CN108550380A - A kind of drug safety information monitoring method and device based on public network - Google Patents
A kind of drug safety information monitoring method and device based on public network Download PDFInfo
- Publication number
- CN108550380A CN108550380A CN201810326260.6A CN201810326260A CN108550380A CN 108550380 A CN108550380 A CN 108550380A CN 201810326260 A CN201810326260 A CN 201810326260A CN 108550380 A CN108550380 A CN 108550380A
- Authority
- CN
- China
- Prior art keywords
- public network
- adverse events
- information
- target
- domain name
- 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
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Toxicology (AREA)
- Pharmacology & Pharmacy (AREA)
- Biomedical Technology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application discloses a kind of drug safety information monitoring method based on public network, rule can be crawled according to data, automatically the adverse events information of target medicine is obtained automatically from target public network, acquired adverse events information can reflect that patient uses the safety of target medicine in public medium.Then, classification and the statistical analysis of system organ are carried out to the adverse events information according to keyword.In this way, medicine enterprise can recognize that after using target medicine, the quantity etc. of which adverse events and various adverse events has occurred in patient in public network media according to classification results.Compared with traditional approach, the embodiment of the present application can automatically be monitored the drug safety information of target public network, the waste for avoiding manpower, improves treatment effeciency, realizes and is effectively monitored to the drug safety information that the drug of production generates on public network.
Description
Technical field
This application involves artificial intelligence fields, more particularly to a kind of drug safety information monitoring side based on public network
Method and device.
Background technology
Presently, there are medical resource anxiety, the short problem of patient's Waiting time, patient can neither be after using drug for China
The adverse events of generation are reported to medical worker, are not also formed and are reported adverse events to the custom looked forward to medicine.With network
Development and universal, more and more patients progress medication exchange on public network after using drug, to being sent out after using drug
Raw adverse events are putd question to or are discussed on public network, which for example may include mhkc, forum, blog
Deng, thus will produce a large amount of patient medication information in public network.
Medicine enterprise is often desirable to obtain patient using the adverse events occurred after drug, with by being analyzed to adverse events
The safety of the drug is solved, to realize that the drug safety information looked forward to the medicine is monitored.Traditional monitoring mode, needs medicine
Enterprise personnel, which take artificial mode to be inquired one by one on public network and obtain patient, uses the adverse events occurred after certain drug
Then information is analyzed the adverse events information got, is counted one by one, to understand the safety of the drug, realize
Monitoring to drug security information on public network.
Since public network data include many kinds, and various drug peaces may be issued on each public network
Full information, therefore, the drug safety information source on public network is different, and information content is excessive, not by arranging well, adopts
Mode manually is difficult to be inquired a large amount of drug safety information on public network, arranged, and needing to waste a large amount of people
Power, it is difficult to which the drug safety information generated on public network is effectively monitored.
Invention content
In order to solve the above-mentioned technical problem, this application provides a kind of drug safety information monitoring side based on public network
Method and device automatically get the adverse events information of target medicine from the bulk information of target public network, and to it
Automatically the processing such as classify is carried out, avoids the waste of manpower, improve treatment effeciency, realizes to the drug of production in public network
The drug safety information generated on network is effectively monitored.
The embodiment of the present application discloses following technical solution:
In a first aspect, the embodiment of the present application provides a kind of drug safety information monitoring method based on public network, institute
The method of stating includes:
Rule is crawled according to data, the adverse events information of target medicine is obtained from target public network;
Event category is carried out to the adverse events information according to keyword and obtains classification results, different keywords corresponds to
Different event types.
Optionally, the method further includes:
To the adverse events information carry out domain name identification, obtain include the public network of the adverse events information domain
Name;
The target public network is redefined according to domain name.
Optionally, described that the target public network is redefined according to domain name, including:
The corresponding public network of domain name is determined as target public network;
Or, described redefine the target public network according to domain name, including:
Count the number that domain name occurs;
The corresponding public network of domain name that the number is more than to predetermined threshold value is determined as target public network.
Optionally, described to crawl rule according to data, the adverse events letter of target medicine is obtained from target public network
Breath, including:
Rule is crawled according to data, is obtained and the relevant text to be determined of target medicine from the target public network;
Extracted from the text to be determined according to the keyword include the adverse events information text;
The adverse events information is obtained from the text.
Optionally, described to obtain the adverse events information from the text, including:
The keyword is extracted from the text;
The adverse events information is determined according to the context of the keyword.
Optionally, it is described according to keyword to the adverse events information carry out event category obtain classification results it
Afterwards, the method further includes:
According to the classification results, the adverse events information is counted, generates summary report.
Second aspect, the embodiment of the present application provide a kind of drug safety information monitoring device based on public network, institute
It includes acquiring unit and taxon to state device:
The acquiring unit obtains the bad of target medicine for crawling rule according to data from target public network
Event information;
The taxon obtains classification knot for carrying out event category to the adverse events information according to keyword
Fruit, different keywords correspond to different event types.
Optionally, described device further includes recognition unit and determination unit:
The recognition unit obtains including the adverse events for carrying out domain name identification to the adverse events information
The domain name of the public network of information;
The determination unit, for redefining the target public network according to domain name.
Optionally, the determination unit is used to the corresponding public network of domain name being determined as target public network;
Or, the determination unit is used to count the number of domain name appearance;The number is more than to the domain of predetermined threshold value
The corresponding public network of name is determined as target public network.
Optionally, the acquiring unit is used for:Rule is crawled according to data, acquisition and mesh from the target public network
Mark the relevant text to be determined of drug;It includes the adverse events letter to be extracted from the text to be determined according to the keyword
The text of breath;The adverse events information is obtained from the text.
Optionally, the acquiring unit is used for:The keyword is extracted from the text;According to the upper of the keyword
Hereafter determine the adverse events information.
Optionally, described device further includes generation unit:
The generation unit generates abstract for according to the classification results, being counted to the adverse events information
Report.
The embodiment of the present application has the following advantages it can be seen from above-mentioned technical proposal:
When the drug safety information to public network is monitored, rule can be crawled according to data, automatically from target
The adverse events information of target medicine is obtained in public network, which can reflect that patient uses after target medicine
Which adverse events has occurred, to reflect the safety of the target medicine.Then, the adverse events are believed according to keyword
Breath is classified, and obtains classification results, wherein different keywords corresponds to different event types.In this way, medicine enterprise can root
Recognize that after using target medicine, the quantity of which adverse events and various adverse events has occurred in patient according to classification results
Deng.Compared with traditional approach, the embodiment of the present application automatically can get target from the bulk information of target public network
The adverse events information of drug, and the processing such as classify is carried out automatically to it, the waste of manpower is avoided, treatment effeciency is improved,
It realizes and the drug safety information that the drug of production generates on public network is effectively monitored.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application without having to pay creative labor, may be used also for those of ordinary skill in the art
With obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of drug safety information monitoring system Organization Chart based on public network provided by the embodiments of the present application;
Fig. 2 is a kind of flow of the drug safety information monitoring method based on public network provided by the embodiments of the present application
Figure;
Fig. 3 is drug safety inter-area traffic interarea structure chart provided by the embodiments of the present application;
Fig. 4 is a kind of structural frames of the drug safety information monitoring device based on public network provided by the embodiments of the present application
Figure.
Specific implementation mode
Below in conjunction with the accompanying drawings, embodiments herein is described.
Applicant it has been investigated that, in traditional drug safety information monitoring method, can only be existed by artificial mode
It browses, inquire one by one on public network, to obtain patient using the adverse events information occurred after certain drug, then to getting
Adverse events information analyzed, counted one by one, to understand the safety of the drug, drug on public network is pacified in realization
The monitoring of full information.
But since the source of drug security information on public network is numerous, and include a large amount of drug safety information, it should
A large amount of drug safety information is not difficult the adverse events for obtaining target medicine by the way of artificial by arranging well
Information, it is also difficult to statistic of classification etc. be carried out to adverse events information, and need to waste a large amount of manpowers, to be difficult to the medicine to production
The drug safety information that product generate on public network is effectively monitored.
For this purpose, the embodiment of the present application provides a kind of drug safety information monitoring method based on public network, this method
Can automatically get the adverse events information of target medicine from the bulk information of target public network, and to its automatically into
The processing such as row classification, avoid the waste of manpower, improve treatment effeciency, realize and produced on public network to the drug of production
Raw drug safety information is effectively monitored.
A kind of drug safety information monitoring system framework based on public network is shown referring to Fig. 1, Fig. 1, in the system
May include target public network 101, acquisition server 102, Analysis server 103 and user terminal 104.
Target public network 101 can be the network for using the patient of target medicine to be used for exchanging, publicity medication is experienced,
Such as may include appointed website, forum, mhkc, blog etc..May include being directed to for patient's publication on target public network 101
A large amount of adverse events information of target medicine.
For example, it can be that the mhkc about heart disease drug might have cardiac in the mhkc to specify mhkc
Effect, the usage experience etc. for often exchanging certain heart disease drug may also have some user's meetings for paying close attention to the heart disease drug
Browse the mhkc, or even proposition problem etc. on the mhkc.Therefore, if using the heart disease drug as target medicine, in order to obtain
The adverse events information of the target medicine is taken, can may be obtained in the mhkc using the mhkc as target public network 101
Take the adverse events information of the heart disease drug.
Acquisition server 102 can crawl rule according to data, and target medicine is automatically obtained from target public network 101
The adverse events information of product, the adverse events information can reflect patient using which adverse events has occurred after target medicine,
To reflect the safety of the target medicine.
Analysis server 103 can classify to the adverse events information according to keyword, obtain classification results, with
The classification results from Analysis server 103 can be obtained by user terminal 104 by continuing medicine enterprise after an action of the bowels, so as to according to classification results
Drug safety information is monitored.Wherein, different keywords corresponds to different event types.The keyword can be based on
International Conference on Harmonisation of Technical Requirements for Registration of Pharmaceuticals for Human use (International Conference on Harmonization of
Technical Requirements for Registration of Pharmaceuticals for Human Use, referred to as
ICH) International Medical medication dictionary (Medical Dictionary for Regulatory Activities, abbreviation MedDRA)
It obtains, which can be the event type classified based on ICH International Medical medication dictionaries (MedDRA).
It is understood that user terminal 104 can be the terminal devices such as computer, mobile terminal, tablet computer.When with
When family terminal 104 is mobile terminal, user terminal 104 can obtain the classification from Analysis server 103 by short message cat 105
As a result.
The adverse events information that the embodiment of the present application is previously mentioned can refer to that patient's body after using target medicine is sent out
Raw bad clinical events.For example, patient has occurred the symptoms such as vomiting, diarrhea, then vomits, diarrhea after using target medicine A
Adverse events can be used as.
Fig. 1 is only the system architecture illustrated example of the embodiment of the present application, does not constitute the restriction to the embodiment of the present application.
Below in conjunction with the accompanying drawings, to a kind of drug safety information monitoring side based on public network provided by the embodiments of the present application
Method is introduced.
Referring to Fig. 2, the flow chart of Fig. 2 shows a kind of drug safety information monitoring method based on public network, including:
S201, rule is crawled according to data, the adverse events information of target medicine is obtained from target public network.
Target public network can be the source with the relevant information of target medicine, can be with the relevant information of target medicine
Including adverse events information.
When medicine enterprise wishes to be monitored the security information that target medicine generates on public network, target can be inputted
The title of drug, to trigger S201, to realize the automatic monitoring to drug safety information.
When acquisition server 102 executes S201, acquisition server 102 can obtain target from target public network 101
The adverse events information of drug.It, can be in acquisition server in order to ensure that acquisition server 102 obtains the safety of information process
Fire wall 106 is set between 102 and target public network 101, ensures that the information that acquisition server 102 is got is safe.
It should be noted that input target medicine title after, can target public network swash get largely with
The relevant text of target medicine, but there may be the text of the sales information including target medicine including mesh in these texts
The advertising information of the text including target medicine of the effect of marking the text including target medicine of the composition information of drug information
The text etc. of text and adverse events information including target medicine.It can be seen that in a large amount of texts crawled, only portion
Single cent is originally the required text for including adverse events information, in order to crawl out adverse events information from bulk information,
A kind of realization method of S201 may include:
S2011, rule is crawled according to data, is obtained and the relevant text to be determined of target medicine from target public network
This.
For example, after the title of input target medicine, swashes in target public network and get 1000 and target medicine phase
There is the text including target medicine of the sales information for including target medicine in the text to be determined in the text to be determined closed
The effect of text including target medicine of composition information information text including target medicine advertising information text and packet
Include the text etc. of the adverse events information of target medicine.
S2012, extracted from the text to be determined according to the keyword include the adverse events information text.
For the text including different information, included by keyword may it is different, in this way, can basis
Keyword extracts the text for including adverse events information from text to be determined.
By taking above-mentioned text to be determined as an example, for the text of the sales information including target medicine, keyword may be
" price ", " sales volume " etc.;For the text of the composition information including target medicine, keyword may be " ingredient ", " content "
And various chemical names etc.;The text of adverse events information including target medicine, keyword may be " diarrhea ", " vomit
Spit ", " dizziness " etc..Therefore, by keyword " diarrhea ", " vomiting ", " dizziness " etc., packet can be extracted from text to be determined
The text of adverse events information is included, if the text that 1000 texts to be determined include adverse events information there are 50, is utilized
Keyword can extract 50 texts for including adverse events information.
S2013, the adverse events information is obtained from the text.
After getting the text including adverse events information, the content of big section may be included in the text, wherein only
Fraction is related to the adverse events information of target medicine, for example, the content of the text is " to begin to use ××× from January
Drug, initial effect well, do not occur and still after one month, start similar to bad reflections such as dizzy, vomitings
Existing erythema ... ", " ××× drug " can be as target medicine at this time, and " erythema " can be as the adverse events of target medicine
Information, it is seen then that in the big section word of the text, only after " erythema " that is partly previously mentioned be adverse events information, remaining
Not required information.In this case, in order to determined from the text including adverse events information adverse events believe
Breath, the keyword can be extracted from the text, then, the adverse events are determined according to the context of the keyword
Information.
Continue with " begin to use ××× drug from January, initial effect well, do not occur similar to it is dizzy,
The bad reflections such as vomiting still after one month, start erythema occur ... " for, the keyword extracted from the text can
To include that dizziness, vomiting, erythema etc. still can be seen that dizzy, vomiting is not that the patient occurs according to the context of keyword
Adverse events information, the patient occur adverse events be erythema this article therefore can be determined according to the context of keyword
This adverse events information is " erythema ".
In some cases, may include what some were repeated in target public network swashes the adverse events information got
Event information, for example, the patient of target medicine was used to issue the notice for including adverse events information on mhkc, the notice
It may be reprinted, in this case, in order to obtain the adverse events information for using the patient of the target medicine to issue, avoided
Adverse events information duplicates, and a kind of realization method of S201 may include:Rule is crawled according to data, from target public network
The adverse events information to be determined of target medicine is obtained in network;Duplicate removal processing is carried out to the adverse events information to be determined, is obtained
To the adverse events information.By duplicate removal processing, the repetition of adverse events information is not only avoided, can also effectively be reduced pair
The processing quantity of adverse events information improves efficiency.
S202, classification results are obtained to adverse events information progress event category according to keyword.
Wherein, different keywords corresponds to different event types.It should be noted that in the present embodiment, Ke Yigen
Event category is carried out to adverse events information according to different granularities.For example, adverse events information " dizziness ", dizziness can be used as should
The keyword of adverse events information, adverse events information " headache ", headache can be as the keywords of the adverse events information.When
When granularity of classification is thicker, adverse events information " dizziness " and adverse events information " headache " are divided into same type, at this point, can
To think that keyword " dizziness " and keyword " headache " are identical keywords;When granularity of classification is thinner, adverse events letter
Breath " dizziness " and adverse events information " headache " are divided into different type, at this point it is possible to think keyword " dizziness " and keyword
" headache " is different keyword.
It is understood that since same patient in the text may be inconsistent to the statement of same adverse events information,
Such as " headache " and " headache ", actually " headache " and " headache " is an adverse events information, should in order to accurately determine out
Patient can be gathered the different expression of same adverse events information using the adverse events information occurred after target medicine
It closes, which is expressed using identical statement.
Medicine enterprise can be recognized according to the classification results patient using after target medicine, have occurred which adverse events with
And the quantity etc. of various adverse events, the drug safety information that the drug of production generates on public network is carried out to realize
Effectively monitor.
After obtaining classification results, in order to which classification results are intuitive, visually displaying administration enterprise takes referring to Fig. 1 in analysis
Application server 107 can be set between business device 103 and user terminal 104, application server 107 can be tied according to the classification
Fruit counts the adverse events information, generates the visualization statistical result such as summary report.Wherein, summary report can be with
The source etc. of the adverse events information, adverse events information that include including event type, each event type.
When the drug safety information to public network is monitored, rule can be crawled according to data, automatically from target
The adverse events information of target medicine is obtained in public network, which can reflect that patient uses after target medicine
Which adverse events has occurred, to reflect the safety of the target medicine.Then, the adverse events are believed according to keyword
Breath is classified, and obtains classification results, wherein different keywords corresponds to different event types.In this way, medicine enterprise can root
Recognize that after using target medicine, the quantity of which adverse events and various adverse events has occurred in patient according to classification results
Deng.Compared with traditional approach, the embodiment of the present application automatically can get target from the bulk information of target public network
The adverse events information of drug, and the processing such as classify is carried out automatically to it, the waste of manpower is avoided, treatment effeciency is improved,
It realizes and the drug safety information that the drug of production generates on public network is effectively monitored.
It should be noted that since public network includes many kinds, if all carrying out drug to each public network
Security information monitors, it may be necessary to carry out a large amount of data processing, put into and consume a large amount of resource.For this purpose, in the present embodiment
In, can to the adverse events information carry out domain name identification, obtain include the public network of the adverse events information domain
Which name to identify which public network is the adverse events information for being directed to target medicine come from, or mostlys come from
Public network.Then, the target public network is redefined according to domain name.
When redefining the target public network according to domain name, may include two kinds of situations, separately below into
Row is introduced.
Wherein, a kind of it may is that, the corresponding public network of domain name is determined as target public network.Namely
It says, the public network that will obtain adverse events information is all used as target public network, and is used as target public network before
But the public network of adverse events information has not been obtained can not be re-used as target public network later.Both the throwing of resource had been reduced
Enter and consume, improve monitoring specific aim, and avoids omitting any adverse events information.
For example, when this is monitored target medicine security information, is identified and determined in adverse events information by domain name
80% comes from mhkc, and 10% comes from specified network, and 9% comes from forum, and 1% comes from blog, from remaining public network
On do not get adverse events information, then mhkc, specified network, forum and blog can be determined as target public network,
When being monitored to target medicine security information next time, only the drug in mhkc, specified network, forum and blog can be pacified
Full information is monitored, without monitoring remaining public network.
It is another it may is that, the number that statistics domain name occurs;The number is more than to the domain name of predetermined threshold value
Corresponding public network is determined as target public network.That is, all regarding the main source of adverse events information as target
Public network, the public network that some are only capable of with very low amount adverse events information is no longer monitored, so as to having
Drug safety information on representative public network is effectively monitored, and input and the consumption of resource are reduced.
For example, determining that adverse events information has 100, wherein the domain name of mhkc occurs 80 times, and the domain name of forum occurs 15
Secondary, the domain name of blog occurs 2 times, and the domain name of network is specified to occur 3 times.If predetermined threshold value is set as 10, at this point, the domain of the mhkc
The number that name and the domain name of the forum occur is more than 10, then can the mhkc and the forum be determined as target public network,
When next time is monitored target medicine security information, only the drug safety information on the mhkc and the forum can be supervised
It surveys, without monitoring remaining public network.
Based on previous embodiment, the drug safety information of public network is being monitored using system shown in Figure 1 framework
When, drug safety inter-area traffic interarea structure chart may refer to shown in Fig. 3, including data adverse events information source layer, bad thing
Part information collection layer, event category layer, presentation layer and client.
Wherein, adverse events information source layer can be the target public network being previously mentioned in previous embodiment;Bad thing
Part acquisition layer can be used for executing the correlation step for obtaining adverse events information in S201;Event category layer can be used for executing
The correlation steps such as event category are carried out to adverse events information in S202;Presentation layer can be used for classification results utilizing visualization
Mode show on the client administration enterprise, the visual means are such as can be statistical graph.
The present embodiment can crawl rule when the drug safety information to public network is monitored according to data, from
The dynamic adverse events information that target medicine is obtained from bad event information source layer, the adverse events information can reflect that patient makes
With which adverse events has occurred after target medicine, to reflect the safety of the target medicine.Then, event category layer can be with
Classified to the adverse events information that adverse events acquisition layer is got according to keyword, obtain classification results, wherein is different
Keyword correspond to different event types.Finally, presentation layer can by classification results in the way of visual in client
Upper displaying administration enterprise.In this way, medicine enterprise can recognize which patient after using target medicine, has occurred according to classification results
The quantity etc. of adverse events and various adverse events.The embodiment of the present application can be automatically from a large amount of letters of target public network
The adverse events information of target medicine is got in breath, and the processing such as classify is carried out automatically to it, is avoided the waste of manpower, is carried
High treatment effeciency, realizes and is effectively monitored to the drug safety information that the drug of production generates on public network.
Based on a kind of drug safety information monitoring method based on public network that previous embodiment provides, the present embodiment carries
For a kind of drug safety information monitoring device based on public network, shown referring to Fig. 4, Fig. 4 a kind of based on public network
The structure diagram of drug safety information monitoring device, including acquiring unit 401 and taxon 402:
The acquiring unit 401 obtains target medicine not for crawling rule according to data from target public network
Good event information;
The taxon 402 is classified for carrying out event category to the adverse events information according to keyword
As a result, different keywords corresponds to different event types.
Optionally, described device further includes recognition unit and determination unit:
The recognition unit obtains including the adverse events for carrying out domain name identification to the adverse events information
The domain name of the public network of information;
The determination unit, for redefining the target public network according to domain name.
Optionally, the determination unit is used to the corresponding public network of domain name being determined as target public network;
Or, the determination unit is used to count the number of domain name appearance;The number is more than to the domain of predetermined threshold value
The corresponding public network of name is determined as target public network.
Optionally, the acquiring unit is used for:Rule is crawled according to data, acquisition and mesh from the target public network
Mark the relevant text to be determined of drug;It includes the adverse events letter to be extracted from the text to be determined according to the keyword
The text of breath;The adverse events information is obtained from the text.
Optionally, the acquiring unit is used for:The keyword is extracted from the text;According to the upper of the keyword
Hereafter determine the adverse events information.
Optionally, described device further includes generation unit:
The generation unit generates abstract for according to the classification results, being counted to the adverse events information
Report.
When the drug safety information to public network is monitored, acquiring unit 401 can crawl rule according to data,
Automatically the adverse events information of target medicine is obtained from target public network, which can reflect that patient uses
Which adverse events has occurred after target medicine, to reflect the safety of the target medicine.Then, taxon 402 can be with
Classified to the adverse events information according to keyword, obtains classification results, wherein different keywords corresponds to different
Event type.In this way, medicine enterprise can recognize which patient after using target medicine, it is bad to have occurred according to classification results
The quantity etc. of event and various adverse events.Compared with traditional approach, the embodiment of the present application can be automatically public from target
The adverse events information of target medicine is got in the bulk information of network, and the processing such as classify is carried out automatically to it, is avoided
The waste of manpower, improves treatment effeciency, realize drug safety information that the drug of production is generated on public network into
Row effectively monitors.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and foregoing routine can be stored in a computer read/write memory medium, which exists
When execution, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned can be in following media at least one
Kind:Read-only memory (English:Read-onlymemory, abbreviation:ROM), RAM, magnetic disc or CD etc. are various can store journey
The medium of sequence code.
It should be noted that each embodiment in this specification is described in a progressive manner, each embodiment it
Between just to refer each other for identical similar part, each embodiment focuses on the differences from other embodiments.
For equipment and system embodiment, since it is substantially similar to the method embodiment, so describe fairly simple,
The relevent part can refer to the partial explaination of embodiments of method.Equipment and system embodiment described above is only schematic
, wherein may or may not be physically separated as the unit that separating component illustrates, shown as unit
Component may or may not be physical unit, you can be located at a place, or may be distributed over multiple networks
On unit.Some or all of module therein can be selected according to the actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art are without creative efforts, you can to understand and implement.
The above, only a kind of specific implementation mode of the application, but the protection domain of the application is not limited thereto,
Any one skilled in the art is in the technical scope that the application discloses, the change or replacement that can be readily occurred in,
It should all cover within the protection domain of the application.Therefore, the protection domain of the application should be with scope of the claims
Subject to.
Claims (10)
1. a kind of drug safety information monitoring method based on public network, which is characterized in that the method includes:
Rule is crawled according to data, the adverse events information of target medicine is obtained from target public network;
Event category is carried out to the adverse events information according to keyword and obtains classification results, different keywords corresponds to different
Event type.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
To the adverse events information carry out domain name identification, obtain include the public network of the adverse events information domain name;
The target public network is redefined according to domain name.
3. according to the method described in claim 2, it is characterized in that, described according to domain name to redefine the target public
Network, including:
The corresponding public network of domain name is determined as target public network;
Or, described redefine the target public network according to domain name, including:
Count the number that domain name occurs;
The corresponding public network of domain name that the number is more than to predetermined threshold value is determined as target public network.
4. according to the method described in claim 1, it is characterized in that, described crawl rule according to data, from target public network
The middle adverse events information for obtaining target medicine, including:
Rule is crawled according to data, is obtained and the relevant text to be determined of target medicine from the target public network;
Extracted from the text to be determined according to the keyword include the adverse events information text;
The adverse events information is obtained from the text.
5. according to the method described in claim 4, it is characterized in that, described obtain the adverse events letter from the text
Breath, including:
The keyword is extracted from the text;
The adverse events information is determined according to the context of the keyword.
6. according to the method described in claim 1, it is characterized in that, it is described according to keyword to the adverse events information into
After row event category obtains classification results, the method further includes:
According to the classification results, the adverse events information is counted, generates summary report.
7. a kind of drug safety information monitoring device based on public network, which is characterized in that described device includes acquiring unit
And taxon:
The acquiring unit obtains the adverse events of target medicine for crawling rule according to data from target public network
Information;
The taxon obtains classification results, no for carrying out event category to the adverse events information according to keyword
Same keyword corresponds to different event types.
8. device according to claim 7, which is characterized in that described device further includes recognition unit and determination unit:
The recognition unit obtains including the adverse events information for carrying out domain name identification to the adverse events information
Public network domain name;
The determination unit, for redefining the target public network according to domain name.
9. device according to claim 8, which is characterized in that the determination unit is used for domain name is corresponding public
Network is determined as target public network;
Or, the determination unit is used to count the number of domain name appearance;The number is more than to the domain name pair of predetermined threshold value
The public network answered is determined as target public network.
10. device according to claim 7, which is characterized in that the acquiring unit is used for:Rule is crawled according to data,
It is obtained and the relevant text to be determined of target medicine from the target public network;According to the keyword from described to be determined
Extraction includes the text of the adverse events information in text;The adverse events information is obtained from the text.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810326260.6A CN108550380A (en) | 2018-04-12 | 2018-04-12 | A kind of drug safety information monitoring method and device based on public network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810326260.6A CN108550380A (en) | 2018-04-12 | 2018-04-12 | A kind of drug safety information monitoring method and device based on public network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108550380A true CN108550380A (en) | 2018-09-18 |
Family
ID=63514754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810326260.6A Pending CN108550380A (en) | 2018-04-12 | 2018-04-12 | A kind of drug safety information monitoring method and device based on public network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108550380A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111312347A (en) * | 2020-02-03 | 2020-06-19 | 卫宁健康科技集团股份有限公司 | Medical adverse event clue identification method and device, electronic equipment and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101667194A (en) * | 2009-09-29 | 2010-03-10 | 北京大学 | Automatic abstracting method and system based on user comment text feature |
CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
CN102708096A (en) * | 2012-05-29 | 2012-10-03 | 代松 | Network intelligence public sentiment monitoring system based on semantics and work method thereof |
CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
CN103701769A (en) * | 2013-11-07 | 2014-04-02 | 江南大学 | Method and system for detecting hazardous network source |
CN104765947A (en) * | 2015-03-02 | 2015-07-08 | 大连理工大学 | Method for mining potential adverse drug reaction data from big data |
CN104951539A (en) * | 2015-06-19 | 2015-09-30 | 成都艾尔普科技有限责任公司 | Internet data center harmful information monitoring system |
CN106649498A (en) * | 2016-10-10 | 2017-05-10 | 合肥红珊瑚软件服务有限公司 | Network public opinion analysis system based on crawler and text clustering analysis |
-
2018
- 2018-04-12 CN CN201810326260.6A patent/CN108550380A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101667194A (en) * | 2009-09-29 | 2010-03-10 | 北京大学 | Automatic abstracting method and system based on user comment text feature |
CN101853277A (en) * | 2010-05-14 | 2010-10-06 | 南京信息工程大学 | Vulnerability data mining method based on classification and association analysis |
CN102708096A (en) * | 2012-05-29 | 2012-10-03 | 代松 | Network intelligence public sentiment monitoring system based on semantics and work method thereof |
CN103544255A (en) * | 2013-10-15 | 2014-01-29 | 常州大学 | Text semantic relativity based network public opinion information analysis method |
CN103701769A (en) * | 2013-11-07 | 2014-04-02 | 江南大学 | Method and system for detecting hazardous network source |
CN104765947A (en) * | 2015-03-02 | 2015-07-08 | 大连理工大学 | Method for mining potential adverse drug reaction data from big data |
CN104951539A (en) * | 2015-06-19 | 2015-09-30 | 成都艾尔普科技有限责任公司 | Internet data center harmful information monitoring system |
CN106649498A (en) * | 2016-10-10 | 2017-05-10 | 合肥红珊瑚软件服务有限公司 | Network public opinion analysis system based on crawler and text clustering analysis |
Non-Patent Citations (2)
Title |
---|
蔡永铭等: "基于社交网络监测药品不良反应", 《医学信息学杂志》 * |
赵明珍: "面向社交网络的潜在药物不良反应发现", 《中文信息学报》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111312347A (en) * | 2020-02-03 | 2020-06-19 | 卫宁健康科技集团股份有限公司 | Medical adverse event clue identification method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20020082868A1 (en) | Systems, methods and computer program products for creating and maintaining electronic medical records | |
Du et al. | A bibliometric analysis of emergency management using information systems (2000-2016) | |
DE112019001136T5 (en) | ANALYSIS OF ADVERSE MEDICINE EFFECTS | |
CA2883388A1 (en) | Mental modeling method and system | |
Akbar et al. | Content Analysis of Social Media: Public and Government Response to COVID-19 Pandemic in Indonesia | |
Foreit et al. | Increasing access to family planning (FP) and reproductive health (RH) services through task-sharing between community health workers (CHWs) and community mid-level professionals in large-scale public-sector programs: a literature review to help guide case studies | |
Beerepoot et al. | Seeing the signs of workarounds: a mixed-methods approach to the detection of nurses’ process deviations | |
Shneiderman et al. | Interactive visual event analytics: Opportunities and challenges | |
CN112328856A (en) | Common event tracking method and device, computer equipment and computer readable medium | |
Lee et al. | Real-time digital flu surveillance using twitter data | |
Liu et al. | Epic30m: An epidemics corpus of over 30 million relevant tweets | |
CN112259243B (en) | Single-disease clinical path construction method and system based on bidirectional GRUs | |
CN113947959A (en) | Remote teaching system and live broadcast problem screening system based on MR technology | |
CN108550380A (en) | A kind of drug safety information monitoring method and device based on public network | |
CN109243549A (en) | A kind of intelligent follow-up method, device and server | |
CN109035094A (en) | Teaching method, device and terminal device based on artificial intelligence | |
Proulx et al. | Avian flu case study with nspace and geotime | |
Graco et al. | Toward knowledge-driven data mining | |
CN106951688B (en) | A kind of dialectical system of Chinese medicine four methods of diagnosis parting | |
Atanacio et al. | Development and evaluation of rural health unit record management system with data analytics for municipality of Bay, Laguna using ISO 25010 | |
MASHUDI et al. | THE USE OF CHATBOT SYSTEMS IN ONLINE COUNSELING SERVICES: A BIBLIOMETRIC MAPPING | |
Mandal et al. | Predicting zika prevention techniques discussed on twitter: An exploratory study | |
CN105975792A (en) | Big-data-based dermatoglyph analysis and processing device and method | |
Aljarboa et al. | Investigating acceptance factors of Clinical Decision Support Systems in a developing country context | |
CN110460452A (en) | Information push method and Related product |
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: 20180918 |
|
RJ01 | Rejection of invention patent application after publication |