CN108171401A - A kind of recommendation method and system of scientific research personnel - Google Patents
A kind of recommendation method and system of scientific research personnel Download PDFInfo
- Publication number
- CN108171401A CN108171401A CN201711306645.8A CN201711306645A CN108171401A CN 108171401 A CN108171401 A CN 108171401A CN 201711306645 A CN201711306645 A CN 201711306645A CN 108171401 A CN108171401 A CN 108171401A
- Authority
- CN
- China
- Prior art keywords
- scientific research
- research personnel
- evaluation index
- scoring
- recommendation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of recommendation method and system of scientific research personnel, and the method includes：Collect the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；Evaluation index to be recommended to assign corresponding weight described in each single item, evaluation index and each single item is recommended to recommend the weight of evaluation index according to each single item, calculates the scoring of each scientific research personnel；According to the scoring of each scientific research personnel, generation meets the recommendation list of the scientific research personnel of preset characteristic attribute index.The present invention is by recommending evaluation index to assign corresponding weight the every of scientific research personnel, the scoring of scientific research personnel is calculated, and scientific research personnel is screened according to preset characteristic attribute index, by the scientific research personnel after screening according to the recommendation list of the height generation scientific research personnel of scoring, for selection of the user to outstanding scientific research personnel, the indices of scientific research personnel are quantified, the recommendation list finally by the scientific research personnel of scoring generation is more accurate.
Description
Technical field
The present invention relates to technical field of information recommendation, more particularly, to the recommendation method and system of scientific research personnel a kind of.
Background technology
In each scientific research field, user is intended to that researcher outstanding in this research field can be understood, for example, in life
Health field, patient wish to find expert outstanding in a certain scientific research field, then how to find the outstanding of oneself satisfaction
Scientific research personnel
At present, user be essentially all by itself experience or check being discussed in detail for each scientific research personnel, and
The evaluation of each scientific research personnel is considered according to being discussed in detail come self judgment and other people for each scientific research personnel
The scientific research personnel which is outstanding is selected, but this selection to outstanding scientific research personnel is compared blindly, is not much objective basis,
The outstanding scientific research personnel of selection is also not accurate enough.
Invention content
The present invention provides a kind of a kind of scientific research personnel's for overcoming the above problem or solving the above problems at least partly
Recommend method and system.
According to an aspect of the present invention, the recommendation method of scientific research personnel a kind of is provided, including：
Collect the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；
Evaluation index to be recommended to assign corresponding weight described in each single item, recommend according to each single item evaluation index and
Each single item recommends the weight of evaluation index, calculates the scoring of each scientific research personnel；
According to the scoring of each scientific research personnel, generation meets the recommendation name of the scientific research personnel of preset characteristic attribute index
It is single.
Based on the above technical solution, the present invention can also be improved as follows.
Further, the multinomial recommendation evaluation index includes undertaking the subject amount of money, honorary title, paper data and public sentiment
Data, the data that publish thesis include publish thesis quantity and quantity to be quoted.
Further, it is described to be specifically included for evaluation index is recommended to assign corresponding weight described in each single item：
Publish thesis quantity and the quantity to be quoted are normalized into generation variable P1 and P2 respectively；
The weight a1 and a2 of P1 and P2 is exported according to the important relationship of P1 and P2 by user, generation characterization paper data
Variable P=P1*a1+P2*a2；
Each scientific research personnel is undertaken into the subject amount of money, honorary title and public sentiment data normalization, is generated corresponding
Variable M, R and N according to the survey data of user, generate weighted value W1, W2, W3 and W4 of M, R, P and N；
Correspondingly, described recommend evaluation index and each single item to recommend the weight of evaluation index, meter according to each single item
The scoring for calculating each scientific research personnel specifically includes：
Calculate the scoring score=W1*M+W2*R+W3*P+W4*N of each scientific research personnel.
Further, the honorary title includes multiple, is denoted as R={ R1, R2 ..., Ri ... Rn }, is each honor
Title sets weight, forms weight set ω={ ω1,ω2,…,ωi,...ωn, into
And honorary title is calculated
Further, the survey data according to user, weighted value W1, W2, W3 and the W4 for generating M, R, P and N are specific
Including：
The survey data according to user, weighted value W1, W2, W3 and W4 of generation M, R, P and N are specifically included：
According to the survey data of user, evaluation index is recommended to judge items, obtain M/R=B12, M/N=B13,
M/P=B14, R/N=B23, R/P=B24 and N/P=B34；
Generator matrixWherein, Bij=1/Bji, i, j=1,2,3,4；
Above-mentioned matrix by row is normalized, forms the matrix after normalizationIts
In, Cij=Bij/max(Bij), i, j=1,2,3,4；
Generate the weighted value W of M, R, P and Ni=(Ci1+Ci2+Ci3+Ci4)/4。
Further, the multinomial characteristic attribute index includes age, ambit and characteristic key words, passes through such as lower section
Formula obtains the characteristic key words of each scientific research personnel：
The project name undertaken to each scientific research personnel and publishing thesis keyword carry out text analyzing, obtain the section
The characteristic key words of ambit where grinding personnel.
Further, the scoring according to each scientific research personnel, generation meet the section of preset characteristic attribute index
The recommendation list for grinding personnel specifically includes：
Judge whether age, ambit and the characteristic key words of each scientific research personnel meet preset age, subject
Field and the condition of characteristic key words reject the scientific research personnel for the condition that is unsatisfactory for；
It for the scientific research personnel obtained after rejecting, is ranked up according to the height of the scoring of scientific research personnel, generates scientific research people
The recommendation results of member.
Further, the scoring according to each scientific research personnel, generation meet the section of preset characteristic attribute index
The recommendation list for grinding personnel further includes later：
According to the evaluation data of user again, the weight for recommending evaluation index described in each single item is readjusted, is regenerated
The recommendation list of scientific research personnel.
According to another aspect of the present invention, a kind of commending system of scientific research personnel is provided, including：
Collection module, for collecting the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；
Computing module, for evaluation index to be recommended to assign corresponding weight described in each single item, being pushed away according to each single item
It recommends evaluation index and each single item recommends the weight of evaluation index, calculate the scoring of each scientific research personnel；
Generation module, for according to the scoring of each scientific research personnel, generation to meet the section of preset characteristic attribute index
Grind the recommendation list of personnel.
According to a further aspect of the invention, a kind of non-transient computer readable storage medium storing program for executing is provided, it is described non-transient
Computer-readable recording medium storage computer instruction, the computer instruction make the recommendation of the computer execution scientific research personnel
Method.
A kind of scientific research personnel provided by the invention recommends method and system, by evaluation being recommended to refer to the every of scientific research personnel
Mark assigns corresponding weight, the scoring of scientific research personnel is calculated, and according to preset characteristic attribute index to scientific research personnel
It is screened, by the scientific research personnel after screening according to the recommendation list of the height generation scientific research personnel of scoring, for user to outstanding
Scientific research personnel selection, the indices of scientific research personnel are quantified, are pushed away finally by the scientific research personnel of scoring generation
It is more accurate to recommend list.
Description of the drawings
Fig. 1 is the recommendation method flow diagram of the scientific research personnel of one embodiment of the invention；
The commending system that Fig. 2 is the scientific research personnel of another embodiment of the present invention connects block diagram；
Fig. 3 is the integrated connection block diagram of the commending system of the scientific research personnel of another embodiment of the invention.
Specific embodiment
With reference to the accompanying drawings and examples, the specific embodiment of the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but be not limited to the scope of the present invention.
Referring to Fig. 1, the recommendation method of the scientific research personnel of one embodiment of the invention is provided, can be realized to each scientific research
The recommendation of the scientific research personnel in field.This method includes：It collects the multinomial characteristic attribute index of each scientific research personnel and multinomial pushes away
Recommend evaluation index；Evaluation index to be recommended to assign corresponding weight described in each single item, recommend evaluation index according to each single item
And each single item recommends the weight of evaluation index, calculates the scoring of each scientific research personnel；According to commenting for each scientific research personnel
Point, generation meets the recommendation list of the scientific research personnel of preset characteristic attribute index.
It realizes the recommendation to the scientific research personnel in each field, needs to assess the Research funding of each scientific research personnel,
The present embodiment mainly collects the characteristic attribute index of each scientific research personnel and recommends evaluation index, wherein, each scientific research people
The characteristic attribute index and recommendation evaluation index of member has multinomial.When assessing each scientific research personnel, mainly according to every
The multinomial recommendation evaluation index of one scientific research personnel is assessed.Evaluation index is recommended to assign corresponding weight, root for each single item
Recommend evaluation index and corresponding weight according to each single item, the scoring of each scientific research personnel is calculated.Judge each section
Whether the multinomial characteristic attribute index for grinding personnel meets the condition of preset multinomial characteristic attribute index, will meet condition
Scientific research personnel screens, then according to each scientific research personnel scoring generation scientific research personnel recommendation list, usually according to
The height of the scoring of scientific research personnel is recommended.
On the basis of above-described embodiment, in one embodiment of the present of invention, the multinomial recommendation evaluation index includes holding
Carry on a shoulder pole the subject amount of money, honorary title, paper data and public sentiment data, the data that publish thesis, which include publishing thesis, quantity and is drawn
With number.
Wherein, in the present embodiment, the recommendation evaluation index of each scientific research personnel include undertake the subject amount of money, honor claims
Number, paper data and public sentiment data, paper data mainly include publish thesis quantity and quantity to be quoted.These recommend evaluation index
It needs to use when subsequently to the scoring of each scientific research personnel, rear extended meeting is described in detail.
It is described to recommend evaluation described in each single item in one embodiment of the present of invention on the basis of the various embodiments described above
Index assigns corresponding weight and specifically includes：Quantity is published thesis by described and the quantity to be quoted normalizes generation variable respectively
P1 and P2；The weight a1 and a2 of P1 and P2 is exported according to the important relationship of P1 and P2 by user, generation characterization paper data
Variable P=P1*a1+P2*a2；Each scientific research personnel is undertaken into the subject amount of money, honorary title and public sentiment data normalization,
Corresponding variable M, R and N are generated, according to the survey data of user, generates weighted value W1, W2, W3 and W4 of M, R, P and N；Accordingly
, it is described that evaluation index and each single item is recommended to recommend the weight of evaluation index according to each single item, calculate each scientific research
The scoring of personnel specifically includes：Calculate the scoring score=W1*M+W2*R+W3*P+W4*N of each scientific research personnel.
Mainly include above embodiments illustrate, the recommendation evaluation index of each scientific research personnel undertake the subject amount of money,
Honorary title, paper data and public sentiment data, paper data therein include publish thesis quantity and quantity to be quoted.It will deliver
Quantity of Papers and quantity to be quoted normalize the corresponding variable P1 and P2 of generation respectively, to be described below conveniently, P1 and P2 generation respectively
Table publishes thesis quantity and quantity to be quoted.According to the survey data of user, i.e. user to the important relationship of P1 and P2, output P1 and
The weight a1 and a2 of P2, the variable P=P1*a1+P2*a2 of generation characterization paper data, has just obtained the variable P of paper data.
Wherein, the subject amount of money, honorary title and public sentiment data are undertaken for each scientific research personnel, to these indexs
It is normalized respectively, generates corresponding variable M, R and N, and according to the survey data of user, generation respectively undertakes the subject amount of money
M, weighted value W1, W2, W3 and W4 of honorary title R, paper data P and public sentiment data N.According to indices and indices
Weighted value, calculate the scoring score=W1*M+W2*R+W3*P+W4*N of each scientific research personnel, and then obtain each section
Grind the scoring of personnel.
On the basis of the various embodiments described above, in an alternative embodiment of the invention, the honorary title includes multiple, note
For R={ R1, R2 ..., Ri ... Rn }, weight is set for each honorary title, forms weight set ω={ ω1,ω2,…,
ωi,...ωn, and then honorary title is calculated
Wherein, the honorary title in the recommendation evaluation index of each scientific research personnel includes multiple, can be denoted as R=
{ R1, R2 ..., Ri ... Rn }, and corresponding weight is set for each honorary title, form weight set ω={ ω1,
ω2,…,ωi,...ωn, and then the variable for title of winning honor
On the basis of the various embodiments described above, in one embodiment of the present of invention, the survey data according to user is raw
Weighted value W1, W2, W3 and W4 into M, R, P and N are specifically included：According to the survey data of user, evaluation index is recommended to items
It is judged, obtains M/R=B12, M/N=B13, M/P=B14, R/N=B23, R/P=B24 and N/P=B34；Generator matrixWherein, Bij=1/Bji, i, j=1,2,3,4；Above-mentioned matrix is normalized by row, shape
Into the matrix after normalizationWherein, Cij=Bij/max(Bij), i, j=1,2,3,4；Generation
M, the weighted value W of R, P and Ni=(Ci1+Ci2+Ci3+Ci4)/4, and then respectively obtain each scientific research personnel undertakes the subject amount of money
M, weight W1, W2, W3 and W4 of honorary title R, paper data P and public sentiment data N.
On the basis of the various embodiments described above, in one embodiment of the present of invention, the multinomial characteristic attribute index includes
Age, ambit and characteristic key words obtain the characteristic key words of each scientific research personnel in the following way：To each
The project name that scientific research personnel undertakes and the keyword that publishes thesis carry out text analyzing, subject neck where generating the scientific research personnel
The characteristic key words in domain.
Wherein, the multinomial characteristic attribute index of each scientific research personnel mainly includes age, ambit and feature critical
Word.Wherein, the corresponding characteristic key words of each scientific research personnel are by undertaking project name to scientific research personnel and publishing thesis
Keyword carries out text analyzing, generates the characteristic key words of the scientific research personnel.
It is described according to each scientific research personnel's in one embodiment of the present of invention on the basis of the various embodiments described above
Scoring generates the recommendation list of scientific research personnel for meeting preset characteristic attribute index and specifically includes：Judge each scientific research people
Whether age, ambit and the characteristic key words of member meet the condition of preset age, ambit and characteristic key words, will
The scientific research personnel for being unsatisfactory for condition rejects；For the scientific research personnel obtained after rejecting, according to scientific research personnel scoring height into
Row sequence generates the recommendation results of scientific research personnel.
The multinomial characteristic attribute index of each scientific research personnel has been obtained, that is, has collected the year of each scientific research personnel
After age, ambit and characteristic key words, judge whether age, ambit and the characteristic key words of each scientific research personnel are full
The condition at foot preset age, ambit and characteristic key words, the scientific research personnel for the condition that meets is screened.Than
Such as, user intentionally get the age between 30-60 Sui, life and health field, liver and spleen research direction scientific research personnel recommendation name
It is single, then the characteristic attribute index of each aforementioned scientific research personnel with the characteristic attribute index set is matched, will be unsatisfactory for
The scientific research personnel of condition rejects, and obtains the score data for the scientific research personnel for meeting condition.For the scientific research personnel after rejecting, according to
The height of the scoring of each scientific research personnel is ranked up, and generates the recommendation results of scientific research personnel.
It is described according to each scientific research personnel's in one embodiment of the present of invention on the basis of the various embodiments described above
Scoring, generation further include after meeting the recommendation list of the scientific research personnel of preset characteristic attribute index：According to user again
Data are evaluated, readjust the weight for recommending evaluation index described in each single item, regenerate the recommendation list of scientific research personnel.
The recommendation list of the scientific research personnel of above-mentioned generation is recommended into user, according to the survey data whether user is satisfied with,
The weight that each single item recommends evaluation index is readjusted, recalculates the scoring of each scientific research personnel, and then regenerate section
Grind the recommendation list of personnel.
Referring to Fig. 2, the commending system of the scientific research personnel of one embodiment of the invention is provided, including collection module 21, meter
Calculate module 22 and generation module 23.
Collection module 21 refers to for collecting the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation
Mark.
Module 22 is assigned, for evaluation index to be recommended to assign corresponding weight described in each single item.
Computing module 23, for evaluation index and each single item to be recommended to recommend the power of evaluation index according to each single item
Weight, calculates the scoring of each scientific research personnel.
Generation module 24, for according to the scoring of each scientific research personnel, generation to meet preset characteristic attribute index
The recommendation list of scientific research personnel.
Referring to Fig. 3, provide the commending system of the scientific research personnel of another embodiment of the present invention, including collection module 21,
Assign module 22, computing module 23, generation module 24, judgment module 25 and adjustment module 26.
Collection module 21 refers to for collecting the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation
Mark.
Module 22 is assigned, for evaluation index to be recommended to assign corresponding weight described in each single item.
Computing module 23, for evaluation index and each single item to be recommended to recommend the power of evaluation index according to each single item
Weight, calculates the scoring of each scientific research personnel.
Generation module 24, for according to the scoring of each scientific research personnel, generation to meet preset characteristic attribute index
The recommendation list of scientific research personnel.
Wherein, module 22 is assigned, specifically for quantity and the quantity to be quoted of publishing thesis is distinguished normalizing metaplasia
Into variable P1 and P2；The weight a1 and a2 of P1 and P2, generation characterization paper are exported according to the important relationship of P1 and P2 by user
The variable P=P1*a1+P2*a2 of data；Each scientific research personnel is undertaken into the subject amount of money, honorary title and public sentiment data
Normalization, generates corresponding variable M, R and N, according to the survey data of user, generate M, R, P and N weighted value W1, W2, W3 and
W4；Correspondingly, computing module 23, specifically for calculating the scoring score=W1*M+W2*R+W3*P+ of each scientific research personnel
W4*N。
Computing module 23 is additionally operable to that honorary title is calculated Wherein, it is described
Honorary title include it is multiple, be denoted as R={ R1, R2 ..., Ri ... Rn }, for each honorary title set weight, formed weight
Set ω={ ω1,ω2,…,ωi,...ωn}。
Generation module 24 is additionally operable to the survey data according to user, evaluation index is recommended to judge items, obtains M/
R=B12, M/N=B13, M/P=B14, R/N=B23, R/P=B24 and N/P=B34；Generator matrixWherein, Bij=1/Bji, i, j=1,2,3,4；Above-mentioned matrix is normalized by row,
Form the matrix after normalizationWherein, Cij=Bij/max(Bij), i, j=1,2,3,4；It is raw
Into the weighted value W of M, R, P and Ni=(Ci1+Ci2+Ci3+Ci4)/4。
Generation module 24 is additionally operable to the project name undertaken to each scientific research personnel and the keyword that publishes thesis progress
Text analyzing, the characteristic key words of ambit where generating the scientific research personnel, wherein, multinomial characteristic attribute index includes year
Age, ambit and characteristic key words.
Judgment module 25, for judging whether the age of each scientific research personnel, ambit and characteristic key words meet
The condition at preset age, ambit and characteristic key words rejects the scientific research personnel for the condition that is unsatisfactory for；Correspondingly, generation
Module 24, for the scientific research personnel obtained after rejecting, being ranked up according to the height of the scoring of scientific research personnel, generating scientific research people
The recommendation results of member.
Module 26 is adjusted, for the evaluation data according to user again, readjusts and recommends evaluation index described in each single item
Weight, regenerate the recommendation list of scientific research personnel.
The present invention also provides a kind of non-transient computer readable storage medium storing program for executing, which deposits
Computer instruction is stored up, which makes computer perform the recommendation side of scientific research personnel that above-mentioned corresponding embodiment is provided
Method, such as including：Collect the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；For each single item institute
It states and evaluation index is recommended to assign corresponding weight, evaluation index and each single item is recommended to recommend evaluation index according to each single item
Weight, calculate the scoring of each scientific research personnel；According to the scoring of each scientific research personnel, generation meets preset feature category
The recommendation list of the scientific research personnel of property index.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and aforementioned program can be stored in a computer read/write memory medium, the program
When being executed, step including the steps of the foregoing method embodiments is performed；And aforementioned storage medium includes：ROM, RAM, magnetic disc or light
The various media that can store program code such as disk.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
Technical solution is stated substantially in other words to embody the part that the prior art contributes in the form of software product, it should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
It enables and (can be personal computer, server or the network equipment etc.) so that computer equipment is used to perform each implementation
Certain Part Methods of example or embodiment.
A kind of scientific research personnel provided by the invention recommends method and system, by evaluation being recommended to refer to the every of scientific research personnel
Mark assigns corresponding weight, the scoring of scientific research personnel is calculated, and according to preset characteristic attribute index to scientific research personnel
It is screened, by the scientific research personnel after screening according to the recommendation list of the height generation scientific research personnel of scoring, for user to outstanding
Scientific research personnel selection, the indices of scientific research personnel are quantified, are pushed away finally by the scientific research personnel of scoring generation
It is more accurate to recommend list.
Finally, the present processes are only preferable embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in the protection of the present invention
Within the scope of.
Claims (10)
1. a kind of recommendation method of scientific research personnel, which is characterized in that including：
Collect the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；
Evaluation index to be recommended to assign corresponding weight described in each single item, recommend evaluation index and each according to each single item
Item recommends the weight of evaluation index, calculates the scoring of each scientific research personnel；
According to the scoring of each scientific research personnel, generation meets the recommendation list of the scientific research personnel of preset characteristic attribute index.
2. the recommendation method of scientific research personnel as described in claim 1, which is characterized in that the multinomial recommendation evaluation index includes
Undertake the subject amount of money, honorary title, paper data and public sentiment data, the data that publish thesis include publishing thesis quantity and by
Number of references.
3. the recommendation method of scientific research personnel as claimed in claim 2, which is characterized in that described to recommend evaluation described in each single item
Index assigns corresponding weight and specifically includes：
Publish thesis quantity and the quantity to be quoted are normalized into generation variable P1 and P2 respectively；
The weight a1 and a2 of P1 and P2, the variable of generation characterization paper data are exported according to the important relationship of P1 and P2 by user
P=P1*a1+P2*a2；
Each scientific research personnel is undertaken into the subject amount of money, honorary title and public sentiment data normalization, generates corresponding variable
M, R and N according to the survey data of user, generates weighted value W1, W2, W3 and W4 of M, R, P and N；
Correspondingly, described recommend evaluation index and each single item to recommend the weight of evaluation index according to each single item, calculate every
The scoring of one scientific research personnel specifically includes：
Calculate the scoring score=W1*M+W2*R+W3*P+W4*N of each scientific research personnel.
4. the recommendation method of scientific research personnel as claimed in claim 2 or claim 3, which is characterized in that the honorary title include it is multiple,
R={ R1, R2 ..., Ri ... Rn } is denoted as, weight is set for each honorary title, forms weight set ω={ ω1,
ω2,…,ωi,...ωn, and then honorary title is calculated
5. the recommendation method of scientific research personnel as claimed in claim 4, which is characterized in that the survey data according to user,
Weighted value W1, W2, W3 and W4 of generation M, R, P and N are specifically included：
The survey data according to user, weighted value W1, W2, W3 and W4 of generation M, R, P and N are specifically included：
According to the survey data of user, evaluation index is recommended to judge items, obtain M/R=B12, M/N=B13, M/P=
B14, R/N=B23, R/P=B24 and N/P=B34；
Generator matrixWherein, Bij=1/Bji, i, j=1,2,3,4；
Above-mentioned matrix by row is normalized, forms the matrix after normalizationWherein, Cij
=Bij/max(Bij), i, j=1,2,3,4；
Generate the weighted value W of M, R, P and Ni=(Ci1+Ci2+Ci3+Ci4)/4。
6. the recommendation method of scientific research personnel as claimed in claim 3, which is characterized in that the multinomial characteristic attribute index includes
Age, ambit and characteristic key words obtain the characteristic key words of each scientific research personnel in the following way：
The project name undertaken to each scientific research personnel and publishing thesis keyword carry out text analyzing, obtain scientific research people
The characteristic key words of ambit where member.
7. the recommendation method of scientific research personnel as claimed in claim 6, which is characterized in that described according to each scientific research personnel's
Scoring generates the recommendation list of scientific research personnel for meeting preset characteristic attribute index and specifically includes：
Judge whether age, ambit and the characteristic key words of each scientific research personnel meet preset age, ambit
With the condition of characteristic key words, the scientific research personnel for the condition that is unsatisfactory for is rejected；
For the scientific research personnel obtained after rejecting, it is ranked up according to the height of the scoring of scientific research personnel, generates scientific research personnel's
Recommendation results.
8. the recommendation method of scientific research personnel as described in claim 1, which is characterized in that described according to each scientific research personnel's
Scoring, generation further include after meeting the recommendation list of the scientific research personnel of preset characteristic attribute index：
According to the evaluation data of user again, the weight for recommending evaluation index described in each single item is readjusted, regenerates scientific research
The recommendation list of personnel.
9. a kind of commending system of scientific research personnel, which is characterized in that including：
Collection module, for collecting the multinomial characteristic attribute index of each scientific research personnel and multinomial recommendation evaluation index；
Module is assigned, for evaluation index to be recommended to assign corresponding weight described in each single item；
Computing module for evaluation index and each single item to be recommended to recommend the weight of evaluation index according to each single item, calculates
The scoring of each scientific research personnel；
Generation module, for according to the scoring of each scientific research personnel, generation to meet the scientific research people of preset characteristic attribute index
The recommendation list of member.
10. a kind of non-transient computer readable storage medium storing program for executing, which is characterized in that the non-transient computer readable storage medium storing program for executing is deposited
Computer instruction is stored up, the computer instruction makes the computer perform the method as described in claim 1-8 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711306645.8A CN108171401A (en) | 2017-12-11 | 2017-12-11 | A kind of recommendation method and system of scientific research personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711306645.8A CN108171401A (en) | 2017-12-11 | 2017-12-11 | A kind of recommendation method and system of scientific research personnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108171401A true CN108171401A (en) | 2018-06-15 |
Family
ID=62525702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711306645.8A Pending CN108171401A (en) | 2017-12-11 | 2017-12-11 | A kind of recommendation method and system of scientific research personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108171401A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727059A (en) * | 2018-11-20 | 2019-05-07 | 北京云和互动信息技术有限公司 | A kind of evaluation method and system based on big data |
| CN110737859A (en) * | 2019-09-09 | 2020-01-31 | 苏宁云计算有限公司 | UP main matching method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916425A (en) * | 2010-08-13 | 2010-12-15 | 中国科学院水生生物研究所 | Method for comprehensively evaluating ecosystem service of artificial wetland |
| CN102156706A (en) * | 2011-01-28 | 2011-08-17 | 清华大学 | Mentor recommendation system and method |
| CN105139119A (en) * | 2015-08-18 | 2015-12-09 | 杭州后博科技有限公司 | College teachers' current scientific research capability evaluation model and system |
| CN106844665A (en) * | 2017-01-20 | 2017-06-13 | 中山大学 | A kind of paper based on the distributed expression of adduction relationship recommends method |
-
2017
- 2017-12-11 CN CN201711306645.8A patent/CN108171401A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916425A (en) * | 2010-08-13 | 2010-12-15 | 中国科学院水生生物研究所 | Method for comprehensively evaluating ecosystem service of artificial wetland |
| CN102156706A (en) * | 2011-01-28 | 2011-08-17 | 清华大学 | Mentor recommendation system and method |
| CN105139119A (en) * | 2015-08-18 | 2015-12-09 | 杭州后博科技有限公司 | College teachers' current scientific research capability evaluation model and system |
| CN106844665A (en) * | 2017-01-20 | 2017-06-13 | 中山大学 | A kind of paper based on the distributed expression of adduction relationship recommends method |
Non-Patent Citations (1)
| Title |
|---|
| 吴小妹 等: "基于科技创新人才信息平台数据挖掘的科研能力评价模型研究", 《科技通报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727059A (en) * | 2018-11-20 | 2019-05-07 | 北京云和互动信息技术有限公司 | A kind of evaluation method and system based on big data |
| CN110737859A (en) * | 2019-09-09 | 2020-01-31 | 苏宁云计算有限公司 | UP main matching method and device |
| CN110737859B (en) * | 2019-09-09 | 2022-09-27 | 苏宁云计算有限公司 | UP master matching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Leydesdorff et al. | The operationalization of “fields” as WoS subject categories (WC s) in evaluative bibliometrics: The cases of “library and information science” and “science & technology studies” | |
| Mejia et al. | Exploring topics in bibliometric research through citation networks and semantic analysis | |
| US10332007B2 (en) | Computer-implemented system and method for generating document training sets | |
| JP6369053B2 (en) | MATCHING DEVICE, MATCHING METHOD, AND PROGRAM | |
| US8892561B2 (en) | Refinement and calibration mechanism for improving classification of information assets | |
| US8661034B2 (en) | Bimodal recommendation engine for recommending items and peers | |
| CN109564669A (en) | Based on trust score and geographic range searching entities | |
| CN106650273A (en) | Behavior prediction method and device | |
| US20120296835A1 (en) | Patent scoring and classification | |
| JP6488753B2 (en) | Information processing method | |
| Zaras et al. | Dominance-based rough set approach in selection of portfolio of sustainable development projects | |
| Nakatsuji et al. | Collaborative filtering by analyzing dynamic user interests modeled by taxonomy | |
| CN108171401A (en) | A kind of recommendation method and system of scientific research personnel | |
| Hu et al. | Tourism demand forecasting using nonadditive forecast combinations | |
| Silva et al. | A dominance-based rough set approach applied to evaluate the credit risk of sovereign bonds | |
| Lee | Linking technology roadmapping to patent analysis | |
| Ebadi et al. | iSEER: an intelligent automatic computer system for scientific evaluation of researchers | |
| CN109801162A (en) | A kind of credit rating method that social media data are merged with multi-standard cross-certification | |
| CN109063944A (en) | City banking index analysis method and device based on big data analysis technology | |
| US20220318236A1 (en) | Library information management system | |
| Aboucaya et al. | Detecting obstacles to collaboration in an online participatory democracy platform: a use-case driven analysis | |
| JP7454213B2 (en) | New business proposal computer system, new business proposal computer program, new business proposal method, new business proposal device | |
| Ullah et al. | Efficient portfolio management using topsis and ada-boost | |
| Nadali et al. | Class Labeling of Bank Credit's Customers Using AHP and SAW for Credit Scoring with Data Mining Algorithms | |
| Litvinchev et al. | An interactive algorithm for portfolio bi-criteria optimization of R&D projects in public organizations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180615 |
|
| RJ01 | Rejection of invention patent application after publication |