Google Inc.

Microsoft Technology Licensing, LLC

Jia Liu

Shankar R Ponnekanti

Deepak Ravichandran

Yijian Bai

Sittichai Jiampojamarn

Manojav Patil

Xincheng Zhang

Dongmin Zhang

Jeffrey William Pasternack

Michael Bachman

Haowen Ning

Pujita Mathur

Kelly K Hosokawa

Ryan A Espiritu

Howard Mario Narvaez

Neil Cruz Pomerleau

Arya Ghatak Choudhury

Akshaya Subbaraya Bhat

Ngoc M Vu

Yizhou Pan

Christian Wilhelm Kurt Byza

Ning Xu

Methods are presented for classifying responses to communications. One method includes presenting, in a first user interface (UI), a message from a sender to a recipient requesting a response. The first UI includes response options of a first classification, a second classification, and an entry field for entering a free text message. Another operation is for receiving a recipient response with a selection of: (a) the first or the second button and (b) the free text message entered in the text entry field. The method further includes generating a featurized recipient response based on the free text message and the selection. An acceptance machine-learning (ML) model calculates a classification value of the recipient response from a set of possible classification values based on the featurized recipient response. The method further includes presenting, in a second UI for the sender, an indicator for the message and the calculated classification value.

Communication response analyzer

Sharing online with granularity is described, including providing content for presenting to a user; receiving input from the user indicating identification of a portion of the content; associating with another user a notice of availability of the content; receiving a request from the another user, the request identifies the content; and providing the content for presenting to the another user, such that at least a part of the portion of the content is positioned for presenting without navigation input from the another user.

Sharing online with granularity

Privacy-protected search is described, including obtaining a set of search results responsive to a search input from a first user; determining, from the search results and based on a social graph, that a first search result associated with a second user is indicated as keeping an identity of the second user hidden; determining whether other search results in the set are indicated as keeping respective identities of associated other users hidden; calculating a score for the first search result based at least on the determinations, the score indicates the likelihood of the first user guessing the identity of the second user; and determining whether to provide to the first user the first search result based on the score for the first search result.

Privacy-protected search

A computerized method and system operable to build a device identifier similarity model with online event signals and determine similar network device identifiers. A processing circuit receives a first set of network device identifiers. The processing circuit represents each network device identifier of the first set by feature data associated with each network device identifier's network activity, where the feature data is associated with the content clicked-on or converted-on. The processing circuit applies abstractions on the feature data to form concepts. The processing circuit derives at least one hierarchy of feature data based on the keywords and concepts of the feature data. The processing circuit expands the feature data based on the derived at least one hierarchy of feature data and generates the device identifier similarity model based on the expanded feature data. The processing circuit is also capable of determining long-term and short-term history events.

Device identifier similarity models derived from online event signals

A computerized method for generating a representative model for a plurality of different models identified by similar feature data. A processing circuit receives a plurality of different models, each model configured for use in generating a second set of network user identifiers based on a first set of network user identifiers. The processing circuit receives feature data for each of the plurality of different models, each feature data having a corresponding feature weight data. The processing circuit identifies similar models within the plurality of different models based on a similarity of the feature data between models within the plurality of different models. The processing circuit generates the representative model to represent the similar models. The representative model may be used to generate the second set of network user identifiers based on the feature data and corresponding weight data of the representative model.

Generating a representative model for a plurality of models identified by similar feature data

A computerized method of creating a classifier model to determine whether a network user should be added to a list of similar network users. A first list of network users, a second list of network users who are not on the first list of network users and characteristic data associated with the network users' network activity are received. A time period is designated. A first category of network activities performed by a network user on the first list within the designated time period is identified. A second category of network activities performed at any time by network users on the second list is identified. A third category of network activities performed by network users on the first list at a time outside of the designated time period is identified. The classifier model is generated based on the first, second and third categories of network activities.

Creating a classifier model to determine whether a network user should be added to a list

A popularity score or rating may be provided for a third-party content item. The popularity score may be compared with an average score of similar genre third-party content items to determine a relationship of the popularity score relative to the average score of similar genre third-party content items. A popularity or other visual indicator may be provided proximate to the third-party content item to provide a visual indication of the relationship. The popularity indicator may include a bar or a plurality of symbols in some implementations.

Visual indicator based on relative rating of content item

A computer-implemented method for sending a personalized electronic message using predefined templates including personalization symbols is provided. The method includes receiving a selection of an electronic message template from a user, wherein the electronic message template is stored in a data structure and wherein the electronic message template comprises a predefined personalization symbol for personalizing the electronic message template. The method also includes obtaining the electronic message template from the data structure, and generating content for inclusion in a personalized electronic message body based on the electronic message template, the step of generating comprising replacing the personalization symbol, based on a predefined rule, with a default value associated with the personalization symbol. The method further includes providing a draft electronic message comprising the personalized electronic message body. Systems and machine-readable media are also provided.

Electronic messages using predefined templates

Systems and methods for identifying a similar user identifier include analyzing history data indicative of webpages visited by a set of user identifiers. A product category corresponding to a specific manufacturer or a specific product from the manufacturer may be identified using the history data and associated with the set of user identifiers. A user identifier may be identified as being similar to those in the set based in part on the user identifier also being associated with the product category.

Identifying a similar user identifier

A computerized method, system for, and computer-readable medium operable to select an algorithm for generating models configured to identify similar user identifiers. A first plurality of models generated by a first algorithm is received. A plurality of lists of similar user identifiers is generated. User queries associated with user identifiers on the plurality of lists of similar user identifiers are identified. Predicted click-through rates for the user queries is received. An average predicted click-through rate is computed for each model based on the predicted click-through rates. A weighted average predicted click-through rate associated with the first plurality of models is computed. The weighted average predicted click-through rate for the first plurality of models can be compared to a weighted average predicted click-through rate for a second plurality of models generated by a second algorithm. The algorithm for generating models is selected based on the comparison.

Selecting an algorithm for identifying similar user identifiers based on predicted click-through-rate

A method of setting a threshold similarity score value for a first plurality of network user identifiers. The first plurality of network user identifiers, a second plurality of network user identifiers and characteristic data associated with the network user identifiers is received. A performance target and an experimental threshold similarity score value are designated. A similarity score between the first and second plurality of network user identifiers is calculated. Performance statistics data for each of the second plurality of network user identifiers having a similarity score greater than or equal to the experimental threshold similarity score value is collected and compared to the similarity score of the network user identifier. Based on the comparison, the experimental threshold similarity score value is adjusted to a similarity score value that achieves the performance target and the threshold similarity score value is set to the adjusted experimental threshold similarity score value.

Adjust similar users identification based on performance feedback

Systems and methods of selecting consumers to receive content on a computer network are provided. A user list identifying a first plurality of users having a group of features corresponding to internet activity of the first plurality of users can be obtained at a computing device. A subgroup of features can be selected from the group of features, and a cluster of users of the first plurality of users can be identified. The users of the cluster of users can each have at least one feature of the subgroup of features. A supplemental user having a supplemental feature can be identified. A correlation between the supplemental feature and at least one feature of the subgroup of features can be determined, and an expanded user list that includes at least one of the first plurality of users and the supplemental user can be generated.

Computer networked selecting of consumer interests

A computerized method for determining a model refresh rate for a model representing a list of network user identifiers includes receiving a first and a second model representing the list at a first and a second time, respectively. Similarity between the first and second model is calculated. If the similarity is less than a threshold value, the model refresh rate is a predetermined rate. If the similarity is equal to or exceeds the threshold value, the model refresh rate is decreased to a less frequent rate. A similarity between a reference model and a selected model in a same content category may be calculated. If the similarity is less than a threshold value, the model refresh rate for the selected model is a predetermined rate. If the similarity is equal to or exceeds the threshold value, the model refresh rate for the reference model is applied to the selected model.

Determining a model refresh rate

Systems and methods for providing an email certificate for an email message. In some aspects, a method includes receiving a request from a user for providing an email certificate for an email message, generating an email certificate by encrypting the email message, and sending the email certificate to the user.

Email certificates

A computerized method, system for, and computer-readable medium operable to select a list of network user identifiers. A processing circuit receives a list of network user identifiers represented by long-term history data indicative of web pages visited prior to a first time and short-term history data indicative of web pages visited after the first time and prior to a second time. Long-term interest categories, corresponding weight values for each long-term interest category, short-term interest categories and corresponding weight values for each short-term interest category are identified. A model comprising the long-term and short-term interest categories is generated based on the weight values of the long-term and short-term interest categories using either arithmetic or harmonic progression. The processing circuit receives a list of candidate network user identifiers and generates a list of similar network user identifiers based on the model.

Growing community of inventors

Sunnyvale, CA, United States of America

Jia Liu