CN117235373B - Scientific research hot spot recommendation method based on information entropy - Google Patents
Scientific research hot spot recommendation method based on information entropy Download PDFInfo
- Publication number
- CN117235373B CN117235373B CN202311510648.9A CN202311510648A CN117235373B CN 117235373 B CN117235373 B CN 117235373B CN 202311510648 A CN202311510648 A CN 202311510648A CN 117235373 B CN117235373 B CN 117235373B
- Authority
- CN
- China
- Prior art keywords
- expert
- scientific research
- index
- hot spot
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011160 research Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000009825 accumulation Methods 0.000 abstract description 5
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 abstract description 2
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Abstract
The invention provides a scientific research hot spot recommending method based on information entropy, which comprises the following steps: s1: collecting expert attribute data; s2: performing expert clustering calculation; s3: and performing expert group recommendation hot spot. The invention introduces a peer assessment mechanism, can effectively utilize the knowledge accumulation and experience accumulation of expert groups, and can more scientifically and objectively recommend submitted scientific research hotspots. The invention optimizes the objective weight of the recommended index based on the principle of information entropy, can reflect the objective distribution of the recommended index from the statistical perspective, and effectively eliminates subjective deviation caused by group decision. The traditional recommendation algorithm mostly needs to adopt neural network calculation, the calculation cost is high, the calculation process of the invention does not involve complex mathematical operation, the calculation can be realized rapidly through a computer program, and the application prospect is wide.
Description
Technical Field
The invention particularly relates to a scientific research hot spot recommendation method based on information entropy.
Background
The main task of the recommendation system is to obtain the preference characteristics of the user on the articles by analyzing the user information, the article information or other auxiliary information, and accordingly recommend the articles to the user. The academic circles have no research results of scientific research hot spot recommendation models and algorithms, so that scientific research personnel can spend a great deal of time on searching research hot spots when carrying out research work, and the demands are urgent in the scientific research field. The conventional recommendation algorithm is mostly applied to the e-commerce field, personalized commodity recommendation is carried out according to the preference of a user, but the recommendation model and recommendation algorithm research aiming at the scientific research field are rare. The reason is that the scientific research field needs to take a plurality of factors into consideration and can dynamically change, and the scientific research workers can be provided with more accurate hot spot direction recommendation by means of priori knowledge and experience accumulation of experts, and how to construct an expert decision model in a recommendation system is a technical difficulty, and especially avoids factors such as subjectivity and the like of expert decisions in a practice level.
In summary, a research hotspot recommendation method based on information entropy is provided to solve the above problems.
Disclosure of Invention
The invention aims to provide the scientific research hot spot recommending method based on the information entropy, which can well solve the problems.
In order to meet the requirements, the invention adopts the following technical scheme: the method for recommending the scientific research hot spots based on the information entropy comprises the following steps:
s1: collecting expert attribute data;
s2: performing expert clustering calculation;
s3: and performing expert group recommendation hot spot.
The scientific research hot spot recommendation method based on the information entropy has the following advantages:
(1) The invention introduces a peer assessment mechanism, can effectively utilize the knowledge accumulation and experience accumulation of expert groups, and can more scientifically and objectively recommend submitted scientific research hotspots.
(2) The invention optimizes the objective weight of the recommended index based on the principle of information entropy, can reflect the objective distribution of the recommended index from the statistical perspective, and effectively eliminates subjective deviation caused by group decision.
(3) The traditional recommendation algorithm mostly needs to adopt neural network calculation, the calculation cost is high, the calculation process of the invention does not involve complex mathematical operation, the calculation can be realized rapidly through a computer program, and the application prospect is wide.
It should be noted that, all actions for acquiring signals, information or data in the present application are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
Drawings
The accompanying drawings, where like reference numerals refer to identical or similar parts throughout the several views and which are included to provide a further understanding of the present application, are included to illustrate and explain illustrative examples of the present application and do not constitute a limitation on the present application. In the drawings:
fig. 1 schematically shows a flow chart of a scientific research hot spot recommendation method based on information entropy according to an embodiment of the application.
Description of the embodiments
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and specific embodiments.
In the following description, references to "one embodiment," "an embodiment," "one example," "an example," etc., indicate that the embodiment or example so described may include a particular feature, structure, characteristic, property, element, or limitation, but every embodiment or example does not necessarily include the particular feature, structure, characteristic, property, element, or limitation. In addition, repeated use of the phrase "according to an embodiment of the present application" does not necessarily refer to the same embodiment, although it may.
Certain features have been left out of the following description for simplicity, which are well known to those skilled in the art. The notations, abbreviations and symbols in this application are as follows:
the method is a set of scientific research hotspots to be recommended, and comprises specific technical directions and keywords. For example;
Ffor the recommendation index set, the recommendation index includes: the number of published papers in the last three years, the citation rate in the last three years, the number of declared projects, the publication grade distribution of the published papers, engineering application prospect and other indexes;
is recommended index->The weight of the expert group is formulated according to the preference of the expert, and the subsequent adjustment can be carried out according to the decision distribution condition of the expert group;
for expert group of the same line, ->；/>Wherein->The attributes of the expert in registration include academic, professional, current direction, work unit, and three years of hosting research projects.
According to an embodiment of the application, a scientific research hot spot recommendation method based on information entropy is provided, as shown in fig. 1, wherein three main steps are respectively performed by an expert attribute data acquisition module, an expert clustering module and an expert group recommendation module. The expert attribute information acquisition module automatically acquires the attribute of an expert in a scientific research management system during registration, wherein the attribute comprises information such as academic, professional, current engaged direction, work unit, new three-year hosting of research project, release paper and the like, and forms an expert attribute set; the expert clustering module utilizes expert registration information feature vectors to perform clustering, calculates similarity among the experts based on a cosine similarity formula, and selects a set of research level, background and basic similarity experts; the expert group recommendation module is used for online scoring of scientific research hotspots by the selected expert group, providing a group decision weight calculation method based on an information entropy theory, and outputting the recommended scientific research hotspot direction under the group decision condition.
According to one embodiment of the application, the scientific research hot spot recommending method based on the information entropy comprises the following steps:
s1: collecting expert attribute data;
s2: performing expert clustering calculation;
s3: and performing expert group recommendation hot spot.
According to one embodiment of the application, the step S2 of the scientific research hotspot recommendation method based on information entropy specifically includes:
s21: any expert（/>) Can be individually formed into a set, i.e.)>Finishing initialization;
s22: the similarity between the experts in the collection is calculated by cosine similarity, i.eWherein->And->Respectively represent expert->And->Is the kth attribute of (a); setting a threshold value M, ifThen->；
S23: order the，/>Stopping the clustering algorithm when all expert sets are traversed, and selecting research level, background and basic similarity expert sets +.>The method comprises the steps of carrying out a first treatment on the surface of the If the expert has not completed the traversal, go to step S22.
According to one embodiment of the application, the step S3 of the scientific research hotspot recommendation method based on information entropy specifically includes:
s31: selecting expert sets by a clustering algorithmBy->The expert group in the process recommends and scores the scientific research hotspots, and the scores are recorded; constructing an expert recommendation scoring matrix according to scoring results>I.e. +.>，/>The method comprises the steps of carrying out a first treatment on the surface of the Wherein->For expert->For the scientific research hot spot->Attribute of->Results of scoring were performed.
According to an embodiment of the present application, step S31 of the information entropy-based scientific research hotspot recommendation method further includes:
s32: calculating recommendation indexThe probability of occurrence is->；
According to the information entropy theory, the smaller the information entropy of the evaluation index, the larger the variation degree of the group decision result, the more the provided information quantity, the larger the function of the group evaluation, the larger the weight of the group evaluation index, and the index can be givenEntropy weight is->；
Defining an information utility value A, whereinThe positive correlation between the information utility value and the information quantity can be effectively fed back; the information utility value is normalized to obtain the entropy weight of each index, namely index +.>Is given by the weight of；
According to an embodiment of the present application, step S32 of the information entropy-based scientific research hotspot recommendation method further includes:
s33: calculating individual expert's using weighted sum formulasScoring of each scientific research hotspot is +.>Constructing a group decision model as +.>，/>The method comprises the steps of scoring obtained group decision scores for all expert pairs of scientific research hotspots based on index weights;
by usingThe value of>According to the group decision model, calculating scientific research hotspots under the expert group decision condition>Is scored +.>Ranking recommendations are performed according to the scores, and the hot spot study direction with the highest score is recommended to be declared or focused.
According to one embodiment of the application, the specific mode of the scientific research hot spot recommending method based on the information entropy is as follows: firstly, initializing a system (the system consists of an expert attribute information acquisition module, an expert clustering module and an expert group recommendation module), automatically acquiring attribute information of an expert, including information such as academic, professional, current engaged direction, work unit, new three-year-old hosting of research project, release paper and the like, and forming an expert attribute set; then finishing the step S2 of expert clustering calculation, and selecting a set of study level, background and basic similarity experts by adopting a cosine similarity method; finally, the step of recommending hot spots by expert groups is completed, groups are formed by the experts with similar research backgrounds, group decision is realized by using an expert group recommending algorithm, the experts with similar research backgrounds are realized, and the scientific research hot spots are recommended by collective wisdom.
The foregoing examples are merely representative of several embodiments of the present invention, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit of the invention, which are within the scope of the invention. The scope of the invention should therefore be pointed out with reference to the appended claims.
Claims (3)
1. The scientific research hot spot recommending method based on the information entropy is characterized by comprising the following steps of:
s1: collecting expert attribute data;
s2: performing expert clustering calculation;
s3: performing expert group recommendation hotspots;
the step S3 specifically includes:
s31: selecting expert sets by a clustering algorithmBy->The expert group in the process recommends and scores the scientific research hotspots, and the scores are recorded; constructing an expert recommendation scoring matrix according to scoring results>I.e. +.>，/>The method comprises the steps of carrying out a first treatment on the surface of the Wherein->For expert->For the scientific research hot spot->Attribute of->A scoring result is carried out;
the method comprises the steps of providing a set of scientific research hotspots to be recommended, wherein n is a natural number and represents the number of the scientific research hotspots;
is a recommended index set, wherein m is a natural number and represents the number of indexes;
the step S31 further includes:
s32: calculating the occurrence probability of the recommended index asThe method comprises the steps of carrying out a first treatment on the surface of the According to the information entropy theory, the smaller the information entropy of the evaluation index, the larger the variation degree of the group decision result, the more the provided information quantity, the larger the function of the group evaluation, the larger the weight of the group evaluation index, and the index +.>Entropy weight is->；
Defining an information utility value A, whereinThe positive correlation between the information utility value and the information quantity can be effectively fed back; the information utility value is normalized to obtain the entropy weight of each index, namely index +.>Is given by the weight of；
Is recommended index->Weight of->。
2. The information entropy-based scientific research hotspot recommendation method of claim 1, wherein S2 specifically comprises:
s21: any expertCan form a set independently +.>I.e. +.>Finishing initialization, wherein s is a natural number;
s22: the similarity between the experts in the collection is calculated by cosine similarity, i.eWherein->And->Respectively represent expert->And->Is the kth attribute of (a); setting a threshold M, if->Then->；
S23: order the，/>Stopping the clustering algorithm when all expert sets are traversed, and selecting research level, background and basic similarity expert sets +.>The method comprises the steps of carrying out a first treatment on the surface of the If the expert has not completed the traversal, go to step S22.
3. The method for recommending scientific research hotspots based on information entropy according to claim 1, wherein the step S32 further comprises:
s33: calculating individual expert's using weighted sum formulasScoring of each scientific research hotspot is +.>Constructing a group decision model as +.>，/>For all experts to research hotspots, scoring the obtained group decision score based on the index weight, ++>Representing expert->For the scientific research hot spot->Scoring of (2);
by usingThe value of>According to the group decision model, calculating scientific research hotspots under the expert group decision condition>Is scored +.>Ranking recommendations are performed according to the scores, and the hot spot study direction with the highest score is recommended to be declared or focused.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311510648.9A CN117235373B (en) | 2023-11-14 | 2023-11-14 | Scientific research hot spot recommendation method based on information entropy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311510648.9A CN117235373B (en) | 2023-11-14 | 2023-11-14 | Scientific research hot spot recommendation method based on information entropy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117235373A CN117235373A (en) | 2023-12-15 |
| CN117235373B true CN117235373B (en) | 2024-03-15 |
Family
ID=89084625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311510648.9A Active CN117235373B (en) | 2023-11-14 | 2023-11-14 | Scientific research hot spot recommendation method based on information entropy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117235373B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114254201A (en) * | 2021-12-23 | 2022-03-29 | 深圳供电局有限公司 | Recommendation method for science and technology project review experts |
| CN115238168A (en) * | 2022-06-02 | 2022-10-25 | 郑州大学 | Self-adaptive remote medical expert recommendation method |
| WO2023035499A1 (en) * | 2021-09-10 | 2023-03-16 | 国网上海市电力公司 | Method and system for comprehensive evaluation of resilience of power distribution network |
| CN115936455A (en) * | 2022-11-10 | 2023-04-07 | 河南大学 | Probability language multi-attribute group decision method based on correlation coefficient and improved entropy |
| CN116611610A (en) * | 2023-04-24 | 2023-08-18 | 国网江苏省电力有限公司经济技术研究院 | Park comprehensive energy system scheduling evaluation method considering multi-attribute group decision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3194689A1 (en) * | 2020-10-01 | 2022-04-07 | Thomas KEHLER | Infinitely scaling a/b testing |
-
2023
- 2023-11-14 CN CN202311510648.9A patent/CN117235373B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023035499A1 (en) * | 2021-09-10 | 2023-03-16 | 国网上海市电力公司 | Method and system for comprehensive evaluation of resilience of power distribution network |
| CN114254201A (en) * | 2021-12-23 | 2022-03-29 | 深圳供电局有限公司 | Recommendation method for science and technology project review experts |
| CN115238168A (en) * | 2022-06-02 | 2022-10-25 | 郑州大学 | Self-adaptive remote medical expert recommendation method |
| CN115936455A (en) * | 2022-11-10 | 2023-04-07 | 河南大学 | Probability language multi-attribute group decision method based on correlation coefficient and improved entropy |
| CN116611610A (en) * | 2023-04-24 | 2023-08-18 | 国网江苏省电力有限公司经济技术研究院 | Park comprehensive energy system scheduling evaluation method considering multi-attribute group decision |
Non-Patent Citations (3)
| Title |
|---|
| 基于多属性智能决策方法的个人理财决策支持系统的设计与实现;祝凌凌;中国优秀硕士学位论文全文数据库 信息科技辑(第03期);I138-601 * |
| 论文推荐-传播模型构建及评价指标研究;惠淑敏;;科研管理(第10期);148-154 * |
| 面向应急决策的专家意见融合研究;叶光辉;李纲;;情报学报(第03期);32-42 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117235373A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wan et al. | A hesitant fuzzy mathematical programming method for hybrid multi-criteria group decision making with hesitant fuzzy truth degrees | |
| CN107391687B (en) | Local log website-oriented hybrid recommendation system | |
| Tang et al. | Personalized recommendation via parameter-free contextual bandits | |
| US8661034B2 (en) | Bimodal recommendation engine for recommending items and peers | |
| Li et al. | Automatic paper-to-reviewer assignment, based on the matching degree of the reviewers | |
| CN106934493B (en) | Construction method of electric power customer value evaluation model | |
| Xiao et al. | Multistage decision support framework for sites selection of solar power plants with probabilistic linguistic information | |
| Treerattanapitak et al. | Exponential fuzzy C-means for collaborative filtering | |
| CN111144831B (en) | Accurate selection screening system and method suitable for recruitment | |
| CN107194672B (en) | Review distribution method integrating academic expertise and social network | |
| Zheng et al. | Mutual benefit aware task assignment in a bipartite labor market | |
| Wang et al. | Collaborative filtering recommendation based on fuzzy clustering of user preferences | |
| Hamdani et al. | A method of weight update in group decision-making to accommodate the interests of all the decision makers | |
| CN111078859B (en) | Author recommendation method based on reference times | |
| CN117235373B (en) | Scientific research hot spot recommendation method based on information entropy | |
| Cai et al. | Query weighting for ranking model adaptation | |
| CN104462480B (en) | Comment big data method for digging based on typicalness | |
| Iyengar et al. | A collaborative filtering based model for recommending graduate schools | |
| Văduva | On solving some types of multiple attribute decision making problems | |
| Zhu et al. | Integrating a prospect theory-based consensus-reaching process into large-scale quality function deployment and its application in the evaluation of contingency plan | |
| CN110750572A (en) | Adaptive method and device for heuristic evaluation of scientific and technological achievements | |
| Guo et al. | K-loop free assignment in conference review systems | |
| Wang et al. | A pso-based web document classification algorithm | |
| Alhabashneh et al. | Adaptive information retrieval system based on fuzzy profiling | |
| Wang | Fairness Metrics for Recommender Systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |