Methods to present search keywords for image-based queries

A computer-implemented method, comprising:

• receiving multimedia data from a client computing device, the multimedia data including at least two differing content types;
• identifying at least one feature of an object of interest in the multimedia data;
• identifying a first plurality of content items associated with the multimedia data by searching at least one data store using the multimedia data, the identifying the first plurality of content items based at least in part on matching the at least one feature of the object of interest;
• obtaining a similarity confidence score for each of the first plurality of content items;
• removing at least one content item below a predetermined similarity confidence score threshold;
• identifying a second plurality of content items from one or more remaining content items;
• obtaining a plurality of keywords by identifying at least one keyword for each of the second plurality of content items;
• identifying a subset of the plurality of keywords by determining a set of unique keywords within the plurality of keywords;
• generating a search string including at least one keyword of the subset of keywords, wherein the generated search string is configured to provide the results of a keyword search of one or more data stores using the at least one of the plurality of keywords capable of selection by a user of the client computing device;
• and
• causing the generated search string to be displayed on the client computing device.

A computing system, comprising:

• at least one processor;
• and
• a memory device including instructions that, when executed by the at least one processor, cause the computing system to:
• obtain an image of an item;
• transmit the image of the item to a server computer in an image query, wherein the server computer:
• receives the image query;
• identifies at least one feature of an object of interest in the image;
• identifies a first number of features identified in content of at least two differing types, the first number of features associated with the image query, the identifying the first number of features based at least in part a match with the object of interest;
• obtains a similarity confidence score for each of the first number of features;
• removes at least one feature below a predetermined similarity confidence score threshold;
• identifies a second number of features from one or more remaining features;
• obtains a plurality of keywords associated with the image query, based at least in part on the second number of features;
• identifies a subset of the plurality of keywords by determining a set of unique keywords within the plurality of keywords;
• and
• generates at least one search string based on the subset of the plurality of keywords;
• receive the at least one search string in response to the image query, the at least one search string including at least one keyword of the plurality of keywords associated with the image;
• and
• display, on the computing system as a hyperlink, the at least one search string as a selectable option to a user, the at least one search string including at least one keyword of the subset of keywords capable of being selected by the user for a data store search.