A clinical data acquisition management system

Abstract

The application relates to the technical field of data collection management, and discloses a clinical data collection management system which comprises a data collection and integration module, a data verification and cleaning module, a safe storage and management module, a report generation and export module, a user permission and audit module and a training and support module; the data collection and integration module is responsible for collecting clinical data, supports multiple data input modes and equipment integration; the data verification and cleaning module verifies and cleans the collected data, and identifies and processes abnormal data. Through the introduction of a Bayesian network into the data collection and integration module for data consistency and correctness verification, and the use of a Kalman filtering algorithm for equipment data fusion processing, the accuracy and consistency of clinical data are effectively improved, data entry errors are reduced, and a support vector machine algorithm is used in the data verification and cleaning module for abnormal data detection.

Description

Technical Field

[0001] This invention relates to the field of data acquisition and management technology, specifically a clinical data acquisition and management system. Background Technology

[0002] In modern medical and clinical research, the collection, effective management, and secure storage of clinical data are crucial to ensuring research quality and patient safety. However, existing clinical data collection and management systems limit the overall performance and reliability of the system in terms of data collection, validation, storage, report generation, and user support.

[0003] Data input and device integration rely on manual entry or simple automated tools, lacking effective fusion processing algorithms, which leads to data redundancy, conflicts, and issues with consistency and accuracy, resulting in a high data entry error rate.

[0004] Traditional data validation and cleaning methods cannot effectively handle anomalous and high-dimensional data, lack advanced algorithm support, and lack verification of data order relationships, thus affecting data quality.

[0005] Traditional systems lack dynamic permission adjustment mechanisms and transparent audit trails, making it difficult to effectively prevent permission abuse and unauthorized access. Furthermore, the report generation process relies on manual operations or semi-automated tools, which is inefficient and prone to inconsistencies and errors. They also lack automated compliance check mechanisms.

[0006] Therefore, those skilled in the art provide a clinical data acquisition and management system to address the problems mentioned in the background section. Summary of the Invention

[0007] To address the shortcomings of existing technologies, this invention provides a clinical data acquisition and management system to solve the problems mentioned in the background section.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a clinical data acquisition and management system, comprising a data acquisition and integration module, a data verification and cleaning module, a secure storage and management module, a report generation and export module, and a user permission and auditing module;

[0009] The data acquisition and integration module is responsible for collecting clinical data and supports multiple data input methods and device integration.

[0010] The data verification and cleaning module verifies and cleans the collected data, and identifies and processes abnormal data.

[0011] The secure storage and management module securely stores clinical data, manages data access permissions, and maintains data integrity and availability.

[0012] The report generation and export module generates compliant clinical reports and supports multiple data export formats to facilitate data sharing and analysis.

[0013] The user permissions and auditing module manages user access permissions and records and tracks data operations;

[0014] The training and support module provides training and technical support for system operation, enabling users to effectively use the system and quickly resolve problems.

[0015] Preferably, the data acquisition and integration module includes a data input unit, a device integration unit, and a data verification unit; the data input unit supports multiple data input methods; the device integration unit integrates and manages different medical devices; and the data verification unit performs preliminary verification during the data input process to prevent data entry errors.

[0016] The data verification and cleaning module includes a data verification unit, a data cleaning unit, and an anomaly detection unit. The data verification unit verifies the collected data. The data cleaning unit cleans incomplete, duplicate, or abnormal data and identifies and processes anomalies in the data through rules and algorithms. The anomaly detection unit uses advanced algorithms to detect abnormal patterns in the data, providing a foundation for data cleaning.

[0017] The secure storage and management module includes a data storage unit, an access control unit, and a data backup unit. The data storage unit is responsible for securely storing clinical data, using encryption technology to protect the data and prevent unauthorized access. The access control unit manages user access permissions to the data. The data backup unit backs up the data periodically and provides data recovery.

[0018] Preferably, the report generation and export module includes a report generation unit, a data export unit, and a compliance check unit; the report generation unit generates clinical research reports that comply with industry and regulatory standards, and summarizes and displays the analysis results; the data export unit supports multiple data export formats; and the compliance check unit performs compliance checks during the report generation process.

[0019] The user permissions and auditing module includes a user management unit, an audit log unit, and a permission review unit. The user management unit creates and manages system users and their roles, assigns corresponding permissions, and controls users' access to different system functions and data. The audit log unit records user operations and data modifications, providing detailed audit logs. The permission review unit periodically reviews and adjusts user permissions.

[0020] The training and support module includes a training unit, a technical support unit, and a user feedback unit. The training unit provides training materials and online courses on system operation. The technical support unit provides multi-channel technical support to help users solve technical problems during use. The user feedback unit collects user feedback, provides improvement suggestions, and helps the system development team optimize system functions and user experience.

[0021] Preferably, in the data input unit, during the data input process, a Bayesian network is used to verify the consistency and correctness of the data. The Bayesian network formula is as follows:

[0022]

[0023] Among them, X i This is the current data point, Parents(X) i ) is related to X i Other related data points, P(X) i Parents(X) i )) is the conditional probability of the current data point given relevant data points;

[0024] In the device integration unit, Kalman filtering can be used for data fusion. The Kalman filtering formula is as follows:

[0025] Prediction update steps:

[0026]

[0027] P k|k-1 =AP k-1|k-1 A T +Q,

[0028] Correction and update steps:

[0029] K k =P k|k-1 H T HP k|k-1 H T +R) -1 ,

[0030]

[0031] P k|k =(IK k H)P k|k-1 ,

[0032] in, It is the predicted state vector, P k|k-1 Here, A is the predicted covariance matrix, B is the state transition matrix, and u is the control input matrix. kHere, Q is the control input vector, R is the process noise covariance, and K is the measurement noise covariance. k It is the Kalman gain, H is the observation matrix, and z is the Kalman gain. k These are actual measured values.

[0033] Preferably, in the data verification unit, support vector machines are used for anomaly detection. The support vector machine anomaly detection formula is as follows:

[0034] Objective function:

[0035]

[0036] Constraints:

[0037] y i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0, i=1,…,n,

[0038] Where w is the weight vector, b is the bias term, and ξ is the bias term. i φ(x) is a slack variable, C is a penalty parameter, and φ(x) is a slack i ) is a kernel function that maps input data to a high-dimensional space.

[0039] Preferably, in the data verification unit, a Hidden Markov Model (HMM) is used to verify the consistency and order of the data. The HMM formula is as follows:

[0040] State transition probability:

[0041] P(S t =s j |S t-1 =s i ) = A ij ,

[0042] Observation probability:

[0043] P(O t =o k |S t =s j ) = B jk ,

[0044] Initial state probability:

[0045] P(S1=s i ) = π i ,

[0046] Among them, S t O represents the hidden state at time t. t Let A represent the observed value at time t. ijIt is state s i to state s j The transition probability, B jk In state s j The following observations were made of o k The probability, π i The initial state is s i The probability of;

[0047] In the data cleaning unit, Lagrange interpolation is used to handle missing data issues, filling in missing data through interpolation. The Lagrange interpolation formula is as follows:

[0048] Given n data points (x0, y0), (x1, y1), ..., (x n ,y n The interpolation polynomial P(x) is expressed as:

[0049]

[0050] Where the Lagrange basis function L i (x) is defined as:

[0051]

[0052] This formula is used to calculate the interpolation polynomial, which is then used to predict missing values.

[0053] Preferably, in the permission management unit, a role-based access control model is used to manage user permissions. The mathematical expression of RBAC typically involves the mapping of relationships between users, roles, and permissions. The basic formula for RBAC is:

[0054] User and role mapping:

[0055]

[0056] Where U is the set of users, R is the set of roles, and UA is the mapping relationship between users and roles;

[0057] Role and permission mapping:

[0058]

[0059] Where P is the set of permissions, and PA is the mapping relationship between roles and permissions;

[0060] User permission deduction:

[0061]

[0062] This formula represents the set of permissions P that user u obtains through his set of roles R.

[0063] Preferably, the user management unit uses an attribute-based access control model to manage user access permissions. The access control model determines access permissions based on a combination of user attributes, environment attributes, and resource attributes. The access control model formula is as follows:

[0064] The decision rules of the access control model are expressed as follows:

[0065] Permit = f(U,R,E),

[0066] Where U is the set of user attributes, R is the set of resource attributes, E is the set of environmental attributes, and f is the decision function;

[0067] Specific access decisions are evaluated according to the following rules:

[0068]

[0069] Access control models dynamically determine user access permissions by combining multiple attributes.

[0070] Preferably, the permission review unit uses a dynamic permission review algorithm to adjust user permissions based on user behavior analysis and risk scoring, and combines machine learning algorithms to evaluate user permission usage and dynamically adjust permissions. The risk scoring algorithm formula is as follows:

[0071] Behavioral deviation calculation:

[0072]

[0073] Among them, A ij It is the behavioral data of user i on operation j. D is the average behavior of a user on operation j. i It is a behavioral deviation of user i;

[0074] Risk score calculation:

[0075]

[0076] Among them, R i Let be the risk score of user i, and max(D) be the maximum value of user behavior deviation;

[0077] Dynamic permission adjustment:

[0078]

[0079] Among them, P i T1 and T2 are the permissions for user i, and T1 and T2 are the risk thresholds for adjusting permissions.

[0080] Preferably, the training unit employs a personalized learning path recommendation algorithm to dynamically recommend the most suitable learning content and path based on the user's learning behavior and history. The personalized learning path recommendation formula is as follows:

[0081] User similarity calculation:

[0082]

[0083] Among them, Sim(u i ,u j ) is user u i and u j The similarity between them, r i,k User u i The rating of learning content k User u i The average rating, C is the user u i and u j The collection of content that receives joint ratings;

[0084] Content Recommendation:

[0085]

[0086] Among them, P(C i |U i ) is a given user u i Content C i The probability of recommendation, P(U) i |C i ) is user u i Learning Content C i The conditional probability, P(C) i ) is content C i The prior probability, P(U) i ) is user U i The probability distribution.

[0087] This invention provides a clinical data acquisition and management system. It has the following beneficial effects:

[0088] 1. This invention improves the accuracy and consistency of clinical data and reduces data entry errors by introducing a Bayesian network into the data acquisition and integration module for data consistency and correctness verification, and using a Kalman filter algorithm for the fusion processing of device data. Furthermore, the invention uses a support vector machine algorithm in the data verification and cleaning module for abnormal data detection, and combines it with a hidden Markov model to verify the sequential relationship of the data, ensuring the accurate identification and processing of abnormal data, and providing a solid foundation for data cleaning.

[0089] 2. This invention protects data by employing advanced encryption technology in the secure storage and management module, and manages user permissions using a role-based access control model. The system can effectively prevent unauthorized access, ensuring the security and compliance of data storage. Furthermore, the user permission and audit module, combined with the blockchain technology-based audit log storage method and dynamic permission review algorithm, can record user operations in detail, periodically review and dynamically adjust user permissions, ensuring the transparency and security of system operations.

[0090] 3. In the report generation and export module, this invention utilizes a natural language generation algorithm to automatically generate clinical research reports that comply with industry and regulatory standards. This ensures the compliance of the report content through a compliance check unit, thereby improving the efficiency and quality of report generation. At the same time, it introduces a personalized learning path recommendation algorithm to dynamically recommend learning content based on the user's learning behavior, thereby improving the relevance of training. This algorithm can quickly locate and resolve technical problems encountered by users during use, enhancing the system's user support capabilities. Attached Figure Description

[0091] Figure 1 This is a system diagram of the present invention;

[0092] Figure 2 This is a schematic diagram of the data acquisition and integration module of the present invention;

[0093] Figure 3 This is a schematic diagram of the data verification and cleaning module of the present invention;

[0094] Figure 4 This is a schematic diagram of the secure storage and management module of the present invention;

[0095] Figure 5 This is a schematic diagram of the report generation and export module of the present invention;

[0096] Figure 6 This is a schematic diagram of the user permissions and auditing module of the present invention;

[0097] Figure 7 This is a schematic diagram of the training and support module of the present invention. Detailed Implementation

[0098] To enable those skilled in the art to understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.

[0099] The present invention will now be described in detail with reference to the accompanying drawings:

[0100] Example:

[0101] Please see the appendix Figure 1 - Appendix Figure 7 This invention provides a clinical data acquisition and management system, including a data acquisition and integration module, a data verification and cleaning module, a secure storage and management module, a report generation and export module, a user access control and auditing module, and a training and support module. The data acquisition and integration module is responsible for collecting clinical data and supports multiple data input methods and device integration. The data verification and cleaning module verifies and cleans the collected data, identifies and processes abnormal data. The secure storage and management module securely stores clinical data, manages data access permissions, and maintains data integrity and availability. The report generation and exporting module generates compliant clinical reports and supports multiple data export formats to facilitate data sharing and analysis. The user access control and auditing module manages user access permissions and records and tracks data operations. The training and support module provides system operation training and technical support, enabling users to effectively use the system and quickly resolve problems.

[0102] The data acquisition and integration module offers several advantages: It enhances the flexibility of data acquisition, enabling the integration and management of multiple medical devices, automating data acquisition, reducing manual input errors, and improving data acquisition efficiency and accuracy. The data verification and cleaning module reduces the risk of data errors and maintains high data quality. The secure storage and management module prevents unauthorized access and data leakage, flexibly manages user permissions, ensures the security and compliance of data access, and guarantees the consistency and availability of data during storage and access. The report generation and export module reduces manual operations, improves report generation efficiency, and ensures that report content complies with relevant regulations and standards. The user permissions and auditing module enhances system security and prevents abuse of permissions. The training and support module ensures that users can quickly master the system's operation, improving work efficiency and enhancing user experience.

[0103] The data acquisition and integration module includes a data input unit, a device integration unit, and a data verification unit. The data input unit supports multiple data input methods. The device integration unit integrates and manages different medical devices. The data verification unit performs preliminary verification during data input to prevent data entry errors. The data verification and cleaning module includes a data verification unit, a data cleaning unit, and an anomaly detection unit. Data verification verifies the collected data. The data cleaning unit cleans incomplete, duplicate, or abnormal data and identifies and processes anomalies in the data through rules and algorithms. The anomaly detection unit uses advanced algorithms to detect abnormal patterns in the data, providing a foundation for data cleaning. The secure storage and management module includes a data storage unit, a permission management unit, and a data backup unit. The data storage unit is responsible for securely storing clinical data, using encryption technology to protect the data and prevent unauthorized access. The permission management unit manages user access permissions to the data. The data backup unit backs up the data regularly and provides data recovery capabilities.

[0104] The data input unit reduces errors during manual entry by automating input, improving the accuracy of data collection; the device integration unit enables automated data collection, reducing data entry time and manual intervention, and avoiding data conflicts and redundancy; the data verification unit ensures the basic correctness of the data through preliminary verification, reducing the workload of subsequent data processing.

[0105] The data validation unit reduces errors in the data, lowering compliance risks in subsequent data processing and analysis; the data cleaning unit automatically identifies and processes anomalies in the data through rules and algorithms, reducing manual intervention and improving work efficiency; the anomaly detection unit accurately identifies anomalous data, providing reliable anomaly detection results for the data cleaning unit.

[0106] The data storage unit offers several advantages: it uses encryption technology to protect data, preventing unauthorized access and data leakage, ensuring data confidentiality, and avoiding data corruption; the access control unit prevents data misuse and enhances system compliance; and the data backup unit enables the system to quickly resume normal operation, ensuring business continuity.

[0107] The report generation and export module includes a report generation unit, a data export unit, and a compliance check unit. The report generation unit generates clinical research reports that comply with industry and regulatory standards, summarizing and displaying analysis results. The data export unit supports multiple data export formats. The compliance check unit performs compliance checks during the report generation process. The user permissions and audit module includes a user management unit, an audit log unit, and a permission review unit. The user management unit creates and manages system users and their roles, assigns corresponding permissions, and controls user access to different system functions and data. The audit log unit records user operations and data modifications, providing detailed audit logs. The permission review unit periodically reviews and adjusts user permissions. The training and support module includes a training unit, a technical support unit, and a user feedback unit. The training unit provides training materials and online courses on system operation. The technical support unit provides multi-channel technical support to help users solve technical problems encountered during use. The user feedback unit collects user feedback, provides improvement suggestions, and helps the system development team optimize system functions and user experience.

[0108] The report generation unit reduces manual operation time and improves report generation efficiency and accuracy; the data export unit increases the flexibility of data processing and exchange; the compliance check unit reduces compliance risks, reduces human error through automated checks, and improves the accuracy and credibility of reports.

[0109] The user management unit offers the following benefits: flexible permission allocation and fine-grained permission control based on user roles, improving system security and operational efficiency; the audit log unit provides detailed audit logs, ensuring the transparency and traceability of system operations; and the permission review unit prevents permission abuse by regularly reviewing permission configurations to promptly identify and correct unreasonable permission settings, reducing security risks.

[0110] The training unit shortens the learning curve, ensuring users can continuously learn and master new system features; the technical support unit provides timely responses to user needs, ensuring smooth system operation and user satisfaction; and the user feedback unit provides important references for system optimization, helping the system development team optimize system functions and user experience, ensuring the system continuously meets user needs.

[0111] In the data input unit, during the data input process, a Bayesian network is used to verify the consistency and correctness of the data. The Bayesian network formula is as follows:

[0112]

[0113] Among them, X i This is the current data point, Parents(X) i ) is related to X i Other related data points, P(X)i Parents(X) i )) is the conditional probability of the current data point given relevant data points;

[0114] In the equipment integration unit, Kalman filtering can be used for data fusion. The Kalman filtering formula is as follows:

[0115] Prediction update steps:

[0116]

[0117] P k|k-1 =AP k-1|k-1 A T +Q,

[0118] Correction and update steps:

[0119] K k =P k|k-1 H T HP k|k-1 H T +R) -1 ,

[0120]

[0121] P k|k =(IK k H)P k|k-1 ,

[0122] in, It is the predicted state vector, P k|k-1 Here, A is the predicted covariance matrix, B is the state transition matrix, and u is the control input matrix. k Here, Q is the control input vector, R is the process noise covariance, and K is the measurement noise covariance. k It is the Kalman gain, H is the observation matrix, and z is the Kalman gain. k These are actual measured values.

[0123] The function of Bayesian network formula is to calculate the conditional probability of the current data point and its associated data points, determine whether the data point conforms to the expected probability distribution, and verify the logical consistency of the data. By analyzing the dependencies and conditional probabilities between data points, Bayesian network can identify abnormal or unreasonable data points and ensure the correctness of the data.

[0124] The Kalman filter formula plays a crucial role in the prediction update step. By predicting the state at the next moment based on the current state and control input, it provides an initial estimate of the equipment data. The update of the covariance matrix reflects the uncertainty of the prediction. Combined with process noise and the system model, the Kalman filter can dynamically adjust the accuracy of the prediction. Through the measurement update step, the predicted state is corrected using actual measurement data. The Kalman gain matrix determines the weight of the measurement data and the predicted data, thereby achieving optimal fusion of multi-source data and reducing the impact of noise on the results.

[0125] In the data validation unit, support vector machines are used for anomaly detection. The anomaly detection formula for support vector machines is as follows:

[0126] Objective function:

[0127]

[0128] Constraints:

[0129] y i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0, i=1,…,n,

[0130] Where w is the weight vector, b is the bias term, and ξ is the bias term. i φ(x) is a slack variable, C is a penalty parameter, and φ(x) is a slack i ) is a kernel function that maps input data to a high-dimensional space.

[0131] Support Vector Machine (SVM) anomaly detection formulas distinguish between normal and abnormal data by finding a hyperplane in a high-dimensional space that maximizes the inter-class margin. Slack variables are introduced by ξ when noise or overlap in the data. i Support Vector Machines (SVMs) strike a balance between accurate classification and error tolerance. In anomaly detection, SVMs are trained to distinguish between normal and anomalous data points. The objective function minimizes the norm of the weight vector. 2 This makes the model more stable, avoids overfitting, and accurately identifies outlier data by handling nonlinear boundaries through kernel functions.

[0132] In the data validation unit, a Hidden Markov Model (HMM) is used to verify the consistency and order of the data. The HMM formula is as follows:

[0133] State transition probability:

[0134] P(S t =s j |S t-1 =s i ) = A ij ,

[0135] Observation probability:

[0136] P(O t =o k |S t =s j ) = B jk ,

[0137] Initial state probability:

[0138] P(S1=s i ) = π i ,

[0139] Among them, S t O represents the hidden state at time t. t Let A represent the observed value at time t. ij It is state s i to state s j The transition probability, B jk In state s j The following observations were made of o k The probability, π i The initial state is s i The probability of;

[0140] In the data cleaning unit, Lagrange interpolation is used to handle missing data issues, filling in missing data through interpolation. The Lagrange interpolation formula is:

[0141] Given n data points (x0, y0), (x1, y1), ..., (x n ,y n The interpolation polynomial P(x) is expressed as:

[0142]

[0143] Where the Lagrange basis function L i (x) is defined as:

[0144]

[0145] This formula is used to calculate the interpolation polynomial, which is then used to predict missing values.

[0146] The role of Hidden Markov Models (HMMs) in data validation units is to verify whether the data changes according to the expected sequence, ensure the correct logical order of the data, infer whether the observed data conforms to the expected hidden state pattern, verify the correctness of the data, and ensure the consistency of the data from beginning to end.

[0147] The role of Lagrange interpolation in the data cleaning unit is to construct an interpolation polynomial P(x). Lagrange interpolation can predict function values ​​at missing data points and fill in the missing data by constructing a smooth polynomial curve using existing data points, ensuring that the interpolated data maintains consistency and continuity with the original data.

[0148] In the access control unit, a role-based access control model is used to manage user permissions. The mathematical expression of RBAC typically involves the mapping of relationships between users, roles, and permissions. The basic formula for RBAC is:

[0149] User and role mapping:

[0150]

[0151] Where U is the set of users, R is the set of roles, and UA is the mapping relationship between users and roles;

[0152] Role and permission mapping:

[0153]

[0154] Where P is the set of permissions, and PA is the mapping relationship between roles and permissions;

[0155] User permission deduction:

[0156]

[0157] This formula represents the set of permissions P that user u obtains through his set of roles R.

[0158] The user-role mapping formula simplifies the permission management process by mapping users to roles. Roles act as an intermediate layer of permissions, enabling administrators to manage user access permissions more efficiently.

[0159] The role-permission mapping formula allows administrators to manage the relationship between roles and permissions without requiring users to configure permissions, thus reducing management complexity, improving management efficiency, and reducing the possibility of errors.

[0160] The function of the user permission derivation formula is that user permissions are derived from their roles, which means that the allocation and modification of user permissions can be achieved by adjusting the user's role, thus realizing dynamic permission management.

[0161] In the user management unit, an attribute-based access control model is used to manage user access permissions. This model determines access permissions based on a combination of user attributes, environment attributes, and resource attributes. The access control model formula is as follows:

[0162] The decision rules of the access control model are expressed as follows:

[0163] Permit = f(U,R,E),

[0164] Where U is the set of user attributes, R is the set of resource attributes, E is the set of environmental attributes, and f is the decision function;

[0165] Specific access decisions are evaluated according to the following rules:

[0166]

[0167] Access control models dynamically determine user access permissions by combining multiple attributes.

[0168] By combining multiple attributes of users, resources, and environment, the ABAC model can dynamically determine user access permissions based on context. This dynamism makes access control more flexible and refined, allowing for precise restriction or permission of resource access, thereby improving security.

[0169] The access decision formula ensures the clarity and consistency of permission decisions based on the results of the decision function f(U,R,E). Access decisions are based on real-time attribute evaluation, and the system can dynamically adjust permissions when user attributes, resource attributes, or environmental attributes change, ensuring that the security policy is always consistent with the actual situation.

[0170] The ABAC model, by combining multi-dimensional attributes to determine access permissions, offers greater flexibility compared to traditional role-based or other static rule-based models. Administrators can define complex access rules based on business needs and security policies.

[0171] In the permission review unit, a dynamic permission review algorithm is used to adjust user permissions based on user behavior analysis and risk scoring. It also incorporates machine learning algorithms to evaluate user permission usage and dynamically adjust permissions. The risk scoring algorithm formula is as follows:

[0172] Behavioral deviation calculation:

[0173]

[0174] Among them, A ij It is the behavioral data of user i on operation j. D is the average behavior of a user on operation j. i It is a behavioral deviation of user i;

[0175] Risk score calculation:

[0176]

[0177] Among them, R iLet be the risk score of user i, and max(D) be the maximum value of user behavior deviation;

[0178] Dynamic permission adjustment:

[0179]

[0180] Among them, P i T1 and T2 are the permissions for user i, and T1 and T2 are the risk thresholds for adjusting permissions.

[0181] The behavioral deviation calculation formula works by calculating the deviation of a user's behavioral data in a specific operation from the overall average behavior, assessing the difference between the user's behavior and the normal operating pattern, and thus alerting potential security risks;

[0182] The risk score calculation formula measures a user's risk level in a relative way by standardizing the user's behavioral deviations. A high score indicates that the user's behavior is abnormal.

[0183] The dynamic permission adjustment formula adjusts user permissions based on their risk score. If the risk score is below a threshold, user permissions are increased; if the risk score is above a threshold, user permissions are reduced or restricted. This dynamic adjustment mechanism helps to respond promptly to changes in user behavior and enhances system security.

[0184] In the training unit, a personalized learning path recommendation algorithm is used to dynamically recommend the most suitable learning content and path based on the user's learning behavior and history. The personalized learning path recommendation formula is as follows:

[0185] User similarity calculation:

[0186]

[0187] Among them, Sim(u i ,u j ) is user u i and u j The similarity between them, r i,k User u i The rating of learning content k User u i The average rating, C is the user u i and u j The collection of content that receives joint ratings;

[0188] Content Recommendation:

[0189]

[0190] Among them, P(C i |U i ) is a given user u iContent C i The probability of recommendation, P(U) i |C i ) is user u i Learning Content C i The conditional probability, P(C) i ) is content C i The prior probability, P(U) i ) is user U i The probability distribution.

[0191] The user similarity calculation formula assesses the similarity of learning preferences by calculating the differences in users' ratings of shared learning content. A high similarity indicates that users' learning habits and interests are similar. User similarity is the foundation of personalized recommendation algorithms. By identifying users similar to the target user, the system can recommend learning content to the target user based on the learning history of similar users.

[0192] The content recommendation formula uses Bayesian inference to calculate the probability of recommending a certain learning content given specific user attributes and historical behavior. In this way, the system can dynamically adjust the recommended content to match the user's needs and interests, and at the same time, combine the user's personalized data to provide more targeted learning path recommendations.

[0193] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A clinical data collection management system, characterized by, The system comprises a data collection and integration module, a data verification and cleaning module, a secure storage and management module, a report generation and export module, a user permission and audit module, and a training and support module. The data collection and integration module is responsible for collecting clinical data, supporting multiple data input methods and device integration. The data collection and integration module comprises a data input unit, a device integration unit, and a data verification unit. In the data input unit, the consistency and correctness of the verification data are verified by using the Bayesian network during the data input process, and the Bayesian network formula is: , wherein, is the current data point, is another data point associated with the given relevant data point, is the conditional probability of the current data point given the given relevant data point; The device integration unit can use Kalman filtering for data fusion. The prediction update step is as follows: ， ， The correction update step is as follows: ， ， ， wherein, is a predicted state vector, is a predicted covariance matrix, is a state transition matrix, is a control input matrix, is a control input vector, is a process noise covariance, is a measurement noise covariance, is a Kalman gain, is an observation matrix, is an actual measurement value; The data verification and cleaning module verifies and cleans the collected data, identifies and processes abnormal data. The data verification and cleaning module comprises a data verification unit, a data cleaning unit, and an anomaly detection unit. The data verification unit verifies the collected data. The data cleaning unit cleans incomplete, duplicate, or abnormal data and identifies and processes abnormal items in the data through rules and algorithms. The permission management unit manages user permissions based on a role-based access control model, and manages permissions of users in the system by An algorithm represents the relationship mapping among users, roles, and permissions, and the algorithm is as follows: The algorithm is as follows: User-to-Character Mapping: , wherein, is a set of users, is a set of roles, is a mapping relationship between users and roles; Role-to-privilege mapping: , wherein, is a set of permissions, is a mapping relationship between roles and permissions; User rights derivation: , This formula represents the user By the role set The set of permissions acquired ; The anomaly detection unit uses advanced algorithms to detect abnormal patterns in the data and provides a basis for data cleaning. The secure storage and management module securely stores clinical data, manages data access permissions, and maintains data integrity and availability. The secure storage and management module comprises a data storage unit, a permission management unit, and a data backup unit. The data storage unit securely stores clinical data, uses encryption technology to protect data, and prevents unauthorized access. The permission management unit manages user access permissions for data. The data backup unit regularly backs up data and provides data recovery. The report generation and export module generates standardized clinical reports and supports multiple data export formats to complete data sharing and analysis. The report generation and export module comprises a report generation unit, a data export unit, and a compliance check unit. The report generation unit generates clinical research reports that meet industry and regulatory standards, summarizes and displays analysis results. The data export unit supports multiple data export formats. The compliance check unit performs compliance checks during report generation. The user permission and audit module manages user access permissions, records, and tracks data operations. The user permission and audit module comprises a user management unit, an audit log unit, and a permission review unit. The user management unit creates and manages system users and their roles, assigns appropriate permissions, and controls user access to different system functions and data. The audit log unit records user operations and data modifications and provides detailed audit logs. The permission review unit regularly reviews and adjusts user permissions. The training and support module provides training and technical support for system operation, enabling users to effectively use the system and quickly solve problems. The training and support module includes a training unit, a technical support unit and a user feedback unit; the training unit provides training materials and online courses for system operation; the technical support unit provides multi-channel technical support to help users solve technical problems in the use process; the user feedback unit collects user feedback, provides improvement suggestions, and helps the system development team optimize system functions and user experience; In the training unit, a personalized learning path recommendation algorithm is used to dynamically recommend the most suitable learning content and path according to the user's learning behavior and history, and the personalized learning path recommendation formula is as follows: User similarity calculation: , wherein, is a similarity between users and , is a rating of a user to a learning content , is an average rating of a user , is a set of contents commonly rated by users and . Content recommendation: , wherein, is a recommendation probability for a given user when content is presented to the user, is a conditional probability that a user learns content , is a prior probability that content is presented to the user, is a probability distribution of users .

2. The clinical data capture management system of claim 1, wherein, In the data verification unit, support vector machine is used for anomaly detection, and the support vector machine anomaly detection formula is as follows: Objective function: , Constraints: , wherein, is a weight vector, is a bias term, is a slack variable, is a penalty parameter, is a kernel function that maps input data into a high-dimensional space.

3. The clinical data capture management system of claim 1, wherein, In the data verification unit, hidden Markov model is used to verify the consistency and sequence relationship of data, and the hidden Markov model formula is as follows: State transition probabilities: , Observation probability: , Initial state probabilities: , wherein, denotes the hidden state at time , denotes the observation at time , is the state transition probability from state , is the probability of observing in state , is the probability of the initial state being ; In the data cleaning unit, Lagrange interpolation method is used to process data missing problem, and missing data is filled by interpolation, and the Lagrange interpolation formula is as follows: For a given bit data point , the interpolating polynomial is expressed as: , where the Lagrangian function is defined as: , The formula is used to calculate the interpolation polynomial, and the missing value is predicted by the interpolation polynomial.

4. The clinical data capture management system of claim 1, wherein, In the user management unit, an attribute-based access control model is used to manage user access rights, and the access control model determines access rights through the combination of user attributes, environment attributes and resource attributes, and the access control model formula is as follows: The decision rule of the access control model is represented as: , wherein, is a set of user attributes, is a set of resource attributes, is a set of environmental attributes, is a decision function; Specific access decisions are evaluated by the following rules: , The access control model controls the right through the combination of multiple attributes to dynamically determine the access right of the user.

5. The clinical data capture management system of claim 1, wherein, In the permission review unit, a dynamic permission review algorithm is used to adjust user permissions based on user behavior analysis and risk scoring, and machine learning algorithms are used to evaluate user permission usage and dynamically adjust permissions, and the risk scoring algorithm formula is as follows: Behavioral bias calculation: , wherein, is a user the behavior data of the user on the operation , is the average behavior of the user on the operation , is the behavior deviation of the user . Risk score calculation: , wherein, is a risk score of a user , is a maximum value of a user behavior bias; Dynamic permission adjustment: , wherein is the permission of the user , is the risk threshold for adjusting the permission.

Images