A tractor user management system and method

Abstract

A tractor user management system and method, relating to the field of tractors, includes multi-factor authentication of a user through at least two combinations of RFID radio frequency identification, PIN code verification and facial recognition, and a three-level permission hierarchical control mechanism to achieve hard isolation of permissions; automatically loads personalized configuration parameters to the electronic control system according to the identity information, and realizes cross-device configuration migration based on SM4 encryption; real-time collection of vehicle speed, engine load rate, PTO speed and rear suspension opening to construct a normalized working condition feature vector, matching calculation with a working condition mode library through weighted Euclidean distance, and adaptive weighted correction of electronic control parameters combined with a user preference weight vector. The present application effectively solves the problems of traditional tractor operation permission ambiguity, parameter repeated adjustment, fault traceability difficulty and the like, and improves the operation safety, work efficiency and after-market service capability.

Description

Technical Field

[0001] This invention relates to the field of tractor technology, and in particular to a tractor user management system and method. Background Technology

[0002] With the rapid development of intelligent agricultural machinery, coupled with the accelerated land transfer, the popularization of large-scale field operations, and the routine operation of professional agricultural machinery operators, the market demands for tractors, as core agricultural operation equipment, to improve their operational safety, efficiency, and intelligent control capabilities. Currently, most tractors still use traditional mechanical keys for starting and paper ledgers for recording operational information. Frequent driver changes can lead to repeated adjustments of operating parameters, resulting in shortcomings such as unclear operating permissions, missing operation records, high management costs, and insufficient ease of operation. In the event of improper driving, misuse of equipment, or machinery malfunction, it is also difficult to quickly trace and handle the situation, making it difficult to adapt to the requirements of intelligent and intensive development of agricultural equipment.

[0003] Especially in real-world scenarios where tractors are shared by multiple users and work tasks are frequently switched, the lack of effective user identification and access control can easily lead to problems such as human error, unclear responsibilities, and equipment abuse, affecting the overall lifespan of the machine and operational efficiency. To address these issues, developing a user management system capable of identifying drivers, assigning permissions, recording behavior, personalizing data, and providing remote monitoring has become an important direction in the development of modern intelligent tractor technology. This system is of great significance for improving the safety, intelligence level, and after-sales service capabilities of agricultural machinery. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, this invention discloses a tractor user management system and method. The aim is to provide a tractor user management system and method based on multi-identity recognition and behavior collection, capable of identifying individual user identities, usage behaviors, and operating environments, and achieving deep integration of personalized tractor management, thereby improving service efficiency, enhancing safety control, and reducing the risk of misuse.

[0005] To achieve the above-mentioned objectives, the present invention adopts the following technical solution:

[0006] A tractor user management system and method, comprising the following steps:

[0007] S1. User authentication: In response to the user's authentication request, the user's identity is verified through multi-factor authentication to determine the identity information of the currently operating user;

[0008] S2. Personalized configuration loading: Based on the identity information, retrieve the personalized configuration parameters bound to the current operating user from the preset user configuration database, and load the personalized configuration parameters into the tractor's electronic control system;

[0009] S3. Multi-source working condition feature acquisition: During the operation of the tractor, multi-source working condition feature data are acquired in real time to construct the current working condition feature vector;

[0010] S4. Adaptive matching and parameter adjustment of working conditions: The current working condition feature vector is matched and calculated with each standard working condition mode in the preset working condition mode library to determine the target working condition mode to which the current working condition belongs. Based on the target working condition mode and the preference weight of the current operator, the corresponding electronic control adjustment parameters are generated to adaptively adjust the power system and / or hydraulic system of the tractor.

[0011] S5. Operation Information Recording and Synchronization: Records the current operation status data, operation parameters, and user behavior data during the current operation process and uploads them to the cloud data management platform.

[0012] Preferably, in step S3, the multi-source operating condition feature data includes: real-time vehicle speed. Engine load rate , power output shaft speed and rear suspension opening The construction of the current operating condition feature vector includes: normalizing the collected feature data of each operating condition to obtain a normalized feature vector. The normalized feature vector is subjected to sliding window filtering to remove outliers; wherein, when the deviation of a certain feature value from the mean of the sliding window exceeds a preset deviation threshold, the outlier is replaced by the mean of the sliding window.

[0013] Preferably, in step S4, the matching calculation includes: calculating the current operating condition feature vector. With the first in the working condition mode library Standard operating mode Weighted Euclidean distance between them:

[0014]

[0015] in, For the first Matching weights corresponding to each working condition feature dimension. For the first The standard operating mode in the first Standard values ​​for each feature dimension; the matching degree is calculated based on the weighted Euclidean distance:

[0016]

[0017] The standard operating condition mode with the highest matching degree is selected as the candidate target operating condition mode; when the matching degree of the candidate target operating condition mode is... Greater than or equal to the preset matching threshold When the candidate target working condition mode is confirmed to be the target working condition mode to which the current working condition belongs; when the matching degree is less than the preset matching threshold If the current operating mode remains unchanged, an unrecognized operating mode prompt will be output.

[0018] Preferably, in step S4, generating the corresponding electronic control adjustment parameters based on the target operating mode and the current user's preference weights includes: obtaining the current user's preference weight vector. ,in , , , Let these represent the weights for economic preference, efficiency preference, work quality preference, and comfort preference, respectively, and satisfy the following conditions: ;

[0019] The basic electronic control parameter set is determined based on the target operating mode, and the target engine speed, gearbox shifting strategy, and hydraulic system response rate in the basic electronic control parameter set are weighted and corrected based on the preference weight vector to generate the final electronic control adjustment parameters. The dynamic calibration of the preference weight vector includes: recording the number of times the current operator manually intervenes in the electronic control adjustment parameters during the operation; when the number of manual interventions accumulates to a preset intervention threshold within a preset statistical period, the preference weight vector is incrementally updated according to the direction and magnitude of the manual intervention, and the normalization constraint is re-executed.

[0020] Preferably, step S4 further includes:

[0021] When it is detected that the tractor receives an implement identification message sent by the attached implement via the ISOBUS bus, the corresponding target working condition mode is directly locked according to the implement type identifier in the implement identification message, and the matching degree is forcibly set to 100%, skipping the matching calculation step;

[0022] When the ISOBUS bus communication is interrupted or the machine identification message verification fails, it automatically degrades to the matching calculation mode based on the multi-source working condition feature data.

[0023] Step S4 further includes anti-jump processing: when the target operating condition modes calculated in two consecutive sampling periods are inconsistent, only when the matching degree of the new target operating condition mode is continuous... Each sampling period is greater than the preset matching threshold. When switching operating modes, the process is as follows: This is the preset number of confirmation cycles.

[0024] Preferably, in step S1, the multi-factor authentication method includes at least two of RFID radio frequency identification, PIN code verification, and facial recognition;

[0025] The user authentication also includes hierarchical access control:

[0026] The permission level is determined based on the identity information of the currently operating user, and the permission level includes:

[0027] Static operation permissions correspond to permissions granted only through RFID radio frequency identification authentication, allowing entry and exit from the driver's cab and static operations;

[0028] Routine operation permissions are granted through a combination of RFID radio frequency identification and facial recognition authentication, allowing the execution of routine field operations.

[0029] Special operating permissions, which correspond to a combination of facial recognition and PIN code verification, allow the execution of agricultural machinery repair and cross-regional operations;

[0030] When the authentication method of the current user does not meet the authentication combination required by its permission level, the execution of the corresponding function is restricted and an insufficient permission prompt is output.

[0031] Preferably, in step S2, the personalized configuration parameters include at least one of seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​of operating parameters; it also includes a cross-device configuration migration step:

[0032] When the current user authenticates their identity on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform, and after decryption and verification, it is loaded into the electronic control system of the second tractor.

[0033] The encrypted configuration data is encrypted and stored using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user.

[0034] A tractor user management system, comprising:

[0035] The user identification module is used to respond to the user's authentication request, verify the user's identity through multi-factor authentication, and determine the identity information of the currently operating user.

[0036] The personalized configuration module is used to retrieve the personalized configuration parameters bound to the current operating user from the preset user configuration database based on the identity information, and load the personalized configuration parameters into the tractor's electronic control system;

[0037] The working condition acquisition module is used to collect multi-source working condition feature data in real time during the operation of the tractor and construct the current working condition feature vector.

[0038] The working condition matching and adjustment module is used to match and calculate the current working condition feature vector with each standard working condition mode in the preset working condition mode library, determine the target working condition mode to which the current working condition belongs, and generate corresponding electronic control adjustment parameters according to the target working condition mode and the preference weight of the current operator, so as to adaptively adjust the power system and / or hydraulic system of the tractor.

[0039] The job information management module is used to record the working condition data, operation parameters and user behavior data during the current job process, and upload them to the cloud data management platform.

[0040] Preferably, the user identification module includes at least two of the following: an RFID radio frequency identification unit, a PIN code verification unit, and a face recognition unit;

[0041] The user identification module is also used to perform hierarchical access control, specifically including:

[0042] The user's permission level is determined based on their current identity information. The permission levels include static operation permission, regular operation permission, and special operation permission. Static operation permission corresponds to authentication only through the RFID radio frequency identification unit. Regular operation permission corresponds to authentication through a combination of the RFID radio frequency identification unit and the face recognition unit. Special operation permission corresponds to authentication through a combination of the face recognition unit and the PIN code verification unit.

[0043] The user identification module is also used to restrict the execution of the corresponding function and output an insufficient permission prompt when the authentication method of the current operating user does not meet the authentication combination required by its permission level.

[0044] The personalized configuration parameters in the personalized configuration module include at least one of the following: seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​for operating parameters.

[0045] The personalized configuration module is also used to perform cross-device configuration migration: when the current user authenticates on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform, and after decryption and verification, it is loaded into the electronic control system of the second tractor; the encrypted configuration data is encrypted and stored using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user.

[0046] Preferably, the cloud-based data management platform includes:

[0047] The data storage sub-platform is used to encrypt and store the uploaded working condition data, operation parameters and user behavior data, and to establish a multi-dimensional data index with the user identity as the primary key.

[0048] The fault warning sub-platform is used to perform real-time analysis of the operating condition data. When at least one of the engine temperature, hydraulic system pressure, or transmission system vibration parameters is detected to exceed a preset safety threshold, fault warning information is generated, and the warning level is determined according to the fault type and severity.

[0049] The maintenance dispatch sub-platform is used to automatically generate maintenance work orders based on the fault warning information. The maintenance work order includes a fault description, a list of required spare parts, and recommended maintenance personnel. The maintenance dispatch sub-platform is also used to intelligently dispatch work orders based on the location information of the current user and the availability status of the recommended maintenance personnel.

[0050] The maintenance closed-loop management sub-platform is used to track the entire lifecycle status of the maintenance work order from creation, dispatch, on-site repair to archiving and evaluation, and to associate the repair record with the equipment file of the corresponding tractor and the user file of the current operator after the repair is completed.

[0051] By employing the technical solution described above, the present invention has the following beneficial effects:

[0052] (1) This invention adopts a multi-factor authentication method that combines at least two of RFID radio frequency identification, PIN code verification and face recognition, and establishes a three-level hierarchical control mechanism of static operation permission, regular operation permission and special operation permission. This ensures that operations of different permission levels must be executed through the corresponding strength of authentication combination, effectively solving the problems of ambiguous operation permissions, personnel misoperation and equipment abuse in traditional tractor operation. It achieves hard isolation of permissions from the authentication level and improves the overall machine operation security.

[0053] (2) The present invention automatically loads a subset of configurations such as seat position, rearview mirror angle, air conditioning temperature, instrument panel layout and preset values ​​of operating parameters according to user identity information through a personalized configuration module, eliminating the problem of repeated manual adjustment of operating parameters when multiple drivers take turns using the same tractor, and significantly improving the convenience of operation and work efficiency.

[0054] (3) This invention uses the SM4 symmetric encryption algorithm to encrypt and store configuration data and realize cross-device configuration migration, so that the user's personalized configuration can be seamlessly reused between any tractors that have been connected to the system, while ensuring the security of configuration data during cloud storage and transmission, and solving the problem that configuration data is limited to a single device in the traditional way.

[0055] (4) This invention collects multi-source operating condition feature data such as vehicle speed, engine load rate, PTO speed and rear suspension opening in real time, constructs normalized feature vectors and performs matching calculations based on weighted Euclidean distance and operating condition mode library, and performs adaptive weighted correction of electronic control parameters by combining user preference weight vectors, thereby realizing the automation and personalization of operating condition identification and parameter adjustment, avoiding the lag and inconsistency of manual adjustment based on driver experience in the traditional method, and improving the quality of operation and fuel economy.

[0056] (5) By introducing a fast locking mechanism for ISOBUS machine identification messages and an automatic degradation strategy when communication is interrupted, this invention takes into account both the response speed of working condition identification and the reliability of the system. At the same time, by using an anti-jump processing mechanism, the target working condition mode is required to meet the threshold condition within N consecutive sampling periods before it can be switched, which effectively avoids frequent jumps in electrical control parameters caused by working condition fluctuations and ensures the stability of operation.

[0057] (6) This invention uses a dynamic calibration mechanism for the preference weight vector to incrementally learn and update the system based on the direction and magnitude of the user's manual intervention, so that the system can continuously adapt to changes in user preferences as the usage time increases, reduce the frequency of manual intervention, and achieve human-machine collaborative evolution.

[0058] (7) This invention integrates four sub-platforms—data storage, fault early warning, maintenance scheduling, and maintenance closed-loop management—through a cloud-based data management platform. This enables full traceability of work data, proactive early warning of faults, and intelligent dispatch and full lifecycle tracking of maintenance work orders. It solves the problems of missing operation records, difficulty in tracing faults, and delayed maintenance response under the traditional paper-based ledger management method, reduces management costs, and improves aftermarket service capabilities. Attached Figure Description

[0059] Figure 1 A schematic diagram of the layered architecture of the tractor user management system;

[0060] Figure 2 Flowchart for user registration and device binding;

[0061] Figure 3 Flowchart for personalized configuration and dynamic matching for users;

[0062] Figure 4 This is a schematic diagram of the multi-source working condition matching algorithm system architecture for tractors;

[0063] Figure 5 Flowchart for anomaly warning and maintenance task assignment. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0065] Combined with appendix Figures 1-5 The tractor user management system and method disclosed in some embodiments of the present invention include the following steps: S1, user identity authentication: in response to the user's authentication request, the user's identity is verified through multi-factor authentication to determine the identity information of the current operating user.

[0066] S2. Personalized configuration loading: Based on the identity information, retrieve the personalized configuration parameters bound to the current user from the preset user configuration database, and load the personalized configuration parameters into the tractor's electronic control system.

[0067] S3. Multi-source working condition feature acquisition: During the operation of the tractor, multi-source working condition feature data are acquired in real time to construct the current working condition feature vector.

[0068] S4. Adaptive matching and parameter adjustment of working conditions: The current working condition feature vector is matched and calculated with each standard working condition mode in the preset working condition mode library to determine the target working condition mode to which the current working condition belongs. Based on the target working condition mode and the preference weight of the current operator, the corresponding electronic control adjustment parameters are generated to adaptively adjust the power system and / or hydraulic system of the tractor.

[0069] S5. Operation Information Recording and Synchronization: Records the current operation status data, operation parameters, and user behavior data during the current operation process and uploads them to the cloud data management platform.

[0070] like Figure 1As shown, the above method is implemented based on the overall architecture of the tractor multi-user management system. This system adopts a layered hardware and software architecture, with the upper layer being the software functional module layer 10 and the lower layer being the hardware device unit layer 20. The two layers collaborate through bidirectional data interaction. The hardware device unit layer 20 includes onboard hardware and a backend / terminal. The onboard hardware includes a door lock remote control 21, a radio frequency antenna 22, a cockpit domain display screen 23, a body controller 24, and an agricultural machinery monitoring terminal 25. The backend / terminal includes a web server 26, a database server 27, and a mobile terminal 28. The software functional module layer 10 includes a user identification module 11, a personalized configuration module 12, an operation permission control module 13, a job information management module 14, and a cloud data management platform 15. Before using this system, users must complete the registration and binding process: Users access the registration interface through mobile terminal 28 or Web server 26, fill in their basic personal information and operation qualification information. After the system reviews and verifies the information submitted by the user, it assigns a unique identity to the user and binds the identity to the RFID radio frequency card held by the user. At the same time, a "user-tractor-qualification" triple binding relationship is established in the database server 27. That is, a user's identity information is associated with the number of the tractor equipment that he / she can operate and the operation qualification level he / she holds. This triple binding relationship serves as the basis for subsequent permission determination and personalized configuration retrieval.

[0071] In some embodiments, in step S1, the multi-factor authentication method includes at least two of RFID radio frequency identification, PIN code verification, and facial recognition. Specifically, user authentication adopts a two-stage progressive authentication mechanism. The first stage is the long-distance authentication stage: when a user approaches the tractor carrying a bound RFID radio frequency card, the radio frequency antenna 22 installed at the tractor door senses the radio frequency signal emitted by the door lock remote control 21 and transmits the signal to the body controller 24. The body controller 24 parses the identity identifier carried in the radio frequency signal and compares it with the user information registered in the database server 27. After successful verification, the door lock is activated to unlock, allowing the user to enter the cab. The second stage is the in-cabin authentication stage: after the user enters the cab, the cabin domain display screen 23 displays an authentication interface, requiring the user to perform further identity verification. This further identity verification method varies depending on the user's required permission level, including PIN code verification and / or facial recognition. Facial recognition uses a camera integrated above the cabin domain display screen 23 to capture the user's facial image and compares it with the user's facial feature template pre-stored in the database server 27. If the comparison is successful, the user's identity is confirmed.

[0072] like Figure 2As shown, the user authentication also includes hierarchical access control: the access level is determined based on the current user's identity information. The access levels include: static operation access, corresponding to RFID radio frequency identification authentication only, allowing entry and exit from the cab and static operations; regular operation access, corresponding to a combination of RFID radio frequency identification and facial recognition authentication, allowing regular field operations; and special operation access, corresponding to a combination of facial recognition and PIN code verification authentication, allowing agricultural machinery repair and cross-regional operations. When the current user's authentication method does not meet the required combination for their access level, the execution of the corresponding function is restricted and an insufficient access warning is displayed. Specifically, when the user only completes the first stage of RFID radio frequency identification authentication, the operation access control module 13 determines that the user is currently at the static operation access level. At this time, the vehicle body controller 24 only allows door unlocking and static operations inside the cab (such as adjusting the seat and viewing instrument panel information), but prohibits engine ignition and any driving or operating operations. When users need to perform routine field operations such as tilling and sowing, they must complete facial recognition authentication on the cockpit domain display screen 23. After successful verification by the operation permission control module 13, the permission level is upgraded to the routine operation permission. At this time, the vehicle controller 24 allows engine ignition and power output shaft engagement. When users need to perform special operations such as agricultural machinery maintenance or cross-regional operations, they must further verify their identity by entering a PIN code in addition to facial recognition. The operation permission control module 13 then upgrades the permission level to the special operation permission, opening all operation functions. The binding relationship between the above three levels of permissions and authentication methods ensures that operations of different permission levels must be executed through corresponding strengths of authentication combinations, thereby achieving hard isolation of permissions at the hardware level and preventing low-permission users from exceeding their authority.

[0073] like Figure 3As shown, in some embodiments, in step S2, the personalized configuration parameters include at least one of seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​of operating parameters. After user authentication is completed in step S1, the personalized configuration module 12 retrieves the set of personalized configuration parameters bound to the user from the database server 27 based on the confirmed identity information. This set of configuration parameters is dynamically bound to the user identity in the form of a configuration subset, and each user has an independent configuration subset. After retrieving the corresponding configuration subset, the personalized configuration module 12 sends the parameters contained therein to the corresponding actuators through the body controller 24: the seat position parameters drive the electric seat adjustment mechanism to adjust the seat to the user's preset fore-aft position, backrest angle, and height; the rearview mirror angle parameters drive the electric rearview mirror adjustment mechanism to adjust the rearview mirror to the user's preset angle; the air conditioning temperature parameters are sent to the air conditioning control unit to set the target temperature; the instrument panel display layout parameters control the cockpit domain display screen 23 to switch to the user's preferred information display interface layout; and the preset values ​​of operating parameters are loaded into the agricultural machinery monitoring terminal 25 as the user's default initial values ​​for operating parameters. The automatic loading process of the above-mentioned personalized configuration is automatically triggered after the user completes identity authentication, without the need for the user to manually adjust each item. When multiple drivers take turns using the same tractor, the personalized configuration module 12 automatically loads the corresponding user's configuration subset after each identity switch, eliminating the problem of repeated manual adjustment of operating parameters caused by frequent driver changes in the traditional method.

[0074] like Figure 3As shown, the tractor user management method in this embodiment also includes a cross-device configuration migration step: when the current user performs identity authentication on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform 15, decrypted and verified, and then loaded into the electronic control system of the second tractor; the encrypted configuration data is encrypted and stored using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user. Specifically, when the user completes identity authentication on a non-frequently used tractor (i.e., the second tractor), the body controller 24 of the second tractor initiates a configuration data request to the cloud data management platform 15 through the agricultural machinery monitoring terminal 25, carrying the user's identity identifier in the request. After receiving the request, the cloud data management platform 15 retrieves the user's encrypted configuration data from the database server 27 according to the identity identifier and sends the encrypted configuration data to the second tractor. After receiving the encrypted configuration data, the second tractor uses the key bound to the user's identity information to perform SM4 decryption. After successful decryption, the data integrity is verified, and if the verification is successful, the configuration parameters are loaded into the local electronic control system. Because the key is bound to the user's identity information, even if the encrypted configuration data is intercepted during transmission, unauthorized parties cannot decrypt and obtain the user's personalized configuration content. This cross-device migration mechanism allows users' personalized configurations to be seamlessly migrated and reused across any connected system, following the user's identity, rather than being limited to a single device.

[0075] In some embodiments, in step S3, the multi-source operating condition feature data includes: real-time vehicle speed. Engine load rate , power output shaft speed and rear suspension opening The above four operating condition characteristic data are obtained through different sensors and controllers on the tractor: real-time vehicle speed. Speed ​​data is collected via speed sensors mounted on the gearbox output shaft or wheels; engine load rate. This value, obtained through the engine electronic control unit (ECU), reflects the ratio of the current actual engine output torque to the maximum available torque at the current engine speed; the power take-off shaft speed. The rear suspension opening is collected by a speed sensor mounted on the PTO output shaft. The data is collected by an angle sensor or displacement sensor mounted on the rear suspension mechanism. The multi-source operating condition feature input unit 31 is connected to the aforementioned sensors and controllers via a CAN bus to acquire the above four operating condition feature data in real time at a preset sampling period. The above four feature data cover four dimensions: tractor driving state, power load state, implement drive state, and implement posture state, which can characterize the current operating condition of the tractor from multiple perspectives.

[0076] like Figure 4 As shown, the construction of the current operating condition feature vector includes: the data preprocessing unit 33 normalizing the collected operating condition feature data to obtain a normalized feature vector. Because vehicle speed, engine load rate, PTO speed, and rear suspension opening have different physical dimensions and numerical ranges, directly calculating the distance would lead to the feature dimensions with larger numerical ranges dominating the matching results. Therefore, it is necessary to normalize each feature dimension, mapping the values ​​of each dimension to a unified dimensionless interval. After normalization, the values ​​of each feature dimension are within the same comparable scale range, thus ensuring the balance of the contribution of each dimension in the subsequent weighted Euclidean distance calculation.

[0077] The data preprocessing unit 33 performs sliding window filtering on the normalized feature vector to remove outliers. Specifically, when a feature value deviates from the mean of the sliding window by more than a preset deviation threshold, the outlier is replaced by the mean of the sliding window. In the actual operating environment of a tractor, sensors may generate occasional abnormal readings due to factors such as vibration, dust, and electromagnetic interference. If outliers are directly included in the feature vector for matching calculations, the matching results will deviate from the actual operating conditions. Sliding window filtering maintains a fixed-length time window, calculates the mean of each feature dimension within the window, and when the deviation of the current sampled value from this mean exceeds a preset deviation threshold, the sampled value is determined to be an outlier and replaced by the window mean. This processing method effectively suppresses the interference of occasional noise on the matching results while ensuring data real-time performance, improving the stability of operating condition identification.

[0078] like Figure 4 As shown, in some embodiments, in step S4, the matching calculation includes: the working condition difference comparison subunit 352 calculating the current working condition feature vector. Compared with the i-th standard working condition mode in the working mode threshold library 351 Weighted Euclidean distance between them:

[0079]

[0080] in, For the first Matching weights corresponding to each working condition feature dimension. For the first The standard operating mode in the first The standard values ​​for each feature dimension are pre-stored in the 351 operation mode threshold library. Each standard operation mode corresponds to a typical operation scenario (such as deep tillage, shallow tillage, sowing, transportation, rotary tillage, etc.), and the standard values ​​of each feature dimension under that scenario are recorded in the form of a four-dimensional feature vector. The introduction of weighted Euclidean distance allows the contribution of different feature dimensions to the matching result to be expressed through matching weights. Differentiated adjustments are made; for example, engine load rate and rear suspension opening are more distinguishable under deep tillage conditions, so they can be assigned a larger matching weight; while vehicle speed is more distinguishable under transportation conditions, so it can be assigned a larger matching weight. The setting of matching weights allows the algorithm to adaptively adjust the importance of each dimension according to the characteristics of each operating mode, avoiding the excessive influence of a single dimension on the matching results.

[0081] like Figure 4 As shown, the weighted comprehensive matching calculation subunit 353 calculates the matching degree based on the weighted Euclidean distance:

[0082]

[0083] This matching formula maps the weighted Euclidean distance to a range of 0% to 100%, where the current operating condition feature vector is completely consistent with a certain standard operating condition pattern (i.e., d). i =0), the matching degree is 100%; as the distance between the two increases, the matching degree monotonically decreases. The standard working condition mode with the highest matching degree is selected as the candidate target working condition mode; the matching threshold judgment subunit 354 judges the matching degree of the candidate target working condition mode. Is it greater than or equal to the preset matching threshold? If so, then the candidate target working condition mode is confirmed as the target working condition mode to which the current working condition belongs; when the matching degree is less than the preset matching threshold If the current operating mode remains unchanged, an "operating mode not recognized" message will be output. Preset matching threshold. The setting is used to prevent mismatches when the operating condition characteristics are unclear or when the system is in the transition area between two operating conditions. When the matching degree of all standard operating conditions does not reach the threshold, the system will not switch modes, but will maintain the currently confirmed operating condition mode and continue to operate. At the same time, the operating condition is not recognized prompt is output on the cockpit domain display screen 23 to inform the driver that the current operating condition has not been effectively recognized. The driver can choose to manually specify the operating condition mode.

[0084] like Figure 4 As shown, in some embodiments, in step S4, generating corresponding electronic control adjustment parameters based on the target operating mode and the current user's preference weights includes: the user preference setting unit 32 obtaining the current user's preference weight vector. ,in , , , Let represent the weights of economic preference, efficiency preference, work quality preference, and comfort preference, respectively, and satisfy the following conditions:

[0085]

[0086] The preference weight vector reflects the degree to which each user prioritizes different performance indicators during the task: economic preference weight. Efficiency preference weight represents the degree to which users value fuel economy. This represents the degree to which users value task speed and efficiency, and the weighting of task quality preferences. This characterizes the degree of importance users place on operational outcomes (such as uniform tillage depth and seeding evenness), with a weighting for comfort preferences. This represents the user's level of emphasis on driving comfort (such as vibration and noise). Different users can set different combinations of preference weights according to their own work needs and habits. This preference weight vector is stored in the database server 27 as part of the user's personalized configuration.

[0087] like Figure 4 As shown, the adaptive mapping unit 34 determines the basic electronic control parameter set according to the target operating condition mode, and performs weighted correction on the engine speed target value, transmission shift strategy, and hydraulic system response rate in the basic electronic control parameter set based on the preference weight vector, generating the final electronic control adjustment parameters, which are output through the vehicle electronic control parameter output branch 36. Specifically, each standard operating condition mode corresponds to a set of basic electronic control parameters, which includes the default engine speed target value, default transmission shift strategy (such as shift point, gear selection logic), and default hydraulic system response rate under that operating condition. After determining the target operating condition mode, the adaptive mapping unit 34 first retrieves the basic electronic control parameter set corresponding to that mode, and then performs weighted correction on each parameter according to the current user's preference weight vector: when the user's economic preference weight... When the target engine speed is high, the engine speed target value is adjusted towards lower speeds, and the transmission shift strategy is adjusted towards earlier upshifts to reduce fuel consumption; when the user's efficiency preference weight is high... When the target engine speed is high, the engine speed target value is adjusted towards higher speeds, and the transmission shift strategy is adjusted towards delayed upshifts to improve operating speed; when the user's work quality preference weight is high... At higher speeds, the hydraulic system response rate is corrected towards a higher response direction to ensure the suspension system quickly tracks changes in terrain; when the user's comfort preference weight is higher... At higher speeds, the hydraulic system response rate is adjusted to a smoother level, and the engine speed fluctuation range is narrowed to reduce vibration and noise in the cab. Through the above weighted adjustment, users with different preference weights under the same target operating condition will obtain different electronic control adjustment parameters, realizing the integration of adaptive operating condition adjustment and personalized user needs.

[0088] like Figure 4 As shown, the dynamic calibration of the preference weight vector includes: the manual intervention interface 37 records the number of times the current user manually intervenes in the electronic control adjustment parameters during the operation; when the number of manual interventions accumulates to a preset intervention threshold within a preset statistical period, the preference weight vector is incrementally updated according to the direction and magnitude of the manual intervention, and the normalization constraint is re-executed. In actual operation, users may modify the electronic control adjustment parameters automatically generated by the system through the manual intervention interface 37 (such as manually adjusting the throttle, manually switching gears, and manually adjusting the hydraulic response). These manual intervention behaviors imply the user's dissatisfaction with the current adjustment strategy or the intention to adjust it. The operation information management module 14 continuously records the manual intervention events of each user, including the time of intervention, the type of intervention parameter, the direction of intervention (increase or decrease), and the magnitude of intervention. When the number of manual interventions by a user within a preset statistical period accumulates to a preset intervention threshold (e.g., 10 times), the system determines that the current preference weight vector can no longer accurately reflect the user's actual needs and triggers the recalibration of the preference weights. The calibration process calculates the adjustment amount for each preference dimension based on the direction and magnitude of manual intervention, incrementally updates the preference weight vector, and then re-executes the normalization constraint to ensure that the sum of all weights remains equal to 1. This incremental learning mechanism enables the system to continuously adapt to changes in user preferences as user usage time increases, achieving human-machine co-evolution and reducing the frequency of manual user intervention.

[0089] like Figure 4As shown, in some embodiments, step S4 further includes: when the tractor receives an implement identification message sent by the implement via the ISOBUS bus, the corresponding target working condition mode is directly locked according to the implement type identifier in the implement identification message, and the matching degree is forcibly set to 100%, skipping the matching calculation step. ISOBUS (ISO11783) is a standard communication protocol in the field of agricultural machinery. Implements mounted on the rear of the tractor (such as plows, seeders, rotary tillers, etc.) can send implement identification messages to the tractor via the ISOBUS bus. The message contains information such as implement type identifier, implement width, and required PTO speed. When the multi-source working condition feature input unit 31 detects a valid implement identification message, the current working condition mode can be directly determined according to the implement type identifier, without having to perform the matching calculation process based on multi-source working condition feature data, thereby shortening the response time of working condition identification and improving the timeliness of mode switching.

[0090] like Figure 4 As shown, when the ISOBUS bus communication is interrupted or the machine identification message verification fails, the system automatically downgrades to a matching calculation mode based on the multi-source operating condition feature data. In actual operation, ISOBUS communication may be interrupted due to loose connectors, damaged cables, or electromagnetic interference, or the messages sent by the machine may fail verification due to data errors. In the above abnormal situations, the multi-source operating condition feature input unit 31 automatically switches to the matching calculation mode based on the multi-source operating condition feature data, that is, it resumes the matching calculation process based on weighted Euclidean distance in steps S3 and S4, ensuring that even when ISOBUS is unavailable, the system can still achieve operating condition identification through sensor data, ensuring the continuity of operation management.

[0091] like Figure 4 As shown, step S4 further includes anti-jump processing: when the target operating condition modes calculated in two consecutive sampling periods are inconsistent, the matching degree of the new target operating condition mode is only greater than the preset matching threshold for N consecutive sampling periods. When switching between operating modes, N is the preset number of confirmation cycles. During tractor operation, operating characteristic data may experience short-term fluctuations. For example, when the tractor briefly transitions between two operating modes, the matching calculation results may rapidly alternate between the two modes. If mode switching is performed immediately for each change in matching results, it will cause frequent jumps in electronic control parameters, affecting operational smoothness and driving comfort. Anti-jump processing introduces the constraint of the number of confirmation cycles N, requiring that the new target operating mode must meet the matching threshold condition for N consecutive sampling cycles before switching can be performed. This filters out short-term operating condition fluctuations and avoids frequent mode jumps that could impact the power and hydraulic systems.

[0092] like Figure 4 As shown, the parameter storage synchronization unit 38 uses EEPROM to realize the power-off storage of local electronic control parameters and user preferences, ensuring that the parameter configuration is not lost after the vehicle is powered on again; at the same time, a two-way communication link is established between the agricultural machinery monitoring terminal 25 and the cloud data management platform 15 to synchronously upload the local parameter configuration to the cloud, supporting the consistent reuse of parameters by the same driver on multiple tractors.

[0093] like Figure 5 As shown, in some embodiments, step S5 records the operating condition data, operating parameters, and user behavior data during the current operation and uploads them to the cloud data management platform 15. The operating condition data includes the operating condition feature vectors for each sampling period during the operation, the matched target operating condition mode, and the matching degree value; the operating parameters include the actual operating parameters of the electronic control system such as engine speed, gearbox gear, hydraulic system pressure, and PTO speed; the user behavior data includes user authentication records, manual intervention events, and preference weight adjustment records. After being aggregated by the operation information management module 14, the above data is uploaded to the cloud data management platform 15 via the wireless communication module of the agricultural machinery monitoring terminal 25 through the wireless communication network for centralized storage and analysis, providing data support for subsequent fault warning, maintenance scheduling, and user behavior analysis.

[0094] like Figure 1 As shown in some embodiments of the present invention, a tractor multi-user management system includes: a user identification module 11, used to verify the identity of the user through multi-factor authentication in response to the user's authentication request, and determine the identity information of the current operating user; a personalized configuration module 12, used to retrieve personalized configuration parameters bound to the current operating user from a preset user configuration database according to the identity information, and load the personalized configuration parameters into the tractor's electronic control system; a working condition acquisition module, used to collect multi-source working condition feature data in real time during the tractor's operation, and construct a current working condition feature vector; and a working condition matching module. The matching and adjustment module is used to match and calculate the current working condition feature vector with each standard working condition mode in the preset working condition mode library, determine the target working condition mode to which the current working condition belongs, and generate corresponding electronic control adjustment parameters according to the target working condition mode and the preference weight of the current operator, so as to adaptively adjust the power system and / or hydraulic system of the tractor; the operation information management module 14 is used to record the working condition data, operation parameters and user behavior data during the current operation process, and upload them to the cloud data management platform 15; the working condition matching and adjustment module performs the working condition adaptive matching and parameter adjustment steps as described above.

[0095] like Figure 1As shown, in the above system, the user identification module 11 is implemented at the hardware level using a door lock remote control 21, an RF antenna 22, a cockpit domain display screen 23, and a vehicle body controller 24. The RF antenna 22 is installed at the tractor door to sense the RFID radio frequency card signal emitted by the door lock remote control 21; the vehicle body controller 24 receives the signal transmitted by the RF antenna 22 and performs identity verification and door lock control; the cockpit domain display screen 23 is used to display the authentication interface, collect PIN code input, and drive the camera for facial recognition. The personalized configuration module 12 is implemented at the hardware level using the vehicle body controller 24 and the cockpit domain display screen 23. The vehicle body controller 24 is responsible for sending configuration parameters to actuators such as the seat adjustment mechanism, rearview mirror adjustment mechanism, and air conditioning control unit, while the cockpit domain display screen 23 is responsible for switching the display layout. The operating condition acquisition module is implemented at the hardware level using an agricultural machinery monitoring terminal 25 and various sensors. The agricultural machinery monitoring terminal 25 is connected to the engine ECU, transmission controller, hydraulic controller, and PTO controller via a CAN bus to acquire real-time operating condition characteristic data. The algorithm calculation of the working condition matching and adjustment module is executed in the processor of the agricultural machinery monitoring terminal 25. The electronic control adjustment parameters obtained from the matching calculation are sent to the engine ECU, transmission controller and hydraulic controller via CAN bus. The operation information management module 14 is implemented based on the storage unit and wireless communication module of the agricultural machinery monitoring terminal 25. The storage unit is used to cache operation data locally, and the wireless communication module is used to upload data to the cloud data management platform 15.

[0096] like Figure 2 As shown, in some embodiments, the user identification module 11 includes at least two of an RFID radio frequency identification unit, a PIN code verification unit, and a face recognition unit. The RFID radio frequency identification unit includes a radio frequency antenna 22 installed at the vehicle door and a body controller 24 communicatively connected to it. The operating frequency of the radio frequency antenna 22 is consistent with the operating frequency of the RFID radio frequency card held by the user, and is used to read the identity information in the radio frequency card within a preset sensing distance. The PIN code verification unit is implemented through the touch interface of the cockpit domain display screen 23. The user enters a preset number of digits on the touch interface, and the system compares the entered PIN code with the PIN code bound to the user in the database server 27 for verification. The face recognition unit is implemented through a camera and image processing chip integrated above the cockpit domain display screen 23. After the camera captures the user's facial image, the image processing chip extracts facial feature points and compares them with pre-stored facial feature templates in the database server 27.

[0097] like Figure 2As shown, the user identification module 11 is also used to perform hierarchical access control, specifically including: determining the corresponding access level based on the identity information of the current user, wherein the access level includes static operation access, regular operation access, and special operation access; wherein, the static operation access corresponds to authentication only through the RFID radio frequency identification unit, the regular operation access corresponds to authentication through a combination of the RFID radio frequency identification unit and the face recognition unit, and the special operation access corresponds to authentication through a combination of the face recognition unit and the PIN code verification unit. The user identification module 11 is also used to restrict the execution of the corresponding function and output an insufficient access prompt when the authentication method of the current user does not meet the authentication combination required for its access level. This insufficient access prompt is displayed in the form of text and / or icons on the cockpit domain display screen 23, while the body controller 24 disables the execution circuit of the corresponding function, preventing unauthorized operation from both software prompts and hardware power-off.

[0098] like Figure 3 As shown, the personalized configuration parameters in the personalized configuration module 12 include at least one of the following: seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​for operating parameters. The personalized configuration module 12 is also used to perform cross-device configuration migration: when the current user authenticates their identity on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform 15, decrypted, verified, and then loaded into the electronic control system of the second tractor. The encrypted configuration data is encrypted using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user. The SM4 symmetric encryption algorithm is a national standard algorithm with a key length of 128 bits. Binding the key to the user's identity information means that only users with correct identity information can generate the corresponding decryption key, thereby ensuring the security of the configuration data during cloud storage and transmission.

[0099] like Figure 5 As shown, in some embodiments, the cloud data management platform 15 includes a data storage sub-platform, used to encrypt and store the uploaded working condition data, operating parameters, and user behavior data, and to establish a multi-dimensional data index with the user identity as the primary key. After receiving the work data uploaded by each tractor, the data storage sub-platform encrypts the data and stores it in the database server 27. Simultaneously, it establishes a multi-dimensional data index with the user identity identifier as the primary key. This multi-dimensional index includes time dimension, tractor equipment dimension, working condition mode dimension, and operation type dimension, supporting rapid data retrieval and statistical analysis by any combination of dimensions.

[0100] like Figure 5As shown, the fault early warning sub-platform is used to perform real-time analysis of the operating data. When at least one of the engine temperature, hydraulic system pressure, or transmission system vibration parameters exceeds a preset safety threshold, a fault early warning message is generated, and the warning level is determined according to the fault type and severity. The fault early warning sub-platform continuously receives and analyzes the operating data uploaded by each tractor, and monitors key parameters such as engine coolant temperature, hydraulic oil pressure, and transmission system vibration acceleration in real time. When at least one of the above parameters exceeds the corresponding preset safety threshold, a potential fault risk is determined, and a fault early warning message is generated. The fault early warning message includes the fault type (such as overheating, overpressure, abnormal vibration), the tractor number where the fault occurred, the time of the fault occurrence, and the corresponding parameter values. The warning level is divided into multiple levels according to the fault type and the severity of the parameter exceeding the threshold. Different levels correspond to different response strategies. High-level warnings simultaneously push alarm information to the user's mobile terminal 28 and the maintenance dispatch sub-platform.

[0101] like Figure 5 As shown, the maintenance dispatch sub-platform is used to automatically generate maintenance work orders based on the fault warning information. The maintenance work order includes a fault description, a list of required spare parts, and recommended maintenance personnel. The maintenance dispatch sub-platform is also used for intelligent work order matching based on the location information of the current user and the availability status of the recommended maintenance personnel. When the fault warning sub-platform generates fault warning information, the maintenance dispatch sub-platform automatically matches the corresponding maintenance plan according to the fault type, generating a maintenance work order containing a fault description, a list of required spare parts, and recommended maintenance personnel. The spare parts list is retrieved from the spare parts knowledge base according to the fault type, and recommended maintenance personnel are filtered based on their skills, qualifications, historical maintenance records, and current availability. Intelligent work order matching comprehensively considers the distance between the current location of the faulty tractor and the locations of available maintenance personnel, the current workload of the maintenance personnel, and the skill matching degree, selecting the optimal maintenance personnel for work order assignment and pushing the maintenance work order to the maintenance personnel's mobile terminal 28.

[0102] like Figure 5As shown, the maintenance closed-loop management sub-platform tracks the entire lifecycle status of maintenance work orders, from creation, dispatch, on-site repair to archiving and evaluation. After repair completion, the sub-platform links the repair record to the corresponding tractor's equipment file and the current operator's user file. The maintenance closed-loop management sub-platform tracks the entire lifecycle status of each maintenance work order, which sequentially goes through stages such as creation, dispatch, acceptance, on-site visit, on-site repair, repair completion, user confirmation, and archiving and evaluation. Each stage's status change is recorded with a timestamp and operator information. After repair completion, the repair personnel fill out a repair report on mobile terminal 28, including fault cause analysis, replacement parts details, repair time, and post-repair test results. The user confirms and evaluates the repair service through mobile terminal 28. After archiving and evaluation, the repair record is simultaneously linked to the corresponding tractor's equipment file (for tracing the equipment's full lifecycle maintenance history) and the current operator's user file (for analyzing the correlation between the user's operating habits and fault occurrence), forming a complete maintenance closed loop. The four sub-platforms work together to build a complete maintenance management chain, from data collection, anomaly detection, early warning push, work order creation, intelligent work order dispatch, on-site repair to archiving and evaluation, realizing the transformation of tractor maintenance management from passive response to proactive prevention.

[0103] It should be noted that the components or steps in the above embodiments can be interchanged, substituted, added, or deleted. Therefore, the combinations formed by these reasonable permutations and transformations should also fall within the protection scope of this invention, and the protection scope of this invention should not be limited to the above embodiments.

[0104] The parts of this invention not described in detail are prior art. It will be apparent to those skilled in the art that this invention is not limited to the details of the above exemplary embodiments, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be regarded as exemplary and non-limiting in all respects, and are intended to encompass all changes falling within the meaning and scope of equivalents within this invention.

Claims

1. A method for managing tractor users, characterized in that, Includes the following steps: S1. User authentication: In response to the user's authentication request, the user's identity is verified through multi-factor authentication to determine the identity information of the currently operating user; S2. Personalized configuration loading: Based on the identity information, retrieve the personalized configuration parameters bound to the current operating user from the preset user configuration database, and load the personalized configuration parameters into the tractor's electronic control system; S3. Multi-source working condition feature acquisition: During the operation of the tractor, multi-source working condition feature data are acquired in real time to construct the current working condition feature vector; S4. Adaptive matching and parameter adjustment of working conditions: The current working condition feature vector is matched and calculated with each standard working condition mode in the preset working condition mode library to determine the target working condition mode to which the current working condition belongs. Based on the target working condition mode and the preference weight of the current operator, the corresponding electronic control adjustment parameters are generated to adaptively adjust the power system and / or hydraulic system of the tractor. S5. Operation Information Recording and Synchronization: Records the current operation status data, operation parameters, and user behavior data during the current operation process and uploads them to the cloud data management platform.

2. The tractor user management method as described in claim 1, characterized in that, In step S3, the multi-source operating condition feature data includes: real-time vehicle speed. Engine load rate , power output shaft speed and rear suspension opening The construction of the current operating condition feature vector includes: normalizing the collected feature data of each operating condition to obtain a normalized feature vector. The normalized feature vector is subjected to sliding window filtering to remove outliers; wherein, when the deviation of a certain feature value from the mean of the sliding window exceeds a preset deviation threshold, the outlier is replaced by the mean of the sliding window.

3. The tractor user management method as described in claim 2, characterized in that, In step S4, the matching calculation includes: calculating the current working condition feature vector. With the first in the working condition mode library Standard operating mode Weighted Euclidean distance between them: in, For the first Matching weights corresponding to each working condition feature dimension. For the first The standard operating mode in the first Standard values ​​for each feature dimension; the matching degree is calculated based on the weighted Euclidean distance: The standard operating condition mode with the highest matching degree is selected as the candidate target operating condition mode; when the matching degree of the candidate target operating condition mode is... Greater than or equal to the preset matching threshold When the candidate target working condition mode is confirmed to be the target working condition mode to which the current working condition belongs; when the matching degree is less than the preset matching threshold If the current operating mode remains unchanged, an unrecognized operating mode prompt will be output.

4. The tractor user management method as described in claim 3, characterized in that, In step S4, generating the corresponding electronic control adjustment parameters based on the target operating mode and the current user's preference weights includes: obtaining the current user's preference weight vector. ,in , , , Let these represent the weights for economic preference, efficiency preference, work quality preference, and comfort preference, respectively, and satisfy the following conditions: ; The basic electronic control parameter set is determined based on the target operating mode, and the target engine speed, gearbox shifting strategy, and hydraulic system response rate in the basic electronic control parameter set are weighted and corrected based on the preference weight vector to generate the final electronic control adjustment parameters. The dynamic calibration of the preference weight vector includes: recording the number of times the current operator manually intervenes in the electronic control adjustment parameters during the operation; when the number of manual interventions accumulates to a preset intervention threshold within a preset statistical period, the preference weight vector is incrementally updated according to the direction and magnitude of the manual intervention, and the normalization constraint is re-executed.

5. The tractor user management method as described in claim 1, characterized in that, Step S4 further includes: When it is detected that the tractor receives an implement identification message sent by the attached implement via the ISOBUS bus, the corresponding target working condition mode is directly locked according to the implement type identifier in the implement identification message, and the matching degree is forcibly set to 100%, skipping the matching calculation step; When the ISOBUS bus communication is interrupted or the machine identification message verification fails, it automatically degrades to the matching calculation mode based on the multi-source working condition feature data. Step S4 further includes anti-jump processing: when the target operating condition modes calculated in two consecutive sampling periods are inconsistent, only when the matching degree of the new target operating condition mode is continuous... Each sampling period is greater than the preset matching threshold. When switching operating modes, the process is as follows: This is the preset number of confirmation cycles.

6. The tractor user management method as described in claim 1, characterized in that, In step S1, the multi-factor authentication method includes at least two of RFID radio frequency identification, PIN code verification, and facial recognition; The user authentication also includes hierarchical access control: The permission level is determined based on the identity information of the currently operating user, and the permission level includes: Static operation permissions correspond to permissions granted only through RFID radio frequency identification authentication, allowing entry and exit from the driver's cab and static operations; Routine operation permissions are granted through a combination of RFID radio frequency identification and facial recognition authentication, allowing the execution of routine field operations. Special operating permissions, which correspond to a combination of facial recognition and PIN code verification, allow the execution of agricultural machinery repair and cross-regional operations; When the authentication method of the current user does not meet the authentication combination required by its permission level, the execution of the corresponding function is restricted and an insufficient permission prompt is output.

7. The tractor user management method as described in claim 1, characterized in that, In step S2, the personalized configuration parameters include at least one of the following: seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​for operating parameters; it also includes a cross-device configuration migration step: When the current user authenticates their identity on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform, and after decryption and verification, it is loaded into the electronic control system of the second tractor. The encrypted configuration data is encrypted and stored using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user.

8. The tractor user management system as described in claim 1, characterized in that, include: The user identification module is used to respond to the user's authentication request, verify the user's identity through multi-factor authentication, and determine the identity information of the currently operating user. The personalized configuration module is used to retrieve the personalized configuration parameters bound to the current operating user from the preset user configuration database based on the identity information, and load the personalized configuration parameters into the tractor's electronic control system; The working condition acquisition module is used to collect multi-source working condition feature data in real time during the operation of the tractor and construct the current working condition feature vector. The working condition matching and adjustment module is used to match and calculate the current working condition feature vector with each standard working condition mode in the preset working condition mode library, determine the target working condition mode to which the current working condition belongs, and generate corresponding electronic control adjustment parameters according to the target working condition mode and the preference weight of the current operator, so as to adaptively adjust the power system and / or hydraulic system of the tractor. The job information management module is used to record the working condition data, operation parameters and user behavior data during the current job process, and upload them to the cloud data management platform.

9. The tractor user management system as described in claim 8, characterized in that, The user identification module includes at least two of the following: an RFID radio frequency identification unit, a PIN code verification unit, and a face recognition unit; The user identification module is also used to perform hierarchical access control, specifically including: The user's permission level is determined based on their current identity information. The permission levels include static operation permission, regular operation permission, and special operation permission. Static operation permission corresponds to authentication only through the RFID radio frequency identification unit. Regular operation permission corresponds to authentication through a combination of the RFID radio frequency identification unit and the face recognition unit. Special operation permission corresponds to authentication through a combination of the face recognition unit and the PIN code verification unit. The user identification module is also used to restrict the execution of the corresponding function and output an insufficient permission prompt when the authentication method of the current operating user does not meet the authentication combination required by its permission level. The personalized configuration parameters in the personalized configuration module include at least one of the following: seat position parameters, rearview mirror angle parameters, air conditioning temperature parameters, instrument panel display layout parameters, and preset values ​​for operating parameters. The personalized configuration module is also used to perform cross-device configuration migration: when the current user authenticates on the second tractor, the encrypted configuration data of the current user is downloaded from the cloud data management platform, and after decryption and verification, it is loaded into the electronic control system of the second tractor; the encrypted configuration data is encrypted and stored using the SM4 symmetric encryption algorithm, and the key is bound to the identity information of the current user.

10. The tractor user management system as described in claim 8, characterized in that, The cloud-based data management platform includes: The data storage sub-platform is used to encrypt and store the uploaded working condition data, operation parameters and user behavior data, and to establish a multi-dimensional data index with the user identity as the primary key. The fault warning sub-platform is used to perform real-time analysis of the operating condition data. When at least one of the engine temperature, hydraulic system pressure, or transmission system vibration parameters is detected to exceed a preset safety threshold, fault warning information is generated, and the warning level is determined according to the fault type and severity. The maintenance dispatch sub-platform is used to automatically generate maintenance work orders based on the fault warning information. The maintenance work order includes a fault description, a list of required spare parts, and recommended maintenance personnel. The maintenance dispatch sub-platform is also used to intelligently dispatch work orders based on the location information of the current user and the availability status of the recommended maintenance personnel. The maintenance closed-loop management sub-platform is used to track the entire lifecycle status of the maintenance work order from creation, dispatch, on-site repair to archiving and evaluation, and to associate the repair record with the equipment file of the corresponding tractor and the user file of the current operator after the repair is completed.

Images