Methods and apparatus to generate corrected online audience measurement data are disclosed. An example method includes determining a corrected audience count of streaming media for a demographic group by: calculating a deduplication factor for a demographic group using a first audience count, a second audience count, and a third audience count; estimating a fourth audience count for the demographic group, the fourth audience count indicative of a number of people who accessed the streaming media; estimating a fifth audience count for the demographic group, the fifth audience count indicative of a number of people who accessed text content; and applying the deduplication factor to a sum of the fourth audience count and the fifth audience count to determine the corrected audience count. The example method also includes generating ratings information for the streaming media based on subtracting the corrected audience count from the first audience count.

Methods and systems for providing information associated with a location history of a mobile device to one or more applications are disclosed. A mobile device generates one or more location history records based on one or more locations of the mobile device, each location history record comprising one or more points of interest and a duration at the one or more points of interest, receives an information request from at least one application, determines a subset of the one or more location history records that meet criteria from the information request, determines a level of permission for the at least one application based on the information request and the subset of the one or more location history records, and provides information associated with the subset of the one or more location history records to the at least one application based on the level of permission.

Social media networking applications, web sites, and services creates implicit relationships between users based on their interest or participation in real-world and optionally virtual or online activities in addition to explicitly defined peer relationships. User profiles, activity entities, and expressions may be associated with metadata to assist in searching and navigation. Metadata is implicitly associated with user profiles, activity entities, expressions, or other data entities based on user behavior using metadata collector. A metadata collector is a poll, survey, list, questionnaire, census, test, game, or other type of presentation adapted to solicit user interaction. A metadata collector is associated with metadata elements. When users interact with a metadata collector, their user profiles and the data entities included in their interactions become associated with the metadata elements of the metadata collector. These metadata element associations may then be used for any purpose.

This paper presents a practical method for measuring the impact of multiple marketing events on sales, including marketing events that are not traditionally trackable. The technique infers which of several competing media events are likely to have caused a given conversion. The method is tested using hold-out sets, and also a live media experiment for determining whether the method can accurately predict television-generated web conversions.

The present teaching relates to managing online experiments. In one example, a plurality of experiment layers is created with respect to a plurality of online users. Each experiment layer includes at least one experiment each of which includes one or more buckets associated with respective features to be experimented on. Each of the plurality of online users is assigned to a corresponding bucket in each experiment layer, such that the user is simultaneously associated with multiple experiments in different layers. User event data related to the plurality of experiment layers are collected from the plurality of online users. One or more contaminated buckets are automatically detected based on the user event data.

Disclosed here is a system that can obtain attributes of an advertisement, where an attribute has a continuous value, and a range of acceptable values is uncertain. The system can create a file including contents that when provided to a predetermined function produce a value of the attribute. Based on the file, the system can generate values corresponding to the attributes. Based on the generated values, the system can create the advertisement. The system can obtain a response data to the created advertisement and can fit a multidimensional function to the attributes and the user response data. Based on the multidimensional function, the system can determine next values and next ranges, where the next values and the next ranges indicate an improvement in the response data.

The system and method for AI driven marketing and generating personalized recommendations. The system and method provide for a digital companion that may act like a human friend to the user, understands the needs of the user, and based on this understanding, suggest one or more recommendations for products and services to the user. The predictions for the recommendation come from complex processing steps in which an intent score is calculated by intent score algorithm. The digital companion can be presented to the user through an interface, wherein digital companion has an avatar generated based on likeness of the user. The interface includes holographic models that can visually, emotionally, and verbally interact with the user.

Provided are systems and methods for face reenactment. An example method includes receiving a target video that includes at least one target frame, where the at least one target frame includes a target face, receiving a scenario including a series of source facial expressions, determining, based on the target face, a target facial expression of the target face, synthesizing, based on a parametric face model and a texture model, an output face including the target face, where the target facial expression of the target face is modified to imitate a source facial expression of the series of source facial expressions, and generating, based on the output face, a frame of an output video. The parametric face model includes a template mesh pre-generated based on historical images of faces of a plurality of individuals, where the template mesh includes a pre-determined number of vertices.

The present disclosure provides a method and system for generating a plurality of journeys for engaging a plurality of users in real-time. The system receives a first set of data associated with the plurality of users. In addition, the system fetches a second set of data associated with a plurality of past events on a plurality of platforms through one or more communication devices. Further, the system obtains a third set of data associated with a plurality of live events. Furthermore, the system analyzes the first set of data, the second set of data and the third set of data using one or more machine learning algorithms. Moreover, the system generates the plurality of journeys for engaging the plurality of users through a plurality of channels. Also, the system creates one or more goals for each of the plurality of journeys of the plurality of platforms.

A health care provider (HCP) engagement engine is disclosed. The HCP engagement engine facilitates effective communication between pharmaceutical sales representatives (medical reps) and HCPs by generating, using machine learning algorithms, messages for the medical reps to send to HCPs. The recommended messages may be sent over a network and may include email messages, text messages, or online chat messages. The recommended messages may be drafted entirely by the engagement engine or may be drafted as addenda to messages already used by the medical reps. The HCP engagement engine uses historical data on actions performed by the HCPs and medical reps, as well as data collected from historical message recommendation events, in order to produce message recommendations.