Multi-level authority management tower crane remote control method and system

Abstract

The embodiment of the invention provides a multistage authority management tower crane remote control method and system, and belongs to the technical field of tower crane operation control. The method comprises the following steps: obtaining an association permission of an initial user; collecting target image data when the target tower crane transports the target object under the current operation parameters; performing target tracking on the target object according to the target image data to obtain target position information of the target object; identifying a transportation state of the target object according to the target position information and the target image data to obtain a target transportation state corresponding to the target object; adjusting the current operation parameter according to the target transportation state to obtain a target operation parameter, and determining a target adjustment strategy corresponding to the target operation parameter; determining a target permission corresponding to the target adjustment strategy according to the permission mapping table, and determining a target user corresponding to the target adjustment strategy according to the target permission and the associated permission; and determining a target control result corresponding to the target tower crane according to the target user and the target adjustment strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of tower crane operation control, and in particular to a tower crane remote control method and system with multi-level authority management. Background Art

[0002] As a key equipment on a construction site, the safe operation of a tower crane is crucial to the overall safety of the construction site. However, during the operation of a tower crane, the risk of operation by non-professionals or non-related personnel under different conditions is extremely high, and thus the safety of the construction site and the normal operation of the equipment cannot be guaranteed. In order to ensure the safe and efficient operation of the tower crane, the training and authorization system for professional operators must be strictly implemented, and unauthorized outsiders are strictly prohibited from operating the tower crane. However, in the actual construction process, the authority requirements may change at any time. The existing technology still has deficiencies in distinguishing the staff who need corresponding authority to operate under different conditions, and thus cannot meet the requirements of dynamic authority management, reducing the flexibility and safety of tower crane operation. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a tower crane remote control method and system with multi-level authority management, aiming to solve the problem that there are still deficiencies in the related technology in distinguishing the operations of staff who need corresponding permissions under different conditions, and thus cannot meet the requirements of dynamic authority management, reducing the flexibility and safety of tower crane operations.

[0004] In a first aspect, an embodiment of the present invention provides a tower crane remote control method with multi-level authority management, comprising: Receiving user information input by an initial user, and reviewing the identity corresponding to the initial user according to the user information, to obtain a review result corresponding to the initial user; When the audit result is approved, the associated permissions corresponding to the initial user are obtained; Collecting target image data corresponding to the target tower crane transporting the target object under the current operating parameters; Tracking the target object according to the target image data to obtain target position information corresponding to the target object; Identify the transportation state of the target object according to the target position information and the target image data, and obtain the target transportation state corresponding to the target object; Adjusting the current operating parameters according to the target transportation state to obtain target operating parameters, and determining a target adjustment strategy corresponding to the target operating parameters; Determine the target permission corresponding to the target adjustment policy according to the permission mapping table, and determine the target user corresponding to the target adjustment policy according to the target permission and the associated permission; A target control result corresponding to the target tower crane is determined according to the target user and the target adjustment strategy.

[0005] In a second aspect, an embodiment of the present invention provides a tower crane remote control system with multi-level authority management, including: An identity verification module is used to receive user information input by an initial user, and verify the identity corresponding to the initial user according to the user information to obtain a verification result corresponding to the initial user; A permission obtaining module, used for obtaining the associated permissions corresponding to the initial user when the audit result is passed; A data acquisition module is used to acquire target image data corresponding to when the target tower crane transports the target object under current operating parameters; A target tracking module, used to track the target object according to the target image data, and obtain target position information corresponding to the target object; A state recognition module, used to recognize the transportation state of the target object according to the target position information and the target image data, and obtain the target transportation state corresponding to the target object; A strategy determination module, configured to adjust the current operating parameters according to the target transportation state, obtain target operating parameters, and determine a target adjustment strategy corresponding to the target operating parameters; A permission determination module, used to determine the target permission corresponding to the target adjustment policy according to the permission mapping table, and determine the target user corresponding to the target adjustment policy according to the target permission and the associated permission; The target control module is used to determine the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy.

[0006] The embodiment of the present invention provides a tower crane remote control method and system with multi-level authority management, the method comprising: receiving user information input by an initial user, and auditing the identity corresponding to the initial user according to the user information, and obtaining the audit result corresponding to the initial user; when the audit result is that the audit is passed, obtaining the associated authority corresponding to the initial user; collecting target image data corresponding to the target tower crane when transporting a target object under current operating parameters; tracking the target object according to the target image data, and obtaining the target position information corresponding to the target object; identifying the transportation state of the target object according to the target position information and the target image data, and obtaining the target transportation state corresponding to the target object; adjusting the current operating parameters according to the target transportation state, obtaining the target operating parameters, and determining the target adjustment strategy corresponding to the target operating parameters; determining the target authority corresponding to the target adjustment strategy according to the authority mapping table, and determining the target user corresponding to the target adjustment strategy according to the target authority and the associated authority; determining the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy. The method ensures that only the authorized initial user can operate the tower crane by reviewing the identity and associated permissions of the initial user, thereby reducing the risk of unauthorized operation. The method then achieves real-time tracking of the target object by collecting and analyzing target image data, thereby ensuring accuracy and safety during transportation. The target transportation status of the target object is then identified through target position information and target image data, thereby timely discovering abnormal situations and making adjustments. The current operating parameters of the target tower crane are then dynamically adjusted according to the target transportation status of the target object, the operating process is optimized, and efficiency and safety are improved. The target operating parameters are then obtained, and the target adjustment strategy corresponding to the target operating parameters is then obtained. The target permissions corresponding to the target adjustment strategy are then determined according to the permission mapping table, and the target user who executes the target adjustment strategy is determined in combination with the associated permissions of the initial user. The final control result of the target tower crane is then determined according to the target user and the target adjustment strategy, thereby ensuring accuracy and safety of the operation. The method solves the problem that the related technologies still have deficiencies in distinguishing the operations of staff members who need corresponding permissions under different situations, and cannot meet the requirements of dynamic permission management, thereby reducing the flexibility and safety of tower crane operations and improving the flexibility and safety of tower crane operations. The method also significantly improves the accuracy and safety of tower crane operations through identity authentication, real-time monitoring, dynamic adjustment and permission matching, optimizes the operation process, improves work efficiency, and significantly improves the safety and efficiency of operations, thus meeting the needs of modern construction projects for efficient and safe operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0008] Figure 1 A flowchart of a tower crane remote control method with multi-level authority management provided by an embodiment of the present invention; Figure 2 A schematic diagram of the module structure of a tower crane remote control system with multi-level authority management provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0011] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0012] The embodiment of the present invention provides a tower crane remote control method and system with multi-level authority management. The tower crane remote control method with multi-level authority management can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0013] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0014] Please refer to Figure 1 , Figure 1 A schematic flow chart of a tower crane remote control method with multi-level authority management provided by an embodiment of the present invention.

[0015] like Figure 1 As shown, the tower crane remote control method with multi-level authority management includes steps S101 to S108.

[0016] Step S101: receiving user information input by an initial user, and verifying the identity corresponding to the initial user according to the user information to obtain a verification result corresponding to the initial user.

[0017] Exemplarily, user information corresponding to the initial user is obtained from the user interface, the user information includes an ID number or a unique identifier, and password information corresponding to the ID number or the unique identifier, and the user information may also include facial information or fingerprint information, and then the identity corresponding to the initial user is audited based on the user information to obtain an audit result corresponding to the initial user. The audit result is one of passing the audit or failing the audit.

[0018] For example, user information is submitted to an identity verification system or a third-party authentication service (such as an ID card verification API) for verification to obtain the audit results.

[0019] Step S102: When the audit result is passed, the associated authority corresponding to the initial user is obtained.

[0020] Exemplarily, when the audit result is passed, the identity of the initial user (such as an ordinary operator, technical supervisor or safety administrator) can be confirmed, and the associated permissions corresponding to the initial user can be obtained. The associated permissions include but are not limited to the initial user being able to operate the operating components of the tower crane or access the tower crane status information, modify key parameters of the tower crane, etc.

[0021] For example, if the initial user is a general operator, the associated permissions are that the initial user may be authorized to operate specific parts of the tower crane, such as the lifting mechanism, luffing mechanism, slewing mechanism and walking mechanism, or the associated permissions are that the initial user can view the real-time status information of the tower crane, such as the current position, load condition, working hours, etc. For example, if the initial user is a technical supervisor, the associated permissions are that the initial user is allowed to modify certain key parameters of the tower crane to adapt to different working environments or task requirements, which may include operating speed, working range restrictions, etc. For example, if the initial user is a safety administrator, the associated permissions are that the initial user is allowed to take over control or make system settings in an emergency.

[0022] Exemplarily, when the audit result is that the audit fails, the initial user is required to re-enter the user information until the audit result is that the audit passes.

[0023] Step S103: collecting target image data corresponding to when the target tower crane transports the target object under the current operating parameters.

[0024] Exemplarily, the specific operation scenario and target object of the target tower crane are determined. For example, the target tower crane is carrying construction materials, and the target object can be construction materials. Therefore, a suitable location is selected around the target tower crane to install the camera to ensure that the image of the target tower crane and the target object can be clearly captured. The installation location of the camera should take into account the viewing angle, light conditions and occlusion. Therefore, according to the acquisition requirements, the shooting parameters of the camera, such as resolution, frame rate, exposure time, etc., are configured to ensure the image quality and data accuracy. At the same time, ensure that the camera can automatically adjust the parameters according to the lighting conditions.

[0025] For example, when the target tower crane starts to transport the target object, the camera is started to collect images of the target object, thereby obtaining target image data. The target image data includes but is not limited to the collection time and the image information corresponding to the collection time.

[0026] Step S104: Track the target object according to the target image data to obtain target position information corresponding to the target object.

[0027] Exemplarily, the collected target image data is preprocessed to improve image quality and facilitate subsequent processing. The preprocessing step may include denoising, image enhancement, contrast adjustment, etc. According to the characteristics of the target object such as shape, color, motion characteristics, etc., the target algorithm is determined from the target tracking algorithm such as the algorithm based on feature matching, the template-based matching algorithm, and the algorithm based on deep learning, and then the target image is tracked according to the target algorithm and the target image data, so as to obtain the target position information corresponding to the target object. The target position information is the position information of the target object in the target image data.

[0028] In some embodiments, the target tracking of the target object according to the target image data to obtain target position information corresponding to the target object includes: using a first target tracking model to track the target object in the target image data to obtain first position information corresponding to the target object; using a second target tracking model to track the target object in the target image data to obtain second position information corresponding to the target object; performing union calculation on the first position information and the second position information to obtain maximum position information corresponding to the target object; obtaining a target area image corresponding to the target object from the target image data according to the maximum position information; performing target recognition on the target area image to obtain target edge information corresponding to the target object in the target area image; and determining the target position information corresponding to the target object according to the target edge information and the target image data.

[0029] Exemplarily, a first target tracking model such as a deep learning-based model is determined, and then the collected target image data is input into the first target tracking model to obtain first position information corresponding to the target object.

[0030] Exemplarily, a second target tracking model different from the first target tracking model is determined. The second target tracking model may also be based on a deep learning model, but the model structure is different from the first target tracking model. The same target image data is input into the second target tracking model, and then the second target tracking model is used to track the target object in the target image data, and output the second position information of the target object.

[0031] Exemplarily, the first position information and the second position information are combined to obtain the maximum position information of the target object. The purpose of the combination calculation is to combine the results of the first target tracking model and the second target tracking model to provide support for obtaining more accurate target position information later.

[0032] Exemplarily, the maximum position information is used to intercept image data from the target image data to obtain a target region image corresponding to the target image data under the maximum position information, thereby performing target recognition on the extracted target region image to determine target edge information of the target object in the target region image.

[0033] Exemplarily, the minimum bounding rectangle of the target edge information is calculated to obtain a target matrix corresponding to the target edge information, and then the target rectangle is placed in the target image data to obtain the rectangular position information of the target rectangle in the target image data, and the rectangular position information is determined as the target position information of the target object.

[0034] Specifically, the above steps can improve the accuracy and robustness of target tracking and position recognition, ensuring accurate tracking and recognition of target objects in complex environments and dynamic changes.

[0035] In some embodiments, the use of the first target tracking model to track the target object in the target image data to obtain the first position information corresponding to the target object includes: when the target image information is a preset frame, using the template determination layer of the first target tracking model to obtain the target template corresponding to the target object in the target image information; when the target image information is not the preset frame, obtaining the associated feature information corresponding to the previous frame image corresponding to the target image information, and using the template update layer of the first target tracking model to determine the target reliability corresponding to the target template according to the associated feature information, and updating the target template according to the target reliability to obtain the updated target template; using the The deep feature extraction layer of the first target tracking model performs feature extraction on the target image data according to the target template to obtain initial feature information; the multi-template attention mechanism layer of the target tracking model performs multi-dimensional attention feature extraction on the initial feature information to obtain attention feature information; the shallow feature extraction layer of the first target tracking model performs feature extraction on the target image data according to the target template to obtain shallow feature information; the feature fusion layer of the first target tracking model performs weighted fusion on the attention feature information and the shallow feature information to obtain target feature information; the target prediction layer of the first target tracking model performs target recognition according to the target feature information to obtain the first position information corresponding to the target object.

[0036] Exemplarily, first determine whether the current target image information is a preset frame (such as the first frame). If it is a preset frame, use the template determination layer of the first target tracking model to extract the target template corresponding to the target object from the target image information. If the target image information is not a preset frame, obtain the associated feature information corresponding to the previous frame image, and then use the template update layer of the first target tracking model to determine the target reliability of the target template according to the associated feature information. Update the target template based on the target reliability to obtain an updated target template.

[0037] For example, the maximum value and the minimum value in the associated feature information are obtained, and then the square value of the first difference between the maximum value and the minimum value is calculated to obtain the first data, and then the square value of the second difference between each data in the associated feature information and the minimum value is summed and averaged to obtain the second data, and then the target reliability of the target template is obtained according to the ratio between the first data and the second data. When the target reliability is greater than the historical mean reliability of the target template, the target template is updated to obtain an updated target template.

[0038] Exemplarily, the deep feature extraction layer of the first target tracking model is used to perform feature extraction on the target image data according to the updated target template to obtain initial feature information, and then the multi-template attention mechanism layer of the first target tracking model is used to perform multi-dimensional attention feature extraction on the initial feature information to obtain attention feature information, and the shallow feature extraction layer of the first target tracking model is used to perform feature extraction on the target image data according to the target template to obtain shallow feature information, and then the feature fusion layer of the first target tracking model is used to perform weighted fusion of the attention feature information and the shallow feature information to obtain target feature information, and finally the target prediction layer of the first target tracking model is used to perform target recognition according to the target feature information to obtain the first position information corresponding to the target object.

[0039] Specifically, the above scheme uses the first target tracking model to track the target object in the target image information and outputs the first position information of the target object. This method combines multiple links such as template determination, feature extraction, attention mechanism and feature fusion to ensure the accuracy and robustness of target tracking.

[0040] In some embodiments, the use of a second target tracking model to track the target object in the target image data to obtain second position information corresponding to the target object includes: obtaining a first hash feature and a first color feature corresponding to the previous frame image corresponding to the target image information under the target template; obtaining an image position corresponding to the target object in the previous frame image, and sliding the target image information according to the image position and the target template to obtain a target area; performing feature extraction on the target area to obtain a second hash feature and a second color feature corresponding to the target area; obtaining a first similarity corresponding to the target area according to the first hash feature and the second hash feature; obtaining a second similarity corresponding to the target area according to the first color feature and the second color feature; fusing the first similarity and the second similarity to determine a target similarity corresponding to the target area; and determining the second position information corresponding to the target object in the target image data according to the target similarity.

[0041] Exemplarily, the previous frame image corresponding to the target image data is obtained, and then the associated region corresponding to the target object is obtained according to the image position corresponding to the previous frame image, and then the first hash feature is extracted from the associated region using a feature extraction algorithm (such as local binary pattern (LBP), histogram of oriented gradients (HOG), etc.). A color feature extraction algorithm (such as color histogram, color moment, etc.) is used on the associated region to obtain the first color feature extracted from the previous frame image under the target template from the associated region.

[0042] Exemplarily, the image position (such as the center point or bounding box) of the target object in the previous frame of the image is obtained, and then the target template is slid in the target image information with the image position of the target object as the reference position to determine the target area. Thus, a feature extraction algorithm (such as local binary pattern (LBP), histogram of oriented gradients (HOG), etc.) is used to extract the second hash feature from the target area. A color feature extraction algorithm (such as color histogram, color moment, etc.) is used on the target area to obtain the second color feature corresponding to the target area.

[0043] Exemplarily, the first similarity between the target region and the associated region is calculated using the first hash feature and the second hash feature according to the cosine similarity, and the second similarity between the target region and the associated region is calculated using the first color feature and the second color feature according to the cosine similarity, and finally the first similarity and the second similarity are weightedly fused to determine the corresponding target similarity between the target region and the associated region.

[0044] Exemplarily, multiple target areas are obtained by sliding in the target image information in sequence according to the image position and the target template, and then the target similarity corresponding to each target area is obtained according to the above steps, and then the target area corresponding to the maximum target similarity is obtained, and then the position information of the target area corresponding to the maximum target similarity in the target image information is obtained, and then the position information is determined as the second position information corresponding to the target object.

[0045] In some embodiments, feature extraction is performed on the target area to obtain a second hash feature corresponding to the target area, including: graying the target area to obtain a gray area, and performing pixel mean processing on the gray area to obtain a first pixel mean; performing pixel mean processing on the first pixel information corresponding to each row in the gray area to obtain a second pixel mean, and performing pixel mean processing on the second pixel information corresponding to each column in the gray area to obtain a third pixel mean; arranging the gray area from left to right and from top to bottom to obtain a target sequence, comparing two adjacent data in the target sequence to obtain a first comparison result; determining adjacent hash features corresponding to the gray area according to the first comparison result; comparing the second pixel means corresponding to two adjacent first pixel information in the gray area to obtain a second comparison result, and determining the corresponding pixel information of the gray area according to the second comparison result. adjacent row hash features; comparing the third pixel means corresponding to two adjacent second pixel information in the grayscale area to obtain a third comparison result, and determining the adjacent column hash features corresponding to the grayscale area according to the third comparison result; comparing the second pixel mean corresponding to the first pixel information in the grayscale area with the first pixel mean to obtain a fourth comparison result, and determining the first mean hash feature corresponding to the grayscale area according to the fourth comparison result; comparing the third pixel mean corresponding to the second pixel information in the grayscale area with the first pixel mean to obtain a fifth comparison result, and determining the second mean hash feature corresponding to the grayscale area according to the fifth comparison result; feature splicing the adjacent hash features, the adjacent row hash features, the adjacent column hash features, the first mean hash features and the second mean hash features to obtain the second hash features corresponding to the target area.

[0046] Exemplarily, the target region image is converted into a grayscale image, and then the grayscale region corresponding to the target region in the grayscale image is obtained, thereby reducing the influence of gray color information in the hash feature.

[0047] Exemplarily, all pixels in the grayscale area are averaged to calculate the first pixel mean of the grayscale area, and then the first pixel information corresponding to each row in the grayscale area is averaged to obtain the second pixel mean of each row, and the second pixel information corresponding to each column in the grayscale area is averaged to obtain the third pixel mean of each column.

[0048] Exemplarily, the grayscale area is arranged from left to right and from top to bottom to form a target sequence, so that two adjacent data in the target sequence are compared to obtain a first comparison result. The first comparison result can be a difference or size characterization relationship of adjacent pixel values, where the size characterization relationship is that the first pixel value is greater than the second pixel value to the right of the first pixel value, or the first pixel value is less than or equal to the second pixel value to the right of the first pixel value.

[0049] Exemplarily, the adjacent hash feature corresponding to the grayscale region is determined according to the first comparison result. The adjacent hash feature reflects the association between adjacent pixels in the grayscale region. For example, when the first comparison result is that the first pixel value is greater than the second pixel value on the right side of the first pixel value, it is represented by a first eigenvalue of 1 or other numerical values, and when the first comparison result is that the first pixel value is less than or equal to the second pixel value on the right side of the first pixel value, it is represented by a second eigenvalue of 0 or other numerical values, thereby obtaining the adjacent hash feature according to the first comparison result.

[0050] Exemplarily, the second pixel means corresponding to two adjacent first pixel information in the grayscale area are compared to obtain a second comparison result, and the adjacent row hash feature corresponding to the grayscale area is determined according to the second comparison result. For example, when the second comparison result is that the second pixel mean of the current row is greater than the second pixel mean of the next row of the current row, it is represented by a third eigenvalue of 1 or other numerical values, and when the second comparison result is that the second pixel mean of the current row is less than or equal to the second pixel mean of the next row of the current row, it is represented by a fourth eigenvalue of 0 or other numerical values. Thus, the adjacent row hash feature is obtained according to the second comparison result.

[0051] Exemplarily, the third pixel means corresponding to two adjacent second pixel information in the grayscale area are compared to obtain a third comparison result, and the adjacent column hash feature corresponding to the grayscale area is determined according to the third comparison result. For example, when the third comparison result is that the third pixel mean of the current column is greater than the third pixel mean of the next column of the current column, the fifth eigenvalue 1 or other numerical value is used to represent it, and when the third comparison result is that the third pixel mean of the current column is less than or equal to the third pixel mean of the next column of the current column, the sixth eigenvalue 0 or other numerical value is used to represent it. Thus, the adjacent column hash feature is obtained according to the third comparison result.

[0052] Exemplarily, the second pixel mean corresponding to the first pixel information in the grayscale area is compared with the first pixel mean to obtain a fourth comparison result, and the first mean hash feature corresponding to the grayscale area is determined according to the fourth comparison result. For example, when the fourth comparison result is that the second pixel mean of the current row is greater than the first pixel mean, the seventh eigenvalue 1 or other numerical value is used to represent it, and when the fourth comparison result is that the second pixel mean of the current row is less than or equal to the first pixel mean, the eighth eigenvalue 0 or other numerical value is used to represent it. Thus, the first mean hash feature is obtained according to the fourth comparison result.

[0053] Exemplarily, the third pixel mean corresponding to the second pixel information in the grayscale area is compared with the first pixel mean to obtain a fifth comparison result, and the second mean hash feature corresponding to the grayscale area is determined according to the fifth comparison result. For example, when the fifth comparison result is that the third pixel mean of the current row is greater than the first pixel mean, the ninth eigenvalue 1 or other numerical value is used to represent it, and when the fifth comparison result is that the third pixel mean of the current column is less than or equal to the first pixel mean, the tenth eigenvalue 0 or other numerical value is used to represent it. Thus, the second mean hash feature is obtained according to the fifth comparison result.

[0054] Exemplarily, adjacent hash features, adjacent row hash features, adjacent column hash features, the first mean hash feature, and the second mean hash feature are concatenated to obtain a second hash feature corresponding to the target area.

[0055] Specifically, the above steps can effectively extract the key hash features of the target area, providing accurate and rich feature information for subsequent target tracking and recognition. This method combines multiple technologies such as grayscale processing, pixel mean calculation, sequence comparison and feature splicing to ensure the comprehensiveness and robustness of feature extraction.

[0056] Step S105 : identifying the transportation status of the target object according to the target position information and the target image data, and obtaining the target transportation status corresponding to the target object.

[0057] Exemplarily, the transportation state of the target object is abnormally identified based on the target position information and the target image data, thereby obtaining the target transportation state corresponding to the target object.

[0058] In some embodiments, the identifying the transportation status of the target object according to the target position information and the target image data to obtain the target transportation status corresponding to the target object includes: determining the real position information corresponding to the target object according to the target position information and the target image information; determining the target change amount corresponding to the target object according to the real position information, and determining the target change sequence corresponding to the target object at the current moment according to the target change amount; performing data clustering on the target change sequence to obtain an initial clustering result, and analyzing the clustering reliability between clustering clusters in the initial clustering result to obtain a target reliability value corresponding to the initial clustering result; adjusting the initial clustering result according to the target reliability value to obtain a target clustering result; obtaining the historical clustering result of the target object at the previous moment corresponding to the current moment, and identifying the transportation status of the target object according to the historical clustering result and the target clustering result to obtain the target transportation status corresponding to the target object.

[0059] Exemplarily, the camera calibration technology is used to obtain the camera intrinsic parameter matrix and camera extrinsic parameter matrix corresponding to the camera, and then the pixel coordinates of the target object are converted to the camera coordinate system according to the camera intrinsic parameter matrix based on the target position information and target image information, and then the coordinates in the camera coordinate system are converted into coordinates in the world coordinate system using the camera extrinsic parameter matrix to obtain the real position information of the target object.

[0060] Exemplarily, based on the real position information of the target object, the position change (such as speed, moving distance, etc.) of the target object between the current moment and the previous moment is calculated, so as to generate a target change sequence corresponding to the target object at the current moment based on the target change at consecutive moments.

[0061] Exemplarily, a clustering algorithm (such as K-means, DBSCAN, etc.) is used to cluster the target change sequence to obtain an initial clustering result, and then the clustering reliability between the clusters in the initial clustering result is analyzed to calculate the distance information between each cluster, so as to obtain the target reliability value corresponding to the initial clustering result according to the distance information. Then, according to the target reliability value, the initial clustering result is adjusted to optimize the division of clusters and obtain the target clustering result.

[0062] Exemplarily, the historical clustering result of the target object at the previous moment corresponding to the current moment is obtained, and the first cluster center corresponding to the historical clustering result is obtained, and the second cluster center corresponding to the target clustering result is obtained, so as to calculate the center distance between the first cluster center and the second cluster center according to the Euclidean distance or the Manhattan distance, and set a larger first preset distance to detect whether the target object has a problem of moving too fast or moving too fast. Set a smaller second preset distance to detect whether the target object has a problem of moving too slow or moving too slowly. When the center distance is greater than the first preset distance, it is determined that the target object has a problem of moving too fast or moving too fast, and the transportation state of the target object is determined to be abnormal transportation. When the center distance is between the first preset distance and the second preset distance, it is determined that the target object moves normally, and the transportation state of the target object is determined to be normal transportation. When the center distance is less than the second preset distance, it is determined that the target object has a problem of moving too slow or moving too slowly, and the transportation state of the target object is determined to be abnormal transportation.

[0063] Exemplarily, the center distance can indicate whether the target clustering result has significant changes relative to the historical clustering result. If the target clustering result has significant changes relative to the historical clustering result, it indicates that the target transportation state corresponding to the target object is transportation abnormality.

[0064] In some embodiments, the analyzing the clustering reliability between clustering clusters in the initial clustering result to obtain the target reliability value corresponding to the initial clustering result includes: calculating the first distance between each target change amount in the target change sequence and the cluster center corresponding to each clustering cluster; calculating the second distance between the cluster centers corresponding to any two clustering clusters; fusing the first distance and the second distance to determine the target reliability value corresponding to the initial clustering result; wherein the target reliability value is obtained according to the following formula:

[0065] in, represents the target reliability value, represents the adjustment factor, n represents the number of targets corresponding to the target change sequence, m represents the number of clusters corresponding to the cluster clusters in the initial clustering result, represents the first distance between the j-th target change amount in the target change sequence and the cluster center corresponding to the i-th cluster, represents the second distance between the cluster center corresponding to the i-th cluster and the cluster center corresponding to the p-th cluster, and k represents a weighted index.

[0066] Exemplarily, the first distance is obtained by calculating the Euclidean distance between each target change amount in the target change sequence and the cluster center corresponding to each cluster cluster. The first distance reflects the proximity of each target change amount to each cluster center. The second distance is obtained by calculating the Euclidean distance between the cluster centers corresponding to any two cluster clusters. The second distance reflects the degree of separation between different cluster centers.

[0067] Exemplarily, the target reliability value corresponding to the initial clustering result is obtained by fusing the first distance and the second distance according to the following formula. This formula comprehensively considers the closeness between the target change amount and the cluster center and the separation between the cluster centers, and then obtains the target reliability value according to the following formula:

[0068] in, represents the target reliability value, represents the adjustment factor, n represents the number of targets corresponding to the target change sequence, m represents the number of clusters corresponding to the clustering clusters in the initial clustering result, It represents the first distance between the jth target change in the target change sequence and the cluster center corresponding to the i-th cluster. represents the second distance between the cluster center corresponding to the i-th cluster and the cluster center corresponding to the p-th cluster, and k represents the weighted index.

[0069] Exemplarily, by fusing the first distance between the target change and the cluster center and the second distance between the cluster centers, the distribution of the target change and the degree of separation between the clusters are comprehensively considered, thereby improving the reliability of the clustering results. Relying solely on a single factor (such as the distance between the target change and the cluster center) may not be able to fully reflect the quality of the clustering results. By fusing multiple factors, the limitations of a single factor are avoided and the accuracy of the clustering results is improved. Thus, by calculating the target reliability value, the quality of the clustering results can be quantified, providing a more reliable basis for subsequent data analysis and decision-making, and then the clustering strategy can be optimized according to the target reliability value, further improving the clustering effect and enhancing the data-driven decision-making ability, thereby providing a more reliable basis for subsequent data analysis and decision-making.

[0070] In some embodiments, the identifying the transportation status of the target object based on the target position information and the target image data to obtain the target transportation status corresponding to the target object includes: determining the real position information corresponding to the target object based on the target position information and the target image information; performing path fitting based on the real position information to obtain a target fitting path corresponding to the target object; performing path prediction on the current operating parameters of the target object using a path prediction model to obtain a target predicted path corresponding to the target object; determining the path deviation between the target fitting path and the target predicted path, and determining the target transportation status corresponding to the target object based on the path deviation.

[0071] Exemplarily, the camera calibration technology is used to obtain the camera intrinsic parameter matrix and camera extrinsic parameter matrix corresponding to the camera, and then the pixel coordinates of the target object are converted into the camera coordinate system according to the camera intrinsic parameter matrix based on the target position information and the target image information, and then the coordinates in the camera coordinate system are converted into coordinates in the world coordinate system using the camera extrinsic parameter matrix to obtain the real position information of the target object, thereby obtaining the real position information of the target object over a period of time, and then using a path fitting algorithm (such as polynomial fitting, spline curve fitting, etc.) to fit the real position information to obtain the target fitting path corresponding to the target object.

[0072] Exemplarily, the path prediction model is used to predict the target predicted path corresponding to the target object under the current operating parameters according to the current operating parameters and the initial position information of the target object. Thus, the target fitting path and the target predicted path are compared, and the path deviation between the two is calculated, such as the Euclidean distance, the Manhattan distance, etc., and then the target transportation state of the target object is evaluated according to the size of the path deviation.

[0073] Exemplarily, when the path deviation is greater than a set threshold, the transportation state of the target object is determined to be abnormal transportation. When the path deviation is less than or equal to the set threshold, the transportation state of the target object is determined to be normal transportation.

[0074] Specifically, the above steps not only realize the accurate monitoring and anomaly detection of the transportation status of the target object, but also provide strong support for the management and optimization of the transportation process, significantly improving the efficiency, reliability and safety of the transportation process.

[0075] Step S106: adjusting the current operating parameters according to the target transportation state to obtain target operating parameters, and determining a target adjustment strategy corresponding to the target operating parameters.

[0076] Exemplarily, the target transportation state of the target object includes two situations: normal transportation and abnormal transportation. When the target transportation state is abnormal transportation caused by too fast transportation, the parameters for the transportation speed in the current operation parameters are adjusted to obtain the target operation parameters. When the target transportation state is abnormal transportation caused by too slow transportation, the parameters for the transportation speed in the current operation parameters are adjusted to obtain the target operation parameters; when the target transportation state is abnormal transportation caused by the transportation path being inconsistent with the preset, the parameters for the transportation path in the current operation parameters are adjusted to obtain the target operation parameters.

[0077] Exemplarily, the target adjustment strategy is obtained from a strategy database according to the difference between the current operating parameters and the target operating parameters.

[0078] Step S107: determining the target permission corresponding to the target adjustment policy according to the permission mapping table, and determining the target user corresponding to the target adjustment policy according to the target permission and the associated permission.

[0079] Exemplarily, a permission mapping table is set according to historical experience or expert experience, and then a query is performed from the permission mapping table according to the target adjustment policy, so as to obtain the target permission corresponding to the target adjustment policy.

[0080] Exemplarily, the target permission and the associated permission are intersected to obtain the target user corresponding to each policy in the target adjustment policy.

[0081] Step S108: determining a target control result corresponding to the target tower crane according to the target user and the target adjustment strategy.

[0082] Exemplarily, the target adjustment strategy is sent to a terminal device corresponding to the target user, and then the target user operates the target tower crane according to the target adjustment strategy, thereby obtaining a target control result corresponding to the target tower crane.

[0083] In some embodiments, after determining the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy, the method also includes: determining the occurrence frequency corresponding to the target authority in the target adjustment strategy, and determining a first adjustment priority corresponding to the target adjustment strategy according to the occurrence frequency; determining the target danger level corresponding to the target adjustment strategy, and determining a second adjustment priority corresponding to the target adjustment strategy according to the target danger level; adjusting the target authority of the target adjustment policy according to the first adjustment priority and the second adjustment priority to obtain the optimized authority corresponding to the target adjustment strategy; modifying the authority mapping table according to the optimized authority and the target adjustment strategy to obtain the modified authority mapping table.

[0084] Exemplarily, the frequency of occurrence of the target permissions in the target adjustment strategy over a period of time is collected. For example, the frequency of occurrence is the number of times the target permissions are used every day, week, or month. Thus, the first adjustment priority is set according to the frequency of occurrence of the target permissions. For example, a target permission with a high frequency of occurrence can be set to a low priority, and vice versa.

[0085] For example, the target danger level corresponding to each target authority is evaluated according to the potential risks and impacts of the target adjustment strategy. The target danger level can be calculated by expert evaluation, historical data analysis or risk model. Thus, the second adjustment priority corresponding to the target adjustment strategy is determined according to the target danger level. The more dangerous the target danger level is, the lower the second adjustment priority is, and the safer the target danger level is, the higher the second adjustment priority is.

[0086] Exemplarily, a mapping table between adjustment priorities and adjustment values ​​is determined, and then a first value corresponding to the first adjustment priority and a second value corresponding to the second adjustment priority are obtained according to the mapping table, so as to determine a target value by fusing the first value and the second value, and then the target value is compared with a preset value. When the target value is greater than the preset value, the target authority corresponding to the target adjustment policy is upgraded to obtain priority authority; when the target value is less than the preset value, the target authority corresponding to the target adjustment policy is reduced to obtain priority authority; when the target value is equal to the preset value, the target authority corresponding to the target adjustment policy remains unchanged.

[0087] Exemplarily, the permission mapping table is modified according to the optimized permission and the target adjustment strategy, and the optimized target permission and its corresponding target adjustment strategy are updated into the permission mapping table, thereby ensuring the accuracy and effectiveness of the permission mapping table.

[0088] Specifically, by comprehensively considering the frequency of occurrence and the level of danger, the target authority is dynamically adjusted, thereby improving the flexibility and adaptability of authority management. Thus, by setting the first adjustment priority and the second adjustment priority, the accuracy of authority adjustment is optimized, the efficiency of authority management is improved, and support is provided for the subsequent improvement of the effectiveness of strategy execution, thereby ensuring the precise control and optimization of authority management, and providing strong support for the safe operation of the target tower crane.

[0089] See also Figure 2 , Figure 2A tower crane remote control system 200 with multi-level authority management is provided in the embodiment of the present application. The tower crane remote control system 200 with multi-level authority management includes an identity verification module 201, an authority acquisition module 202, a data acquisition module 203, a target tracking module 204, a state recognition module 205, a strategy determination module 206, an authority determination module 207, and a target control module 208, wherein the identity verification module 201 is used to receive user information input by an initial user, and to verify the identity corresponding to the initial user according to the user information, and obtain the verification result corresponding to the initial user; the authority acquisition module 202 is used to obtain the associated authority corresponding to the initial user when the verification result is passed; the data acquisition module 203 is used to collect target image data corresponding to the target tower crane when it transports the target object under the current operating parameters; the target tracking module 204, used to track the target object according to the target image data, and obtain the target position information corresponding to the target object; the state identification module 205, used to identify the transportation state of the target object according to the target position information and the target image data, and obtain the target transportation state corresponding to the target object; the strategy determination module 206, used to adjust the current operating parameters according to the target transportation state, obtain the target operating parameters, and determine the target adjustment strategy corresponding to the target operating parameters; the authority determination module 207, used to determine the target authority corresponding to the target adjustment strategy according to the authority mapping table, and determine the target user corresponding to the target adjustment strategy according to the target authority and the associated authority; the target control module 208, used to determine the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy.

[0090] In some implementations, the tower crane remote control system 200 with multi-level authority management may be applied to a terminal device.

[0091] It should be noted that, technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the tower crane remote control system 200 with multi-level authority management described above can refer to the corresponding process in the aforementioned embodiment of the tower crane remote control method with multi-level authority management, and will not be repeated here.

[0092] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the tower crane remote control methods with multi-level authority management provided in the description of the embodiment of the present invention.

[0093] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0094] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0095] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0096] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A tower crane remote control method with multi-level authority management, characterized in that: The method comprises: Receiving user information input by an initial user, and reviewing the identity corresponding to the initial user according to the user information, to obtain a review result corresponding to the initial user; When the audit result is approved, the associated permissions corresponding to the initial user are obtained; Collecting target image data corresponding to the target tower crane transporting the target object under the current operating parameters; Tracking the target object according to the target image data to obtain target position information corresponding to the target object; Identify the transportation state of the target object according to the target position information and the target image data, and obtain the target transportation state corresponding to the target object; Adjusting the current operating parameters according to the target transportation state to obtain target operating parameters, and determining a target adjustment strategy corresponding to the target operating parameters; Determine the target permission corresponding to the target adjustment policy according to the permission mapping table, and determine the target user corresponding to the target adjustment policy according to the target permission and the associated permission; A target control result corresponding to the target tower crane is determined according to the target user and the target adjustment strategy.

2. The method according to claim 1, characterized in that Tracking the target object according to the target image data to obtain target position information corresponding to the target object includes: Tracking the target object in the target image data using a first target tracking model to obtain first position information corresponding to the target object; Tracking the target object in the target image data using a second target tracking model to obtain second position information corresponding to the target object; Performing a union calculation on the first position information and the second position information to obtain the maximum position information corresponding to the target object; Obtaining a target area image corresponding to the target object from the target image data according to the maximum position information; Performing target recognition on the target area image to obtain target edge information corresponding to the target object in the target area image; The target position information corresponding to the target object is determined according to the target edge information and the target image data.

3. The method according to claim 2, characterized in that The step of tracking the target object in the target image data by using the first target tracking model to obtain first position information corresponding to the target object includes: When the target image information is a preset frame, a target template corresponding to the target object in the target image information is obtained by using the template determination layer of the first target tracking model; When the target image information is not the preset frame, the associated feature information corresponding to the previous frame image corresponding to the target image information is obtained, and the target reliability corresponding to the target template is determined according to the associated feature information by using the template update layer of the first target tracking model, and the target template is updated according to the target reliability to obtain the updated target template; Using the deep feature extraction layer of the first target tracking model to extract features from the target image data according to the target template to obtain initial feature information; Using the multi-template attention mechanism layer of the target tracking model to perform multi-dimensional attention feature extraction on the initial feature information to obtain attention feature information; Using the shallow feature extraction layer of the first target tracking model to extract features from the target image data according to the target template to obtain shallow feature information; Using the feature fusion layer of the first target tracking model, weighted fusion is performed on the attention feature information and the shallow feature information to obtain target feature information; The target prediction layer of the first target tracking model is used to perform target recognition according to the target feature information to obtain the first position information corresponding to the target object.

4. The method according to claim 3, characterized in that The using the second target tracking model to track the target object in the target image data to obtain second position information corresponding to the target object includes: Obtaining a first hash feature and a first color feature corresponding to the previous frame image corresponding to the target image information under the target template; Obtaining an image position corresponding to the target object in the previous frame image, and sliding in the target image information according to the image position and the target template to obtain a target area; Extracting features of the target area to obtain a second hash feature and a second color feature corresponding to the target area; Obtaining a first similarity corresponding to the target area according to the first hash feature and the second hash feature; Obtaining a second similarity corresponding to the target area according to the first color feature and the second color feature; fusing the first similarity and the second similarity to determine a target similarity corresponding to the target area; The second position information corresponding to the target object in the target image data is determined according to the target similarity.

5. The method according to claim 4, characterized in that Extracting features from the target area to obtain a second hash feature corresponding to the target area includes: Performing grayscale processing on the target area to obtain a grayscale area, and performing pixel mean processing on the grayscale area to obtain a first pixel mean; Performing pixel mean processing on the first pixel information corresponding to each row in the grayscale area to obtain a second pixel mean, and performing pixel mean processing on the second pixel information corresponding to each column in the grayscale area to obtain a third pixel mean; Arranging the grayscale areas from left to right and from top to bottom to obtain a target sequence, and comparing two adjacent data in the target sequence to obtain a first comparison result; Determine adjacent hash features corresponding to the grayscale area according to the first comparison result; Comparing the second pixel means corresponding to two adjacent first pixel information in the grayscale area to obtain a second comparison result, and determining the adjacent row hash features corresponding to the grayscale area according to the second comparison result; Comparing the third pixel means corresponding to two adjacent pieces of the second pixel information in the grayscale area to obtain a third comparison result, and determining the adjacent column hash features corresponding to the grayscale area according to the third comparison result; Comparing the second pixel mean corresponding to the first pixel information in the grayscale area with the first pixel mean to obtain a fourth comparison result, and determining a first mean hash feature corresponding to the grayscale area according to the fourth comparison result; Comparing the third pixel mean corresponding to the second pixel information in the grayscale area with the first pixel mean to obtain a fifth comparison result, and determining a second mean hash feature corresponding to the grayscale area according to the fifth comparison result; The adjacent hash features, the adjacent row hash features, the adjacent column hash features, the first mean hash features and the second mean hash features are concatenated to obtain the second hash feature corresponding to the target area.

6. The method according to claim 1, characterized in that The identifying the transportation state of the target object according to the target position information and the target image data to obtain the target transportation state corresponding to the target object includes: Determine the real position information corresponding to the target object according to the target position information and the target image information; Determine a target change amount corresponding to the target object according to the real position information, and determine a target change sequence corresponding to the target object at a current moment according to the target change amount; Performing data clustering on the target change sequence to obtain an initial clustering result, and analyzing the clustering reliability between clustering clusters in the initial clustering result to obtain a target reliability value corresponding to the initial clustering result; Adjusting the initial clustering result according to the target reliability value to obtain a target clustering result; A historical clustering result of the target object at a previous moment corresponding to the current moment is obtained, and the transportation state of the target object is identified according to the historical clustering result and the target clustering result to obtain the target transportation state corresponding to the target object.

7. The method according to claim 6, characterized in that The analyzing the clustering reliability between the clustering clusters in the initial clustering result to obtain the target reliability value corresponding to the initial clustering result includes: Calculating a first distance between each target change amount in the target change sequence and a cluster center corresponding to each cluster cluster; Calculating a second distance between the cluster centers corresponding to any two of the cluster clusters; fusing the first distance and the second distance to determine the target reliability value corresponding to the initial clustering result; The target reliability value is obtained according to the following formula: ； in, represents the target reliability value, represents the adjustment factor, n represents the number of targets corresponding to the target change sequence, m represents the number of clusters corresponding to the cluster clusters in the initial clustering result, represents the first distance between the j-th target change amount in the target change sequence and the cluster center corresponding to the i-th cluster, represents the second distance between the cluster center corresponding to the i-th cluster and the cluster center corresponding to the p-th cluster, and k represents a weighted index.

8. The method according to claim 1, characterized in that The identifying the transportation state of the target object according to the target position information and the target image data to obtain the target transportation state corresponding to the target object includes: Determine the real position information corresponding to the target object according to the target position information and the target image information; Perform path fitting according to the real position information to obtain a target fitting path corresponding to the target object; Using a path prediction model to perform path prediction on the current operating parameters of the target object to obtain a target predicted path corresponding to the target object; A path deviation between the target fitting path and the target predicted path is determined, and the target transportation state corresponding to the target object is determined according to the path deviation.

9. The method according to any one of claims 1 to 8, characterized in that After determining the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy, the method further includes: Determine an occurrence frequency corresponding to the target authority in the target adjustment strategy, and determine a first adjustment priority corresponding to the target adjustment strategy according to the occurrence frequency; Determining a target risk level corresponding to the target adjustment strategy, and determining a second adjustment priority corresponding to the target adjustment strategy according to the target risk level; Adjust the target authority of the target adjustment strategy according to the first adjustment priority and the second adjustment priority to obtain the optimization authority corresponding to the target adjustment strategy; The permission mapping table is modified according to the optimization permission and the target adjustment strategy to obtain the modified permission mapping table.

10. A tower crane remote control system with multi-level authority management, characterized in that: include: An identity verification module is used to receive user information input by an initial user, and verify the identity corresponding to the initial user according to the user information to obtain a verification result corresponding to the initial user; A permission obtaining module, used for obtaining the associated permissions corresponding to the initial user when the audit result is passed; A data acquisition module is used to acquire target image data corresponding to when the target tower crane transports the target object under current operating parameters; A target tracking module, used to track the target object according to the target image data, and obtain target position information corresponding to the target object; A state recognition module, used to recognize the transportation state of the target object according to the target position information and the target image data, and obtain the target transportation state corresponding to the target object; A strategy determination module, configured to adjust the current operating parameters according to the target transportation state, obtain target operating parameters, and determine a target adjustment strategy corresponding to the target operating parameters; A permission determination module, used to determine the target permission corresponding to the target adjustment policy according to the permission mapping table, and determine the target user corresponding to the target adjustment policy according to the target permission and the associated permission; The target control module is used to determine the target control result corresponding to the target tower crane according to the target user and the target adjustment strategy.

Images