公开(公告)号：US20240256301A1

公开(公告)日：2024-08-01

申请号：US18421105

申请日：2024-01-24

申请人： Walmart Apollo, LLC

发明人： Rahul Radhakrishnan Iyer ,  Malay Kumar Patel ,  Saurabh Kumar ,  Sushant Kumar ,  Kannan Achan

IPC分类号： G06F9/451 ,  G06F40/40

CPC分类号： G06F9/451 ,  G06F40/40

摘要： Systems and methods for context aware engagement are disclosed. A request for a user interface, including a user identifier, is received. A set of features associated with the user identifier are obtained and a user embedding is generated by applying an autoencoder to the set of features. A set of potential tasks associated with an enrollment portion of the user interface is obtained. A task embedding is generated for each task in the set of potential tasks. A user-task affinity is generated by comparing the user embedding to each task embedding. A ranked set of tasks is generated by ranking each task based on the user-task affinity. A set of interface elements related to the highest ranked tasks in the ranked set of tasks is generated. A user interface including interface elements is generated and transmitted to a device that requested the user interface.

公开(公告)号：US12026357B2

公开(公告)日：2024-07-02

申请号：US17589871

申请日：2022-01-31

申请人： Walmart Apollo, LLC

发明人： Priyanka Bhatt ,  Anshika Singh ,  Shankar Bhargava ,  Cole Warren Dutcher ,  Muzhou Liang ,  Saurabh Kumar

IPC分类号： G06F3/0484 ,  G10L15/18 ,  G10L15/22

CPC分类号： G06F3/0484 ,  G10L15/18 ,  G10L15/22 ,  G10L2015/223

摘要： A method implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media. The method can include receiving, via a computer network, a user interaction signal from a user device for a user. The method further can include after receiving the user interaction signal, determining, in real-time via a machine learning model, a plurality of user intent labels based at least in part on transaction data, interaction data, and incident data for the user. The machine learning model can include pre-trained based on historical input data and historical output data associated with multiple users comprising the user. The historical input data can comprise historical feature embedding vectors for historical transaction data, historical interaction data, and historical incident data associated with the multiple users. The historical output data can include historical intent labels determined based at least in part on user-uttered intents by the multiple users in historical conversation data, identified by natural language understanding. In some embodiments, the method also can include, after determining the plurality of user intent labels, determining, in real-time, one or more user intent candidates of the plurality of user intent labels based on a confidence threshold. In a few embodiments, the method further can include, after determining the one or more user intent candidates, determining, in real-time, one or more user interface components for the one or more user intent candidates. After determining the one or more user interface components, the method further can include transmitting, via the computer network, the one or more user interface components to be presented on a user interface executed on the user device for the user. Other embodiments are described.

公开(公告)号：US20220155926A1

公开(公告)日：2022-05-19

申请号：US17589871

申请日：2022-01-31

申请人： Walmart Apollo, LLC

发明人： Priyanka Bhatt ,  Anshika Singh ,  Shankar Bhargava ,  Cole Warren Dutcher ,  Muzhou Liang ,  Saurabh Kumar

IPC分类号： G06F3/0484 ,  G10L15/18 ,  G10L15/22

摘要： A method implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media. The method can include receiving, via a computer network, a user interaction signal from a user device for a user. The method further can include after receiving the user interaction signal, determining, in real-time via a machine learning model, a plurality of user intent labels based at least in part on transaction data, interaction data, and incident data for the user. The machine learning model can include pre-trained based on historical input data and historical output data associated with multiple users comprising the user. The historical input data can comprise historical feature embedding vectors for historical transaction data, historical interaction data, and historical incident data associated with the multiple users. The historical output data can include historical intent labels determined based at least in part on user-uttered intents by the multiple users in historical conversation data, identified by natural language understanding. In some embodiments, the method also can include, after determining the plurality of user intent labels, determining, in real-time, one or more user intent candidates of the plurality of user intent labels based on a confidence threshold. In a few embodiments, the method further can include, after determining the one or more user intent candidates, determining, in real-time, one or more user interface components for the one or more user intent candidates. After determining the one or more user interface components, the method further can include transmitting, via the computer network, the one or more user interface components to be presented on a user interface executed on the user device for the user. Other embodiments are described.