US2022027404A1PendingUtilityA1

Determining and utilizing actual purpose of user-assembled collection of electronic content items

Assignee: GOOGLE LLCPriority: Jul 30, 2019Filed: Oct 11, 2021Published: Jan 27, 2022
Est. expiryJul 30, 2039(~13 yrs left)· nominal 20-yr term from priority
G06F 16/9535G06F 16/9574G06F 16/535G06N 20/00G06F 16/5866G06F 16/51G06Q 30/0263G06F 16/437G06Q 30/0269G06F 16/55G06F 16/435
51
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

Implementations are described for determining, based on a user-assembled collection of electronic content items, at least one actual purpose for the assembled collection. Those implementations are further directed to selecting an additional electronic content item based on the at least one actual purpose being assigned to the additional electronic content item in an electronic database. Those implementations are yet further directed to, responsive to the selecting, causing a suggestion for the additional electronic content item to be rendered at a client device associated with a user account that is assigned to the user-assembled collection.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A method implemented by one or more processors, the method comprising:
 identifying electronic content items based on the electronic content items having each been assigned to a particular collection of a user account;   generating, for each of the electronic content items, corresponding candidate purposes and corresponding measures for the electronic content item,
 wherein generating the corresponding candidate purposes and the corresponding measures, for each of the electronic content items, is based on processing the electronic content item, and 
 wherein each of the corresponding measures defines a corresponding strength of correlation, of one of the corresponding candidate purposes, to a corresponding one of the electronic content items; 
   determining that a particular candidate purpose, of the corresponding candidate purposes, is an actual purpose for the particular collection, wherein determining that the particular candidate purpose is the actual purpose for the particular collection is based on both:
 (i) a quantity of occurrences of the particular candidate purpose amongst the electronic content items, and 
 (ii) magnitudes of the corresponding measures for the particular candidate purpose; 
   responsive to determining the particular candidate purpose is the actual purpose for the particular collection:
 causing a suggestion to be rendered that includes a title that corresponds to the particular candidate purpose and that includes a selectable confirm option; and 
   responsive to selection of the selectable confirm option during rendering of the suggestion:
 automatically assigning the title to the particular collection. 
   
     
     
         2 . The method of  claim 1 , wherein determining, based on the magnitudes of the corresponding measures for the particular candidate purpose, that the particular candidate purpose is the actual purpose for the particular collection comprises:
 generating a cumulative measure of the magnitudes of the corresponding measures for the particular candidate purpose; and   determining that the particular candidate purpose is the actual purpose based on the cumulative measure.   
     
     
         3 . The method of  claim 2 , wherein determining, based on the magnitudes of the corresponding measures for the particular candidate purpose, that the particular candidate purpose is the actual purpose for the particular collection further comprises:
 determining an alternative cumulative measure for an alternate candidate purpose of the corresponding candidate purposes, wherein determining the alternative cumulative measure is based on the magnitudes of the corresponding measures for the alternate candidate purpose; and   determining that the particular candidate purpose is the actual purpose based on comparing the cumulative measure to the alternate cumulative measure.   
     
     
         4 . The method of  claim 3 , wherein determining, based on the quantity of occurrences of the particular candidate purpose amongst the electronic content items, that the particular candidate purpose is the actual purpose for the particular collection comprises:
 determining that the quantity is greater than an alternate quantity of occurrences of an alternate particular candidate purpose, of the corresponding candidate purposes, amongst the electronic content items.   
     
     
         5 . The method of  claim 4 , wherein generating the corresponding candidate purposes and the corresponding measures comprises, for a given image that is one of the electronic content items:
 processing the image, using one or more machine learning models, to determine one or more classifications of one or more objects included in the image; and   determining the corresponding candidate purposes and the corresponding measures, for the given image, based on a database that stores associations of object classifications to candidate purposes and measures.   
     
     
         6 . The method of  claim 2 , wherein determining, based on the quantity of occurrences of the particular candidate purpose amongst the electronic content items, that the particular candidate purpose is the actual purpose for the particular collection comprises:
 determining that the quantity is greater than an alternate quantity of occurrences of an alternate particular candidate purpose, of the corresponding candidate purposes, amongst the electronic content items.   
     
     
         7 . The method of  claim 1 , wherein determining, based on the quantity of occurrences of the particular candidate purpose amongst the electronic content items, that the particular candidate purpose is the actual purpose for the particular collection comprises:
 determining that the quantity is greater than an alternate quantity of occurrences of an alternate particular candidate purpose, of the corresponding candidate purposes, amongst the electronic content items.   
     
     
         8 . The method of  claim 1 , wherein generating the corresponding candidate purposes and the corresponding measures comprises, for a given image that is one of the electronic content items:
 processing the image, using one or more machine learning models, to determine one or more classifications of one or more objects included in the image; and   determining the corresponding candidate purposes and the corresponding measures, for the given image, based on a database that stores associations of object classifications to candidate purposes and measures.   
     
     
         9 . The method of  claim 1 , further comprising:
 selecting a given additional electronic content item from a corpus of additional content items, wherein selecting the given additional electronic content item is based on the actual purpose, for the particular collection, being assigned to the given additional electronic content item in an electronic database; and   responsive to selecting the given additional content item:   causing an additional content suggestion, for the given additional electronic content item, to be rendered at a client device associated with the user account,   wherein the additional content suggestion is selectable to cause the given additional electronic content item to be rendered at the client device and/or to add the additional electronic content item to the particular collection.   
     
     
         10 . A system comprising:
 memory storing instructions;   one or more processors executing the instructions, stored in the memory, to cause one or more of the processors to:
 identify electronic content items based on the electronic content items having each been assigned to a particular collection of a user account; 
 generate, for each of the electronic content items, corresponding candidate purposes and corresponding measures for the electronic content item,
 wherein in generating the corresponding candidate purposes and the corresponding measures one or more of the processors are to generate the corresponding candidate purposes and the corresponding measures, for each of the electronic content items, based on processing the electronic content item, and 
 wherein each of the corresponding measures defines a corresponding strength of correlation, of one of the corresponding candidate purposes, to a corresponding one of the electronic content items; 
 
 determine that a particular candidate purpose, of the corresponding candidate purposes, is an actual purpose for the particular collection, wherein determining that the particular candidate purpose is the actual purpose for the particular collection is based on both:
 (i) a quantity of occurrences of the particular candidate purpose amongst the electronic content items, and 
 (ii) magnitudes of the corresponding measures for the particular candidate purpose; 
 
 responsive to determining the particular candidate purpose is the actual purpose for the particular collection:
 cause a suggestion to be rendered that includes a title that corresponds to the particular candidate purpose and that includes a selectable confirm option; and 
 
 responsive to selection of the selectable confirm option during rendering of the suggestion:
 automatically assign the title to the particular collection. 
 
   
     
     
         11 . The system of  claim 10 , wherein in determining, based on the magnitudes of the corresponding measures for the particular candidate purpose, that the particular candidate purpose is the actual purpose for the particular collection, one or more of the processors are to:
 generate a cumulative measure of the magnitudes of the corresponding measures for the particular candidate purpose; and   determine that the particular candidate purpose is the actual purpose based on the cumulative measure.   
     
     
         12 . The system of  claim 11 , wherein in determining, based on the magnitudes of the corresponding measures for the particular candidate purpose, that the particular candidate purpose is the actual purpose for the particular collection, one or more of the processors are to:
 determine an alternative cumulative measure for an alternate candidate purpose of the corresponding candidate purposes, wherein determining the alternative cumulative measure is based on the magnitudes of the corresponding measures for the alternate candidate purpose; and   determine that the particular candidate purpose is the actual purpose based on comparing the cumulative measure to the alternate cumulative measure.   
     
     
         13 . The system of  claim 11 , wherein in determining, based on the quantity of occurrences of the particular candidate purpose amongst the electronic content items, that the particular candidate purpose is the actual purpose for the particular collection, one or more of the processors are to:
 determine that the quantity is greater than an alternate quantity of occurrences of an alternate particular candidate purpose, of the corresponding candidate purposes, amongst the electronic content items.   
     
     
         14 . The system of  claim 10 , wherein in determining, based on the quantity of occurrences of the particular candidate purpose amongst the electronic content items, that the particular candidate purpose is the actual purpose for the particular collection, one or more of the processors are to:
 determine that the quantity is greater than an alternate quantity of occurrences of an alternate particular candidate purpose, of the corresponding candidate purposes, amongst the electronic content items.   
     
     
         15 . The system of  claim 10 , wherein in generating the corresponding candidate purposes and the corresponding measures one or more of the processors are to, for a given image that is one of the electronic content items:
 process the image, using one or more machine learning models, to determine one or more classifications of one or more objects included in the image; and   determine the corresponding candidate purposes and the corresponding measures, for the given image, based on a database that stores associations of object classifications to candidate purposes and measures.   
     
     
         16 . The system of  claim 10 , wherein one or more of the processors, in executing the instructions, are further to:
 select a given additional electronic content item from a corpus of additional content items, wherein selecting the given additional electronic content item is based on the actual purpose, for the particular collection, being assigned to the given additional electronic content item in an electronic database; and   responsive to selecting the given additional content item:
 cause an additional content suggestion, for the given additional electronic content item, to be rendered at a client device associated with the user account, 
 wherein the additional content suggestion is selectable to cause the given additional electronic content item to be rendered at the client device and/or to add the additional electronic content item to the particular collection.

Join the waitlist — get patent alerts

Track US2022027404A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.