CN105468920B - A kind of method for establishing model and application method for evaluating novelty assessment report quality - Google Patents
A kind of method for establishing model and application method for evaluating novelty assessment report quality Download PDFInfo
- Publication number
- CN105468920B CN105468920B CN201510890524.7A CN201510890524A CN105468920B CN 105468920 B CN105468920 B CN 105468920B CN 201510890524 A CN201510890524 A CN 201510890524A CN 105468920 B CN105468920 B CN 105468920B
- Authority
- CN
- China
- Prior art keywords
- novelty
- assessment report
- novelty assessment
- pertinent literature
- evaluation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000011156 evaluation Methods 0.000 claims abstract description 47
- 238000012417 linear regression Methods 0.000 claims abstract description 26
- 238000011478 gradient descent method Methods 0.000 claims abstract description 8
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 32
- 230000017105 transposition Effects 0.000 claims description 11
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 230000006870 function Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- 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 method for establishing model for evaluating novelty assessment report quality, comprising: extracts the corresponding retrieval type of more novelty assessment reports, pertinent literature and retrieval conclusion；The corresponding characteristic parameter of novelty assessment report is obtained according to each retrieval type, pertinent literature and retrieval conclusion；Expert is obtained to the scoring information of novelty assessment report；The relationship of the characteristic parameter Yu the scoring information is established by the way of linear regression model (LRM)；The linear regression model (LRM) for using the characteristic parameter and the scoring information to establish is trained using gradient descent method to obtain the model of the evaluation novelty assessment report quality.It can be seen that in the above process, it is only necessary to which expert gives a mark to the novelty assessment report of the limited quantity of selection, and the model can be applied in other novelty assessment reports to be evaluated, therefore, saves human cost.In addition, the present invention also provides a kind of application methods for evaluating novelty assessment report quality.
Description
Technical field
The present invention relates to scientific and technical literatures to look into new technical field, builds more particularly to a kind of model for evaluating novelty assessment report quality
Cube method and application method.
Background technique
It is continuously increased with new demand is looked into scientific and technical literature, the requirement to scientific and technical literature current awareness search work is constantly promoted, urgently
A kind of method for needing quantitative evaluation sci-tech novelty retrieval report quality, objectively to evaluate the quality of Cha Xinyuan current awareness search work, and mentions
Rise the management level to Cha Xinyuan current awareness search work.
Popular say of novelty assessment report is the retrieval work done in the record of existing document to given document, for example, right
Given document carries out duplicate checking etc., makes relevant report to given document by certain retrieval work, such as repeated,
Similitude, novelty etc..Since novelty assessment report is the final accounts done to given document, to novelty assessment report
Quality proposes higher requirement.
It in existing novelty assessment report evaluation method, is built upon on the basis of expert estimation, such as fuzzy comprehensive evoluation mould
Type, analytic hierarchy process (AHP), entropy assessment belong to the method based on expert estimation.Workflow is as follows:
The first step acquires N (usual N≤10) piece novelty assessment report, sets M (usual M≤15) a evaluation index；
Second step, inviting expert is that M evaluation index of every report is given a mark one by one, obtains the matrix A of a N*M；
Third step judges the significance level of M index by matrix analysis, and assigns its weight；
4th step, for the marking that the N+1 novelty assessment report, expert carry out it in M evaluation index, according to third step
It is middle to solve obtained index weights, summation is weighted to M marking to get the quality of this novelty assessment report is arrived.
For the above method, it is strictly dependent on marking of the human expert under different indexs, although can be from marking square
Automatic calculation obtains the weight of different indexs in battle array, but the subjectivity of expert estimation will have a direct impact on the objective of evaluation result
With it is reasonable.Meanwhile this kind of methods are not applied for large-scale novelty assessment report quality evaluation work.In addition, working as novelty assessment report
When measuring more, the cost of labor needed can be very big.
It can be seen that how to improve objectivity and accuracy, and reduce cost of labor when evaluating novelty assessment report quality
It is those skilled in the art's urgent problem to be solved.
Summary of the invention
The object of the present invention is to provide a kind of method for establishing model for evaluating novelty assessment report quality, for looking into new report when evaluation
When accusing quality, objectivity and accuracy how are improved, and reduce cost of labor.
In order to solve the above technical problems, the present invention provides a kind of method for establishing model for evaluating novelty assessment report quality, comprising:
Extract the corresponding retrieval type of more novelty assessment reports, pertinent literature and retrieval conclusion；
The corresponding feature of the novelty assessment report is obtained according to each retrieval type, the pertinent literature and the retrieval conclusion
Parameter；
Expert is obtained to the scoring information of the novelty assessment report；
The relationship of the characteristic parameter Yu the scoring information is established by the way of linear regression model (LRM)；
The linear regression model (LRM) for using the characteristic parameter and the scoring information to establish is carried out using gradient descent method
Training obtains the model of the evaluation novelty assessment report quality.
Preferably, the characteristic parameter includes:
The retrieval type of the novelty assessment report and the degree of correlation of novelty items；
The degree of correlation of the pertinent literature of the novelty assessment report and the novelty items；
The technorati authority of the pertinent literature of the novelty assessment report；
The accuracy rate of the pertinent literature of the novelty assessment report；
The recall rate of the pertinent literature of the novelty assessment report；
The correctness of the retrieval conclusion of the novelty assessment report.
Preferably, the retrieval type of the novelty assessment report and the degree of correlation of novelty items are obtained by calculation formula；
Wherein, calculation formula is
wiKeyword set W={ the w used for the retrieval type1,w2,…,wmIn i-th of keyword, wiFor wi's
Vector indicates；w′jKeyword set W '={ the w ' provided for novelty items d '1,w’2,…,w’nIn j-th of keyword, w 'j
For w 'jVector indicate；p(wi,w′j) indicate keyword wi、w′jCo-occurrence probabilities in the same document, p (wi) and p (w 'j)
Respectively indicate keyword wi、w′jIn the prior probability that document occurs, T is the transposition of vector.
Preferably, the pertinent literature of the novelty assessment report and the degree of correlation of the novelty items are obtained by calculation formula；
Wherein, calculation formula are as follows:
D is the set for the pertinent literature retrieved in novelty assessment report；dkFor the kth piece pertinent literature in D；D ' is to look into new item
Mesh；dkFor dkDocument vector indicate；The document vector that d ' is d ' indicates；| D | indicate the quantity of document in set D；T is vector
Transposition.
Preferably, the technorati authority of the pertinent literature of the novelty assessment report by look into new document publication source, publish the time limit,
Cited rate obtains.
Preferably, the accuracy rate of the pertinent literature of the novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows: Precision=| D1|/|D|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the archives in D with novelty items true correlation
It closes, | D1|, | D | respectively indicate set D1, quantity of document in D.
Preferably, the recall rate of the pertinent literature of the novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows: Recall=| D1|/|D2|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the archives in D with novelty items true correlation
It closes, D2For the literature collection in searchable data resource with novelty items true correlation, | D |, | D1|、|D2| respectively indicate collection
Close D, D1、D2In quantity of document.
Preferably, the correctness of the retrieval conclusion of the novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows:
tiFor i-th of technical essential of novelty items；akFor the literature summary of k-th of pertinent literature in novelty assessment report；ti
For tiParagraph vector indicate；akFor akParagraph vector indicate；T is the transposition of vector.
Preferably, the model of the evaluation novelty assessment report quality are as follows:
Wherein, ω=[ω0,ω1,...,ω6]TFor model parameter, pass through formulaThe minimum value for solving J obtains；X=[0, x1,...,x6] it is described
The characteristic parameter of novelty assessment report；T is the transposition of vector.
A kind of application method for evaluating novelty assessment report quality, based on the model of the described evaluation novelty assessment report quality,
Include:
Extract retrieval type, pertinent literature and the retrieval conclusion in novelty assessment report to be evaluated；
The mould of the evaluation novelty assessment report quality is obtained according to the retrieval type, the pertinent literature and the retrieval conclusion
The corresponding characteristic parameter of type；
The characteristic parameter is inputted in the model of the evaluation novelty assessment report quality to obtain corresponding evaluation score.
The method for establishing model of evaluation novelty assessment report quality provided by the present invention is obtained based on more novelty assessment reports
The retrieval type, pertinent literature and retrieval conclusion of every novelty assessment report are taken, then every is obtained by above three parameter and looks into new report
Corresponding characteristic parameter is accused, evaluation is obtained using gradient descent method as training sample using characteristic parameter and the scoring information of expert and is looked into
Newly reported model.It can be seen that in the above process, it is only necessary to which expert beats the novelty assessment report of the limited quantity of selection
Point, and the model can be applied in other novelty assessment reports to be evaluated, therefore, save human cost.
Detailed description of the invention
In order to illustrate the embodiments of the present invention more clearly, attached drawing needed in the embodiment will be done simply below
It introduces, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ordinary skill people
For member, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow chart of method for establishing model for evaluating novelty assessment report quality provided by the invention；
Fig. 2 is a kind of flow chart of application method for evaluating novelty assessment report quality provided by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, those of ordinary skill in the art are without making creative work, obtained every other
Embodiment belongs to the scope of the present invention.
Core of the invention is to provide a kind of method for establishing model and application method for evaluating novelty assessment report quality.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.
Embodiment one
Fig. 1 is a kind of flow chart of method for establishing model for evaluating novelty assessment report quality provided by the invention.Such as Fig. 1 institute
Show, the method for establishing model of evaluation novelty assessment report quality includes:
S10: the corresponding retrieval type of more novelty assessment reports, pertinent literature and retrieval conclusion are extracted.
In specific implementation, need to choose more novelty assessment reports, it is to be appreciated that the quantity of the novelty assessment report of selection is got over
More, then the model of the evaluation novelty assessment report quality obtained is better.For example, 100 can be chosen.It is corresponding to obtain every novelty assessment report
Retrieval type, pertinent literature and retrieval conclusion.Retrieval type is the search strategy that novelty retriever is used when looking into new, using some passes
The disjunctive normal form of keyword indicates.Pertinent literature be novelty retriever obtained when using retrieval type searching database resource, via
Document relevant with novelty items is thought in novelty retriever judgement.Retrieval conclusion is novelty retriever according to novelty items and related text
The innovative or difference type conclusion about the technical essential in novelty items that the manual analysis offered obtains.
S11: it is corresponding that the novelty assessment report is obtained according to each retrieval type, the pertinent literature and the retrieval conclusion
Characteristic parameter.
According to the retrieval type that step S10 is obtained, pertinent literature and retrieval conclusion obtain the corresponding feature of every novelty assessment report
Parameter.It should be noted that then obtain is 100 groups of retrieval types, pertinent literature, Cha Xinjie if there is 100 novelty assessment reports
By and 100 groups of characteristic parameters.
S12: expert is obtained to the scoring information of the novelty assessment report.
It is the novelty assessment report marking chosen by expert, obtains scoring information.It should be noted that expert here can be with
It is given a mark by being mostly expert for it, for example, 10 experts can be selected, then a novelty assessment report just obtains 10 scoring informations,
As soon as it is of course also possible to be given a mark by expert for it, then a novelty assessment report obtains 1 scoring information.Expert is new for looking into
The scoring process of report can be carried out using index in the prior art, wouldn't be repeated here.
S13: the relationship of characteristic parameter and scoring information is established by the way of linear regression model (LRM).
The pass between characteristic parameter and scoring information is established by the way of linear regression model (LRM) when obtaining scoring information
System is to obtain linear regression model (LRM).
S14: the linear regression model (LRM) for using characteristic parameter and scoring information to establish is trained using gradient descent method
Obtain the model of the evaluation novelty assessment report quality.
Learning training is carried out to the linear regression model (LRM) that step S13 is obtained using gradient descent method and obtains evaluation novelty assessment report
The model of quality.
The method for establishing model of evaluation novelty assessment report quality provided in this embodiment is obtained based on more novelty assessment reports
The retrieval type, pertinent literature and retrieval conclusion of every novelty assessment report are taken, then every is obtained by above three parameter and looks into new report
Corresponding characteristic parameter is accused, with the linear regression model (LRM) that characteristic parameter and the scoring information of expert are established, using gradient descent method
Linear regression model (LRM) is trained to obtain the model of evaluation novelty assessment report.It can be seen that in the above process, it is only necessary to specially
Family gives a mark to the novelty assessment report of the limited quantity of selection, and the model can be applied to other novelty assessment reports to be evaluated
In, therefore, save human cost.
Wherein, the characteristic parameter includes:
The retrieval type of the novelty assessment report and the degree of correlation of novelty items；
The degree of correlation of the pertinent literature of the novelty assessment report and the novelty items；
The technorati authority of the pertinent literature of the novelty assessment report；
The accuracy rate of the pertinent literature of the novelty assessment report；
The recall rate of the pertinent literature of the novelty assessment report；
The correctness of the retrieval conclusion of the novelty assessment report.
In specific implementation, according to retrieval type, pertinent literature, the available multiple features of three parameters of retrieval conclusion, originally
In embodiment, the retrieval type of novelty assessment report and the degree of correlation of novelty items, the phase of novelty assessment report are obtained by above three parameter
Close the degree of correlation of document and the novelty items, the technorati authority of the pertinent literature of novelty assessment report, novelty assessment report pertinent literature
Accuracy rate, the recall rate of the pertinent literature of novelty assessment report, novelty assessment report retrieval conclusion correctness.
Specifically, the retrieval type of novelty assessment report and the degree of correlation of novelty items are obtained by calculation formula；
Wherein, calculation formula is
wiKeyword set W={ the w used for the retrieval type1,w2,…,wmIn i-th of keyword, wiFor wi's
Vector indicates；w′jKeyword set W '={ the w ' provided for novelty items d '1,w’2,…,w’nIn j-th of keyword, w 'j
For w 'jVector indicate；p(wi,w′j) indicate keyword wi、w′jCo-occurrence probabilities in the same document, p (wi) and p (w 'j)
Respectively indicate keyword wi、w′jIn the prior probability that document occurs, T is the transposition of vector.
The pertinent literature of novelty assessment report and the relatedness computation formula of the novelty items obtain；
Wherein, calculation formula are as follows:
D is the set for the pertinent literature retrieved in novelty assessment report；dkFor the kth piece pertinent literature in D；D ' is to look into new item
Mesh；dkFor dkDocument vector indicate；The document vector that d ' is d ' indicates；| D | indicate the quantity of document in set D；T is vector
Transposition.
The technorati authority of the pertinent literature of novelty assessment report is by looking into the publication source of new document, publishing the time limit, Cited rate acquisition.
The accuracy rate of the pertinent literature of novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows: Precision=| D1|/|D|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the archives in D with novelty items true correlation
It closes, | D1|, | D | respectively indicate set D1, quantity of document in D.
The recall rate of the pertinent literature of novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows: Recall=| D1|/|D2|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the archives in D with novelty items true correlation
It closes, D2For the literature collection in searchable data resource with novelty items true correlation, | D |, | D1|、|D2| respectively indicate collection
Close D, D1、D2In quantity of document.
The correctness of the retrieval conclusion of novelty assessment report is obtained by calculation formula；
Wherein, calculation formula are as follows:
tiFor i-th of technical essential of novelty items；akFor the literature summary of k-th of pertinent literature in novelty assessment report；ti
For tiParagraph vector indicate；akFor akParagraph vector indicate；T is the transposition of vector.
It should be noted that the technical essential of the correctness of the retrieval conclusion of novelty assessment report and retrieval conclusion and novelty items
Difference type, innovative type it is related.Difference type, the innovative type of the technical essential of novelty items are obtained by calculation formula
It arrives；Wherein, calculation formula are as follows:
Evaluate the model of novelty assessment report quality are as follows: H is threshold parameter.
Wherein, ω=[ω0,ω1,...,ω6]TFor model parameter, pass through formulaThe minimum value for solving J obtains；X=[0, x1,...,x6] it is described
The characteristic parameter of novelty assessment report；T is the transposition of vector.
J is the objective function of setting, is solved by using gradient descent method to J, the corresponding mould when making J minimum
Shape parameter ω has just obtained the model of evaluation novelty assessment report quality.
Embodiment two
Fig. 2 is a kind of flow chart of application method for evaluating novelty assessment report quality provided by the invention.Evaluation is looked into new
The application method of report quality includes:
S20: retrieval type, pertinent literature and the retrieval conclusion in novelty assessment report to be evaluated are extracted.
S21: the evaluation novelty assessment report quality is obtained according to the retrieval type, the pertinent literature and the retrieval conclusion
The corresponding characteristic parameter of model.
S22: the characteristic parameter is inputted in the model of the evaluation novelty assessment report quality to obtain corresponding evaluation point
Number.
The model for needing to use the evaluation novelty assessment report quality in embodiment one in the present embodiment passes through in the model
Input corresponding characteristic parameter, so that it may export corresponding evaluation result, i.e. evaluation score.Specifically, to be evaluated look into newly is extracted
Retrieval type, pertinent literature and retrieval conclusion in report.The model of evaluation novelty assessment report quality is obtained according to above three parameter
Corresponding characteristic parameter.It is understood that when the corresponding characteristic parameter of model of evaluation novelty assessment report quality is described looks into newly
The degree of correlation of the retrieval type of report and novelty items, the degree of correlation of the pertinent literature of the novelty assessment report and the novelty items,
The technorati authority of the pertinent literature of the novelty assessment report, the accuracy rate of the pertinent literature of the novelty assessment report, the novelty assessment report
The recall rate of pertinent literature, the novelty assessment report retrieval conclusion correctness when, then on the characteristic parameter in step S21 is exactly
State 6 characteristic parameters.Characteristic parameter in step S21 needs corresponding with the characteristic parameter in the step S13 in embodiment one.It will
Obtained characteristic parameter is input in the model of evaluation novelty assessment report quality to obtain corresponding evaluation score.
The application method of evaluation novelty assessment report quality provided by the invention directlys adopt evaluation novelty assessment report quality
Model, when giving a mark to novelty assessment report to be evaluated, it is only necessary to extract corresponding characteristic parameter in novelty assessment report to be evaluated and be input to
It in the model for evaluating novelty assessment report quality, does not need expert and gives a mark, therefore save cost of labor.
The method for establishing model and application method of evaluation novelty assessment report quality provided by the present invention have been carried out in detail above
It is thin to introduce.Each embodiment is described in a progressive manner in specification, the highlights of each of the examples are with other realities
The difference of example is applied, the same or similar parts in each embodiment may refer to each other.For device disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part illustration
?.It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, also
Can be with several improvements and modifications are made to the present invention, these improvement and modification also fall into the protection scope of the claims in the present invention
It is interior.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Claims (8)
1. a kind of method for establishing model for evaluating novelty assessment report quality characterized by comprising
Extract the corresponding retrieval type of more novelty assessment reports, pertinent literature and retrieval conclusion；
The corresponding feature ginseng of the novelty assessment report is obtained according to each retrieval type, the pertinent literature and the retrieval conclusion
Number；
Expert is obtained to the scoring information of the novelty assessment report；
The relationship of the characteristic parameter Yu the scoring information is established by the way of linear regression model (LRM)；
The linear regression model (LRM) for using the characteristic parameter and the scoring information to establish is trained using gradient descent method
Obtain the model of the evaluation novelty assessment report quality；
The characteristic parameter includes:
The retrieval type of the novelty assessment report and the degree of correlation of novelty items；
The degree of correlation of the pertinent literature of the novelty assessment report and the novelty items；
The technorati authority of the pertinent literature of the novelty assessment report；
The accuracy rate of the pertinent literature of the novelty assessment report；
The recall rate of the pertinent literature of the novelty assessment report；
The correctness of the retrieval conclusion of the novelty assessment report.
2. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The retrieval type of announcement and the degree of correlation of novelty items are obtained by calculation formula；
Wherein, calculation formula is
wiKeyword set W={ the w used for the retrieval type1,w2,…,wmIn i-th of keyword, wiFor wiVector
It indicates；w′jKeyword set W '={ the w ' provided for novelty items d '1,w’2,…,w’nIn j-th of keyword, w 'jFor
w′jVector indicate；p(wi,w′j) indicate keyword wi、w′jCo-occurrence probabilities in the same document, p (wi) and p (w 'j) point
It Biao Shi not keyword wi、w′jIn the prior probability that document occurs, T is the transposition of vector.
3. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The pertinent literature of announcement and the degree of correlation of the novelty items are obtained by calculation formula；
Wherein, calculation formula are as follows:
D is the set for the pertinent literature retrieved in novelty assessment report；dkFor the kth piece pertinent literature in D；D ' is novelty items；dkFor
dkDocument vector indicate；The document vector that d ' is d ' indicates；| D | indicate the quantity of document in set D；T is the transposition of vector.
4. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The technorati authority of the pertinent literature of announcement is by looking into the publication source of new document, publishing the time limit and Cited rate acquisition.
5. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The accuracy rate of the pertinent literature of announcement is obtained by calculation formula；
Wherein, calculation formula are as follows: Precision=| D1|/|D|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the literature collection in D with novelty items true correlation, | D1
|, | D | respectively indicate set D1, quantity of document in D.
6. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The recall rate of the pertinent literature of announcement is obtained by calculation formula；
Wherein, calculation formula are as follows: Recall=| D1|/|D2|；
D is the set for the pertinent literature retrieved in novelty assessment report, D1For the literature collection in D with novelty items true correlation, D2For
In searchable data resource with the literature collection of novelty items true correlation, | D |, | D1|、|D2| respectively indicate set D, D1、
D2In quantity of document.
7. the method for establishing model of evaluation novelty assessment report quality according to claim 1, which is characterized in that described to look into new report
The correctness of the retrieval conclusion of announcement is obtained by calculation formula；
Wherein, calculation formula are as follows:
tiFor i-th of technical essential of novelty items；akFor the literature summary of k-th of pertinent literature in novelty assessment report；tiFor ti
Paragraph vector indicate；akFor akParagraph vector indicate；T is the transposition of vector.
8. a kind of application method for evaluating novelty assessment report quality, is looked into based on evaluation described in claim 1-7 any one
The model of latest report quality characterized by comprising
Extract retrieval type, pertinent literature and the retrieval conclusion in novelty assessment report to be evaluated；
The model pair of the evaluation novelty assessment report quality is obtained according to the retrieval type, the pertinent literature and the retrieval conclusion
The characteristic parameter answered；
The characteristic parameter is inputted in the model of the evaluation novelty assessment report quality to obtain corresponding evaluation score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510890524.7A CN105468920B (en) | 2015-12-07 | 2015-12-07 | A kind of method for establishing model and application method for evaluating novelty assessment report quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510890524.7A CN105468920B (en) | 2015-12-07 | 2015-12-07 | A kind of method for establishing model and application method for evaluating novelty assessment report quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105468920A CN105468920A (en) | 2016-04-06 |
| CN105468920B true CN105468920B (en) | 2019-03-12 |
Family
ID=55606611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510890524.7A Active CN105468920B (en) | 2015-12-07 | 2015-12-07 | A kind of method for establishing model and application method for evaluating novelty assessment report quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105468920B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880693A (en) * | 2012-09-20 | 2013-01-16 | 浙江大学 | Music recommendation method based on individual vocality |
| CN103488648A (en) * | 2012-06-13 | 2014-01-01 | 阿里巴巴集团控股有限公司 | Multilanguage mixed retrieval method and system |
| CN103514369A (en) * | 2013-09-18 | 2014-01-15 | 上海交通大学 | Regression analysis system and method based on active learning |
-
2015
- 2015-12-07 CN CN201510890524.7A patent/CN105468920B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488648A (en) * | 2012-06-13 | 2014-01-01 | 阿里巴巴集团控股有限公司 | Multilanguage mixed retrieval method and system |
| CN102880693A (en) * | 2012-09-20 | 2013-01-16 | 浙江大学 | Music recommendation method based on individual vocality |
| CN103514369A (en) * | 2013-09-18 | 2014-01-15 | 上海交通大学 | Regression analysis system and method based on active learning |
Non-Patent Citations (3)
| Title |
|---|
| "信息检索相关技术研究";王树梅;《中国优秀博士论文全文数据库 信息科技辑》;20080115(第1期);第44页第3.31节，第48-49页第3.4.1节,第61页第4.4.1.2节 |
| "文献学术特征与科技查新项目新颖性的模型与预判";周新跃;《情报杂志》;20150518;第34卷(第5期);第73页第1节-第74页第3.1节，第75页第4.1节 |
| "查新报告质量的评价体系研究";王世雯 等;《情报理论与实践》;20100630;第33卷(第6期);第96页第4.1节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105468920A (en) | 2016-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110462604A (en) | The data processing system and method for association internet device are used based on equipment | |
| CN108108821A (en) | Model training method and device | |
| CN106844530A (en) | Training method and device of a kind of question and answer to disaggregated model | |
| CN105117460A (en) | Learning resource recommendation method and system | |
| CN108763332A (en) | A kind of generation method and device of Search Hints word | |
| CN107545038B (en) | Text classification method and equipment | |
| CN105975596A (en) | Query expansion method and system of search engine | |
| CN108549907A (en) | A kind of data verification method based on multi-source transfer learning | |
| CN108062366A (en) | Public culture information recommendation system | |
| CN113918806A (en) | Method for automatically recommending training courses and related equipment | |
| CN104951807A (en) | Stock market emotion determining method and device | |
| Rakhman et al. | Applying analytic hierarchy process for measuring knowledge management readiness in government institutions | |
| CN108960884A (en) | Information processing method, model building method and device, medium and calculating equipment | |
| CN105138684B (en) | A kind of information processing method and information processing unit | |
| CN114239924A (en) | Influence index determination method and device based on weather parameters | |
| CN107679174A (en) | Construction method, device and the server of Knowledge Organization System | |
| CN105468920B (en) | A kind of method for establishing model and application method for evaluating novelty assessment report quality | |
| CN105095385B (en) | A kind of output method and device of retrieval result | |
| CN113808709B (en) | Psychological elasticity prediction method and system based on text analysis | |
| CN109902196A (en) | A kind of trademark class recommended method, device, computer equipment and storage medium | |
| CN115293275A (en) | Data identification method and device, electronic equipment and storage medium | |
| CN105893363A (en) | A method and a system for acquiring relevant knowledge points of a knowledge point | |
| Si et al. | An empirical study on the performance evaluation of scientific data sharing platforms in China | |
| CN107066602A (en) | A kind of news information method for pushing and system | |
| CN104239314A (en) | Search word expanding method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |