A smart healthcare service big data management system

Abstract

This invention discloses a smart healthcare service big data management system, belonging to the field of smart healthcare service technology. It includes an information service module, an island identification module, a service planning module, and a data analysis module. The information service module is used to set and update the information service map. The island identification module is used to perform data island analysis, acquire medical data collection records from various user entities, obtain the information service map, and perform real-time analysis of the medical data collection records based on the information service map to determine the data type of the island. The service planning module is used to divide the information service map into several service analysis areas. The data analysis module is used to analyze the collected medical data in the corresponding service analysis areas according to preset management items, obtain the monitoring and management results of the management items in the corresponding service analysis areas, identify the data type of the island in the corresponding service analysis areas, and perform deviation analysis on the corresponding management items based on the data type of the island to obtain the island impact value.

Description

Technical Field

[0001] This invention belongs to the field of smart healthcare service technology, specifically a smart healthcare service big data management system. Background Technology

[0002] Smart healthcare is a specialized medical term that has emerged in recent years. It utilizes advanced technologies such as the Internet of Things, big data, and cloud computing to create regional medical information platforms for health records, enabling interaction between patients, medical staff, medical institutions, and medical equipment, gradually achieving the goal of informatization. Through smart healthcare, health service institutions can ensure service quality and improve service efficiency; public health institutions can effectively carry out disease management, health management, emergency management, and health education.

[0003] However, existing smart healthcare systems still have some shortcomings in processing big data and managing medical services. For example, while smart healthcare service big data management systems aim to achieve data interconnection, in practical applications, the problem of data silos still exists. In particular, with changes in hospital systems and technologies, data silos are in a dynamic state of flux, making it impossible to fully resolve the data silo problem. Moreover, the data silo problem will prevent the representativeness of medical results based on medical data analysis from reaching its optimal level.

[0004] Based on this, the invention provides a smart medical service big data management system. Summary of the Invention

[0005] To address the problems existing in the above solutions, the present invention provides a smart healthcare service big data management system.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A smart healthcare service big data management system includes an information service module, an island identification module, a service planning module, and a data analysis module;

[0008] The information service module is used to set and update the information service graph, which is used to display the subject information of each subject user and the scope of medical data.

[0009] Furthermore, the methods for setting up the information service map include:

[0010] Real-time collection of entity information from various entities, and generation of initial information graphs based on the entity information;

[0011] According to the initial information map, a corresponding information identification unit is configured for the main user. The information identification unit is used to identify the unit data range of the corresponding branch unit within the main user; the unit data range of the corresponding branch unit within the main user is identified in real time through the information identification unit.

[0012] The data ranges of each unit are integrated into the medical data range of the main user; information is supplemented to the initial information graph based on the medical data range of each main user, and the initial information graph after information supplementation is marked as an information service graph.

[0013] Furthermore, the identification method for the information identification unit includes:

[0014] Establish a data recognition model, the expression of which is:

[0015] ;

[0016] In the formula: s i The input data represents the corresponding medical data type within the branch unit, i = 1, 2, ..., n, where n is the number of medical data types within the branch unit; the output data is the data identification value SU(s). i The data identification value is 1 or 0;

[0017] The medical data types of branch units are identified in real time, and the medical data types are analyzed through a data identification model to obtain the data identification values ​​of the medical data types.

[0018] Medical data types with a data identification value of 1 within a branch unit are integrated into the unit data range of that branch unit.

[0019] The isolated data identification module is used to perform data isolated data analysis, acquire medical data collection records of each subject user in real time, obtain information service graphs, analyze medical data collection records in real time based on information service graphs, determine the data type of isolated data, and issue isolated data warnings to relevant management personnel based on the data type of isolated data.

[0020] Furthermore, the cause of the islanding is identified based on the islanding data type, and the cause of the islanding is displayed to the administrators.

[0021] Furthermore, a solution is determined based on the cause of the islanding issue, and the solution is then presented to the administrators.

[0022] Furthermore, the degree of impact is determined based on the type of isolated data, and this degree of impact is then displayed to the management personnel.

[0023] Furthermore, real-time analysis of medical data collection records is performed based on the information service map, including:

[0024] The medical data collection records are classified in real time according to the preset unit duration to obtain corresponding unit record data; the unit data range of the unit record data is identified according to the information service map; and the unit identification record corresponding to the unit record data is identified.

[0025] The unit identification record is calibrated according to the unit data range to obtain the type of the branch unit to be analyzed;

[0026] The interval duration of the type to be analyzed is identified in real time, and the type to be analyzed is determined to be an isolated data type based on the interval duration.

[0027] The service planning module is used to divide the information service map into regions, forming several service analysis regions.

[0028] Furthermore, methods for dividing the information service map into regions include:

[0029] The information service map is divided into several unit areas according to the residential community; data on the medical treatment choices of various medical entities in the corresponding unit areas are collected;

[0030] The medical treatment selection data is categorized according to disease type to obtain the corresponding medical treatment classification data for each disease type;

[0031] Based on the medical treatment classification data corresponding to the unit area, the proportion of medical treatment for the corresponding subject user is calculated, and the proportions of medical treatment are integrated into the disease unit data of the disease type in the unit area; the disease unit data of each unit area are merged to obtain the basic analysis area of ​​the corresponding subject user for the corresponding disease type.

[0032] Identify management items, merge the corresponding basic analysis areas based on the management items, and obtain the corresponding service analysis areas.

[0033] Furthermore, the disease unit data from each unit region are merged, including:

[0034] Identify the main user with the highest medical treatment rate in the disease unit data, and merge that unit area into the basic analysis area corresponding to the disease type of the main user.

[0035] This process continues until all unit regions have been merged, thus completing the merge analysis.

[0036] The data analysis module is used to analyze the collected medical data of the corresponding service analysis area according to the preset management items, and obtain the monitoring and management results of the corresponding management items in the corresponding service analysis area; identify the isolated data type of the corresponding service analysis area, perform deviation analysis on the corresponding management items according to the isolated data type, and obtain the isolated impact value; and supplement the isolated impact value into the corresponding monitoring and management results.

[0037] Furthermore, methods for performing deviation analysis on corresponding management items based on the isolated data type include:

[0038] Identify isolated data types and perform analysis and simulation based on them. The simulation method involves conducting separate simulations and analyses on medical data collection that includes isolated data types and medical data collection that does not include isolated data types. Calculate the corresponding result deviation values ​​and mark the corresponding result deviation values ​​as isolated impact values.

[0039] Compared with the prior art, the beneficial effects of the present invention are:

[0040] Through the coordinated efforts of the information service module, data silo identification module, service planning module, and data analysis module, the system can perceive changes in hospital systems and technologies in real time. Through innovative data integration and collaboration mechanisms, it dynamically adjusts data connection strategies, breaks down data barriers, and achieves seamless connection and real-time sharing between different medical data sources. By solving the data silo problem, medical data can be comprehensively and accurately aggregated and analyzed. Complete and high-quality datasets can more realistically reflect the actual situation of medical services, thereby improving the accuracy and reliability of medical data analysis. This will make medical decisions and treatment plans based on the analysis results more scientific and targeted, providing patients with higher-quality medical services and effectively improving medical quality and patient satisfaction. By integrating various medical data resources, the system achieves unified data management and efficient utilization, enabling it to process massive amounts of medical data more quickly and accurately, providing medical institutions with more comprehensive and in-depth medical service management support. At the same time, the system's stability and scalability are significantly improved, better adapting to the future development needs of medical business and providing strong support for the sustainable development of smart healthcare. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0043] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0044] like Figure 1As shown, a smart healthcare service big data management system includes an information service module, an island identification module, a service planning module, and a data analysis module.

[0045] The information service module is used to identify, in real time, various hospitals, medical institutions, clinics, and other main users within the service area, and to collect the main information of each main user in real time. This main information includes location information, information about the various medical departments they possess, names, and other relevant information. An initial information map is generated based on this main user information, displaying the main user information in a map-based format. Based on the initial information map, corresponding information identification units are configured for each main user. These information identification units are used to statistically analyze the types of medical data generated by each medical department within the corresponding main user entity, i.e., to statistically analyze the types of medical data that the medical department has for big data medical services. Different formats of the same data type are considered the same type of medical data. Medical departments within the main user entity are marked as branch units. The information identification units identify the medical data types of each branch unit corresponding to the main user entity in real time, integrating them into the unit data range of the branch unit, and then integrating the data ranges of each unit into the main user entity's medical data range. The initial information map is supplemented with information based on the medical data ranges of each main user entity, i.e., the corresponding medical data ranges are added, and the current initial information map is marked as an information service map.

[0046] In one embodiment, the information identification unit can be implemented based on existing technologies, such as the most common method of input and update by staff within the corresponding user group; or it can be based on intelligent identification technology to identify various medical data types of the branch unit.

[0047] In one embodiment, the method for the information identification unit to statistically analyze the medical data types corresponding to the branch units includes:

[0048] Acquire historical medical data of various formats and types that may exist in each branch unit, including different types of the same data; establish data standards for medical data types that conform to the application of big data in medical services, which are generally a set of various required medical data types. Data belonging to this set is considered to meet the data standards, although other representations are also acceptable; set up a training set based on historical medical data and data standards, and build a data recognition model based on the training set. The expression of the data recognition model is:

[0049] ;

[0050] In the formula: s i The input data represents the corresponding medical data type within the branch unit, i = 1, 2, ..., n, where n is the number of medical data types within the branch unit; the output data is the data identification value SU(s). i The data identification value is 1 or 0;

[0051] The system identifies the types of medical data in branch units in real time, analyzes the identified medical data types through a data identification model, and obtains the corresponding data identification values ​​for each medical data type.

[0052] Medical data types with a data identification value of 1 are integrated into the unit data range of the corresponding branch unit.

[0053] The data silo identification module is used to perform data silo analysis, acquire medical data collection records of each subject user in real time, and collect medical data collection records based on the data collection needs of medical service big data. The medical data collection records include various medical data records collected from the subject user, which are a continuously accumulated record; acquire information service graph, analyze the medical data collection records in real time according to the information service graph, determine the data type of silo, and issue silo warnings to relevant management personnel.

[0054] In one embodiment, the reasons for the islanding of islanded data types can be analyzed, and the reasons for the islanding can be presented to management personnel.

[0055] In one embodiment, based on the above embodiments, a corresponding solution can be determined based on the cause of the islanding, and the solution can be synchronously sent to the administrator; the specific solution can be determined based on existing methods, such as changing the data format or adjusting the communication protocol.

[0056] In one embodiment, the impact of the isolated data type on the data analysis results after intelligent big data can also be analyzed. The degree of impact can be measured by simulating the deviation between the results with and without the isolated data type.

[0057] In one embodiment, real-time analysis of medical data collection records based on an information service graph includes:

[0058] Based on the information service map, identify the medical data range of the corresponding medical data collection records, identify the various medical data types corresponding to the corresponding branch units in the medical data collection records, and integrate the unit identification records marked as the branch units; calibrate the unit identification records of each branch unit according to the medical data range, determine the missing medical data types, and then determine the isolated data types.

[0059] In one embodiment, to further improve recognition accuracy, real-time analysis of medical data collection records is performed based on the information service map, including:

[0060] The preset unit duration is typically one day, two days, three days, or one week. Medical data collection records are categorized in real-time based on the unit duration to obtain corresponding unit record data. Specifically, medical data collection records within the time period corresponding to the current time and unit duration are marked as unit record data. The unit data range corresponding to the unit record data is identified using the information service map. The medical data types corresponding to the unit record data are identified and integrated, marked as unit identification records. The unit identification records are calibrated based on the unit data range, and medical data types not present in the unit identification records are marked as types to be analyzed.

[0061] The interval for real-time identification of the type to be analyzed refers to the time interval between the last identification of the type to be analyzed. If it is the first time it is used, it is the time interval between the start time of use. The interval is used to determine whether the type to be analyzed is an isolated data type. That is, the interval is compared with the preset time, and the types to be analyzed that are longer than the preset time are marked as isolated data types.

[0062] In one embodiment, real-time analysis of medical data collection records based on an information service graph can also be performed to determine the type of isolated data based on other existing methods.

[0063] The service planning module is used to divide the information service map into regions, forming several service analysis regions.

[0064] In one embodiment, a method for dividing an information service map into regions includes:

[0065] The information service map is divided into several unit areas, which are divided in the form of residential communities, i.e., one community corresponds to one unit area; the medical selection data of each unit area is determined based on the medical data of each medical entity, that is, the medical entity selected by patients in the unit area when they have different diseases. Detailed patient information is not required, which reduces the risk of patient information leakage. That is, the disease type and distribution of each patient can be determined at the main user, and then the data is summarized and distributed to the corresponding unit areas.

[0066] The medical treatment selection data is classified according to disease type, and the corresponding medical treatment selection data for each disease type is obtained and integrated into medical treatment classification data for that disease type.

[0067] Based on the medical treatment classification data of each subject user corresponding to the disease type in this unit area, the proportion of medical treatment for the corresponding subject user in this unit area is calculated, that is, the proportion of medical treatment is calculated based on the number of medical treatments, the number of patients, etc.; integrated into the disease unit data of this disease type in this unit area, that is, the disease unit data consists of the proportion of medical treatment for each subject user; the disease unit data of each unit area are merged to obtain the basic analysis area of ​​the corresponding subject user for the corresponding disease type.

[0068] Identify the management items to be analyzed later. Management items include items that need to be analyzed and monitored, such as the use of various drugs, the number of patients with various diseases, disease trends, and medical costs. Merge the corresponding basic analysis areas according to the management items to obtain the service analysis areas corresponding to the management items.

[0069] In one embodiment, merging disease unit data from each unit region includes:

[0070] Identify the disease type and the proportion of each medical visit corresponding to the disease unit data, assign the unit area to the subject user corresponding to the highest proportion of medical visits, and merge the unit areas corresponding to the subject user to form the basic analysis area for the corresponding disease type for that subject user.

[0071] In one embodiment, merging disease unit data from each unit region includes:

[0072] It is also possible to analyze the medical treatment classification data corresponding to the disease type in the unit area, and determine whether the differences between the monitoring and management results of the corresponding management needs in the subsequent process meet the allowable requirements. If the requirements are met, the data is merged. Subsequently, a new medical treatment ratio is determined based on the merged medical treatment classification data, and then the data is merged again according to the above embodiment. For the main user whose medical treatment classification data is merged, if the medical treatment ratio of the merged medical treatment classification data is the highest, then the unit area belongs to the basic analysis area of ​​the corresponding main user. The same unit area can appear in multiple basic analysis areas.

[0073] In one embodiment, merging the corresponding basic analysis regions based on management items includes:

[0074] Identify the basic analysis areas corresponding to the management requirements. For example, for drug monitoring, determine the corresponding basic analysis area based on the disease associated with the drug. Analyze the differences between the basic analysis areas on the relevant item, such as drug usage. Determine the differences in drug usage in the corresponding areas. The differences can be statistically calculated on a per capita basis. Merge the differences within the allowable range, and do not merge the differences otherwise, resulting in several service analysis areas. The corresponding difference requirements can be set according to actual needs. Alternatively, the differences in the analysis results can be merged. For example, analyze the data corresponding to the basic analysis areas separately to obtain two analysis results. Calculate the difference between the two analysis results and merge the differences within the allowable error range.

[0075] In one embodiment, the corresponding basic analysis regions can be merged according to the management items. Merging analysis can also be performed based on existing methods, such as merging analysis based on clustering algorithms, deep learning algorithms, etc.

[0076] In one embodiment, the information service map is divided into regions. The corresponding radiation range of the main user is determined based on the historical medical data of the main user, and the regions are divided according to the radiation range. For overlapping parts, they can be allocated proportionally. If the differences in the subsequent regulatory results are within the allowable range, they can also be merged to reduce the number of regions.

[0077] In one embodiment, the information service map can be divided into regions, or it can be divided based on other existing methods, such as intelligent division based on intelligent models built using machine learning, deep learning algorithms, etc.

[0078] The data analysis module is used to analyze the collected medical data of the corresponding service analysis area according to preset management items, and obtain the monitoring and management results of the corresponding management items in the corresponding service analysis area. Management items include the use of various drugs, the number of patients with various diseases, disease change trends, medical treatment costs, etc. The monitoring and management results are generally displayed in the form of curves, such as the monitoring demand for medical treatment costs for influenza, the monitoring curve for the number of influenza patients, and the drug consumption curve for the corresponding service analysis area. The module also identifies the isolated data types corresponding to the corresponding service analysis area, analyzes the possible management deviations of the corresponding management items based on the isolated data types, and determines the isolated impact value. The isolated impact value is then added to the corresponding monitoring and management results to facilitate managers' understanding of the possible deviations in the monitoring and management results.

[0079] In one embodiment, the setting and data analysis of management items are performed in accordance with the management items of the existing medical service management system; the difference lies in that after regional division, additional analysis is performed for the corresponding regions.

[0080] In one embodiment, a method for performing deviation analysis on corresponding management items based on the isolated data type includes:

[0081] Identify isolated data types, conduct analysis and simulation based on isolated data types, determine the deviation between the regulatory monitoring results analyzed when data of isolated data types are missing and the regulatory monitoring results analyzed when data of isolated data types are not missing, and mark it as the isolated impact value; corresponding historical medical data can be used for simulation analysis to determine the possible deviation value of the analysis results when data of the corresponding isolated data types are missing, and then match an isolated impact value that is closest to the background corresponding to the service analysis area.

[0082] In one embodiment, deviation analysis is performed on the corresponding management items based on the isolated data type. Deviation analysis can be performed based on existing methods, such as using historical medical data to build a training set, building a deviation analysis model based on deep learning algorithms, training the model using the training set, and performing intelligent analysis using the successfully trained deviation analysis model.

[0083] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0084] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A smart healthcare service big data management system, characterized in that, It includes an information service module, an island identification module, a service planning module, and a data analysis module; The information service module is used to set and update the information service graph, which is used to display the subject information of each subject user and the scope of medical data. The isolated data identification module is used to perform data isolated data analysis, acquire medical data collection records of each subject user in real time, obtain information service graphs, analyze medical data collection records in real time based on information service graphs, determine the data type of isolated data, and issue isolated data warnings to relevant management personnel based on the data type of isolated data. The service planning module is used to divide the information service map into regions, forming several service analysis regions; The data analysis module is used to analyze the collected medical data of the corresponding service analysis area according to the preset management items, and obtain the monitoring and management results of the corresponding management items in the corresponding service analysis area; identify the isolated data type of the corresponding service analysis area, and perform deviation analysis on the corresponding management items according to the isolated data type to obtain the isolated impact value; The impact values ​​of isolated islands will be added to the corresponding monitoring and management results; Methods for dividing information service maps into regions include: The information service map is divided into several unit areas according to the residential community; data on the medical treatment choices of various medical entities in the corresponding unit areas are collected; The medical treatment selection data is categorized according to disease type to obtain the corresponding medical treatment classification data for each disease type; Based on the medical treatment classification data corresponding to the unit area, the proportion of medical treatment for the corresponding subject user is calculated, and the proportions of medical treatment are integrated into the disease unit data of the disease type in the unit area; the disease unit data of each unit area are merged to obtain the basic analysis area of ​​the corresponding subject user for the corresponding disease type. Identify management items, merge the corresponding basic analysis areas based on the management items, and obtain the corresponding service analysis areas.

2. The smart healthcare service big data management system according to claim 1, characterized in that, The methods for setting up an information service map include: Real-time collection of entity information from various entities, and generation of initial information graphs based on the entity information; According to the initial information map, a corresponding information identification unit is configured for the main user. The information identification unit is used to identify the unit data range of the corresponding branch unit within the main user; the unit data range of the corresponding branch unit within the main user is identified in real time through the information identification unit. The data ranges of each unit are integrated into the medical data range of the main user; information is supplemented to the initial information graph based on the medical data range of each main user, and the initial information graph after information supplementation is marked as an information service graph.

3. The smart healthcare service big data management system according to claim 2, characterized in that, The identification methods for information recognition units include: Establish a data recognition model, the expression of which is: ； In the formula: s i The input data represents the corresponding medical data type within the branch unit, i = 1, 2, ..., n, where n is the number of medical data types within the branch unit; the output data is the data identification value SU(s). i The data identification value is 1 or 0; The medical data types of branch units are identified in real time, and the medical data types are analyzed through a data identification model to obtain the data identification values ​​of the medical data types. Medical data types with a data identification value of 1 within a branch unit are integrated into the unit data range of that branch unit.

4. The smart healthcare service big data management system according to claim 1, characterized in that, Identify the cause of the islanding based on the islanding data type, and then display the cause of the islanding to the administrators.

5. The smart healthcare service big data management system according to claim 1, characterized in that, The degree of impact is determined based on the type of isolated data, and this degree of impact is then displayed to the management personnel.

6. The smart healthcare service big data management system according to claim 2, characterized in that, Real-time analysis of medical data collection records based on the information service map, including: The medical data collection records are classified in real time according to the preset unit duration to obtain corresponding unit record data; the unit data range of the unit record data is identified according to the information service map; and the unit identification record corresponding to the unit record data is identified. The unit identification record is calibrated according to the unit data range to obtain the type of the branch unit to be analyzed; The interval duration of the type to be analyzed is identified in real time, and the type to be analyzed is determined to be an isolated data type based on the interval duration.

7. The smart healthcare service big data management system according to claim 1, characterized in that, The disease unit data from each unit region is merged, including: Identify the main user with the highest medical treatment rate in the disease unit data, and merge that unit area into the basic analysis area corresponding to the disease type of the main user. This process continues until all unit regions have been merged, thus completing the merge analysis.

8. The smart healthcare service big data management system according to claim 1, characterized in that, Methods for performing deviation analysis on corresponding management items based on isolated data types include: Identify isolated data types and perform analysis and simulation based on them. The simulation method involves conducting separate simulations and analyses on medical data collection that includes isolated data types and medical data collection that does not include isolated data types. Calculate the corresponding result deviation values ​​and mark the corresponding result deviation values ​​as isolated impact values.

Images