Intelligent medical service big data management system

Abstract

The invention discloses a smart medical service big data management system, which belongs to the technical field of smart medical services and comprises an information service module, an island identification module, a service planning module and a data analysis module. The information service module is used for setting and updating an information service graph; the island identification module is used for carrying out data island analysis, acquiring medical data acquisition records of each main user, acquiring an information service graph, carrying out real-time analysis on the medical data acquisition records according to the information service graph, and determining an island data type; the service planning module is used for carrying out regional division on the information service graph to form a plurality of service analysis regions; the data analysis module is used for analyzing the collected medical data of the corresponding service analysis area according to a preset management item to obtain a monitoring management result of the management item in the corresponding service analysis area; and identifying the island data type of the corresponding service analysis area, and performing deviation analysis on the corresponding management item according to the island data type to obtain an island influence value.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart medical services, and specifically is a smart medical service big data management system. Background Art

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

[0003] However, the existing smart medical system still has some shortcomings in processing big data and managing medical services. For example, the smart medical service big data management system aims to achieve data interconnection and interoperability, but in actual applications, there is still the problem of data silos, especially with the changes in hospital systems and technologies, data silos are in dynamic changes, which makes it impossible to fully solve the problem of data silos; and due to the problem of data silos, the representativeness of medical results based on medical data analysis cannot reach the best.

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

[0005] In order to solve the problems existing in the above solutions, the present invention provides a smart medical service big data management system.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A smart medical service big data management system, including 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 an information service map, and the information service map is used to display the subject information and medical data range of each subject user.

[0007] Furthermore, the method for setting the information service graph includes: Collect the subject information of each subject user in real time, and generate an initial information graph based on the subject information; According to the initial information graph, a corresponding information identification unit is configured for the main user, and the information identification unit is used to identify the unit data range of the corresponding branch unit in the main user; the unit data range of the corresponding branch unit in 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; the initial information graph is supplemented with information according to the medical data range of each main user, and the initial information graph after the information supplement is marked as an information service graph.

[0008] Furthermore, the identification method of the information identification unit includes: Establish a data recognition model. The expression of the data recognition model is: ; Where: s i is the input data, which indicates the corresponding medical data type in the branch unit, i=1, 2, ..., n, where n is the number of medical data types in the branch unit; the output data is the data identification value SU (s i ), the data identification value is 1 or 0; Identify in real time the type of medical data possessed by the branch unit, analyze the type of medical data through a data identification model, and obtain a data identification value of the type of medical data; The medical data types with data identification values ​​of 1 in the branch unit are integrated into the unit data range of the branch unit.

[0009] The island identification module is used to perform data island analysis, obtain medical data collection records of each subject user in real time, obtain an information service map, perform real-time analysis on the medical data collection records based on the information service map, determine the type of island data, and issue island warnings to relevant managers based on the type of island data.

[0010] Furthermore, the cause of the islanding is identified according to the islanding data type, and the cause of the islanding is displayed to the management personnel.

[0011] Furthermore, a solution is determined according to the cause of the island, and the solution is presented to management personnel.

[0012] Furthermore, the impact degree is determined according to the island data type, and the impact degree is displayed to the management personnel.

[0013] Furthermore, the medical data collection records are analyzed in real time according to the information service graph, including: Preset unit duration, classify the medical data collection record in real time according to the unit duration, and obtain corresponding unit record data; identify the unit data range of the unit record data according to the information service graph; and identify the unit identification record corresponding to the unit record data; Calibrate the unit identification record 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 whether the type to be analyzed is an island data type is determined according to the interval duration.

[0014] The service planning module is used to divide the information service graph into regions to form a plurality of service analysis regions.

[0015] Furthermore, the method for dividing the information service graph into regions includes: Divide the information service map into several unit areas according to residential areas; collect the medical treatment selection data of each medical subject in the corresponding unit area; Classify the medical treatment selection data according to the disease type, and obtain the medical treatment classification data corresponding to the corresponding disease type; According to the medical classification data corresponding to the unit area, the medical proportion corresponding to the corresponding subject user is counted, and each medical proportion is integrated into the disease unit data of the disease type in the unit area; according to the disease unit data of each unit area, the basic analysis area of ​​the corresponding subject user for the corresponding disease type is obtained by merging; Identify the management items, merge the corresponding basic analysis areas according to the management items, and obtain the corresponding service analysis areas.

[0016] Furthermore, the disease unit data of each unit area are merged, including: Identify the main user with the highest proportion of medical treatment in the disease unit data, and merge the unit area into the basic analysis area corresponding to the disease type of the main user; And so on, until all unit areas are merged, and the merged analysis is completed.

[0017] The data analysis module is used to analyze the collected medical data in 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 island data type of the corresponding service analysis area, and perform deviation analysis on the corresponding management items according to the island data type to obtain the island impact value; and add the island impact value to the corresponding monitoring and management results.

[0018] Furthermore, the method for performing deviation analysis on corresponding management items according to the island data type includes: Identify the island data type, and perform analysis and simulation based on the island data type. The simulation method is to separately simulate and analyze the collected medical data including the island data type and the collected medical data excluding the island data type, calculate the corresponding result deviation value, and mark the corresponding result deviation value as the island impact value.

[0019] Compared with the prior art, the present invention has the following beneficial effects: Through the cooperation between the information service module, the island identification module, the service planning module, and the data analysis module, the changing factors of the hospital system and technology can be perceived in real time. Through the innovative data integration and coordination mechanism, the data connection strategy can be dynamically adjusted to break down the data barriers and realize the seamless connection and real-time sharing between different medical data sources. By solving the problem of data islands, medical data can be comprehensively and accurately gathered and analyzed. A complete and high-quality data set can more realistically reflect the actual situation of medical services, thereby improving the accuracy and reliability of medical data analysis. This will make the medical decisions and treatment plans based on the analysis results more scientific and targeted, provide patients with better medical services, and effectively improve the quality of medical care and patient satisfaction. By integrating various medical data resources and realizing unified management and efficient use of data, the system can process massive medical data more quickly and accurately, and provide more comprehensive and in-depth medical service management support for medical institutions. At the same time, the stability and scalability of the system have also been significantly improved, which can better adapt to the development needs of future medical business and provide strong guarantees for the sustainable development of smart medical care. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] like Figure 1 As shown, a smart medical service big data management system 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 identify the main users such as hospitals, medical institutions, clinics, etc. in the docking service area in real time, and collect the main information of each main user in real time. The main information includes location information, information of each medical department, name and other related information; generate an initial information map based on each main information, that is, display the main information of each main user in the form of a map; configure a corresponding information identification unit for the corresponding main user according to the initial information map, and the information identification unit is used to count the type of medical data generated by each medical department in the corresponding user subject, that is, count the types of medical data that the medical department has which medical service big data needs, and different formats of the same data type are regarded as the same medical data type or type; mark the medical department in the main user as a branch unit; identify the medical data type of each branch unit corresponding to the main user in real time through the information identification unit, integrate them into the unit data range of the branch unit, and integrate each unit data range into the medical data range of the main user; supplement the initial information map according to the medical data range of each main user, that is, supplement the corresponding medical data range, and mark the current initial information map as an information service map.

[0024] In one embodiment, the function of the information identification unit can be implemented based on existing technologies, such as the most common input and update by staff within the corresponding subject user; it can also be based on intelligent recognition technology to identify various medical data types possessed by the branch unit.

[0025] In one embodiment, the method for the information identification unit to count the types of medical data corresponding to the branch units includes: Obtain historical medical data of various formats and types that each branch unit may have, that is, including different types of the same data; set data standards for medical data types that meet the application of medical service big data, which is generally a set of various medical data types required. If they belong to this set, they are considered to meet the data standards, and they can also be represented by other methods; set a training set based on historical medical data and data standards, and establish a data recognition model based on the training set. The expression of the data recognition model is: ; Where: s i is the input data, which indicates the corresponding medical data type in the branch unit, i=1, 2, ..., n, where n is the number of medical data types in the branch unit; the output data is the data identification value SU (s i ), the data identification value is 1 or 0; Identify the type of medical data possessed by the branch unit in real time, analyze the identified type of medical data through a data identification model, and obtain a data identification value corresponding to the corresponding type of medical data; The medical data type with a data identification value of 1 is integrated into the unit data range of the corresponding branch unit.

[0026] The island identification module is used to perform data island analysis, obtain the medical data collection records of each main user in real time, and collect medical data based on the data collection needs of medical service big data. The medical data collection record includes various medical data records collected from the main user, which is a continuous cumulative record; obtain an information service graph, perform real-time analysis on the medical data collection record according to the information service graph, determine the island data type, and issue an island warning to relevant management personnel.

[0027] In one embodiment, the islanding reasons of the islanding data types may be analyzed and displayed to the management personnel.

[0028] In one embodiment, based on the above embodiment, a corresponding solution can be determined based on the cause of the island, and the solution can be sent to the management personnel simultaneously; the specific solution can be determined based on the existing method, such as changing the data format, adjusting the communication protocol, etc.

[0029] In one embodiment, the influence of the island type data on the data analysis results after intelligent big data can also be analyzed, and the degree of deviation of the results with and without the island type data can be simulated as the influence degree.

[0030] In one embodiment, real-time analysis of medical data collection records is performed according to the information service graph, including: According to the information service graph, the medical data scope of the corresponding medical data collection record is identified, the various medical data types corresponding to the corresponding branch units in the medical data collection record are identified, and the unit identification records marked as the branch units are integrated; the unit identification records of each branch unit are calibrated according to the medical data scope, the missing medical data types are determined, and then the island data types are determined.

[0031] In one embodiment, in order to further improve the recognition accuracy, the medical data collection records are analyzed in real time according to the information service graph, including: The unit duration is preset, which is generally one day, two days, three days, one week, etc.; the medical data collection records are classified in real time according to the unit duration to obtain the corresponding unit record data, that is, the medical data collection records of the time period corresponding to the current time and the unit duration are marked as unit record data; the unit data range corresponding to the corresponding unit record data is identified according to the information service graph; the medical data type corresponding to the unit record data is identified, and the integrated mark is made into a unit identification record; the unit identification record is calibrated according to the unit data range, and the medical data type not in the unit identification record is marked as a type to be analyzed; The interval time for real-time identification of the type to be analyzed refers to the interval time between the last identification of the type to be analyzed. If it is the first use, it is the interval time between the start time of use. Whether the type to be analyzed is an island data type is determined based on the interval time. That is, the interval time is compared with the preset time, and the type to be analyzed that is greater than the preset time is marked as an island data type.

[0032] In one embodiment, the medical data collection records are analyzed in real time according to the information service graph, and the island data type can also be determined based on other existing methods.

[0033] The service planning module is used to divide the information service graph into regions to form a plurality of service analysis regions.

[0034] In one embodiment, a method for dividing an information service graph into regions includes: The information service graph is divided into several unit areas, which are divided in the form of residential communities, that is, one community corresponds to one unit area; based on the medical data of each medical subject, the medical selection data of each unit area is determined, that is, the medical subject selected by the patients in the unit area for different disease types, and detailed patient information is not required, reducing the risk of patient information leakage, that is, the disease type and distribution of each patient can be determined at the subject user, and then subsequently summarized and distributed to the corresponding unit area; Classify the medical treatment selection data according to the disease type, obtain the medical treatment selection data corresponding to the corresponding disease type, and integrate them into the medical treatment classification data of the disease type; According to the medical classification data of each main user of the disease type in the unit area, the proportion of the corresponding main user in the unit area is counted, that is, the proportion of medical treatment is calculated according to the number of medical treatments, the number of patients, etc.; the disease unit data of the disease type in the unit area is integrated, that is, the proportion of medical treatment corresponding to each main user in the disease unit data; the disease unit data of each unit area is merged to obtain the basic analysis area of ​​the corresponding main user for the corresponding disease type; Identify the management items for subsequent analysis, such as the use of various drugs, the number of patients with various disease types, disease trends, medical costs, and other items that require analysis and supervision. Merge the corresponding basic analysis areas based on the management items to obtain the service analysis areas corresponding to the management items.

[0035] In one embodiment, the disease unit data of each unit area are merged, including: Identify the disease type and each medical proportion corresponding to the disease unit data, assign the unit area to the main user corresponding to the highest medical proportion, merge the various unit areas corresponding to the main user, and form the basic analysis area of ​​the main user for the corresponding disease type.

[0036] In one embodiment, the disease unit data of each unit area are merged, including: It is also possible to analyze the medical classification data corresponding to the disease type in the unit area to determine whether the differences between the monitoring and management results of the subsequent corresponding management needs meet the permitted requirements. If the requirements are met, the data is merged, and a new medical proportion is subsequently determined based on the merged medical classification data. The merger is then performed according to the above embodiment. For the main user whose medical classification data is merged, if the medical proportion of the merged medical classification data is the highest, then the unit area belongs to the basic analysis area of ​​the merged corresponding main user, and the same unit area can appear in multiple basic analysis areas.

[0037] In one embodiment, merging corresponding basic analysis areas according to management items includes: Identify the basic analysis areas that meet the management item requirements, such as drug monitoring, and determine the corresponding basic analysis areas according to the diseases corresponding to the supplies; analyze the differences between the basic analysis areas on the associated items, such as drug dosage, and determine the differences in drug dosage in the corresponding areas. The differences can be statistically calculated on a per capita basis, and the differences within the allowable range will be merged, otherwise they will not be merged, to obtain several service analysis areas, where the corresponding difference requirements are set according to actual needs; it is also possible to perform a merge analysis based on the differences in the analysis results, such as analyzing the data corresponding to the basic analysis area separately, obtaining two analysis results, calculating the difference between the two analysis results, and merging the differences within the allowable error range.

[0038] In one embodiment, the corresponding basic analysis areas are merged according to the management items, and the merged analysis may also be performed based on existing methods, such as based on a clustering algorithm, a deep learning algorithm, and the like.

[0039] In one embodiment, the information service map is divided into regions, and the corresponding radiation range is determined according to the historical medical data of the main user, and the regions are divided according to the radiation range; for the overlapping parts, they can be allocated in proportion, and if the differences in the subsequent corresponding supervision results are within the allowable range, they can also be merged to reduce the number of regions.

[0040] In one embodiment, the information service graph is divided into regions, and the division can also be performed based on other existing methods, such as intelligent division by establishing an intelligent model based on machine learning, deep learning algorithms, etc.

[0041] 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. The management items include the use of various drugs, the number of patients with various disease types, the trend of disease changes, medical costs, etc. The monitoring and management results are generally displayed in the form of curves, such as the medical cost monitoring needs of influenza in the corresponding service analysis area, the influenza patient number monitoring curve, the drug consumption curve, etc.; identify the island data type corresponding to the corresponding service analysis area, analyze the possible management deviations of the corresponding management items according to the island data type, and determine the island impact value; add the island impact value to the corresponding monitoring and management result, so that the management personnel can understand the possible deviations of the monitoring and management results.

[0042] In one embodiment, the setting of management items and data analysis are performed in accordance with the management items of the existing medical service management system; the difference is that after the regional division, additional analysis is performed on the corresponding regions.

[0043] In one embodiment, a method for performing deviation analysis on corresponding management items according to island data types includes: Identify the island data type, perform analysis and simulation based on the island data type, determine the deviation between the regulatory monitoring results analyzed when the data of the island data type is missing and the regulatory monitoring results analyzed when the data of the island data type is not missing, and mark it as the island impact value; use the corresponding historical medical data to perform simulation analysis to determine the possible result deviation value of the analysis in the absence of data of the corresponding island data type, and then match an island impact value that is closest to the corresponding background of the service analysis area.

[0044] In one embodiment, deviation analysis is performed on corresponding management items according to the island data type. The deviation analysis can be performed based on existing methods, such as using historical medical data to establish a training set, establishing a deviation analysis model based on a deep learning algorithm, training is performed using the training set, and intelligent analysis is performed using the deviation analysis model after successful training.

[0045] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0046] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A smart medical service big data management system, characterized in that: It includes information service module, island identification module, service planning module and data analysis module; The information service module is used to set and update the information service map, and the information service map is used to display the subject information and medical data range of each subject user; The island identification module is used to perform data island analysis, obtain medical data collection records of each subject user in real time, obtain an information service map, perform real-time analysis on the medical data collection records according to the information service map, determine the type of island data, and issue an island warning to relevant managers according to the type of island data; The service planning module is used to divide the information service graph into regions to form a number of service analysis regions; The data analysis module is used to analyze the collected medical data in 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 island data type of the corresponding service analysis area, and perform deviation analysis on the corresponding management items according to the island data type to obtain the island impact value; and add the island impact value to the corresponding monitoring and management results.

2. The smart medical service big data management system according to claim 1, characterized in that: The method of setting up the information service graph includes: Collect the subject information of each subject user in real time, and generate an initial information graph based on the subject information; According to the initial information graph, a corresponding information identification unit is configured for the main user, and the information identification unit is used to identify the unit data range of the corresponding branch unit in the main user; the unit data range of the corresponding branch unit in the main user is identified in real time by the information identification unit; Integrate each unit data range into a medical data range of a main user; supplement the initial information graph according to the medical data range of each main user, and mark the initial information graph after the information supplement as an information service graph.

3. A smart medical service big data management system according to claim 2, characterized in that: The identification method of the information identification unit includes: Establish a data recognition model. The expression of the data recognition model is: ； Where: s i is the input data, which indicates the corresponding medical data type in the branch unit, i=1, 2, ..., n, where n is the number of medical data types in the branch unit; the output data is the data identification value SU (s i ), the data identification value is 1 or 0; Identify in real time the type of medical data possessed by the branch unit, analyze the type of medical data through a data identification model, and obtain a data identification value of the type of medical data; The medical data types with data identification values ​​of 1 in the branch unit are integrated into the unit data range of the branch unit.

4. The smart medical service big data management system according to claim 1, characterized in that: The cause of the island is identified according to the island data type, and the cause of the island is displayed to the management personnel.

5. The smart medical service big data management system according to claim 1, characterized in that: An impact degree is determined according to the island data type, and the impact degree is displayed to the management personnel.

6. The smart medical service big data management system according to claim 2, characterized in that: Real-time analysis of medical data collection records based on information service graphs, including: Preset unit duration, classify the medical data collection record in real time according to the unit duration, and obtain corresponding unit record data; identify the unit data range of the unit record data according to the information service graph; and identify the unit identification record corresponding to the unit record data; Calibrate the unit identification record 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 whether the type to be analyzed is an island data type is determined according to the interval duration.

7. The smart medical service big data management system according to claim 1, characterized in that: Methods for dividing information service graphs into regions include: Divide the information service map into several unit areas according to residential areas; collect the medical treatment selection data of each medical subject in the corresponding unit area; Classify the medical treatment selection data according to the disease type, and obtain the medical treatment classification data corresponding to the corresponding disease type; According to the medical classification data corresponding to the unit area, the medical proportion corresponding to the corresponding subject user is counted, and each medical proportion is integrated into the disease unit data of the disease type in the unit area; according to the disease unit data of each unit area, the basic analysis area of ​​the corresponding subject user for the corresponding disease type is obtained by merging; Identify the management items, merge the corresponding basic analysis areas according to the management items, and obtain the corresponding service analysis areas.

8. The smart medical service big data management system according to claim 7, characterized in that: The disease unit data of each unit area are merged, including: Identify the main user with the highest proportion of medical treatment in the disease unit data, and merge the unit area into the basic analysis area corresponding to the disease type of the main user; And so on, until all unit areas are merged, and the merged analysis is completed.

9. The smart medical service big data management system according to claim 1, characterized in that: Methods for performing deviation analysis on corresponding management items according to island data types include: Identify the island data type, and perform analysis and simulation based on the island data type. The simulation method is to separately simulate and analyze the collected medical data including the island data type and the collected medical data excluding the island data type, calculate the corresponding result deviation value, and mark the corresponding result deviation value as the island impact value.

Images