CN114911620A - Medical scientific research data subscription method and system - Google Patents
Medical scientific research data subscription method and system Download PDFInfo
- Publication number
- CN114911620A CN114911620A CN202210529243.9A CN202210529243A CN114911620A CN 114911620 A CN114911620 A CN 114911620A CN 202210529243 A CN202210529243 A CN 202210529243A CN 114911620 A CN114911620 A CN 114911620A
- Authority
- CN
- China
- Prior art keywords
- scientific research
- research data
- data
- task
- server
- 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.)
- Pending
Links
- 238000011160 research Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036316 preload Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of hospital information data systems, and particularly relates to a medical scientific research data subscription method and system. The method of the invention comprises the following steps: step 1, generating a cache scientific research data task, and estimating the time required for completing the cache scientific research data task; step 2, predicting the idle time period of the server by using a prediction model; the prediction model is obtained by training by using historical operation parameter data of the server as training data; and 3, comparing the estimated time length obtained in the step 1 with the idle time period obtained in the step 2, and determining the execution time of the cache scientific research data task. The invention can effectively avoid the scientific research data subscription task from increasing the burden on the server in the peak period of the operation of the server, increases the overall operation efficiency of the hospital server, and has good application prospect.
Description
Technical Field
The invention belongs to the technical field of hospital information data systems, and particularly relates to a medical scientific research data subscription method and system.
Background
The hospital information data system is an important component of the construction of modern hospitals. The hospital information data system plays an important role in treatment and diagnosis of patients, and is used for storing information of medical record information, examination results, medication and treatment information and the like of the patients. Together, this information constitutes a large amount of medical data.
The medical data can record the disease development of the patient and can be used as scientific research data. When scientific research personnel carry out scientific research, a large amount of existing medical data need to be subscribed according to different subject requirements, and the development trend of the data is researched by reading the data and searching rules and characteristics. The subscription of medical data from hospital information databases is a basic requirement for researchers to conduct research in the field.
However, due to the complex setting of departments, the diversity of examination items, and the like, the hospital information data system is composed of a large number of subsystems including HIS, CIS, LIS, EMR, PACS, RIS, CAD, and the like. Furthermore, since medical data can accumulate over time, the amount of data stored in these systems is often very large. And the data used for scientific research generally has larger data information and time span. Therefore, the problem that data query is slow and efficiency is low exists in the process of subscribing the scientific research data, so that the task of subscribing the scientific research data often occupies a large amount of server resources, and normal execution of other tasks of the server is influenced.
Because the scientific research data subscription task is less urgent than other tasks of the hospital, if the scientific research data subscription can be carried out in the idle time of the server, the overall operation efficiency of the hospital can be more effectively improved. In order to efficiently utilize the idle time of the server and solve the problem that non-emergency tasks occupy server resources, a method and a system for providing advertisements by using the idle time of a channel by CN99120627.4 propose a technical scheme for sending the advertisements by using the idle time of the server. However, the advertisement sending is a task which can be completed quickly, and the time for subscribing the scientific research data is long, so that the task of subscribing the scientific research data is difficult to insert into the idle time of the server flexibly like the advertisement sending. Therefore, how to coordinate the subscription task of the scientific research data in the hospital information data system and other tasks of the server is still a problem to be solved urgently in the field.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a method and a system for subscribing medical scientific research data, aiming at matching a task of subscribing the scientific research data with the idle time of a server, realizing the task of subscribing the scientific research data in the idle time of service and avoiding the influence of the subscribed scientific research data with too long time on other tasks of the server.
A medical scientific research data subscription method comprises the following steps:
step 1, generating a cache scientific research data task, and estimating the time required for completing the cache scientific research data task;
step 2, predicting the idle time period of the server by using a prediction model; the prediction model is obtained by training by using historical operation parameter data of the server as training data;
and 3, comparing the estimated time length obtained in the step 1 with the idle time period obtained in the step 2, and determining the execution time of the cache scientific research data task.
Preferably, in step 1, the inputting information input when the task of generating the cached scientific research data is input includes: scientific research data content, scientific research data coverage, scientific research data types and time limit for completing loading.
Preferably, in step 3, the estimated duration of step 1 is compared with the idle time period obtained in step 2 before the time limit for completing the loading.
Preferably, in step 2, the historical operating parameter data is selected from one or a combination of two or more of a CPU usage rate, a memory usage rate, a network connection number, and a network card traffic.
Preferably, in step 2, the historical operating parameter data is preprocessed before being used, and the preprocessing includes one or a combination of two or more of noise reduction, calculation of a mean value of the historical operating parameter data, and calculation of a variance of the historical operating parameter data.
Preferably, in step 2, the prediction model is selected from SVM, MLP, XGBOOST or LGBM.
Preferably, in step 2, the prediction model used is trained again after a time period has elapsed.
Preferably, the one time period is one month, two months or one quarter.
The invention also provides a system for the medical scientific research data subscription method, which comprises the following steps:
the input module is used for inputting and generating a cache scientific research data task;
the time length calculation module is used for predicting the time length required for completing the task of caching scientific research data;
the idle time period calculation module is used for predicting the idle time period of the server by using the prediction model;
and the comparison module is used for comparing the duration with the idle time period and determining the execution time of the cache scientific research data task.
The present invention also provides a computer-readable storage medium having stored thereon a computer program for implementing the above-described medical research data subscription method.
In the traditional server resource allocation method, the scientific research data subscription task is started as long as the server is idle, however, the scientific research data subscription task consumes a long time, and other tasks are frequently intervened in the scientific research data subscription task, and the scientific research data subscription task is still not completed. This can lead to problems with other tasks being slow to perform. According to the method, the idle time period of the server of the hospital is predicted through the prediction model, the idle time period is compared with the time required by the scientific research data subscription task, and the scientific research data subscription task consuming longer time is arranged in the idle time period with enough length to preload the scientific research data. By coordinating the execution time of the scientific research data subscription tasks according to the method, the crowding of the scientific research data subscription tasks on server resources can be effectively avoided, the speed of other tasks is increased, and the operation efficiency of the server for integrally executing various tasks is improved.
Obviously, many modifications, substitutions, and variations are possible in light of the above teachings of the invention, without departing from the basic technical spirit of the invention, as defined by the following claims.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. All the technologies realized based on the above contents of the present invention belong to the scope of the present invention.
Drawings
Fig. 1 is a schematic structural diagram of a hardware platform according to embodiment 1;
fig. 2 is a schematic flowchart of a scientific research data subscription method in embodiment 1.
Detailed Description
It should be noted that, in the embodiment, the algorithm of the steps of data acquisition, transmission, storage, processing, etc. which are not specifically described, as well as the hardware structure, circuit connection, etc. which are not specifically described, can be implemented by the contents disclosed in the prior art.
Example 1
The hardware platform used in this embodiment is shown in fig. 1, and includes: the system comprises a data server 10 and a client 20, wherein the data server 10 is arranged in a hospital and used for storing medical data in the hospital; and the user terminal 20, the terminals of scientific research personnel and doctors, is used for linking the server and calling and accessing the medical data in the data server.
The embodiment is implemented on the hardware platform, and the following system for coordinating execution time of scientific research data subscription tasks is constructed:
the input module is used for inputting and generating a cache scientific research data task;
the time length calculation module is used for predicting the time length required for completing the task of caching scientific research data;
the idle time period calculation module is used for predicting the idle time period of the server by using the prediction model;
and the comparison module is used for comparing the duration with the idle time period and determining the execution time of the cache scientific research data task.
Through the system, the scientific research data subscription method of the embodiment is shown in fig. 2, and includes the following steps:
step 1, generating a cache scientific research data task (namely a scientific research data subscription task), and estimating the time required for completing the cache scientific research data task;
the input information includes: scientific research data content, scientific research data coverage, scientific research data types, time limit for completing loading and the like. For example: the scientific research data needing to be cached can be the record, distribution and morbidity of all medical records of a certain disease in the last year; or a chest C image taken by the imaging department in approximately one month; the time to complete the load may be 9 am each day.
Step 2, predicting the idle time period of the server by using a prediction model; the prediction model is obtained by training by using historical operation parameter data of the server as training data.
The historical operation parameter data is selected from one or the combination of two or more of CPU utilization rate, memory utilization rate, network connection number and network card flow. The historical operating parameter data is preprocessed before being used, and the preprocessing comprises one or the combination of two or more of noise reduction, calculation of the mean value of the historical operating parameter data and calculation of the variance of the historical operating parameter data. The calculated mean and variance can be used as features, and the number of features used by the prediction model is increased.
The time span for the modeled historical operating parameter data is one or two months.
The prediction model may be selected from SVM, MLP, XGBOST or LGBM. The present embodiment uses the same or recent samples for training, and the sample size is small, so the SVM algorithm is preferable.
Considering that the idle time of the hospital server is influenced by more factors, the used prediction model is trained again after each time period. For example: in month 1, the server is idle in the time period of (10: 00-10: 30), but for some reason, the server is gradually busy in the later months in the time period of (10: 00-10: 30), and at the moment, the prediction result of the model trained by the historical parameter data of month 1 may not accord with the running state of the actual server. Therefore, the model can be retrained through the latest one-month server operation parameter data, the retrained prediction model is used for prediction, and the prediction result of the prediction model is ensured to be consistent with the actual operation condition of the server. In other embodiments, when the model is trained, the model training can be performed again by using the data of the operation parameters of the current historical server.
And 3, before the time limit of loading is finished, comparing the time length estimated in the step 1 with the idle time period obtained in the step 2, and determining the execution time of the scientific research data caching task.
According to the characteristics of hospital work, the prediction result of the idle time period of one example is as follows: a (10: 00-10: 30), B (12: 00-13: 00), C (15: 00-15: 30), D (18: 00-19: 00) and E (21: 00-08: 00), and selecting proper idle time periods to perform caching tasks in the four time periods every day for generating caching scientific research data tasks. Such as: and if the time required for completing the scientific research data caching task is 18:00 and the time required for completing the scientific research data caching task is 45 minutes, starting to execute the caching task in the time period B.
The embodiment can show that the invention provides a novel method for coordinating the execution time of the scientific research data subscription task, and the method can effectively avoid the burden of the scientific research data subscription task on the server in the peak period of the operation of the server by accurately matching the time required by the scientific research data subscription task with the idle time period of the server, thereby increasing the overall operation efficiency of the hospital server and having good application prospect.
Claims (10)
1. A medical scientific research data subscription method is characterized by comprising the following steps:
step 1, generating a cache scientific research data task, and estimating the time required for completing the cache scientific research data task;
step 2, predicting the idle time period of the server by using a prediction model; the prediction model is obtained by training by using historical operation parameter data of the server as training data;
and 3, comparing the estimated time length obtained in the step 1 with the idle time period obtained in the step 2, and determining the execution time of the cache scientific research data task.
2. The medical scientific research data subscription method according to claim 1, characterized in that: in step 1, inputting information input when generating a task of caching scientific research data comprises: scientific research data content, scientific research data coverage, scientific research data types and time limit for completing loading.
3. The medical scientific research data subscription method according to claim 2, characterized in that: and 3, comparing the estimated time length obtained in the step 1 with the idle time period obtained in the step 2 before the time limit for completing loading.
4. The medical scientific research data subscription method according to claim 1, characterized in that: in step 2, the historical operation parameter data is selected from one or a combination of two or more of a CPU utilization rate, a memory utilization rate, a network connection number and a network card flow rate.
5. The medical scientific research data subscription method according to claim 4, wherein: in step 2, the historical operating parameter data is preprocessed before being used, and the preprocessing comprises one or a combination of two or more of noise reduction, calculation of the mean value of the historical operating parameter data and calculation of the variance of the historical operating parameter data.
6. The medical research data subscription method according to claim 1, wherein: in step 2, the prediction model is selected from SVM, MLP, XGBOST or LGBM.
7. The medical scientific research data subscription method according to claim 1, characterized in that: in step 2, the used prediction model is subjected to model training again after a time period.
8. The medical scientific research data subscription method according to claim 7, wherein: the one time period is one month, two months or one quarter.
9. A system for implementing the medical scientific data subscription method according to any one of claims 1 to 8, comprising:
the input module is used for inputting and generating a cache scientific research data task;
the time length calculation module is used for predicting the time length required for completing the task of caching scientific research data;
the idle time period calculation module is used for predicting the idle time period of the server by using the prediction model;
and the comparison module is used for comparing the duration with the idle time period and determining the execution time of the cache scientific research data task.
10. A computer-readable storage medium characterized by: stored thereon a computer program for implementing a method for subscribing to medical scientific data according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210529243.9A CN114911620A (en) | 2022-05-16 | 2022-05-16 | Medical scientific research data subscription method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210529243.9A CN114911620A (en) | 2022-05-16 | 2022-05-16 | Medical scientific research data subscription method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114911620A true CN114911620A (en) | 2022-08-16 |
Family
ID=82767123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210529243.9A Pending CN114911620A (en) | 2022-05-16 | 2022-05-16 | Medical scientific research data subscription method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114911620A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105955873A (en) * | 2016-04-27 | 2016-09-21 | 乐视控股(北京)有限公司 | Task processing method and apparatus |
CN109614231A (en) * | 2018-12-04 | 2019-04-12 | 广东亿迅科技有限公司 | Idle server resource discovery method, device, computer equipment and storage medium |
-
2022
- 2022-05-16 CN CN202210529243.9A patent/CN114911620A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105955873A (en) * | 2016-04-27 | 2016-09-21 | 乐视控股(北京)有限公司 | Task processing method and apparatus |
CN109614231A (en) * | 2018-12-04 | 2019-04-12 | 广东亿迅科技有限公司 | Idle server resource discovery method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111045814B (en) | Resource scheduling method and terminal equipment | |
US20080301399A1 (en) | Prefetching apparatus, prefetching method and prefetching program product | |
WO2021159638A1 (en) | Method, apparatus and device for scheduling cluster queue resources, and storage medium | |
US9176805B2 (en) | Memory dump optimization in a system | |
JP7244711B2 (en) | clinical risk model | |
CN113792920B (en) | Single-consulting-room-oriented hospital consultation sequence optimization method and device | |
KR20090122103A (en) | Method and apparatus for maintaining and processing provenance data in data stream processing system | |
CN109840141B (en) | Thread control method and device based on cloud monitoring, electronic equipment and storage medium | |
CN112100034A (en) | Service monitoring method and device | |
CN113835874A (en) | Deep learning service scheduling method, system, terminal and storage medium | |
CN116302898A (en) | Task management method and device, storage medium and electronic equipment | |
CN109446225A (en) | Data cache method, device, computer equipment and storage medium | |
CN111951939A (en) | Medical resource optimal allocation method, system, equipment and storage medium | |
CN111028931B (en) | Medical data processing method and device, electronic equipment and storage medium | |
CN113360941A (en) | Medical data processing method and device based on digital twins and computer equipment | |
CN110347546B (en) | Dynamic adjustment method, device, medium and electronic equipment for monitoring task | |
CN114911620A (en) | Medical scientific research data subscription method and system | |
CN116844725A (en) | Health information generation method, device, medium and equipment | |
EP3268877A1 (en) | A data processing system and the related method for displaying medical images | |
CN113296907B (en) | Task scheduling processing method, system and computer equipment based on clusters | |
CN114201369A (en) | Server cluster management method and device, electronic equipment and storage medium | |
EP3032424A1 (en) | Registering an event | |
Liu et al. | Multivariate analysis of physicians’ practicing behaviors in an urgent care telemedicine intervention | |
CN118136208A (en) | Medical behavior event processing method, system, equipment and storage medium | |
CN116991563B (en) | Queue generating method and device supporting rapid sandbox construction |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220816 |
|
RJ01 | Rejection of invention patent application after publication |