CN111739595A

CN111739595A - Medical big data sharing analysis method and device

Info

Publication number: CN111739595A
Application number: CN202010720451.8A
Authority: CN
Inventors: 文建全; 王先知; 吴翊; 唐起华; 李熙; 姜赳赳
Original assignee: Hunan Trasen Technology Co ltd
Current assignee: Hunan Trasen Technology Co ltd
Priority date: 2020-07-24
Filing date: 2020-07-24
Publication date: 2020-10-02
Anticipated expiration: 2040-07-24
Also published as: CN111739595B

Abstract

The invention relates to the technical field of big data processing, in particular to a medical big data sharing analysis method and device. The medical big data sharing analysis method comprises the following steps: receiving preset medical big data information sent by a plurality of servers, and constructing a first to-be-processed knowledge graph through a first logic relation tree obtained by interacting big data to be integrated with the plurality of servers; receiving a plurality of second logic relation trees sent by a plurality of servers to obtain a second knowledge graph to be processed; integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph; acquiring medical big data information to be processed, and respectively sending the medical big data information to be processed to a plurality of servers; when a plurality of sub-sharing identifications returned by a plurality of servers based on the target knowledge graph aiming at the medical big data information to be processed are received, the big data sharing result is integrated by the aid of the plurality of sub-sharing identifications, and medical big data can be conveniently shared.

Description

Medical big data sharing analysis method and device

Technical Field

The invention relates to the technical field of big data processing, in particular to a medical big data sharing analysis method and device.

Background

The application of big data is more common, all trades are all related, and the medical industry is also using big data, and along with the increase of data volume, the diversification of data type, user when carrying out data sharing, if directly send all data, because too huge data volume, can occupy more resources, and the relevant user of medical treatment does not generally possess the professional equipment that can handle huge data volume. Moreover, the logic and format of data transmission between the medical related users are not completely the same, so that when data sharing is performed between the medical related users, a corresponding sharing strategy needs to be formulated every time of sharing, and the method is very complex and inconvenient.

In view of this, it is necessary for those skilled in the art to provide a convenient medical big data sharing analysis scheme.

Disclosure of Invention

The invention aims to provide a medical big data sharing analysis method, a medical big data sharing analysis device, a computer device and a readable storage medium.

In a first aspect, an embodiment of the present invention provides a medical big data sharing analysis method, which is applied to a computer device, and includes:

receiving preset medical big data information sent by a plurality of servers, and constructing a first to-be-processed knowledge graph through a first logic relation tree obtained by interacting big data to be integrated with the plurality of servers on the basis of the preset medical big data information, wherein the preset medical big data information represents an address index of shared big data in the servers;

receiving a plurality of second logic relation trees sent by the plurality of servers, and integrating the plurality of second logic relation trees to obtain a second knowledge graph to be processed;

integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph, and sending the target knowledge graph to the plurality of servers so that the plurality of servers can share big data by using the target knowledge graph;

acquiring to-be-processed medical big data information, and respectively sending the to-be-processed medical big data information to the plurality of servers, wherein the to-be-processed medical big data information represents an address index of to-be-processed shared big data to be shared;

and when a plurality of sub-sharing identifications returned by the plurality of servers aiming at the medical big data information to be processed based on the target knowledge graph are received, integrating a big data sharing result by using the plurality of sub-sharing identifications, and finishing the medical big data sharing analysis.

Optionally, the step of integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph includes:

obtaining a plurality of sample big data from the plurality of servers, and integrating the plurality of sample big data to obtain a first big data sample object set, wherein the sample big data represents private big data in the servers;

integrating preset medical big data information sent by the plurality of servers to obtain a second big data sample object set;

obtaining a target big data sample object set based on the first big data sample object set and the second big data sample object set;

calculating a first incidence relation by using the first big data sample object set and the target big data sample object set, and calculating a second incidence relation by using the second big data sample object set and the target big data sample object set;

and integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph according to the first incidence relation and the second incidence relation to obtain the target knowledge graph.

Optionally, the step of constructing a first to-be-processed knowledge graph through a first logical relationship tree obtained by interacting to-be-integrated big data with the plurality of servers based on the preset medical big data information includes:

dividing the plurality of servers into at least one cluster by using the preset medical big data information, and sending information of a matching server belonging to the same cluster to a main server in each cluster, wherein the main server is a server with a preset folder in the shared big data, and the matching server is a server without the preset folder in the shared big data;

receiving first big data to be integrated sent by the main server and second big data to be integrated sent by the matching server, and integrating the first big data to be integrated and the second big data to be integrated to obtain integrated big data, wherein the first big data to be integrated is obtained by the main server through preset big data interaction with the matching server determined by the information of the matching server;

respectively returning the integrated big data to the main server and the matching server;

receiving a first-stage first logic relationship tree of the main server for the integrated big data transmission, receiving a second-stage first logic relationship tree of the matching server for the integrated big data transmission, and integrating the first-stage first logic relationship tree and the second-stage first logic relationship tree to obtain the first logic relationship tree corresponding to each cluster, thereby obtaining at least one first logic relationship tree;

and integrating the at least one first logic relation tree to obtain the first to-be-processed knowledge graph.

Optionally, the step of receiving a plurality of second logical relationship trees sent by the plurality of servers, and integrating the plurality of second logical relationship trees to obtain a second to-be-processed knowledge graph includes:

receiving a second logic relation tree sent by each server, thereby obtaining a plurality of second logic relation trees;

and integrating the plurality of second logic relation trees to obtain the second to-be-processed knowledge graph.

Optionally, before the receiving preset medical big data information sent by a plurality of servers, the method further includes:

generating a security verification code and sending the security verification code to the plurality of servers; the security verification code is used for encrypting the big data to be integrated by the server when the big data to be integrated are interacted; correspondingly, the constructing a first to-be-processed knowledge graph based on the preset medical big data information through a first logic relationship tree obtained by interacting big data to be integrated with the plurality of servers includes: and constructing the first to-be-processed knowledge graph through the first logic relationship tree obtained by interacting the to-be-integrated big data encrypted with the plurality of servers based on the preset medical big data information.

Optionally, the step of encrypting the big data to be integrated includes:

acquiring a security verification trigger action sent by a target server, wherein the target server is a server associated with a server where big data to be integrated is located in the plurality of servers, and the security verification trigger action is used for indicating the computer equipment to send a verification action for acquiring a first security feature vector to the target server;

receiving the first security feature vector of the target to-be-integrated big data corresponding to the server where the big data to be integrated is located, which is returned by the target server based on the verification action;

determining a security verification vector associated with the target big data to be integrated according to the first security feature vector, and acquiring a preset verification vector for verifying the security verification vector from a first verification vector set, wherein the security verification vector is content information in the first security feature vector associated with the target big data to be integrated, the security verification vector comprises a vector type index and a vector numerical index corresponding to the first security feature vector, the security verification vector comprises a target security feature vector associated with the target big data to be integrated, and the preset verification vector is determined by a third-party security platform associated with the computer device;

acquiring a feature element set associated with the preset verification vector;

if the feature element set contains a first security feature vector associated with the vector type index and the vector numerical index, and the source identifier of the first security feature vector belongs to a preset source database corresponding to the first security feature vector, determining that the security confidence of the security verification vector exceeds a preset confidence threshold;

when the safety confidence of the safety verification vector exceeds a preset confidence threshold, extracting the target safety feature vector from the safety verification vector;

acquiring a target cluster from a big data information processing platform associated with the computer equipment, and traversing servers on the target cluster;

if the server which is traversed on the target cluster and is associated with the target safety feature vector is determined as a reference server, the safety verification of the target to-be-integrated big data is determined to be completed, and the safety verification is passed;

acquiring a second security feature vector from a first verification vector set associated with the computer equipment according to a security verification trigger action, and returning the second security feature vector to a target server as response information corresponding to the security verification trigger action so that the target server performs security verification on the second security feature vector, wherein the second security feature vector carries a first security verification subcode associated with the computer equipment;

receiving an encryption process processing result sent by the target server based on the first security verification subcode, wherein the encryption process processing result carries a security mapping file obtained by performing security transcoding operation on a target character string by using the first security verification subcode;

decrypting the security mapping file through a second security verification sub-code corresponding to the first security verification sub-code to obtain a target character string associated with the security verification trigger action;

generating a security verification code for communication connection with the target server according to the target character string;

when the security verification passes and the encryption flow associated with the security verification trigger action is completed, establishing communication connection with the target server, and acquiring a server updating trigger action sent by the target server based on a security verification code corresponding to the communication connection;

determining a server which is in the target cluster except the reference server and is irrelevant to the target security feature vector as an irrelevant server based on the server updating triggering action, wherein the target security feature vector comprises identity address index information used for representing the target big data to be integrated;

checking the irrelevant server in the target cluster, determining a reference server in the checked target cluster as a correlation server associated with the target big data to be integrated, and searching big data type information matched with the identity address index information in the correlation server;

performing security transcoding operation on the searched big data type information by using the security verification code, taking the big data type information after the security transcoding operation as a security verification result, returning the security verification result to the target server to complete the encryption of the big data to be integrated, wherein the security authentication code is determined jointly by the target server and the computer device participating in the encryption process, the security verification result is obtained after security transcoding operation is carried out on big data type information associated with the target big data to be integrated through the security verification code, and the big data type information associated with the target big data to be integrated is big data type information matched with the target security feature vector in a reference server acquired from a big data information processing platform associated with the computer equipment.

Optionally, when receiving a plurality of sub-sharing identifiers returned by the plurality of servers for the to-be-processed medical big data information based on the target knowledge graph, integrating a big data sharing result by using the plurality of sub-sharing identifiers, and completing medical big data sharing analysis, the method includes:

receiving sub-sharing identifications sent by each server aiming at the medical big data information to be processed based on the target knowledge graph, so as to obtain a plurality of sub-sharing identifications;

and integrating the plurality of sub-sharing identifications to obtain a big data sharing result, and finishing the big data sharing.

In a second aspect, an embodiment of the present invention provides a medical big data sharing analysis apparatus, which is applied to a computer device, and includes:

the system comprises a receiving module, a first processing module and a second processing module, wherein the receiving module is used for receiving preset medical big data information sent by a plurality of servers, and constructing a first to-be-processed knowledge graph through a first logic relation tree obtained by interacting big data to be integrated with the plurality of servers based on the preset medical big data information, and the preset medical big data information represents an address index of shared big data in the servers; receiving a plurality of second logic relation trees sent by the plurality of servers, and integrating the plurality of second logic relation trees to obtain a second knowledge graph to be processed;

the processing module is used for integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph and sending the target knowledge graph to the plurality of servers so that the plurality of servers can share big data by using the target knowledge graph;

the acquisition module is used for acquiring to-be-processed medical big data information and respectively sending the to-be-processed medical big data information to the plurality of servers, wherein the to-be-processed medical big data information represents an address index of to-be-processed shared big data to be shared;

and the sharing module is used for integrating a big data sharing result by utilizing the plurality of sub-sharing identifications when receiving a plurality of sub-sharing identifications returned by the plurality of servers aiming at the to-be-processed medical big data information based on the target knowledge graph, so as to complete medical big data sharing analysis.

In a third aspect, an embodiment of the present invention provides a computer device, where the computer device includes a processor and a non-volatile memory storing computer instructions, and when the computer instructions are executed by the processor, the computer device executes the medical big data sharing analysis method according to the first aspect.

In a fourth aspect, the embodiment of the present invention provides a readable storage medium, where the readable storage medium includes a computer program, and the computer program controls, when running, a computer device where the readable storage medium is located to perform the medical big data sharing analysis method according to the first aspect.

Compared with the prior art, the beneficial effects provided by the invention comprise: the embodiment of the invention adopts a medical big data sharing analysis method, a medical big data sharing analysis device, computer equipment and a readable storage medium, wherein a first to-be-processed knowledge graph is constructed by receiving preset medical big data information sent by a plurality of servers and carrying out interaction on big data to be integrated with the plurality of servers to obtain a first logic relation tree based on the preset medical big data information, wherein the preset medical big data information represents an address index of the shared big data in the servers; receiving a plurality of second logic relation trees sent by the plurality of servers, and integrating the plurality of second logic relation trees to obtain a second to-be-processed knowledge graph; then integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph, and sending the target knowledge graph to the plurality of servers so that the plurality of servers can share big data by using the target knowledge graph; acquiring to-be-processed medical big data information, and respectively sending the to-be-processed medical big data information to the plurality of servers, wherein the to-be-processed medical big data information represents an address index of to-be-processed shared big data to be shared; and finally, when a plurality of sub-sharing identifications returned by the plurality of servers aiming at the medical big data information to be processed based on the target knowledge graph are received, integrating a big data sharing result by using the plurality of sub-sharing identifications, completing medical big data sharing analysis, and conveniently realizing the operation of sharing big data.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below. It is appreciated that the following drawings depict only certain embodiments of the invention and are therefore not to be considered limiting of its scope. For a person skilled in the art, it is possible to derive other relevant figures from these figures without inventive effort.

Fig. 1 is a schematic block diagram of a medical big data sharing analysis system provided in an embodiment of the present invention;

FIG. 2 is a flowchart illustrating steps of a medical big data sharing analysis method according to an embodiment of the present invention;

fig. 3 is a block diagram schematically illustrating a structure of a medical big data sharing and analyzing device according to an embodiment of the present invention;

fig. 4 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the described embodiments are one-stage embodiments of the invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

Furthermore, the terms "first," "second," and the like are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.

The following detailed description of embodiments of the invention refers to the accompanying drawings.

At present, big data have gone deep into each industry, field, make contributions to the improvement of people's standard of living. However, for the medical industry, as the big data related business develops, the data volume thereof becomes larger and larger, and the demands of different users are also increased. Due to the characteristics of big data, all data are directly shared, so that more computing resources are occupied, meanwhile, data processing logics, formats and the like adopted by all medical related users (such as hospitals) during docking are not completely the same, medical related users are different from users specially used for information processing, and the medical related users do not have mature big data processing capacity, so that the users need to customize a data sharing strategy every time when sharing big data, and great inconvenience is brought. To solve the aforementioned problems, please refer to fig. 1, in which fig. 1 is an interactive schematic diagram of a medical big data sharing analysis system according to an embodiment of the present invention. The medical big data sharing analysis system may include a computer device 100 and a plurality of servers 200 communicatively connected to the computer device 100. The medical big data sharing and analyzing system shown in fig. 1 is only one possible embodiment, and in other possible embodiments, the medical big data sharing and analyzing system may include only one of the components shown in fig. 1 or may also include other components.

The server 200 may include a mobile device, a tablet computer, a laptop computer, etc., or any combination thereof. In some embodiments, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, or the like, or any combination thereof. In some embodiments, the smart home devices may include control devices of smart electrical devices, smart monitoring devices, smart televisions, smart cameras, and the like, or any combination thereof. In some embodiments, the wearable device may include a smart bracelet, a smart lace, smart glass, a smart helmet, a smart watch, a smart garment, a smart backpack, a smart accessory, or the like, or any combination thereof. In some embodiments, the smart mobile device may include a smartphone, a personal digital assistant, a gaming device, and the like, or any combination thereof. In some embodiments, the virtual reality device and/or the augmented reality device may include a virtual reality helmet, virtual reality glass, a virtual reality patch, an augmented reality helmet, augmented reality glass, an augmented reality patch, or the like, or any combination thereof. For example, the virtual reality device and/or augmented reality device may include various virtual reality products and the like.

In an embodiment of the present invention, the computer device 100 and the plurality of servers 200 in the medical big data sharing and analyzing system may cooperatively perform a medical big data sharing and analyzing method according to the following method embodiment, please refer to fig. 2, and fig. 2 is a schematic flowchart of steps of the medical big data sharing and analyzing method according to the embodiment of the present invention. The medical big data sharing analysis method provided by the present invention is described in detail below, and is executed by the computer device 100 in fig. 1.

Step 201, receiving preset medical big data information sent by a plurality of servers 200, and constructing a first to-be-processed knowledge graph through a first logic relationship tree obtained by performing to-be-integrated big data interaction with the plurality of servers 200 based on the preset medical big data information.

The preset medical big data information represents an address index of the shared big data in the server 200.

Step 202, receiving a plurality of second logical relationship trees sent by the plurality of servers 200, and integrating the plurality of second logical relationship trees to obtain a second to-be-processed knowledge graph.

Step 203, integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph, and sending the target knowledge graph to the plurality of servers 200, so that the plurality of servers 200 share the big data by using the target knowledge graph.

And step 204, acquiring the medical big data information to be processed, and respectively sending the medical big data information to be processed to the plurality of servers 200.

The to-be-processed medical big data information represents the address index of the to-be-processed shared big data to be shared.

Step 205, when receiving a plurality of sub-sharing identifiers returned by the plurality of servers 200 for the medical big data information to be processed based on the target knowledge graph, integrating a big data sharing result by using the plurality of sub-sharing identifiers, and completing the medical big data sharing analysis.

In the embodiment of the present invention, the computer device 100 may also be one of the servers 200, which is not limited herein. Since the big data sharing among users is mostly not only shared once, the sharing rule can be constructed first. Specifically, preset medical big data information sent by a plurality of servers 200 may be received, and in the embodiment of the present invention, the preset medical big data information may be a known sample, and basic information such as data content, type, address index, and the like of the preset medical big data information may be obtained in advance (for example, basic related information of a patient and a storage location of the basic related information of the patient in the server 200). The first logical relationship tree may be obtained by performing to-be-integrated big data interaction with the plurality of servers 200, that is, simulating to perform big data transmission, it should be understood that the first logical relationship tree may be obtained by performing to-be-integrated big data interaction multiple times, and then the first to-be-processed knowledge graph may be constructed based on the first logical relationship tree. Meanwhile, a plurality of second logical relationship trees sent by the plurality of servers 200 may be obtained, and it should be noted that the data transmitted from the computer device 100 to the server 200 may correspond to the first logical relationship tree, that is, the first to-be-processed knowledge graph, and the data transmitted from the server 200 to the computer device 100 may correspond to the second logical relationship tree, that is, the second to-be-processed knowledge graph. The first knowledge graph and the second knowledge graph are integrated to obtain a target knowledge graph, and big data can be shared based on the target knowledge graph. Specifically, the to-be-processed medical big data information may be acquired, the to-be-processed medical big data information may be input by a user, that is, the to-be-processed medical big data information may represent the address index of the to-be-processed shared big data to be shared. The medical big data information to be processed can be sent to each server 200, so that each server 200 can share the big data based on the pre-constructed target knowledge graph. The server 200 may generate the sub-sharing identifier through the target knowledge graph, the sub-sharing identifier may represent relevant information, including address indexes, names, types, and the like, of the to-be-shared big data to be processed in the corresponding server 200, and the big data sharing result may be determined based on the plurality of sub-sharing identifiers, so as to implement big data sharing. Through the steps, the problem of unsmooth data sharing among different users due to different data transmission logics and rules can be solved through the target knowledge graph, the users are helped not to make corresponding sharing strategies every time data sharing is carried out, useless workload of the users is reduced, and the purpose of conveniently sharing medical big data is achieved.

On the basis of the foregoing, as an alternative embodiment, the foregoing step 203 may be implemented by the following specific implementation.

Substep 203-1, obtaining a plurality of sample big data from a plurality of servers 200, and integrating the plurality of sample big data to obtain a first big data sample object set.

Wherein the sample big data characterizes private big data in the server 200.

And a substep 203-2, integrating the preset medical big data information sent by the plurality of servers 200 to obtain a second big data sample object set.

Substep 203-3, a target big data sample object set is obtained based on the first big data sample object set and the second big data sample object set.

Substep 203-4, calculating a first association relationship using the first set of big data sample objects and the target set of big data sample objects, and calculating a second association relationship using the second set of big data sample objects and the target set of big data sample objects.

And a substep 203-5 of integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph according to the first association relation and the second association relation to obtain a target knowledge graph.

Specifically, a plurality of sample big data may be acquired from a plurality of servers 200, and basic information such as an address index, data content, data type (e.g., medical-related data), and data name of the sample big data may be known in advance. A first set of big data sample objects may be obtained by integrating a plurality of sample big data. The preset medical big data information sent by the plurality of servers 200 can be integrated to obtain a second big data sample object set. The two can then be integrated to obtain a target big data sample object set. The first big data sample object set and the second big data sample object set can be respectively adopted to be compared with the target big data sample object set, and corresponding first incidence relation and second incidence relation are obtained. Then, the first to-be-processed knowledge graph and the second to-be-processed knowledge graph can be integrated based on the second association relation and the second association relation, and the target knowledge graph is obtained. Through the steps, the reference basis, namely the target knowledge graph, required by the computer equipment 100 during data sharing can be obtained conveniently, manual operation is reduced, and convenience of medical related users in big data sharing is improved.

On the basis of the foregoing, in order to be able to explain the foregoing step 201 in detail, a specific implementation of the step 201 is provided below.

Substep 201-1, using the preset medical big data information, dividing the plurality of servers 200 into at least one cluster, and sending information of a matching server belonging to the same cluster to the main server in each cluster.

The main server is the server 200 with the preset folder in the shared big data, and the matching server is the server 200 without the preset folder in the shared big data.

And a substep 201-2 of receiving the first big data to be integrated sent by the main server and the second big data to be integrated sent by the matching server, and integrating the first big data to be integrated and the second big data to be integrated to obtain the integrated big data.

The first big data to be integrated is obtained by the main server through interaction of preset big data with the matching server determined by the information of the matching server.

And a substep 201-3 of returning the integrated big data to the main server and the matching server respectively.

And a substep 201-4, receiving a first logic relationship tree of a first stage of the integrated big data transmission by the main server, receiving a first logic relationship tree of a second stage of the integrated big data transmission by the matching server, and integrating the first logic relationship tree of the first stage and the first logic relationship tree of the second stage to obtain a first logic relationship tree corresponding to each cluster, thereby obtaining at least one first logic relationship tree.

Substep 201-5, integrating at least one first logical relationship tree to obtain a first to-be-processed knowledge graph.

The plurality of servers 200 may be divided into at least one cluster by presetting the type, data content, and the like of the medical big data information as a division basis, and the division standard between different clusters may refer to the same division basis. A master server may be selected in the cluster for coordinating the interaction of the other remaining matching servers. The first big data to be integrated and the big data to be integrated corresponding to the main server and the matching server can be obtained respectively, processed to obtain the integrated big data, and fed back to the main server and the matching server. After the main server obtains the integrated big data, the first logic relation tree of the first stage can be constructed, and meanwhile, the matching server can also construct the first logic relation tree of the second stage after receiving the integrated big data. And performing memorability integration on the first logical relationship tree and the second logical relationship tree to obtain a first logical relationship tree corresponding to at least one cluster. It should be understood that a cluster may correspond to a logical relationship tree, and the first to-be-processed knowledge-graph may be obtained by integrating all the obtained first logical relationship trees.

For the above substeps 201-5, embodiments of the present invention provide the following specific implementations.

(1) And carrying out data volume statistics on the preset medical big data information in each cluster to obtain the cluster big data corresponding to each cluster.

(2) And counting the total big data of the preset medical big data information sent by the plurality of servers 200 to obtain a second big data sample object set.

(3) Weight information is calculated for each of the at least one first logical relationship trees using the cluster big data and the second big data sample object set.

(4) And weighting at least one first logic relation tree according to the weight information to obtain a first to-be-processed knowledge graph.

The reference basis may be a data amount of preset medical big data information, and the preset medical big data information corresponding to each cluster may be counted to obtain the big data of each corresponding cluster. The sum total big data corresponding to the preset medical big data information of all the servers 200 can be determined. The total big data can be placed and processed into a second big data sample set, and the first logical relationship tree matching corresponding weight information corresponding to each cluster big data can be determined based on the relationship between the data volume of each cluster big data and the data volume of the second big data sample set. And performing weighting operation on the first logic relation tree to construct and obtain a first to-be-processed knowledge graph.

Specifically, the preset medical big data information includes an identification document capable of characterizing whether the server 200 has a preset folder, and for the aforementioned sub-step 201-1, the following more detailed implementation is also provided in the embodiments of the present invention.

(1) And comparing the preset medical big data information sent by each server 200 to obtain a comparison result.

(2) When the comparison result indicates that the preset medical big data information sent by the at least two servers 200 is the same, the at least two servers 200 are divided into a cluster, so that at least one cluster is obtained.

(3) According to the identification document, a main server and a matching server are determined from each server 200 of each cluster in at least one cluster, and the information of the matching server is sent to the main server.

As described above, the basis for dividing the servers 200 into the same cluster may be the same, and in the embodiment of the present invention, the data type information may be data type information in the preset medical big data information, and when the data type information is the same, the servers may be divided into the same cluster. After the division into the same cluster, the master server may be determined according to the identification document in the preset folder. Specifically, the main server may be a preset server 200 with a strong data processing capability.

In addition to providing the step of obtaining the first to-be-processed knowledge-graph, the embodiment of the present invention also provides a specific implementation manner of the aforementioned step 202, which is used to describe how to obtain the second to-be-processed knowledge-graph through the following steps.

Sub-step 202-1, receiving the second logical relationship tree sent by each server 200, thereby obtaining a plurality of second logical relationship trees.

And a substep 202-2 of integrating the plurality of second logical relationship trees to obtain a second to-be-processed knowledge graph.

The method for constructing the second to-be-processed knowledge graph may refer to the method for constructing the first knowledge graph, and is not described herein again.

In addition, before step 201, in order to ensure the security of data sharing, the following steps are further provided in the embodiment of the present invention.

Step 301, generating a security verification code, and sending the security verification code to a plurality of servers 200, wherein the security verification code is used for encrypting the big data to be integrated by the servers 200 when the big data to be integrated are interacted. Accordingly, step 201 may include the following embodiments based on the foregoing.

And a substep 201-6 of constructing a first to-be-processed knowledge graph through a first logic relationship tree obtained by interacting the to-be-integrated big data encrypted with the plurality of servers 200 based on preset medical big data information.

In order to ensure the security of big data sharing, the security of the sent big data and the security of the received big data are included. The security verification code may be generated, and based on this, the first to-be-processed knowledge graph may be constructed through the first logical relationship tree obtained by interacting the to-be-integrated big data encrypted with the plurality of servers 200.

On the basis of the foregoing, the embodiment of the present invention provides a step of adding to-be-integrated big data, which can be specifically implemented in the following manner.

Substep 301-1, obtain the security verification trigger action sent by the target server.

The target server is a server 200 associated with the server 200 where the big data to be integrated is located in the plurality of servers 200, and the security verification trigger action is used for instructing the computer device 100 to send a verification action for acquiring the first security feature vector to the target server.

And a substep 301-2 of receiving a first security feature vector of the target big data to be integrated, which is returned by the target server based on the verification action and corresponds to the server 200 where the big data to be integrated is located.

And a substep 301-3, determining a security verification vector associated with the target big data to be integrated according to the first security feature vector, and acquiring a preset verification vector for verifying the security verification vector from the first verification vector set.

The security verification vector is content information in a first security feature vector associated with the target big data to be integrated, the security verification vector includes a vector type index and a vector numerical index corresponding to the first security feature vector, the security verification vector includes a target security feature vector associated with the target big data to be integrated, and the preset verification vector is determined by a third-party security platform associated with the computer device 100.

Sub-step 301-4, a set of feature elements associated with a preset verification vector is obtained.

In sub-step 301-5, if the feature element set includes a first security feature vector associated with the vector type indicator and the vector value indicator, and the source identifier of the first security feature vector belongs to a preset source database corresponding to the first security feature vector, it is determined that the security confidence of the security verification vector exceeds a preset confidence threshold.

And a substep 301-6, extracting the target security feature vector from the security verification vector when the security confidence of the security verification vector exceeds a preset confidence threshold.

Substep 301-7, retrieving the target cluster from the big data information processing platform associated with the computer device 100, traversing the servers 200 on the target cluster.

In sub-step 301-8, if the server 200 associated with the target security feature vector is traversed on the target cluster, determining that the server 200 associated with the target security feature vector is traversed as a reference server, determining that security verification on the target to-be-integrated big data is completed, and the security verification is passed.

Sub-step 301-9, obtaining a second security feature vector from the first set of authentication vectors associated with the computer device 100 according to the security authentication trigger action, and returning the second security feature vector to the target server as response information corresponding to the security authentication trigger action, so that the target server performs security authentication on the second security feature vector.

Wherein the second security feature vector carries therein the first security verifier code associated with the computer device 100.

And a substep 301-10 of receiving the encryption flow processing result sent by the target server based on the first security verification subcode.

And the encryption flow processing result carries a security mapping file obtained by performing security transcoding operation on the target character string by using the first security verification subcode.

And a substep 301-11, decrypting the security mapping file through a second security verification subcode corresponding to the first security verification subcode to obtain a target character string associated with the security verification trigger action.

And a substep 301-12 of generating a security verification code for communication connection with the target server according to the target character string.

And substeps 301-13, when the security verification passes and the encryption process associated with the security verification trigger action is completed, establishing a communication connection with the target server, and acquiring a server update trigger action sent by the target server based on a security verification code corresponding to the communication connection.

Substeps 301-14, determining servers 200 in the target cluster other than the reference server and not associated with the target security feature vector as unrelated servers based on the server update trigger action.

The target security feature vector comprises identity address index information used for representing the target to-be-integrated big data.

And substeps 301-15, performing investigation on irrelevant servers in the target cluster, determining reference servers in the investigated target cluster as associated servers associated with the target big data to be integrated, and searching the big data type information matched with the identity address index information in the associated servers.

And substeps 301-16, performing security transcoding operation on the searched big data type information by using a security verification code, taking the big data type information after the security transcoding operation as a security verification result, and returning the security verification result to the target server to complete the encryption of the big data to be integrated.

The security verification code is determined by the target server and the computer device 100 which participate in the encryption process, the security verification result is obtained after security transcoding operation is performed on big data type information associated with the target big data to be integrated through the security verification code, and the big data type information associated with the target big data to be integrated is big data type information matched with the target security feature vector in a reference server acquired from a big data information processing platform associated with the computer device 100.

In other implementation manners of the embodiment of the invention, the server updating triggering action carries a reference server safety factor; the aforementioned step 301 may further include the following implementation manner to determine the security verification result, where the reference server security factor is a target security factor in the local security verification interval stored in the second set of verification vectors of the target server.

And substeps 301-17, pulling the security verification intervals of all servers 200 on the target cluster from the big data information processing platform based on the server updating trigger action, and obtaining a comparison safety factor in the security verification intervals of all servers 200, wherein the comparison safety factor is the target safety factor on the target cluster.

Substeps 301-18 determine a security verification interval to be synchronized for server synchronization between the target server and the computer device 100 based on a security factor difference parameter between the comparison security factor and the reference server security factor.

And substeps 301-19, taking the security verification interval to be synchronized as a security verification result, and returning the security verification result to the target server.

The security verification trigger action may be an operation of clicking a certain key on the corresponding interactive screen by the user, or may be an externally input physical signal, which is not limited herein. The security verification trigger signal may instruct the computer device 100 to send a verification action to the target server for obtaining the first security feature vector. After receiving the first security feature vector returned by the target server, determining the first security feature vector, determining a security verification vector associated with the target big data to be integrated, and further acquiring a preset verification vector for verifying the security verification vector from the first verification vector set. The first set of authentication vectors may be a set of vectors that are pre-set for authenticating the secure authentication vector.

The method includes the steps that a feature element set associated with a preset verification vector can be obtained, a first safety feature vector associated with a vector type index and a vector numerical index is contained in the feature element set after judgment, and a source identifier of the first safety feature vector belongs to a preset source database corresponding to the first safety feature vector, and then the safety confidence coefficient of the safety verification vector is determined to exceed a preset confidence coefficient threshold value. Specifically, the confidence threshold may be an integer of 0 or 1, and the preset confidence threshold may be set to 0, and when the security confidence of the security verification vector exceeds the preset confidence threshold, that is, the security confidence of the security verification vector is 1, the target security feature vector may be further obtained.

The target cluster may be obtained from a big data information processing platform, it being understood that the plurality of clusters of servers 200 associated with the computer device 100 may all be considered to be on a big data information processing platform. When the server 200 associated with the target security feature vector appears when the server 200 on the target cluster is traversed, the server 200 traversed to be associated with the target security feature vector is determined as a reference server, the security verification of the target to-be-integrated big data is determined to be completed, and the security verification is passed.

Based on the foregoing security verification-related operation, a second security feature vector is obtained from the first verification vector set associated with the computer device 100 again according to the security verification trigger action, and the second security feature vector is returned to the target server as response information corresponding to the security verification trigger action, so that the target server performs security verification on the second security feature vector. The encryption flow processing result obtained by performing the encryption flow processing on the first security authentication subcode in the second security feature vector can be received. Meanwhile, a second security verification subcode corresponding to the first security verification subcode can be set to decrypt the security mapping file, so as to obtain a target character string associated with the security verification trigger action, and it is worth explaining that the target character string can be understood as a decryption rule of the security mapping file. The parameter may be a fixed parameter or a random parameter, which is not limited in the embodiment of the present invention. After the security verification code is obtained, in order to reduce the operation pressure of the computer device 100 and the server 200, the server 200 unrelated to the target security feature vector may be checked, i.e., the unrelated server is removed from the target cluster. And after the security verification code is determined, the security transcoding operation can be performed on the big data type information based on the security verification code, so that a security verification result is determined, the security verification result is sent to the target server, and the encryption process of the big data to be integrated can be considered to be completed. Through the steps, the calculation amount can be reduced, meanwhile, the encryption of the big data to be integrated is realized, and the secrecy of the sharing related big data can be stably realized.

On the basis of the foregoing, as an alternative implementation, the embodiment of the present invention provides a specific implementation of the foregoing step 205.

And a substep 205-1 of receiving the sub-sharing identifiers sent by each server 200 for the medical big data information to be processed based on the target knowledge graph, so as to obtain a plurality of sub-sharing identifiers.

And a substep 205-2, integrating the plurality of sub-sharing identifications to obtain a big data sharing result, and completing medical big data sharing analysis.

In addition to the above steps, in the embodiment of the present invention, when the security verification state is a failure state, request failure information corresponding to the security verification trigger action may be generated, and the request failure information is returned to the target server, so that the target server performs failure analysis based on the request failure information.

The embodiment of the invention provides a medical big data sharing and analyzing device, which is applied to a computer device 100 and comprises:

the receiving module 1101 is configured to receive preset medical big data information sent by the plurality of servers 200, and construct a first to-be-processed knowledge graph through a first logical relationship tree obtained by interacting big data to be integrated with the plurality of servers 200 based on the preset medical big data information, where the preset medical big data information represents an address index of shared big data in the servers; and receiving a plurality of second logical relationship trees sent by a plurality of servers 200, and integrating the plurality of second logical relationship trees to obtain a second to-be-processed knowledge graph.

The processing module 1102 is configured to integrate the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph, and send the target knowledge graph to the multiple servers 200, so that the multiple servers 200 share the big data by using the target knowledge graph.

The obtaining module 1103 is configured to obtain to-be-processed medical big data information, and send the to-be-processed medical big data information to the multiple servers 200, where the to-be-processed medical big data information represents an address index of to-be-processed shared big data to be shared.

The sharing module 1104 is configured to, when receiving a plurality of sub-sharing identifiers returned by the plurality of servers 200 based on the target knowledge graph for the medical big data information to be processed, integrate a big data sharing result by using the plurality of sub-sharing identifiers, and complete medical big data sharing analysis.

Further, the processing module 1102 is specifically configured to:

acquiring a plurality of sample big data from a plurality of servers 200, and integrating the plurality of sample big data to obtain a first big data sample object set, wherein the sample big data represents private big data in the servers; integrating preset medical big data information sent by a plurality of servers 200 to obtain a second big data sample object set; obtaining a target big data sample object set based on the first big data sample object set and the second big data sample object set; calculating a first incidence relation by using the first big data sample object set and the target big data sample object set, and calculating a second incidence relation by using the second big data sample object set and the target big data sample object set; and integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph according to the first incidence relation and the second incidence relation to obtain a target knowledge graph.

Further, the receiving module 1101 is specifically configured to:

dividing a plurality of servers 200 into at least one cluster by using preset medical big data information, and sending information of a matching server belonging to the same cluster to a main server in each cluster, wherein the main server is a server 200 with a preset folder in shared big data, and the matching server is a server 200 without the preset folder in the shared big data; receiving first big data to be integrated sent by a main server and second big data to be integrated sent by a matching server, and integrating the first big data to be integrated and the second big data to be integrated to obtain integrated big data, wherein the first big data to be integrated is obtained by the main server through preset big data interaction with the matching server determined by the information of the matching server; respectively returning the integrated big data to the main server and the matching server; receiving a first-stage first logic relationship tree sent by a main server aiming at the integrated big data, receiving a second-stage first logic relationship tree sent by a matching server aiming at the integrated big data, and integrating the first-stage first logic relationship tree and the second-stage first logic relationship tree to obtain a first logic relationship tree corresponding to each cluster so as to obtain at least one first logic relationship tree; and integrating at least one first logic relation tree to obtain a first to-be-processed knowledge graph.

Further, the receiving module 1101 is specifically configured to:

receiving the second logical relationship trees sent by each server 200, thereby obtaining a plurality of second logical relationship trees; and integrating the plurality of second logic relation trees to obtain a second to-be-processed knowledge graph.

The medical big data sharing analysis device 110 further includes a security module 1105, the security module 1105 is configured to:

generating a security verification code and transmitting the security verification code to the plurality of servers 200; the security verification code is used for encrypting the big data to be integrated by the server 200 when the big data to be integrated interacts. Correspondingly, the receiving module 1101 is specifically configured to:

based on the preset medical big data information, a first to-be-processed knowledge graph is constructed through a first logic relation tree obtained through interaction of the big data to be integrated after being encrypted with the plurality of servers 200.

Further, the security module 1105 is specifically configured to:

acquiring a security verification trigger action sent by a target server, wherein the target server is a server 200 associated with a server 200 where big data to be integrated is located in the plurality of servers 200, and the security verification trigger action is used for instructing the computer device 100 to send a verification action for acquiring a first security feature vector to the target server; receiving a first security feature vector of the target big data to be integrated, which is returned by the target server based on the verification action and corresponds to the server 200 where the big data to be integrated is located; determining a security verification vector associated with the target big data to be integrated according to the first security feature vector, and acquiring a preset verification vector for verifying the security verification vector from the first verification vector set, wherein the security verification vector is content information in the first security feature vector associated with the target big data to be integrated, the security verification vector includes a vector type index and a vector numerical index corresponding to the first security feature vector, the security verification vector includes a target security feature vector associated with the target big data to be integrated, and the preset verification vector is determined by a third-party security platform associated with the computer device 100; acquiring a feature element set associated with a preset verification vector; if the feature element set contains a first security feature vector associated with the vector type index and the vector numerical index, and the source identifier of the first security feature vector belongs to a preset source database corresponding to the first security feature vector, determining that the security confidence of the security verification vector exceeds a preset confidence threshold; when the safety confidence of the safety verification vector exceeds a preset confidence threshold, extracting a target safety characteristic vector from the safety verification vector; acquiring a target cluster from a big data information processing platform associated with the computer equipment 100, and traversing the server 200 on the target cluster; if the server 200 associated with the target security feature vector is traversed on the target cluster, determining the server 200 associated with the target security feature vector as a reference server, and determining that the security verification of the target to-be-integrated big data is completed and the security verification is passed; acquiring a second security feature vector from the first authentication vector set associated with the computer device 100 according to the security authentication trigger action, and returning the second security feature vector to the target server as response information corresponding to the security authentication trigger action so that the target server performs security authentication on the second security feature vector, wherein the second security feature vector carries a first security authentication subcode associated with the computer device 100; receiving an encryption flow processing result sent by a target server based on a first security verification subcode, wherein the encryption flow processing result carries a security mapping file obtained by performing security transcoding operation on a target character string by using the first security verification subcode; decrypting the security mapping file through a second security verification sub-code corresponding to the first security verification sub-code to obtain a target character string associated with the security verification trigger action; generating a security verification code for communication connection with a target server according to the target character string; when the security verification passes and an encryption flow associated with the security verification trigger action is completed, establishing communication connection with a target server, and acquiring a server updating trigger action sent by the target server based on a security verification code corresponding to the communication connection; determining a server 200 which is in the target cluster except the reference server and is irrelevant to a target security feature vector as an irrelevant server based on a server updating triggering action, wherein the target security feature vector comprises identity address index information used for representing target to-be-integrated big data; checking irrelevant servers in the target cluster, determining a reference server in the checked target cluster as a correlation server associated with the target big data to be integrated, and searching big data type information matched with the identity address index information in the correlation server; and carrying out safe transcoding operation on the searched big data type information by using a safe verification code, using the big data type information after the safe transcoding operation as a safe verification result, and returning the safe verification result to the target server to finish the encryption of the big data to be integrated, wherein the safe verification code is jointly determined by the target server and the computer equipment 100 participating in the encryption process, the safe verification result is obtained after carrying out safe transcoding operation on the big data type information associated with the target big data to be integrated through the safe verification code, and the big data type information associated with the target big data to be integrated is the big data type information matched with the target safe characteristic vector in a reference server obtained from a big data information processing platform associated with the computer equipment 100.

Further, the sharing module 1104 is specifically configured to:

receiving sub-sharing identifications sent by each server 200 aiming at medical big data information to be processed based on a target knowledge graph, thereby obtaining a plurality of sub-sharing identifications; and integrating the plurality of sub-sharing identifications to obtain a big data sharing result, and finishing medical big data sharing analysis.

It should be noted that, for the implementation principle of the medical big data sharing analysis apparatus 110, reference may be made to the implementation principle of the medical big data sharing analysis method, which is not described herein again, and it should be understood that the division of each module of the apparatus is only a division of a logic function, and all or part of the division may be integrated on a physical entity or may be physically separated during actual implementation. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the receiving module 1101 may be a processing element separately set up, or may be implemented by being integrated into a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and the processing element of the apparatus calls and executes the functions of the receiving module 1101. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when some of the above modules are implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can call program code. As another example, these modules may be integrated together, implemented in the form of a system-on-a-chip (SOC).

The embodiment of the invention provides a computer device 100, wherein the computer device 100 comprises a processor and a nonvolatile memory storing computer instructions, and when the computer instructions are executed by the processor, the computer device 100 executes the medical big data sharing analysis method. As shown in fig. 4, fig. 4 is a block diagram of a computer device 100 according to an embodiment of the present invention. The computer device 100 includes a medical big data sharing analysis apparatus, a memory 111, a processor 112, and a communication unit 113.

To facilitate the transfer or interaction of data, the elements of the memory 111, the processor 112 and the communication unit 113 are electrically connected to each other, directly or indirectly. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The medical big data sharing analysis device comprises at least one software functional module which can be stored in the memory 111 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of the computer device 100. The processor 112 is used for executing executable modules stored in the memory 111, such as software functional modules and computer programs included in the medical big data sharing and analyzing device.

The readable storage medium comprises a computer program, and when the computer program runs, the computer device 100 where the readable storage medium is located is controlled by the computer program to execute the medical big data sharing analysis method.

In summary, with the medical big data sharing analysis method, device, computer equipment, and readable storage medium provided by the embodiments of the present invention, a first to-be-processed knowledge graph is constructed by receiving preset medical big data information sent by a plurality of servers, and performing interaction with the plurality of servers through a first logical relationship tree obtained by interacting big data to be integrated based on the preset medical big data information, where the preset medical big data information represents an address index of shared big data in the servers; receiving a plurality of second logic relation trees sent by the plurality of servers, and integrating the plurality of second logic relation trees to obtain a second to-be-processed knowledge graph; then integrating the first to-be-processed knowledge graph and the second to-be-processed knowledge graph to obtain a target knowledge graph, and sending the target knowledge graph to the plurality of servers so that the plurality of servers can share big data by using the target knowledge graph; acquiring to-be-processed medical big data information, and respectively sending the to-be-processed medical big data information to the plurality of servers, wherein the to-be-processed medical big data information represents an address index of to-be-processed shared big data to be shared; and finally, when a plurality of sub-sharing identifications returned by the plurality of servers aiming at the medical big data information to be processed based on the target knowledge graph are received, integrating a big data sharing result by using the plurality of sub-sharing identifications, completing medical big data sharing analysis, and conveniently realizing the operation of sharing the medical big data so as to help a user improve the processing efficiency of processing medical related services based on the shared medical big data.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical big data sharing analysis method is applied to computer equipment and comprises the following steps:

2. The method of claim 1, wherein the step of integrating the first to-be-processed knowledge-graph and the second to-be-processed knowledge-graph to obtain a target knowledge-graph comprises:

3. The method according to claim 1 or 2, wherein the step of constructing a first to-be-processed knowledge graph through a first logical relationship tree obtained through big data interaction to be integrated with the plurality of servers based on the preset medical big data information comprises:

4. The method according to claim 1, wherein the step of receiving a plurality of second logical relationship trees sent by the plurality of servers and integrating the plurality of second logical relationship trees to obtain a second to-be-processed knowledge graph comprises:

5. The method according to claim 1, wherein before the receiving preset medical big data information sent by a plurality of servers, the method further comprises:

6. The method according to claim 5, wherein the step of encrypting the big data to be integrated comprises:

acquiring a feature element set associated with the preset verification vector;

7. The method according to claim 1, wherein the step of integrating a big data sharing result by using a plurality of sub-sharing identifiers when receiving the plurality of sub-sharing identifiers returned by the plurality of servers for the to-be-processed medical big data information based on the target knowledge graph to complete medical big data sharing analysis comprises:

8. A medical big data sharing and analyzing device is applied to computer equipment and comprises:

9. A computer device comprising a processor and a non-volatile memory storing computer instructions, wherein when the computer instructions are executed by the processor, the computer device performs the medical big data sharing analysis method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that the readable storage medium comprises a computer program, and the computer program controls a computer device of the readable storage medium to execute the medical big data sharing analysis method according to any one of claims 1 to 7.