Metadata tag description generation

Patent metadata

Field	Value
Publication number	US-2016358096-A1
Application number	US-201514728440-A
Country	US
Kind code	A1
Filing date	Jun 2, 2015
Priority date	Jun 2, 2015
Publication date	Dec 8, 2016
Grant date	—

Abstract

One or more techniques and/or systems are provided for metadata tag evaluation. For example, a metadata tag, associated with content, may be identified (e.g., a hashtag #ML may be used to tag a social network post). A set of characters, within the content, may be evaluated utilizing a probability matrix and the content to identify an expanded metadata tag (e.g., an expanded hashtag “machine learning”). Descriptive content, such as websites, articles, social network posts, and/or other content associated with the expanded metadata tag, may be retrieved. A description for the metadata tag may be generated based upon the descriptive content (e.g., a definition for machine learning). In this way, the description, related metadata tags, and/or supplemental content may be provided to users having an interest in learning about the metadata tag.

First claim

1 . A method of improving computer search results by extending a computer search index with generated metadata tag descriptions, the method comprising:
obtaining, at a computing device, content comprising a metadata tag comprising textual characters; generating, with the computing device, words corresponding to the textual characters utilizing a probability matrix that identifies probabilities that one or more textual characters represent one or more words based on other textual characters of a same metadata tag and based on the obtained content; generating, with the computing device, an expanded version of the metadata tag, the expanded metadata tag comprising the generated words in place of the corresponding textual characters of the metadata tag; retrieving, at the computing device, descriptive content providing further information about the expanded metadata tag, the descriptive content differing from the obtained content; and generating, at the computing device, a description for the metadata tag based upon the retrieved descriptive content.

2 . The method of claim 1 , comprising:
receiving a search query comprising the metadata tag; identifying the expanded metadata tag as an expansion of the metadata tag; and providing the generated description for the metadata tag as a search result for the query.

3 . The method of claim 1 , comprising:
obtaining a second content comprising a second metadata tag, the obtained second content also comprising the metadata tag; and identifying the second metadata tag as being related to the metadata tag.

4 . The method of claim 3 , comprising:
receiving a search query comprising the metadata tag; and providing both the description for the metadata tag and, as a suggestion, the second metadata tag.

5 - 7 . (canceled)

8 . The method of claim 1 , wherein the generating the words corresponding to the textual characters comprises:
identifying a first set of one or more words corresponding to a first set of one or more textual characters based upon the first set of one or more textual characters having a first probability of representing the first set of one or more words, within the probability matrix, above a threshold; identifying a second set of one or more words corresponding to for a second set of one or more textual characters based upon the second set of one or more textual characters having a second probability of representing the second set of one or more words, within the probability matrix, above the threshold; and including the first and second sets of one or more words within the expanded metadata tag based upon a phrase, comprising the first and second sets of one or more words having a phrase probability of being represented by the textual characters of the metadata tag, within the probability matrix, above a phrase threshold.

9 . The method of claim 1 , the generating the description comprising:
extracting a descriptive phrase from the descriptive content; and responsive to the descriptive phrase occurring within the descriptive content above a threshold, including the descriptive phrase within the description.

10 . The method of claim 1 , the generating the description comprising:
generating a first description candidate and a second description candidate for the metadata tag based upon the descriptive content; and receiving a user selection of either the first description candidate or the second description candidate for utilization in generating the description for the metadata tag.

11 . The method of claim 1 , comprising:
responsive to determining that the expanded metadata tag corresponds to at least one of spam or explicit content, marking at least one of the metadata tag or the generated description as at least one of spam or explicit content.

12 . The method of claim 1 , further comprising:
associating a first temporal identifier with the generated description, the first temporal identifier corresponding to a first time range during which the generated description is descriptive of the metadata tag; generating a second description for the metadata tag associated with a second time range, the generated second description differing from the generated description and based on a second descriptive content that differs from the descriptive content; and associating a second temporal identifier with the generated second description, the second temporal identifier corresponding to the second time range during which the generated second description is descriptive of the metadata tag.

13 . (canceled)

14 . A computing device for improving computer search results by extending a computer search index with generated metadata tag descriptions, the computing device comprising:
one or more processing units; and computer-readable memory comprising computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to:
obtain content comprising a metadata tag comprising textual characters;
generate words corresponding to the textual characters utilizing a probability matrix that identifies probabilities that one or more textual characters represent one or more words based on other textual characters of a same metadata tag and based on the obtained content;
generate an expanded version of the metadata tag, the expanded metadata tag comprising the generated words in place of the corresponding textual characters of the metadata tag;
retrieve descriptive content providing further information about the expanded metadata tag, the descriptive content differing from the obtained content; and
generate a description for the metadata tag based upon the retrieved descriptive content.

15 . The computing device of claim 14 , wherein the computer-readable memory comprises further computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to:
receive a search query comprising the metadata tag; identify the expanded metadata tag as an expansion of the metadata tag; and provide the generated description for the metadata tag as a search result for the query.

16 . The computing device of claim 14 , wherein the computer-readable memory comprises further computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to:
obtain a second content comprising a second metadata tag, the obtained second content also comprising the metadata tag; identify the second metadata tag as being related to the metadata tag; receive a search query comprising the metadata tag; and provide both the description for the metadata tag and, as a suggestion, the second metadata tag.

17 . (canceled)

18 . The computing device of claim 14 , wherein the computer-executable instructions directed to generating the words corresponding to the textual characters comprise further computer-executable instructions, which, when executed by the one or more processing units, cause the computing device to:
identify a first set of one or more words corresponding to a first set of one or more textual characters based upon the first set of one or more textual characters having a first probability of representing the first set of one or more words, within the probability matrix, above a threshold; identify a second set of one or more words corresponding to a second set of one or more textual characters based upon the second set of one or more textual characters having a second probability of representing the second set of one or more words, within the probability matrix, above the thresh

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Bannur Sushma Nagesh
• Alonso Omar
• Hentschel Martin

Classifications

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/907 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/7867

  using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings · CPC title

• G06N99/005 Primary

  Physics · mapped topic

• G06F17/3082

  Physics · mapped topic