Method and user device for generating predicted survey participation data at the user device
A method for generating predicted survey participation data at a current user device. A server collects training behavioral data related to a website from a plurality of user devices. The server also collects training survey participation data related to the website from at least some of the plurality of user devices. The server analyzes the training survey participation data and the corresponding training behavioral data to infer correlations between the training survey participation data and the corresponding training behavioral data. The server further generates predictive survey participation patterns based on the inferred correlations. The server transmits the predictive survey participation patterns to the current user device. The current device collects current behavioral data related to the website. Then, the current user device determines predicted survey participation data for the current user device in relation to the website based on the current behavioral data and the predictive survey participation patterns.
1. A method for generating a predicted intent of a user at a user device, the method comprising:
collecting by a processing unit of a training server training behavioral data from a plurality of user devices, the training behavioral data being representative of a series of actions performed by a user of each of the plurality of user devices while visiting a specific website;
collecting by the processing unit of the training server training survey participation data from at least some of the plurality of user devices, the training survey participation data corresponding to survey information received from the users of the at least some of the plurality of user devices when participating to a web survey related to the visit of the specific website, the survey information received from the users of the at least some of the plurality of user devices being at least partially related to an intent of the users for visiting the specific website;
determining by the processing unit of the training server the intent of the users of the at least some of the plurality of user devices in relation to the visit of the specific website based on the training survey participation data;
processing by a neural network executed by the processing unit of the training server the intent of the users of the at least some of the plurality of user devices and the corresponding training behavioral data to infer correlations between the intent of the users of the at least some of the plurality of user devices and the corresponding training behavioral data;
generating by the neural network executed by the processing unit of the training server a predictive user intent model based on the inferred correlations, the predictive user intent model comprising weights of the neural network, the predictive user intent model allowing to extrapolate a user intent using behavioral data;
transmitting the predictive user intent model comprising the weights of the neural network from the training server to a current user device and storing the predictive user intent model comprising the weights of the neural network at a memory of the current user device;
collecting by a processing unit of the current user device current behavioral data, the current behavioral data being representative of a series of actions performed by a user of the current user device while visiting the specific website; and
determining by the processing unit of the current user device a predicted intent of the user of the current user device in relation to the specific website, the determination being performed by the execution of a lightweight version of the neural network using the weights comprised in the predictive user intent model transmitted by the training server and stored at the current user device to process the current behavioral data for determining the predicted intent of the user of the current user device in relation to the specific website.
2. The method of claim 1 , wherein the training behavioral data and the current behavioral data comprise at least one of the following: visited URLs of the specific website, a keyword occurrence during the visit of the specific website, a time spent on a visited web page of the specific website, a scrolling activity on a visited web page of the specific website, a backtracking activity on a visited web page of the specific website, an action firing activity on a visited web page of the specific website, an exit activity on a visited web page of the specific website, and a hit activity on a visited web page of the specific website.
3. The method of claim 1 , wherein the current user device is a mobile device.
4. The method of claim 3 , wherein the current user device is a mobile device consisting of a smartphone or a tablet.
5. The method of claim 1 , wherein the predicted intent of the user of the current user device in relation to the specific website consists of information gathering, price learning, purchase, account management or user support.