A9.com, Inc.

Microsoft Technology Licensing, LLC

Colloquis, Inc.

Francois Huet

Gray Salmon Norton

Jagadeshwar Nomula

Erick Cantu-Paz

Yue Zhou

Daniel Eric Rose

Timothy L Kay

Anil A Sewani

Stephen D Klein

Damien Saint Macary

Vamsi Salaka

David Mark Ciemiewicz

Yichen Zhou

Priyank Singh

Bing Yin

Matthew Carlin

Christopher Varano

Pierre Berkaloff

Embodiments of the present invention provide improved techniques for determining long term relevance and user behavior using query chains. The query chains may first be detected and then annotated into different types of chains based at least in part on various decision rules, machine-learned classifiers, and inter-query relationships. The query chains may then be subsequently used to train models for predicting user behavior and providing more relevant results to a user's queries. A content provider system according to various embodiments may aggregate historical data associated with previous search and/or transaction data, which may be analyzed to detect query chains, for example, whether queries are chained to each other. Determining whether queries are chained to each other may involve incorporating decision rules and reformulation models, analyzing temporal windows between queries, and/or analyzing inter-query relationships.

Systems and methods for determining long term relevance with query chains

The arrangement and selection of digital content to present to a user can be based at least in part upon probabilities of the user selecting to view more information and/or entering into a transaction with respect to instances of the content. For example, user behavior with respect to various items provided through a content provider can be determined in order to calculate a probability that a user was searching for a particular type of item for a given search. The user behavior can include historical action data, such as information that indicates items that were selected in response to a particular search and/or items that were purchased in response to a particular search. The historical action data can be analyzed to generate an index that indicates a likelihood that the search was intended for a particular type of product. Additionally, the historical data can be used to train language models that can be used to determine a probability of interest for a particular type of product for a given search. Once a query is received, items of interest can be determined using one of the index or language models, and those items can be presented to the user.

Determine product relevance

Approaches are described for ranking multiple products or other items, such as products obtained in response to a search request submitted to a server. The ranking system determines a ranking score for the products based on both data available online and item data that must be computed offline due to longer computation time or unavailability of data. The ranking score can be used to rank the products and determine which products are the most relevant to the user. A hybrid boosting method is used to first train an online ranking function to produce an online ranking score for the item. In the second phase, an offline ranking function is trained to produce a second ranking score for the item. The online rank score is combined with the offline rank score at query time to produce a combined rank for the items in the search results.

Combined online and offline ranking for search results

Various approaches provide for determining the selection and/or ranking of items to display based at least in part upon the probabilities of a user being interested in those items. The probabilities can be based on profile information of a user. The profile information can include a three-dimensional virtual model of the user. When a search for content is received, the information for the three-dimensional virtual model can be used to determine a set of items. For each item, a matching score quantifying a visual appreciation can be determined based on how well an item virtually 'fits' the three-dimensional virtual model. Based on the matching score, the selection and/or ranking of items to display can be determined. In some situations, the items can be shown to appear to be worn by the three-dimensional virtual model. The user can purchase items, cause item information to be presented to other users or sent to other devices, and/or perform other such actions.

Displaying relevant content

The relevance or ranking of various dynamically-determined instances of content can be adjusted or otherwise improved based on aspects such as the freshness or seasonality of the content. In many conventional relevance or ranking algorithms, factors such as popularity, performance, and profit are used to determine which content to present to a user, as well as how to display the selected content. Such algorithms do not necessarily reflect domain-specific knowledge very well, and thus fail to accurately select content that is of differing levels appeal at various ages of the content and/or during various seasons of the year. Freshness and/or seasonality adjustment scores can be used to generate improved relevance, selection, or ranking determinations for various categories of content.

Freshness and seasonality-based content determinations

Video content can be analyzed to identify particular sections of the video content. Speech to text or similar techniques can be used to obtain a transcription of the video content. The transcription can be indexed (e.g., timestamped) to the video content. Information describing how users are interacting with or consuming the video content (e.g., social media information, viewing history data, etc.) can be collected and used to identify the particular sections. Once the particular sections have been identified, other services can be provided. For example, custom trailers and summaries of the video content can be generated based on the identified sections. Additionally, the video content can be augmented to include additional information relevant to the particular sections, such as production information, actor information, or other information. The additional information can be added so as not to interfere with the important sections.

Section identification in video content

Combined online and offline ranking

Methods and apparatus provide the capability of receiving at least a portion of a message in natural language format from a user prior to submission of the message to an automated agent for a response, analyzing the at least the portion of the message, and providing a suggestion to the user, based upon the analyzed at least the portion of the message, for altering the message to improve ability of the automated agent to respond to the message.

Methods and apparatus to help users of a natural language system formulate queries

A system and method are provided for escalating a user or customer to a live agent from a conversational agent when predetermined criteria are met. The conversational agent textually converses in so-called natural language interaction and can run on a computer, such as a server. Upon receiving a first query, the conversational agent creates a new case, and interacts with the customer, in an attempt to resolve the case and satisfy the user. The predetermined criteria for escalation may include a determination that the conversational agent is unable to satisfy a computer-to-computer information request. Alternatively, the predetermined criteria may include patterns and/or words associated with frustration, for example, and/or unrecognized query subject matter, high priority queries, for example to increase sales, etc.

Methods and apparatus for use in computer-to-human escalation

A conversational agent receives a textual user message and escalates the user to a live agent if predetermined criteria are met.

Methods and apparatus to evaluate the semantic proximity between reference free-form text entry and a candidate free-form text request.

Growing community of inventors

Santa Cruz, CA, United States of America

Francois Huet