CN113674869B - Medical big data sharing method and system based on artificial intelligence - Google Patents
Medical big data sharing method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN113674869B CN113674869B CN202111223736.1A CN202111223736A CN113674869B CN 113674869 B CN113674869 B CN 113674869B CN 202111223736 A CN202111223736 A CN 202111223736A CN 113674869 B CN113674869 B CN 113674869B
- Authority
- CN
- China
- Prior art keywords
- obtaining
- medical data
- medical
- index
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a medical big data sharing method and system based on artificial intelligence, wherein the method comprises the following steps: obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform; storing the first rare case and correspondingly generating a first retrieval characteristic; according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period; constructing a first access trend prediction model according to the first cloud processor; inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index; judging whether the first prediction index is in a preset prediction index or not; and if so, completing data uploading on a plurality of associated medical data sharing platforms. The method solves the technical problem that in the prior art, based on the particularity of the rare cases, the corresponding medical data sharing method is not intelligent enough, and therefore isolated circulation of the rare cases is caused.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a medical big data sharing method and system based on artificial intelligence.
Background
Under the circumstance of rapid development of informatization, the investment of informatization construction is also increased in each medical institution, and the informatization level of medical systems is also continuously improved. Opening the information barriers among the medical institutions and realizing the sharing of medical data is a necessary trend meeting the actual data requirements of the medical and health industry, and has great application value. The data sharing can be integrated with medical information of each medical institution to form larger medical data, but the data sharing breakthrough still has larger obstacles due to the characteristics of the medical data such as the mass, the multi-party possession, the complexity, the safety and the like.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
in the prior art, the particularity based on rare cases exists, so that the corresponding medical data sharing method is not intelligent enough, and the technical problem of isolated circulation of the rare cases is caused.
Disclosure of Invention
The embodiment of the application provides a medical big data sharing method and system based on artificial intelligence, solves the technical problems that in the prior art, the method for sharing medical data based on rare cases is not intelligent enough, and isolated circulation of rare cases is caused, and achieves the technical effects of improving the intelligent calculation level for processing rare case data and realizing interconnection and intercommunication of rare case information by combining artificial intelligence and big data.
In view of the foregoing problems, the present application provides a medical big data sharing method and system based on artificial intelligence.
In a first aspect, an embodiment of the present application provides an artificial intelligence based medical big data sharing method, where the method is applied to an artificial intelligence based medical big data sharing system, the system is connected to a first cloud processor in communication, and the method includes: obtaining first medical data sharing platform information; establishing a first platform feature tag according to the first medical sharing platform information; obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform; storing the first rare case and correspondingly generating a first retrieval characteristic; according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period; constructing a first access trend prediction model according to the first cloud processor; inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index; judging whether the first prediction index is in a preset prediction index or not; if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms, wherein the plurality of associated medical data sharing platforms are mutually connected with the first medical data sharing platform; uploading the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
In another aspect, the present application further provides a medical big data sharing system based on artificial intelligence, where the system includes: a first obtaining unit for obtaining first medical data sharing platform information; the first construction unit is used for establishing a first platform feature tag according to the first medical sharing platform information; a second obtaining unit configured to obtain a first rare case by performing a rarity analysis on the medical data in the first medical data sharing platform; the first generating unit is used for storing the first rare case and correspondingly generating a first retrieval characteristic; a third obtaining unit, configured to obtain a first click amount and a first usage amount in a first preset period according to the first retrieval feature; the second construction unit is used for constructing a first access trend prediction model according to the first cloud processor; a fourth obtaining unit, configured to input the first click amount and the first usage amount into the first visit trend prediction model, and obtain a first prediction index; the first judgment unit is used for judging whether the first prediction index is in a preset prediction index or not; a fifth obtaining unit, configured to obtain a plurality of associated medical data sharing platforms if the first prediction index is in the preset prediction index, where the plurality of associated medical data sharing platforms are platforms that are connected to the first medical data sharing platform; a first uploading unit, configured to upload the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
In a third aspect, the present invention provides an artificial intelligence based medical big data sharing system, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the method comprises the steps of establishing a characteristic label corresponding to a platform by analyzing information in a first medical data sharing platform, conveniently performing unified analysis on all sharing platforms, performing rarity analysis on all medical data in the platform to obtain a retrieval characteristic generated by storing a first rare case, further inputting the click rate and the use amount of the first rare case into an access trend prediction model established in a cloud processor according to the retrieval characteristic to obtain a corresponding first prediction index, further judging whether the first prediction index is in a preset prediction index, if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms mutually connected with the first medical data sharing platform, and performing multi-platform uploading sharing on the medical data corresponding to the first rare case, the intelligent computing level for processing the rare case data is improved and the technical effect of interconnection and intercommunication of the rare case information is achieved through combination of artificial intelligence and big data.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
FIG. 1 is a schematic flow chart illustrating a medical big data sharing method based on artificial intelligence according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a medical big data sharing system based on artificial intelligence according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: the device comprises a first obtaining unit 11, a first constructing unit 12, a second obtaining unit 13, a first generating unit 14, a third obtaining unit 15, a second constructing unit 16, a fourth obtaining unit 17, a first judging unit 18, a fifth obtaining unit 19, a first uploading unit 20, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304 and a bus interface 305.
Detailed Description
The embodiment of the application provides a medical big data sharing method and system based on artificial intelligence, solves the technical problems that in the prior art, the method for sharing medical data based on rare cases is not intelligent enough, and isolated circulation of rare cases is caused, and achieves the technical effects of improving the intelligent calculation level for processing rare case data and realizing interconnection and intercommunication of rare case information by combining artificial intelligence and big data. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Under the circumstance of rapid development of informatization, the investment of informatization construction is also increased in each medical institution, and the informatization level of medical systems is also continuously improved. Opening the information barriers among the medical institutions and realizing the sharing of medical data is a necessary trend meeting the actual data requirements of the medical and health industry, and has great application value. The data sharing can be integrated with medical information of each medical institution to form larger medical data, but the data sharing breakthrough still has larger obstacles due to the characteristics of the medical data such as the mass, the multi-party possession, the complexity, the safety and the like. However, the particularity of rare cases exists in the prior art, so that the corresponding medical data sharing method is not intelligent enough, and the technical problem of isolated circulation of rare cases is caused.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides an artificial intelligence based medical big data sharing method, wherein the method is applied to an artificial intelligence based medical big data sharing system which is in communication connection with a first cloud processor, and the method comprises the following steps: obtaining first medical data sharing platform information; establishing a first platform feature tag according to the first medical sharing platform information; obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform; storing the first rare case and correspondingly generating a first retrieval characteristic; according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period; constructing a first access trend prediction model according to the first cloud processor; inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index; judging whether the first prediction index is in a preset prediction index or not; if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms, wherein the plurality of associated medical data sharing platforms are mutually connected with the first medical data sharing platform; uploading the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides an artificial intelligence based medical big data sharing method, where the method is applied to an artificial intelligence based medical big data sharing system, the system is connected to a first cloud processor in communication, and the method includes:
step S100: obtaining first medical data sharing platform information;
step S200: establishing a first platform feature tag according to the first medical sharing platform information;
specifically, the first medical data sharing platform is a sharing platform of the current health medical big data, the sharing platforms of all areas are closely related, the application value of the sharing platforms is effectively exerted in all application fields, and the sharing of the medical big data is completed based on all communication platforms, wherein the sharing platform is a medical data sharing exchange platform, and information sharing and exchange are directly performed through a uniform information network platform, so that health information resources are integrated. Because the shared data are of a plurality of types and the main shared attributes in each platform are different, for example, based on the information such as the communication attributes, research characteristics, data types and the like, the platform feature tags of the first medical shared platform information are established based on the attributes of the shared platform, so that intelligent tag management can be performed on each platform based on the tags, tagged feature management on the shared platform is achieved, and the subsequent shared management efficiency is improved.
Step S300: obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform;
specifically, rarity analysis is performed on medical data in the first medical data sharing platform, namely, all case information in the platform is specifically analyzed, so that rare cases are extracted based on the platform built by a computer, and rare cases are further obtained, wherein the medical data in the first medical data sharing platform comprise a plurality of medical data such as disease categories, disease characteristics, examination results, medical orders, treatment conditions, and review conditions, and the rare cases are not shared timely due to the fact that a large amount of medical data are dispersedly stored in each medical institution, and the timely sharing of the rare cases can provide case references for other medical institutions, so that the rare case resources are screened timely through further analysis of the rare cases, and the effective reference of the rare cases is improved.
Step S400: storing the first rare case and correspondingly generating a first retrieval characteristic;
specifically, in the process of storing the first rare case, each piece of information of cases, such as patient condition information, treatment information, medication information, diseased characteristic information, examination information, and the like, of the patient included in the first rare case is stored in a cloud database as a first storage unit, wherein the first cloud processor is intelligently connected with the cloud database, and the data stored in the cloud database ensures timeliness and integrity of the data in the cloud processor. Furthermore, the first retrieval feature is constructed based on the main feature of the first rare case, and is an effective feature set of the first rare case, and according to the first retrieval feature, the detailed tracking calculation of the reference of the first rare case can be guaranteed, so that the intelligent processing of data is achieved, and the technical effect of improving the response accuracy of the system is achieved.
Step S500: according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period;
specifically, the first preset period is a time period set in advance, and the setting process may be specifically set based on a total access amount of the sharing platform, for example, when the access amount in the sharing platform continuously rises in a period of time, a corresponding proportion calculation may be performed on the first preset period, where the first preset period and the total access amount of the sharing platform are in an inverse proportion relationship, and further, the first click amount and the first usage amount are a search click amount and a usage amount of the first search feature in the sharing platform, so that a relevant usage value of the first rare case can be determined, and basic data is provided for a subsequent calculation.
Step S600: constructing a first access trend prediction model according to the first cloud processor;
specifically, the first access trend prediction model is a model constructed by a basic model of a neural network model, and the first access trend prediction model is a convergence model obtained by performing supervised learning based on a plurality of effective data, wherein the specific training process is that in the first cloud processor, training data are provided to the processor by a cloud database, so that the data processing process realizes cloud computing.
Step S700: inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index;
specifically, the first visit trend prediction model is a neural network model constructed based on cloud computing, and the first click quantity and the first usage quantity are input into the first visit trend prediction model for data training, so as to obtain the first prediction index, specifically, the first prediction index can predict hot-spot trends of the first rare case, and judge the effective value referential of the first rare case, so as to facilitate the processing of relevant data by a platform constructed by a computer, wherein the first visit trend prediction model is a model established based on a neural network model, the neural network is an operation model formed by interconnection of a large number of neurons, the output of the network is expressed according to a logic strategy of a network connection mode, and the output prediction index is more accurate through the data training of the first visit trend prediction model, the technical effect of intelligently processing data is achieved.
Step S800: judging whether the first prediction index is in a preset prediction index or not;
step S900: if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms, wherein the plurality of associated medical data sharing platforms are mutually connected with the first medical data sharing platform;
specifically, the preset prediction index is an expected target data index, and when the first prediction index reaches the expected target index, the first rare case is indicated to have a certain use value, the hot spot trend of reference of the first rare case is increased, so that a plurality of associated medical data sharing platforms which are connected with the first medical data sharing platform are obtained, wherein the process of obtaining the plurality of associated medical data sharing platforms is to facilitate the sharing of the rare cases on the platforms, improve the medical value rare cases to be encountered by each medical institution for all medical institutions to call and learn, and greatly help small medical institutions to find the uncommon cases early, so as to provide help for the balanced development of medical treatment. Therefore, the development of a grading diagnosis and treatment system and remote medical work is realized, and the utilization rate of medical data resources is improved.
Step S1000: uploading the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
Specifically, all data resources related to the first rare case are uploaded on a plurality of sharing platforms according to the first uploading instruction, further, medical information of each medical institution can be fused in the data platforms, valuable medical data can be analyzed, and effective data support is provided for disease causes, disease groups, special-effect medicines and the like of various rare diseases.
Further, in the step S300 of obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform, the method further includes:
step S310: obtaining a first screening case by screening all medical data in the first medical data sharing platform;
step S320: screening the incidence of the first screened case to obtain a second screened case, wherein the incidence of the second screened case is less than or equal to a preset incidence;
step S330: obtaining the first rare case based on the second screening case;
step S340: obtaining a first assigned category of the first rare case;
step S350: establishing a first rare signature of the first rare case based on the first category to which the first rare case belongs;
step S360: adding the first rare feature to the first retrieval feature.
Specifically, the process of obtaining the first screening case is to perform first case screening on all medical data in the first medical data sharing platform, extract all rare case information with low incidence of disease from the medical data, classify and store the rare case information correspondingly, further, the process of obtaining the second screening case is to control the incidence of the case based on big data, extract the case reaching the rare expectation standard, arrange the cases in the second screening case from small to large according to the incidence of disease, further extract the related case information with the lowest incidence of disease to obtain the first rare case information, because the circulation of the rare case information is not strong enough, the rare case information obtained by the logic screening mode has extremely high effective value, and further, the category of the first rare case is taken as the additional feature of the first retrieval feature to complete specific calculation, the process of adding the first rare feature is a materialized hotspot value analysis of the domain to which the first rare case belongs.
Further, the constructing a first access trend prediction model according to the first cloud processor, in step S600 in this embodiment of the present application, further includes:
step S610: uploading all case data in the second screened case to the first cloud processor for data calculation to obtain a first average click rate and a first average usage amount;
step S620: establishing the first access trend prediction model by taking the first average click quantity and the first average usage quantity as input data;
step S630: the first visit trend prediction model is obtained by training a plurality of groups of training data to convergence, wherein each group of data in the plurality of groups of training data comprises the first average click quantity, the first average usage quantity and identification information used for identifying visit trends;
step S640: obtaining a first output of the first visit trend prediction model, wherein the first output is a result of predicting a rare case visit trend.
Specifically, the training data of the first visit trend prediction model is obtained by training after data calculation is performed in a cloud processor, the first visit trend prediction model is a model established based on a neural network model, the neural network is an operation model formed by interconnection of a large number of neurons, and the output of the network is expressed according to a logic strategy of the connection mode of the network. Further, the training process is substantially a supervised learning process, each of the plurality of sets of training data includes the first average click amount, the first average usage amount, and identification information used for identifying an access trend, the first access trend prediction model performs continuous self-correction and adjustment until an obtained output result is consistent with the identification information, the supervised learning of the set of data is finished, and the supervised learning of the next set of data is performed. When the output information of the first visit trend prediction model reaches a preset accuracy rate/reaches a convergence state, the supervised learning process is ended, and the corresponding prediction result is more accurately output through the training of the first visit trend prediction model.
Further, step S500 in the embodiment of the present application further includes:
step S510: obtaining a first case propagation path according to the first usage, wherein the first case propagation path is in a mapping relation with the first rare case;
step S520: tracking the first case propagation path according to a first information tracking instruction to obtain first tracking data;
step S530: generating a first propagation index by calculating the first trace data;
step S540: performing incremental learning on the first access trend prediction model according to the first propagation index to obtain a second access trend prediction model;
step S550: and obtaining a second prediction index according to the second access trend prediction model.
Specifically, the first case propagation path is a usage path of the first rare case, such as forwarding, sharing, downloading, and the like, and the first case propagation path is in a mapping relationship with the first rare case, that is, the first rare case is mapped to a plurality of paths in the first case propagation path respectively, so as to perform data tracking of a case with respect to the propagation path, where the first tracking data is an updated access trend prediction model obtained by performing machine learning based on the first access trend prediction model, and the second access trend prediction model is obtained by performing propagation calculation on the propagation path and analyzing and generating corresponding calculation data by using a propagation algorithm, and needs to combine with old training data of the first access trend prediction model to complete a comprehensive incremental learning result, therefore, after the first propagation index is subjected to incremental learning, the basic performance of the first access trend prediction model can be reserved, model performance can be updated, and then the second prediction index is obtained, wherein the second prediction index is prediction data obtained based on a new model, and the incremental learning based on the propagation index is achieved, so that the accurate prediction performance of the model is improved.
Further, step S540 in the embodiment of the present application further includes:
step S541: obtaining N propagation indexes which are more than or equal to a preset propagation index by screening the first propagation index;
step S542: inputting the N propagation indexes into the first visit trend prediction model to obtain a third prediction index, wherein the third prediction index is an index obtained by inputting the N propagation indexes;
step S543: performing loss analysis according to the third prediction index to obtain first loss data;
step S544: and obtaining the second visit trend prediction model according to the first loss data.
Specifically, by screening all the propagation indexes by materialization indexes and extracting the propagation indexes with effective values, thereby obtaining the N propagation indexes, further training the data set of the N propagation indexes as a new training set, since the second visit trend prediction model is based on the introduced loss function to complete the analysis of data loss and obtain a new model, wherein the first loss data is loss data representing a relative prediction of the first visit trend prediction model to the third prediction index, and incremental learning of the second visit trend prediction model is completed based on the first loss data, wherein, incremental learning means that a learning system can continuously learn new knowledge from new samples, and can save most of the previously learned knowledge, and the incremental learning is very similar to the self learning mode of human beings. The system can continuously trend predict cases as the propagation index of the first rare case is continuously updated. Therefore, through the training of the loss data, the second visit trend prediction model keeps the basic data characteristics of the first visit trend prediction model, meanwhile, the trend prediction accuracy is improved, and the technical effect of intelligent learning is achieved.
Further, embodiment S800 of the present application further includes:
step S810: if the first prediction index is not in the preset prediction index, obtaining a first return instruction;
step S820: judging whether the second prediction index is in the preset prediction index or not according to the first return instruction;
step S830: if the second prediction index is in the preset prediction index, obtaining a second uploading instruction;
step S840: and completing multi-platform data sharing of the first rare case according to the second uploading instruction.
Specifically, it is determined whether the first prediction index is in the preset prediction index, wherein, the first prediction index is an output result of the first visit trend prediction model, and when the first prediction index is not in, and then according to the return instruction, making secondary judgment on the second prediction index and the preset prediction index, wherein, the second prediction index is an output result of the second visit trend prediction model, if the second prediction index is in the preset prediction index, it indicates that the second prediction index reaches the target expected index at present, therefore, rare case sharing is carried out on the plurality of associated medical data sharing platforms which are mutually connected with the first medical data sharing platform, and the technical effect of realizing interconnection and intercommunication of rare case information by combining artificial intelligence and big data is achieved.
Further, step S1000 in the embodiment of the present application includes:
step S1010: retrieving the medical data according to the first retrieval characteristics to obtain first retrieved medical data;
step S1020: obtaining a second preset period;
step S1030: updating the first retrieval medical data according to the second preset period to obtain first updated medical data;
step S1040: and pushing the first updated medical data correspondingly as the added information of the first rare case.
Specifically, the first retrieved medical data is obtained by retrieving relevant medical data based on all features in the first retrieved features, and further, the first retrieved medical data is medical data related to the first rare case, documents and materials can be provided for researching the first rare case, so that continuous retrieval data based on big data in the second preset period is judged, the latest relevant research document materials are updated to keep the updating performance of the materials so as to obtain the first updated medical data, and further, the first updated medical data is used as relevant push information for clicking or using the first rare case, so that good service is provided for obtaining relevant medical resources, retrieval resources are saved, and the purpose of combining artificial intelligence and big data is achieved, the technical effect of improving the intelligent calculation level for processing the rare case data is achieved.
To sum up, the medical big data sharing method and system based on artificial intelligence provided by the embodiment of the application have the following technical effects:
1. the method comprises the steps of establishing a characteristic label corresponding to a platform by analyzing information in a first medical data sharing platform, conveniently performing unified analysis on all sharing platforms, performing rarity analysis on all medical data in the platform to obtain a retrieval characteristic generated by storing a first rare case, further inputting the click rate and the use amount of the first rare case into an access trend prediction model established in a cloud processor according to the retrieval characteristic to obtain a corresponding first prediction index, further judging whether the first prediction index is in a preset prediction index, if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms mutually connected with the first medical data sharing platform, and performing multi-platform uploading sharing on the medical data corresponding to the first rare case, the intelligent computing level for processing the rare case data is improved and the technical effect of interconnection and intercommunication of the rare case information is achieved through combination of artificial intelligence and big data.
2. Due to the adoption of the mode that propagation path tracking is carried out on rare cases, propagation calculation is carried out on each mapped propagation path, corresponding calculation data are generated by analyzing a propagation algorithm, and incremental learning of the first access trend prediction model is correspondingly completed based on the first propagation index and the loss function, the technical effects of improving the prediction accuracy of the model trend and intelligently processing data are achieved.
3. Due to the fact that the data storage training is conducted through the cloud processor, and the mode that the process of screening and cleaning is conducted on the propagation indexes according to certain logic rules is adopted, the incremental learning data quality and effectiveness are improved, the technical effects of intelligently analyzing data and improving the training performance of model data are achieved.
Example two
Based on the same inventive concept as the method for sharing medical big data based on artificial intelligence in the foregoing embodiment, the present invention further provides a system for sharing medical big data based on artificial intelligence, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first medical data sharing platform information;
a first constructing unit 12, where the first constructing unit 12 is configured to establish a first platform feature tag according to the first medical sharing platform information;
a second obtaining unit 13, wherein the second obtaining unit 13 is configured to obtain a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform;
a first generating unit 14, wherein the first generating unit 14 is configured to store the first rare case and correspondingly generate a first retrieval feature;
a third obtaining unit 15, where the third obtaining unit 15 is configured to obtain a first click amount and a first usage amount in a first preset period according to the first retrieval feature;
a second constructing unit 16, where the second constructing unit 16 is configured to construct a first access trend prediction model according to the first cloud processor;
a fourth obtaining unit 17, where the fourth obtaining unit 17 is configured to input the first click amount and the first usage amount into the first visit tendency prediction model to obtain a first prediction index;
a first judging unit 18, where the first judging unit 18 is configured to judge whether the first prediction index is in a preset prediction index;
a fifth obtaining unit 19, configured to obtain a plurality of associated medical data sharing platforms if the first prediction index is in the preset prediction index, where the plurality of associated medical data sharing platforms are platforms interconnected with the first medical data sharing platform;
a first uploading unit 20, wherein the first uploading unit 20 is configured to upload the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
Further, the system further comprises:
a sixth obtaining unit configured to obtain a first screened case by performing case screening on all medical data in the first medical data sharing platform;
a seventh obtaining unit, configured to obtain a second screening case by screening the incidence of the first screening case, where the second screening case is a case with an incidence of less than or equal to a preset incidence;
an eighth obtaining unit for obtaining the first rare case based on the second screening case;
a ninth obtaining unit for obtaining a first belonging category of the first rare case;
a tenth obtaining unit for establishing a first rare feature of the first rare case according to the first belonging category;
a first adding unit for adding the first rare feature to the first retrieval feature.
Further, the system further comprises:
an eleventh obtaining unit, configured to upload all case data in the second screened case to the first cloud processor for data calculation, so as to obtain a first average click rate and a first average usage amount;
a third construction unit, configured to construct the first access trend prediction model using the first average click rate and the first average usage amount as input data;
a twelfth obtaining unit, configured to train the first visit trend prediction model to convergence through multiple sets of training data, where each set of data in the multiple sets of training data includes the first average click amount, the first average usage amount, and identification information used to identify a visit trend;
a thirteenth obtaining unit configured to obtain a first output result of the first visit trend prediction model, wherein the first output result is a result of predicting a rare case visit trend.
Further, the system further comprises:
a fourteenth obtaining unit, configured to obtain a first case propagation path according to the first usage, where the first case propagation path is in a mapping relationship with the first rare case;
a fifteenth obtaining unit, configured to track the first case propagation path according to a first information tracking instruction, and obtain first tracking data;
a second generation unit configured to generate a first propagation index by calculating the first trace data;
a sixteenth obtaining unit, configured to perform incremental learning on the first access trend prediction model according to the first propagation index, and obtain a second access trend prediction model;
a seventeenth obtaining unit, configured to obtain a second prediction index according to the second visit trend prediction model.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain N propagation indexes that are greater than or equal to a preset propagation index by screening the first propagation index;
a nineteenth obtaining unit, configured to input the N propagation indexes into the first visit tendency prediction model, and obtain a third prediction index, where the third prediction index is an index obtained by inputting N propagation indexes;
a twentieth obtaining unit, configured to perform loss analysis according to the third prediction index, and obtain first loss data;
further, the system further comprises:
a twenty-first obtaining unit, configured to obtain a first return instruction if the first prediction index is not in the preset prediction index;
a second determining unit, configured to determine whether the second prediction index is in the preset prediction index according to the first return instruction;
a twenty-second obtaining unit, configured to obtain a second upload instruction if the second prediction index is in the preset prediction index;
and the second uploading unit is used for completing multi-platform data sharing of the first rare case according to the second uploading instruction.
Further, the system further comprises:
a twenty-third obtaining unit, configured to retrieve the medical data according to the first retrieval feature, and obtain first retrieved medical data;
a twenty-fourth obtaining unit, configured to obtain a second preset period;
a twenty-fifth obtaining unit, configured to update the first retrieved medical data according to the second preset period, and obtain first updated medical data;
a first pushing unit for pushing the first updated medical data as the addition information of the first rare case correspondingly.
Various changes and specific examples of the artificial intelligence based medical big data sharing method in the first embodiment of fig. 1 are also applicable to the artificial intelligence based medical big data sharing system in the present embodiment, and through the foregoing detailed description of the artificial intelligence based medical big data sharing method, those skilled in the art can clearly know the implementation method of the artificial intelligence based medical big data sharing system in the present embodiment, so for the brevity of the description, detailed descriptions are omitted here.
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the artificial intelligence based medical big data sharing method in the foregoing embodiment, the invention further provides an artificial intelligence based medical big data sharing system, on which a computer program is stored, and when the program is executed by a processor, the steps of any one of the methods of the artificial intelligence based medical big data sharing method are realized.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides an artificial intelligence based medical big data sharing method, which is applied to an artificial intelligence based medical big data sharing system, wherein the system is in communication connection with a first cloud processor, and the method comprises the following steps: obtaining first medical data sharing platform information; establishing a first platform feature tag according to the first medical sharing platform information; obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform; storing the first rare case and correspondingly generating a first retrieval characteristic; according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period; constructing a first access trend prediction model according to the first cloud processor; inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index; judging whether the first prediction index is in a preset prediction index or not; if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms, wherein the plurality of associated medical data sharing platforms are mutually connected with the first medical data sharing platform; uploading the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction. The technical problem that in the prior art, due to the particularity of rare cases, corresponding medical data sharing methods are not intelligent enough, and isolated circulation of rare cases is caused is solved, the intelligent calculation level for processing rare case data is improved through the combination of artificial intelligence and big data, and the technical effect of interconnection and intercommunication of rare case information is achieved.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. An artificial intelligence based medical big data sharing method is applied to an artificial intelligence based medical big data sharing system, the system is connected with a first cloud processor in a communication mode, and the method comprises the following steps:
obtaining first medical data sharing platform information;
establishing a first platform feature tag according to the first medical sharing platform information;
obtaining a first rare case by performing rarity analysis on the medical data in the first medical data sharing platform;
storing the first rare case and correspondingly generating a first retrieval characteristic, wherein the first retrieval characteristic is constructed based on the main characteristic of the first rare case and is an effective characteristic set of the first rare case;
according to the first retrieval characteristic, obtaining a first click quantity and a first usage quantity in a first preset period;
constructing a first access trend prediction model according to the first cloud processor, wherein the first access trend prediction model is a model constructed by a basic model of a neural network model, the first access trend prediction model is a convergence model obtained by supervised learning based on a plurality of effective data, and the first access trend prediction model is specifically trained by providing training data from a cloud database to the first cloud processor, so that the data processing process realizes cloud computing;
inputting the first click quantity and the first usage quantity into the first visit trend prediction model to obtain a first prediction index, wherein the first prediction index can predict the hot spot trend of the first rare case and judge the effective value referential of the first rare case;
judging whether the first prediction index is in a preset prediction index or not;
if the first prediction index is in the preset prediction index, obtaining a plurality of associated medical data sharing platforms, wherein the plurality of associated medical data sharing platforms are mutually connected with the first medical data sharing platform;
uploading the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
2. The method of claim 1, the obtaining a first rare case by performing a rarity analysis on medical data in the first medical data sharing platform, the method further comprising:
obtaining a first screening case by screening all medical data in the first medical data sharing platform;
screening the incidence of the first screened case to obtain a second screened case, wherein the incidence of the second screened case is less than or equal to a preset incidence;
obtaining the first rare case based on the second screening case;
obtaining a first assigned category of the first rare case;
establishing a first rare signature of the first rare case based on the first category to which the first rare case belongs;
adding the first rare feature to the first retrieval feature.
3. The method of claim 2, the building a first access trend prediction model according to the first cloud processor, the method further comprising:
uploading all case data in the second screened case to the first cloud processor for data calculation to obtain a first average click rate and a first average usage amount;
establishing the first access trend prediction model by taking the first average click quantity and the first average usage quantity as input data;
the first visit trend prediction model is obtained by training a plurality of groups of training data to convergence, wherein each group of data in the plurality of groups of training data comprises the first average click quantity, the first average usage quantity and identification information used for identifying visit trends;
obtaining a first output of the first visit trend prediction model, wherein the first output is a result of predicting a rare case visit trend.
4. The method of claim 1, further comprising:
obtaining a first case propagation path according to the first usage, wherein the first case propagation path is in a mapping relation with the first rare case;
tracking the first case propagation path according to a first information tracking instruction to obtain first tracking data;
generating a first propagation index by calculating the first trace data;
performing incremental learning on the first access trend prediction model according to the first propagation index to obtain a second access trend prediction model;
and obtaining a second prediction index according to the second access trend prediction model.
5. The method of claim 4, further comprising:
obtaining N propagation indexes which are more than or equal to a preset propagation index by screening the first propagation index;
inputting the N propagation indexes into the first visit trend prediction model to obtain a third prediction index, wherein the third prediction index is an index obtained by inputting the N propagation indexes;
performing loss analysis according to the third prediction index to obtain first loss data;
and obtaining the second visit trend prediction model according to the first loss data.
6. The method of claim 4, the determining whether the first prediction index is within a preset prediction index, the method further comprising:
if the first prediction index is not in the preset prediction index, obtaining a first return instruction;
judging whether the second prediction index is in the preset prediction index or not according to the first return instruction;
if the second prediction index is in the preset prediction index, obtaining a second uploading instruction;
and completing multi-platform data sharing of the first rare case according to the second uploading instruction.
7. The method of claim 1, further comprising:
retrieving the medical data according to the first retrieval characteristics to obtain first retrieved medical data;
obtaining a second preset period;
updating the first retrieval medical data according to the second preset period to obtain first updated medical data;
and pushing the first updated medical data correspondingly as the added information of the first rare case.
8. An artificial intelligence based medical big data sharing system, wherein the system comprises:
a first obtaining unit for obtaining first medical data sharing platform information;
the first construction unit is used for establishing a first platform feature tag according to the first medical sharing platform information;
a second obtaining unit configured to obtain a first rare case by performing a rarity analysis on the medical data in the first medical data sharing platform;
a first generation unit, configured to store the first rare case and correspondingly generate a first retrieval feature, where the first retrieval feature is constructed based on main features of the first rare case and is a valid feature set of the first rare case;
a third obtaining unit, configured to obtain a first click amount and a first usage amount in a first preset period according to the first retrieval feature;
the second construction unit is used for constructing a first access trend prediction model according to the first cloud processor, wherein the first access trend prediction model is a model constructed by a basic model of a neural network model, the first access trend prediction model is a convergence model obtained by supervised learning based on a plurality of effective data, and the specific training process of the first access trend prediction model is realized by providing training data for the first cloud processor from a cloud database, so that the data processing process realizes cloud computing;
a fourth obtaining unit, configured to input the first click volume and the first usage volume into the first visit trend prediction model to obtain a first prediction index, where the first prediction index is capable of performing hot-spot trend prediction on the first rare case and determining an effective value referential property of the first rare case;
the first judgment unit is used for judging whether the first prediction index is in a preset prediction index or not;
a fifth obtaining unit, configured to obtain a plurality of associated medical data sharing platforms if the first prediction index is in the preset prediction index, where the plurality of associated medical data sharing platforms are platforms that are connected to the first medical data sharing platform;
a first uploading unit, configured to upload the first rare case to the plurality of associated medical data sharing platforms according to a first uploading instruction.
9. An artificial intelligence based medical big data sharing system, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-7 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111223736.1A CN113674869B (en) | 2021-10-21 | 2021-10-21 | Medical big data sharing method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111223736.1A CN113674869B (en) | 2021-10-21 | 2021-10-21 | Medical big data sharing method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113674869A CN113674869A (en) | 2021-11-19 |
| CN113674869B true CN113674869B (en) | 2021-12-24 |
Family
ID=78550703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111223736.1A Active CN113674869B (en) | 2021-10-21 | 2021-10-21 | Medical big data sharing method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674869B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110838370A (en) * | 2019-12-03 | 2020-02-25 | 中国医学科学院北京协和医院 | Rare disease registration system |
| CN111402973B (en) * | 2020-03-02 | 2023-07-07 | 平安科技（深圳）有限公司 | Information matching analysis method, device, computer system and readable storage medium |
| CN112071385A (en) * | 2020-09-23 | 2020-12-11 | 广州瀚信通信科技股份有限公司 | Rare disease auxiliary analysis method and device based on artificial intelligence and storage medium |
| CN112735555B (en) * | 2021-01-20 | 2022-09-27 | 山东第一医科大学附属省立医院(山东省立医院) | Rare disease data acquisition and reporting method and system |
-
2021
- 2021-10-21 CN CN202111223736.1A patent/CN113674869B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113674869A (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112784092B (en) | Cross-modal image text retrieval method of hybrid fusion model | |
| Montesinos-López et al. | Multi-environment genomic prediction of plant traits using deep learners with dense architecture | |
| Li et al. | Calibrating cellular automata based on landscape metrics by using genetic algorithms | |
| Liu et al. | Simulating land-use dynamics under planning policies by integrating artificial immune systems with cellular automata | |
| Mugera | Measuring technical efficiency of dairy farms with imprecise data: a fuzzy data envelopment analysis approach | |
| Whitsed et al. | A hybrid genetic algorithm with local optimiser improves calibration of a vegetation change cellular automata model | |
| CN112580902B (en) | Object data processing method and device, computer equipment and storage medium | |
| Yang et al. | An intelligent method to discover transition rules for cellular automata using bee colony optimisation | |
| CN112561031A (en) | Model searching method and device based on artificial intelligence and electronic equipment | |
| CN106164896A (en) | For finding multidimensional recursive learning process and the system of complicated two analogues or many analogues relation | |
| Alexandridis et al. | Real Estate valuation and forecasting in non-homogeneous markets: A case study in Greece during the financial crisis | |
| Leusin et al. | Patenting patterns in Artificial Intelligence: Identifying national and international breeding grounds | |
| Turgut et al. | A framework proposal for machine learning-driven agent-based models through a case study analysis | |
| Mittas et al. | Integrating non-parametric models with linear components for producing software cost estimations | |
| Liao et al. | Reimagining multi-criterion decision making by data-driven methods based on machine learning: A literature review | |
| Jie | RETRACTED ARTICLE: Precision and intelligent agricultural decision support system based on big data analysis | |
| Narmatha et al. | Ovarian cysts classification using novel deep reinforcement learning with Harris Hawks Optimization method | |
| Jia et al. | A privacy-sensitive service selection method based on artificial fish swarm algorithm in the internet of things | |
| CN113674869B (en) | Medical big data sharing method and system based on artificial intelligence | |
| CN114900435B (en) | Connection relation prediction method and related equipment | |
| CN115631008B (en) | Commodity recommendation method, device, equipment and medium | |
| Zou et al. | Uncertain Weibull regression model with imprecise observations | |
| Liang et al. | A statistical analysis model of big data for precise poverty alleviation based on multisource data fusion | |
| Reddy et al. | A Beginner's Guide to Federated Learning | |
| Bee Hua | The state of applications of quantitative analysis techniques to construction economics and management (1983 to 2006) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |