CN107480295B - The modification method of user data - Google Patents
The modification method of user data Download PDFInfo
- Publication number
- CN107480295B CN107480295B CN201710758812.6A CN201710758812A CN107480295B CN 107480295 B CN107480295 B CN 107480295B CN 201710758812 A CN201710758812 A CN 201710758812A CN 107480295 B CN107480295 B CN 107480295B
- Authority
- CN
- China
- Prior art keywords
- data
- association
- degree
- information
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
Abstract
The invention discloses a kind of modification methods of user data to establish logical base according to medical advice information and big data information；Personal information data are brought into logical base, when the data of personal information and the reference data of logical base mismatch, then the data are false data；According to the valid data in personal information, false data is calculated, the best possibility result of false data is obtained in conjunction with logical base；The missing data of personal information is inferred according to the valid data of personal information simultaneously, the best possibility result of missing data is obtained in conjunction with logical base；It is inference data by best possibility result queue when best possibility result meets degree of association demand；And it is perfect to remind client to carry out inference data.Through the invention, it improves false data and examines the accuracy rate filled with modified accuracy rate and missing data, guarantee the validity of user data.
Description
Technical field
The present invention relates to technical field of data processing, more particularly, to a kind of modification method of user data.
Background technique
With the development of the social economy, the change of people's diet structure and living habit, causes obesity, hypertension, glycosuria
The disease incidence of the diseases such as disease linearly rises, therefore effective prevention of disease becomes the problem of various circles of society pay close attention to the most.
According to the research report of the World Health Organization, the disease of the mankind 1/3 can be avoided by prevention and health care, 1/3
Therapeutic effect can be improved by effective communication in the available effective control of disease early detection, 1/3 disease.For disease,
Treatment is not unique approach, is effectively prevented by health control, controls disease and promote the efficiency of disease treatment and is only the mankind
Healthy is basic.
Prior art multi-pass carries out health evaluating to the userspersonal information collected excessively, pre- with the health for establishing personalized
Anti- scheme.However, since the personal information data of user easily occur omitting in typing or the problems such as mistake, cause to collect
Not the problems such as user data is not inconsistent there are shortage of data, false data or logic.Missing data and false data not only compromise number
According to integrality, also result in data analysis conclusion there is deviation.It is often pre-charged in order to avoid there is such case
The data of these missings, however the generally existing missing data filling of traditional big data supplement/verification method and false data are tested
The low problem of the accuracy rate of card.
Therefore, it in view of the above-mentioned problems, the present invention provides a kind of modification method of user data, improves false data and examines
The accuracy rate filled with modified accuracy rate and missing data, guarantees the validity of user data.
Summary of the invention
In view of this, the present invention provides a kind of modification method of user data, improves false data and examine and modified
Accuracy rate and the accuracy rate of missing data filling, guarantee the validity of user data.
In order to solve the above-mentioned technical problem, the present invention proposes a kind of modification method of user data, comprising:
According to medical advice information and big data information, logical base is established；Wherein, the logical base is regular factor and ginseng
Examine the degree of association between data；
The personal information data for obtaining user, the personal information data are brought into the logical base, examine described
Whether people's information data matches with the reference data in the logical base；
When the data of personal information reference data corresponding with the logical base matches, then the personal information
Data be truthful data, and by the data markers be valid data；
When corresponding with the logical base reference data of the data of the personal information mismatches, then the personal information
Data be false data；
According to the valid data in the personal information, the false data is calculated, is obtained described at least one
A possibility that false data as a result, the possibility result is brought into the logical base, obtain the possibility result with it is right
The degree of association of the user tag is answered, and by the degree of association according to priority ranking, obtaining the best of the false data can
It can property result；
The degree of association threshold value for setting the best possibility result and the corresponding user tag, it is described best when acquisition
When possibility result is more than or equal to the degree of association threshold value with the degree of association of the corresponding user tag, by the best possibility
Result queue is inference data；
When the best possibility result of acquisition is less than the degree of association threshold with the degree of association of the corresponding user tag
When value, the false data in the personal information is calculated according to the big data information, obtains the false data
Best possibility as a result, bring the best possibility result into the logical base, obtain the best possibility result with it is right
The degree of association for answering the user tag, when the degree of association is more than or equal to the degree of association threshold value, by the best possibility
Result queue is inference data；When the degree of association is less than the degree of association threshold value, then according to the big data information to institute
The false data stated in personal information calculated again, until the best possibility result and the corresponding user of acquisition
Until the degree of association of label is more than or equal to the degree of association threshold value.
Further, further includes:
When in the personal information there are when shortage of data, according to the valid data in the personal information, to missing number
According to being calculated, a possibility that obtaining at least one missing data as a result, the possibility result is brought into the logical base,
The degree of association of the possibility result with the corresponding user tag is obtained, and the degree of association is obtained according to priority ranking
Obtain the best possibility result of the missing data；
The degree of association threshold value for setting the best possibility result and the corresponding user tag, it is described best when acquisition
When possibility result is more than or equal to the degree of association threshold value with the degree of association of the corresponding user tag, by the best possibility
Result queue is inference data；
When the best possibility result of acquisition is less than the degree of association threshold with the degree of association of the corresponding user tag
When value, the missing data in the personal information is calculated according to the big data information, obtains the missing data
Best possibility as a result, bring the best possibility result into the logical base, obtain the best possibility result with it is right
The degree of association for answering the user tag, when the degree of association is more than or equal to the degree of association threshold value, by the best possibility
Result queue is inference data；When the degree of association is less than the degree of association threshold value, then according to the big data information to institute
The missing data stated in personal information calculated again, until the best possibility result and the corresponding user of acquisition
Until the degree of association of label is more than or equal to the degree of association threshold value.
Further, further includes:
When the user, which does not finish the inference data, conducts oneself well reason, according to the valid data of the personal information and institute
Logical base is stated periodically the inference data are verified and modified.
Further, further includes:
After the user, which modifies to the inference data, to be improved, the latest data of acquisition is placed again into described patrol
It collects in library, examines whether the perfect latest data matches with the reference data in the logical base；
When the reference data in the latest data and the logical base matches, then the latest data is labeled as
Valid data；
When the reference data in the latest data and the logical base mismatches, then the latest data is false number
According to.
Further, further includes:
The more new state of medical advice information described in dynamic monitoring and the big data information, according to the updated doctor
Tutorial message and the big data information are learned, real-time update is carried out to the logical base；
The updated logical base carries out real-time verification and amendment to the data of the personal information.
Preferably, the medical advice information further comprises: Fo Minghan cardiovascular event risk evaluation model, TIMI
Rating Model, Hamilton depressive scale and diabetes mellitus in China guideline of prevention and treatment.
Preferably, the big data information, further are as follows: the big data of population in the world Information Statistics.
Preferably, the degree of association is divided into: being directly linked and indirect association, the direct correlation include: that direct level-one is closed
Connection, the association of direct second level are associated with direct three-level；The indirect association include: the association of indirect level-one, the association of indirect second level and
Connect three-level association；
Wherein, the priority relationship of the degree of association are as follows: direct level-one association is greater than the association of direct second level and closes greater than direct three-level
The United Nations General Assembly is greater than the association of indirect second level in the association of indirect level-one and is greater than the association of indirect three-level.
Further, the personal information further comprises: personal essential information, personal main suit information, personal health letter
Breath and personal gene information；Wherein,
Individual's essential information, comprising: the nature situation category information such as gender, age, height, weight；
Individual's main suit information, comprising: living habit, mood, medical history, present illness history, allergies, symptom and sign,
Family history, chemical factor, physical factor and social factor；
The personal health information, comprising: biochemical indicator, image data, surgery situation, pathological section and major event；
Individual's gene information, comprising: disease, drug and nutrition.
Compared with prior art, the modification method of a kind of user data of the invention, realize it is following the utility model has the advantages that
(1) modification method of a kind of user data of the present invention, by establishing logical base, according to big data information with
And the valid data of user information, user data is verified, finds the false data in personal information in time, and to user
False data and missing data in data are corrected and perfect in time, guarantee the completeness and efficiency of user data.
(2) modification method of a kind of user data of the present invention, the medical advice information that timely updates and big data letter
Breath, adjusts logical base in real time, and then improves the accuracy rate for verifying and filling to user data, further improves user
The validity of data.
Certainly, implementing any of the products of the present invention specific needs while must not reach all the above technical effect.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Detailed description of the invention
It is combined in the description and the attached drawing for constituting part of specification shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.
Fig. 1 is the flow diagram of the modification method for the user data that the embodiment of the present invention 1 provides；
Fig. 2 is the flow diagram of the modification method for the user data that the embodiment of the present invention 2 provides.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
Embodiment 1
As shown in Figure 1, the modification method of user data provided by the present embodiment 1, includes the following steps:
Step 101, according to medical advice information and big data information, establish logical base；Wherein, the logical base is conventional
The degree of association between the factor and reference data.
Specifically, regular factor library is established according to medical advice information and big data information, and obtained and regular factor phase
Corresponding reference data, according to the relevance level relationship between reference data and the matching convention factor, establish regular factor with
Logical base between reference data.
Further, the degree of association between the regular factor and reference data is divided into: direct correlation and indirect association, institute
Stating direct correlation includes: that direct level-one is associated with, the association of direct second level is associated with direct three-level；The indirect association includes: indirect
Level-one association, the association of indirect second level are associated with indirect three-level；Wherein, the priority relationship of the degree of association are as follows: direct level-one association is big
It is associated with to be associated with greater than the association of indirect level-one greater than indirect second level greater than the association of direct three-level in direct second level and is greater than indirect three-level pass
Connection.
Step 102, the personal information data for obtaining user, the personal information data are brought into the logical base, are examined
Test whether the personal information data match with the reference data in the logical base.
Obtain user personal information data, personal information data are brought into logical base, by personal information data with
Whether the reference data of the matching convention factor is matched, examine personal information data in the zone of reasonableness of reference data.Its
Described in personal information data further include: personal essential information, personal main suit's information, personal health information and personal base
Because of information；Wherein,
Individual's essential information, comprising: the nature situation category information such as gender, age, height, weight；
Individual's main suit information, comprising: living habit, mood, medical history, present illness history, allergies, symptom and sign,
Family history, chemical factor, physical factor and social factor；
The personal health information, comprising: biochemical indicator, image data, surgery situation, pathological section and major event；
Individual's gene information, comprising: disease, drug and nutrition.
Step 103, when the data of personal information reference data corresponding with the logical base matches, then it is described
The data of personal information are truthful data, and are valid data by the data markers.
As the reference frame for calculating other data.
Step 104, when corresponding with the logical base reference data of the data of the personal information mismatches, then it is described
The data of personal information are false data.
It then needs to carry out secondary verifying to false data.
Step 105, according to the valid data in the personal information, the false data is calculated, obtain at least
A possibility that one false data, as a result, the possibility result is brought into the logical base, obtains the possibility
As a result with the degree of association of the corresponding user tag, and the degree of association is obtained into the false data according to priority ranking
Best possibility result.
Specifically, according to the valid data in userspersonal information, false data is calculated, obtains multiple falsenesses
A possibility that data result.These possibility results are brought into logical base, filter out possibility result with it is right in logical base
The data that reference data matches, and the degree of association of a possibility that matching result and the matching convention factor is obtained, based on direct
Level-one, which is associated with to be associated with to be associated with to be associated with greater than indirect second level greater than indirect level-one greater than the association of direct three-level greater than direct second level, to be greater than
The associated rule of indirect three-level, obtains the highest data of the degree of association in a possibility that matching result, and the data are denoted as this
The best possibility result of false data.
The degree of association threshold value of step 106, the setting best possibility result and the corresponding user tag, when acquisition
When the best possibility result is more than or equal to the degree of association threshold value with the degree of association of the corresponding user tag, by described in most
Good possibility result queue is inference data.
Specifically, when the false data of user information is excessive, cause to infer by the valid data of user can
The authenticity of energy property result is lower, specific real at one for the validity for being further ensured that a possibility that deduction obtains result
It applies in example, setting degree of association threshold value is direct three-level association, when the pass of best possibility result regular factor related to logical base
Connection degree is associated with more than or equal to direct three-level, is inference data by best possibility result queue.
Step 107, when the best possibility result and the degree of association of the corresponding user tag of acquisition be less than it is described
When degree of association threshold value, the false data in the personal information is calculated according to the big data information, obtains the void
The best possibility of false data is as a result, bring the best possibility result into the logical base, the acquisition best possibility
As a result with the degree of association of the corresponding user tag, when the degree of association is more than or equal to the degree of association threshold value, general is described most
Good possibility result queue is inference data；When the degree of association is less than the degree of association threshold value, then according to the big data
Information calculates the false data in the personal information again, until acquisition the best possibility result with it is corresponding
Until the degree of association of the user tag is more than or equal to the degree of association threshold value.
In a specific embodiment, setting degree of association threshold value is the association of direct three-level, when passing through personal information data
In the degree of association of best possibility result regular factor related to logical base that is inferred to of valid data closed less than direct three-level
Connection, the then validity for the best possibility result inferred are lower.Further pass through the big data of population in the world Information Statistics
False data in the personal information is calculated, obtains the best possibility of the false data as a result, simultaneously band herein
Enter the verifying for carrying out calculating data in logical base, the verifying referring to described in the present embodiment and modification method circuit sequentially, until obtaining
It takes the best possibility result of the condition of satisfaction and labels it as inference data.
The inference data are marked, and periodically user are reminded to carry out improving modification to the inference data,
In some alternative embodiments, when the user, which does not finish the inference data, conducts oneself well reason, according to the personal information
Valid data and the logical base periodically the inference data are verified and are modified, obtain more accurate data, and
Updated data are continued labeled as inference data, and it is perfect periodically to remind user to carry out the data.
Embodiment 2
As shown in Fig. 2, the modification method of user data provided by the present embodiment 2, includes the following steps:
Step 201, according to medical advice information and big data information, establish logical base；Wherein, the logical base is conventional
The degree of association between the factor and reference data.
Specifically, regular factor library is established according to medical advice information and big data information, and obtained and regular factor phase
Corresponding reference data, according to the relevance level relationship between reference data and the matching convention factor, establish regular factor with
Logical base between reference data.
Further, the degree of association between the regular factor and reference data is divided into: direct correlation and indirect association, institute
Stating direct correlation includes: that direct level-one is associated with, the association of direct second level is associated with direct three-level；The indirect association includes: indirect
Level-one association, the association of indirect second level are associated with indirect three-level；Wherein, the priority relationship of the degree of association are as follows: direct level-one association is big
It is associated with to be associated with greater than the association of indirect level-one greater than indirect second level greater than the association of direct three-level in direct second level and is greater than indirect three-level pass
Connection.
In some specific embodiments, the medical advice information further comprises: Fo Minghan cardiovascular event risk
Assessment models, TIMI Rating Model, Hamilton depressive scale and diabetes mellitus in China guideline of prevention and treatment.The big data information, into
One step are as follows: the big data of population in the world Information Statistics.
Further, the more new state of medical advice information described in dynamic monitoring and the big data information, according to update
The medical advice information and the big data information afterwards carry out real-time update to the logical base, guarantee the logical base
Timeliness and authority.
Step 202, the personal information data for obtaining user, the personal information data are brought into the logical base, are examined
Test whether the personal information data match with the reference data in the logical base.
Obtain user personal information data, personal information data are brought into logical base, by personal information data with
Whether the reference data of the matching convention factor is matched, examine personal information data in the zone of reasonableness of reference data.Its
Described in personal information data further include: personal essential information, personal main suit's information, personal health information and personal base
Because of information；Wherein,
Individual's essential information, comprising: the nature situation category information such as gender, age, height, weight；
Individual's main suit information, comprising: living habit, mood, medical history, present illness history, allergies, symptom and sign,
Family history, chemical factor, physical factor and social factor；
The personal health information, comprising: biochemical indicator, image data, surgery situation, pathological section and major event；
Individual's gene information, comprising: disease, drug and nutrition.
Step 203, when the data of personal information reference data corresponding with the logical base matches, then it is described
The data of personal information are truthful data, and are valid data by the data markers.
As the reference frame for calculating other data.
Further, logical base carries out real-time update according to the update of medical advice information and big data information, after update
Logical base real-time verification and amendment are carried out to the data of personal information.
Step 204, when corresponding with the logical base reference data of the data of the personal information mismatches, then it is described
The data of personal information are false data.
It then needs to carry out secondary verifying to false data.
Step 205, according to the valid data in the personal information, the false data is calculated, obtain at least
A possibility that one false data, as a result, the possibility result is brought into the logical base, obtains the possibility
As a result with the degree of association of the corresponding user tag, and the degree of association is obtained into the false data according to priority ranking
Best possibility result.
Specifically, according to the valid data in userspersonal information, false data is calculated, obtains multiple falsenesses
A possibility that data result.These possibility results are brought into logical base, filter out possibility result with it is right in logical base
The data that reference data matches, and the degree of association of a possibility that matching result and the matching convention factor is obtained, based on direct
Level-one, which is associated with to be associated with to be associated with to be associated with greater than indirect second level greater than indirect level-one greater than the association of direct three-level greater than direct second level, to be greater than
The associated rule of indirect three-level, obtains the highest data of the degree of association in a possibility that matching result, and the data are denoted as this
The best possibility result of false data.
The degree of association threshold value of step 206, the setting best possibility result and the corresponding user tag, when acquisition
When the best possibility result is more than or equal to the degree of association threshold value with the degree of association of the corresponding user tag, by described in most
Good possibility result queue is inference data.
Specifically, when the false data of user information is excessive, cause to infer by the valid data of user can
The authenticity of energy property result is lower, specific real at one for the validity for being further ensured that a possibility that deduction obtains result
It applies in example, setting degree of association threshold value is direct three-level association, when the pass of best possibility result regular factor related to logical base
Connection degree is associated with more than or equal to direct three-level, is inference data by best possibility result queue.
Step 207, when the best possibility result and the degree of association of the corresponding user tag of acquisition be less than it is described
When degree of association threshold value, the false data in the personal information is calculated according to the big data information, obtains the void
The best possibility of false data is as a result, bring the best possibility result into the logical base, the acquisition best possibility
As a result with the degree of association of the corresponding user tag, when the degree of association is more than or equal to the degree of association threshold value, general is described most
Good possibility result queue is inference data；When the degree of association is less than the degree of association threshold value, then according to the big data
Information calculates the false data in the personal information again, until acquisition the best possibility result with it is corresponding
Until the degree of association of the user tag is more than or equal to the degree of association threshold value.
In a specific embodiment, setting degree of association threshold value is the association of direct three-level, when passing through personal information data
In the degree of association of best possibility result regular factor related to logical base that is inferred to of valid data closed less than direct three-level
Connection, the then validity for the best possibility result inferred are lower.Further pass through the big data of population in the world Information Statistics
False data in the personal information is calculated, obtains the best possibility of the false data as a result, simultaneously band herein
Enter the verifying for carrying out calculating data in logical base, the verifying referring to described in the present embodiment and modification method circuit sequentially, until obtaining
It takes the best possibility result of the condition of satisfaction and labels it as inference data.
Step 208, when in the personal information there are when shortage of data, according to the valid data in the personal information,
A possibility that calculating to missing data, obtaining at least one missing data is as a result, the possibility result is brought into described
In logical base, the degree of association of the possibility result with the corresponding user tag is obtained, and by the degree of association according to preferential
Grade sequence, obtains the best possibility result of the missing data.
The degree of association threshold value of step 209, the setting best possibility result and the corresponding user tag, when acquisition
When the best possibility result is more than or equal to the degree of association threshold value with the degree of association of the corresponding user tag, by described in most
Good possibility result queue is inference data.
Step 210, when the best possibility result and the degree of association of the corresponding user tag of acquisition be less than it is described
When degree of association threshold value, the missing data in the personal information is calculated according to the big data information, obtains described lack
The best possibility of data is lost as a result, bringing the best possibility result into the logical base, obtains the best possibility
As a result with the degree of association of the corresponding user tag, when the degree of association is more than or equal to the degree of association threshold value, general is described most
Good possibility result queue is inference data；When the degree of association is less than the degree of association threshold value, then according to the big data
Information calculates the missing data in the personal information again, until acquisition the best possibility result with it is corresponding
Until the degree of association of the user tag is more than or equal to the degree of association threshold value.And by the best possibility result queue be push away
By data.
The inference data are marked, and periodically user are reminded to carry out improving modification to the inference data,
In some alternative embodiments, when the user, which does not finish the inference data, conducts oneself well reason, according to the personal information
Valid data and the logical base periodically the inference data are verified and are modified, obtain more accurate data, and
Updated data are continued labeled as inference data, and it is perfect periodically to remind user to carry out the data.
In other optional embodiments, after the user, which modifies to the inference data, to be improved, it will obtain
Latest data be placed again into the logical base, examine the perfect latest data whether with the reference in the logical base
Data match.
When the reference data in the latest data and the logical base matches, then the latest data is labeled as
Valid data.
When the reference data in the latest data and the logical base mismatches, then the latest data is false number
According to then repeatedly step 206 and step 207 carry out corresponding reckoning processing to the false data.
In a specific embodiment, table 1 is logical base (a part that this table 1 illustrates only logical base), and table 2 is to use
Family personal information；
1 logical base of table
2 userspersonal information of table
Above-mentioned user message table is that certain 58 years old women fills in data, and the userspersonal information in table 2 is updated to table 1 one by one
In logical base in:
1) according to being verified in logical base, other data and patrol that " diet is light " which fills in is filled in diet class
In volume library there is conflict in the reference data of related copula, thus draw a conclusion " diet is light " be false data, need to be referring to this hair
The bright data correcting method according to the valid data in userspersonal information/large database concept information and combines logical base pair
The false data is calculated and is verified.
2) due to the hypertensive patient that the user is age >=50 year old, the pressure value of the user answers >=135, therefore obtains knot
" blood pressure 80~120 " by the user is that false data ibid needs that the false data is calculated and verified.
3) since the user is diabetic, which does not fill in corresponding fasting blood sugar, leads to the shortage of data,
According to the valid data of userspersonal information/big data information, the data of the missing are calculated, it is " empty to extrapolate the user
Abdomen blood glucose >=7.0 " are verified referring to the data of data correcting method of the invention to deduction.
4) since the parameter label is hyperlipidemia patient and is hyperlipidemia family history, user does not fill in lipid examination and refers to
Scale value leads to the shortage of data, according to the valid data of userspersonal information/big data information, carries out to the data of the missing
It calculates, extrapolates the user " HDL-C≤35mg/dl ", tested referring to the data of data correcting method of the invention to deduction
Card.
By above each embodiment it is found that a kind of modification method of user data of the invention, existing beneficial effect
It is:
(1) modification method of a kind of user data of the present invention, by establishing logical base, according to big data information with
And the valid data of user information, user data is verified, finds the false data in personal information in time, and to user
False data and missing data in data are corrected and perfect in time, guarantee the completeness and efficiency of user data.
(2) modification method of a kind of user data of the present invention, the medical advice information that timely updates and big data letter
Breath, adjusts logical base in real time, and then improves the accuracy rate for verifying and filling to user data, further improves user
The validity of data.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, apparatus or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
Although some specific embodiments of the invention are described in detail by example, the skill of this field
Art personnel it should be understood that example above merely to being illustrated, the range being not intended to be limiting of the invention.The skill of this field
Art personnel are it should be understood that can without departing from the scope and spirit of the present invention modify to above embodiments.This hair
Bright range is defined by the following claims.
Claims (8)
1. a kind of modification method of user data characterized by comprising
According to medical advice information and big data information, logical base is established；Wherein, the logical base is regular factor and reference number
The degree of association between；The degree of association is divided into: being directly linked and indirect association, the direct correlation include: that direct level-one is closed
Connection, the association of direct second level are associated with direct three-level；The indirect association include: the association of indirect level-one, the association of indirect second level and
Connect three-level association；Wherein, the priority relationship of the degree of association are as follows: direct level-one association is greater than the association of direct second level and is greater than direct three-level
Association is greater than the association of indirect second level greater than the association of indirect level-one and is greater than the association of indirect three-level；
The personal information data for obtaining user, the personal information data are brought into the logical base, examine the personal letter
Whether breath data match with the reference data in the logical base；
When the data of personal information reference data corresponding with the logical base matches, then the number of the personal information
It according to for truthful data, and is valid data by the data markers；
When corresponding with the logical base reference data of the data of the personal information mismatches, then the number of the personal information
According to for false data；
According to the valid data in the personal information, the false data is calculated, obtains at least one described falseness
A possibility that data as a result, the possibility result is brought into the logical base, obtain the possibility result with to application
The degree of association of family label, and the degree of association is obtained into the best possibility result of the false data according to priority ranking；
The degree of association threshold value for setting the best possibility result and the corresponding user tag, when the best possibility of acquisition
Property result and the degree of association of the corresponding user tag when being more than or equal to the degree of association threshold value, by the best possibility result
Labeled as inference data；
When the best possibility result of acquisition is less than the degree of association threshold value with the degree of association of the corresponding user tag,
Calculate that obtaining the best of the false data can to the false data in the personal information according to the big data information
Can property as a result, bring the best possibility result into the logical base, obtain the best possibility result with it is corresponding described in
The degree of association of user tag, when the degree of association is more than or equal to the degree of association threshold value, by the best possibility result mark
It is denoted as inference data；When the degree of association is less than the degree of association threshold value, then according to the big data information to the individual
False data in information calculated again, until the best possibility result and the corresponding user tag of acquisition
Until the degree of association is more than or equal to the degree of association threshold value.
2. the modification method of user data according to claim 1, which is characterized in that further include:
When in the personal information there are when shortage of data, according to the valid data in the personal information, to missing data into
A possibility that row calculates, obtains at least one missing data is as a result, the possibility result is brought into the logical base, acquisition
The degree of association of the possibility result and the corresponding user tag, and the degree of association is obtained into institute according to priority ranking
State the best possibility result of missing data；
When the best possibility result of acquisition is more than or equal to the degree of association threshold with the degree of association of the corresponding user tag
It is inference data by the best possibility result queue when value；
When the best possibility result of acquisition is less than the degree of association threshold value with the degree of association of the corresponding user tag,
Calculate that obtaining the best of the missing data can to the missing data in the personal information according to the big data information
Can property as a result, bring the best possibility result into the logical base, obtain the best possibility result with it is corresponding described in
The degree of association of user tag, when the degree of association is more than or equal to the degree of association threshold value, by the best possibility result mark
It is denoted as inference data；When the degree of association is less than the degree of association threshold value, then according to the big data information to the individual
Missing data in information calculated again, until the best possibility result and the corresponding user tag of acquisition
Until the degree of association is more than or equal to the degree of association threshold value.
3. the modification method of user data according to claim 2, which is characterized in that further include:
When the user, which does not finish the inference data, conducts oneself well reason, according to the valid data of the personal information and described patrol
Library is collected periodically the inference data are verified and modified.
4. the modification method of user data according to claim 3, which is characterized in that further include:
After the user, which modifies to the inference data, to be improved, the latest data of acquisition is placed again into the logical base
In, examine whether the perfect latest data matches with the reference data in the logical base；
When the reference data in the latest data and the logical base matches, then by the latest data labeled as effective
Data；
When the reference data in the latest data and the logical base mismatches, then the latest data is false data.
5. the modification method of user data according to claim 1, which is characterized in that further include:
The more new state of medical advice information described in dynamic monitoring and the big data information refers to according to the updated medicine
Information and the big data information are led, real-time update is carried out to the logical base；
The updated logical base carries out real-time verification and amendment to the data of the personal information.
6. the modification method of user data according to claim 5, which is characterized in that the medical advice information, into one
Step includes: Fo Minghan cardiovascular event risk evaluation model, TIMI Rating Model, Hamilton depressive scale and diabetes mellitus in China
Guideline of prevention and treatment.
7. the modification method of user data according to claim 5, which is characterized in that the big data information, further
Are as follows: the big data of population in the world Information Statistics.
8. the modification method of user data according to claim 1, which is characterized in that the personal information is further wrapped
It includes: personal essential information, personal main suit information, personal health information and personal gene information；Wherein,
Individual's essential information, comprising: gender, age, height and weight；
Individual main suit information, comprising: living habit, mood, medical history, present illness history, allergies, symptom and sign, family
History, chemical factor, physical factor and social factor；
The personal health information, comprising: biochemical indicator, image data, surgery situation, pathological section and major event；
Individual's gene information, comprising: disease, drug and nutrition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758812.6A CN107480295B (en) | 2017-08-29 | 2017-08-29 | The modification method of user data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710758812.6A CN107480295B (en) | 2017-08-29 | 2017-08-29 | The modification method of user data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107480295A CN107480295A (en) | 2017-12-15 |
| CN107480295B true CN107480295B (en) | 2019-11-15 |
Family
ID=60603198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710758812.6A Active CN107480295B (en) | 2017-08-29 | 2017-08-29 | The modification method of user data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107480295B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108346470A (en) * | 2018-03-19 | 2018-07-31 | 北京工业大学 | A kind of natural quality modification method based on health data analytical technology |
| CN109119171A (en) * | 2018-07-12 | 2019-01-01 | 上海常仁信息科技有限公司 | Health data management system based on big data platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1582443A (en) * | 2001-11-02 | 2005-02-16 | 西门子共同研究公司 | Patient data mining |
| US7912842B1 (en) * | 2003-02-04 | 2011-03-22 | Lexisnexis Risk Data Management Inc. | Method and system for processing and linking data records |
| CN102110228A (en) * | 2009-12-23 | 2011-06-29 | Metaio有限公司 | Method of determining reference features for use in an optical object initialization tracking process and object initialization tracking method |
| CN102930023A (en) * | 2011-11-03 | 2013-02-13 | 微软公司 | A data quality solution based on knowledge |
| CN105074705A (en) * | 2013-02-08 | 2015-11-18 | 百特恩格伍德公司 | Code for patient care device configuration |
| CN106355033A (en) * | 2016-09-27 | 2017-01-25 | 无锡金世纪国民体质与健康研究有限公司 | Life risk assessment system |
-
2017
- 2017-08-29 CN CN201710758812.6A patent/CN107480295B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1582443A (en) * | 2001-11-02 | 2005-02-16 | 西门子共同研究公司 | Patient data mining |
| US7912842B1 (en) * | 2003-02-04 | 2011-03-22 | Lexisnexis Risk Data Management Inc. | Method and system for processing and linking data records |
| CN102110228A (en) * | 2009-12-23 | 2011-06-29 | Metaio有限公司 | Method of determining reference features for use in an optical object initialization tracking process and object initialization tracking method |
| CN102930023A (en) * | 2011-11-03 | 2013-02-13 | 微软公司 | A data quality solution based on knowledge |
| CN105074705A (en) * | 2013-02-08 | 2015-11-18 | 百特恩格伍德公司 | Code for patient care device configuration |
| CN106355033A (en) * | 2016-09-27 | 2017-01-25 | 无锡金世纪国民体质与健康研究有限公司 | Life risk assessment system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107480295A (en) | 2017-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kaplan et al. | Effects of diet and exercise interventions on control and quality of life in non-insulin-dependent diabetes mellitus | |
| Bachiri et al. | Mobile personal health records for pregnancy monitoring functionalities: Analysis and potential | |
| CN102110192A (en) | Auxiliary disease judgment method based on diagnostic element data association | |
| CN105260594A (en) | Individual nutrition evaluation system | |
| US20180060518A1 (en) | Electronic community medical marijuana network | |
| US20180301211A1 (en) | Electronic community medical marijuana network | |
| CN115732058A (en) | Artificial intelligence-based automatic intervention and adjustment method and system for surgical rehabilitation | |
| CN107480295B (en) | The modification method of user data | |
| CN112102956A (en) | Method and system for improving compliance of diabetic patient | |
| CA2577562A1 (en) | Method for improving patient chronic disease education | |
| CN114067940A (en) | Health management method and storage medium | |
| KR20100102963A (en) | Method for producing wellbeing life care index model in ubiquitous environment | |
| Jackson et al. | Patient‐centred outcomes in dietary research | |
| US8775200B1 (en) | System and method for generating patient health management information | |
| CN109616199A (en) | A kind of slow sick screening system | |
| Weber | The evolving clinical management of hypertension | |
| Joymangul et al. | Obstructive sleep apnea compliance: Modeling home care patient profiles | |
| CN116472591A (en) | Techniques for generating predictive outcomes associated with spinal muscular atrophy using artificial intelligence | |
| Matsumoto et al. | DPC in acute-phase inpatient hospital care | |
| Braspenning et al. | Indicators for quality and safety of care | |
| WO2022141926A1 (en) | Gastrointestinal perforation diagnosis and intervention device, and diagnosis and intervention system | |
| Binder et al. | A systematic review of the efficacy of motivational interviewing on occupational performance | |
| Mead et al. | Processes and challenges in clinical decision making | |
| Motahari Nezhad | Methodological challenges in the evidence synthesis of health outcomes of digital health technologies | |
| Dowding et al. | Evidence-based decisions: the role of decision analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |