Multifunctional and integrated chronic disease data management platform

Abstract

The present invention discloses a multifunctional integrated chronic disease data management platform, which relates to the field of data management technology. The platform includes: obtaining a set of functional modules of a target data management platform; interacting with the login log of the target data management platform, performing user clustering and decomposition on the login log, obtaining K user types and K user login coefficients; constructing K password dynamic updaters; obtaining a sequence of access users; obtaining an interval time sequence; rearranging the access user sequence to obtain an updated access user sequence; obtaining a login password sequence; and managing data in the access function module sequence. The present invention solves the technical problem in the prior art that due to the large number of functions of the chronic disease data management platform, parallel calls to the same data are prone to data leakage, and achieves the technical effect of improving the reliability and security of data management.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a multifunctional integrated chronic disease data management platform. Background Art

[0002] In the chronic disease data management platform, there are many functional modules, which often need to call the same data in parallel. For example, when a doctor uses the chronic disease full-process management module, he may also need to access the patient's historical medical records; and when a nurse conducts an intervention follow-up, he may also need to view the real-time health indicators of the same patient. This situation is prone to data leakage, especially in the absence of strict access control and audit mechanisms. Suppose a user accidentally exposes the medical records he accesses when using the intervention follow-up management module, and other unauthorized users can also access the same data through other functional modules, which may lead to the leakage of patient privacy information.

[0003] The existing technology has a technical problem that due to the large number of functions of the chronic disease data management platform, parallel calls to the same data are prone to data leakage. Summary of the invention

[0004] The present application provides a multifunctional integrated chronic disease data management platform, which is used to solve the technical problem in the prior art that due to the large number of functions of the chronic disease data management platform, parallel calls to the same data are prone to data leakage.

[0005] In view of the above problems, the present application provides a multifunctional integrated chronic disease data management platform, which includes:

[0006] A function module set acquisition module is used to acquire a function module set of a target data management platform; a user login coefficient acquisition module is used to interact with the login log of the target data management platform, perform user clustering decomposition on the login log, and obtain K user types and K user login coefficients, wherein K is an integer greater than or equal to 1; a dynamic password updater construction module is used to identify a dynamic login password update strategy based on the K user login coefficients, and construct K password dynamic updaters according to the identification results; an access user sequence acquisition module is used to acquire M access users in a preset time window, sort the M access users in order from the front to the back of the access time, and obtain an access user sequence, wherein M is an integer greater than or equal to 1, wherein the M access users include M access user type identifiers and M access function module identifiers; an interval A time series acquisition module is used to calculate the interval time between two adjacent access users in the access user sequence to obtain an interval time sequence; an update access user sequence acquisition module is used to perform concurrent access screening for the same data based on the interval time sequence, and to rearrange the access user sequence according to the screening result to obtain an update access user sequence; a login password sequence acquisition module is used to use the K password dynamic updaters, in combination with the M access user type identifiers and the update access user sequence to perform login password identification to obtain a login password sequence; a data management module is used to match the function module set according to the M access function module identifiers to obtain an access function module sequence, send the login password sequence to the access users of the update access user sequence in sequence, and manage the data in the access function module sequence.

[0007] In a possible implementation, the functional module set includes a chronic disease full-process management module, an intervention follow-up management module, an injury monitoring management module, and an analysis and prediction management module.

[0008] In a possible implementation, the user login coefficient acquisition module is used to: cluster the login log with user type as an index to obtain K user types; retrieve the login records of each user type in the login log with the K user types as an index to obtain K user login record sets; perform feature decomposition analysis on the K user login record sets to obtain the K user login coefficients.

[0009] In a possible implementation, the user login coefficient obtaining module is used to:

[0010] According to the preset feature set, the K user login record sets are feature-decomposed to obtain K user login duration sets, K user login content change sets and K user minimum interval time sets between two adjacent logins; the K user login duration sets, K user login content change sets and the K user minimum interval time sets between two adjacent logins are feature-concentrated screened to determine the K concentrated user login durations, the K concentrated user login content change amounts and the K concentrated user minimum interval time between two adjacent logins; the K concentrated user login durations, the K concentrated user login content change amounts and the K concentrated user minimum interval time between two adjacent logins are identified using a login coefficient identifier to determine the K user login coefficients.

[0011] In a possible implementation, the user login coefficient obtaining module is used to:

[0012] Calculate the mean of the K user login duration sets respectively to obtain the mean of the K user login durations; use the mean of the K user login durations as K initial iteration centers, input the K initial iteration centers into a weighted iteration formula to obtain K stage iteration centers; perform multiple iterations based on the K stage iteration centers until the Euclidean distance between the stage iteration centers of two adjacent iterations is less than or equal to a preset Euclidean distance, and obtain K target iteration centers; use the K user login durations corresponding to the K target iteration centers as the K concentrated user login durations.

[0013] In a possible implementation, the weighted iteration formula is:

[0014] ;

[0015] in, is the stage iteration center, is a Gaussian function, i is the number of multiple user login durations in the user login duration set whose distance to the initial iteration center is the preset iteration bandwidth, and i is an integer greater than or equal to 1. is the login duration of the i-th user among multiple user login durations whose distance to the initial iteration center is the preset iteration bandwidth, is the initial iteration center.

[0016] In a possible implementation, the dynamic password updater construction module is used to:

[0017] Respectively calculate the ratios of the K user login coefficients to the sum of the K user login coefficients, and use the differences between the ratios and 1 as K dynamic update factors, wherein the dynamic update factor is the maximum similarity between the updated login password and the historical login password; obtain K historical login password sets of K user types; and construct the K password dynamic updaters based on the K dynamic update factors and the K historical login password sets.

[0018] In a possible implementation, the dynamic password updater construction module is used to:

[0019] K sample login password sets are randomly generated, and similarities between the K sample login password sets and the K historical login password sets are calculated to obtain K sample similarity sets; the K sample similarity sets are screened based on the K dynamic update factors, and sample login passwords corresponding to sample similarities greater than the K dynamic update factors are eliminated to obtain K identified sample login password sets; the K password dynamic updaters are constructed according to the K dynamic update factors, the K historical login password sets and the K identified sample login password sets.

[0020] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0021] The present application obtains a set of functional modules of a target data management platform, then interacts with the login log of the target data management platform, performs user clustering and decomposition on the login log, obtains K user types and K user login coefficients, where K is an integer greater than or equal to 1, and then identifies a dynamic login password update strategy based on the K user login coefficients, constructs K password dynamic updaters based on the identification results, obtains M access users in a preset time window, and sorts the M access users in order from the front to the back of the access time to obtain an access user sequence, where M is an integer greater than or equal to 1, where the M access users include M access user type identifiers and M access function identifiers. Module identification, then calculate the interval time between two adjacent access users in the access user sequence to obtain the interval time sequence, perform concurrent access screening for the same data based on the interval time sequence, and rearrange the access user sequence according to the screening results to obtain the updated access user sequence, and then use K password dynamic updaters, combined with M access user type identifications and updated access user sequence to identify the login password, obtain the login password sequence, and then match the M access function module identifications with the function module set to obtain the access function module sequence, send the login password sequence to the access user who updated the access user sequence in turn, and manage the data in the access function module sequence. The technical effect of improving the reliability of data management is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of the structure of the multifunctional integrated chronic disease data management platform provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of a process for obtaining K user login coefficients in the multifunctional integrated chronic disease data management platform provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: function module set acquisition module 11, user login coefficient acquisition module 12, dynamic password updater construction module 13, access user sequence acquisition module 14, interval time sequence acquisition module 15, updated access user sequence acquisition module 16, login password sequence acquisition module 17, data management module 18. DETAILED DESCRIPTION

[0026] The present application provides a multifunctional integrated chronic disease data management platform to solve the technical problem in the prior art that due to the large number of functions of the chronic disease data management platform, parallel calls to the same data are prone to data leakage.

[0027] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0028] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, platform, device, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, platforms, products or devices.

[0029] Embodiment 1: This application embodiment provides a multifunctional fusion chronic disease data management platform, such as Figure 1 As shown, the platform includes:

[0030] Functional module set acquisition module 11, used to acquire the functional module set of the target data management platform;

[0031] Furthermore, the functional module set includes a chronic disease full-process management module, an intervention follow-up management module, an injury monitoring management module and an analysis and prediction management module.

[0032] In a possible embodiment, the target data management platform is used for multifunctional integrated management of chronic disease data, including a set of functional modules. The set of functional modules is used for managing chronic disease data with different functions, including a chronic disease full-process management module, an intervention follow-up management module, an injury monitoring management module, and an analysis and prediction management module.

[0033] Optionally, the chronic disease full process management module is used to track the entire treatment and management process of chronic disease patients. The intervention follow-up management module is used to manage intervention measures and follow-up records for patients. The injury monitoring management module is used to manage data generated by monitoring injuries that may occur to patients during the management process. The analysis and prediction management module is used for data analysis and prediction of future trends.

[0034] By connecting with the target data management platform and calling the function list of the target data management platform through the API, the function module set is obtained. The same data may be called by multiple function modules in the function module set in the same time period. At this time, it is easy for the data to be modified one after another, resulting in inconsistent stored data. Therefore, in order to pave the way for subsequent data calls, it is necessary to first master the settings of each function module in the function module set.

[0035] A user login coefficient obtaining module 12 is used to interact with the login log of the target data management platform, perform user clustering decomposition on the login log, and obtain K user types and K user login coefficients, where K is an integer greater than or equal to 1;

[0036] Further, such as Figure 2 As shown, the user login coefficient obtaining module 12 is used for:

[0037] Clustering the login logs using user type as an index to obtain K user types;

[0038] Using the K user types as indexes, searching for login records of each user type in the login log to obtain K user login record sets;

[0039] Perform feature decomposition analysis on the K user login record sets to obtain the K user login coefficients.

[0040] In a possible embodiment, the user's login log data is obtained from the target data management platform. The login log reflects the application of the target data management platform. Optionally, the login log contains necessary information, such as user ID, login time, operation type, IP address, etc. The login log is obtained for subsequent analysis.

[0041] Different types of users log into the target data management platform for different purposes. For example, doctors log into the target data management platform to update the medical records of patients with chronic diseases, and administrators log into the target data management platform mainly to manage the data of the entire process of chronic diseases. Researchers log into the target data management platform to analyze and predict the medical records of patients with chronic diseases based on the data in the platform. Therefore, it is necessary to perform a cluster analysis of user types based on the login logs to determine the prevalence of each type of user logging into the target data management platform, thereby determining the corresponding user login coefficient. By obtaining the user login coefficient, different password update situations can be determined for different user types in the future, thereby improving management efficiency while ensuring data security.

[0042] Optionally, the login logs are analyzed by selecting a suitable clustering algorithm (such as K-means, hierarchical clustering, etc.), and then the login logs are clustered based on the user's behavior characteristics (such as login frequency, login duration, etc.) to identify K user types. The K user types represent different user identities, such as nurses, doctors, and community administrators.

[0043] In one embodiment, an index is created for each user type, and then the login logs are retrieved and clustered using the user type as the index, and the login logs belonging to the same user type are clustered into one category, thereby obtaining the K user types. The K user types are traversed one by one, and the corresponding login records are retrieved from the login logs, and the login records of each user type are stored in an independent set to obtain the K user login record sets. Each set corresponds to a user type and contains all login records of the type.

[0044] In a possible embodiment, the behavior characteristics of users in the K user login record sets are analyzed and analyzed to determine the common situation of user logins for each user type, thereby obtaining the K user login coefficients. This achieves the technical effect of improving the understanding of user behavior and laying the foundation for subsequent dynamic password updates and access control strategy formulation.

[0045] Furthermore, the user login coefficient obtaining module 12 is used for:

[0046] Decomposing the K user login record sets according to the preset feature set to obtain a set of K user login durations, a set of K user login content change amounts, and a set of K user minimum interval durations between two adjacent logins;

[0047] Performing feature concentration screening on the K user login duration sets, the K user login content change amount sets, and the K user two adjacent login minimum interval time sets, respectively, to determine the K concentrated user login durations, the K concentrated user login content change amounts, and the K concentrated user two adjacent login minimum interval time;

[0048] The login coefficient identifier is used to respectively identify the login durations of the K concentrated users, the changes in the login contents of the K concentrated users, and the minimum interval between two adjacent logins of the K concentrated users to determine the login coefficients of the K users.

[0049] Furthermore, the user login coefficient obtaining module 12 is used for:

[0050] Calculate the mean of the K user login duration sets respectively to obtain the mean of the K user login durations;

[0051] Taking the average login duration of the K users as K initial iteration centers, inputting the K initial iteration centers into the weighted iteration formula to obtain K stage iteration centers;

[0052] Perform multiple iterations based on the K stage iteration centers until the Euclidean distance between the stage iteration centers of two adjacent iterations is less than or equal to a preset Euclidean distance, thereby obtaining K target iteration centers;

[0053] The K user login durations corresponding to the K target iteration centers are used as the K concentrated user login durations.

[0054] Furthermore, the weighted iteration formula is:

[0055] ;

[0056] in, is the stage iteration center, is a Gaussian function, i is the number of multiple user login durations in the user login duration set whose distance to the initial iteration center is the preset iteration bandwidth, and i is an integer greater than or equal to 1. is the login duration of the i-th user among multiple user login durations whose distance to the initial iteration center is the preset iteration bandwidth, is the initial iteration center.

[0057] In one embodiment, the preset feature set includes user login duration, user login content change amount (the amount of data changed after the user logs in), and the minimum interval between two consecutive user logins. Using the preset feature set as an index, feature extraction is performed on the K user login record sets to obtain K user login duration sets, K user login content change amount sets, and K user login minimum interval sets.

[0058] Furthermore, feature concentration screening is performed on the set of K user login durations, the set of K user login content changes, and the set of K user's two adjacent login minimum intervals, to determine the prevalence of each feature of the K user login record set, and to obtain the K concentrated user login durations, the K concentrated user login content changes, and the K concentrated user's two adjacent login minimum intervals.

[0059] Furthermore, the login coefficient identifier is used to identify the login durations of the K concentrated users, the changes in the login contents of the K concentrated users, and the minimum interval between two consecutive logins of the K concentrated users, to determine the login coefficients of the K users. The login coefficient identifier is used to intelligently conduct a comprehensive analysis of the login durations of the concentrated users, the changes in the login contents of the concentrated users, and the minimum interval between two consecutive logins of the concentrated users to determine the user login coefficients. The user login coefficient reflects the operation of the user type when logging into the target data management platform. The larger the user login coefficient, the higher the complexity of the operation of the user type in the target data management platform, and the more reliable management of the login status of the user type is required.

[0060] Preferably, the user login duration in multiple sample sets, the amount of change in the user login content in multiple sample sets, and the minimum interval between two consecutive logins of the user in multiple sample sets are obtained, and the corresponding multiple sample user login coefficients are obtained as training data. The training data is used to perform supervised training on the framework built based on the feedforward neural network, and the many-to-one mapping relationship between the user login duration in the set, the amount of change in the user login content in the set, and the minimum interval between two consecutive logins of the user in the set is learned, and the training is performed until convergence, and the login coefficient identifier that has been trained is obtained.

[0061] In an embodiment of the present application, for K user login duration sets, the mean formula is used to calculate the mean of each set to obtain the mean of the K user login durations. The mean of the K user login durations reflects the average level of the K user login duration sets. The calculated mean of the K user login durations are respectively used as K initial iteration centers. The K initial iteration centers are the initial centers for general analysis of user login durations. Furthermore, the weighted iteration formula is used to perform coordinate iteration on the K initial iteration centers, and the K user login durations after iteration are used as K stage iteration centers. The K stage iteration centers are better able to reflect the general login duration of the K user login duration sets than the K initial iteration centers.

[0062] Then, multiple iterations are performed based on the K stage iteration centers, and the Euclidean distance between the stage iteration centers obtained in two adjacent iterations is calculated after each iteration. When the calculated result is less than or equal to the preset Euclidean distance (the maximum Euclidean distance set by a person skilled in the art that can be considered to have reached a relatively common distribution), the K stage iteration centers obtained in the last iteration are used as the K target iteration centers. The K user login durations corresponding to the K target iteration centers are used as the K concentrated user login durations.

[0063] The weighted iteration formula is used to iteratively update the initial iteration center, wherein the preset iteration bandwidth is the farthest distance of a single iteration analysis when performing iterations and is pre-set by a person skilled in the art. is the stage iteration center, is a Gaussian function, i is the number of multiple user login durations in the user login duration set whose distance to the initial iteration center is the preset iteration bandwidth, and i is an integer greater than or equal to 1. is the login duration of the i-th user among multiple user login durations whose distance to the initial iteration center is the preset iteration bandwidth, is the initial iteration center.

[0064] Based on the same principle as that of obtaining the login durations of the K concentrated users, the set of login content changes of the K users and the set of minimum interval durations between two adjacent logins of the K users are subjected to feature concentrated screening to obtain the login content changes of the K concentrated users and the minimum interval duration between two adjacent logins of the K concentrated users.

[0065] A dynamic password updater construction module 13 is used to identify a dynamic login password update strategy based on the K user login coefficients, and to construct K password dynamic updaters according to the identification results;

[0066] Furthermore, the dynamic password updater construction module 13 is used to:

[0067] Calculate the ratio of the K user login coefficients to the sum of the K user login coefficients respectively, and use the difference between the ratio and 1 as K dynamic update factors, where the dynamic update factor is the maximum similarity between the updated login password and the historical login password;

[0068] Get K historical login password sets of K user types;

[0069] The K password dynamic updaters are constructed based on the K dynamic update factors and the K historical login password sets.

[0070] Furthermore, it is characterized in that the dynamic password updater construction module 13 is used to:

[0071] Randomly generate K sample login password sets, and calculate the similarity between the K sample login password sets and the K historical login password sets to obtain K sample similarity sets;

[0072] The K sample similarity sets are screened based on the K dynamic update factors, and sample login passwords corresponding to sample similarities greater than the K dynamic update factors are eliminated to obtain K identified sample login password sets;

[0073] The K password dynamic updaters are constructed according to the K dynamic update factors, the K historical login password sets and the K identified sample login password sets.

[0074] In a possible embodiment, after obtaining the K user login coefficients, a dynamic data login password update strategy analysis is performed according to the size of the user login coefficients to determine K password dynamic updaters corresponding to the K user types. The K password dynamic updaters are used to iterate the login passwords of different user types.

[0075] In one embodiment, the ratio of the K user login coefficients to the sum of the K user login coefficients is calculated respectively, and the difference between the ratio and 1 is used as K dynamic update factors, wherein the dynamic update factor is the maximum similarity between the updated login password and the historical login password. Then, K historical login password sets of K user types are obtained from the target data management platform. The K password dynamic updaters are constructed based on the K dynamic update factors and the K historical login password sets.

[0076] Preferably, based on the setting rules of the K historical login password sets, K sample login password sets are randomly generated. Exemplarily, changes can be made on the basis of historical passwords, such as adding special characters, changing uppercase and lowercase letters, adding random numbers, etc. Ensure that the new password meets security requirements in terms of complexity and length. And use the cosine similarity formula to calculate the similarity between the K sample login password sets and the K historical login password sets to obtain K sample similarity sets. Then, based on the K dynamic update factors, the K sample similarity sets are screened, and the sample login passwords corresponding to the sample similarities greater than the K dynamic update factors are eliminated, that is, the sample data that does not meet the requirements are eliminated, thereby obtaining K identified sample login password sets. The K password dynamic updaters are constructed according to the K dynamic update factors, the K historical login password sets and the K identified sample login password sets.

[0077] In one possible embodiment, a data structure of a password dynamic updater is created for each user type, which may include fields such as "current password", "historical password set", "dynamic update factor", etc. The latest password in the historical login password set is set as the "current password" field of the dynamic updater. K dynamic updaters are initialized, each corresponding to a user type. For each user type, a new password candidate is generated according to the value of the dynamic update factor. The identified sample login password set in the K identified sample login password sets is set as the "current password" of the dynamic updater to replace the original historical password. By continuously training the K password dynamic updaters according to the K dynamic update factors, the K historical login password sets and the K identified sample login password sets until convergence, dynamic password updates can be performed according to user types. The performance and response speed of the dynamic updater are evaluated to ensure that it meets the security and user experience requirements of the system. The K password dynamic updaters that have been trained are obtained.

[0078] The access user sequence obtaining module 14 is used to obtain M access users in a preset time window, sort the M access users in order of access time from the beginning to the end, and obtain an access user sequence, where M is an integer greater than or equal to 1, and the M access users include M access user type identifiers and M access function module identifiers;

[0079] In one embodiment, user access logs within a preset time window are collected from the target data management platform to ensure that they include user ID, access time, user type, and accessed function module information. M access users are determined based on the user access logs within a preset time window (such as one hour, one day, etc.), where M is an integer greater than or equal to 1. Then, the selected M access users are sorted in order from the front to the back of the access time to ensure the time seriality of the user access records, and an access user sequence is obtained, wherein the access user sequence includes M access user type identifiers and M access function module identifiers.

[0080] An interval time sequence obtaining module 15 is used to calculate the interval time between two adjacent visiting users in the visiting user sequence to obtain an interval time sequence;

[0081] An update access user sequence acquisition module 16 is used to perform concurrent access screening of the same data based on the interval time sequence, and to rearrange the access user sequence according to the screening result to obtain an update access user sequence;

[0082] A login password sequence obtaining module 17, configured to use the K password dynamic updaters, in combination with the M access user type identifiers and the updated access user sequence, to perform login password identification and obtain a login password sequence;

[0083] The data management module 18 is used to match the M access function module identifiers with the function module set to obtain an access function module sequence, send the login password sequence to the access user who updates the access user sequence in sequence, and manage the data in the access function module sequence.

[0084] Optionally, the access time intervals (ie, the differences in access time) between adjacent users in the access user sequence are calculated, and the interval time sequence is obtained according to the calculation results. The interval time sequence reflects the access intervals between adjacent access users.

[0085] Optionally, based on the interval time sequence, the access users are screened to identify concurrent access to the same data (e.g., multiple access users access the same data through different functional modules in a short period of time), and the access users at the back of the screening results are inserted into the position of the access users at the front in the sequence, and the access users are sorted in order according to their purpose (e.g., the access users who modify documents are ranked before the access users who query documents), and the access user sequence is then rearranged to ensure data consistency and access priority, and obtain an updated access user sequence. The updated access user sequence is the user access record that has been screened and rearranged.

[0086] Furthermore, according to the updated access user sequence and each access user type identifier, K password dynamic updaters are called to identify the login passwords of M access users to obtain M login passwords, and the login passwords are sorted according to the updated access user sequence to obtain the login password sequence.

[0087] Then, the M access function module identifiers are matched with the function module set to determine the function module accessed by each user, and the access function module sequence is obtained by serializing the updated access user sequence. The generated login password sequence is sent to the access user who updates the access user sequence in sequence to ensure that each user manages the data in the access function module. The technical effect of ensuring the security and compliance of data access is achieved.

[0088] In summary, the embodiments of the present application have at least the following technical effects:

[0089] This application effectively manages the user's access behavior, calculates the access interval, updates the access sequence, and securely generates and manages the login password. It achieves the technical effect of ensuring access security, data consistency, and effective user access, and realizes the goal of improving the data management reliability of the chronic disease data management platform.

[0090] Any steps of the platform described above may be stored as computer instructions or programs in an unlimited computer memory, and may be called and recognized by an unlimited computer processor to implement any platform in the embodiments of the present application, without any unnecessary restrictions.

[0091] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

[0092] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0094] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A multifunctional and integrated chronic disease data management platform, characterized by: The platform includes: A function module set acquisition module is used to acquire the function module set of the target data management platform; A user login coefficient obtaining module, used to interact with the login log of the target data management platform, perform user clustering decomposition on the login log, and obtain K user types and K user login coefficients, where K is an integer greater than or equal to 1; A dynamic password updater construction module is used to identify the dynamic login password update strategy based on the K user login coefficients, and construct K password dynamic updaters according to the identification results; respectively calculate the ratio of the K user login coefficients to the sum of the K user login coefficients, and use the difference between the ratio and 1 as K dynamic update factors, wherein the dynamic update factor is the maximum similarity between the updated login password and the historical login password; obtain K historical login password sets of K user types; and construct the K password dynamic updaters based on the K dynamic update factors and the K historical login password sets; A visiting user sequence obtaining module, used to obtain M visiting users in a preset time window, sort the M visiting users in order of visiting time from the beginning to the end, and obtain a visiting user sequence, where M is an integer greater than or equal to 1, wherein the M visiting users include M visiting user type identifiers and M access function module identifiers; An interval time sequence obtaining module, used for calculating the interval time between two adjacent visiting users in the visiting user sequence to obtain an interval time sequence; An update access user sequence acquisition module is used to perform concurrent access screening of the same data based on the interval time sequence, and to rearrange the access user sequence according to the screening result to obtain an update access user sequence; A login password sequence acquisition module, used to use the K password dynamic updaters, in combination with the M access user type identifiers and the updated access user sequence to perform login password identification, and obtain a login password sequence; The data management module is used to match the M access function module identifiers with the function module set to obtain an access function module sequence, send the login password sequence to the access user who updates the access user sequence in sequence, and manage the data in the access function module sequence.

2. The multifunctional integrated chronic disease data management platform according to claim 1, characterized in that: The functional module set includes a chronic disease full-process management module, an intervention follow-up management module, an injury monitoring management module and an analysis and prediction management module.

3. The multifunctional integrated chronic disease data management platform according to claim 1, characterized in that: The user login coefficient acquisition module is used for: Clustering the login logs using user type as an index to obtain K user types; Using the K user types as indexes, searching for login records of each user type in the login log to obtain K user login record sets; Perform feature decomposition analysis on the K user login record sets to obtain the K user login coefficients.

4. The multifunctional integrated chronic disease data management platform according to claim 3, characterized in that: The user login coefficient acquisition module is used for: Decomposing the K user login record sets according to the preset feature set to obtain a set of K user login durations, a set of K user login content change amounts, and a set of K user minimum interval durations between two adjacent logins; Performing feature concentration screening on the K user login duration sets, the K user login content change amount sets, and the K user two adjacent login minimum interval time sets, respectively, to determine the K concentrated user login durations, the K concentrated user login content change amounts, and the K concentrated user two adjacent login minimum interval time; The login coefficient identifier is used to respectively identify the login durations of the K concentrated users, the changes in the login contents of the K concentrated users, and the minimum interval between two adjacent logins of the K concentrated users to determine the login coefficients of the K users.

5. The multifunctional integrated chronic disease data management platform according to claim 4, characterized in that: The user login coefficient acquisition module is used for: Calculate the mean of the K user login duration sets respectively to obtain the mean of the K user login durations; Taking the average login duration of the K users as K initial iteration centers, inputting the K initial iteration centers into the weighted iteration formula to obtain K stage iteration centers; Perform multiple iterations based on the K stage iteration centers until the Euclidean distance between the stage iteration centers of two adjacent iterations is less than or equal to a preset Euclidean distance, thereby obtaining K target iteration centers; The K user login durations corresponding to the K target iteration centers are used as the K concentrated user login durations.

6. The multifunctional integrated chronic disease data management platform according to claim 5, characterized in that: The weighted iteration formula is: ； in, is the stage iteration center, is a Gaussian function, i is the number of multiple user login durations in the user login duration set whose distance to the initial iteration center is the preset iteration bandwidth, and i is an integer greater than or equal to 1. is the login duration of the i-th user among multiple user login durations whose distance to the initial iteration center is the preset iteration bandwidth, is the initial iteration center.

7. The multifunctional integrated chronic disease data management platform according to claim 1, characterized in that: The dynamic password updater building block is used to: Randomly generate K sample login password sets, and calculate the similarity between the K sample login password sets and the K historical login password sets to obtain K sample similarity sets; The K sample similarity sets are screened based on the K dynamic update factors, and sample login passwords corresponding to sample similarities greater than the K dynamic update factors are eliminated to obtain K identified sample login password sets; The K password dynamic updaters are constructed according to the K dynamic update factors, the K historical login password sets and the K identified sample login password sets.

Images