Back to results
US 11,776,006 B2Granted
Survey generation framework
AssigneeDell Products L.P.
InventorsBijan Kumar Mohanty, Hung Dinh, Divya Maddi, Cleber Souza
Life of this patent
Estimating the term…
Abstract
In one aspect, an example methodology implementing the disclosed techniques includes, by a survey workflow module, receiving a survey request event for which a survey is requested and generating a first feature vector for the survey request event, wherein the first feature vector comprises features extracted from the survey request event. The method also includes predicting, by a first trained prediction module, whether the survey request event will result in a survey based on the first feature vector, wherein the first trained prediction module is trained using a training dataset generated from a corpus of historical survey request event-survey data.
Claims15
A computer implemented method to predict whether a survey request event will result in a survey, the method comprising:
- extracting, by a survey processing system, a plurality of features from historical survey request event-survey data, the plurality of features indicating a source of the survey request event, a type of survey request event, whether the survey requested by the survey request event is an internal survey or an external survey, and whether the survey requested by the survey request event will or will not result in a survey, wherein the plurality of features influence a prediction of whether to generate a survey;
- generating, by the survey processing system, a training dataset comprising a plurality of training samples, each training sample of the plurality of training samples comprising the plurality of features extracted from the historical survey request event-survey data;
- training, by the survey processing system, a first machine learning (ML) model to predict whether to generate a survey for a survey request event using the training dataset, wherein training the first ML model includes inputting the plurality of training samples to the first ML model;
- receiving, by the survey processing system, a survey request event for which a survey is requested, the survey request event being generated by an enterprise system;
- and
- responsive to receiving the survey request event:
- generating, by the survey processing system, a first feature vector for the survey request event, wherein the first feature vector comprises features extracted from the survey request event;
- predicting, by the survey processing system using the first ML model, whether the survey request event will result in a survey based on the first feature vector;
- responsive to a prediction that the survey request event will result in a survey, generating, by the survey processing system, a survey for the survey request event;
- and
- responsive to a prediction that the survey request event will not result in a survey, not generating, by the survey processing system, a survey for the survey request event.
8 more elements
A system comprising:
- one or more non-transitory machine-readable mediums configured to store instructions;
- and
- one or more processors configured to execute the instructions stored on the one or more non-transitory machine-readable mediums, wherein execution of the instructions causes the one or more processors to:
- extract a plurality of features from historical survey request event-survey data, the plurality of features indicating a source of the survey request event, a type of survey request event, and whether the survey requested by the survey request event is an internal survey or an external survey, and whether the survey requested by the survey request event will or will not result in a survey, wherein the plurality of features influence a prediction of whether to generate a survey;
- generate a training dataset comprising a plurality of training samples, each training sample of the plurality of training samples comprising the plurality of features extracted from historical survey request event-survey data;
- train a first machine learning (ML) model to predict whether to generate a survey for a survey request event using the training dataset, wherein training the first ML model includes inputting the plurality of training samples to the first ML model;
- receive a survey request event for which a survey is requested, the survey request event being generated by an enterprise system;
- and
- responsive to receipt of the survey request event:
- generate a first feature vector for the survey request event, wherein the first feature vector comprises features extracted from the survey request event;
- predict, using the first ML model, whether the survey request event will result in a survey based on the first feature vector;
- responsive to a prediction that the survey request event will result in a survey, generate a survey for the survey request event;
- and
- responsive to a prediction that the survey request event will not result in a survey, not generate a survey for the survey request event.
11 more elements
A non-transitory, computer-readable storage medium has encoded thereon instructions that, when executed by one or more processors, causes a process to be carried out, the process comprising:
- extracting, by a survey processing system, a plurality of features from historical survey request event-survey data, the plurality of features indicating a source of the survey request event, a type of survey request event, whether the survey requested by the survey request event is an internal survey or an external survey, and whether the survey requested by the survey request event will or will not result in a survey, wherein the plurality of features influence a prediction of whether to generate a survey;
- generating, a training dataset comprising a plurality of training samples, each training sample of the plurality of training samples comprising the plurality of features extracted from the historical survey request event-survey data;
- training a first machine learning (ML) model to predict whether to generate a survey for a survey request event using the training dataset, wherein training the first ML model includes inputting the plurality of training samples to the first ML model;
- receiving a survey request event for which a survey is requested, the survey request event being generated by an enterprise system;
- and
- responsive to receiving the survey request event:
- generating, by the survey processing system, a first feature vector for the survey request event, wherein the first feature vector comprises features extracted from the survey request event;
- predicting, by the survey processing system using the first ML model, whether the survey request event will result in a survey based on the first feature vector;
- responsive to a prediction that the survey request event will result in a survey, generating, by the survey processing system, a survey for the survey request event;
- and
- responsive to a prediction that the survey request event will not result in a survey, not generating, by the survey processing system, a survey for the survey request event.
8 more elements
Dependencies are inferred from the claim text.