System and method for recognizing domain specific named entities using domain specific word embeddings

    公开(公告)号:US11687721B2

    公开(公告)日:2023-06-27

    申请号:US17380881

    申请日:2021-07-20

    Applicant: Intuit Inc.

    Abstract: Systems and methods for recognizing domain specific named entities are disclosed. An example method may be performed by one or more processors of a text incorporation system and include extracting a number of terms from a text under consideration, identifying, among the number of terms, a set of unmatched terms that do not match any of a plurality of known terms, passing each respective unmatched term to a vectorization module, embedding a vectorized version of each respective unmatched term in a vector space, comparing each vectorized version to known term vectors, passing, to a machine learning model, candidate terms corresponding to known term vectors closest to the vectorized versions, identifying, using the machine learning model, a best candidate term for each respective unmatched term, mapping the best candidate terms to unmatched terms in the text under consideration, and incorporating the text under consideration into the system based on the mappings.

    Last Mile Churn Prediction
    114.
    发明公开

    公开(公告)号:US20230195476A1

    公开(公告)日:2023-06-22

    申请号:US17552629

    申请日:2021-12-16

    Applicant: Intuit Inc.

    Inventor: Prateek Anand

    CPC classification number: G06F9/445 G06N7/005

    Abstract: A method implements last mile churn prediction. The method includes retrieving data during a user session in response to a trigger. The data includes a list of screen identifiers and a corresponding list of timestamps. The method further includes converting the list of timestamps to a list of time deltas. The list of time deltas includes a time delta that identifies an amount of time between two timestamps of the list of timestamps. The method further includes generating a churn risk from the list of screen identifiers and the list of time deltas. The churn risk identifies a probability that the user session will be terminated. The method further includes transmitting an intervention to intervene in the user session based on the churn risk.

    Method and system of dynamic model selection for time series forecasting

    公开(公告)号:US11663493B2

    公开(公告)日:2023-05-30

    申请号:US16262208

    申请日:2019-01-30

    Applicant: Intuit Inc.

    CPC classification number: G06N3/126 G06F16/285 G06N5/04

    Abstract: Forecasts are provided based on dynamic model selection for different sets of time series. A model comprises a transformation and a prediction algorithm. Given a time series, a transformation is selected for the time series and a prediction algorithm is selected to make a forecast based on the transformed time series. Sets of time series are distinguished from each other based on diverse sparsities, temporal scales and other time series attributes. A model is dynamically selected based on time series attributes to increase forecasting accuracy and decrease forecasting computation time. The dynamic model selection is based on the creation of a meta-model from historical sets of historical time series.

    Display screen with graphical user interface

    公开(公告)号:USD986257S1

    公开(公告)日:2023-05-16

    申请号:US29773195

    申请日:2021-03-08

    Applicant: Intuit Inc.

    Abstract: FIG. 1 is a front view of a display screen with graphical user interface, showing a first transitional image;
    FIG. 2 is a front view of a display screen with graphical user interface, showing a second transitional image; and,
    FIG. 3 is a front view of a display screen with graphical user interface, showing a third transitional image.
    The broken lines showing a display screen, text, and other elements of the graphical user interface in the figures form no part of the claimed design. The appearance of the transitional image sequentially transitions between the images shown in FIGS. 1-3. No ornamental aspects are associated with the process or period in which one image transitions to another image.

Patent Agency Ranking