Content classification system

• US 10,536,728 B2
• Filed: 08/18/2010
• Issued: 01/14/2020
• Est. Priority Date: 08/18/2009
• Status: Active Grant

• Current Assignee: Jinni
• Original Assignee: Jinni
• Inventors: Rimon, Mori, Meshulam, Ram, Ben-Zaken, Izik, Glick, Yosi
• Primary Examiner(s): Skibinsky, Anna
• Application Number:
  US12/859,248
• Publication Number:
  US 20170164011A1
• Time in Patent Office: 3,436 Days
• Field of Search: None
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: H04N 21/232 Content retrieval operation locally within server, e.g. reading video streams from disk arrays storage management G06F3/0604; details of querying and searching of video data from a database G06F16/739

Abstract

A method includes operating a content crawler over a machine communication network to form a set of input content; operating a mapper on a machine memory comprising the input content to form non-transitory machine logic comprising genes for the content, wherein operating the mapper comprises the application of previously mapped genes for the input content to the mapping of subsequent genes for the input content; and applying the genes to a machine memory storing a database of content from which user recommendations are formed.

Claims

1. An apparatus to transform textual content from content files, received over a machine network, into display elements forming an operable user interface on a machine display customized to a specific user;

wherein the content files are selected from the group consisting of content gathered from a weekly TV schedule, video on-demand offerings, and items recorded on a personal video player,

the apparatus comprising;

an input to receive the files from a web crawler;

a mapper operable on the received files to generate a gene vector for each file;

a comparator to determine a similarity between the files by comparing a gene vector P and a gene vector Q for pairs of the files, wherein Pi and Qi represent a salience of the gene in corresponding position i of the vector P and the vector Q;

wherein each gene in the vectors is assigned to a category having a weight Ci between 0 and 1 signifying the category'"'"'s relative importance for determining similarity;

each gene having a weight Ri based on its rarity;

the comparator determining a degree of similarity between the pair of files, as follows;

Sim(P,Q)=E(1−

|Pi−

Qi|)×

Ci×

Ri×

TU(Pi,Qi)

where TU is a tuning function for the effect of salience differences between Pi and Qi on the degree of similarity; and

a display generator to apply the degree of similarity to selecting the display elements thus forming the operable user interface with a subset of operable content controls of high relevance and confidence for the specific user.

2. The apparatus of claim 1, further comprising:

the mapper to apply a plurality of mapping strategies; and

the mapper to employ voting procedures to resolve differences of outcome among the plurality of mapping strategies.

3. The apparatus of claim 1, further comprising:

the mapper distinguishing between salience scores and confidence values for each gene.

4. The apparatus of claim 1, further comprising:

the mapper identifying discourse structure from the linguistic features of the files; and

the mapper increasing a weight applied to the linguistic features that appear in discourse structures rated higher than others to a relevance of each gene.

5. The apparatus of claim 1, further comprising:

the mapper tagging a particular file of the files with one or more sentiment gene, reflecting subjective experience-related expressions in multiple free text sources referencing content of the particular file;

the mapper determining collective verdicts for the sentiment gene if there is a high degree of agreement among the free text sources in regard to the content of the particular file; and

the mapper marking the sentiment gene with a controversy indicator if a consensus does not exist among the free text sources in regard to the content of the particular file.

6. The apparatus of claim 5, further comprising:

the collective verdicts reflecting sentiment negation of the content of the particular file.

7. The apparatus of claim 1, further comprising:

the mapper applying filtering to the genes to associate a score and a confidence value to each of the second genes.

8. The apparatus of claim 1, further comprising:

the mapper organizing the genes in a taxonomy which distinguishes between content category types and comprises a hierarchy within the content category types.

9. The apparatus of claim 1, further comprising:

the mapper organized as a cascade of machine procedures, each procedure in the cascade of machine procedures configured to map at least one content category types to gene mappings; and

the gene mappings for a first content category type produced in a first machine procedure at a first stage of the cascade of machine procedures utilized to produce next gene mappings for a second content category type in a second machine procedure at a second stage of the cascade of machine procedures latter to the first stage.

10. The apparatus of claim 1, further comprising:

the mapper generating a reference semantic vector for a reference set of input content previously rated by the specific user;

the mapper grouping the reference semantic vector into taste clusters wherein each of the taste clusters represents one of multiple tastes of the specific user; and

the mapper building a taste profile based on the multiple tastes of the specific user.