Content Item Rearrangement Within A Digital Whiteboard

Abstract

Content items are rearranged within a digital collaboration space (e.g., a digital whiteboard) based on category metadata determined for the content items using one or more learning models. The content items are added to the digital collaboration space by one or more users. For each of the content items, category metadata is determined using a learning model that processes information associated with the content item. A rearrangement of the content items is determined based on the category metadata determined for each of the content items. The content items, rearranged according to the rearrangement, are then output to a layer of the digital collaboration space. Other rearrangements of the content items can be determined based on non-category metadata associated with the content items, and the content items, rearranged according to those other rearrangements, can be output to other layers of the digital collaboration space.

What is claimed is: 
     
         1 . A method, comprising:
 training a machine learning model to determine metadata associated with digital whiteboard content items;   outputting, based on input obtained from one or more user devices, content items at initial locations within a digital whiteboard;   outputting rearrangements of the content items, determined based on at least first metadata and second metadata determined for each of the content items using the trained machine learning model, to different layers of the digital whiteboard; and   further training the trained machine learning model based on information, obtained from a user device of the one or more user devices, indicating, for a content item of the content items, a new location different from a rearranged location within one of the rearrangements.   
     
     
         2 . The method of  claim 1 , comprising:
 instantiating the digital whiteboard using digital whiteboard software of a software platform during a video conference implemented using conferencing software of the software platform.   
     
     
         3 . The method of  claim 1 , comprising:
 determining the rearrangements based on input received from at least one of the one or more user devices.   
     
     
         4 . The method of  claim 1 , comprising:
 determining, using the trained machine learning model, that two or more of the content items correspond to common content; and   determining, based on the two or more of the content items corresponding to the common content, to use only one of the two or more of the content items within a rearrangement of the rearrangements.   
     
     
         5 . The method of  claim 1 , comprising:
 determining, for a rearrangement of the rearrangements, to rearrange two or more of the content items to represent a flowchart indicative of a sequence of operations.   
     
     
         6 . The method of  claim 1 , wherein the outputting of the rearrangements to the different layers of the digital whiteboard enables the user device to navigably access, within the digital whiteboard, either of a first rearrangement or a second rearrangement at a given time. 
     
     
         7 . The method of  claim 1 , wherein the rearrangements include at least a first rearrangement and a second rearrangement, and wherein locations of the content items relative to one another in the second rearrangement are different from the initial locations and from the locations of the content items in the first rearrangement. 
     
     
         8 . The method of  claim 1 , wherein the first metadata for the content item corresponds to text or non-text content visually represented within the content item and the second metadata for the content item corresponds to data not visually represented within the content item. 
     
     
         9 . The method of  claim 1 , wherein one or more of the content items is added to the digital whiteboard by processing an image representing a physical content item within a physical space. 
     
     
         10 . The method of  claim 1 , wherein the content items are color coded to identify source locations of the content items within the digital whiteboard. 
     
     
         11 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
 training a machine learning model to determine metadata associated with digital whiteboard content items;   outputting, based on input obtained from one or more user devices, content items at initial locations within a digital whiteboard;   outputting rearrangements of the content items, determined based on at least first metadata and second metadata determined for each of the content items using the trained machine learning model, to different layers of the digital whiteboard; and   further training the trained machine learning model based on information, obtained from a user device of the one or more user devices, indicating, for a content item of the content items, a new location different from a rearranged location within one of the rearrangements.   
     
     
         12 . The non-transitory computer readable medium of  claim 11 , wherein the input is obtained while the one or more user devices are connected to a video conference. 
     
     
         13 . The non-transitory computer readable medium of  claim 11 , the operations comprising:
 generating a document representing a rearrangement of the rearrangements.   
     
     
         14 . The non-transitory computer readable medium of  claim 11 , wherein one of the rearrangements includes a flowchart generated to represent a sequence associated with at least some of the content items. 
     
     
         15 . A system, comprising:
 one or more memories; and   one or more processors configured to execute instructions stored in the one or more memories to:
 train a machine learning model to determine metadata associated with digital whiteboard content items; 
 output, based on input obtained from one or more user devices, content items at initial locations within a digital whiteboard; 
 output rearrangements of the content items, determined based on at least first metadata and second metadata determined for each of the content items using the trained machine learning model, to different layers of the digital whiteboard; and 
 further train the trained machine learning model based on information, obtained from a user device of the one or more user devices, indicating, for a content item of the content items, a new location different from a rearranged location within one of the rearrangements. 
   
     
     
         16 . The system of  claim 15 , wherein the content items are added to the digital whiteboard based on input data obtained from multiple user devices of the one or more user devices. 
     
     
         17 . The system of  claim 15 , wherein the rearrangements include a first rearrangement and a second rearrangement, wherein an arrangement of the content items within the first rearrangement is different from an arrangement of the content items within the second rearrangements. 
     
     
         18 . The system of  claim 15 , wherein a first rearrangement of the rearrangements is based on the first metadata and a second rearrangement of the rearrangements is based on the second metadata. 
     
     
         19 . The system of  claim 15 , wherein at least some of the content items are sticky notes. 
     
     
         20 . The system of  claim 15 , wherein the digital whiteboard is implemented using a unified communication as a service platform.