Talent recommendation method and apparatus

A recommendation method and talent technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve problems such as low flexibility and accuracy, fixed number of topics, etc., to improve accuracy and flexibility , Avoid the effect of large topic redundancy

Active Publication Date: 2017-11-03
三螺旋大数据科技(昆山)有限公司
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The above three methods all belong to simple topic evolution. When using the above methods for topic evolution, it is easy to cause the problem that the number of topics in different time windows is fixed, which i

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
  • Talent recommendation method and apparatus
  • Talent recommendation method and apparatus
  • Talent recommendation method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] See figure 1 As shown in the flowchart of the first talent recommendation method, the method includes the following steps:

[0030] Step S102, obtaining text data from a preset database; wherein, the text data includes at least one of an article, a paper, and a webpage text;

[0031] For example, the above-mentioned database can be a comprehensive database covering multiple fields (including industry, agriculture, medicine, etc.) and multiple document forms (including dissertations, conference papers, newspapers and periodicals, etc.), or a single field, specialized A professional database in the form of literature. When you use a professional database for processing, you can get popular topics in the current field and their corresponding talents.

[0032] Step S104, classify the text data according to the release time of the text data;

[0033] The classification criteria can be set in advance according to the development level of the current field, that is, the classificatio...

Embodiment 2

[0045] See figure 2 The flow chart of the second talent recommendation method shown is implemented on the basis of the talent recommendation method provided in Embodiment 1. The method includes the following steps:

[0046] Step S202: Acquire text data from a preset database; wherein, the text data includes at least one of an article, a paper, and a webpage text;

[0047] Step S204, extract the release time of the text data;

[0048] Step S206: Match the release time with multiple preset time periods respectively, and determine the time period to which the text data belongs according to the matching result;

[0049] For example, if one year is used as the time period and the theme of each year in the last ten years is obtained, the above multiple time periods can be 2017, 2016, ... until 2008, a total of 10 time periods; determine the release time of the text data The specific time period it belongs to; for example, the release time is June 22, 2016 and the time period it belongs to ...

Embodiment 3

[0061] See image 3 The flow chart of the third talent recommendation method shown is implemented on the basis of the talent recommendation method provided in the first or second embodiment; this method expands the traditional topic model into a more specific topic level by using the HDP model In order to solve the problem of using only the fixed number of topics in the time window in LDA, the method includes the following steps:

[0062] Step S302, categorizing academic articles such as papers according to time periods (also called time windows);

[0063] Step S304, using HDP to extract topics from the collection of articles in each time period;

[0064] Step S306: Obtain popular topics in the current time period according to the evolution process of the topics;

[0065] In step S308, talents are selected from article authors corresponding to the popular topics for recommendation.

[0066] It can be seen from the above steps S302 to S308 that the method first discretizes the academic ...

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 provides a talent recommendation method and apparatus. The method comprises the steps of obtaining text data from a preset database, wherein the text data at least comprises one of articles, papers and webpage texts; according to release time of the text data, classifying the text data; by adopting a layered Dirichlet process, performing topic extraction processing on the text data corresponding to each type; according to a processing result, obtaining hot topics of a current time period; and recommending authors of the text data corresponding to the hot topics as talents. According to the method and the apparatus, the topic in each time period and the current hot topics can be flexibly and accurately obtained, so that the problem of high extracted topic redundancy or topic omission caused by manual setting of a topic number is avoided, and the accuracy and flexibility of recommending the talents according to the hot topics are improved.

Description

Technical field [0001] The invention relates to the technical field of data retrieval, in particular to a method and device for recommending talents. Background technique [0002] In order to obtain the evolution of topics over time, the prior art usually adopts the following three methods: One is to combine time information into the LDA model, and introduce time factors into the LDA model, so that each topic adds a time attribute, and then Express the distribution of topics at different times; the second is to use LDA to obtain topics, and then retrieve and quantify the distribution of topics in time; the third is to discretize the text to the corresponding time window, and then according to each time window Subject extraction on the text collection. [0003] The above three methods are simple theme evolution. When the above methods are used for theme evolution, it is easy to cause the problem of a fixed number of topics in different time windows, which in turn leads to lower fle...

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
IPC IPC(8): G06F17/30
CPCG06F16/35G06F16/9535
Inventor 李微王泽华吴志成张健徐衔郭晓茹
Owner 三螺旋大数据科技(昆山)有限公司
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