Determination of content score

• US 10,325,033 B2
• Filed: 10/28/2016
• Issued: 06/18/2019
• Est. Priority Date: 10/28/2016
• Status: Active Grant

• Current Assignee: Searchmetrics GmbH
• Original Assignee: Searchmetrics GmbH
• Inventors: Kagoshima, Alexander, Londenberg, Kai, Xu, Fang
• Primary Examiner(s): Wilson, Kimberly L
• Application Number:
  US15/337,268
• Publication Number:
  US 20180121430A1
• Time in Patent Office: 963 Days
• Field of Search: 707706
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A computer-implemented method of determining a content score of resource content comprises receiving one or more main topics highly relevant to the resource content; receiving the resource content; determining, using the one or more main topics, a content score value indicating the content score; and outputting the determined content score value, a corresponding system, computing device and non-transitory computer-readable storage medium.

Claims

1. A computer-implemented method of determining a content score of one or more resource contents, the computer-implemented method comprising:

a) receiving in a processor from a user the one or more resource contents and one or more main topics, wherein the one or more resource contents are contents of webpages which are completed or partially completed;

b) automatically with the processor determining an overall content score value of the one or more resource contents in real-time while the user is creating or editing the one or more resource contents by;

i) determining individual content score values which include a quantity score value and a language content score value,

ii) determining weighted individual content score values by weighting the individual content score values, and

iii) summing the weighted individual content score values;

c) automatically with the processor determining instructions to improve the overall content score value;

d) outputting the overall content score value and presenting to the user in a form of a document or a webpage;

e) outputting the instructions as textual instructions, graphical instructions, or both;

f) editing the one or more resource contents by the user based on the instructions to increase the overall content score value of the one or more resource contents so that one or more webpages become more relevant according to the one or more main topics and will be ranked higher by one or more search engines;

wherein determining the quantity score value includes;

i) calculating a length ratio by dividing a length of the one or more resource contents by a target length value; and

ii) applying a function to the length ratio so that values of the length ratio which are greater than 0 and less than 0.5 are amplified and the values of the length ratio which are greater than 0.5 are attenuated, wherein the function is a smooth and strictly monotonically increasing function; and

wherein the language content score value is determined by automatically determining a language of the one or more resource contents, and wherein the determining of the language content score value includes;

i) calculating two or more of the following;

a weighted word distribution score value, a weighted unigram score value, a weighted bigram score value, and a weighted punctuation score value; and

ii) averaging or multiplying at least two of the following;

the weighted word distribution score value, the weighted unigram score value, the weighted bigram score value, and the weighted punctuation score value.

2. The computer-implemented method of claim 1, wherein the method includes outputting the individual content score values and presenting to the user in the document or the webpage.

3. The computer-implemented method of claim 1, wherein the one or more resource contents include at least one of:

a textual element, a structural element, a title element, a heading element, a table element, a media element, a graphical element, a video element, an interactive element, a link element, a map element, and an app element; and

wherein the one or more resource contents include at least one of a design, a layout, or an arrangement.

4. The computer-implemented method of claim 1, wherein the method includes automatically obtaining one or more relevant topics from a plurality of resources on a computer network;

and

wherein the individual content score values include a relevance score value which is determined by using the one or more relevant topics.

5. The computer-implemented method of claim 4, wherein the computer network is a World-Wide Web.

6. The computer-implemented method of claim 4, wherein calculating the relevance score value includes:

i) automatically converting the one or more resource contents into one or more content vectors and the one or more relevant topics into one or more relevant topic vectors;

ii) determining one or more relevant-topic similarity values indicating similarity of the one or more relevant topic vectors to the one or more content vectors; and

iii) aggregating the one or more relevant-topic similarity values to calculate the relevance score value.

7. The computer-implemented method of claim 6, wherein Word2Vec converts the one or more resource contents into the one or more content vectors and the one or more relevant topics into the one or more relevant topic vectors.

8. The computer-implemented method of claim 1, wherein the individual content score values include a relevance score value and the method includes:

i) automatically converting the one or more resource contents into one or more content vectors and the one or more main topics into one or more main topic vectors;

ii) determining one or more main-topic similarity values indicating similarity of the one or more main topic vectors to the one or more content vectors; and

iii) aggregating the one or more main-topic similarity values to calculate the relevance score value.

9. The computer-implemented method of claim 8, wherein Word2Vec converts the one or more resource contents into the one or more content vectors and the one or more main topics into the one or more main topic vectors.

10. A computer-implemented method to determine a content score of one or more resource contents comprising:

a) receiving in a processor from a user the one or more resource contents and one or more main topics, wherein the one or more resource contents are contents of webpages which are completed or partially completed;

b) automatically with the processor determining an overall content score value of the one or more resource contents in real-time while the user is creating or editing the one or more resource contents by;

1) determining individual content score values which include a quantity score value, a relevance score value, and a language content score value,

2) determining weighted individual content score values by weighting the individual content score values, and

3) summing the weighted individual content score values;

c) automatically with the processor determining instructions to improve the overall content score value of the one or more resource contents;

d) outputting the overall content score value and presenting to the user in a form of a document or a webpage;

e) outputting the instructions as textual instructions, graphical instructions, or both; and

f) editing the one or more resource contents by the user based on the instructions to increase the overall content score value of the one or more resource contents so that one or more webpages become more relevant according to the one or more main topics and will be ranked higher by one or more search engines;

wherein determining the quantity score value includes;

i) calculating a length ratio by dividing a length of the one or more resource contents by a target length value; and

ii) applying a function to the length ratio so that values of the length ratio which are greater than 0 and less than 0.5 are amplified and the values of the length ratio which are greater than 0.5 are attenuated, wherein the function is a smooth and strictly monotonically increasing function; and

wherein determining the relevance score value includes automatically obtaining one or more relevant topics from a plurality of resources on a computer network and using the one or more relevant topics to determine the relevance score value;

or

wherein determining the relevance score value includes;

i) automatically converting the one or more resource contents into one or more content vectors, and automatically converting the one or more main topics into one or more main topic vectors or the one or more relevant topics into one or more relevant topic vectors;

ii) determining one or more main topic similarity values indicating similarity of the one or more main topic vectors to the one or more content vectors, or determining one or more relevant topic similarity values indicating similarity of the one or more relevant topic vectors to the one or more content vectors;

iii) aggregating the one or more main topic similarity values or the one or more relevant topic similarity values to calculate the relevance score value; and

wherein determining the language content score value includes;

i) automatically determining a language of the one or more resource contents;

ii) calculating two or more of the following;

a weighted word distribution score value, a weighted unigram score value, a weighted bigram score value, and a weighted punctuation score value; and

iii) averaging or multiplying at least two of the following;

the weighted word distribution score value, the weighted unigram score value, the weighted bigram score value, and the weighted punctuation score value.

11. The computer-implemented method of claim 10, wherein the method includes outputting the individual content score values and presenting to the user in the document or the webpage.

12. The computer-implemented method of claim 10, wherein the one or more resource contents include at least one of:

a textual element, a structural element, a title element, a heading element, a table element, a media element, a graphical element, a video element, an interactive element, a link element, a map element, and an app element; and

wherein the one or more resource contents include at least one of a design, a layout, or an arrangement.

13. The computer-implemented method of claim 10, wherein the computer network is a World-Wide Web.

14. The computer-implemented method of claim 10, wherein Word2Vec converts the one or more resource contents into the one or more content vectors and the one or more main topics into the one or more main topic vectors.