CN110675083A - Comprehensive recommendation method and device in scientific and technological field - Google Patents

Comprehensive recommendation method and device in scientific and technological field Download PDF

Info

Publication number
CN110675083A
CN110675083A CN201910947748.5A CN201910947748A CN110675083A CN 110675083 A CN110675083 A CN 110675083A CN 201910947748 A CN201910947748 A CN 201910947748A CN 110675083 A CN110675083 A CN 110675083A
Authority
CN
China
Prior art keywords
scientific
dimension
index
scientific research
total
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
Application number
CN201910947748.5A
Other languages
Chinese (zh)
Inventor
刘玮
李超
纪玉春
马欢
马璐
刘铭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National Computer Network and Information Security Management Center
Original Assignee
National Computer Network and Information Security Management Center
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National Computer Network and Information Security Management Center filed Critical National Computer Network and Information Security Management Center
Priority to CN201910947748.5A priority Critical patent/CN110675083A/en
Publication of CN110675083A publication Critical patent/CN110675083A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063Operations research, analysis or management
    • G06Q10/0639Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393Score-carding, benchmarking or key performance indicator [KPI] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation; Time management
    • G06Q10/105Human resources
    • G06Q10/1053Employment or hiring

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 invention discloses a comprehensive recommendation method in the technical field, which comprises the following steps: establishing a scientific and technological information base; setting a plurality of dimensions, a plurality of indexes, index weights of the indexes and dimension weights of the dimensions by adopting a subjective experience method; obtaining data of each index of each researcher, carrying out non-dimensionalization processing to obtain index values, calculating the total dimensionality score of each dimensionality of each researcher, sequencing the overall dimensionality scores in the same dimensionality according to a descending order, and taking K before ranking1A location researcher; calculating to obtain the comprehensive score of each scientific research personnel, sorting in descending order, and ranking K before2The scientific research personnel. The method has the advantages that the dimensionality and the index can be freely set, and scientific research personnel can be accurately, comprehensively, conveniently and quickly recommended. The invention discloses a comprehensive recommendation device in the scientific field, which comprises a storage module, a data processing module and a scientific research personnel recommendation module. The invention has the advantages of freely setting dimension and index, and accurately, comprehensively, conveniently and quickly recommendingThe beneficial effect of scientific research personnel.

Description

Comprehensive recommendation method and device in scientific and technological field
Technical Field
The invention relates to the field of scientific and technological evaluation. More specifically, the invention relates to a comprehensive recommendation method and device in the technical field.
Background
With the continuous development of scientific technology, numerous scientific research institutions and scientific research personnel emerge, a large number of scientific research achievements are generated, and the comprehensive strength of the scientific research institutions and the scientific research personnel is uneven. Under the background of big data, in order to quickly obtain excellent scientific achievements, scientific research institutions and scientific research personnel in some fields, comprehensive and accurate evaluation needs to be carried out on the excellent scientific research achievements, scientific research personnel and scientific research personnel, and at present, an evaluation index system for comprehensive strength of the relevant scientific research achievements, scientific research personnel and scientific research institutions in the scientific and technological fields is often fixed and unified, and the relevant scientific research personnel cannot be comprehensively recommended outwards accurately according to actual needs.
Disclosure of Invention
An object of the present invention is to solve at least the above problems and to provide at least the advantages described later.
The invention also aims to provide a comprehensive recommendation method in the scientific field, which can freely set dimensions and indexes and accurately, comprehensively, conveniently and quickly recommend scientific research personnel.
Still provide a comprehensive recommendation device in science and technology field, can freely set up dimension and index, accurate, comprehensive, convenient, swift recommendation scientific research personnel.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a comprehensive recommendation method in the scientific field, comprising:
establishing a scientific and technological information base, wherein scientific research personnel information and scientific research result information are stored in the scientific and technological information base;
setting multiple dimensions for evaluating scientific researchers, multiple indexes under each dimension, index weight of each index and dimension weight of each dimension by adopting a subjective experience method, wherein the sum of all index weights under the same dimension is equal to 1, and the sum of all dimension weights is equal to 1;
from the scientific and technical informationObtaining data of each index of each scientific research personnel from a library, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research personnel, calculating the total dimensionality score of each dimensionality of each scientific research personnel according to the weight and the index value of each index, sequencing the total dimensionality scores of all scientific research personnel in a descending order under the same dimensionality, and taking K before ranking1The position scientific researchers are dimension recommenders of the dimension;
the calculation formula of the dimension total score of one scientific researcher in one dimension is shown as formula (1):
Figure BDA0002224684440000021
wherein i is represented as the ith dimension; m represents m indexes in the ith dimension; j represents the j index in the ith dimension; a isijThe index weight of the j index under the ith dimension is represented; y isijIndex value, max (y), representing the j index in the i dimension of a researcherij) The maximum value of the index value of the jth index of all scientific researchers in the ith dimension is represented, min (y)ij) The minimum value of the index values of j index of all scientific researchers in i dimension is represented, YiRepresenting the dimension total score of a scientific research personnel in the ith dimension;
calculating according to the dimension weight and the total dimension score of each dimension to obtain the comprehensive score of each scientific research personnel, sorting in descending order, and ranking K before2The scientific researchers are comprehensive recommenders;
wherein, the calculation formula of the comprehensive score of one scientific research personnel is shown as formula (2):
Figure BDA0002224684440000022
where n represents a total of n dimensions, i represents the ith dimension, biA dimension weight representing an ith dimension; y isiThe dimension total score of one scientific research personnel in the ith dimension is represented, and the comprehensive score of each scientific research personnel is represented by Y.
Preferably, the method further comprises the following steps:
setting multiple dimensions for evaluating scientific achievements, multiple indexes under each dimension, index weights of the indexes and dimension weights of the dimensions by adopting a subjective experience method, wherein the sum of all the index weights under the same dimension is equal to 1, and the sum of all the dimension weights is equal to 1;
obtaining data of each index of each scientific research result from the scientific and technological information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research result, calculating the total dimensionality score of each scientific research result in each dimensionality according to the weight and the index value of each index, sequencing the total dimensionality scores of all scientific research results in a descending order under the same dimensionality, and taking K before ranking3The scientific research result of the item is the dimension recommendation result of the dimension;
the calculation formula of the overall score of the scientific achievements in one dimension is shown as a formula (3):
Figure BDA0002224684440000031
wherein k is represented as the kth dimension; h represents h indexes in the k dimension; l represents the l index in the k dimension; a isklAn index weight representing the l index in the k dimension; y isklIndex value, max (y), representing the l index in the k dimension of a scientific achievementkl) The maximum value of index values of the ith index in the kth dimension, min (y) of all scientific achievementskl) The minimum value of index values of the ith index in the kth dimension, YkRepresenting the dimension total score of a scientific research result in the k dimension;
calculating according to the weight of each dimension and the total score of the evaluation dimension to obtain the comprehensive scores of all scientific achievements, sorting in descending order, and ranking K before4The item scientific research results of the items are comprehensive recommendation results;
wherein, the calculation formula of the comprehensive score of the scientific research result is shown as formula (4):
Figure BDA0002224684440000032
where p represents a total of p dimensions, k represents the k-th dimension, bkA dimension weight representing a k-th dimension; y iskThe overall dimension score of a scientific result in the k dimension is shown, and B shows the comprehensive score of each scientific result.
Preferably, the method further comprises the following steps:
scientific research institution information is stored in the scientific information base;
setting a plurality of indexes for evaluating scientific research institutions and index weights of the indexes by adopting a subjective experience method, wherein the sum of all the index weights is equal to 1; obtaining data of each index of each scientific research institution from the scientific information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research institution, calculating the total score of each scientific research institution according to the weight and the index value of each index, sorting the total scores of all scientific research institutions in a descending order, and taking K before ranking5The individual scientific research institution is the recommendation institution;
wherein, the calculation formula of the total score of a scientific research institution is shown as formula (5):
Figure BDA0002224684440000033
wherein q represents a total of q indices; f represents the f-th index; bfAn index weight representing an f-th index; y isfAnd C represents the total score of a scientific research institution.
Preferably, the method of non-dimensionalizing is a normalization method.
Preferably, the dimensionality used for evaluating the scientific researchers comprises freshness, diversity, actual combat ability, scientific research ability and academic influence of the scientific researchers, wherein indexes of the freshness comprise research time, award achievement quantity and cooperation achievement quantity of the scientific researchers in one field, indexes of the diversity comprise label classification quantity and paper quantity of papers published by the scientific researchers, indexes of the actual combat ability comprise project quantity born by the scientific researchers, indexes of the scientific research ability comprise classification of the papers and corresponding paper quantity and high quoted paper quantity, and indexes of the academic influence comprise paper quoted frequency, high quoted paper quantity, important scientific research project quantity and award achievement quantity.
Preferably, the dimensionality for evaluating the scientific research results comprises freshness, popularity and influence of the scientific research results, wherein the index of the freshness of the scientific research results comprises a time span between a publishing time of the scientific research results and a current time span, the index of the popularity of the scientific research results comprises a time span between the publishing time of the scientific research results and the current time span between the publishing time of the scientific research results and the number of times the scientific research results are quoted, and the index of the influence of the scientific research results comprises the popularity and the influence factor.
Preferably, the indexes for evaluating the scientific research institutions comprise the number of awards, the number of co-construction laboratories, the number of partners, academic activities, dimensionality scores of the scientific research personnel, comprehensive scores of the scientific research personnel and the number of service objects.
Still provide a comprehensive recommendation device in science and technology field, include:
the storage module is used for storing the information of scientific research personnel and the information of scientific research results;
the data processing module is used for setting dimensions, a plurality of indexes under each dimension, index weights of the indexes and dimension weights of the dimensions, acquiring data of the indexes from the scientific and technological information base, carrying out non-dimensionalization processing on the data of the indexes to obtain index values of the non-dimensionalized indexes, calculating the total dimensionality score of each dimension of each scientific researcher according to the index weights and the index values, sequencing the total dimensionality scores of all the scientific researchers in a descending order under the same dimension, calculating the comprehensive scores of each scientific researcher, and sequencing the total dimensionality scores in the descending order;
a scientific research personnel recommending module for outputting the K before the dimension total score ranking1Rank K before researcher information and composite score2And (4) position of scientific research personnel information.
Preferably, the system further comprises a data processing module for calculating the total dimensionality score of each scientific research result in each dimensionality, sorting the total dimensionality scores of all scientific research results in a descending order in the same dimensionality, calculating the comprehensive scores of all scientific research results, and sorting the scores in the descending order;
scientific research result recommending module for outputting K before dimension total score ranking3Scientific achievements information and comprehensive score ranking K of items4The information of the scientific achievements of the items.
Preferably, the method further comprises the following steps:
the storage module stores scientific research institution information;
the data processing module is used for calculating the total score of each scientific research institution and sequencing the total scores of all the scientific research institutions in a descending order;
a recommendation module of scientific research institution for outputting K before the total score ranking5Individual research institution information.
The invention at least comprises the following beneficial effects:
firstly, different dimensions and indexes under each dimension can be set according to specific requirements of scientific researchers, such as the diversity and the actual combat ability of the scientific researchers are observed, two dimensions of the diversity and the actual combat ability can be set, or the weights of the two dimensions are set to be larger than those of the other dimensions, the indexes under each dimension can be artificially set, for example, the diversity dimensions reflect the multiple aspects of the scientific researchers, the influenced indexes comprise the label classification quantity and the paper quantity of papers, and if the paper quantity is observed, the weight of the index can be increased, so that the requirements of human units on the scientific researchers can be better matched through the free setting.
Secondly, dimension and weight are set and indexes and weight are set in front according to the needs of the people using units, so that the purpose that the dimension ranking and the total ranking are carried out on scientific research personnel meeting the needs of the people using units is achieved, the people using units can select the dimensions, the positioning is accurate, and the selection is convenient and quick.
Thirdly, dimension ranking and total ranking are carried out on the scientific research achievements meeting the requirements by setting dimension and weight thereof and setting indexes and weight thereof in front according to the requirements, so that people can select the ranking, the positioning is accurate, and the selection is convenient and quick.
Fourthly, indexes and weights thereof are set according to requirements in the front, so that the scientific research institutions meeting the requirements of the scientific research institutions are ranked for selection, the positioning is accurate, and the selection is convenient and quick. .
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
Fig. 1 is a block diagram of one embodiment of the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1, the present invention provides a comprehensive recommendation method in the scientific field, which includes:
establishing a scientific and technological information base, wherein scientific research personnel information and scientific research result information are stored in the scientific and technological information base, such as the academic calendar of scientific research personnel, the engaged scientific research projects, the research time, the number of published papers, the quality of the papers and the like;
setting multiple dimensions for evaluating scientific researchers, multiple indexes under each dimension, index weight of each index and dimension weight of each dimension by adopting a subjective experience method, wherein the sum of all index weights under the same dimension is equal to 1, and the sum of all dimension weights is equal to 1; different dimensions and indexes under each dimension can be set according to specific requirements of scientific researchers, such as the diversity and the actual combat ability of the scientific researchers are observed, two dimensions of the diversity and the actual combat ability can be set, or the weights of the two dimensions are set to be larger than those of the other dimensions, the indexes under each dimension can be artificially set, for example, the diversity dimensions reflect the multiple aspects of the scientific researchers, the influenced indexes comprise the label classification number and the paper number of papers, and if the paper number is observed more, the weight of the index can be increased, so that the requirements of human units on the scientific researchers can be better matched through the free setting.
Obtaining data of each index of each scientific research personnel from the scientific and technological information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research personnel, wherein the non-dimensionalization processing methods are various, such as standardization methods and index methods, which are all existing methods, calculating the dimension total score of each dimension of each scientific research personnel according to the weight and the index value of each index, sequencing the dimension total scores of all scientific research personnel in a descending order under the same dimension, and taking K before ranking1The position scientific researchers are dimension recommenders of the dimension; the ranking of each scientific research personnel in a certain dimension set by the method can be obtained, so that the ranking can be selected by the personnel unit.
The calculation formula of the dimension total score of one scientific researcher in one dimension is shown as formula (1):
Figure BDA0002224684440000061
wherein i is represented as the ith dimension; m represents m indexes in the ith dimension; j represents the j index in the ith dimension; a isijThe index weight of the j index under the ith dimension is represented; y isijIndex value, max (y), representing the j index in the i dimension of a researcherij) The maximum value of the index value of the jth index of all scientific researchers in the ith dimension is represented, min (y)ij) The minimum value of the index values of j index of all scientific researchers in i dimension is represented, YiRepresenting the dimension total score of a scientific research personnel in the ith dimension;
calculating according to the dimension weight and the total dimension score of each dimension to obtain the comprehensive score of each scientific research personnel, sorting in descending order, and ranking K before2The scientific researchers are comprehensive recommenders; the total ranking of all dimensions set by each scientific research personnel in the method can be obtained, so that the scientific research personnel can select the total ranking by the personnel units.
Wherein, the calculation formula of the comprehensive score of one scientific research personnel is shown as formula (2):
Figure BDA0002224684440000062
where n represents a total of n dimensions, i represents the ith dimension, biA dimension weight representing an ith dimension; y isiThe dimension total score of one scientific research personnel in the ith dimension is represented, and the comprehensive score of each scientific research personnel is represented by Y.
According to the technical scheme, the dimensionality and the weight thereof are set in the front according to the needs of the people using units, the indexes and the weight thereof are set, the purposes of carrying out dimensionality ranking and total ranking on scientific research personnel meeting the needs of the people using units are achieved, the people using units can select the dimensionality ranking and the total ranking, the positioning is accurate, and the selection is convenient and rapid.
In another technical solution, the method further comprises:
setting multiple dimensions for evaluating scientific achievements, multiple indexes under each dimension, index weights of the indexes and dimension weights of the dimensions by adopting a subjective experience method, wherein the sum of all the index weights under the same dimension is equal to 1, and the sum of all the dimension weights is equal to 1; different dimensions and indexes under each dimension can be set according to specific requirements on scientific achievements, for example, the influence on the scientific achievements is looked upon, the influence can be set as an important dimension, or the weight of the dimension is set to be larger than that of other dimensions, the indexes under each dimension can be manually set, for example, the indexes of the influence comprise popularity and influence factors, if the influence factors are looked more, the weight of the indexes can be increased, and therefore the requirements of the scientific research personnel on matching personnel units can be better through the free setting.
Obtaining data of each index of each scientific research result from the scientific and technological information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research result, calculating the total dimensionality score of each scientific research result in each dimensionality according to the weight and the index value of each index, sequencing the total dimensionality scores of all scientific research results in a descending order under the same dimensionality, and taking K before ranking3The scientific research result of the item is the dimension recommendation result of the dimension; the ranking of each scientific research result in a certain dimension set by the method can be obtained, so that the scientific research results can be selected by people.
The calculation formula of the overall score of the scientific achievements in one dimension is shown as a formula (3):
wherein k is represented as the kth dimension; h represents h indexes in the k dimension; l represents the l index in the k dimension; a isklAn index weight representing the l index in the k dimension; y isklIndex value, max (y), representing the l index in the k dimension of a scientific achievementkl) The maximum value of index values of the ith index in the kth dimension, min (y) of all scientific achievementskl) The minimum value of index values of the ith index in the kth dimension, YkRepresenting the dimension total score of a scientific research result in the k dimension;
calculating according to the weight of each dimension and the total score of the evaluation dimension to obtain the comprehensive scores of all scientific achievements, sorting in descending order, and ranking K before4The item scientific research results of the items are comprehensive recommendation results; the total ranking of each scientific result in all dimensions set by the method can be obtained, so that the scientific results can be selected by people.
Wherein, the calculation formula of the comprehensive score of the scientific research result is shown as formula (4):
Figure BDA0002224684440000081
where p represents a total of p dimensions, k represents the k-th dimension, bkA dimension weight representing a k-th dimension; y iskThe overall dimension score of a scientific result in the k dimension is shown, and B shows the comprehensive score of each scientific result.
According to the technical scheme, the dimensionality and the weight thereof are set in front according to the requirements, and the indexes and the weight thereof are set, so that the purposes of carrying out dimensionality ranking and total ranking on the scientific achievements meeting the requirements are achieved, the selection is provided for people, the positioning is accurate, and the selection is convenient and quick.
In another technical solution, the method further comprises:
scientific research institution information is stored in the scientific information base, such as members of scientific research institutions, research projects participated by the scientific research institutions, the grade of the projects, the quantity of obtained awards and the like;
setting a plurality of indexes for evaluating scientific research institutions and index weights of the indexes by adopting a subjective experience method, wherein the sum of all the index weights is equal to 1; obtaining data of each index of each scientific research institution from the scientific information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research institution, calculating the total score of each scientific research institution according to the weight and the index value of each index, sorting the total scores of all scientific research institutions in a descending order, and taking K before ranking5The individual scientific research institution is the recommendation institution; different indexes can be set according to specific requirements of scientific research institutions for manual setting, such as the number of awards, scientific and technological progress awards above provincial level, evaluation competition awards at home and abroad and the like, such as the number of co-construction laboratories, and if the number of awards is emphasized, the weight of the indexes can be increased, so that the requirements on the scientific research institutions can be better matched through the free setting.
Wherein, the calculation formula of the total score of a scientific research institution is shown as formula (5):
Figure BDA0002224684440000082
wherein q represents a total of q indices; f represents the f-th index; bfAn index weight representing an f-th index; y isfAnd C represents the total score of a scientific research institution. The ranking of all the indicators set by each scientific research institution in the method can be obtained for selection.
In the technical scheme, indexes and weights thereof are set according to requirements in the front, so that scientific research institutions meeting the requirements of the scientific research institutions can be ranked for selection, the positioning is accurate, and the selection is convenient and quick.
In another embodiment, the non-dimensionalization process is a normalization process.
Assuming that n dimensions are shared, m indexes are shared under one dimension, and each index is respectively expressed as x1,x2,x3,…,xmThe index number m of each dimension can be different (m is used uniformly to facilitate expression of a formula), and xij(i 1,2, …, n; j 1,2, …, m) represents the raw data of j index of a scientific researcher/achievement/organization in i dimension, yijDenotes xijThe index value after the non-dimensionalization processing,and σijRespectively representing the mean value and the standard deviation of j index of i dimension of all scientific researchers/achievements/institutions after non-dimensionalization processing. The formula of the normalization method is as follows:
Figure BDA0002224684440000092
after all the index data are processed in the step, a non-dimensionalized index value can be obtained, and the dimensional relation among the data is eliminated. The index system in the recommended module of the scientific research institution only comprises one dimension, and i is 1.
In another technical scheme, the dimension for evaluating the scientific researchers comprises freshness, diversity, actual combat ability, scientific research ability and academic influence of the scientific researchers, wherein indexes of the freshness comprise research time, award achievement quantity and cooperation achievement quantity of the scientific researchers in a field, indexes of the diversity comprise label classification quantity and paper quantity of papers published by the scientific researchers, indexes of the actual combat ability comprise project quantity born by the scientific researchers, indexes of the scientific research ability comprise classification of the papers, corresponding paper quantity and high quoted paper quantity, and indexes of the academic influence comprise frequency of quoted papers by the scientific researchers, high quoted paper number, important scientific research project quantity and award achievement quantity. Important scientific research projects refer to national key research and development plans such as air pollution cause and control technology research, typical fragile ecological restoration and protection research, 863 plan and the like.
The comprehensive ability of a scientific research personnel can be described in an all-round way by the aid of the four dimensions of freshness, diversity, actual combat ability, scientific research ability and academic influence, so that the user can select the dimension and index suitable for the user.
In another technical scheme, the dimension for evaluating the scientific research results comprises freshness, popularity and influence of the scientific research results, wherein the index of the freshness of the scientific research results comprises a time span between a publishing time of the scientific research results and the current time span, the index of the popularity of the scientific research results comprises a time span between the publishing time of the scientific research results and the current time span between the publishing time of the scientific research results and the number of times the scientific research results are quoted, and the index of the influence of the scientific research results comprises popularity and influence factor. The Influence Factor (IF) is a general journal evaluation index in the world, is an important index for measuring the academic level of the journal and the quality of a paper, and is a relative statistic.
The three dimensions of freshness, popularity and influence can describe the comprehensive ability of a scientific research result in an all-round way, so that better dimensions and indexes are provided for users.
In another technical scheme, the indexes for evaluating the scientific research institutions comprise prize obtaining quantity, co-construction laboratory quantity, partner quantity, academic activities, dimensionality scores of the scientific research personnel, comprehensive scores of the scientific research personnel and service object quantity. The comprehensive capability of a scientific research institution can be described in all directions, so that better indexes are provided for users.
Still provide a comprehensive recommendation device in science and technology field, include:
the storage module is used for storing scientific research personnel information and scientific research result information, such as the academic calendar of the scientific research personnel, the engaged scientific research projects, the research time, the number of published papers, the quality of the papers and the like;
the data processing module is used for setting dimensions, a plurality of indexes under each dimension, index weights of the indexes and dimension weights of the dimensions, acquiring data of the indexes from the scientific and technological information base, carrying out non-dimensionalization processing on the data of the indexes to obtain index values of the non-dimensionalized indexes, calculating the total dimensionality score of each dimension of each scientific researcher according to the index weights and the index values, sequencing the total dimensionality scores of all the scientific researchers in a descending order under the same dimension, calculating the comprehensive scores of each scientific researcher, and sequencing the total dimensionality scores in the descending order;
a scientific research personnel recommending module for outputting the K before the dimension total score ranking1Rank K before researcher information and composite score2And (4) position of scientific research personnel information.
According to the technical scheme, the dimensionality and the weight thereof are set in the front according to the needs of the people using units, the indexes and the weight thereof are set, the purposes of carrying out dimensionality ranking and total ranking on scientific research personnel meeting the needs of the people using units are achieved, the people using units can select the dimensionality ranking and the total ranking, the positioning is accurate, and the selection is convenient and rapid.
In another technical scheme, the system further comprises a data processing module, a data processing module and a data processing module, wherein the data processing module is used for calculating the dimension total score of each scientific research result in each dimension, sorting the dimension total scores of all the scientific research results in a descending order under the same dimension, calculating the comprehensive scores of all the scientific research results, and sorting the scores in the descending order;
scientific research result recommending module for outputting K before dimension total score ranking3Scientific achievements information and comprehensive score ranking K of items4The information of the scientific achievements of the items.
According to the technical scheme, the dimensionality and the weight thereof are set in front according to the requirements, and the indexes and the weight thereof are set, so that the purposes of carrying out dimensionality ranking and total ranking on the scientific achievements meeting the requirements are achieved, the selection is provided for people, the positioning is accurate, and the selection is convenient and quick.
In another technical solution, the method further comprises:
the storage module stores scientific research institution information, such as members of the scientific research institutions, research projects participated by the scientific research institutions, project levels, project quantity, obtained award quantity and the like;
the data processing module is used for calculating the total score of each scientific research institution and sequencing the total scores of all the scientific research institutions in a descending order;
a recommendation module of scientific research institution for outputting K before the total score ranking5Individual research institution information.
In the technical scheme, indexes and weights thereof are set according to requirements in the front, so that scientific research institutions meeting the requirements of the scientific research institutions can be ranked for selection, the positioning is accurate, and the selection is convenient and quick.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.

Claims (10)

1. The comprehensive recommendation method in the scientific and technological field is characterized by comprising the following steps:
establishing a scientific and technological information base, wherein scientific research personnel information and scientific research result information are stored in the scientific and technological information base;
setting multiple dimensions for evaluating scientific researchers, multiple indexes under each dimension, index weight of each index and dimension weight of each dimension by adopting a subjective experience method, wherein the sum of all index weights under the same dimension is equal to 1, and the sum of all dimension weights is equal to 1;
obtaining data of each index of each scientific research personnel from the scientific and technological information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research personnel, calculating the total dimensionality score of each dimensionality of each scientific research personnel according to the weight and the index value of each index, sequencing the total dimensionality scores of all scientific research personnel in a descending order under the same dimensionality, and taking K before ranking1The position scientific researchers are dimension recommenders of the dimension;
the calculation formula of the dimension total score of one scientific researcher in one dimension is shown as formula (1):
Figure FDA0002224684430000011
wherein i is represented as the ith dimension; m represents m indexes in the ith dimension; j represents the j index in the ith dimension; a isijThe index weight of the j index under the ith dimension is represented; y isijIndex value, max (y), representing the j index in the i dimension of a researcherij) The maximum value of the index value of the jth index of all scientific researchers in the ith dimension is represented, min (y)ij) The minimum value of the index values of j index of all scientific researchers in i dimension is represented, YiRepresenting the dimension total score of a scientific research personnel in the ith dimension;
calculating according to the dimension weight and the total dimension score of each dimension to obtain the comprehensive score of each scientific research personnel, sorting in descending order, and ranking K before2The scientific researchers are comprehensive recommenders;
wherein, the calculation formula of the comprehensive score of one scientific research personnel is shown as formula (2):
where n represents a total of n dimensions, i represents the ith dimension, biA dimension weight representing an ith dimension; y isiThe dimension total score of one scientific research personnel in the ith dimension is represented, and the comprehensive score of each scientific research personnel is represented by Y.
2. The comprehensive recommendation method in the scientific and technological field according to claim 1, further comprising:
setting multiple dimensions for evaluating scientific achievements, multiple indexes under each dimension, index weights of the indexes and dimension weights of the dimensions by adopting a subjective experience method, wherein the sum of all the index weights under the same dimension is equal to 1, and the sum of all the dimension weights is equal to 1;
obtaining from the scientific and technological information baseTaking data of each index of each scientific research result, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research result, calculating the total dimensionality score of each scientific research result in each dimensionality according to the weight and the index value of each index, sorting the total dimensionality scores of all scientific research results in a descending order under the same dimensionality, and taking K before ranking3The scientific research result of the item is the dimension recommendation result of the dimension;
the calculation formula of the overall score of the scientific achievements in one dimension is shown as a formula (3):
Figure FDA0002224684430000021
wherein k is represented as the kth dimension; h represents h indexes in the k dimension; l represents the l index in the k dimension; a isklAn index weight representing the l index in the k dimension; y isklIndex value, max (y), representing the l index in the k dimension of a scientific achievementkl) The maximum value of index values of the ith index in the kth dimension, min (y) of all scientific achievementskl) The minimum value of index values of the ith index in the kth dimension, YkRepresenting the dimension total score of a scientific research result in the k dimension;
calculating according to the weight of each dimension and the total score of the evaluation dimension to obtain the comprehensive scores of all scientific achievements, sorting in descending order, and ranking K before4The item scientific research results of the items are comprehensive recommendation results;
wherein, the calculation formula of the comprehensive score of the scientific research result is shown as formula (4):
Figure FDA0002224684430000022
where p represents a total of p dimensions, k represents the k-th dimension, bkA dimension weight representing a k-th dimension; y iskThe dimension total score of a scientific result in the k dimension is represented, and B represents each scientific resultAnd (5) comprehensively scoring the fruits.
3. The comprehensive recommendation method in the scientific and technological field according to claim 1, further comprising:
scientific research institution information is stored in the scientific information base;
setting a plurality of indexes for evaluating scientific research institutions and index weights of the indexes by adopting a subjective experience method, wherein the sum of all the index weights is equal to 1; obtaining data of each index of each scientific research institution from the scientific information base, carrying out non-dimensionalization processing on the data of each index to obtain an index value of each non-dimensionalized index of each scientific research institution, calculating the total score of each scientific research institution according to the weight and the index value of each index, sorting the total scores of all scientific research institutions in a descending order, and taking K before ranking5The individual scientific research institution is the recommendation institution;
wherein, the calculation formula of the total score of a scientific research institution is shown as formula (5):
Figure FDA0002224684430000031
wherein q represents a total of q indices; f represents the f-th index; bfAn index weight representing an f-th index; y isfAnd C represents the total score of a scientific research institution.
4. A comprehensive recommendation method in the scientific and technological field according to any one of claims 1 to 3, wherein the non-dimensionalization processing method is a normalization method.
5. The comprehensive recommendation method in scientific and technological fields as claimed in claim 1, wherein the dimensions for evaluating the researchers include freshness, diversity, actual combat ability, scientific research ability, academic influence of the researchers, wherein the index of freshness includes research time, number of awards and number of cooperation results of the researchers in a field, the index of diversity includes number of label classifications of papers published by the researchers and number of papers, the index of actual combat ability includes number of items undertaken by the researchers, the index of scientific research ability includes number of classifications of papers and corresponding number of papers, number of highly cited papers, and the index of academic influence includes number of times of citations of papers by the researchers, number of highly cited papers, number of major scientific research items and number of awards.
6. The comprehensive recommendation method in the scientific field according to claim 2, wherein the dimensions for evaluating the scientific results include freshness, popularity, and influence of the scientific results, wherein the index of freshness of the scientific results includes a time span between a time of releasing the scientific results and a current time span, the index of popularity of the scientific results includes a time span between a time of releasing the scientific results and a current time span between times of quoting the scientific results, and the index of influence of the scientific results includes popularity and influence factors.
7. The method of claim 3, wherein the index for evaluating the scientific research institution comprises a number of awards, a number of co-construction laboratories, a number of partners, academic campaigns, a dimension score of the scientific research personnel, a comprehensive score of the scientific research personnel, and a number of service objects.
8. A comprehensive recommendation device based on any one of claims 1 to 7 in the scientific and technological field, comprising:
the storage module is used for storing the information of scientific research personnel and the information of scientific research results;
the data processing module is used for setting dimensions, a plurality of indexes under each dimension, index weights of the indexes and dimension weights of the dimensions, acquiring data of the indexes from the scientific and technological information base, carrying out non-dimensionalization processing on the data of the indexes to obtain index values of the non-dimensionalized indexes, calculating the total dimensionality score of each dimension of each scientific researcher according to the index weights and the index values, sequencing the total dimensionality scores of all the scientific researchers in a descending order under the same dimension, calculating the comprehensive scores of each scientific researcher, and sequencing the total dimensionality scores in the descending order;
a scientific research personnel recommending module for outputting the K before the dimension total score ranking1Rank K before researcher information and composite score2And (4) position of scientific research personnel information.
9. The comprehensive recommendation device in the scientific field as claimed in claim 8, further comprising said data processing module for calculating the total score of each scientific research result in each dimension, and sorting the total scores of all scientific research results in a descending order in the same dimension, and calculating the comprehensive scores of all scientific research results in a descending order;
scientific research result recommending module for outputting K before dimension total score ranking3Scientific achievements information and comprehensive score ranking K of items4The information of the scientific achievements of the items.
10. The integrated scientific and technological recommendation apparatus as set forth in claim 8, further comprising:
the storage module stores scientific research institution information;
the data processing module is used for calculating the total score of each scientific research institution and sequencing the total scores of all the scientific research institutions in a descending order;
a recommendation module of scientific research institution for outputting K before the total score ranking5Individual research institution information.
CN201910947748.5A 2019-10-08 2019-10-08 Comprehensive recommendation method and device in scientific and technological field Pending CN110675083A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910947748.5A CN110675083A (en) 2019-10-08 2019-10-08 Comprehensive recommendation method and device in scientific and technological field

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910947748.5A CN110675083A (en) 2019-10-08 2019-10-08 Comprehensive recommendation method and device in scientific and technological field

Publications (1)

Publication Number Publication Date
CN110675083A true CN110675083A (en) 2020-01-10

Family

ID=69080950

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910947748.5A Pending CN110675083A (en) 2019-10-08 2019-10-08 Comprehensive recommendation method and device in scientific and technological field

Country Status (1)

Country Link
CN (1) CN110675083A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111598418A (en) * 2020-04-29 2020-08-28 思创数码科技股份有限公司 Balance-based item sorting method, balance-based item sorting device, balance-based item sorting equipment and storage medium
CN112508461A (en) * 2021-01-27 2021-03-16 中国科学院自动化研究所 Academic influence evaluation service platform system and device for multiple elements

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103606115A (en) * 2013-12-05 2014-02-26 国家电网公司 Evaluation method of energy-saving type power grid
CN109003010A (en) * 2018-10-17 2018-12-14 国网湖南省电力有限公司 The evaluation method of power grid project investment benefit
CN109544006A (en) * 2018-11-23 2019-03-29 国网浙江省电力有限公司电力科学研究院 A method of evaluation electric automobile charging station economic benefit
CN109615251A (en) * 2018-12-18 2019-04-12 北京领科智汇科技有限公司 A kind of scientific research personnel's academic aptitude evaluation method based on subjective and objective aggregative weighted multidimensional information
CN109978411A (en) * 2019-04-10 2019-07-05 交通运输部科学研究院 A kind of communications and transportation development index building model

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103606115A (en) * 2013-12-05 2014-02-26 国家电网公司 Evaluation method of energy-saving type power grid
CN109003010A (en) * 2018-10-17 2018-12-14 国网湖南省电力有限公司 The evaluation method of power grid project investment benefit
CN109544006A (en) * 2018-11-23 2019-03-29 国网浙江省电力有限公司电力科学研究院 A method of evaluation electric automobile charging station economic benefit
CN109615251A (en) * 2018-12-18 2019-04-12 北京领科智汇科技有限公司 A kind of scientific research personnel's academic aptitude evaluation method based on subjective and objective aggregative weighted multidimensional information
CN109978411A (en) * 2019-04-10 2019-07-05 交通运输部科学研究院 A kind of communications and transportation development index building model

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111598418A (en) * 2020-04-29 2020-08-28 思创数码科技股份有限公司 Balance-based item sorting method, balance-based item sorting device, balance-based item sorting equipment and storage medium
CN112508461A (en) * 2021-01-27 2021-03-16 中国科学院自动化研究所 Academic influence evaluation service platform system and device for multiple elements

Similar Documents

Publication Publication Date Title
Aziz et al. MCDM-AHP method in decision makings
Lewis et al. Text similarity: an alternative way to search MEDLINE
CN107391547B (en) Human object data matching method and system
CN106202377B (en) A kind of online collaboration sort method based on stochastic gradient descent
CN110675083A (en) Comprehensive recommendation method and device in scientific and technological field
CN104966106B (en) A kind of biological age substep Forecasting Methodology based on support vector machines
CN109558983A (en) Network courses dropping rate prediction technique and device
CN113918806A (en) Method for automatically recommending training courses and related equipment
CN107992613A (en) A kind of Text Mining Technology protection of consumers' rights index analysis method based on machine learning
CN113011788B (en) Emergency decision method for offshore traffic accident, terminal equipment and storage medium
Costa et al. Automatic classification of computational thinking skills in elementary school math questions
Lakshmi et al. An identification of better engineering college with conflicting criteria using adaptive TOPSIS
CN109344400A (en) A kind of judgment method and device of document storage
Saputra et al. Implementation of Profile Matching Method to Determine the Performance Evaluation of the Best Information Systems Lecturer at Prima Indonesia University: Implementation of Profile Matching Method to Determine the Performance Evaluation of the Best Information Systems Lecturer at Prima Indonesia University
CN108959568A (en) Intelligent file dissemination system and distribution method
CN112862641A (en) Retired soldier training recommendation method, equipment and storage medium
Szyjewski et al. A study on existing and actually used capabilities of mobile phones technologies
CN106875088A (en) Scientific research institution's academic evaluation method and system based on periodical editorial member's index
Mallafi et al. Prediction modelling in career management
Văduva On solving some types of multiple attribute decision making problems
CN110297886A (en) OJ topic classifier construction method and topic analogy method based on short text
Wati et al. Comparative Analysis of Multi-Criteria Decision Making for Student Degree Completion Time based on Entropy Weighted
CN109102164A (en) Platform evaluation method, apparatus, computer equipment and storage medium
CN115101160A (en) Drug sales data mining and retrieving method and device
Rice et al. Internal analyses of the least preferred co-worker (LPC) scale

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200110

RJ01 Rejection of invention patent application after publication