Medical big data management method and system

Abstract

The invention relates to a medical big data management method and system, and the method comprises the steps: transmitting a big data node content signature request to a big data node after a medical terminal receives a broadcast and before the medical terminal creates a trusted connection with the big data node; and the big data node sends a content signature request response to the medical terminal and then provides big data content for the medical terminal. According to the method, for the big data nodes containing multiple or a large number of big data servers or data partitions, support for rapidly understanding the big data content is provided before the trusted connection with the big data nodes is created, so that the data processing difficulty brought by a large data size is reduced, the providing efficiency of the big data content is improved, and the data processing efficiency is improved. And finally, the medical big data management capability and efficiency are improved.

Description

[Technical Field]

[0001] This invention belongs to the field of smart healthcare technology, and in particular relates to a method and system for managing medical big data. [Background Technology]

[0002] With the rapid development of big data and internet technologies, the medical Internet of Things (IoT), born from their application in the medical field, has inadvertently permeated every aspect of everyone's life. The resulting smart healthcare is a patient-centric healthcare service model that integrates IoT, cloud computing, and other technologies. It utilizes new sensors, IoT, and communication technologies combined with modern medical concepts to construct a medical information platform centered on medical big data. This platform integrates business processes between medical institutions, optimizes the storage, use, and provision of medical resources, and enables the rational allocation of medical resources, truly achieving patient-centric smart healthcare.

[0003] Among these, data openness, flow, and sharing are crucial driving forces for the development of smart healthcare. Smart healthcare platforms can typically provide big data content services tailored to the actual needs and intentions of different patients or institutions based on their own stored content preferences. For example, by analyzing the smart healthcare big data of patients or medical institutions to determine their corresponding smart healthcare interests, targeted big data content can be provided. It is evident that the hidden value potential of medical big data is enormous.

[0004] However, with the rapid development of technologies related to medical content service provision, the size of medical big data content is also growing exponentially, putting enormous pressure on existing medical content platforms. On the one hand, there's the issue of trustworthiness. Medical data itself has significant privacy characteristics; therefore, the security and trustworthiness of content provision and data access are particularly important. Blindly establishing trusted connections to form data links between two parties is clearly unreliable and inefficient. On the other hand, there's the issue of controllability. The large data size increases the difficulty of data processing, making it crucial to quickly understand the content of big data nodes for relatively accurate content provision. Therefore, designing comprehensive data acquisition methods and efficient big data content provision methods are technical problems to be solved. Based on these problems, this invention addresses big data nodes that encompass multiple or large numbers of big data servers or big data partitions. By providing support for rapid understanding of big data content before creating trusted connections with big data nodes, it reduces the data processing difficulty caused by large data sizes, improves the efficiency of big data content provision, and ultimately enhances the management capabilities and efficiency of medical big data. [Summary of the Invention]

[0005] To address the aforementioned problems in the prior art, this invention proposes a medical big data management method and system, the method comprising:

[0006] Step S1: The big data node calculates its own content identifier and sends a content provision broadcast; the content provision broadcast includes the content identifier; wherein: the content identifier is a tuple, where each element is used to indicate a summary description of one dimension of the content stored in the big data node; the content identifier of the big data node reflects the content storage preferences in the big data node;

[0007] Step S2: After receiving the broadcast, the medical terminal proactively sends a content signature request to the big data node before establishing a trusted connection with the big data node; the big data node provides a content signature request response to the medical terminal; the content signature response includes a content signature vector; after receiving the broadcast, the medical terminal determines whether it is possible to meet the content acquisition requirements based on the tuple information in the content identifier.

[0008] Step S3: The big data node determines the content signature vector; specifically: the big data node obtains the content outline of each big data server or data partition, samples the content outline through sparse sampling to obtain a low data volume outline, and calculates the content signature vector corresponding to the big data server or data partition in the content signature through the low data volume outline.

[0009] Step S3 specifically includes the following steps;

[0010] Step SA31: Obtain an unprocessed big data server or data partition as the current data content;

[0011] Step SA33: Obtain the element value of each element in the content signature using a sparse sampling method based on logical partitioning; Step SA33 specifically includes the following steps:

[0012] Step SA331: Obtain each file identifier in the current data content and arrange them sequentially to form a content outline;

[0013] Step SA332: Sample the content contour using a sparse sampling method to obtain a low-data-volume contour; the sparse sampling method is to obtain the file identifier in the content contour at a preset interval to obtain a low-data-volume contour.

[0014] Step SA333: Obtain summary description information of each dimension of the file corresponding to the file representation through the file identifier in the low data volume profile;

[0015] Step SA334: Calculate the statistical value of the summary description of each dimension in the low data volume profile as the element value in the content signature vector corresponding to the dimension; proceed to step SA35;

[0016] Step SA35: Determine whether the big data server or data partition has been processed. If so, end; otherwise, return to step SA31.

[0017] Step S4: Determine and send a content signature request response to the medical terminal; the content signature request response includes a content signature vector;

[0018] Step S5: Determine whether to access the big data node based on the content signature vector in the node content signature request response; if so, establish a trusted connection between the request and the big data node; and after establishing the trusted connection, access the big data node to obtain big data content or the big data node pushes big data content to the medical terminal.

[0019] Furthermore, the content delivery broadcast also includes descriptive information about the content identifier related to the content representation.

[0020] Furthermore, the big data nodes periodically calculate their own content tags to update the content tags in real time or periodically.

[0021] Furthermore, when the amount of recently added data in a big data node reaches a preset size, its own content tags are calculated.

[0022] Furthermore, the summary description information indicated by each element in the content signature vector is used to determine whether the summary description information meets the content acquisition requirements of the medical terminal.

[0023] A medical big data management system includes: a medical terminal and a big data node; wherein: the medical terminal and the big data node are communicatively connected; the medical big data management system is used to implement the above-mentioned medical big data management method.

[0024] Furthermore, the big data node may include multiple big data servers or a single big data server. When the big data node includes a single big data server, the big data server includes multiple data partitions.

[0025] Furthermore, the medical terminal and big data node can be one or more.

[0026] A medical big data management platform includes a processor coupled to a memory, the memory storing program instructions, and the medical big data management method is implemented when the program instructions stored in the memory are executed by the processor.

[0027] A computer-readable storage medium includes a program that, when run on a computer, causes the computer to perform the described medical big data management method.

[0028] The beneficial effects of this invention include:

[0029] (1) By enabling reliable understanding of the content provisioning capabilities and other service information of big data nodes before the creation of a trusted connection between the big data server and the content provision, that is, before the content is provided, the big data nodes used to establish a trusted connection can be selected.

[0030] (2) Low-data-volume contour information is obtained through sparse sampling to describe the general contour of each data space in the big data node, instead of directly providing capabilities to the big data node as a whole, which improves the targeting of subsequent trusted connections; further, based on file size adaptability, the logical partitioning and non-logical partitioning methods are selected, which greatly reduces the amount of summary description information that needs to be analyzed and calculated without reducing the contour resolution, and provides a basis for understanding the capabilities before creating trusted connections.

[0031] (3) Based on the content tag vector, some element values ​​are masked by access frequency or access queue length, which dynamically and simply guides the access rhythm of medical terminals, affects the possibility of big data nodes being requested to access rather than directly cutting off access channels, and ensures the efficiency of big data management. [Attached Image Description]

[0032] The accompanying drawings, which are provided to further illustrate the invention and form part of this application, are not intended to unduly limit the invention. In the drawings:

[0033] Figure 1 A schematic diagram of the medical big data management method provided by the present invention.

Detailed Implementation Methods

[0034] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions are merely for explaining the present invention and are not intended to limit the scope of the invention.

[0035] This invention proposes a medical big data management method and system, as shown in the appendix. Figure 1 As shown, the method includes the following steps:

[0036] Step S1: The big data node calculates its own content identifier and sends a content provision broadcast; the content provision broadcast includes the content identifier; wherein: the content identifier is a tuple, where each element is used to indicate a summary description of one dimension of the content stored in the big data node; therefore, the content identifier is used to reflect the overall situation of the content stored by the big data node; the content identifier of the big data node reflects the content storage preferences in the big data node; the big data node exhibits an overall content provision preference and maintains this preference, or characteristic, in the subsequent content storage and update process; that is, when storing content, there must be a selection of the content to be stored or updated; the data stored by the big data node can obviously be described from multiple perspectives to better portray it comprehensively;

[0037] Preferably, the content delivery broadcast also includes descriptive information about the content identifier related to the content representation;

[0038] Preferred method: Broadcast content when the content identifier changes; the content identifier can be calculated based on the result of the content signature vector calculation in subsequent steps;

[0039] Preferably, the dimensions described by the elements include: application field, data volume, data type, amount of newly added data, security level, etc.

[0040] Preferably, the big data node periodically calculates its own content tags to update the content tags in real time or periodically;

[0041] Preferred method: When the amount of recently added data in a big data node reaches a preset size, calculate its own content tags;

[0042] Preferably, the big data node includes one or more big data servers; these big data servers form a content providing entity group, transparently providing content to the medical terminal as a whole big data node;

[0043] Step S2: After receiving the broadcast, the medical terminal proactively sends a content signature request to the big data node before establishing a trusted connection with the big data node; the big data node provides a content signature request response to the medical terminal; the content signature response includes a content signature vector; after receiving the broadcast, the medical terminal determines whether it is possible to meet the content acquisition requirements based on the tuple information in the content identifier.

[0044] Preferred method: Determine whether the summary description information meets the content retrieval requirements by judging the summary description indicated by each element in the content signature vector;

[0045] Wherein: the content signing request is a security-verified request; the content signing request response provided by the big data node is also a security-verified request; the content signing request response provided by the big data node is also a security-verified request.

[0046] Preferred configuration: Security verification is performed by providing security tags through a third-party node; upon receiving a temporary security tag issuance request from the medical terminal, the third-party node performs security registration for the medical terminal and issues a temporary security tag; upon receiving a content tag request, the big data node requests the third-party node to determine whether a registration exists for the medical terminal. If so, it further performs additional security registration. After the additional registration is performed for the big data node, the big data node responds using a temporary security tag; if no registration exists for the medical terminal, no response is given.

[0047] Preferably: the sending node content signature request occurs before a trusted connection is established; wherein: the content signature vector indicates low data volume profile information of the content that the big data node can provide; when the big data node includes multiple big data servers, each element in the vector is used to indicate the low data volume profile information of one big data server; when it includes one big data server, each element in the vector is used to indicate the low data volume profile information of each data partition in a big data node.

[0048] Step S3: The big data node determines the content signature vector; specifically: the big data node obtains the content outline for each big data server or data partition, samples the content outline using a sparse sampling method to obtain a low-data-volume outline, and calculates the content signature vector corresponding to the big data server or data partition in the content signature using the low-data-volume outline; that is, the number of content signature vectors is equal to the number of big data servers or data partitions.

[0049] Step S3 specifically includes the following steps;

[0050] Step SA31: Obtain an unprocessed big data server or data partition as the current data content;

[0051] Step SA33: Obtain the element value of each element in the content signature using a sparse sampling method based on logical partitioning; Step SA33 specifically includes the following steps:

[0052] Step SA331: Obtain each file identifier in the current data content and arrange them sequentially to form a content outline;

[0053] Step SA332: Sample the content contour using a sparse sampling method to obtain a low-data-volume contour; the sparse sampling method is to obtain the file identifier in the content contour at a preset interval to obtain a low-data-volume contour.

[0054] Step SA333: Obtain summary description information of each dimension of the file corresponding to the file representation through the file identifier in the low data volume profile; here, "file" refers to the organization of content; files can be constructed in any form, and the file type can be various types of images, documents, etc.

[0055] Step SA334: Calculate the statistical value of the summary description of each dimension in the low data volume profile as the element value in the content signature vector corresponding to the dimension; proceed to step SA35;

[0056] Preferably, the statistical value is an average, cumulative value, etc.

[0057] Step SA35: Determine whether the big data server or data partition has been processed. If so, end; otherwise, return to step SA31.

[0058] A more preferred approach is: considering that sparse sampling can significantly reduce the amount of summary information that needs to be analyzed and calculated, but file size affects the efficiency and accuracy of sparse sampling; therefore, the alternative is:

[0059] Step S3 specifically includes the following steps:

[0060] Step S31: Obtain an unprocessed big data server or data partition as the current data content;

[0061] Step S32: Obtain the average size of the files in the current data content; if the average size is greater than the large size threshold or less than the small size threshold, proceed to step S34; otherwise, proceed to the next step.

[0062] Preferably, the average size is the current data content size divided by the number of files;

[0063] Alternative: The average size is the average file size of most files;

[0064] Step S33: Obtain the element value of each element in the content signature using a sparse sampling method based on logical partitioning; Step S33 specifically includes the following steps:

[0065] Step S331: Obtain each file identifier in the current data content and arrange them sequentially to form a content outline;

[0066] Step S332: Sample the content contour using a sparse sampling method to obtain a low-data-volume contour; the sparse sampling method is to obtain the file identifier in the content contour at a preset interval to obtain a low-data-volume contour; for example: every 5 files;

[0067] Step S333: Obtain summary description information of each dimension of the file corresponding to the file representation through the file identifier in the low data volume profile; here, "file" refers to the way the content is organized; any form can be used to constitute a file, and the file type can be various types of images, documents, etc.

[0068] Step S334: Calculate the statistical value of the summary description of each dimension in the low data volume profile as the element value in the content signature vector corresponding to the dimension; proceed to step S35;

[0069] Preferably, the statistical value is an average, cumulative value, etc.

[0070] Step S34: Obtain the element value of each element in the content signature using a sparse sampling method based on non-logical partitioning; Step S34 specifically includes the following steps:

[0071] Step S341: Divide the current content into multiple data units according to the preset data size; the size of each data unit is the preset data size; any part that is less than the preset data size is padded with the default value; after division, a preset number of data units are obtained;

[0072] Step S342: Select a data cell from a preset number of data cells and extract the summary description information of each dimension corresponding to the data content in that data cell;

[0073] Preferably, the preset quantity is 10-1000;

[0074] Preferred method: Select a preset number of data units containing the file header as the selected data units; when multiple such data units exist, determine the first data unit as the selected data unit;

[0075] Preferably: By accessing the file header of the file in the data unit, a summary description of each dimension corresponding to the data content in the data unit can be obtained;

[0076] Step S343: Calculate the statistical value of the summary description of each dimension of each selected data unit as the element value of the corresponding element in the content signature vector corresponding to the dimension;

[0077] Step S35: Determine whether the big data server or data partition has been processed. If yes, end; otherwise, return to step S31.

[0078] Of course, a preferred approach is to pre-calculate the content tag vectors and determine them by directly reading them when a response is needed. In this case, the pre-calculated content tags need to be updated in real time or periodically, because the content stored at each location in a big data node changes rapidly.

[0079] This invention obtains low-data-volume contours through sparse sampling, and further selects logical and non-logical partitioning methods based on file size adaptability. Without reducing the contour resolution, it greatly reduces the amount of summary description information that needs to be analyzed and calculated, providing a foundation for understanding capabilities before creating trusted connections.

[0080] Step S4: Determine and send a content signature request response to the medical terminal based on the working status of the big data node; the content signature request response includes a content signature vector; Step S4 specifically includes the following steps:

[0081] Step S41: Determine the access frequency of each data partition of the big data server within the big data node or determine the access queue length of each big data server within the big data node.

[0082] Preferably, the access frequency is the recent access frequency;

[0083] Step S42: When the access frequency is high-frequency or the access queue length is greater than the preset length, the content signature vector element corresponding to the data partition or big data server is set to the default value; the data partition or big data server set to the default value will be blocked in subsequent accesses or when accessed through a medical terminal, the provided content signature vector element will not contribute, thus reducing the possibility of the big data node being requested to establish a trusted connection.

[0084] For example: 0 or the maximum value;

[0085] Step S43: Send the node content signature request response containing the content signature vector to the medical terminal;

[0086] Based on content tag vectors, this invention masks some element values ​​by access frequency or access queue length, which dynamically and simply guides the access rhythm of medical terminals, affecting the possibility of big data nodes being requested to access rather than directly cutting off access channels, thus ensuring the efficiency of big data management.

[0087] Step S5: Determine whether to access the big data node based on the content signature vector in the node content signature request response; if so, establish a trusted connection between the request and the big data node; and after establishing the trusted connection, access the big data node to obtain big data content or the big data node pushes big data content to the medical terminal.

[0088] The establishment of a trusted connection between the request and the big data node specifically involves: the medical terminal providing a trusted connection request, including a trusted certificate and secure signature information, to the big data node; the big data node obtaining its own trusted control policy to determine whether it can meet the trusted requirements in the trusted certificate; if so, it further determines whether the security control policy authenticates the secure signature information; if the authentication is successful, it sends a trusted connection request response to the medical terminal; this is a one-way handshake method, but a two-way handshake can also be used; the security control policy performs parallel verification of the security of the link data and the trustworthiness of the data content provided, completing trusted authentication simultaneously with the establishment of the link;

[0089] The step of determining whether to access the big data node based on the content signature vector in the node content signature request response is as follows: the content acquisition requirement is vectorized, and each content signature vector is matched with the content acquisition requirement in turn. If there are one or N matching results indicating that the similarity is greater than the similarity threshold, it is determined that the big data node will be accessed.

[0090] Preferably, N is a preset value; the higher the threshold of N, the greater the likelihood of meeting the requirements during subsequent accesses; the similarity threshold can be set to a relatively high value.

[0091] Preferably, the method further includes step S6: when the medical terminal accesses the big data node, the big data node allocates access requests according to the working status of each big data server or data partition; the working status of the big data server and data partition changes in real time, and if the big data server or data partition set to the default value does not contribute, it may still have the opportunity to provide services to the medical terminal if it becomes idle later;

[0092] Alternatively: When a medical terminal accesses the big data node, the big data node allocates access requests based on the working status of each big data server or data partition and the satisfaction of the demand.

[0093] This invention supports the reliable understanding of the content provisioning capabilities and other service information of big data nodes before the creation of a trusted connection with the big data server, that is, before content provision, thereby enabling the selection of big data nodes for subsequent establishment of trusted connections.

[0094] Based on the same inventive concept, the present invention also provides a medical big data management system, the system comprising: a medical terminal and a big data node; wherein: the medical terminal and the big data node are communicatively connected; the system is used to implement the above-described medical big data management method;

[0095] Preferably, the medical terminal and the big data node are one or more; the big data node includes multiple big data servers; each big data server has a different real-time content signature vector; the big data server is transparent to the medical terminal.

[0096] The big data node includes a big data server, and the big data server includes multiple data partitions, each with a different real-time content signature vector; the big data partitions are transparent to the medical terminal.

[0097] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but does not necessarily, correspond to a file in a file system. A program can be stored as part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to said program, or in multiple co-located files (e.g., a file storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on a single computer or on multiple computers located at a single site or distributed across multiple sites and interconnected by a communications network.

[0098] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for managing medical big data, characterized in that, The method includes: Step S1: The big data node calculates its own content identifier and sends a content provision broadcast; the content provision broadcast includes the content identifier; wherein: the content identifier is a tuple, where each element is used to indicate a summary description of one dimension of the content stored in the big data node; the content identifier of the big data node reflects the content storage preferences in the big data node; Step S2: After receiving the broadcast, the medical terminal proactively sends a content signature request to the big data node before establishing a trusted connection with the big data node; the big data node provides a content signature request response to the medical terminal; the content signature response includes a content signature vector; after receiving the broadcast, the medical terminal determines whether it is possible to meet the content acquisition requirements based on the tuple information in the content identifier. Step S3: The big data node determines the content signature vector; specifically: the big data node obtains the content outline of each big data server or data partition, samples the content outline through sparse sampling to obtain a low data volume outline, and calculates the content signature vector corresponding to the big data server or data partition in the content signature through the low data volume outline. Step S3 specifically includes the following steps; Step SA31: Obtain an unprocessed big data server or data partition as the current data content; Step SA33: Obtain the element value of each element in the content signature using a sparse sampling method based on logical partitioning; Step SA33 specifically includes the following steps: Step SA331: Obtain each file identifier in the current data content and arrange them sequentially to form a content outline; Step SA332: Sample the content contour using a sparse sampling method to obtain a low-data-volume contour; the sparse sampling method is to obtain the file identifier in the content contour at a preset interval to obtain a low-data-volume contour. Step SA333: Obtain summary description information of each dimension of the file corresponding to the file representation through the file identifier in the low data volume profile; Step SA334: Calculate the statistical value of the summary description of each dimension in the low data volume profile as the element value in the content signature vector corresponding to the dimension; proceed to step SA35; Step SA35: Determine whether the big data server or data partition has been processed. If so, end; otherwise, return to step SA31. Step S4: Determine and send a content signature request response to the medical terminal; the content signature request response includes a content signature vector; Step S5: Determine whether to access the big data node based on the content signature vector in the node content signature request response; if so, establish a trusted connection between the request and the big data node; and after establishing the trusted connection, access the big data node to obtain big data content or the big data node pushes big data content to the medical terminal.

2. The medical big data management method according to claim 1, characterized in that, The content delivery broadcast also includes descriptive information about the content identifiers related to the content representation.

3. The medical big data management method according to claim 2, characterized in that, The big data nodes periodically calculate their own content tags to update the content tags in real time or periodically.

4. The medical big data management method according to claim 3, characterized in that, When the amount of recently added data in a big data node reaches a preset size, its own content tags are calculated.

5. The medical big data management method according to claim 4, characterized in that, The content signature vector is used to determine whether the summary description information meets the content acquisition requirements of the medical terminal by judging the summary description indicated by each element.

6. A medical big data management system, characterized in that, include: The medical terminal and the big data node are communicatively connected; the medical big data management system is used to implement the medical big data management method according to any one of claims 1-5.

7. The medical big data management method according to claim 6, characterized in that, The big data node may contain multiple big data servers or a single big data server. When the big data node contains a single big data server, the big data server may contain multiple data partitions.

8. The medical big data management system according to claim 6, characterized in that, The medical terminal and big data node may be one or more.

9. A medical big data management platform, characterized in that, The device includes a processor coupled to a memory, the memory storing program instructions, and when the program instructions stored in the memory are executed by the processor, the medical big data management method according to any one of claims 1-5 is implemented.

10. A computer-readable storage medium, characterized in that, Includes a program that, when run on a computer, causes the computer to perform the medical big data management method as described in any one of claims 1-5.

Images