User-Guided Term Suggestions

Abstract

Methods and apparatus related to providing user-guided term suggestions. Some implementations may be directed to identifying user input that includes at least one term and identifying a user-initiated activity near the term. An edit term may be identified based on the user-initiated activity near the term, an edit position in the edit term may be identified, and one or more candidate terms may be identified based on the edit term. Similarity measures for the candidate terms may be determined. The similarity measure of a given candidate term of the candidate terms may be based on the edit position. One or more of the candidate terms may be selected as suggested terms based on the similarity measures and the selected suggested terms provided for potential replacement of the edit term.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 identifying user input that includes at least one term;   identifying a user-initiated activity near the at least one term;   identifying an edit term of the at least one term based on the user-initiated activity near the at least one term;   identifying an edit position in the edit term;   identifying one or more candidate terms based on the edit term;   determining similarity measures for the candidate terms, wherein the similarity measure of a given candidate term of the candidate terms is based on the edit position;   selecting one or more of the candidate terms as suggested terms based on the similarity measures; and   providing the selected suggested terms for potential replacement of the edit term.   
     
     
         2 . The method of  claim 1 , wherein at least one of the candidate terms is identified based on the edit position. 
     
     
         3 . The method of  claim 1 , wherein identifying the user-initiated activity is based on one or more of detecting a user selection in the display and detecting a cursor position in the display. 
     
     
         4 . The method of  claim 3 , wherein identifying the user-initiated activity is based on comparison of a time duration of the user selection or the cursor position to a time threshold. 
     
     
         5 . The method of  claim 4 , wherein the time threshold is inversely proportional to one or more of an area size covered by the user-initiated activity, a number of terms within the area covered by the user-initiated activity, a screen size, a screen resolution, and a font size. 
     
     
         6 . The method of  claim 1 , wherein the edit position includes a single position and the single position is identified when the user-initiated activity is directly adjacent to a single character in the edit term. 
     
     
         7 . The method of  claim 1 , wherein the number of characters in the edit position is inversely proportional to one or more of a size of the edit term, a screen size, a screen resolution, and a font size. 
     
     
         8 . The method of  claim 1 , wherein the similarity measure for the given candidate term is based on an edit similarity score, wherein the edit similarity score is indicative of the difference between the edit term and the given candidate term near the edit position. 
     
     
         9 . The method of  claim 8 , wherein the edit similarity score is a real number between zero and one. 
     
     
         10 . The method of  claim 8 , wherein the edit similarity score equals one if the candidate term differs from the edit term by the replacement, addition or deletion of one or more characters in the edit position, and the edit similarity score equals zero otherwise. 
     
     
         11 . The method of  claim 8 , wherein the similarity measure for the given candidate term is based on multiplying the similarity measure with the edit similarity score. 
     
     
         12 . The method of  claim 1 , wherein the edit position is identified based on the user-initiated activity. 
     
     
         13 . The method of  claim 1 , wherein the similarity measure for the given candidate term is further based on one or more of popularity of the given candidate term, relevance of the given candidate term to the edit term, historical edits using the given candidate term, and contextual usage of the edit term. 
     
     
         14 . The method of  claim 1 , wherein identifying an edit term from the at least one term further includes:
 identifying an edit area corresponding to the user-initiated activity;   identifying a set of the terms within the edit area;   determining a relevance score for each term in the set of the terms, wherein the relevance score for each term is based on a likelihood of replacing the term; and   selecting the edit term from the set of the terms based on the relevance score.   
     
     
         15 . The method of  claim 14 , wherein identifying the edit area is based on one or more of an area size covered by the user-initiated activity, a number of the terms within the area covered by the user-initiated activity, a screen size, a screen resolution, and a font size. 
     
     
         16 . A system including memory and one or more processors operable to execute instructions stored in the memory, wherein the instructions include instructions to:
 identify user input that includes at least one term;   identify a user-initiated activity near the at least one term;   identify an edit term of the at least one term based on the user-initiated activity near the at least one term;   identify an edit position in the edit term;   identify one or more candidate terms based on the edit term;   determine similarity measures for the candidate terms, wherein the similarity measure of a given candidate term of the candidate terms is based on the edit position;   select one or more of the candidate terms as suggested terms based on the similarity measures; and   provide the selected suggested terms for potential replacement of the edit term.   
     
     
         17 . The system of  claim 16 , wherein the instructions to identify the at least one of the candidate terms include instructions to identify the at least one of the candidate terms based on the edit position. 
     
     
         18 . The system of  claim 16 , wherein the instructions to identify the user-initiated activity include instructions to identify the user-initiated activity based on one or more of detecting a user selection in the display and detecting a cursor position in the display. 
     
     
         19 . The system of  claim 18 , wherein the instructions to identify the user-initiated activity include instructions to identify the user-initiated activity based on comparison of a time duration of the user selection or the cursor position to a time threshold. 
     
     
         20 . The system of  claim 19 , wherein the time threshold is inversely proportional to one or more of an area size covered by the user-initiated activity, a number of terms within the area covered by the user-initiated activity, a screen size, a screen resolution, and a font size. 
     
     
         21 . The system of  claim 16 , wherein the number of characters in the edit position is inversely proportional to one or more of a size of the edit term, a screen size, a screen resolution, and a font size. 
     
     
         22 . The system of  claim 16 , wherein the instructions to determine the similarity measure for the given candidate term include instructions to determine the similarity measure for the given candidate term based on an edit similarity score, wherein the edit similarity score is indicative of the difference between the edit term and the given candidate term near the edit position. 
     
     
         23 . The system of  claim 16 , wherein the instructions to determine the similarity measure for the given candidate term include instructions to determine the similarity measure for the given candidate term based on one or more of popularity of the given candidate term, relevance of the given candidate term to the edit term, historical edits using the given candidate term, and contextual usage of the edit term. 
     
     
         24 . The system of  claim 16 , wherein the instructions to identify an edit term further include instructions to:
 identify an edit area corresponding to the user-initiated activity;   identify a set of the terms within the edit area;   determine a relevance score for each term in the set of the terms, wherein the relevance score for each term is based on a likelihood of replacing the term; and   select the edit term from the set of the terms based on the relevance score.   
     
     
         25 . The system of  claim 24 , wherein the instructions to identify the edit area further include instructions to identify the edit area based on one or more of an area size covered by the user-initiated activity, a number of the terms within the area covered by the user-initiated activity, a screen size, a screen resolution, and a font size. 
     
     
         26 . A non-transitory computer readable storage medium storing computer instructions executable by a processor to perform a method comprising:
 identifying user input that includes at least one term;   identifying a user-initiated activity near the at least one term;   identifying an edit term of the at least one term based on the user-initiated activity near the at least one term;   identifying an edit position in the edit term;   identifying one or more candidate terms based on the edit term;   determining similarity measures for the candidate terms, wherein the similarity measure of a given candidate term of the candidate terms is based on the edit position;   selecting one or more of the candidate terms as suggested terms based on the similarity measures; and   providing the selected suggested terms for potential replacement of the edit term.