User information management method and system based on online diagnosis system

Abstract

The application relates to the field of artificial intelligence and discloses a user information management method and system based on an online diagnosis and treatment system, which is used for improving the user information management accuracy of the online diagnosis and treatment system. The method comprises the following steps: performing information change monitoring on user personal information; when a diagnosis and treatment information change event is monitored, determining target change information in the user personal information according to the diagnosis and treatment information change event; performing information attribute analysis on the target change information to obtain a target attribute type, and matching a target anomaly detection model corresponding to the target change information according to the target attribute type; inputting the target change information into the target anomaly detection model to perform information anomaly change detection, and obtaining an information anomaly detection result corresponding to each target user; generating an abnormal alarm priority corresponding to the target change information according to the target attribute type, and performing online diagnosis and treatment monitoring on a plurality of target users according to the abnormal alarm priority and the information anomaly detection result.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to a user information management method and system based on an online diagnosis and treatment system. Background Technology

[0002] Currently, with the rapid development of artificial intelligence technology, online diagnosis and treatment systems have greatly improved users' quality of life and the level of medical care and scientific research. These systems can quickly diagnose conditions based on images and text descriptions, thus improving diagnostic efficiency.

[0003] However, the online diagnosis and treatment system does not promptly track and warn of changes in user information in real time, resulting in lag and inaccuracy in the analysis of user information, meaning that the accuracy of existing solutions is low. Summary of the Invention

[0004] This invention provides a user information management method and system based on an online medical system, which is used to improve the accuracy of user information management in the online medical system.

[0005] The first aspect of this invention provides a user information management method based on an online medical system. The method includes: acquiring personal information of multiple target users from a preset online medical system database, and monitoring changes in the personal information of each target user according to a preset medical information management strategy; when a medical information change event is detected, determining target change information in the user's personal information based on the event; performing information attribute analysis on the target change information to obtain target attribute types, and matching a target anomaly detection model corresponding to the target change information based on the target attribute types; inputting the target change information into the target anomaly detection model for information anomaly change detection, obtaining information anomaly detection results for each target user; generating anomaly alarm priorities corresponding to the target change information based on the target attribute types, and performing online medical monitoring on the multiple target users based on the anomaly alarm priorities and the information anomaly detection results.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the step of obtaining user personal information of multiple target users from a preset online medical system database and monitoring information changes of user personal information of each target user according to a preset medical information management strategy includes: creating a database connection channel between multiple target users and the online medical system database; querying user personal information corresponding to each target user from the online medical system database based on the database connection channel, wherein the user personal information includes: user identity information and user historical medical information; setting a medical information management strategy corresponding to each target user according to the user historical medical information; generating a monitoring period according to the medical information management strategy, and monitoring information changes of user personal information of each target user according to the monitoring period.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of determining the target change information in the user's personal information based on the medical information change event when the medical information change event is detected includes: converting the user's personal information into a list to generate a user information list corresponding to the user's personal information; when the medical information change event is detected, extracting information change identifiers from the user information list to obtain target information change identifiers; and performing information detection and information recognition on the target information change identifiers according to a preset information change validity period to obtain target change information.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the step of performing information attribute analysis on the target change information to obtain the target attribute type, and matching the target anomaly detection model corresponding to the target change information according to the target attribute type, includes: performing information attribute relationship mapping analysis on the target change information according to a preset information attribute mapping relationship to obtain the target attribute type; constructing multiple candidate anomaly detection models based on the online diagnosis and treatment system database; and matching the target anomaly detection model corresponding to the target attribute type from the multiple candidate anomaly detection models.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the step of inputting the target change information into the target anomaly detection model for information anomaly change detection to obtain information anomaly detection results corresponding to each target user includes: inputting the target change information into the target anomaly detection model, wherein the target anomaly detection model includes: a feature extraction network, an embedding layer, a convolutional network, and a normalization layer; extracting feature elements from the target change information through the feature extraction network to obtain multiple feature elements; inputting the multiple feature elements into the embedding layer for vector encoding to obtain a feature input vector; inputting the feature input vector into the convolutional network for anomaly feature processing to obtain a target feature vector; inputting the target feature vector into the normalization layer for anomaly probability analysis to output target probability data; and generating information anomaly detection results corresponding to each target user based on the target probability data.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the step of generating an anomaly alarm priority corresponding to the target change information based on the target attribute type, and performing online diagnosis and monitoring of the multiple target users based on the anomaly alarm priority and the information anomaly detection result, includes: obtaining a weight value corresponding to the target change information based on the target attribute type; generating an anomaly alarm priority corresponding to the target change information based on the weight value; sorting the information anomaly detection result according to the anomaly alarm priority to obtain a target sequence; and performing online diagnosis and monitoring of the multiple target users based on the target sequence.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the user information management method based on the online diagnosis and treatment system further includes: acquiring historical diagnosis and treatment information change events of the target user, and determining whether the target user has at least two diagnosis and treatment information change events based on the historical diagnosis and treatment information change events; if so, calculating the interval time corresponding to the two diagnosis and treatment information change events; determining whether the interval time is greater than a preset time threshold; if it is greater, adjusting the priority of the abnormal alarm corresponding to the target user.

[0012] A second aspect of the present invention provides a user information management system based on an online medical system. The user information management system includes: an acquisition module, configured to acquire user personal information of multiple target users from a preset online medical system database, and to monitor information changes of the user personal information of each target user according to a preset medical information management strategy; a monitoring module, configured to determine target change information in the user personal information based on the medical information change event when a medical information change event is detected; an analysis module, configured to perform information attribute analysis on the target change information to obtain target attribute types, and to match a target anomaly detection model corresponding to the target change information based on the target attribute types; a detection module, configured to input the target change information into the target anomaly detection model for information anomaly change detection, and to obtain information anomaly detection results corresponding to each target user; and a processing module, configured to generate anomaly alarm priorities corresponding to the target change information based on the target attribute types, and to perform online medical monitoring of the multiple target users based on the anomaly alarm priorities and the information anomaly detection results.

[0013] Optionally, in a first implementation of the second aspect of the present invention, the acquisition module is specifically used for: creating a database connection channel between multiple target users and the online medical system database; querying user personal information corresponding to each target user from the online medical system database based on the database connection channel, wherein the user personal information includes: user identity information and user historical medical information; setting a medical information management strategy corresponding to each target user according to the user's historical medical information; generating a monitoring period according to the medical information management strategy, and monitoring changes in user personal information of each target user according to the monitoring period.

[0014] Optionally, in a second implementation of the second aspect of the present invention, the monitoring module is specifically used to: convert the user's personal information into a list to generate a user information list corresponding to the user's personal information; when a change event in medical information is detected, extract the information change identifier from the user information list to obtain a target information change identifier; and perform information detection and information recognition on the target information change identifier according to a preset effective time for information change to obtain target change information.

[0015] Optionally, in a third implementation of the second aspect of the present invention, the analysis module is specifically used to: perform information attribute relationship mapping analysis on the target change information according to a preset information attribute mapping relationship to obtain the target attribute type; construct multiple candidate anomaly detection models based on the online diagnosis and treatment system database; and match the target anomaly detection model corresponding to the target attribute type from the multiple candidate anomaly detection models.

[0016] Optionally, in a fourth implementation of the second aspect of the present invention, the detection module is specifically used for: inputting the target change information into the target anomaly detection model, wherein the target anomaly detection model includes: a feature extraction network, an embedding layer, a convolutional network, and a normalization layer; extracting feature elements from the target change information through the feature extraction network to obtain multiple feature elements; inputting the multiple feature elements into the embedding layer for vector encoding to obtain a feature input vector; inputting the feature input vector into the convolutional network for anomaly feature processing to obtain a target feature vector; inputting the target feature vector into the normalization layer for anomaly probability analysis to output target probability data; and generating an information anomaly detection result corresponding to each target user based on the target probability data.

[0017] Optionally, in a fifth implementation of the second aspect of the present invention, the processing module is specifically used to: obtain a weight value corresponding to the target change information based on the target attribute type; generate an anomaly alarm priority corresponding to the target change information according to the weight value; sort the information anomaly detection results according to the anomaly alarm priority to obtain a target sequence; and perform online diagnosis and monitoring of the multiple target users according to the target sequence.

[0018] Optionally, in a sixth implementation of the second aspect of the present invention, the user information management system based on the online diagnosis and treatment system further includes: an adjustment module, configured to acquire historical diagnosis and treatment information change events of a target user, and determine whether the target user has at least two diagnosis and treatment information change events based on the historical diagnosis and treatment information change events; if so, calculate the interval time corresponding to the two diagnosis and treatment information change events; determine whether the interval time is greater than a preset time threshold; if it is greater, adjust the priority of the abnormal alarm corresponding to the target user.

[0019] A third aspect of the present invention provides a user information management device based on an online diagnosis and treatment system, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the user information management device based on the online diagnosis and treatment system to execute the aforementioned user information management method based on the online diagnosis and treatment system.

[0020] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described user information management method based on an online medical system.

[0021] The technical solution provided by this invention involves monitoring changes in user personal information; when a change in medical information is detected, the target change information in the user's personal information is determined based on the change event; the target change information undergoes information attribute analysis to obtain the target attribute type, and a target anomaly detection model corresponding to the target change information is matched based on the target attribute type; the target change information is input into the target anomaly detection model for information anomaly change detection to obtain the information anomaly detection result for each target user; anomaly alarm priority corresponding to the target change information is generated based on the target attribute type, and online medical monitoring is performed on multiple target users based on the anomaly alarm priority and the information anomaly detection result. This invention improves the accuracy of user information management in the online medical system by monitoring information changes for each target user, analyzing the detected changes through a pre-built target anomaly detection model, and then performing online medical monitoring on multiple target users based on the anomaly analysis results. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of an embodiment of the user information management method based on an online diagnosis and treatment system according to the present invention; Figure 2 This is a schematic diagram of another embodiment of the user information management method based on an online diagnosis and treatment system according to the present invention; Figure 3 This is a schematic diagram of an embodiment of a user information management system based on an online diagnosis and treatment system according to the present invention; Figure 4 This is a schematic diagram of another embodiment of the user information management system based on the online diagnosis and treatment system in this invention. Detailed Implementation

[0023] This invention provides a user information management method and system based on an online medical consultation system, which improves the accuracy of user information management in the online medical consultation system. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device 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 units not explicitly listed or inherent to such processes, methods, products, or devices.

[0024] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the user information management method based on an online diagnosis and treatment system in this invention includes: 101. Obtain the personal information of multiple target users from the preset online diagnosis and treatment system database, and monitor the changes in the personal information of each target user according to the preset diagnosis and treatment information management strategy; It is understood that the executing entity of this invention can be a user information management system based on an online diagnosis and treatment system, or it can be a terminal or a server; the specific implementation is not limited here. This embodiment of the invention will be described using a server as an example.

[0025] It should be noted that the pre-set online medical system database stores historical monitoring data from all users of the system. Users can have their personal information collected via data acquisition devices within the system, including but not limited to blood pressure, heart rate, body temperature, weight, and height. Furthermore, the online medical system includes an expert medical database, which stores user data corresponding to different ailments. Upon receiving user data, the backend decision-making system uses the expert medical database to determine the ailment and then issues corresponding diagnostic analysis results. This online diagnosis and treatment system can be installed on smart hospital terminals and user personal terminals. After collecting user personal information, the system uploads it through a cloud computing platform. It can centrally process batches of user personal information uploaded by online diagnosis and treatment systems. Online diagnosis and treatment systems sharing a single cloud computing platform can be networked for centralized management. After the data is uploaded, the cloud computing platform performs preliminary parsing and processing. If multiple data points in the user's personal information are within the standard range, the data is not uploaded to the backend decision-making system, and a diagnosis and treatment instruction is sent to the online diagnosis and treatment system to optimize the user's personal information. If multiple data points in the user's personal information are outside the standard range, the user's personal information is uploaded to the backend decision-making system, which then formulates a diagnosis and treatment instruction and sends it back to the cloud computing platform, which then distributes it to the online diagnosis and treatment system. Furthermore, in this embodiment, the user's personal information for each target user is encrypted and encapsulated, allowing for separate storage and monitoring of information changes for each target user. Specifically, the server collects personal information of users used to provide medical services, extracts personal ID information from the tags entering the predetermined data reading area, receives personal security information through the data interface, checks whether the input personal security information is the same as the stored personal ID information, receives request items through the interface, searches for the requested data in the data corresponding to the extracted personal ID information, obtains the personal information of multiple target users, and further, the server monitors information changes of each user's personal information according to the preset medical information management strategy.

[0026] It should be noted that when monitoring information changes, the server uses a pre-defined field detection function for real-time detection, which improves the timeliness and accuracy of detecting changes in user personal information.

[0027] 102. When a change event in medical information is detected, determine the target changed information in the user's personal information based on the change event; Specifically, after detecting a field change event in a user's personal information, the system can identify the changed field identifier, determine the target changed field corresponding to the identifier from a pre-set API information database, and return the target changed field to the user's personal information via the API access interface. It should be noted that the server can automatically identify the changed fields when the API interface documentation changes in real time, extract the changed field data and update the API database. Then, by mapping the data to the fields actually used by the program, the server can find the required field values ​​based on the field mapping table in the database when the API changes, and directly extract the corresponding changed fields from the API database, ensuring the continuity of operation.

[0028] 103. Perform information attribute analysis on target change information to obtain target attribute types, and match the target anomaly detection model corresponding to the target change information based on the target attribute types; First, the server uses a full permutation algorithm to derive all attribute ranking schemes from the target change information. Based on the connection attributes between each pair of attribute indicators in the target change information, connection attribute information is added to each attribute ranking scheme. The MDS algorithm is then used to reduce the dimensionality of all attribute ranking schemes and cluster them for visualization analysis. The server obtains the target attribute type through interaction analysis and information attribute analysis between various views, and matches the target anomaly detection model corresponding to the target change information based on the target attribute type.

[0029] It should be noted that during model matching, the server determines keywords based on target attributes. Further, the server determines the corresponding target attribute type based on the determined keywords. At the same time, the server performs field type analysis based on the target change information to determine the corresponding field type. Finally, the server performs model matching based on the target attribute type and the field type to determine the corresponding target anomaly detection model.

[0030] 104. Input the target change information into the target anomaly detection model to detect information anomaly changes and obtain the information anomaly detection results for each target user; Specifically, the server calculates evaluation thresholds for assessing normality and abnormality based on detected target change information and environmental data. The calculated evaluation thresholds are compared with abnormal evaluation values ​​to determine the abnormality. If the evaluation threshold exceeds the adverse state judgment value representing an abnormality, the server calculates the abnormality arrival time corresponding to each evaluation judgment value based on the stored evaluation thresholds and the calculation time of the addition operation, and displays the abnormality. At the same time, the server obtains the information abnormality detection results corresponding to each target user.

[0031] 105. Generate abnormal alarm priorities corresponding to target change information based on target attribute type, and perform online diagnosis and monitoring for multiple target users based on abnormal alarm priorities and information anomaly detection results.

[0032] Specifically, the server generates anomaly alarm priorities corresponding to target change information based on the target attribute type. This involves the server receiving fault detection messages, retrieving sequence numbers from each message, and generating the corresponding anomaly alarm priorities based on these sequence numbers. Further, the server performs online diagnosis and monitoring for multiple target users based on the anomaly alarm priorities and information anomaly detection results. Specifically, the server primarily determines the corresponding response level based on the anomaly alarm priorities and generates response strategies based on the information anomaly detection results. Finally, the server performs online diagnosis and monitoring based on the aforementioned response levels and response strategies.

[0033] In this embodiment of the invention, information changes to user personal information are monitored. When a change event in medical information is detected, the target change information in the user's personal information is determined based on the change event. Information attribute analysis is performed on the target change information to obtain the target attribute type, and a target anomaly detection model corresponding to the target change information is matched according to the target attribute type. The target change information is input into the target anomaly detection model for information anomaly change detection to obtain the information anomaly detection result for each target user. An anomaly alarm priority corresponding to the target change information is generated according to the target attribute type, and online medical monitoring is performed on multiple target users based on the anomaly alarm priority and the information anomaly detection result. This invention improves the accuracy of user information management in the online medical system by monitoring information changes for each target user, analyzing the monitored changes through a pre-built target anomaly detection model, and then performing online medical monitoring on multiple target users based on the anomaly analysis results.

[0034] Please see Figure 2 Another embodiment of the user information management method based on an online diagnosis and treatment system in this invention includes: 201. Obtain the personal information of multiple target users from the preset online diagnosis and treatment system database, and monitor the changes in the personal information of each target user according to the preset diagnosis and treatment information management strategy; Specifically, database connection channels are created between multiple target users and the online medical system database; based on the database connection channels, user personal information corresponding to each target user is queried from the online medical system database, including user identity information and user historical medical information; medical information management strategies are set for each target user according to the user's historical medical information; a monitoring period is generated according to the medical information management strategy, and information changes of user personal information for each target user are monitored according to the monitoring period.

[0035] It should be noted that the personal information of multiple target users is stored through partitioned data, with the online diagnosis and treatment system database used to simultaneously contain digitized fields and other data in the same channel within a frame. Therefore, the server can combine fields and data in a common information field and transmit them frame by frame simultaneously on the same channel through a digital switching network. The switching network includes a common port with a digital interface connected to the port. The digital interface can separate and combine fields and data fields. The digital interface is connected to the server to create database connection channels between multiple target users and the online diagnosis and treatment system database. Furthermore, the server uses user personal information to indicate the configuration information of the storage system resources constituting the database. When changes are detected in the preset storage area to extract resources from the invalid preset storage area that constitutes the changed preset storage area as monitoring target resources, the server obtains performance information indicating the monitoring status to determine the object resources from the storage system. It judges whether the performance information of the monitoring target resources matches the pre-set strategy and sets the diagnosis and treatment information management strategy corresponding to each target user according to the user's historical diagnosis and treatment information. The server generates a listening period according to the diagnosis and treatment information management strategy and listens for information changes of user personal information for each target user according to the listening period. This application improves the efficiency of data listening by reducing the number of required ports and network channels.

[0036] 202. When a change event in medical information is detected, determine the target changed information in the user's personal information based on the change event; Specifically, user personal information is converted into a list to generate a user information list corresponding to the user's personal information; when a change event in medical information is detected, the information change identifier is extracted from the user information list to obtain the target information change identifier; according to the preset information change validity time, the target information change identifier is detected and identified to obtain the target change information.

[0037] This process involves: acquiring data table types of user personal information, generating corresponding type data, converting the user personal information into a list format, and generating a corresponding data list, i.e., a user information list corresponding to the user personal information. Further, the server, based on a preset standard data list template matching the type data, performs missing data column setting processing on the user information list to generate a corrected user information list. When a change in medical information is detected, the information change identifier is extracted from the user information list to obtain the target information change identifier. Based on a preset effective information change time, the target information change identifier is detected and identified to obtain the target change information.

[0038] During monitoring, the service can identify the changed field identifier of the user's personal information after detecting a field change event. Based on the changed field identifier, it determines the target changed field corresponding to the changed field identifier from the preset API information database. Through the API access interface, the target changed field is returned to the user's personal information. The service also performs information detection and identification on the target information change identifier according to the preset information change validity time to obtain the target change information. By mapping it with the fields actually used by the program, when the API changes, the server can look up the required field value according to the field mapping table in the database and directly extract the corresponding changed field from the API database, ensuring the continuity of operation.

[0039] 203. Perform information attribute analysis on the target change information to obtain the target attribute type, and match the target anomaly detection model corresponding to the target change information according to the target attribute type; Specifically, based on the pre-set information attribute mapping relationship, information attribute relationship mapping analysis is performed on the target change information to obtain the target attribute type; multiple candidate anomaly detection models are constructed based on the online diagnosis and treatment system database; and the target anomaly detection model corresponding to the target attribute type is matched from the multiple candidate anomaly detection models.

[0040] The server obtains historical user attribute information and stores or updates it to a local information storage table to establish a mapping relationship between attribute information storage address and interface. It also inserts historical user attribute information into the target change information and sends it to the server for attribute relationship mapping to obtain the target attribute type.

[0041] It should be noted that before model selection, the server collects target data, including historical and real-time target data. The target data is preprocessed and features are extracted. Using the historical target data as the training set, multiple parallel ensemble anomaly detection models based on local features are trained. The trained parallel ensemble anomaly detection models are used to infer the real-time target data and filter out the target's anomaly data. Specifically, the server matches the target anomaly detection model corresponding to the target attribute type from multiple candidate anomaly detection models. This application utilizes the relationships between local data to filter the base models, avoiding the cancellation between high-performing and low-performing base classifiers, and making better use of local data features.

[0042] 204. Input the target change information into the target anomaly detection model to detect information anomaly changes and obtain the information anomaly detection results for each target user; Specifically, target change information is input into a target anomaly detection model, which includes a feature extraction network, an embedding layer, a convolutional network, and a normalization layer. The feature extraction network extracts feature elements from the target change information to obtain multiple feature elements. These multiple feature elements are then input into the embedding layer for vector encoding to obtain a feature input vector. The feature input vector is then input into the convolutional network for anomaly feature processing to obtain a target feature vector. The target feature vector is then input into the normalization layer for anomaly probability analysis to output target probability data. Based on the target probability data, an anomaly detection result corresponding to each target user is generated.

[0043] It should be noted that the training process of this target anomaly detection model also includes determining n samples and corresponding label matrices in the training dataset. The elements in the label matrix indicate whether the i-th sample contains the object indicated by the j-th label. A feature extraction network is used to extract the feature matrix of the n samples, and a feature mapping network is used to obtain the predicted label matrix of the feature matrix. The elements in the predicted label matrix indicate the confidence that the i-th sample contains the object indicated by the j-th label. Based on the label matrix and the predicted label matrix, multiple feature elements are obtained. During recognition, the Viterbi algorithm is used. By calculating the maximum probability of the feature input vector during the transition process, recognition is performed based on the model corresponding to the maximum probability. Anomaly probability analysis is conducted, and target probability data is output. Based on the target probability data, information anomaly detection results corresponding to each target user are generated.

[0044] 205. Obtain the weight value corresponding to the target change information based on the target attribute type; 206. Generate the priority of abnormal alarms corresponding to target change information based on the weight value; 207. Sort the anomaly detection results according to the priority of the anomaly alarm to obtain the target sequence; Specifically, the evaluation attribute index information of the evaluation target is obtained. Each evaluation attribute index information includes multiple evaluation index information. Based on the evaluation index information, the evaluation index score of each evaluation index is calculated. The analytic hierarchy process (AHP) is used to determine the weight vector of the evaluation index and the weight vector of the evaluation attribute index. Based on the evaluation index weight vector, the weight value corresponding to the target change information is obtained. The server receives the anomaly alarm priority corresponding to the target change information based on the weight value, sorts the information anomaly detection results according to the anomaly alarm priority, and obtains the target sequence.

[0045] 208. Conduct online diagnosis and monitoring of multiple target users based on the target sequence.

[0046] Optionally, the system obtains the target user's historical medical information change events and determines whether the target user has at least two medical information change events based on these events. If so, it calculates the interval between the two medical information change events and determines whether the interval is greater than a preset time threshold. If it is, it adjusts the priority of the abnormal alarm corresponding to the target user.

[0047] Specifically, the system calculates click events related to changes in the data storage area of ​​the target user. The effective field change time ratio within each change cycle is set to 0.45 by default. In one change cycle, the system calculates the number of effective changed fields for the target user, which is 3 by default. Then, it calculates the time interval between two consecutive field changes and determines whether the interval is greater than a preset time threshold. If it is greater, the priority of the abnormal alarm corresponding to the target user is adjusted.

[0048] In this embodiment of the invention, information changes to user personal information are monitored. When a change event in medical information is detected, the target change information in the user's personal information is determined based on the change event. Information attribute analysis is performed on the target change information to obtain the target attribute type, and a target anomaly detection model corresponding to the target change information is matched according to the target attribute type. The target change information is input into the target anomaly detection model for information anomaly change detection to obtain the information anomaly detection result for each target user. An anomaly alarm priority corresponding to the target change information is generated according to the target attribute type, and online medical monitoring is performed on multiple target users based on the anomaly alarm priority and the information anomaly detection result. This invention improves the accuracy of user information management in the online medical system by monitoring information changes for each target user, analyzing the monitored changes through a pre-built target anomaly detection model, and then performing online medical monitoring on multiple target users based on the anomaly analysis results.

[0049] The above describes the user information management method based on the online diagnosis and treatment system in the embodiments of the present invention. The following describes the user information management system based on the online diagnosis and treatment system in the embodiments of the present invention. Please refer to [link / reference]. Figure 3 One embodiment of the user information management system based on the online diagnosis and treatment system in this invention includes: The acquisition module 301 is used to acquire the personal information of multiple target users from the preset online diagnosis and treatment system database, and to monitor the changes in the personal information of each target user according to the preset diagnosis and treatment information management strategy. The monitoring module 302 is used to determine the target change information in the user's personal information based on the medical information change event when a medical information change event is detected. The analysis module 303 is used to perform information attribute analysis on the target change information to obtain the target attribute type, and match the target anomaly detection model corresponding to the target change information according to the target attribute type. The detection module 304 is used to input the target change information into the target anomaly detection model to detect information anomaly changes and obtain the information anomaly detection result for each target user. The processing module 305 is used to generate an anomaly alarm priority corresponding to the target change information according to the target attribute type, and to perform online diagnosis and monitoring of the multiple target users according to the anomaly alarm priority and the information anomaly detection result.

[0050] In this embodiment of the invention, information changes to user personal information are monitored. When a change event in medical information is detected, the target change information in the user's personal information is determined based on the change event. Information attribute analysis is performed on the target change information to obtain the target attribute type, and a target anomaly detection model corresponding to the target change information is matched according to the target attribute type. The target change information is input into the target anomaly detection model for information anomaly change detection to obtain the information anomaly detection result for each target user. An anomaly alarm priority corresponding to the target change information is generated according to the target attribute type, and online medical monitoring is performed on multiple target users based on the anomaly alarm priority and the information anomaly detection result. This invention improves the accuracy of user information management in the online medical system by monitoring information changes for each target user, analyzing the monitored changes through a pre-built target anomaly detection model, and then performing online medical monitoring on multiple target users based on the anomaly analysis results.

[0051] Please see Figure 4 Another embodiment of the user information management system based on the online diagnosis and treatment system in this invention includes: The acquisition module 301 is used to acquire the personal information of multiple target users from the preset online diagnosis and treatment system database, and to monitor the changes in the personal information of each target user according to the preset diagnosis and treatment information management strategy. The monitoring module 302 is used to determine the target change information in the user's personal information based on the medical information change event when a medical information change event is detected. The analysis module 303 is used to perform information attribute analysis on the target change information to obtain the target attribute type, and match the target anomaly detection model corresponding to the target change information according to the target attribute type. The detection module 304 is used to input the target change information into the target anomaly detection model to detect information anomaly changes and obtain the information anomaly detection result for each target user. The processing module 305 is used to generate an anomaly alarm priority corresponding to the target change information according to the target attribute type, and to perform online diagnosis and monitoring of the multiple target users according to the anomaly alarm priority and the information anomaly detection result.

[0052] Optionally, the acquisition module 301 is specifically used for: creating database connection channels between multiple target users and the online diagnosis and treatment system database; querying user personal information corresponding to each target user from the online diagnosis and treatment system database based on the database connection channels, wherein the user personal information includes: user identity information and user historical diagnosis and treatment information; setting a diagnosis and treatment information management strategy for each target user according to the user's historical diagnosis and treatment information; generating a monitoring period according to the diagnosis and treatment information management strategy, and monitoring information changes of user personal information for each target user according to the monitoring period.

[0053] Optionally, the monitoring module 302 is specifically used to: convert the user's personal information into a list to generate a user information list corresponding to the user's personal information; when a change event in medical information is detected, extract the information change identifier from the user information list to obtain the target information change identifier; and perform information detection and information recognition on the target information change identifier according to a preset effective time for information change to obtain the target change information.

[0054] Optionally, the analysis module 303 is specifically used to: perform information attribute relationship mapping analysis on the target change information according to a preset information attribute mapping relationship to obtain the target attribute type; construct multiple candidate anomaly detection models based on the online diagnosis and treatment system database; and match the target anomaly detection model corresponding to the target attribute type from the multiple candidate anomaly detection models.

[0055] Optionally, the detection module 304 is specifically used for: inputting the target change information into the target anomaly detection model, wherein the target anomaly detection model includes: a feature extraction network, an embedding layer, a convolutional network, and a normalization layer; extracting feature elements from the target change information through the feature extraction network to obtain multiple feature elements; inputting the multiple feature elements into the embedding layer for vector encoding to obtain a feature input vector; inputting the feature input vector into the convolutional network for anomaly feature processing to obtain a target feature vector; inputting the target feature vector into the normalization layer for anomaly probability analysis to output target probability data; and generating information anomaly detection results corresponding to each target user based on the target probability data.

[0056] Optionally, the processing module 305 is specifically used for: obtaining the weight value corresponding to the target change information based on the target attribute type; generating an anomaly alarm priority corresponding to the target change information according to the weight value; sorting the information anomaly detection results according to the anomaly alarm priority to obtain a target sequence; and performing online diagnosis and monitoring on the multiple target users according to the target sequence.

[0057] Optionally, the user information management system based on the online diagnosis and treatment system further includes: The adjustment module 306 is used to acquire historical medical information change events of the target user, and determine whether the target user has at least two medical information change events based on the historical medical information change events; if so, calculate the interval time corresponding to the two medical information change events; determine whether the interval time is greater than a preset time threshold; if it is greater, adjust the priority of the abnormal alarm corresponding to the target user.

[0058] In this embodiment of the invention, information changes to user personal information are monitored. When a change event in medical information is detected, the target change information in the user's personal information is determined based on the change event. Information attribute analysis is performed on the target change information to obtain the target attribute type, and a target anomaly detection model corresponding to the target change information is matched according to the target attribute type. The target change information is input into the target anomaly detection model for information anomaly change detection to obtain the information anomaly detection result for each target user. An anomaly alarm priority corresponding to the target change information is generated according to the target attribute type, and online medical monitoring is performed on multiple target users based on the anomaly alarm priority and the information anomaly detection result. This invention improves the accuracy of user information management in the online medical system by monitoring information changes for each target user, analyzing the monitored changes through a pre-built target anomaly detection model, and then performing online medical monitoring on multiple target users based on the anomaly analysis results.

[0059] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0060] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0061] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A user information management method based on an online diagnosis and treatment system, characterized in that, The user information management method based on the online diagnosis and treatment system includes: The system retrieves personal information of multiple target users from a pre-set online medical system database and monitors changes in the personal information of each target user according to a pre-set medical information management strategy. When a change event in medical information is detected, the target change information in the user's personal information is determined based on the change event. The process involves: performing information attribute analysis on the target change information to obtain target attribute types; and matching the target attribute types with target anomaly detection models corresponding to the target change information. Specifically, this includes: performing information attribute relationship mapping analysis on the target change information based on preset information attribute mapping relationships to obtain target attribute types; constructing multiple candidate anomaly detection models based on the online diagnosis and treatment system database; and matching the target anomaly detection model corresponding to the target attribute type from the multiple candidate anomaly detection models. The process involves inputting the target change information into the target anomaly detection model for information anomaly change detection, thereby obtaining information anomaly detection results for each target user. Specifically, this includes: inputting the target change information into the target anomaly detection model, which comprises a feature extraction network, an embedding layer, a convolutional network, and a normalization layer; extracting feature elements from the target change information using the feature extraction network to obtain multiple feature elements; inputting the multiple feature elements into the embedding layer for vector encoding to obtain a feature input vector; inputting the feature input vector into the convolutional network for anomaly feature processing to obtain a target feature vector; inputting the target feature vector into the normalization layer for anomaly probability analysis to output target probability data; and generating information anomaly detection results for each target user based on the target probability data. Based on the target attribute type, an abnormal alarm priority corresponding to the target change information is generated, and online diagnosis and monitoring of the multiple target users are performed based on the abnormal alarm priority and the information anomaly detection results.

2. The user information management method based on an online diagnosis and treatment system according to claim 1, characterized in that, The process involves retrieving personal information of multiple target users from a pre-set online medical system database, and monitoring changes in the personal information of each target user according to a pre-set medical information management strategy. This includes: Create database connection channels between multiple target users and the database of the online diagnosis and treatment system; Based on the database connection channel, the user's personal information corresponding to each target user is queried from the online diagnosis and treatment system database, wherein the user's personal information includes: user identity information and user's historical diagnosis and treatment information; Based on the user's historical medical information, set up a medical information management strategy for each target user; A monitoring period is generated based on the aforementioned medical information management strategy, and information changes of each target user's personal information are monitored according to the monitoring period.

3. The user information management method based on an online diagnosis and treatment system according to claim 1, characterized in that, When a change event in medical information is detected, determining the target change information in the user's personal information based on the change event includes: The user's personal information is converted into a list to generate a user information list corresponding to the user's personal information; When a change event in medical information is detected, the information change identifier is extracted from the user information list to obtain the target information change identifier; Based on the preset effective time of information change, the target information change identifier is detected and identified to obtain the target change information.

4. The user information management method based on an online diagnosis and treatment system according to claim 1, characterized in that, The step of generating anomaly alarm priorities corresponding to the target change information based on the target attribute type, and performing online diagnosis and monitoring of the multiple target users based on the anomaly alarm priorities and the information anomaly detection results, includes: Obtain the weight value corresponding to the target change information based on the target attribute type; Generate anomaly alarm priority corresponding to the target change information based on the weight value; The abnormal information detection results are sorted according to the abnormal alarm priority to obtain the target sequence; Online diagnosis and monitoring are performed on the multiple target users based on the target sequence.

5. The user information management method based on an online diagnosis and treatment system according to claim 1, characterized in that, The user information management method based on the online diagnosis and treatment system also includes: Obtain historical medical information change events of the target user, and determine whether the target user has at least two medical information change events based on the historical medical information change events; If it exists, calculate the time interval between the two changes in medical information; Determine whether the interval time is greater than a preset time threshold; If the value is greater than the target user's, the priority of the abnormal alarm will be adjusted.

6. A user information management system based on an online diagnosis and treatment system, characterized in that, The user information management system based on the online diagnosis and treatment system includes: The acquisition module is used to obtain the personal information of multiple target users from the preset online diagnosis and treatment system database, and to monitor the changes in the personal information of each target user according to the preset diagnosis and treatment information management strategy. The monitoring module is used to determine the target change information in the user's personal information based on the monitoring event when a change event in medical information is detected. The analysis module is used to perform information attribute analysis on the target change information to obtain the target attribute type, and match the target anomaly detection model corresponding to the target change information according to the target attribute type; specifically, it includes: performing information attribute relationship mapping analysis on the target change information according to a preset information attribute mapping relationship to obtain the target attribute type; constructing multiple candidate anomaly detection models based on the online diagnosis and treatment system database; and matching the target anomaly detection model corresponding to the target attribute type from the multiple candidate anomaly detection models; A detection module is used to input the target change information into the target anomaly detection model for information anomaly change detection, and obtain information anomaly detection results for each target user. Specifically, it includes: inputting the target change information into the target anomaly detection model, wherein the target anomaly detection model includes: a feature extraction network, an embedding layer, a convolutional network, and a normalization layer; extracting feature elements from the target change information through the feature extraction network to obtain multiple feature elements; inputting the multiple feature elements into the embedding layer for vector encoding to obtain a feature input vector; inputting the feature input vector into the convolutional network for anomaly feature processing to obtain a target feature vector; inputting the target feature vector into the normalization layer for anomaly probability analysis to output target probability data; and generating information anomaly detection results for each target user based on the target probability data. The processing module is used to generate anomaly alarm priorities corresponding to the target change information based on the target attribute type, and to perform online diagnosis and monitoring of the multiple target users based on the anomaly alarm priorities and the information anomaly detection results.

7. The user information management system based on an online diagnosis and treatment system according to claim 6, characterized in that, The acquisition module is specifically used for: Create database connection channels between multiple target users and the database of the online diagnosis and treatment system; Based on the database connection channel, the user's personal information corresponding to each target user is queried from the online diagnosis and treatment system database, wherein the user's personal information includes: user identity information and user's historical diagnosis and treatment information; Based on the user's historical medical information, set up a medical information management strategy for each target user; A monitoring period is generated based on the aforementioned medical information management strategy, and information changes of each target user's personal information are monitored according to the monitoring period.

8. The user information management system based on the online diagnosis and treatment system according to claim 7, characterized in that, The monitoring module is specifically used for: The user's personal information is converted into a list to generate a user information list corresponding to the user's personal information; When a change event in medical information is detected, the information change identifier is extracted from the user information list to obtain the target information change identifier; Based on the preset effective time of information change, the target information change identifier is detected and identified to obtain the target change information.

Images