Knowledge pushing method and system for scientific research tasks

A technology of knowledge push and task, applied in the field of knowledge push and system for scientific research tasks, can solve problems such as low accuracy, inability to achieve accurate push of scientific research task knowledge, single algorithm, etc., to achieve the effect of improving work efficiency

Pending Publication Date: 2022-07-08
CHENGDU AIRCRAFT INDUSTRY GROUP +1
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its shortcoming is that it completely uses the tag matching algorithm to realize the push, the algorithm is single, and it is impossible to realize the accurate push of scientific research task knowledge
It is characterized in that it first trains the preset tag topic LDA model according to the training sample and the training sample preset topic tag, uses the LDA model to calculate the text topic tag vector, and then uses the text similarity algorithm to obtain the similarity based on the results of the above processing The disadvantage is that the similarity value is calculated by the LDA model first, and then realized by the text similarity algorithm. Its accuracy depends largely on the LDA model generated by the training samples and the preset topic tags of the training samples. The accuracy is not high. , it is impossible to accurately push the knowledge of scientific research tasks

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Knowledge pushing method and system for scientific research tasks
  • Knowledge pushing method and system for scientific research tasks
  • Knowledge pushing method and system for scientific research tasks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] A knowledge push method for scientific research tasks, first classify tasks, and then describe user portraits according to different task classifications, set corresponding portrait labels for each user, and tag specific tasks under a certain category. ; For specific tasks, a hybrid similarity algorithm is used to implement knowledge push to users; the hybrid similarity algorithm includes a tag matching algorithm and a text similarity algorithm, and the recommended results of the tag matching algorithm and the text similarity algorithm are combined, and the tags The products of the recommendation scores of the matching algorithm and the text similarity algorithm and the preset weight are added together to obtain the recommended list and the recommendation score of the hybrid similarity algorithm respectively correspondingly.

[0038] Further, the weights of the label matching algorithm and the text similarity algorithm are respectively 0.6 and 0.4, then the recommendatio...

Embodiment 2

[0041] This embodiment is optimized on the basis of Embodiment 1, and the formula of the recommendation score calculated by the tag matching algorithm is as follows:

[0042]

[0043] where: N(u, i) represents the task u and knowledge i shared labels,

[0044] ω uk represent tasks u with tags k The relevance degree of , that is, the weight of the label relative to the task;

[0045] r ki Indicates the label k with knowledge i The relevance degree of , that is, the weight of the label relative to the knowledge.

[0046] Further, in the tag matching algorithm, the number of matching tags and the tag weight are considered to improve the accuracy of the recommendation result, and the tag weight is determined according to the order of the tags.

[0047] The other parts of this embodiment are the same as those of Embodiment 1, and thus are not repeated here.

Embodiment 3

[0049] This embodiment is optimized on the basis of Embodiment 1 or 2. In the text similarity algorithm, the task is firstly represented by text, the corresponding task text feature vector and knowledge document feature vector are generated, and then the cosine similarity The algorithm obtains the knowledge recommendation list and the recommendation score corresponding to each knowledge.

[0050] Further, the value of each attribute field of the task, as well as the text content of the task name and task description are grouped together, and then the keywords are extracted by the TF-IDF algorithm and the occurrence frequency of the keywords is calculated, which is represented by a vector; for any given The two space vectors A and B of , the cosine similarity θ is calculated by the dot product and the vector length, the formula is as follows:

[0051]

[0052] of which: A i , B i represent the components of each dimension of vector A and B, respectively;

[0053] Then, th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a knowledge pushing method and system oriented to scientific research tasks, and the method comprises the steps: firstly classifying the tasks, then carrying out user portrait description, setting a corresponding portrait label for each user, and carrying out the labeling processing of a specific task under a certain classification; aiming at a specific task, realizing knowledge pushing to the user by adopting a mixed similarity algorithm; the mixed similarity algorithm comprises a label matching algorithm and a text similarity algorithm, combining recommendation results of the label matching algorithm and the text similarity algorithm, and adding products of recommendation scores of the label matching algorithm and the text similarity algorithm and preset weights, and respectively and correspondingly obtaining a recommendation list to be selected and a recommendation score of the hybrid similarity algorithm. According to the method, the scientific research task is taken as a dimension, the knowledge in the knowledge database is accurately pushed to the user by adopting a mixed weighting mode of a label matching algorithm and a text similarity algorithm, and the working efficiency is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of data push methods, and in particular relates to a knowledge push method and system for scientific research tasks. Background technique [0002] In the management of scientific research projects, a large amount of data, information and knowledge are generated. However, due to the relative dispersion of knowledge and the lack of knowledge consistency, many valuable knowledge has been isolated or even buried for a long time and cannot be effectively used. Knowledge is an important The value of assets is not realized. [0003] In order to effectively improve work efficiency, it is necessary to develop a reasonable and effective knowledge push mechanism. Knowledge push in scientific research project management needs to target specific tasks. However, most push methods are based on user portraits, and no task-specific knowledge push method has been found. [0004] User portrait refers to obtaining user-relate...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/335G06F16/33G06F16/338G06F16/35G06F40/216G06F40/289
CPCG06F16/335G06F16/3344G06F16/3346G06F16/35G06F16/338G06F40/289G06F40/216
Inventor 王金安陈昱旻邓建何天豪
Owner CHENGDU AIRCRAFT INDUSTRY GROUP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap