target task information can be ID processing task information (such as image information, text information, etc. on the ID).

[0043] Step S102: determining the task processing result corresponding to the target task information according to the target task information.

[0044] The task processing result can indicate the conclusion obtained after analyzing the target task information, which is used to determine whether the task is completed, qualified, or needs further processing.

[0045] In specific implementations, the acquired target task information can be analyzed and processed using preset rules, algorithms, or neural network models to produce a task-related processing result. The processing result reflects the current status of the task or whether it meets the requirements.

[0046] As an example, a pre-trained behavior level determination model can be used to obtain a task processing result based on the user's driving behavior data.

[0047] As an example, a pre-trained behavior anomaly determination model can be used to obtain task processing results based on road test behavior data.

[0048] In one application scenario, the platform compares and verifies the driver's ID information with data stored in the database to determine whether the ID is authentic and valid, and whether it is within its validity period. The results may be "ID is valid, passed review" or "ID is expired, failed review", etc.

[0049] In one application scenario, the platform uses a grading model to assess a driver's driving risk level based on collected driving behavior data. For example, if a driver frequently brakes suddenly and speeds, the result might be "high-risk driving behavior, training required."

[0050] In one application scenario, the platform scores and evaluates a driver's road test behavior data according to pre-set scoring criteria. The results may be "Pass the road test and be able to work" or "Fail the road test and need to retake the test."

[0051] Step S103: determining a task solution measure corresponding to the task processing result according to the task processing result.

[0052] Based on the results of the task, develop corresponding solutions or action plans to resolve problems encountered during the task or promote the successful completion of the task. The solutions are targeted and feasible.

[0053] For example, if the result is "Document expired, review failed," the solution might be to notify the driver to update their documents promptly and provide instructions and process for updating. If the driver fails to update their documents within a certain period of time, the platform may suspend their ability to accept orders.

[0054] For example, for a "high-risk driving behavior, training required" result, the platform can provide drivers with online driving training courses, requiring them to complete the course and pass the assessment within a specified timeframe. Furthermore, the platform can monitor the driver's driving behavior in real time and provide reminders to help them improve their habits.

[0055] For example, if the driver's result is "failed the road test and needs to retake it," the platform will arrange the time and location for the next road test and provide targeted review materials and coaching. Before the driver retakes the road test, the platform can also conduct a mock test to help the driver familiarize themselves with the test process and requirements.

[0056] The multi-dimensional task-based management and control method provided in this embodiment can determine the task processing results corresponding to different target task information without manual review or notification, thereby improving processing efficiency and meeting the needs of online car-hailing platforms for rapid response and efficient operation.

[0057] In one possible implementation, the target task information includes document processing task information; and the above step S102 includes:

[0058] Step S1021: Determine the image data uploaded by the user according to the target task information.

[0059] Target task information: It is the starting basis for the entire task processing process and determines the direction and focus of subsequent operations. Different task types correspond to different information requirements.

[0060] User-uploaded image data: refers to files containing visual information submitted by users to the system to complete specific tasks, such as ID photos, vehicle photos, etc.

[0061] Based on the target task information obtained previously (such as document processing task information, driver recognition task information, road test task information, etc.), the image type that the user needs to upload in the current task scenario is clarified, and then the corresponding image data is accurately located and extracted from the data submitted by the user.

[0062] For example, when the target task information is a document processing task information, the system determines that the user needs to upload photos of documents such as driver's license, vehicle registration certificate, and online ride-hailing driver qualification certificate. For example, when a new driver registers on an online ride-hailing platform, they follow the system prompts to upload photos of the front and back of their driver's license.

[0063] Step S1022: Identify the image data and determine the text information corresponding to the image data.

[0064] Image recognition technology (such as optical character recognition (OCR) technology) is used to analyze and process the extracted image data, and the text content in the image is converted into computer-recognizable text information for further processing and analysis.

[0065] Text information can indicate the text content obtained after image recognition and is a digital representation of key information in the image.

[0066] As an example, in an online ride-hailing scenario, OCR is performed on a driver's license photo uploaded by a user. The driver's license number, name, permitted vehicle type, and expiration date are extracted from the photo and converted into text-based data. For example, the recognized driver's license number is "123456789012345678," the name is "Zhang San," the permitted vehicle type is "C1," and the expiration date is "December 31, 2030."

[0067] Step S1023: determining target key information from the text information, wherein the target key information includes at least one of: name, ID number, ID validity period, and permitted vehicle type.

[0068] Target key information: It is the part of the text information that has important value and significance and can directly affect the results of task processing. The key information required for different task types may vary.

[0069] According to the specific requirements of the task, key information closely related to the task is filtered out from the recognized text information. This key information is crucial for judging whether the task meets the requirements.

[0070] As an example, in a document processing task, key information such as name, ID number, ID expiration date, and permitted vehicle type is extracted from the recognized driver's license text. For example, the target key information determined from the above recognition results is the name "Zhang San", ID number "123456789012345678", ID expiration date "December 31, 2030", and permitted vehicle type "C1".

[0071] Step S1024 : comparing the target key information with the historical association information stored in the preset database to determine the task processing result corresponding to the target task information, wherein the task processing result indicates whether the target key information and the historical association information are consistent.

[0072] The preset database can store relevant information and data about historical users for comparison and verification with current task information. Historically relevant information can be historical data that corresponds to the current target key information, typically information already stored in the database during the user's previous registration and review processes. The task processing result is a conclusion drawn from the comparison results, used to indicate the consistency between the target key information and the historical relevant information, thereby determining whether the task has passed review or meets requirements. The extracted target key information is compared with the historical relevant information stored in the preset database. A comparative analysis is performed to determine whether the two are consistent. The processing result of the current target task information is determined based on the comparison results.

[0073] As an example, the target key information extracted from the driver's license uploaded by a new driver (name "Zhang San", ID number "123456789012345678", ID expiration date "December 31, 2030", and permitted vehicle type "C1") is compared with the historical association information stored in the preset database when the driver previously registered. If the name, ID number, ID expiration date, and permitted vehicle type in the historical association information are exactly the same as the current target key information, the task processing result is "approved"; if there is an inconsistency, such as the ID expiration date has expired or the permitted vehicle type does not match, the task processing result is "approved" and the specific inconsistency information is prompted.

[0074] In one possible implementation, in certain special scenarios, such as when a vehicle does not have onboard sensors, data can be collected through external devices, or the accelerometer, gyroscope and other functions of a mobile phone can be used to assist in collecting some data.

[0075] The multi-dimensional task-based management and control method provided in this embodiment eliminates the need for manual operations, from determining image data to identifying text information, and then extracting and comparing key information. For example, when processing the registration information of a large number of online ride-hailing drivers, the ID photos uploaded by each driver can be quickly processed, greatly reducing processing time and improving work efficiency.

[0076] In one possible implementation, step S103 includes:

[0077] Step S1031 : When the task processing result indicates that the target key information and the historical association information are inconsistent, the task processing result is sent to the user's terminal device so that the user can re-upload new image data.

[0078] The terminal device can be a device used by the user to interact with the system, specifically a mobile phone, platform computer, or other device with network connection function and certain information processing capabilities, which can receive and display the information sent by the system. After completing the comparison of the target key information with the historical related information in the preset database, a task processing result will be obtained. When the result clearly shows that there is an inconsistency between the target key information and the historical related information, the system will trigger subsequent operations. The inconsistent task processing results are sorted and packaged, and sent to the terminal device bound to the user when registering or logging in, such as a mobile phone, tablet computer, etc., through a specific communication protocol (such as HTTP, WebSocket, etc.). After the user's terminal device receives the task processing result, it will display information to the user in the form of notifications, pop-ups, text messages, etc., informing the user that there is a problem with the uploaded image data and that new image data needs to be uploaded again.

[0079] For example, when a new driver registers on a ride-hailing platform, they upload a photo of their driver's license. After image recognition and comparison, the system discovers that the license number on the driver's license doesn't match the driver's license number previously registered in the platform's database. The system then sends a "Document Number Inconsistency" task result to the driver's phone, which then displays a notification stating "Driver's license information is incorrect. Please re-upload your license photo."

[0080] In one possible implementation, step S103 includes:

[0081] Step S1032: Send the target key information to the management page for display so that the target key information can be manually reviewed.

[0082] The system extracts the target's key information (such as name, ID number, ID expiration date, and permitted vehicle type) from the current processing flow and transmits it to the management page via the internal network or interface. Upon receiving the target's key information, the management page displays it in an appropriate format (such as a table or list) for easy review by the auditor. Auditors log in to the management page and review each displayed target's key information. Auditors, drawing on their expertise and experience, determine the authenticity, accuracy, and completeness of the target's key information, as well as any anomalies.

[0083] For example, in the case of inconsistent driver's license information, the system not only notifies the driver to re-upload a photo but also sends the extracted target key information (such as name "Zhang San", incorrect ID number "123456789012345678", ID expiration date "December 31, 2030", and permitted vehicle type "C1") to the ride-hailing platform's management page. Auditors can view this information after logging into the management page and manually review the target key information by verifying with the relevant ID management department and comparing historical data to determine the root cause of the problem and a solution.

[0084] For example, when a driver registers or renews their ID, they are required to upload an image of it. The system first utilizes an optical character recognition (OCR) engine to efficiently recognize the printed text on the ID. This engine, based on deep learning OCR technology, is adaptable to documents with varying fonts, layouts, and image quality. After recognition, the information extraction and parsing submodule accurately extracts the relevant information according to the specifications of the document type. Finally, the information is compared with existing driver information in the database or authoritative data sources to ensure accuracy. If any inconsistencies or doubts are found, the system prompts the driver to re-upload the information or conduct manual review.

[0085] In one possible implementation, combining Figure 2As shown, the driver uploads an image of a document such as a driver's license or vehicle registration certificate, and the document image acquisition interface receives the data. The OCR recognition engine recognizes the text in the image and converts it into text. The information extraction and parsing submodule extracts key information from the recognized text, such as name, document number, expiration date, and permitted vehicle type. Through the database comparison interface, the extracted information is compared with existing information in the platform database to verify its accuracy and consistency. For example, when registering or renewing a driver's license, an image of the document must be uploaded. The system first uses the OCR recognition engine to efficiently recognize the printed text on the document. This engine, based on deep learning OCR technology, is adaptable to documents with different fonts, layouts, and image quality. After recognition, the information extraction and parsing submodule accurately extracts the relevant information according to the specifications of the document type. Finally, the information is compared with existing driver information in the database or authoritative data sources to ensure the accuracy of the information. If any inconsistencies or doubts are found, the system prompts the driver to re-upload the information or conduct manual review.

[0086] This embodiment provides a multi-dimensional task-based management and control method. When task processing results indicate a discrepancy between target key information and historically associated information, users are promptly notified via their terminal devices. This allows users to immediately learn of issues with uploaded image data without having to wait or proactively check the review status, improving the timeliness of information acquisition.

[0087] Furthermore, by sending the target key information to the management page for manual review, the reviewer's expertise and experience can be used to reconfirm the system's automated comparison results. Manual review can identify details or special circumstances that the system might have overlooked, thereby improving review accuracy. For example, in some cases, the system may not accurately recognize a handwritten ID number, but a manual reviewer can make a judgment based on handwriting characteristics and contextual information.

[0088] In one possible implementation, the target task information includes driving recognition task information; and the above step S102 includes:

[0089] Step S1025: Determine the user's driving behavior data based on the target task information.

[0090] The target task information can indicate the platform's assessment requirements for the driver's service quality (such as safe driving and service attitude). This step uses on-board sensors, GPS, dashcams, and other equipment to collect the driver's driving behavior data during the order execution process. Driving behavior data includes but is not limited to: the number of sudden braking times, speeding records, and mileage.

[0091] For example, a ride-hailing platform requires drivers to maintain a speed of ≤60 km / h during their orders (target mission information). The platform uses the in-vehicle GPS to record the driver's actual speed (driving behavior data). If a driver's average speed during a particular order is 65 km / h, this data will be extracted and used for subsequent analysis.

[0092] Step S1026 , using the behavior level determination model, obtains a task processing result based on the user's driving behavior data; wherein the task processing result indicates the driving behavior level corresponding to the driving behavior data.

[0093] The behavior level determination model may be an algorithm model trained based on historical driving behavior data, and is used to evaluate the driving behavior level to ensure the safety and compliance of driving behavior.

[0094] The behavior grading model uses machine learning algorithms (such as support vector machines, random forests, or deep learning) to train driving behavior data and establish a mapping relationship between behavior characteristics and grades. After inputting driving behavior data, the model outputs the corresponding driving behavior grade (e.g., "Excellent," "Pass," or "Needs Improvement").

[0095] The multi-dimensional task-based control method provided in this embodiment automatically analyzes driving behavior data using a behavior grading model, eliminating the need for manual intervention and significantly improving processing efficiency. Furthermore, the system can process large amounts of driving data in real time or in batches, quickly generating driving behavior grading results, making it suitable for large-scale online ride-hailing platforms.

[0096] In one possible implementation, step S103 includes:

[0097] Step S1033: When the driving behavior level is greater than the level threshold, determine the training scenario information corresponding to the driving behavior data, wherein the training scenario information includes at least one of safety knowledge course information and simulated accident drill information.

[0098] The level threshold can indicate the driving behavior level standard set by the platform, which is used to distinguish whether the driver needs training. Training scenario information: training content or form designed for specific problems of drivers, aimed at improving their driving skills and safety awareness. In the online car-hailing scenario, the platform pre-sets the driving behavior level threshold (such as "needs improvement" or "unqualified"). When the system determines that the driver's driving behavior level exceeds the threshold, it matches the corresponding training scenario information based on the specific driving behavior data (such as the frequency of sudden braking, the number of speeding, etc.). Training scenario information may include: safety knowledge course information: such as online courses such as "Defensive Driving Skills" and "Driving Safety in Bad Weather"; simulated accident drill information: such as virtual reality (VR) drill scenarios that simulate skidding and rear-end collisions in rainy days.

[0099] Step S1034: Determine the user's training evaluation result for the training scenario information.

[0100] After the user performs training according to the training scenario information, a training evaluation result of the user with respect to the training scenario information may be determined.

[0101] As an example, after a driver completes training, the platform can evaluate his or her learning outcomes through the following methods: course testing: setting multiple-choice questions, true-or-false questions and other tests after the online course; drill scoring: scoring VR drills based on indicators such as operation accuracy and reaction speed; comprehensive scoring: combining course testing and drill scoring to generate training evaluation results (such as "qualified" or "unqualified").

[0102] For example: A driver completed the "Emergency Braking Skills and Anticipation" course test and scored 75 points (the passing score is 70 points), but an "accident" occurred due to an operational error during the VR drill, and the final overall score was "unqualified".

[0103] Step S1035 : generating training modification suggestions corresponding to the training evaluation results based on the training evaluation results, and sending the training modification suggestions to the user's terminal device.

[0104] Training modification suggestions can indicate improvement measures based on the evaluation results, aiming to help drivers improve their driving abilities. Based on the training evaluation results, the platform can provide drivers with personalized improvement suggestions and send them to the driver's terminal via app message, SMS, or email. For example, suggestions include "Recommend retaking Chapter 3 of 'Emergency Braking Techniques and Anticipation'"; "Recommend completing three simulated rain-weather skidding drills"; and "Submit a monthly safe driving reflection report."

[0105] In one possible implementation, combining Figure 3 As shown, the data collection interface can be used to collect driver driving behavior data (such as the number of sudden braking times, speeding records, mileage, etc.), accident records, violation information, etc. The driving risk assessment submodule uses big data analysis technology and machine learning algorithms to analyze the collected data and assess the driver's driving risk level. Based on the assessment results, the training program generation submodule formulates a personalized safety training program for the driver, including recommended online courses, simulated accident drill scenarios, etc. Drivers access the online learning platform through the online learning platform interface to learn safety knowledge, watch teaching videos, and participate in simulated accident drills. After the training, the training assessment submodule organizes an online assessment, including theoretical knowledge tests and practical operation simulation assessments. The training effect evaluation submodule conducts a comprehensive evaluation of the training effect based on the assessment results and the performance during the learning process (such as learning time, participation, answer accuracy, etc.).

[0106] In real-world scenarios, the platform continuously collects data on drivers' driving behavior. For example, on-board sensors and positioning systems capture data on drivers' sudden braking, sharp turns, speeding, and other behaviors. The driving risk assessment submodule utilizes this data, combined with machine learning algorithms such as decision trees and neural networks, to quantitatively assess drivers' driving risks, categorizing them into three levels: high, medium, and low. For high-risk drivers, the system generates more targeted training programs, including additional safety courses and simulated accident drills for complex scenarios. The online learning platform provides a wealth of multimedia teaching resources, allowing drivers to learn anytime, anywhere. The training assessment submodule utilizes a variety of assessment methods to ensure a comprehensive evaluation of drivers' learning outcomes. Based on the assessment results, the training effectiveness evaluation submodule provides drivers with improvement suggestions and provides a basis for optimizing subsequent training programs.

[0107] The multi-dimensional task-based management and control method provided in this embodiment matches targeted training scenario information according to the driver's specific driving behavior data (such as sudden braking, speeding, fatigue driving, etc.). Compared with the traditional training method in related technologies that uses unified training content for all drivers, this application focuses on the driver's weak links and improves training efficiency.

[0108] In one possible implementation, the target task information includes road test task information, wherein the above step S102 includes:

[0109] Step S1027: Determine the user's road test behavior data based on the road test task information.

[0110] Road test task information may refer to the standardized road test tasks set by the ride-hailing platform for drivers, including the test route, scoring criteria (such as points deducted for speeding and lane changing violations), test duration, etc. Road test behavior data may refer to the driver's behavior records generated during the road test, such as whether they exceeded the speed limit, made illegal lane changes, and used turn signals correctly.

[0111] Specifically, the platform collects real-time driving behavior data from onboard devices (such as OBD interfaces and GPS) or third-party testing systems. Driving behavior data can include speed curves, steering wheel angles, braking frequency, lane departure times, and more.

[0112] Step S1028: Using the behavior anomaly determination model, a task processing result is obtained based on the road test behavior data, wherein the task processing result indicates whether there is an anomaly in the user's road test behavior data.

[0113] Anomaly Determination Model: An algorithm based on machine learning or a rules engine is used to determine whether a driver's driving behavior deviates from normal ranges. The road test behavior data serves as the input to the Anomaly Determination Model, and the task processing results serve as the output. The task processing results can indicate whether the driver's road test behavior is abnormal (e.g., "abnormal" or "normal").

[0114] The above step S103 includes:

[0115] Step S1036: When there is an abnormality in the user's road test behavior data, determine the type of the user's road test behavior data.

[0116] The system categorizes abnormal behaviors into specific types based on the dimensions of the triggering rules. These types may include: speed anomaly, operational specification anomaly, safety awareness anomaly, etc.

[0117] Step S1037: Determine the task solution corresponding to the type of the user's road test behavior data based on the type of the user's road test behavior data.

[0118] The type of user road test behavior data (such as "speeding anomaly", "illegal lane change anomaly", "turn signal use anomaly", etc.), and the task solution measures for specific anomaly types (such as training courses, simulation drills, test retakes, etc.).

[0119] In one possible implementation, combining Figure 4 As shown, during the road test, the driver's driving behavior data is collected in real time through the security SDK, for example, to calculate behavioral characteristics such as speeding, sudden acceleration and deceleration, and distracted driving. The driving behavior analysis submodule can use AI algorithms to perform real-time analysis on the collected data to determine whether the driver's operation complies with the regulations. Based on the analysis results, the real-time scoring submodule scores the driver's driving behavior in real time according to pre-set scoring criteria. The invigilator can view the road test process and scoring status through the invigilator monitoring interface and can perform manual intervention if necessary. The abnormal situation handling submodule promptly handles and records emergencies during the road test (such as vehicle failures, violations, etc.).

[0120] More specifically, during the novice driver entrance road test, cameras record the driver's driving operations in all directions, and sensors accurately collect vehicle operating data. The driving behavior analysis submodule uses deep learning algorithms to analyze every driver's operation. For example, by analyzing the steering wheel rotation angle and speed changes, it can determine whether the driver's control of the vehicle is smooth; by monitoring the frequency and intensity of brake and accelerator use, the driver's ability to control speed is evaluated. The real-time scoring submodule uses these analysis results and compares them with detailed scoring criteria, such as operating specifications, safety awareness, and route execution standards, to provide real-time scores. The invigilator can view the driver's road test status in real time through the system's monitoring interface. If any anomalies are found (such as illegal driver operation or vehicle malfunction), the abnormal situation handling submodule can intervene, such as pausing the test and guiding the driver to resolve the problem.

[0121] The multi-dimensional task-based control method provided in this embodiment collects road test behavior data (such as speeding, sudden braking, and turn signal use), covering the entire driving process and avoiding the limitations of a single indicator. Furthermore, it utilizes a behavioral anomaly identification model and automatically identifies abnormal behavior through algorithms (such as threshold judgment and cluster analysis), reducing manual misjudgment.

[0122] In one possible implementation, the method further includes: utilizing a behavior score determination model to determine the user's behavior score based on the road test behavior data.

[0123] User road test behavior data (e.g., speeding frequency, correct turn signal usage, frequency of sudden braking, etc.) can be used as input for a behavior scoring determination model, which maps the behavior data into a behavior score. The output of the behavior scoring determination model can be a user behavior score (e.g., 0-100) and associated task resolution measures.

[0124] The multi-dimensional task-based control method provided in this embodiment quantifies scores through multi-dimensional behavioral data (such as the number of speeding times, turn signal usage rate, and sudden braking frequency) to avoid deviations from human subjective judgment.

[0125] In this embodiment, a multi-dimensional task-based control device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation methods. The details that have been described will not be repeated here. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0126] This embodiment provides a multi-dimensional task-based control device, such as Figure 5As shown, it includes: an acquisition module 501, which is used to obtain target task information; wherein the target task information includes: any one of: document processing task information, driving recognition task information and road test task information; a first determination module 502, which is used to determine the task processing result corresponding to the target task information based on the target task information; a second determination module 503, which is used to determine the task solution measures corresponding to the task processing result based on the task processing result.

[0127] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0128] The multi-dimensional task-based control device in this embodiment is presented in the form of a functional unit, where the functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0129] The embodiment of the present invention also provides a computer device having the above Figure 5 The multi-dimensional task-based control device shown.

[0130] See also Figure 6 , Figure 6 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0131] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0132] The memory 20 stores instructions that can be executed by at least one processor 10, so as to enable at least one processor 10 to execute the method shown in the above embodiment.

[0133] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0134] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0135] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0136] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0137] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0138] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A multi-dimensional task-based management and control method, characterized in that: The method comprises: Obtain target task information; wherein the target task information includes: any one of: document processing task information, driving recognition task information, and road test task information; Determine, based on the target task information, a task processing result corresponding to the target task information; Determine, based on the task processing result, a task solution measure corresponding to the task processing result.

2. The multi-dimensional task-based management and control method according to claim 1, characterized in that: The target task information includes document processing task information. Determining a task processing result corresponding to the target task information based on the target task information includes: Determining the image data uploaded by the user according to the target task information; Identifying the image data and determining text information corresponding to the image data; Determining target key information from the text information, wherein the target key information includes at least one of: name, ID number, ID validity period, and permitted vehicle type; The target key information is compared with the historical association information stored in a preset database to determine a task processing result corresponding to the target task information, wherein the task processing result indicates whether the target key information and the historical association information are consistent.

3. The multi-dimensional task-based management and control method according to claim 2, characterized in that: Determining, based on the task processing result, a task solution measure corresponding to the task processing result, including: When the task processing result indicates that the target key information and the historical association information are inconsistent, the task processing result is sent to the user's terminal device so that the user can re-upload new image data; or The target key information is sent to a management page for display so that the target key information can be manually reviewed.

4. The multi-dimensional task-based management and control method according to claim 1, characterized in that: The target task information includes driving recognition task information. Determining a task processing result corresponding to the target task information based on the target task information includes: Determining the user's driving behavior data based on the target task information; A behavior level determination model is used to obtain a task processing result based on the user's driving behavior data; wherein the task processing result indicates a driving behavior level corresponding to the driving behavior data.

5. The multi-dimensional task-based management and control method according to claim 4, characterized in that: Determining, based on the task processing result, a task solution measure corresponding to the task processing result, including: When the driving behavior level is greater than a level threshold, determining training scenario information corresponding to the driving behavior data, wherein the training scenario information includes at least one of safety knowledge course information and simulated accident drill information; Determining a training evaluation result of a user with respect to the training scenario information; Based on the training evaluation result, a training modification suggestion corresponding to the training evaluation result is generated, and the training modification suggestion is sent to the user's terminal device.

6. The multi-dimensional task-based management and control method according to claim 5, characterized in that: The target task information includes road test task information, wherein determining a task processing result corresponding to the target task information according to the target task information includes: Determine the user's road test behavior data based on the road test task information; Obtaining a task processing result based on the road test behavior data using a behavior anomaly determination model, wherein the task processing result indicates whether the road test behavior data of the user has an anomaly; Determining, based on the task processing result, a task solution measure corresponding to the task processing result, including: When the user's road test behavior data is abnormal, determining the type of the user's road test behavior data; According to the type of the user's road test behavior data, a task solution corresponding to the type of the user's road test behavior data is determined.

7. The multi-dimensional task-based management and control method according to claim 6, characterized in that: The method further comprises: Use the behavior scoring model to determine the user's behavior score based on the road test behavior data.

8. A multi-dimensional task-based control device, characterized in that: The device comprises: An acquisition module, configured to acquire target task information; wherein the target task information includes any one of: document processing task information, driver recognition task information, and road test task information; A first determining module is used to determine the task processing result corresponding to the target task information according to the target task information; The second determining module is used to determine a task solution measure corresponding to the task processing result according to the task processing result.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the multi-dimensional task-based management and control method described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the multi-dimensional task-based management and control method according to any one of claims 1 to 7.

Images