CN107169278A - A kind of data administering method and medical information system - Google Patents
A kind of data administering method and medical information system Download PDFInfo
- Publication number
- CN107169278A CN107169278A CN201710326064.4A CN201710326064A CN107169278A CN 107169278 A CN107169278 A CN 107169278A CN 201710326064 A CN201710326064 A CN 201710326064A CN 107169278 A CN107169278 A CN 107169278A
- Authority
- CN
- China
- Prior art keywords
- data
- feature
- tables
- result
- determined
- 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
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention discloses a kind of data administering method and medical information system, for improving recognition efficiency of the medical information system to data, the difficulty of multiple HIS data fusion is reduced.Data administering method therein includes：At least one tables of data is obtained, wherein, at least one described tables of data comes from least one hospital information system HIS；It is determined that the feature of the data in each tables of data at least one described tables of data；The feature is used for the classification for indicating the data；According to the feature of storage and the corresponding relation of data result, the result of the data in each tables of data is determined；Wherein, the corresponding relation is before current time, the feature of the data in each tables of data and to be determined by machine learning with obtained data result.
Description
Technical field
The present invention relates to medical resource technology of sharing field, more particularly to a kind of data administering method and medical information system
System.
Background technology
Hospital internal construction has hospital information system (Hospital Information System, HIS), realizes doctor
Information sharing inside institute, but the information sharing between hospital can not be realized.
In order to realize the information sharing between hospital, to make full use of limited health care hospital, prior art is set
Put an information system that can carry out collaboration medical profession to support, this system is referred to as medical information system.The doctor
The information of different medical institutions can be obtained by treating information system, such as obtains different HIS data, support different doctors
Treat institution cooperation and complete medical treatment.Medical information system can obtain multiple HIS data, by multiple HIS of acquisition data
Fusion, to cooperate with medical profession.But the description rule of different HIS data may be different, such as same medicine,
One HIS description form is probably A, and another HIS description form is probably B, and this results in medical information system i.e.
Allow to obtain multiple HIS data, also the more difficult multiple HIS of fusion data.
At present, medical information system is obtained after multiple HIS data, is that staff knows to the data of acquisition mostly
Not, data are merged again after identification.However, data are identified artificial mode, to the specialty of staff itself
Outside Capability Requirement is higher, in the case where there are the data of magnanimity, it is clear that people's identification data it is less efficient.
The content of the invention
The embodiment of the present invention provides a kind of data administering method and medical information system, for improving medical information system
The recognition efficiency united to data, reduces the difficulty of multiple HIS data fusion.
In a first aspect, one embodiment of the invention provides a kind of data administering method, applied to medical information system, institute
The information sharing between multiple hospitals can be realized by stating medical information system, the data administering method, including：
At least one tables of data is obtained, wherein, at least one described tables of data comes from least one hospital information system
HIS；
It is determined that the feature of the data in each tables of data at least one described tables of data；
According to the feature of storage and the corresponding relation of data result, the result of the data in each tables of data is determined；
Wherein, the corresponding relation be before current time, the feature of the data in each tables of data and with obtained data knot
Fruit learns what is determined by machine by machine.
Optionally, it is determined that the feature of the data in each tables of data at least one described tables of data, including：
Extract the field information of the data in each tables of data；
The feature of the data is determined from the field information.
Optionally, it is determined that storage feature and data result corresponding relation, including：
Obtain the feature of sample data；
Acquired feature is matched with known data characteristics, the result of the sample data is determined；
Set up the corresponding relation of the feature of the sample data and the result of the sample data.
Optionally, in the feature and the corresponding relation of data result according to storage, the number in each tables of data is determined
According to result after, in addition to：
Update the corresponding relation.
Optionally, the corresponding relation is updated, including：
If it is determined that feature and the known data characteristics of the data mismatch, then by the feature of the data of determination
Update the known data characteristics.
Optionally, the corresponding relation is updated, including：
The feature of the data of determination and known data characteristics are associated, if the degree of association is less than predetermined threshold value,
Then the feature of the data of determination is updated to the known data characteristics.
Optionally, in addition to：
The data for the determining result data currently stored with itself are merged and stored.
Optionally, it is determined that before the feature of data in each tables of data at least one described tables of data, also
Including：
Unnecessary data in each described tables of data of filtering, the unnecessary data, which are used for instruction, to be recognized
Data.
Optionally, it is determined that before the feature of data in each tables of data at least one described tables of data, also
Including：
The data that there is missing in each described tables of data are filled, to cause in each described tables of data
Data are complete.
Second aspect, another embodiment of the present invention provides a kind of medical information system, the medical information system
It can realize the information sharing between multiple hospitals, the medical information system, including：
Acquisition module, for obtaining at least one tables of data, wherein, at least one described tables of data is cured from least one
Institute information system HIS；
First determining module, the spy for determining the data in each tables of data at least one described tables of data
Levy；
Second determining module, for the feature and the corresponding relation of data result according to storage, determines each data
The result of data in table；Wherein, the corresponding relation is the feature of the data in each tables of data before current time
Determined with the data result with obtaining by machine learning.
Optionally, first determining module determines the data in each tables of data at least one described tables of data
Feature, including：
Extract the field information of the data in each tables of data；
The feature of the data is determined from the field information.
Optionally, first determining module determines the feature of storage and the corresponding relation of data result, including：
Obtain the feature of sample data；
Acquired feature is matched with known data characteristics, the result of the sample data is determined；
Set up the corresponding relation of the feature of the sample data and the result of the sample data.
Optionally, in addition to：
Update module, in the feature and the corresponding relation of data result according to storage, determining each tables of data
In data result after, update the corresponding relation.
Optionally, the update module updates the corresponding relation, including：
If it is determined that feature and the known data characteristics of the data mismatch, then by the feature of the data of determination
Update the known data characteristics.
Optionally, the update module updates the corresponding relation, including：
The feature of the data of determination and known data characteristics are associated, if the degree of association is less than predetermined threshold value,
Then the feature of the data of determination is updated to the known data characteristics.
Optionally, in addition to：
Memory module, for the data for the determining result data currently stored with itself to be merged and stored.
Optionally, in addition to：
Filtering module, for it is determined that data in each tables of data at least one described tables of data feature it
Before, unnecessary data in each described tables of data of filtering, the unnecessary data are used for the number for indicating to recognize
According to.
Optionally, in addition to：
Fill module, for it is determined that data in each tables of data at least one described tables of data feature it
Before, the data that there is missing in each described tables of data are filled, to cause the data in each described tables of data
Completely.
In the embodiment of the present invention, the feature of storage and the corresponding relation of data result are before current time, according to each
The feature of data in tables of data and determined with obtained data result by machine learning, so obtaining from least
After one HIS at least one tables of data, can according to the data in the corresponding relation Direct Recognition at least one tables of data, with
It is easy to data carrying out classification fusion.Compared to artificial identification method, it is clear that the recognition efficiency of machine learning is higher.And machine
The identification method of study is also higher compared to the accuracy rate of manual identified, reduces the difficulty of multiple HIS data fusion.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Inventive embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to carrying
The accompanying drawing of confession obtains other accompanying drawings.
Fig. 1 is the flow chart of data administering method provided in an embodiment of the present invention；
Fig. 2 is a kind of structural representation of medical information system provided in an embodiment of the present invention.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
It is a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In the case of not conflicting, the embodiment in the present invention and the feature in embodiment can be mutually combined.And, although in stream
Logical order is shown in journey figure, but in some cases, can be shown or described to be performed different from order herein
The step of.
In addition, the terms "and/or", only a kind of incidence relation for describing affiliated partner, represents there may be
Three kinds of relations, for example, A and/or B, can be represented：Individualism A, while there is A and B, these three situations of individualism B.Separately
Outside, character "/" herein, in the case where not illustrating, it is a kind of relation of "or" to typically represent forward-backward correlation object.
In the embodiment of the present invention, data administering method can apply to medical information system, with realize multiple hospitals it
Between information sharing.Wherein, the information sharing between multiple hospitals, can be multiple hospitals HIS between data fusion
With shared or different applied to hospital internal medical information system, such as hospital internal has different medical treatment letters
Breathization system, between the fusion of data and shared.Certainly, data administering method provided in an embodiment of the present invention, is not limited only to
Applied to medical information system, as long as need to there are multiple subsystems, it is necessary to which the data of multiple subsystems are total to
The data administering method can be applied by enjoying.Below this is introduced so that data administering method is applied to medical information system as an example
The data administering method that inventive embodiments are provided.
Medical information system can be database management language system, may be mounted at terminal device.User passes through end
End equipment can be communicated with multiple HIS, and obtain multiple HIS data, be realized multiple HIS data fusion and storage
And it is shared.In daily management mission, user can be by data storage of the terminal device multiple HIS, and to being stored
Data are operated accordingly, can such as check the data of storage, can also download the data of storage, to realize the pipe to data
Reason is shared.User can be natural person or hospital, or administrative department etc..Terminal device can pass through intelligent hand
The equipment such as machine, personal computer (PC) or tablet personal computer (PAD) are realized.
In existing medical information system, in order to merge multiple HIS data, it is necessary to which the data to multiple HIS are entered
Row identification, the data for belonging to generic merge and stored.Such as the drug data stored in multiple HIS is merged and stored,
The Outpatient Department data stored in multiple HIS is merged and stored.And because the rule of data storage in different HIS may not
Together, then also different for the recognition rule of different HIS data, this is resulted according to a kind of recognition rule, then know
Other data are very limited, it is possible to be only capable of recognizing HIS data, and None- identified other HIS data, it is difficult to realize many
The fusion of individual HIS data, natural medical information system can not preferably realize the shared of multiple HIS data.
At present, to multiple HIS data identification or it is identified by artificial mode, this energy just to staff
Power and skill requirement are higher.Such as, if data to be identified are drug datas, then require staff possesses certain
Pharmaceutical knowledge.Moreover, in face of the mass data to be recognized, manual identified is accomplished by carrying out substantial amounts of analysis work, recognition efficiency
It is relatively low.
Also a kind of identification method is using snapshot or crawls technology.Such as, data snapshot is obtained, passes through the knowledge to snapshot
Other technology, by data convert, and analyzes the structure for obtaining data, with identification data.But the degree of accuracy of this method identification is relied on
In the data of acquisition, the data are obtained by initial data by processing, for initial data, the degree of accuracy of identification
It can reduce.Even and if for same metadata, such as, and identity card/identification card number/ID card No., its essence is a data, but
It is that the form of expression is different, it is necessary to recognize 3 times, analyze 3 times, it is clear that workload is also larger.Same metadata is directed to, every time
Identification and classification analysis are needed, there are certain replicate analysis.
In consideration of it, the embodiment of the present invention provides a kind of data administering method and medical information system, machine can be passed through
Multiple HIS data are identified the method for study, and the data after identification are merged and stored, and realize melting for data
Close, recognition efficiency is also higher.
Technical scheme provided in an embodiment of the present invention is introduced below in conjunction with the accompanying drawings.
Fig. 1 is referred to, the embodiment of the present invention provides a kind of data administering method, and this method is by being mounted with medical information system
The equipment of software of uniting is performed.Medical information system can realize the information sharing between multiple hospitals, the flow of this method
It is described as follows.
S101：At least one tables of data is obtained, wherein, at least one described tables of data comes from least one information for hospital system
Unite HIS；
S102：It is determined that the feature of the data in each tables of data at least one described tables of data；
S103：According to the feature of storage and the corresponding relation of data result, data in each tables of data are determined
As a result；Wherein, the corresponding relation be before current time, the feature of the data in each tables of data and with obtained number
Determined according to result by machine learning.
In embodiments of the present invention, medical information system can be communicated with least one HIS, be obtained at any time
Take the HIS communicated with tables of data.Wherein, HIS tables of data can be Outpatient Department data table/drug data table/data of registering
Table/prescription data table etc., HIS tables of data can be stored in the form of a table, can also be stored in other possible forms, such as text
The form of shelves.Because the storage form of different HIS tables of data may be identical, it is also possible to different, therefore, medical information system
System is obtained after at least one tables of data, for the ease of unified management, the tables of data of different storage forms may be converted into phase
The tables of data of same storage form.
The content of the data included due to different tables of data also all differences, if medical information system directly will
Data merge and stored, it is clear that the data after merging are more mixed and disorderly, it is also possible to basic just not merge.Therefore, medical information
Change system is obtained after at least one tables of data, it is necessary first to which the data to each tables of data at least one tables of data are known
Not, with perhaps type etc. in the data of each tables of data at least one tables of data acquired in determination, however, it is determined that data
Type it is consistent, be all such as drug data, then the data of same type can be merged and stored, realize melting for data
Close, further realize multiple HIS data it is shared.
In the embodiment of the present invention, due to HIS tables of data include it is a variety of, such as, including drug data table, prescription data
Table, and the content of data included in same class tables of data also has a variety of, such as, the data that drug data table includes have Western medicine
And/or Chinese medicine, Western medicine is also including different Western medicine etc..For different HIS, the data stored for same class tables of data
Representation may be different.If for example, HIS is the HIS that A hospitals are used, then the data of HIS storages potentially include Chinese medicine
Related data, the title of such as Chinese medicine is represented with letter.If HIS is the HIS that B hospitals are used, then the data of HIS storages
The data of the Chinese medicine may also be included, the title of such as Chinese medicine is represented with Chinese character.Medical information system from the HIS of A hospitals and from
The HIS of B hospitals obtains the related data of the Chinese medicine, if only recognized from the title of Chinese medicine, and one is Chinese, and one is word
Mother, it is difficult to Chinese is corresponding with letter, so that it is determined that the data are the data related to Chinese medicine.
Therefore, data of the medical information system in at least one of acquisition tables of data in the embodiment of the present invention are entered
Before row identification, recognition rule can be first determined, data are identified with the recognition rule according to determination.Recognition rule can be managed
The corresponding relation to be set up in advance according to the result of the feature of data and data is solved, is described below.
The feature of data can serve to indicate that the classification of data, attribute etc., and what data can be identified for that data is.Data
Result is type, content of data of identification etc..In order to more fully understand, feature is introduced by way of example below.For example, number
According to being " Ciprofloxacin Tablets ", " astragalus injection ", " Fibrauretinum tablets " etc., corresponding feature is exactly " piece ", " parenteral solution ", data
As a result it is exactly medicine.It the above is only the feature in citing, the embodiment of the present invention and can also be other possible features, here just not
Schematically illustrate one by one, as long as can be used in mark data.Continue by taking above-mentioned example as an example, the feature of data and the knot of data
The corresponding relation that fruit is set up can be " piece ", " parenteral solution " mapping relations with medicine.
Medical information system in the embodiment of the present invention can be set up by the method for machine learning the features of data with
The corresponding relation of the result of data.Medical information system before the feature and the corresponding relation of the result of data for setting up data,
The feature of sample data can be obtained, acquired feature is matched with known data characteristics, sample data is determined
As a result, the corresponding relation of the feature of sample data and the result of sample data is then set up.
Wherein, it can be the data in each tables of data at least one tables of data to obtain sample data.Medical information
Change system obtains the feature of sample data, that is, obtains the spy of the data in each tables of data at least one tables of data
Levy.Medical information system obtains the feature of sample data, can first extract the field information of each sample data, then from field
The feature of data is determined in information.Wherein, field information can serve to indicate that the attribute of data, content etc..For example, sample data
It is drug data, field information can be nomenclature of drug, medicine unit, manufacturer of medicine etc..
In order to more fully understand, table 1 is referred to, so that tables of data is drug data table as an example, medical information system is introduced
How the feature of data is obtained.Table 1 is a kind of example of drug data table.A tables of data includes as can be seen from Table 1
At least one field information, such as title, unit.In the embodiment of the present invention, title, unit etc. are referred to as field.
Table 1, drug data table
In table 1, each field information includes the information of an at least class data, and the information of each classification is corresponding to be included
At least one field.Medical information system can obtain the feature of data, such as capsule from field, such as unit.And it is known
The feature of data, potentially includes unit, such as piece, plate, capsule, it is known that the results of the corresponding data of feature of data be probably medicine
Product.So medical information system is obtained after the feature of data, it can be matched with the feature of known data, so that it is determined that should
The corresponding data result of feature of data.Then the corresponding relation of the feature of data and the result of data is set up.
In possible embodiment, tables of data includes the data of medical personnel, then corresponding field information is potentially included
Name, ID card information etc., if the feature for the data that medical information system is extracted includes ID card information, then accordingly count
It is probably doctor according to result, it is also possible to patient.So can be by the ID card information and the progress of known ID card information
Match somebody with somebody, to further determine that data result is doctor or patient, simply illustrate above certainly, it is also possible to which data to be identified are wrapped
The further feature included, is not limited only to field.
In possible embodiment, it is known that the features of data can store in the form of a table, such as mark sheet A.It will obtain
The features of data matched with the feature of the storage in mark sheet A, can be type matching, can also be complete matching,
Similarity matching, matching regular expressions etc., specifically using which kind of matching way, the embodiment of the present invention is not restricted.Generally inciting somebody to action
, it is necessary to be specified format by the Feature Conversion of acquisition before acquired feature is matched with known data characteristics.This is
Because the requirement of different matching algorithms is different, the form of some requirement input datas is numeral, if so obtained number
According to storage form be Chinese character, then now need to be converted to hanzi form data into the data of digital form.
Medical information system establishes the feature of data and the corresponding relation of data result, it is possible to closed by the correspondence
System's identification data to be identified.The corresponding relation can also be stored in the form of a table, can also be stored in other possible forms.
, can be respectively for every if medical information system obtains at least one tables of data from least one HIS
Data in individual tables of data are identified.Firstly the need of the feature for obtaining the data in each tables of data, acquisition modes with above
The feature mode that medical information system obtains sample data is identical, and here is omitted.Medical information system is obtained often
After the feature of data in individual tables of data, corresponding number can be determined according to the feature and the corresponding relation of data result of data
According to result, to identify data.
In possible embodiment, medical information system it is determined that each tables of data at least one tables of data
In data feature before, data unnecessary in each tables of data can also be filtered, it is not necessary to data be used for indicate
The data that need not be recognized.For example, journal file is potentially included in each tables of data, and for journal file, medical information
Change system need not be recognized, if without filtering, medical information system will travel through the field information of all data, it is clear that
The burden of medical information system is added, recognition time is wasted.
In possible embodiment, medical information system is it is determined that in each tables of data at least one tables of data
Before the feature of data, the data that there is missing in each tables of data can also be filled, to cause each data
Data in table are complete.For example, tables of data is the tables of data about patient, it is generally the case that the field information of the data of patient
Potentially include identification card number, sex, name, then original tables of data may only have identification card number information, name information, and nothing
Gender information, then now, medical information system is exactly to extrapolate accordingly gender information according to identification card number, and by sex
Information is filled into raw data table, is so more conducive to the accuracy that medical information system improves identification.
In possible embodiment, medical information system is it is determined that in each tables of data at least one tables of data
Data feature before, at least one tables of data can also be classified, can be classified according to content.Due to medical treatment
The purpose of information system is exactly that the data for merging multiple HIS realize data sharing between multiple HIS.Therefore, from difference
HIS data can be classified, such as doctor data is classified as a class, drug data is classified as a class, by visiting physician
Data are classified as a class.Medical information system is first classified to be recognized afterwards, just directly the data of identification can be belonged into one after identification
Classification is merged.Otherwise also need to carry out Classification and Identification again, reduce efficiency.
Medical information system, can be currently stored with itself by the data for determining result after the result of data is determined
Data merge and store.Medical information system merges the data and itself currently stored data for determining result, production
The data for changing, the data for producing change are stored, the fusion of data is realized.
In the embodiment of the present invention, the feature of data and the corresponding relation of data result are determined using the method for machine learning,
In identification data, it is also possible to there are the data not recognized, it is also possible to there is a situation where that identification accuracy is not high.Such as,
The feature of data to be identified obtained is not present in the mark sheet of known data, then now can not will be to be identified
What data were identified.For another example the feature of the data to be identified obtained is similar to the feature in the mark sheet of known data,
But similarity is not high, then if the corresponding data result of feature in the mark sheet of known data is defined as to be identified
The result of data, the degree of accuracy of obtained data result is not also high.Therefore, medical information system is to data knowledge to be identified
During other, the feature and the corresponding relation of data result that can be updated the data update recognition rule, can recognize more
Many data to be identified, improve the degree of accuracy of identification data.
In possible embodiment, medical information system is obtained after the feature of data to be identified, will be obtained to be identified
The features of data matched with known data characteristics, if data to be identified are not present in the mark sheet of known data
Feature, then the data to be identified can now be identified by artificial mode, and by the data to be identified
Feature is updated into the mark sheet of known data.Also by the feature of the data to be identified and the result of the data to be identified
Corresponding relation, update to pre-determined data feature and data result corresponding relation.
In possible embodiment, medical information system is obtained after the feature of data to be identified, will be obtained to be identified
The features of data be associated with known data characteristics, or the data result of determination is closed with known data characteristics
Connection, if the degree of association is less than predetermined threshold value, then it represents that obtain the feature of data to be identified and the similarity of known data characteristics
It is relatively low.Predetermined threshold value can be the value that practical work is first set, such as 60%, or other possible values.Now medical information
Change system can just update the corresponding relation of the feature of data to be identified and the result of the data to be identified to true in advance
The feature of fixed data and the corresponding relation of data result.To cause medical information system to pass through in follow-up identification process
Data are identified in the feature of data after renewal and the corresponding relation of data result, and the degree of accuracy of identification data is improved as far as possible.
In the embodiment of the present invention, after the feature of medical information system update data and the corresponding relation of data result, if
When needing to recognize data to be identified again, or obtain after the feature of data to be identified, data to be identified will be obtained
Feature is associated with the known data characteristics after updating, or the known data after the data result of determination and renewal are special
Levy and be associated, if the degree of association is less than predetermined threshold value, then it represents that be after the feature of acquisition data to be identified and renewal known
The similarity of data characteristics is relatively low, and now medical information system just can treat the feature of this data to be identified with this to know
The corresponding relation of the result of other data, updates the feature pass corresponding with data result of the data once updated before
System, to improve the degree of accuracy of identification data as far as possible.The feature of the data updated and the corresponding relation of data result, may be more than
Once, it is cyclically updated, can until the degree of association of the known data characteristics after the feature of data to be identified and renewal is higher
Data to be identified are accurately identified by the feature of the data after renewal and the corresponding relation of data result, otherwise just always more
Newly.
The equipment that the embodiment of the present invention is provided is introduced below in conjunction with the accompanying drawings.
Fig. 2 is referred to, based on same inventive concept, one embodiment of the invention provides a kind of medical information system, the doctor
The information sharing between multiple hospitals can be realized by treating information system, and the medical information system includes acquisition module 201, the
One determining module 202 and the second determining module 203.
Acquisition module 201 can be used for obtaining at least one tables of data, wherein, at least one tables of data comes from least one
Hospital information system HIS；
First determining module 202 is determined for the spy of the data in each tables of data at least one tables of data
Levy；
Second determining module 203 can be used for the feature according to storage and the corresponding relation of data result, it is determined that per number
According to the result of the data in table；Wherein, corresponding relation be before current time, the feature of the data in each tables of data and
Determined with obtained data result by machine learning.
Optionally, the first determining module 202 determines the feature of the data in each tables of data at least one tables of data,
Including：
Extract the field information of the data in each tables of data；
The feature of the data is determined from field information.
Optionally, the first determining module 202 determines the feature of storage and the corresponding relation of data result, including：
Obtain the feature of sample data；
Acquired feature is matched with known data characteristics, the result of sample data is determined；
Set up the corresponding relation of the feature of sample data and the result of sample data.
Optionally, in addition to：
Update module, in the feature and the corresponding relation of data result according to storage, it is determined that in each tables of data
After the result of data, corresponding relation is updated.
Optionally, update module updates corresponding relation, including：
If it is determined that feature and the known data characteristics of data mismatch, then the feature of the data of determination is updated to
The data characteristics known.
Optionally, update module updates corresponding relation, including：
The feature of the data of determination is associated with known data characteristics, will if the degree of association is less than predetermined threshold value
The feature of the data of determination is updated to the known data characteristics.
Optionally, in addition to：
Memory module, for the data for the determining result data currently stored with itself to be merged and stored.
Optionally, in addition to：
Filtering module, for it is determined that before the feature of data in each tables of data at least one tables of data,
Filter data unnecessary in each tables of data, it is not necessary to data be used to indicate the data that need not recognize.
Optionally, in addition to：
Module is filled, for it is determined that before the feature of data in each tables of data at least one tables of data,
The data that there is missing in each tables of data are filled, to cause the data in each tables of data complete.
The medical information system can be used for performing the method that the embodiment shown in Fig. 1 is provided, therefore on the doctor
The function that each functional module can be realized in information system is treated, the corresponding description in the embodiment shown in Fig. 1 is referred to, no
Repeat more.
In the embodiment of the present invention, the feature of storage and the corresponding relation of data result are before current time, according to each
The feature of data in tables of data and determined with obtained data result by machine learning, so obtaining from least
After one HIS at least one tables of data, can according to the data in the corresponding relation Direct Recognition at least one tables of data, with
It is easy to data carrying out classification fusion.Compared to artificial identification method, it is clear that the recognition efficiency of machine learning is higher.And machine
The identification method of study is also higher compared to the accuracy rate of manual identified, reduces the difficulty of multiple HIS data fusion.
It is apparent to those skilled in the art that, for convenience and simplicity of description, only with above-mentioned each function
The division progress of module is for example, in practical application, as needed can distribute above-mentioned functions by different function moulds
Block is completed, i.e., the internal structure of device is divided into different functional modules, to complete all or part of work(described above
Energy.The specific work process of the system, apparatus, and unit of foregoing description, may be referred to corresponding in preceding method embodiment
Journey, will not be repeated here.
, can be by it in several embodiments provided by the present invention, it should be understood that disclosed apparatus and method
Its mode is realized.For example, device embodiment described above is only schematical, for example, the module or unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, such as multiple units or component
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or
The coupling each other discussed or direct-coupling or communication connection can be the indirect couplings of device or unit by some interfaces
Close or communicate to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in the application each embodiment can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used
When, it can be stored in a computer read/write memory medium.Understood based on such, the technical scheme of the application is substantially
The part contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are to cause a computer
Equipment (can be personal computer, server, or network equipment etc.) or processor (processor) perform the application each
The all or part of step of embodiment methods described.And foregoing storage medium includes：General serial bus USB
(Universal Serial Bus flash disk), mobile hard disk, read-only storage (Read-Only Memory, ROM),
Random access memory (RandomAccess Memory, RAM), magnetic disc or CD etc. are various can be with store program codes
Medium.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (10)
1. a kind of data administering method, applied to medical information system, the medical information system can realize multiple doctors
Information sharing between institute, it is characterised in that including：
At least one tables of data is obtained, wherein, at least one described tables of data comes from least one hospital information system HIS；
It is determined that the feature of the data in each tables of data at least one described tables of data；
According to the feature of storage and the corresponding relation of data result, the result of the data in each tables of data is determined；Wherein,
The corresponding relation is before current time, the feature of the data in each tables of data and to pass through with obtained data result
Machine learns what is determined by machine.
2. the method as described in claim 1, it is characterised in that it is determined that in each tables of data at least one described tables of data
Data feature, including：
Extract the field information of the data in each tables of data；
The feature of the data is determined from the field information.
3. method as claimed in claim 2, it is characterised in that it is determined that the feature and the corresponding relation of data result of storage, bag
Include：
Obtain the feature of sample data；
Acquired feature is matched with known data characteristics, the result of the sample data is determined；
Set up the corresponding relation of the feature of the sample data and the result of the sample data.
4. method as claimed in claim 2, it is characterised in that in the feature and the corresponding relation of data result according to storage,
After the result for determining data in each tables of data, in addition to：
Update the corresponding relation.
5. method as claimed in claim 4, it is characterised in that update the corresponding relation, including：
If it is determined that feature and the known data characteristics of the data mismatch, then the feature of the data of determination is updated
To the known data characteristics.
6. method as claimed in claim 4, it is characterised in that update the corresponding relation, including：
The feature of the data of determination and known data characteristics are associated, will if the degree of association is less than predetermined threshold value
The feature of the data determined is updated to the known data characteristics.
7. the method as described in claim 1, it is characterised in that also include：
The data for the determining result data currently stored with itself are merged and stored.
8. the method as described in claim 1-7 is any, it is characterised in that it is determined that each at least one described tables of data
Before the feature of data in individual tables of data, in addition to：
Unnecessary data in each described tables of data of filtering, the unnecessary data are used for the number for indicating to recognize
According to.
9. method as claimed in claim 8, it is characterised in that it is determined that each data at least one described tables of data
Before the feature of data in table, in addition to：
The data that there is missing in each described tables of data are filled, to cause the data in each described tables of data
Completely.
10. a kind of medical information system, the medical information system can realize the information sharing between multiple hospitals, its
It is characterised by, including：
Acquisition module, for obtaining at least one tables of data, wherein, at least one described tables of data is believed from least one hospital
Breath system HIS；
First determining module, the feature for determining the data in each tables of data at least one described tables of data；
Second determining module, for the feature and the corresponding relation of data result according to storage, is determined in each tables of data
Data result；Wherein, the corresponding relation be before current time, the feature of the data in each tables of data and with
What obtained data result was determined by machine learning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710326064.4A CN107169278A (en) | 2017-05-10 | 2017-05-10 | A kind of data administering method and medical information system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710326064.4A CN107169278A (en) | 2017-05-10 | 2017-05-10 | A kind of data administering method and medical information system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107169278A true CN107169278A (en) | 2017-09-15 |
Family
ID=59813800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710326064.4A Pending CN107169278A (en) | 2017-05-10 | 2017-05-10 | A kind of data administering method and medical information system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107169278A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595614A (en) * | 2018-04-20 | 2018-09-28 | 成都智信电子技术有限公司 | Tables of data mapping method applied to HIS systems |
| CN109559808A (en) * | 2018-11-07 | 2019-04-02 | 平安医疗健康管理股份有限公司 | A kind of data processing method, device, equipment and storage medium |
| CN111028931A (en) * | 2019-12-11 | 2020-04-17 | 医渡云（北京）技术有限公司 | Medical data processing method and device, electronic equipment and storage medium |
| CN109559808B (en) * | 2018-11-07 | 2024-06-25 | 深圳平安医疗健康科技服务有限公司 | Data processing method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414324A (en) * | 2008-09-01 | 2009-04-22 | ***集团宽带业务应用国家工程实验室有限公司 | Electronic medical system |
| CN101799807A (en) * | 2009-02-10 | 2010-08-11 | ***通信集团公司 | Heterogeneous data table merging method and system thereof |
| CN104657396A (en) * | 2013-11-25 | 2015-05-27 | 腾讯科技（深圳）有限公司 | Data migration method and device |
| WO2015112202A1 (en) * | 2014-01-21 | 2015-07-30 | PokitDok, Inc. | Dynamic document matching and merging |
-
2017
- 2017-05-10 CN CN201710326064.4A patent/CN107169278A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101414324A (en) * | 2008-09-01 | 2009-04-22 | ***集团宽带业务应用国家工程实验室有限公司 | Electronic medical system |
| CN101799807A (en) * | 2009-02-10 | 2010-08-11 | ***通信集团公司 | Heterogeneous data table merging method and system thereof |
| CN104657396A (en) * | 2013-11-25 | 2015-05-27 | 腾讯科技（深圳）有限公司 | Data migration method and device |
| WO2015112202A1 (en) * | 2014-01-21 | 2015-07-30 | PokitDok, Inc. | Dynamic document matching and merging |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595614A (en) * | 2018-04-20 | 2018-09-28 | 成都智信电子技术有限公司 | Tables of data mapping method applied to HIS systems |
| CN109559808A (en) * | 2018-11-07 | 2019-04-02 | 平安医疗健康管理股份有限公司 | A kind of data processing method, device, equipment and storage medium |
| CN109559808B (en) * | 2018-11-07 | 2024-06-25 | 深圳平安医疗健康科技服务有限公司 | Data processing method, device, equipment and storage medium |
| CN111028931A (en) * | 2019-12-11 | 2020-04-17 | 医渡云（北京）技术有限公司 | Medical data processing method and device, electronic equipment and storage medium |
| CN111028931B (en) * | 2019-12-11 | 2023-08-22 | 医渡云（北京）技术有限公司 | Medical data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529177B (en) | A kind of patient's portrait method and device based on medical big data | |
| Kim et al. | Medical informatics research trend analysis: a text mining approach | |
| WO2021073277A1 (en) | Personalized precise medication recommendation method and apparatus | |
| Ahmad et al. | Emerging trends and evolutions for smart city healthcare systems | |
| CN109920540A (en) | Construction method, device and the computer equipment of assisting in diagnosis and treatment decision system | |
| US11783928B2 (en) | Medical data collection devices, systems, and methods | |
| JP2018060529A (en) | Method and apparatus of context-based patient similarity | |
| CN111048167A (en) | Hierarchical case structuring method and system | |
| CN103761437A (en) | Scientific research data automatic generation system based on clinical data | |
| US20110173261A1 (en) | Using user-attribute ontologies to calculate user-anonymity degrees | |
| KR101320572B1 (en) | System and method for medical treatment pattern based on electronic medical record | |
| US20190108264A1 (en) | System prototype of intelligent regional mobile healthcare integrated data center based on metadata | |
| Pecoraro et al. | Designing ETL tools to feed a data warehouse based on electronic healthcare record infrastructure | |
| CN112863694A (en) | Information recommendation method and device | |
| CN107169278A (en) | A kind of data administering method and medical information system | |
| CN109935287A (en) | A kind of similarity analysis method, device and equipment of medical record information | |
| CN113724830A (en) | Medicine taking risk detection method based on artificial intelligence and related equipment | |
| CN109299238A (en) | A kind of data query method and apparatus | |
| Sony et al. | Semantic Interoperability Model in Healthcare Internet of Things Using Healthcare Sign Description Framework. | |
| WO2023240837A1 (en) | Service package generation method, apparatus and device based on patient data, and storage medium | |
| CN107545140A (en) | A kind of intelligent region emergency medical integrated data centring system prototype | |
| van Mens et al. | Clarifying diagnoses to laymen by employing the SNOMED CT hierarchy | |
| RU2701702C2 (en) | System and method for uniform comparison of unstructured recorded features with associated therapeutic features | |
| CN106934239A (en) | A kind of state of an illness guiding system based on diagnosis and treatment data | |
| WO2022079593A1 (en) | A system and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Xi Inventor before: Chen Xi Inventor before: Mao Mujin |
|
| CB03 | Change of inventor or designer information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170915 |
|
| RJ01 | Rejection of invention patent application after publication |