A multi-user collaborative access method for X-ray image data
Through identity authentication, multi-level encryption and differential privacy protection, collaborative operation recording and intelligent conflict resolution, the problems of low X-ray image data processing efficiency, insufficient data consistency and security in multi-user collaboration environment are solved, achieving high efficiency and security image data processing and collaboration.
Patent Information
- Application Number
- CN202411059665.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-05
AI Technical Summary
In a multi-user collaboration environment, the processing efficiency of X-ray image data is low, data consistency and security are difficult to guarantee, and the operation traceability and transparency are insufficient. The existing technology cannot effectively solve these problems.
Through user identity authentication and dynamic permission allocation, multi-level data encryption and differential privacy protection, collaborative operation recording, differentiated data synchronization and intelligent conflict resolution, detailed operation logging and encryption processing, we provide viewing, labeling, analysis and Report generation tool.
It improves the efficiency and collaboration effect of X-ray image data processing, ensures data consistency and security, enhances the traceability and transparency of the system, reduces operational conflicts, and improves the stability and collaboration efficiency of the system.
Smart Images

Figure CN118568696B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of collaborative access technology, and in particular to a multi-user collaborative access method for X-ray image data. Background Art
[0002] X-ray image data has a wide range of applications in medical imaging, industrial detection, and security inspection. With the development of digital technology, the collection, storage, and processing of X-ray image data have gradually been digitized and informationized. However, there are still some technical difficulties and challenges in the process of multi-user collaborative access and processing of X-ray image data.
[0003] However, the inventors have discovered that this technical solution still has at least the following defects:
[0004] First, data processing efficiency is low: Traditional image data processing methods usually rely on single-user operations and lack an effective multi-user collaboration mechanism. When processing image data, users often need to repeatedly perform operations such as viewing, annotation, analysis, and report generation, resulting in overall inefficiency. In addition, there are many types of image data processing tools, but there is a lack of a unified integration platform, which requires users to switch between different tools, increasing operational complexity and time costs.
[0005] Second, data consistency and security issues: In a multi-user collaborative environment, when different users operate on the same image data at the same time, data conflicts and inconsistencies are likely to occur. In the existing technology, the commonly used optimistic concurrency control and pessimistic concurrency control methods have limitations in dealing with data conflicts and cannot effectively solve the data consistency problems caused by multi-user concurrent operations. At the same time, image data usually contains a large amount of sensitive information. How to ensure data security and privacy protection during multi-user access is also an important technical challenge.
[0006] Third, insufficient traceability and transparency of operations: In the process of multi-user collaboration, the lack of detailed records and management of user operations makes post-audit and operation backtracking difficult. Traditional logging methods often only record basic operation information and cannot fully track users' specific operation behaviors and data changes. In addition, there are certain risks in the security and integrity of log data, which can be easily tampered with or leaked maliciously, resulting in reduced transparency and credibility of the system. Summary of the invention
[0007] Based on the above objectives, the present invention provides a method for multi-user collaborative access to X-ray image data.
[0008] A multi-user collaborative access method for X-ray image data comprises the following steps:
[0009] S1, user identity authentication and access rights allocation: obtain the user's identity information and perform identity authentication, and assign access rights based on the user's identity information, including read, write, modify and delete permissions;
[0010] S2, multi-level data storage encryption and differential privacy protection: During the data storage process, the image data is encrypted at multiple levels, and the differential privacy algorithm is applied to process the data;
[0011] S3, data request processing: when a user issues a data access request, the request processing module parses the request content, confirms the user's authority, and locates the corresponding image data according to the image data ID;
[0012] S4, collaborative operation record: when the user performs collaborative operation, the operation log is recorded, including the operation time, operation user and specific operation content;
[0013] S5, Differentiated data synchronization and intelligent conflict resolution: Record the differences of each operation and synchronize data through differentiated synchronization strategies, predict conflicts in advance and take measures to resolve them;
[0014] S6, Image Data Processing: Provides image data processing tools, including image data viewing, annotation, analysis and report generation.
[0015] Optionally, the user identity authentication and access rights allocation in S1 include:
[0016] S11, user identity information acquisition: obtaining user identity information through a multi-factor authentication method, wherein the multi-factor authentication method includes password authentication, SMS verification code, fingerprint recognition and facial recognition;
[0017] S12, Authentication: Use the SHA-256 algorithm to hash the password entered by the user and generate a hash value of the user's password, expressed as: ;
[0018] Compare the generated hash value with the user password hash value stored in the database. If they match, the verification is successful.
[0019] S13, dynamic access rights allocation: Based on user identity information and operation behavior history, role-based access control and dynamic access control strategies are used to allocate corresponding access rights, including:
[0020] S131, analyze user roles and responsibilities and determine basic access rights;
[0021] S132, adjusting access rights according to the user's operation frequency and historical behavior, expressed as:
[0022] Access_Level (Role,Frequency,Behavior_History ;
[0023] S133, the dynamically adjusted access rights include read, write, modify and delete rights.
[0024] Optionally, S2 includes:
[0025] S21, data sharding and layered encryption:
[0026] S211, data sharding: X-ray image data is divided into several data blocks, each of which is distributed and stored on different nodes:
[0027] S212, layered encryption: multi-layer encryption processing is performed on each data block, specifically including:
[0028] First layer encryption: Use the symmetric encryption algorithm AES to encrypt the data block and generate the first layer of encrypted data, which is expressed as:
[0029] ;
[0030] Second layer of encryption: Use the asymmetric encryption algorithm RSA to encrypt the first layer of encrypted data to generate the second layer of encrypted data, which is expressed as:
[0031] ;
[0032] S22, Differential Privacy Protection:
[0033] S221, Calculate Noise: Apply the differential privacy algorithm to the encrypted data block by adding noise to the data, expressed as:
[0034] ;
[0035] in, is the noise scale parameter, according to the privacy budget , expressed as: ;
[0036] is a function sensitivity, is the privacy budget parameter;
[0037] S222, adds noise to the encrypted data, expressed as:
[0038] ;
[0039] S23, encrypted data storage: the data blocks after multi-level encryption and differential privacy processing are stored in a distributed storage system, and a unique image data identifier is generated for identifying and retrieving image data.
[0040] Optionally, the S3 includes:
[0041] S31, request parsing: when a user issues a data access request, the type of user request (read, write, modify or delete) and image data are obtained, and the request content is parsed into a standard format;
[0042] S32, permission confirmation: According to the user's identity information, query the assigned permissions and use a Boolean function to confirm whether the user has the permission to request the operation, expressed as:
[0043] ;
[0044] like has Permission True , the request continues to be processed, otherwise the request is rejected and an error message of insufficient permissions is returned;
[0045] S33, data location: In the distributed storage system, find the data block location according to the image data ID:
[0046] ;
[0047] Find the node and storage path where the data block is located through the data location mapping table;
[0048] S34, data acquisition and processing: acquire and process image data. If the request type is read, read the data block and perform decryption and differential privacy processing, which is expressed as:
[0049] ;
[0050] If the request type is write or modify, first verify the data format and integrity, then encrypt and store it, as shown below: ;
[0051] If the request type is delete, delete the specified data block, expressed as: delete Data(location) ;
[0052] S35, response generation: Generate a corresponding response message according to the processing result, and return the processing result and data to the user, which is expressed as: .
[0053] Optionally, S4 includes:
[0054] S41, operation capture: When the user performs collaborative operations, the system captures the user operations in real time, including the operation time, the operating user and the specific operation content, including:
[0055] Operation time : Record the specific timestamp of user operations;
[0056] Operation User : Record the username of the user who initiated the operation;
[0057] Operation content : Record the specific operation type (such as read, write, modify or delete) and the data involved;
[0058] S42, operation log generation: Generate an operation log entry from the captured operation information, expressed as:
[0059] ;
[0060] in, It is an operation log entry, including the operation time, operation user and operation content;
[0061] S43, log storage: storing the generated operation log entries in an operation log database, the specific steps include:
[0062] Select a suitable log storage table or file and write the log entry into the log storage table through the insert operation, which is expressed as:
[0063] INSERT INTO LogTable(Time,User,Action) VALUES(T,U,A) ;
[0064] S44, log encryption: encrypting the stored operation logs, including:
[0065] Log entries are encrypted using a symmetric encryption algorithm (such as AES), expressed as:
[0066] ;
[0067] storing the encrypted log entries in a log database;
[0068] S45, log indexing and retrieval: indexing and retrieval of the operation log, specifically including:
[0069] Generate log indexes and classify them by time, user, and operation type;
[0070] Provides a log retrieval interface that allows quick query of logs based on specific conditions (such as time range, user ID, or operation type), expressed as:
[0071] Search Results SEARCH FROM LogTable WHERE Time BETWEEN' ;
[0072] By recording the operation logs of users' collaborative operations, the traceability and transparency of system operations are ensured, the security of log data is enhanced, the logs are prevented from being tampered with or leaked, and the management efficiency and security of the system are improved; this comprehensive logging mechanism provides reliable operation auditing and backtracking support for multi-user collaboration, ensuring the compliance and transparency of data operations.
[0073] Optionally, the S5 includes:
[0074] S51, operation difference record: record the difference in operation, expressed as:
[0075] ;
[0076] in Record the changes in data blocks involved in the operation;
[0077] S52, Differentiated synchronization strategy: Use Version Vector The algorithm identifies and categorizes the different records of user operations and integrates the operations;
[0078] S53, Intelligent Conflict Prediction and Resolution: Analyze historical operation data and current operation behavior to predict and intelligently resolve operation conflicts in advance.
[0079] Optionally, the S52 includes:
[0080] S521, VersionVector Initialization: Each node Maintain a version vector, represented as:
[0081] ;
[0082] in Representation Node The version number of
[0083] S522, operation record update: Whenever a node When performing an operation, update its version vector and record the operation and version vector together, expressed as:
[0084] ;
[0085] ;
[0086] S523, Differential synchronization algorithm: collect operation records and version vectors of all nodes, for each data block , calculate the combined impact of all operations, expressed as:
[0087] ;
[0088] The synchronization algorithm records updated data blocks by merging operations.
[0089] Optionally, the S53 includes:
[0090] S531, current operation behavior analysis: real-time analysis of current user operation behavior, generating current operation records , expressed as:
[0091] ;
[0092] S532, Conflict prediction model construction: Constructing a conflict prediction model ,The training data is the historical operation data set;
[0093] S533, conflict prediction: the current operation behavior feature vector Enter the conflict prediction model MLModel , predict potential conflicts, expressed as:
[0094] ;
[0095] in, Conflict Prediction It is the conflict prediction result, indicating whether the current operation will cause a conflict;
[0096] S534, conflict resolution strategy: For predicted conflicts, adopt intelligent resolution strategies, including:
[0097] Lock conflicting data blocks: Lock data blocks that may conflict while the operation is in progress, expressed as: ;
[0098] User prompts and suggestions: Prompt users with potential conflict information and provide solutions, expressed as:
[0099] notify ,ConflictPrediction);
[0100] S535, synchronization and conflict resolution execution: applying the synchronization result and conflict resolution method, updating the data block, which is expressed as:
[0101] ;
[0102] And distribute the synchronization results to all nodes.
[0103] Optionally, the S532 includes:
[0104] S5321, build a conflict prediction model: the training data is a historical operation data set;
[0105] S5322, Feature Extraction: Extract feature vectors from historical operation data , including operation time intervals, operation frequencies, and user behavior patterns, including:
[0106] Operation time interval: Calculate the time difference between each operation and the previous operation, expressed as:
[0107] ;
[0108] Operation frequency: Calculate the number of operations performed by a user within a certain time window, expressed as:
[0109] ;
[0110] User behavior pattern: extract pattern features based on user operation type and data block ID;
[0111] S5323, training model: constructing a neural network model, including input layer, hidden layer and output layer;
[0112] Input layer: receives the extracted feature vector ;
[0113] Hidden layer: nonlinear transformation, expressed as: ;
[0114] in, It is The activation value of the layer, is the weight matrix, is the bias vector, is the activation function;
[0115] Output layer: Generate conflict prediction results, output as conflict probability , expressed as:
[0116] ;
[0117] in, is the prediction result, is the number of network layers;
[0118] Loss function: Calculate the difference between the predicted value and the actual value, using the binary cross-extraction loss function, expressed as:
[0119] ;
[0120] in, is the actual label, indicating whether a conflict occurs;
[0121] Back propagation: Update weights and biases through the gradient descent algorithm to minimize the loss function, expressed as:
[0122] ;
[0123] in, are model parameters, is the learning rate.
[0124] Optionally, S6 includes:
[0125] S61, image data viewing: provides image data viewing function, supports users to browse and enlarge image data, expressed as: ;
[0126] S62, Image Data Annotation: Provides image data annotation tools to support users to annotate and comment on image data, expressed as:
[0127] ;
[0128] in, is the labeled data, Annotate is the annotation function, coordinates are the marked coordinates, label is the annotation label:
[0129] S63, Image Data Analysis: Provides image data analysis tools, supports automatic and manual image data analysis, and implements image data analysis algorithms, including edge detection and image segmentation, expressed as:
[0130] ;
[0131] ;
[0132] in, is the edge detection result, EdgeDetect is the edge detection algorithm, is the image segmentation result, Segment It is an image segmentation algorithm;
[0133] S64, Report Generation:
[0134] Provide report generation tools to support the generation of reports based on image data and its analysis results;
[0135] Implement a report generation algorithm, including image data, annotations, and analysis results, expressed as:
[0136] ;
[0137] in, is the generated report, is the report generation function, is the image data, is the labeled data, is the edge detection result, is the image segmentation result.
[0138] Beneficial effects of the present invention:
[0139] The present invention enables users to efficiently process and collaborate on image data by providing image data viewing, annotation, analysis and report generation tools. The image data viewing function supports users to examine the image content in detail, the annotation tool allows users to make precise annotations and records on the image data, the analysis tool provides automated and manual image data processing capabilities, and the report generation tool integrates the image data and its analysis results into a comprehensive report. The combination of these functions greatly improves the efficiency of image data processing and the collaborative effect.
[0140] The present invention ensures data consistency and security through operation difference records, differentiated synchronization strategies, and intelligent conflict prediction and resolution. The Version Vector algorithm is used to effectively identify and classify the difference records of user operations, and the operations are integrated through the synchronization algorithm to ensure data consistency. In addition, intelligent conflict prediction and resolution analyzes historical operation data and current operation behaviors, and uses machine learning models to predict and intelligently resolve potential conflicts in advance, thereby reducing operation conflicts and improving system stability and collaboration efficiency.
[0141] The present invention ensures the traceability and transparency of the system through detailed operation log recording and encryption processing. Each user operation is recorded, and sensitive information leakage is prevented through differential privacy protection mechanism. The encrypted storage of operation logs improves the security of data, while the log indexing and retrieval function facilitates post-audit and backtracking. This comprehensive log recording and management mechanism not only improves the management efficiency of the system, but also enhances the security and transparency of data operations, providing reliable technical support for multi-user collaboration. BRIEF DESCRIPTION OF THE DRAWINGS
[0142] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0143] Figure 1 A schematic diagram of a multi-user collaborative access method for X-ray image data according to an embodiment of the present invention;
[0144] Figure 2 Schematic diagram of differentiated data synchronization and intelligent conflict resolution according to an embodiment of the present invention. DETAILED DESCRIPTION
[0145] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.
[0146] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).
[0147] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.
[0148] like Figure 1 - Figure 2 As shown, a multi-user collaborative access method for X-ray image data includes the following steps:
[0149] S1, user identity authentication and access rights allocation: obtain the user's identity information and perform identity authentication to ensure the legitimacy of the accessing user, and allocate access rights based on the user's identity information, including read, write, modify and delete permissions;
[0150] S2, multi-level data storage encryption and differential privacy protection: During the data storage process, the image data is encrypted at multiple levels and the differential privacy algorithm is applied to the data to ensure that personal privacy information will not be leaked during the use and sharing of the data;
[0151] S3, data request processing: when a user issues a data access request, the request processing module parses the request content, confirms the user's authority, and locates the corresponding image data according to the image data ID;
[0152] S4, Collaborative operation record: When users perform collaborative operations, the operation log is recorded, including the operation time, operation user and specific operation content, to facilitate post-audit and backtracking;
[0153] S5, Differentiated data synchronization and intelligent conflict resolution: Record the differences of each operation and synchronize data through differentiated synchronization strategies, predict conflicts in advance and take measures to resolve them;
[0154] S6, Image Data Processing: Provides image data processing tools, including image data viewing, annotation, analysis and report generation.
[0155] Through strict identity authentication and dynamic permission management, the security of the system is ensured, data privacy is further protected, and efficient data access and traceability are achieved. Differentiated data synchronization and conflict resolution strategies improve the efficiency of data analysis and processing. The overall approach not only ensures data security and privacy, but also improves the efficiency and quality of multi-user collaboration, and is innovative and practical.
[0156] User authentication and access rights allocation in S1 include:
[0157] S11, user identity information acquisition: obtaining user identity information through a multi-factor authentication method, where the multi-factor authentication method includes password authentication, SMS verification code, fingerprint recognition, and facial recognition;
[0158] S12, Authentication: Use the SHA-256 algorithm to hash the password entered by the user and generate a hash value of the user's password, expressed as: ;
[0159] Compare the generated hash value with the user password hash value stored in the database. If they match, the verification is successful.
[0160] S13, dynamic access rights allocation: Based on user identity information and operation behavior history, role-based access control and dynamic access control strategies are used to allocate corresponding access rights, including:
[0161] S131, analyze user roles and responsibilities and determine basic access rights;
[0162] S132, adjusting access rights according to the user's operation frequency and historical behavior, expressed as:
[0163] Access_Level (Role,Frequency,Behavior_History ;
[0164] S133, the dynamically adjusted access rights include read, write, modify and delete rights.
[0165] By combining allocation strategies with user roles, operation frequency, and historical behavior, user permissions can be flexibly adjusted to ensure that users have appropriate access rights in different situations, thereby improving system security and operational efficiency. This not only ensures system security and privacy protection, but also improves user experience and system efficiency.
[0166] S2 includes:
[0167] S21, data sharding and layered encryption:
[0168] S211, data sharding: X-ray image data is divided into several data blocks, each of which is distributed and stored on different nodes:
[0169] S212, layered encryption: multi-layer encryption processing is performed on each data block, specifically including:
[0170] First layer encryption: Use the symmetric encryption algorithm AES to encrypt the data block and generate the first layer of encrypted data, which is expressed as:
[0171] ;
[0172] Second layer of encryption: Use the asymmetric encryption algorithm RSA to encrypt the first layer of encrypted data to generate the second layer of encrypted data, which is expressed as:
[0173] ;
[0174] S22, Differential Privacy Protection:
[0175] S221, computational noise: Apply the differential privacy algorithm to the encrypted data block, and add noise to the data to ensure that personal privacy information will not be leaked during the use and sharing of the data, expressed as:
[0176] ;
[0177] in, is the noise scale parameter, according to the privacy budget , expressed as: ;
[0178] is a function sensitivity, is the privacy budget parameter;
[0179] S222, adds noise to the encrypted data, expressed as:
[0180] ;
[0181] S23, encrypted data storage: the data blocks after multi-level encryption and differential privacy processing are stored in a distributed storage system, and a unique image data identifier is generated for identifying and retrieving image data.
[0182] Through data sharding and layered encryption, differential privacy protection and encrypted data storage, the security and privacy protection of X-ray image data are improved, the reliability and scalability of data storage are improved, and subsequent data identification and retrieval are facilitated. This comprehensive protection measure provides safe and reliable guarantees for multi-user collaboration.
[0183] S3 includes:
[0184] S31, request parsing: when a user issues a data access request, the type of user request (read, write, modify or delete) and image data are obtained, and the request content is parsed into a standard format for subsequent processing;
[0185] S32, permission confirmation: According to the user's identity information, query the assigned permissions and use a Boolean function to confirm whether the user has the permission to request the operation, expressed as:
[0186] ;
[0187] like has Permission True , the request continues to be processed, otherwise the request is rejected and an error message of insufficient permissions is returned;
[0188] S33, data location: In the distributed storage system, find the data block location according to the image data ID:
[0189] ;
[0190] Find the node and storage path where the data block is located through the data location mapping table;
[0191] S34, data acquisition and processing: acquire and process image data. If the request type is read, read the data block and perform decryption and differential privacy processing, which is expressed as:
[0192] ;
[0193] If the request type is write or modify, first verify the data format and integrity, then encrypt and store it, as shown below: ;
[0194] If the request type is delete, delete the specified data block, expressed as: delete Data(location) ;
[0195] S35, response generation: Generate a corresponding response message according to the processing result, and return the processing result and data to the user, which is expressed as: ;
[0196] The request processing part parses the request content, confirms user permissions, and locates the corresponding image data according to the image data ID. Each step ensures the security and efficiency of request processing while providing accurate responses to user requests.
[0197] S4 includes:
[0198] S41, operation capture: When the user performs collaborative operations, the system captures the user operations in real time, including the operation time, the operating user and the specific operation content, including:
[0199] Operation time : Record the specific timestamp of user operations;
[0200] Operation User : Record the username of the user who initiated the operation;
[0201] Operation content : Record the specific operation type (such as read, write, modify or delete) and the data involved;
[0202] S42, operation log generation: Generate an operation log entry from the captured operation information, expressed as:
[0203] ;
[0204] in, It is an operation log entry, including the operation time, operation user and operation content;
[0205] S43, log storage: storing the generated operation log entries in an operation log database, the specific steps include:
[0206] Select a suitable log storage table or file and write the log entry into the log storage table through the insert operation, which is expressed as:
[0207] INSERT INTO LogTable(Time,User,Action) VALUES(T,U,A) ;
[0208] S44, log encryption: Encrypt the stored operation logs to ensure the security of the log data, including:
[0209] Log entries are encrypted using a symmetric encryption algorithm (such as AES), expressed as:
[0210] ;
[0211] storing the encrypted log entries in a log database;
[0212] S45, Log indexing and retrieval: To facilitate post-audit and backtracking, the operation logs are indexed and retrieved, including:
[0213] Generate log indexes and classify them by time, user, and operation type;
[0214] Provides a log retrieval interface that allows quick query of logs based on specific conditions (such as time range, user ID, or operation type), expressed as:
[0215] Search Results SEARCH FROM LogTable WHERE Time BETWEEN' ;
[0216] By recording the operation logs of users' collaborative operations, the traceability and transparency of system operations are ensured, the security of log data is enhanced, the logs are prevented from being tampered with or leaked, and the management efficiency and security of the system are improved; this comprehensive logging mechanism provides reliable operation auditing and backtracking support for multi-user collaboration, ensuring the compliance and transparency of data operations.
[0217] S5 includes:
[0218] S51, operation difference record: record the difference in operation, expressed as:
[0219] ;
[0220] in Record the changes in data blocks involved in the operation;
[0221] S52, Differentiated synchronization strategy: Use Version Vector The algorithm identifies and classifies the different records of user operations and integrates the operations to ensure data consistency;
[0222] S53, Intelligent Conflict Prediction and Resolution: Analyze historical operation data and current operation behavior to predict and intelligently resolve operation conflicts in advance.
[0223] By providing an efficient and reliable multi-user collaborative access mechanism for X-ray image data, the stability and collaboration efficiency of the system are improved. This comprehensive solution not only improves the reliability of multi-user collaboration, but also enhances the security and traceability of data operations.
[0224] S52 includes:
[0225] S521, VersionVector Initialization: Each node Maintain a version vector, represented as:
[0226] ;
[0227] in Representation Node The version number of
[0228] S522, operation record update: Whenever a node When performing an operation, update its version vector and record the operation and version vector together, expressed as:
[0229] ;
[0230] ;
[0231] S523, Differential synchronization algorithm: collect operation records and version vectors of all nodes, for each data block , calculate the combined impact of all operations, expressed as:
[0232] ;
[0233] The synchronization algorithm records updated data blocks by merging operations to ensure that all replicas reach a consistent state;
[0234] Through detailed differentiated synchronization strategy steps, efficient consistency of X-ray image data in a multi-user collaborative environment is ensured, which not only improves the accuracy and reliability of data synchronization, but also effectively reduces conflicts caused by concurrent operations, thereby improving system stability and collaboration efficiency.
[0235] S53 includes:
[0236] S531, current operation behavior analysis: real-time analysis of current user operation behavior, generating current operation records , expressed as:
[0237] ;
[0238] S532, Conflict prediction model construction: Constructing a conflict prediction model , the training data is the historical operation data set ;
[0239] S533, conflict prediction: the current operation behavior feature vector Enter the conflict prediction model MLModel , predict potential conflicts, expressed as:
[0240] ;
[0241] in, Conflict Prediction It is the conflict prediction result, indicating whether the current operation will cause a conflict;
[0242] S534, conflict resolution strategy: For predicted conflicts, adopt intelligent resolution strategies, including:
[0243] Lock conflicting data blocks: Lock the data blocks that may conflict while the operation is in progress to prevent concurrent modification, expressed as: ;
[0244] User prompts and suggestions: Prompt users with potential conflict information and provide solutions, expressed as:
[0245] notify ,ConflictPrediction);
[0246] S535, synchronization and conflict resolution execution: applying the synchronization result and conflict resolution method, updating the data block, which is expressed as:
[0247] ;
[0248] Ensure eventual data consistency and distribute synchronization results to all nodes.
[0249] Through intelligent conflict prediction and resolution steps, the system can efficiently analyze historical operation data and current operation behaviors, predict in advance and intelligently resolve operation conflicts. This method not only improves the efficiency of data operations in a multi-user collaborative environment, but also enhances the reliability and security of the system, providing users with a smoother collaborative experience.
[0250] S532 includes:
[0251] S5321, build a conflict prediction model: the training data is a historical operation data set;
[0252] S5322, Feature Extraction: Extract feature vectors from historical operation data , including operation time intervals, operation frequencies, and user behavior patterns, including:
[0253] Operation time interval: Calculate the time difference between each operation and the previous operation, expressed as:
[0254] ;
[0255] Operation frequency: Calculate the number of operations performed by a user within a certain time window, expressed as:
[0256] ;
[0257] User behavior pattern: extract pattern features based on user operation type and data block ID;
[0258] S5323, training model: constructing a neural network model, including input layer, hidden layer and output layer;
[0259] Input layer: receives the extracted feature vector ;
[0260] Hidden layer: nonlinear transformation, expressed as: ;
[0261] in, It is The activation value of the layer, is the weight matrix, is the bias vector, is the activation function;
[0262] Output layer: Generate conflict prediction results, output as conflict probability , expressed as:
[0263] ;
[0264] in, is the prediction result, is the number of network layers;
[0265] Loss function: Calculate the difference between the predicted value and the actual value, using the binary cross-extraction loss function, expressed as:
[0266] ;
[0267] in, is the actual label, indicating whether a conflict occurs;
[0268] Back propagation: Update weights and biases through the gradient descent algorithm to minimize the loss function, expressed as:
[0269] ;
[0270] in, are model parameters, is the learning rate.
[0271] By building conflict prediction models, feature extraction and training neural network models, the prediction of potential conflicts in the multi-user collaboration process is effectively achieved. This not only improves the stability of the system and the collaboration efficiency, but also effectively reduces the operational delays and errors caused by conflicts, providing reliable technical support for multi-user collaboration.
[0272] S6 includes:
[0273] S61, image data viewing: provides image data viewing function, supports users to browse and enlarge image data, expressed as: ;
[0274] S62, Image Data Annotation: Provides image data annotation tools to support users to annotate and comment on image data, expressed as:
[0275] ;
[0276] in, is the labeled data, Annotate is the annotation function, coordinates are the marked coordinates, label is the annotation label:
[0277] S63, Image Data Analysis: Provides image data analysis tools, supports automatic and manual image data analysis, and implements image data analysis algorithms, including edge detection and image segmentation, expressed as:
[0278] ;
[0279] ;
[0280] in, is the edge detection result, EdgeDetect is the edge detection algorithm, is the image segmentation result, Segment It is an image segmentation algorithm;
[0281] S64, Report Generation:
[0282] Provide report generation tools to support the generation of reports based on image data and its analysis results;
[0283] Implement a report generation algorithm, including image data, annotations, and analysis results, expressed as:
[0284] ;
[0285] in, is the generated report, is the report generation function, is the image data, is the labeled data, is the edge detection result, is the image segmentation result.
[0286] Through the steps of image data viewing, annotation, analysis and report generation, users are provided with comprehensive image data processing tools, which improves the processing efficiency and quality of image data, provides strong support for multi-user collaboration, and enhances the practicality of the system and user experience.
[0287] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.
[0288] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A multi-user collaborative access method for X-ray image data, characterized in that: The following steps are involved: S1, user identity authentication and access rights allocation: obtain the user's identity information and perform identity authentication, and assign access rights based on the user's identity information, including read, write, modify and delete permissions; S2, multi-level data storage encryption and differential privacy protection: During the data storage process, the image data is encrypted at multiple levels, and the differential privacy algorithm is applied to process the data; S3, data request processing: when a user issues a data access request, the request processing module parses the request content, confirms the user's authority, and locates the corresponding image data according to the image data ID; S4, Collaboration operation record: When a user performs a collaborative operation, the operation log is recorded, including the operation time, operation user and specific operation content, including: S41, operation capture: When the user performs collaborative operations, the system captures the user operations in real time, including the operation time, the operating user and the specific operation content, including: Operation time : Record the specific timestamp of user operations; Operation User : Record the username of the user who initiated the operation; Operation content : Record the specific operation type and the data involved; S42, operation log generation: Generate an operation log entry from the captured operation information, expressed as: ; in, It is an operation log entry, including the operation time, operation user and operation content; S43, log storage: storing the generated operation log entries in an operation log database, the specific steps include: Select a suitable log storage table or file and write the log entry into the log storage table through the insert operation, which is expressed as: INSERT INTO LogTable(Time,User,Action) VALUES(T,U,A) ; S44, log encryption: encrypting the stored operation logs, including: Log entries are encrypted using a symmetric encryption algorithm, expressed as: ; storing the encrypted log entries in a log database; S45, log indexing and retrieval: indexing and retrieval of the operation log, specifically including: Generate log indexes and classify them by time, user, and operation type; Provides a log retrieval interface that allows quick query of logs based on specific conditions, expressed as: SearchResults = SEARCH FROM LogTable WHERE Time BETWEEN T1 AND T2 AND User = U AND Action = A ; S5, Differentiated data synchronization and intelligent conflict resolution: Record the differences of each operation and synchronize data through differentiated synchronization strategies, predict conflicts in advance and take measures to resolve them, including: S51, operation difference record: record the difference in operation, expressed as: ; in Record the changes in data blocks involved in the operation; S52, Differentiated synchronization strategy: Use Version Vector The algorithm identifies and categorizes the different records of user operations and integrates the operations; S53, intelligent conflict prediction and resolution: Analyze historical operation data and current operation behavior to predict and intelligently resolve operation conflicts in advance; The S52 includes: S521, VersionVector Initialization: Each node Maintain a version vector, represented as: ; in Representation Node The version number of S522, operation record update: Whenever a node When performing an operation, update its version vector and record the operation and version vector together, expressed as: ; ; S523, Differential synchronization algorithm: collect operation records and version vectors of all nodes, for each data block , calculate the combined impact of all operations, expressed as: ; The synchronization algorithm records updated data blocks by merging operations; The S53 includes: S531, current operation behavior analysis: real-time analysis of current user operation behavior, generating current operation records , expressed as: ; S532, Conflict prediction model construction: Constructing a conflict prediction model , the training data is the historical operation data set; S533, conflict prediction: the current operation behavior feature vector Enter the conflict prediction model MLModel , predict potential conflicts, expressed as: ; in, Conflict Prediction It is the conflict prediction result, indicating whether the current operation will cause a conflict; S534, conflict resolution strategy: For predicted conflicts, adopt intelligent resolution strategies, including: Lock conflicting data blocks: Lock data blocks that may conflict while the operation is in progress, expressed as: ; User prompts and suggestions: Prompt users with potential conflict information and provide solutions, expressed as: notify ,ConflictPrediction); S535, synchronization and conflict resolution execution: applying the synchronization result and conflict resolution method, updating the data block, which is expressed as: ; And distribute the synchronization results to all nodes; S6, Image Data Processing: Provides image data processing tools, including image data viewing, annotation, analysis and report generation.
2. A multi-user collaborative access method for X-ray image data according to claim 1, characterized in that: The user identity authentication and access rights allocation in S1 include: S11, user identity information acquisition: obtaining user identity information through a multi-factor authentication method, wherein the multi-factor authentication method includes password authentication, SMS verification code, fingerprint recognition and facial recognition; S12, Authentication: Use the SHA-256 algorithm to hash the password entered by the user and generate a hash value of the user's password, expressed as: ; Compare the generated hash value with the user password hash value stored in the database. If they match, the verification is successful. S13, dynamic access rights allocation: Based on user identity information and operation behavior history, role-based access control and dynamic access control strategies are used to allocate corresponding access rights, including: S131, analyze user roles and responsibilities and determine basic access rights; S132, adjusting access rights according to the user's operation frequency and historical behavior, expressed as: Access_Level (Role,Frequency,Behavior_History ; S133, the dynamically adjusted access rights include read, write, modify and delete rights.
3. The multi-user collaborative access method for X-ray image data according to claim 1, characterized in that: The S2 includes: S21, data sharding and layered encryption: S211, data sharding: X-ray image data is divided into several data blocks, each of which is distributed and stored on different nodes: S212, layered encryption: multi-layer encryption processing is performed on each data block, specifically including: First layer encryption: Use a symmetric encryption algorithm to encrypt the data block and generate the first layer of encrypted data, which is expressed as: ; Second layer encryption: Use an asymmetric encryption algorithm to encrypt the first layer of encrypted data to generate the second layer of encrypted data, which is expressed as: ; S22, Differential Privacy Protection: S221, Calculate Noise: Apply the differential privacy algorithm to the encrypted data block by adding noise to the data, expressed as: ; in, is the noise scale parameter, according to the privacy budget , expressed as: ; is a function sensitivity, is the privacy budget parameter; S222, adds noise to the encrypted data, expressed as: ; S23, encrypted data storage: the data blocks after multi-level encryption and differential privacy processing are stored in a distributed storage system, and a unique image data identifier is generated for identifying and retrieving image data.
4. The multi-user collaborative access method for X-ray image data according to claim 1, characterized in that: The S3 includes: S31, request parsing: when a user issues a data access request, the type and image data of the user's request are obtained, and the request content is parsed into a standard format; S32, permission confirmation: According to the user's identity information, query the assigned permissions and use a Boolean function to confirm whether the user has the permission to request the operation, expressed as: ; like has Permission True , the request continues to be processed, otherwise the request is rejected and an error message of insufficient permissions is returned; S33, data location: In the distributed storage system, find the data block location according to the image data ID: ; Find the node and storage path where the data block is located through the data location mapping table; S34, data acquisition and processing: acquire and process image data. If the request type is read, read the data block and perform decryption and differential privacy processing, which is expressed as: ; If the request type is write or modify, first verify the data format and integrity, then encrypt and store it, as shown below: ; If the request type is delete, delete the specified data block, expressed as: delete Data(location) ; S35, response generation: Generate a corresponding response message according to the processing result, and return the processing result and data to the user, which is expressed as: .
5. The multi-user collaborative access method for X-ray image data according to claim 1, characterized in that: The S532 includes: S5321, build a conflict prediction model: the training data is a historical operation data set; S5322, Feature Extraction: Extract feature vectors from historical operation data , including operation time intervals, operation frequencies, and user behavior patterns, including: Operation time interval: Calculate the time difference between each operation and the previous operation, expressed as: ; Operation frequency: Calculate the number of operations performed by a user within a certain time window, expressed as: ; User behavior pattern: extract pattern features based on user operation type and data block ID; S5323, training model: constructing a neural network model, including input layer, hidden layer and output layer; Input layer: receives the extracted feature vector ; Hidden layer: nonlinear transformation, expressed as: ; in, It is The activation value of the layer, is the weight matrix, is the bias vector, is the activation function; Output layer: Generate conflict prediction results, output as conflict probability , expressed as: ; in, is the prediction result, is the number of network layers; Loss function: Calculate the difference between the predicted value and the actual value, using the binary cross-extraction loss function, expressed as: ; in, is the actual label, indicating whether a conflict occurs; Backpropagation: The gradient descent algorithm updates the weights and biases to minimize the loss function, expressed as: ; in, are model parameters, is the learning rate.
6. The multi-user collaborative access method for X-ray image data according to claim 1, characterized in that: The S6 includes: S61, image data viewing: provides image data viewing function, supports users to browse and enlarge image data, expressed as: ; S62, Image Data Annotation: Provides image data annotation tools to support users to annotate and comment on image data, expressed as: ; in, is the labeled data, Annotate is the annotation function, coordinates are the marked coordinates, label is the annotation label: S63, Image Data Analysis: Provides image data analysis tools, supporting automatic and manual image data analysis, including edge detection and image segmentation, expressed as: ; ; in, is the edge detection result, EdgeDetect is the edge detection algorithm, is the image segmentation result, Segment It is an image segmentation algorithm; S64, Report Generation: Provide report generation tools to generate reports based on image data and analysis results; Realize report generation, including image data, annotations and analysis results, expressed as: ; in, is the generated report, is the report generation function, is the image data, is the labeled data, is the edge detection result, is the image segmentation result.
