SYSTEMS AND METHODS OF MULTIMODAL CLUSTERING USING MACHINE LEARNING
This disclosure relates generally to artificial intelligence structured to generate models based on multimodal input. At least one aspect is directed to a system. The system can include a data processing system comprising memory and one or more processors to generate, by a first model trained using machine learning with input including one or more first features each associated with data structures having a plurality of distinct data types, one or more second features compatible with one of the distinct data types, generate, by a second model trained with input including the second features, a plurality of cluster classifications each compatible with one or more of the distinct data types, and cause a user interface to present one or more of the data structures rendered according to a spatial structure based on the second features and the cluster classifications.
1 . A system, comprising:
a data processing system comprising memory and one or more processors to:
generate, by a first model trained using machine learning with input including one or more first features each associated with data structures having a plurality of distinct data types, one or more second features compatible with one of the distinct data types;
generate, by a second model trained with input including the second features, a plurality of cluster classifications each compatible with one or more of the distinct data types; and
cause a user interface to present one or more of the data structures rendered according to a spatial structure based on the second features and the cluster classifications.
2 . The system of claim 1 , the data processing system to:
instruct the user interface to present one or more of the data structures rendered having an indication identifying a corresponding one of the cluster classifications.
3 . The system of claim 1 , wherein the data structures comprise text, an image, or geospatial data.
4 . The system of claim 1 , the data processing system to:
train, by a first machine learning engine compatible with the plurality of distinct data types and with input including one or more of the data structures, the first model.
5 . The system of claim 4 , the data processing system to:
train, by a second machine learning engine compatible with the second features and with input including one or more of the data structures, the second model.
6 . The system of claim 1 , the data processing system to:
generate, based on the cluster classifications, one or more cluster objects; and
generate one or more links between the cluster objects and one or more of the data structures.
7 . The system of claim 1 , the spatial structure corresponding to a coordinate system compatible with the second features.
8 . The system of claim 1 , each of the second features compatible with each of the data types.
9 . The system of claim 1 , each of the second features compatible with a corresponding one of the data types.
10 . A method, comprising:
generating, by a first model trained using machine learning with input including one or more first features each associated with data structures having a plurality of distinct data types, one or more second features compatible with one of the distinct data types;
generating, by a second model trained with input including the second features, a plurality of cluster classifications each compatible with one or more of the distinct data types; and
causing a user interface to present one or more of the data structures rendered according to a spatial structure based on the second features and the cluster classifications.
11 . The method of claim 10 , further comprising:
instructing the user interface to present one or more of the data structures rendered having an indication identifying a corresponding one of the cluster classifications.
12 . The method of claim 10 , wherein the data structures comprise text, an image, or geospatial data.
13 . The method of claim 10 , further comprising:
training, by a first machine learning engine compatible with the plurality of distinct data types and with input including one or more of the data structures, the first model.
14 . The method of claim 13 , further comprising:
training, by a second machine learning engine compatible with the second features and with input including one or more of the data structures, the second model.
15 . The method of claim 10 , further comprising:
generating, based on the cluster classifications, one or more cluster objects; and
generating one or more links between the cluster objects and one or more of the data structures.
16 . The method of claim 10 , the spatial structure corresponding to a coordinate system compatible with the second features.
17 . The method of claim 10 , each of the second features compatible with each of the data types.
18 . The method of claim 10 , each of the second features compatible with a corresponding one of the data types.
19 . A computer readable medium including one or more instructions stored thereon and executable by a processor to:
generate, by the processor via a first model trained using machine learning with input including one or more first features each associated with data structures having a plurality of distinct data types, one or more second features compatible with one of the distinct data types;
generate, by the processor via a second model trained with input including the second features, a plurality of cluster classifications each compatible with one or more of the distinct data types; and
cause, the processor, a user interface to present one or more of the data structures rendered according to a spatial structure based on the second features and the cluster classifications.
20 . The computer readable medium of claim 19 , wherein the computer readable medium further includes one or more instructions executable by the processor to:
instruct the user interface to present one or more of the data structures rendered having an indication identifying a corresponding one of the cluster classifications,
wherein the data structures comprise text, an image, or geospatial data, and the spatial structure correspond to a coordinate system compatible with the second features.