GRAPH AUGMENTATION FOR NEW APPLICATIONS USING MACHINE LEARNING TECHNIQUES
A graph may be initially seeded with nodes representing applications and tags describing subjective qualities of the applications. A system generates tags for new applications using a supervised machine learning model. The system extracts signals from a newly detected application. The system inputs the signals into a machine learning model, and receives, as output from the model, tags that correspond to the new application and levels of confidence for each tag. The system updates the graph to include one or more nodes corresponding to the new application, with the tags linked to the one or more nodes with an edge that has a weight corresponding to the level of confidence. The system receives a query corresponding to the tag and provides a response to the query based on the one or more nodes corresponding to the new application.
1 . A method for augmenting a graph based on a new application, the method comprising:
extracting signals from the new application;
inputting the extracted signals into a machine learning model;
receiving, as output from the machine learning model, a set of tags that correspond to the new application and levels of confidence for each tag in the set of tags;
updating the graph to include one or more nodes corresponding to the new application, with each tag in the set of tags linked to the one or more nodes with an edge, the edge having a weight corresponding to the level of confidence of the tag;
receiving a query corresponding to a tag in the set of tags; and
providing a response to the query based on the one or more nodes corresponding to the new application.
2 . The method of claim 1 , wherein extracting signals from the new application comprises extracting signals from a graphical user interface of the new application and from a page on an application store corresponding to the new application.
3 . The method of claim 1 , wherein the machine learning model is trained with training data comprising a subset of the graph, the subset of the graph including one or more nodes labeled with tags.
4 . The method of claim 1 , wherein the machine learning model is trained by:
detecting a representative signal in the extracted signals;
mapping the representative signal to a set of training data; and
training the machine learning model with the set of training data.
5 . The method of claim 1 , further comprising selecting the machine learning model from a plurality of candidate machine learning models, each of the candidate machine learning models trained on signals corresponding to a different type of application.
6 . The method of claim 1 , further comprising filtering the set of tags by, for each tag in the set of tags:
comparing the confidence level of the tag to a threshold confidence level; and
responsive to the confidence level of the tag not exceeding the threshold confidence level, filtering the tag from the set of tags.
7 . The method of claim 1 , wherein providing the response to the query comprises providing a subset of the graph comprising nodes connected to the tag by one or more edges.
8 . A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed by one or more processors, causing the one or more processors to perform operations, the instructions comprising instructions to:
extract signals from the new application;
input the extracted signals into a machine learning model;
receive, as output from the machine learning model, a set of tags that correspond to the new application and levels of confidence for each tag in the set of tags;
update the graph to include one or more nodes corresponding to the new application, with each tag in the set of tags linked to the one or more nodes with an edge, the edge having a weight corresponding to the level of confidence of the tag;
receive a query corresponding to a tag in the set of tags; and
provide a response to the query based on the one or more nodes corresponding to the new application.
9 . The non-transitory computer-readable medium of claim 8 , wherein the instructions for extracting signals from the new application comprise instructions to extract signals from a graphical user interface of the new application and from a page on an application store corresponding to the new application.
10 . The non-transitory computer-readable medium of claim 8 , wherein the machine learning model is trained with training data comprising a subset of the graph, the subset of the graph including one or more nodes labeled with tags.
11 . The non-transitory computer-readable medium of claim 8 , wherein the machine learning model is trained by:
detecting a representative signal in the extracted signals;
mapping the representative signal to a set of training data; and
training the machine learning model with the set of training data.
12 . The non-transitory computer-readable medium of claim 8 , wherein the instructions further comprise instructions to select the machine learning model from a plurality of candidate machine learning models, each of the candidate machine learning models trained on signals corresponding to a different type of application.
13 . The non-transitory computer-readable medium of claim 8 , wherein the instructions further comprise instructions to filter the set of tags by, for each tag in the set of tags:
comparing the confidence level of the tag to a threshold confidence level; and
responsive to the confidence level of the tag not exceeding the threshold confidence level, filtering the tag from the set of tags.
14 . The non-transitory computer-readable medium of claim 8 , wherein the instructions for providing the response to the query comprise instructions to provide a subset of the graph comprising nodes connected to the tag by one or more edges.
15 . A system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
extracting signals from the new application;
inputting the extracted signals into a machine learning model;
receiving, as output from the machine learning model, a set of tags that correspond to the new application and levels of confidence for each tag in the set of tags;
updating the graph to include one or more nodes corresponding to the new application, with each tag in the set of tags linked to the one or more nodes with an edge, the edge having a weight corresponding to the level of confidence of the tag;
receiving a query corresponding to a tag in the set of tags; and
providing a response to the query based on the one or more nodes corresponding to the new application.
16 . The system of claim 15 , wherein the operations for extracting signals from the new application comprise extracting signals from a graphical user interface of the new application and from a page on an application store corresponding to the new application.
17 . The system of claim 15 , wherein the machine learning model is trained with training data comprising a subset of the graph, the subset of the graph including one or more nodes labeled with tags.
18 . The system of claim 15 , wherein the machine learning model is trained by:
detecting a representative signal in the extracted signals;
mapping the representative signal to a set of training data; and
training the machine learning model with the set of training data.
19 . The system of claim 15 , wherein the operations further comprise selecting the machine learning model from a plurality of candidate machine learning models, each of the candidate machine learning models trained on signals corresponding to a different type of application.
20 . The system of claim 15 , wherein the operations further comprise filtering the set of tags by, for each tag in the set of tags:
comparing the confidence level of the tag to a threshold confidence level; and
responsive to the confidence level of the tag not exceeding the threshold confidence level, filtering the tag from the set of tags.