Next user interaction prediction
AssigneeSap SE
InventorArshad Sultan
Life of this patent
Estimating the term…
Abstract
In some embodiments, a method receives a set of interactions regarding interactions with an application and generates a plurality of sequences from the set of interactions. Each sequence includes multiple interactions. A plurality of results are generated for the plurality of sequences where a result in the plurality of results is a result for a sequence in the plurality of sequences. The method then trains a prediction network using the plurality of sequences and the plurality of results. The prediction network is usable to predict a next user interaction on the application when being used on a user interface.
Claims20
A method for predicting a user interaction, the method comprising:
- receiving, by a computing device, a set of interactions regarding interactions with an application;
- generating, by the computing device, a plurality of sequences from the set of interactions, wherein each sequence includes multiple interactions;
- generating, by the computing device, a plurality of results for the plurality of sequences, wherein a result in the plurality of results is a result for a sequence in the plurality of sequences;
- and
- training, by the computing device, a prediction network using the plurality of sequences and the plurality of results, wherein the prediction network is usable to predict a next user interaction on the application when being used on a user interface,
- wherein a maximum length of each sequence is defined according to a business process related to the application, and
- wherein the prediction network comprises a neural network that is trained based on the plurality of sequences, wherein the maximum length reduces a raw data size for training the neural network.
A non-transitory computer-readable storage medium containing instructions, that when executed, control a computer system to be operable for:
- receiving a set of interactions regarding interactions with an application;
- generating a plurality of sequences from the set of interactions, wherein each sequence includes multiple interactions;
- generating a plurality of results for the plurality of sequences, wherein a result in the plurality of results is a result for a sequence in the plurality of sequences;
- and
- training a prediction network using the plurality of sequences and the plurality of results, wherein the prediction network is usable to predict a next user interaction on the application when being used on a user interface,
- wherein a maximum length of each sequence is defined according to a business process related to the application, and
- wherein the prediction network comprises a neural network that is trained based on the plurality of sequences, wherein the maximum length reduces a raw data size for training the neural network.
An apparatus comprising:
- one or more computer processors;
- and
- a non-transitory computer-readable storage medium comprising instructions, that when executed, control the one or more computer processors to be configured for:
- receiving a set of interactions regarding interactions with an application;
- generating a plurality of sequences from the set of interactions, wherein each sequence includes multiple interactions;
- generating a plurality of results for the plurality of sequences, wherein a result in the plurality of results is a result for a sequence in the plurality of sequences;
- and
- training a prediction network using the plurality of sequences and the plurality of results, wherein the prediction network is usable to predict a next user interaction on the application when being used on a user interface,
- wherein a maximum length of each sequence is defined according to a business process related to the application, and
- wherein the prediction network comprises a neural network that is trained based on the plurality of sequences, wherein the maximum length reduces a raw data size for training the neural network.
Dependencies are inferred from the claim text.