Image and text data hierarchical classifiers

Abstract

Indexing data is disclosed. An image and a text data associated with a dataset are received. A tag is generated using one or more hierarchical classifiers. The image and the text data are input into at least one of the one or more hierarchical classifiers. A search index is generated based at least on the generated tag.

What is claimed is: 
     
         1 . A system for indexing data, comprising:
 a processor; and   a memory coupled with the processor, wherein the memory is configured to provide the processor with instructions which when executed cause the processor to:
 receive an image and a text data associated with a dataset; 
 generate a tag using one or more hierarchical classifiers, wherein the image and the text data are input into at least one of the one or more hierarchical classifiers; and 
 generate a search index based at least on the generated tag. 
   
     
     
         2 . The system of  claim 1 , wherein the dataset is one of a plurality of datasets processed to generate the search index. 
     
     
         3 . The system of  claim 1 , wherein the text data is a title of a subject of the dataset. 
     
     
         4 . The system of  claim 1 , wherein the dataset includes a reference to the image. 
     
     
         5 . The system of  claim 1 , wherein the instructions which when executed further cause the is processor to obtain the image from a remote network location address identified by the dataset. 
     
     
         6 . The system of  claim 1 , wherein the image is a graphical depiction of a subject of the dataset. 
     
     
         7 . The system of  claim 1 , wherein the dataset specifies attributes of a single product. 
     
     
         8 . The system of  claim 1 , wherein the generated tag is one of a plurality of tags generated by the one or more hierarchical classifiers. 
     
     
         9 . The system of  claim 1 , wherein the text data includes at least a portion of a description of a subject of the dataset. 
     
     
         10 . The system of  claim 1 , wherein the at least one of the one or more hierarchical classifiers includes an artificial neural network. 
     
     
         11 . The system of  claim 1 , wherein generating the tag includes associating the tag with the dataset. 
     
     
         12 . The system of  claim 1 , wherein one classifier of the one or more hierarchical classifiers has identified a previously identified tag that triggered another classifier of the one or more hierarchical classifiers to identify the generated tag. 
     
     
         13 . The system of  claim 1 , wherein at least one hierarchical classifier included in the one or more hierarchical classifiers is conditionally executed based on a result of a higher level hierarchical classifier included in the one or more hierarchical classifiers. 
     
     
         14 . The system of  claim 1 , wherein generating the tag includes determining a confidence indicator associated with the tag that meets a threshold. 
     
     
         15 . The system of  claim 1 , wherein generating the tag includes processing the image using a first artificial neural network, processing the text data using a second artificial neural network, and using a result of the first artificial neural network and a result of the second artificial neural network as inputs to a third artificial neural network. 
     
     
         16 . The system of  claim 1 , wherein generating the tag includes resolving a conflict between the generated tag and a data record of the dataset. 
     
     
         17 . The system of  claim 1 , wherein the search index has been generated at least in part by indexing the generated tag. 
     
     
         18 . The system of  claim 1 , wherein the search index includes an inverted index. 
     
     
         19 . A method for indexing data, comprising:
 receiving an image and a text data associated with a dataset;   using a processor to generate a tag using one or more hierarchical classifiers, wherein the image and the text data are input into at least one of the one or more hierarchical classifiers; and   generating a search index based at least on the generated tag.   
     
     
         20 . A computer program product for indexing data, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
 receiving an image and a text data associated with a dataset;   generating a tag using one or more hierarchical classifiers, wherein the image and the text data are input into at least one of the one or more hierarchical classifiers; and   generating a search index based at least on the generated tag.