Method and apparatus for determining relevance between news and for calculating relaevance among multiple pieces of news
US-2018197045-A1 · Jul 12, 2018 · US
Method and apparatus for determining relevance between news and for calculating relevance among multiple pieces of news
US10217025B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10217025-B2 |
| Application number | US-201615744688-A |
| Country | US |
| Kind code | B2 |
| Filing date | Oct 26, 2016 |
| Priority date | Dec 22, 2015 |
| Publication date | Feb 26, 2019 |
| Grant date | Feb 26, 2019 |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
The present invention provides a method and an apparatus for determining relevance between news and for calculating relevance among multiple pieces of news. The method for determining relevance between news comprises: comparing a piece of first news with a piece of benchmarking news to obtain a distance between the first news and the benchmarking news; comparing a piece of second news with the benchmarking news to obtain a distance between the second news and the benchmarking news; and calculating a distance differential between the distance between the first news and the benchmarking news and the distance between the second news and the benchmarking news to determine the relevance between the first news and the second news according to the distance differential.
First claim
Opening claim text (preview).
What is claimed is: 1. A method for determining relevance between news, comprising: comparing first news with benchmarking, news to obtain a distance between the first news and the benchmarking news; comparing second news with the benchmarking news to obtain a distance between the second news and the benchmarking news; calculating a distance differential between the distance between the first news and the benchmarking news and the distance between the second news and the benchmarking news and determining the relevance between the first news and the second news according to the distance differential; wherein the comparing first news with benchmarking news to obtain a distance between the first news and the benchmarking news further comprises: acquiring a feature attribute of the first news, generating a vector corresponding to the first news according to the feature attribute of the first news, and comparing the vector corresponding to the first news with a vector corresponding to the benchmarking news; and wherein the comparing second news with the benchmarking news to obtain a distance between the second news and the benchmarking news further comprises: acquiring a feature attribute of the second news, generating a vector corresponding to the second news according to the feature attribute of the second news, and comparing the vector corresponding to the second news with the vector corresponding to the benchmarking news. 2. The method according to claim 1 , wherein before comparing the first news with the benchmarking news, the method further comprises: recognizing a type of the first news and selecting the benchmarking news having a corresponding type from a set of benchmarking news. 3. The method according to claim 1 , wherein before comparing the first news with the benchmarking news, the method further comprises: acquiring a keyword in the first news and selecting the benchmarking news having the keyword from the set of benchmarking news. 4. The method according to claim 1 , wherein the acquiring a feature attribute of the first news further comprises: performing word segmentation on the first news to obtain a plurality of words, calculating a word frequency of the plurality of words of the first news, and determining the word frequency as the feature attribute of the first news; and the acquiring a feature attribute of the second news further comprises: performing word segmentation on the second news to obtain a plurality of words, calculating a word frequency of the plurality of words of the second news, and determining the word frequency as the feature attribute of the second news. 5. The method according to claim 1 , wherein determining the relevance between the first news and the second news according to the distance differential further comprises: setting the second news as a piece of news related to the first news when the distance differential is within a preset interval; and pushing the second news when it is required to push news related to the first news. 6. An apparatus for determining relevance between news, comprising: a processor; and a memory communicatively coupled to the processor and storing instructions that upon execution by the processor cause the apparatus to: compare first news with benchmarking news to obtain a distance between the first news and the benchmarking news, compare second news with the benchmarking news to obtain a distance between the second news and the benchmarking news, calculate a distance differential between the distance between the first news and the benchmarking news and the distance between the second news and the benchmarking news to determine the relevance between the first news and the second news according to the distance differential, wherein the memory further storing instructions that upon execution by the processor cause the apparatus to: acquire a feature attribute of the first news, generate a vector corresponding to the first news according to the feature attribute of the first news, compare the vector corresponding to the first news with a vector corresponding to the benchmarking news, acquire a feature attribute of the second news, generate a vector corresponding to the second news according to the feature attribute of the second news, and compare the vector corresponding to the second news with the vector corresponding to the benchmarking news. 7. The apparatus according to claim 6 , wherein the memory further storing instructions that upon execution by the processor cause the apparatus to: recognize a type of the first news and select the benchmarking news having a corresponding type from a set of benchmarking news. 8. The apparatus according to claim 6 , wherein the memory further storing instructions that upon execution by the processor cause the apparatus to: acquire a keyword in the first news and select the benchmarking news having the keyword from the set of benchmarking news. 9. The apparatus according to claim 6 , wherein the memory further storing instructions that upon execution by the processor cause the apparatus to: perform word segmentation on the first news to obtain a plurality of words, calculates a word frequency of the plurality of words of the first news, and determines the word frequency as the feature attribute of the first news; and perform word segmentation on the second news to obtain a plurality of words, calculates a word frequency of the plurality of words of the second news, and determines the word frequency as the feature attribute of the second news. 10. The apparatus according to claim 6 , wherein the memory further storing instructions that upon execution bathe processor cause the apparatus to: identify the second news as a piece of news related to the first news when the distance differential is within a preset interval; and push the second news when it is required to push news related to the first news.
Assignees
Inventors
Classifications
Matching criteria, e.g. proximity measures · CPC title
- G06F40/30Primary
Semantic analysis · CPC title
Query processing · CPC title
Information retrieval; Database structures therefor; File system structures therefor · CPC title
Physics · mapped topic
Patent family
Related publications grouped by family.
External sources
Frequently asked questions
Answers are generated from the same data shown on this page.
- What does patent US10217025B2 cover?
- The present invention provides a method and an apparatus for determining relevance between news and for calculating relevance among multiple pieces of news. The method for determining relevance between news comprises: comparing a piece of first news with a piece of benchmarking news to obtain a distance between the first news and the benchmarking news; comparing a piece of second news with the …
- Who is the assignee on this patent?
- Beijing Qihoo Technology Co
- What technology area does this patent fall under?
- Primary CPC classification G06F40/30. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Tue Feb 26 2019 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 1 related publication on this page (citations in our corpus or others sharing the same primary CPC).