CN107845408A - Data evaluation method and device, storage medium and electronic equipment - Google Patents
Data evaluation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107845408A CN107845408A CN201711006245.5A CN201711006245A CN107845408A CN 107845408 A CN107845408 A CN 107845408A CN 201711006245 A CN201711006245 A CN 201711006245A CN 107845408 A CN107845408 A CN 107845408A
- Authority
- CN
- China
- Prior art keywords
- data
- key message
- data sample
- appraisal result
- sample
- 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.)
- Granted
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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of data evaluation method and device, storage medium and electronic equipment, it is related to technical field of data processing.The data evaluation method includes:Determine the key message in data;Obtain predetermined number data sample and be supplied to rating staff to be scored so as to the rating staff each data sample, obtain the appraisal result of each data sample;The key message vector for judging each data sample with the presence or absence of the key message and according to judged result generation for each data sample;The appraisal result and the key message vector are trained to generate training pattern by regression algorithm;And obtain data to be evaluated and be directed to training pattern described in the data run to be evaluated, the appraisal result to obtain the data to be evaluated is used as evaluation result.While can reduce artificial participation process, the stability and efficiency of data evaluation are improved the disclosure.
Description
Technical field
This disclosure relates to technical field of data processing, is filled in particular to a kind of data evaluation method, data evaluation
Put, storage medium and electronic equipment.
Background technology
With the development of informationized society, big data theory is had penetrated into all trades and professions.In big data field, such as
What sorts out information completely and targetedly data have turned into the key of big data analysis, in the process, it is necessary to data
Evaluated to determine whether data can preferably meet that analysis requires.
It is more and more with the patient data of hospital by taking medical record data in medical industry as an example, in order to better profit from going through
History Couple herbs, medical record data is concluded, summarized, arrange it is more and more important.However, Hospitals at Present is to the whole of medical record data
Science and engineering is made, and mainly carries out manual sorting by related personnel (for example, staff of Record room), sorts out, on the one hand, this data
Arranging needs continual human input, less efficient;On the other hand, related personnel is difficult due to the limitation of its professional domain
To evaluate medical record data towards various diseases with the angle of specialty.
In consideration of it, need a kind of data evaluation method, data evaluation device, storage medium and electronic equipment.
It should be noted that information is only used for strengthening the reason to the background of the disclosure disclosed in above-mentioned background section
Solution, therefore can include not forming the information to prior art known to persons of ordinary skill in the art.
The content of the invention
The purpose of the disclosure is to provide a kind of data evaluation method, data evaluation device, storage medium and electronic equipment,
And then one or more problem caused by the limitation of correlation technique and defect is at least overcome to a certain extent.
According to an aspect of this disclosure, there is provided a kind of data evaluation method, including:
Determine the key message in data;
Obtain predetermined number data sample and be supplied to rating staff so that the rating staff is to each data sample
This is scored, and obtains the appraisal result of each data sample;
Each data sample is judged with the presence or absence of the key message and each data sample is directed to according to judged result generation
This key message vector;
The appraisal result and the key message vector are trained to generate training pattern by regression algorithm;With
And
Obtain data to be evaluated and be directed to training pattern described in the data run to be evaluated, to obtain the valence mumber to be evaluated
According to appraisal result as evaluation result.
In a kind of exemplary embodiment of the disclosure, by regression algorithm to the appraisal result and the key message
Vector be trained including:
The appraisal result of each data sample and the key message vector are fitted by regression algorithm
Analyze to obtain the score of each data sample;
Determined according to the appraisal result of each data sample and with reference to the score of each data sample to scoring
Carry out the score threshold of stepping.
In a kind of exemplary embodiment of the disclosure, the key message includes the first key message and/or the second pass
Key information;
Wherein, first key message includes the information based on data integrity, second key message include with
Indication information corresponding to evaluative dimension.
In a kind of exemplary embodiment of the disclosure, determine that the key message in data includes:
First key message is determined according to preset data specification;And/or
The indication information that the rating staff specifies is defined as second key message.
According to an aspect of this disclosure, there is provided a kind of data evaluation device, including:
Key message determining module, for determining the key message in data;
Data sample grading module, for obtaining predetermined number data sample and being supplied to rating staff so as to institute's commentary
Divide personnel to score each data sample, obtain the appraisal result of each data sample;
Key message vector generation module, for judging each data sample with the presence or absence of the key message and basis
Key message vector of the judged result generation for each data sample;
Training pattern generation module, for being carried out by regression algorithm to the appraisal result and key message vector
Train to generate training pattern;And
Data evaluation module, for obtaining data to be evaluated and being directed to training pattern described in the data run to be evaluated,
Appraisal result to obtain the data to be evaluated is used as evaluation result.
In a kind of exemplary embodiment of the disclosure, the training pattern generation module includes:
Score acquiring unit, for passing through the appraisal result of the regression algorithm to each data sample and the key
Information vector is fitted analysis to obtain the score of each data sample;
Score threshold determining unit, for the appraisal result according to each data sample and with reference to each data
The score of sample determines to carry out scoring the score threshold of stepping.
In a kind of exemplary embodiment of the disclosure, the key message includes the first key message and/or the second pass
Key information;
Wherein, first key message includes the information based on data integrity, second key message include with
Indication information corresponding to evaluative dimension.
In a kind of exemplary embodiment of the disclosure, the key message determining module includes:
First key message determining unit, for determining first key message according to preset data specification;And/or
Person
Second key message determining unit, the indication information for the rating staff to be specified are defined as described second and closed
Key information.
According to an aspect of this disclosure, there is provided a kind of storage medium, be stored thereon with computer program, the computer
The data evaluation method described in above-mentioned any one is realized when program is executed by processor.
According to an aspect of this disclosure, there is provided a kind of electronic equipment, including:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to perform the number described in above-mentioned any one via the executable instruction is performed
According to evaluation method.
In the technical scheme that some embodiments of the present disclosure are provided, obtain the appraisal result of data sample and generate number
According to the key message vector of sample, the appraisal result and key message vector of data sample are trained by regression algorithm,
And evaluating data is treated according to the training pattern of generation and evaluated, on the one hand, artificially data sample is carried out in rating staff
After scoring, no longer there is the process artificially participated in this programme, and solve needs artificial constantly progress data evaluation in the prior art
The problem of;On the other hand, due to reducing the process artificially participated in, therefore, it is possible to reduce due to rating staff's subjective factor band
The problem of data evaluation come is unstable;Another further aspect, due to reducing artificial participation, the efficiency of data evaluation can be improved.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not
The disclosure can be limited.
Brief description of the drawings
Accompanying drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the disclosure
Example, and be used to together with specification to explain the principle of the disclosure.It should be evident that drawings in the following description are only the disclosure
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.In the accompanying drawings:
Fig. 1 diagrammatically illustrates the flow chart of the data evaluation method according to the illustrative embodiments of the disclosure;
Fig. 2 diagrammatically illustrates one embodiment of the data evaluation method according to the illustrative embodiments of the disclosure
The flow chart of whole process;
Fig. 3 diagrammatically illustrates the block diagram of the data evaluation device of the illustrative embodiments according to the disclosure;
Fig. 4 diagrammatically illustrates the block diagram of the training pattern generation module according to the illustrative embodiments of the disclosure;
Fig. 5 diagrammatically illustrates the block diagram of the key message determining module according to the illustrative embodiments of the disclosure;
Fig. 6 shows the schematic diagram of the storage medium of the illustrative embodiments according to the disclosure;And
Fig. 7 diagrammatically illustrates the block diagram of the electronic equipment of the illustrative embodiments according to the disclosure.
Embodiment
Example embodiment is described more fully with referring now to accompanying drawing.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, these embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in one or more embodiments in any suitable manner.In the following description, there is provided permitted
More details fully understand so as to provide to embodiment of the present disclosure.It will be appreciated, however, by one skilled in the art that can
Omitted with putting into practice the technical scheme of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution a presumptuous guest usurps the role of the host to avoid and
So that each side of the disclosure thickens.
In addition, accompanying drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical accompanying drawing mark in figure
Note represents same or similar part, thus will omit repetition thereof.Some block diagrams shown in accompanying drawing are work(
Can entity, not necessarily must be corresponding with physically or logically independent entity.These work(can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Flow chart shown in accompanying drawing is merely illustrative, it is not necessary to including all steps.For example, the step of having
The step of can also decomposing, and having, can merge or part merges, therefore the order actually performed is possible to according to actual conditions
Change.
The data evaluation method of the disclosure will be illustrated by taking medical record data in medical industry as an example below.However, not
It is limited to this, it should be appreciated that the data evaluation method described in the disclosure can also be applied to other field, for example, to investigation
Data in questionnaire carry out data evaluation, carry out data evaluation, etc. to the data in business report.
Fig. 1 diagrammatically illustrates the flow chart of the data evaluation method of the illustrative embodiments of the disclosure.With reference to figure 1,
The data evaluation method may comprise steps of:
S10. the key message in data is determined;
S12. obtain predetermined number data sample and be supplied to rating staff so that the rating staff is to each number
Scored according to sample, obtain the appraisal result of each data sample;
S14. each data sample is judged with the presence or absence of the key message and each number is directed to according to judged result generation
According to the key message vector of sample;
S16. the appraisal result and the key message vector are trained to generate training mould by regression algorithm
Type;And
S18. data to be evaluated are obtained and are directed to training pattern described in the data run to be evaluated, it is described to be evaluated to obtain
The appraisal result of valence mumber evidence is as evaluation result.
In the data evaluation method of the disclosure, obtain the appraisal result of data sample and generate the crucial letter of data sample
Breath vector, is trained by regression algorithm to the appraisal result and key message vector of data sample, and according to the instruction of generation
White silk model is treated evaluating data and evaluated, on the one hand, after rating staff artificially scores data sample, this programme is not
The process artificially participated in again be present, solve the problems, such as to need artificial constantly progress data evaluation in the prior art;On the other hand,
Due to reducing the process artificially participated in, therefore, it is possible to reduce because the data evaluation that rating staff's subjective factor is brought is unstable
The problem of determining;Another further aspect, due to reducing artificial participation, the efficiency of data evaluation can be improved.
The data evaluation method of the illustrative embodiments of the disclosure is described more detail below.
In step slo, the key message in data is determined.
In the illustrative embodiments of the disclosure, key message can include the first key message and/or the second key
Information, specifically, the first key message can include the information based on data integrity, the second key message can be included with commenting
Indication information corresponding to valency dimension.Wherein, evaluative dimension described herein can mean that user it is expected the angle evaluated, example
Such as, the direction of evaluation can be directed to a certain project included in data.
Determine that the key message in data can include determining the first key message according to preset data specification, and/or
The indication information that person specifies rating staff is defined as the second key message.
By taking medical record data in medical industry as an example, the first key message can be included according to for example《Medical record writing is advised substantially
Model》The information determined, for example, developer can in advance by《Medical record writing fundamental norms》In include fundamental norms letter
In the memory cell for ceasing input system, server can extract fundamental norms information from memory cell.Wherein, these are advised substantially
Model information can include but is not limited to patient's name, Gender, patient age, consultation time, symptom description, therapeutic scheme,
Doctor's signature etc..In addition, rating staff and/or developer can also answer according in data integrity demand self-defining case history
When comprising data message, particular determination is not done to this in this illustrative embodiments.
Second key message can be the indication information specified by rating staff according to clinical path, practice guidelines etc., separately
Outside, the information towards specified disease treatment can be included in indication information.So that the case history of hypertension carries out data evaluation as an example, the
Two key messages can include the indication information related to hypertension, for example, systolic pressure, diastolic pressure etc..
It is easily understood that in the example being only determined to medical record data integrality, it can only determine that first is crucial
Information, and be directed in the example of the medical record data of a certain disease, except possible it needs to be determined that in addition to the first key message, it is also necessary to it is determined that
Second key message corresponding to the disease.
In addition, to ensure the accuracy of key message determined, the rating staff described in the disclosure can include each disease
The medical expert in sick field, the doctor with abundant clinical experience etc..In addition, case history described above can be inpatient cases,
Can also be patient medical history, and the disclosure does not do particular determination to the concrete form of case history.
In step s 12, obtain predetermined number data sample and be supplied to rating staff so as to the rating staff couple
Each data sample is scored, and obtains the appraisal result of each data sample.
In the illustrative embodiments of the disclosure, rating staff can generate different comment based on different marking modes
Divide result.Specifically, on the one hand, stepping scoring can be carried out to data sample, that is to say, that data sample can be divided into
Some grades, for example, the scoring of 1-5 shelves can be carried out to data sample, wherein, 1 grade is scoring highest, and 5 grades are to score most
It is low.However, also by 5 grades the highest that scores can be set as, 1 grade be set as scoring it is minimum.Furthermore it is possible to the table in a manner of such as letter
1-5 shelves are levied, for example, A, B, C, D, E.It is easily understood that other shelves that data sample is divided into addition to 5 grades fall within this
Disclosed design, for example, data sample can be divided into 3 grades, 10 grades etc. by rating staff;On the other hand, can be to data sample
This progress is scored in detail, and so that hundred-mark system scores as an example, the scoring of a data sample may be 85 points.It is easily understood that it is directed to
The mode that hundred-mark system is scored, rating staff need to establish more detailed standards of grading.
In addition, server can extract predetermined number data sample at random from each data source, the disclosure is to data sample
Data format do not do particular determination.In addition, predetermined number can be by the work of developer's integrated data total amount, rating staff
Amount and server actual treatment ability sets itself, particular determination is not done to this in this illustrative embodiments.
Still by taking medical record data in medical industry as an example, first, server can extract predetermined number from each data source
Medical record data, wherein, these medical record datas can be the data from each section's chamber system of a hospital, can be from Different hospital
Data, or the medical record data of all hospitals in a certain area can be collected to build unified medical record data pond,
Server can extract predetermined number medical record data from the medical record data pond.Furthermore it is possible to exemplified by predetermined number is set
Such as 1000 parts;Next, 1000 parts of medical record datas can be supplied to one or more medical experts to be scored by server,
To obtain the appraisal result of 1000 parts of case histories.Can comment a certain it should be noted that when medical expert is scored
Valency dimension (or evaluation angle, evaluation of orientations) is scored, for example, when studying the quality of hypertension medical record data, hypertension
The medical expert in field only for the indication information of hypertension can be scored;When studying hepatitis medical record data, liver
The medical expert in sick field can carry out scoring, etc. only for the index of hepatopathy.In addition, for medical expert, with 1-5 shelves
Exemplified by stepping scoring, medical record data can be carried out in stepping mark and deposit system, for example, medical expert thinks a case history number
According to very comprehensive and objective, then the case history can be identified as to 1 grade and as appraisal result;Next, server can obtain
The appraisal result is simultaneously stored to system, and the medical record data and 1 grade of corresponding relation are thus there is in system.
In step S14, each data sample is judged with the presence or absence of the key message and is generated according to judged result
For the key message vector of each data sample.
In the illustrative embodiments of the disclosure, it can be determined that whether the data sample obtained in step S12 includes step
The first key message and/or the second key message determined in rapid S10.Specifically, it is possible, firstly, to it will include in data sample
Compared with information is carried out one by one with the first key message and/or the second key message;Next, using binary representation comparative result as
Example, if an information for comparing data sample is identical with the first key message and/or the second key message, can compare this
Relatively result is arranged to 1, if it find that a certain key message in the first key message and/or the second key message is not in data sample
Occur in this, then the comparative result is arranged to 0.Thus,, can be with after the comparing one by one of information for a data sample
The key message vector that generation is made up of these comparative results (1 or 0);Then, server can store key message vector
To system, to form the one-to-one relationship of data sample and key message vector.
In addition, developer can be similar to information that data sample includes with the key message in setting steps S10
Spend threshold value.If the two meets the similarity threshold, it is considered that the two is identical, and compared one by one, to obtain crucial letter
Breath vector.The disclosure does not do particular determination to the specific method to set up of similarity threshold.In practice, attending doctor may be due to practising
Used problem writes problem and causes some wrong words or the appearance of abbreviation by mistake, by the configuration of similarity threshold, can effectively solve
Certainly these problems.
In step s 16, the appraisal result and the key message vector are trained with life by regression algorithm
Into training pattern.
In the illustrative embodiments of the disclosure, for being generated in the appraisal result and step S14 that are obtained in step S12
Key message vector, can be fitted by regression algorithm.Wherein, the regression algorithm can be that existing at present return is calculated
One kind in method, and the disclosure is not limited the compiler language of regression algorithm.That is, can be by means of regression algorithm
Determine the relation between appraisal result and key message vector.
According to some embodiments of the present disclosure, it is possible, firstly, to using regression algorithm to appraisal result and key message vector
Analysis is fitted, obtains the score after machine learning.Wherein, the score can be represented in the form of decimal, for example, machine learning
Score afterwards can be 0.98;After the score of each data sample is obtained, descending sequence can be carried out to score, in addition,
Ascending sequence can also be carried out to score, particular determination is not done to this in this illustrative embodiments;Next, can be with base
The appraisal result of stepping scoring in step S12, it is determined that carrying out the score threshold of stepping to scoring.
, can be to this after the score of 1000 parts of medical record datas is determined still by taking medical record data in medical industry as an example
1000 scores carry out descending sequence.Next, by taking the scoring of 1-5 shelves as an example, based on the specific fraction of 1000 scores,
Such as data of the score more than 0.9 can be defined as 1 grade, data of the score below 0.9 and more than 0.7 be defined as 2 grades,
Data point below 0.7 and more than 0.6 be defined as 3 grades, data of the score below 0.6 and more than 0.4 be defined as 4 grades, with
And data of the score below 0.4 are defined as 5 grades.Thus, it is possible to the score threshold between 1 grade and 2 grades is defined as 0.9,
Score threshold between 2 grades and 3 grades is defined as 0.7, the score threshold between 3 grades and 4 grades is defined as to 0.6, by 4 grades and 5
Score threshold between shelves is defined as 0.4.Summary, the score after the machine learning of data sample and data sample can be obtained
Originally the relation between the key message included, in certain embodiments, after this relation is considered progress machine training
The training pattern of generation.
It is easily understood that above-mentioned schematically illustrate to be trained appraisal result and key message vector
Process, however, not limited to this, developer can also determine score threshold according to other modes, for example, to 1000
Divide after carrying out descending sequence, five deciles are carried out to score, it is descending respectively to be defined as 1-5 shelves, now, 1 grade of number
Quantity according to sample can be, for example, 216, and the score after machine learning is all higher than being equal to 0.93;The quantity of 2 grades of data sample
Can be, for example, 511, the score after machine learning is less than 0.93 and more than or equal to 0.78;The quantity of 3 grades of data sample can be with
For example, 127, the score after machine learning is less than 0.78 and more than or equal to 0.63;The quantity of 4 grades of data sample can be such as
For 101, the score after machine learning is less than 0.63 and more than or equal to 0.48;The quantity of 5 grades of data sample can be, for example, 45,
Score after machine learning is less than 0.48.Now, the score threshold of 1-5 shelves can be respectively 0.93,0.78,0.63,0.48.This
The open rule to specific generation training pattern does not do particular determination, can be by developer's self-defining.
In step S18, obtain data to be evaluated and be directed to training pattern described in the data run to be evaluated, to obtain
The appraisal result of the data to be evaluated is as evaluation result.
Step S10 to step S16 is directed to data sample, and data sample can be obtained by extracting at random.
After generating training pattern, when needing to carry out data evaluation, server can obtain data to be evaluated and run the training pattern
To obtain the appraisal result of data to be evaluated, and the evaluation result using the appraisal result as the data to be evaluated.That is,
It is possible, firstly, to judge that data to be evaluated whether there is the key message determined in step S10, and treated according to judged result generation
The key message vector of evaluating data.Next, the key of data to be evaluated is determined according to the training pattern generated in step S16
Score corresponding to information vector, and the appraisal result of data to be evaluated is determined according to the concrete numerical value of score, and the scoring is tied
Fruit is as evaluation result.
Still by taking medical record data in medical industry as an example, it is, for example, for the score after data run training pattern to be evaluated
0.88, then it is defined as by less than 0.9 and the data more than 0.7 in 2 grades of example, can be by the scoring knot of the data to be evaluated
Fruit is defined as 2 grades, and using 2 grades of evaluation results as the data to be evaluated.
The whole process of one embodiment of the data evaluation method of the disclosure is illustrated below with reference to Fig. 2.
In step S201, server according to《Medical record writing fundamental norms》The first key message is determined, wherein, the first key message includes
Information based on data integrity;In step S203, server can obtain to be referred to by medical expert according to clinical path, diagnosis and treatment
The second key message that south etc. is determined, wherein, the second key message includes indication information corresponding with hypertension;In step
In S205, server can take 1000 parts of hypertension medical record datas, and point of 1-5 shelves is carried out by the medical expert in hypertension field
Shelves scoring;In step S207, server can determine the first key message that 1000 parts of medical record datas include and second crucial
Information, and generate key message vector;In step S209, server can pass through scoring knot of the regression algorithm to step S205
The key message vector of fruit and step S207 generations is trained to generate training pattern;In step S211, server can be with
Training pattern is run for medical record data to be evaluated, the appraisal result to obtain medical record data to be evaluated is tied as evaluation
Fruit.
By taking medical record data in medical industry as an example, the data evaluation method described in the disclosure, on the one hand, in medical expert couple
After medical record data sample is scored, no longer there is the process artificially participated in this programme, but to case history by way of software
Data are analyzed, scored, and solve the problems, such as that manpower is constantly put into;On the other hand, included in key message complete based on data
In the scheme of the information of whole property, medical record information integrated degree can be evaluated;Another aspect, by the medical science of each disease areas
Expert determines the second key message, and medical record data is evaluated based on the second key message, it is ensured that medical record data towards
The professional evaluation of disease;Another further aspect, by evaluating medical record data, researcher, which can extract, evaluates high case history
Studied, realize the purpose for preferably utilizing historical therapeutic experience, while contribute to the information-based development of medical industry.This
Outside, this programme can substitute the mode of related personnel (for example, staff of Record room) subjective assessment medical record data, therefore,
The problem of medical record data evaluation can be avoided unstable, and reduce the risk of medical record data error evaluation.
It should be noted that although describing each step of method in the disclosure with particular order in the accompanying drawings, still, this is simultaneously
Undesired or hint must perform these steps according to the particular order, or have to carry out the step ability shown in whole
Realize desired result.It is additional or alternative, it is convenient to omit some steps, multiple steps are merged into a step and performed,
And/or a step is decomposed into execution of multiple steps etc..
Further, a kind of data evaluation device is additionally provided in this example embodiment.
Fig. 3 diagrammatically illustrates the block diagram of the data evaluation device of the illustrative embodiments of the disclosure.With reference to figure 3,
Key message determining module 31, data sample can be included according to the data evaluation device 3 of the illustrative embodiments of the disclosure
Grading module 33, key message vector generation module 35, training pattern generation module 37 and data evaluation module 39, wherein:
Key message determining module 31, the key message being determined in data;
Data sample grading module 33, can be used for obtain predetermined number data sample and be supplied to rating staff so as to
The rating staff scores each data sample, obtains the appraisal result of each data sample;
Key message vector generation module 35, it can be used for judging that each data sample whether there is the key message
And the key message vector according to judged result generation for each data sample;
Training pattern generation module 37, can be used for by regression algorithm to the appraisal result and the key message to
Amount is trained to generate training pattern;And
Data evaluation module 39, it can be used for obtaining data to be evaluated and for training described in the data run to be evaluated
Model, the appraisal result to obtain the data to be evaluated are used as evaluation result.
In the data evaluation device of the disclosure, obtain the appraisal result of data sample and generate the crucial letter of data sample
Breath vector, is trained by regression algorithm to the appraisal result and key message vector of data sample, and according to the instruction of generation
White silk model is treated evaluating data and evaluated, on the one hand, after rating staff artificially scores data sample, this programme is not
The process artificially participated in again be present, solve the problems, such as to need artificial constantly progress data evaluation in the prior art;On the other hand,
Due to reducing the process artificially participated in, therefore, it is possible to reduce because the data evaluation that rating staff's subjective factor is brought is unstable
The problem of determining;Another further aspect, due to reducing artificial participation, the efficiency of data evaluation can be improved.
According to the exemplary embodiment of the disclosure, with reference to figure 4, training pattern generation module 37 can include score and obtain list
Member 401 and score threshold determining unit 403, wherein:
Score acquiring unit 401, can be used for by regression algorithm to the appraisal result of each data sample and
The key message vector is fitted analysis to obtain the score of each data sample;
Score threshold determining unit 403, it can be used for the appraisal result according to each data sample and combine each
The score of the data sample determines to carry out scoring the score threshold of stepping.
According to the exemplary embodiment of the disclosure, the key message includes the first key message and/or the second crucial letter
Breath;
Wherein, first key message includes the information based on data integrity, second key message include with
Indication information corresponding to evaluative dimension.
According to the exemplary embodiment of the disclosure, with reference to figure 5, key message determining module 31 can include the first crucial letter
The key message determining module 503 of determining module 501 and second is ceased, wherein:
First key message determining unit 501, it can be used for determining first key message according to preset data specification;
And/or
Second key message determining unit 503, it can be used for the indication information that the rating staff specifies being defined as institute
State the second key message.
Because each functional module of the program analysis of running performance device of embodiment of the present invention is invented with the above method
It is identical in embodiment, therefore will not be repeated here.
In an exemplary embodiment of the disclosure, a kind of computer-readable recording medium is additionally provided, is stored thereon with energy
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product, it includes program code, when described program product is run on the terminal device, institute
State program code be used for make the terminal device perform described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
With reference to shown in figure 6, the program product for being used to realize the above method according to the embodiment of the present invention is described
600, it can use portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as run on PC.However, the program product not limited to this of the present invention, in this document, readable storage medium storing program for executing can be with
Be it is any include or the tangible medium of storage program, the program can be commanded execution system, device either device use or
It is in connection.
Described program product can use any combination of one or more computer-readable recording mediums.Computer-readable recording medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any combination above.The more specifically example of readable storage medium storing program for executing is (non exhaustive
List) include:It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more wires, read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media can be including the data-signal in a base band or as carrier wave part propagation, its
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie beyond readable storage medium storing program for executing
Matter, the computer-readable recording medium can send, propagate either transmit for used by instruction execution system, device or device or and its
The program of combined use.
The program code included on computer-readable recording medium can be transmitted with any appropriate medium, including but not limited to wirelessly, be had
Line, optical cable, RF etc., or above-mentioned any appropriate combination.
Can being combined to write the program operated for performing the present invention with one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., include routine
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
Perform on computing device, partly perform on a user device, the software kit independent as one performs, is partly calculated in user
Its upper side point is performed or performed completely in remote computing device or server on a remote computing.It is remote being related to
In the situation of journey computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide area network
(WAN) user calculating equipment, is connected to, or, it may be connected to external computing device (such as utilize ISP
To pass through Internet connection).
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can realize the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be implemented as following form, i.e.,:It is complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.), or hardware and software, can unite here
Referred to as " circuit ", " module " or " system ".
The electronic equipment 700 according to the embodiment of the invention is described referring to Fig. 7.The electronics that Fig. 7 is shown
Equipment 700 is only an example, should not bring any restrictions to the function and use range of the embodiment of the present invention.
As shown in fig. 7, electronic equipment 700 is showed in the form of universal computing device.The component of electronic equipment 700 can wrap
Include but be not limited to:Above-mentioned at least one processing unit 710, above-mentioned at least one memory cell 720, connection different system component
The bus 730 of (including memory cell 720 and processing unit 710), display unit 740.
Wherein, the memory cell is had program stored therein code, and described program code can be held by the processing unit 710
OK so that the processing unit 710 performs various according to the present invention described in above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 710 can perform step S10 as shown in fig. 1:Determine number
Key message in;Step S12:Obtain predetermined number data sample and be supplied to rating staff so as to the rating staff
Each data sample is scored, obtains the appraisal result of each data sample;Step S14:Judge each data
Key message vector of the sample with the presence or absence of the key message and according to judged result generation for each data sample;Step
S16:The appraisal result and the key message vector are trained to generate training pattern by regression algorithm;And step
Rapid S18:Obtain data to be evaluated and be directed to training pattern described in the data run to be evaluated, to obtain the data to be evaluated
Appraisal result as evaluation result.
Memory cell 720 can include the computer-readable recording medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 7201 and/or cache memory unit 7202, it can further include read-only memory unit (ROM) 7203.
Memory cell 720 can also include program/utility with one group of (at least one) program module 7205
7204, such program module 7205 includes but is not limited to:Operating system, one or more application program, other program moulds
Block and routine data, the realization of network environment may be included in each or certain combination in these examples.
Bus 730 can be to represent the one or more in a few class bus structures, including memory cell bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 700 can also be with one or more external equipments 800 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment communication interacted with the electronic equipment 700 can be also enabled a user to one or more, and/or with causing
Any equipment that the electronic equipment 700 can be communicated with one or more of the other computing device (such as router, modulation /demodulation
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 750.Also, electronic equipment 700 can be with
By network adapter 760 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As illustrated, network adapter 760 is communicated by bus 730 with other modules of electronic equipment 700.
It should be understood that although not shown in the drawings, can combine electronic equipment 700 does not use other hardware and/or software module, including but not
It is limited to:Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can be realized by software, can also be realized by way of software combines necessary hardware.Therefore, according to the disclosure
The technical scheme of embodiment can be embodied in the form of software product, the software product can be stored in one it is non-volatile
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are to cause a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is performed according to disclosure embodiment
Method.
In addition, above-mentioned accompanying drawing is only the schematic theory of the processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limitation purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings was not intended that or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be performed either synchronously or asynchronously in multiple modules.
It should be noted that although some modules or list of the equipment for action executing are referred in above-detailed
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Either the feature of unit and function can embody module in a module or unit.A conversely, above-described mould
Either the feature of unit and function can be further divided into being embodied by multiple modules or unit block.
Those skilled in the art will readily occur to the disclosure its after considering specification and putting into practice invention disclosed herein
His embodiment.The application is intended to any modification, purposes or the adaptations of the disclosure, these modifications, purposes or
Adaptations follow the general principle of the disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.Description and embodiments are considered only as exemplary, and the true scope of the disclosure and spirit are by claim
Point out.
It should be appreciated that the precision architecture that the disclosure is not limited to be described above and is shown in the drawings, and
And various modifications and changes can be being carried out without departing from the scope.The scope of the present disclosure is only limited by appended claim.
Claims (10)
- A kind of 1. data evaluation method, it is characterised in that including:Determine the key message in data;Obtain predetermined number data sample and be supplied to rating staff to enter so as to the rating staff to each data sample Row scoring, obtains the appraisal result of each data sample;Each data sample is judged with the presence or absence of the key message and according to judged result generation for each data sample Key message vector;The appraisal result and the key message vector are trained to generate training pattern by regression algorithm;AndObtain data to be evaluated and be directed to training pattern described in the data run to be evaluated, to obtain the data to be evaluated Appraisal result is as evaluation result.
- 2. data evaluation method according to claim 1, it is characterised in that by regression algorithm to the appraisal result and The key message vector be trained including:Analysis is fitted to the appraisal result of each data sample and the key message vector by regression algorithm To obtain the score of each data sample;Determine to carry out scoring according to the appraisal result of each data sample and with reference to the score of each data sample The score threshold of stepping.
- 3. data evaluation method according to claim 1 or 2, it is characterised in that it is crucial that the key message includes first Information and/or the second key message;Wherein, first key message includes the information based on data integrity, and second key message includes and evaluation Indication information corresponding to dimension.
- 4. data evaluation method according to claim 3, it is characterised in that determine that the key message in data includes:First key message is determined according to preset data specification;And/orThe indication information that the rating staff specifies is defined as second key message.
- A kind of 5. data evaluation device, it is characterised in that including:Key message determining module, for determining the key message in data;Data sample grading module, for obtaining predetermined number data sample and being supplied to rating staff so as to the scoring people Member scores each data sample, obtains the appraisal result of each data sample;Key message vector generation module, for judging each data sample with the presence or absence of the key message and according to judgement As a result key message vector of the generation for each data sample;Training pattern generation module, for being trained by regression algorithm to the appraisal result and the key message vector To generate training pattern;AndData evaluation module, for obtaining data to be evaluated and being directed to training pattern described in the data run to be evaluated, with To the data to be evaluated appraisal result as evaluation result.
- 6. data evaluation device according to claim 5, it is characterised in that the training pattern generation module includes:Score acquiring unit, for passing through the appraisal result of the regression algorithm to each data sample and the key message Vector is fitted analysis to obtain the score of each data sample;Score threshold determining unit, for the appraisal result according to each data sample and with reference to each data sample Score determine to scoring carry out stepping score threshold.
- 7. the data evaluation device according to claim 5 or 6, it is characterised in that it is crucial that the key message includes first Information and/or the second key message;Wherein, first key message includes the information based on data integrity, and second key message includes and evaluation Indication information corresponding to dimension.
- 8. data evaluation device according to claim 7, it is characterised in that the key message determining module includes:First key message determining unit, for determining first key message according to preset data specification;And/orSecond key message determining unit, the indication information for the rating staff to be specified are defined as the described second crucial letter Breath.
- 9. a kind of storage medium, is stored thereon with computer program, it is characterised in that the computer program is executed by processor Data evaluation method any one of Shi Shixian Claims 1-4.
- 10. a kind of electronic equipment, it is characterised in that including:Processor;AndMemory, for storing the executable instruction of the processor;Wherein, the processor is configured to come any one of perform claim requirement 1 to 4 via the execution executable instruction Data evaluation method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711006245.5A CN107845408B (en) | 2017-10-25 | 2017-10-25 | Data evaluation method and device, storage medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711006245.5A CN107845408B (en) | 2017-10-25 | 2017-10-25 | Data evaluation method and device, storage medium and electronic device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107845408A true CN107845408A (en) | 2018-03-27 |
CN107845408B CN107845408B (en) | 2020-10-27 |
Family
ID=61663103
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711006245.5A Active CN107845408B (en) | 2017-10-25 | 2017-10-25 | Data evaluation method and device, storage medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107845408B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109190879A (en) * | 2018-07-18 | 2019-01-11 | 阿里巴巴集团控股有限公司 | A kind of trained method and device for adapting assessment of levels model, evaluation reorganization level |
CN109614987A (en) * | 2018-11-08 | 2019-04-12 | 北京字节跳动网络技术有限公司 | More disaggregated model optimization methods, device, storage medium and electronic equipment |
CN109858812A (en) * | 2019-01-31 | 2019-06-07 | 泰康保险集团股份有限公司 | Human Resources Management Method, device, medium and electronic equipment based on block chain |
CN111949847A (en) * | 2020-08-14 | 2020-11-17 | 中国工商银行股份有限公司 | Information evaluation method, information evaluation device, computer system, and medium |
CN115269932A (en) * | 2022-09-29 | 2022-11-01 | 江西联创精密机电有限公司 | Training scoring method and device for simulation training equipment, storage medium and equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105809360A (en) * | 2016-03-16 | 2016-07-27 | 北京银讯财富信息技术有限公司 | P2P industry risk assessment method |
CN105824806A (en) * | 2016-06-13 | 2016-08-03 | 腾讯科技(深圳)有限公司 | Quality evaluation method and device for public accounts |
US20160364481A1 (en) * | 2013-07-30 | 2016-12-15 | Netflix, Inc. | Media content rankings for discovery of novel content |
CN106294363A (en) * | 2015-05-15 | 2017-01-04 | 厦门美柚信息科技有限公司 | A kind of forum postings evaluation methodology, Apparatus and system |
-
2017
- 2017-10-25 CN CN201711006245.5A patent/CN107845408B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160364481A1 (en) * | 2013-07-30 | 2016-12-15 | Netflix, Inc. | Media content rankings for discovery of novel content |
CN106294363A (en) * | 2015-05-15 | 2017-01-04 | 厦门美柚信息科技有限公司 | A kind of forum postings evaluation methodology, Apparatus and system |
CN105809360A (en) * | 2016-03-16 | 2016-07-27 | 北京银讯财富信息技术有限公司 | P2P industry risk assessment method |
CN105824806A (en) * | 2016-06-13 | 2016-08-03 | 腾讯科技(深圳)有限公司 | Quality evaluation method and device for public accounts |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109190879A (en) * | 2018-07-18 | 2019-01-11 | 阿里巴巴集团控股有限公司 | A kind of trained method and device for adapting assessment of levels model, evaluation reorganization level |
CN109190879B (en) * | 2018-07-18 | 2020-08-11 | 阿里巴巴集团控股有限公司 | Method and device for training adaptation level evaluation model and evaluating adaptation level |
US11074897B2 (en) | 2018-07-18 | 2021-07-27 | Advanced New Technologies Co., Ltd. | Method and apparatus for training adaptation quality evaluation model, and method and apparatus for evaluating adaptation quality |
US11367424B2 (en) | 2018-07-18 | 2022-06-21 | Advanced New Technologies Co., Ltd. | Method and apparatus for training adaptation quality evaluation model, and method and apparatus for evaluating adaptation quality |
CN109614987A (en) * | 2018-11-08 | 2019-04-12 | 北京字节跳动网络技术有限公司 | More disaggregated model optimization methods, device, storage medium and electronic equipment |
CN109858812A (en) * | 2019-01-31 | 2019-06-07 | 泰康保险集团股份有限公司 | Human Resources Management Method, device, medium and electronic equipment based on block chain |
CN109858812B (en) * | 2019-01-31 | 2021-08-24 | 泰康保险集团股份有限公司 | Human resource management method, device, medium and electronic equipment based on block chain |
CN111949847A (en) * | 2020-08-14 | 2020-11-17 | 中国工商银行股份有限公司 | Information evaluation method, information evaluation device, computer system, and medium |
CN115269932A (en) * | 2022-09-29 | 2022-11-01 | 江西联创精密机电有限公司 | Training scoring method and device for simulation training equipment, storage medium and equipment |
Also Published As
Publication number | Publication date |
---|---|
CN107845408B (en) | 2020-10-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Paranjape et al. | Introducing artificial intelligence training in medical education | |
Ferryman et al. | Fairness in precision medicine | |
CN107845408A (en) | Data evaluation method and device, storage medium and electronic equipment | |
Alam | The Secret Sauce of Student Success: Cracking the Code by Navigating the Path to Personalized Learning with Educational Data Mining | |
Kanevsky et al. | Big data and machine learning in plastic surgery: a new frontier in surgical innovation | |
Chan et al. | A framework for characterizing eHealth literacy demands and barriers | |
Chiesa-Estomba et al. | Exploring the potential of Chat-GPT as a supportive tool for sialendoscopy clinical decision making and patient information support | |
US20200279147A1 (en) | Method and apparatus for intelligently recommending object | |
CN111145905B (en) | Target decision model construction method and device, electronic equipment and storage medium | |
TW201535307A (en) | An avatar-based charting method and system for assisted diagnosis | |
CN115458113A (en) | Medical record generation method, system, storage medium and electronic equipment | |
Sai et al. | Generative ai for transformative healthcare: A comprehensive study of emerging models, applications, case studies and limitations | |
Choi et al. | Artificial intelligence in facial plastic surgery: a review of current applications, future applications, and ethical considerations | |
Kugener et al. | Utility of the simulated outcomes following carotid artery laceration video data set for machine learning applications | |
Srinivas et al. | Machine learning and artificial intelligence in surgical research | |
Riechert et al. | The application of activity theory to explain collaborative technology use in healthcare: The case of a chemotherapy ordering system | |
Kay | Foundations for Human-AI teaming for self-regulated learning with explainable AI (XAI) | |
Varghese et al. | Deciphering the role of artificial intelligence in health care, learning and development | |
CN109597989A (en) | Diagnose word normalizing method and device, storage medium, electronic equipment | |
Ma et al. | Towards human-ai deliberation: Design and evaluation of llm-empowered deliberative ai for ai-assisted decision-making | |
Penteado et al. | Detecting behavioral trajectories in continued education online courses | |
Sittig | Clinical Informatics Literacy: 5000 Concepts that Every Informatician Should Know | |
Tamalvanan | Pragmatism in transforming surgical workplace with artificial intelligence | |
Sadeghi et al. | Predicting quality of life based on mental health state: A machine learning approach using Urban-HEART 2 | |
CN107731267A (en) | Targeted customer determines method and device, storage medium, electronic equipment |
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 |