Microsoft Technology Licensing, LLC

Other

Microsoft Corporation

Milind V Mahajan

Alejandro Acero

Xuedong D Huang

Ciprian Ioan Chelba

Ye-Yi Wang

Amit Kumar

Xiaolong Mou

Eric J Horvitz

Dong Yu

Kamal Jain

Asela J Gunawardana

Patrick Nguyen

Kuansan Wang

Arungunram Chandrasekaran Surendran

Fileno A Alleva

Li Jiang

Asela J R Gunawardana

William H Rockenbeck

Yonggang Deng

Peter K L Mau

Alexander G Gounares

John Carlton Platt

Jason Garms

Mary P Czerwinski

Paul A Viola

Yun-Cheng Ju

James G Droppo

Brett David Brewer

Melissa Wood Dunn

Hsiao-Wuen Hon

Julian James Odell

Xiao Li

Karim Taji Farouki

Shishir P Pardikar

Sanaz Ahari

Timothy David Sharpe

Mei-Yuh Hwang

Bo-June Hsu

Michael J Rozak

Darrell Leroy Blegen

Jayaram Nm Nanduri

Abhiram G Khune

Steve Macbeth

John Sie Yuen Lee

Yik-Cheung Tam

Xuendong D Huang

Yu Dong

Applications are surfaced to a user during browsing without requiring a specific search by the user. The applications can be selected for surfacing to the user based on the network address entered into the address bar of a browser, the content of the page corresponding to the network address, or a combination thereof. Applications may be selected for surfacing based on a partial address entered into the address bar and/or based on the web page content that is currently visible in the browser display.

Surfacing applications based on browsing activity

Embodiments of a computer-implemented advertisement display system are disclosed. In one embodiment, the system includes a speech recognition component that processes a video clip and produces a corresponding collection of speech recognition data indicative of an audio portion of the video clip. The system also includes a collection of advertising material. An advertisement selection component selects an advertisement from the collection of advertising material based on the corresponding collection of speech recognition data. The system also includes a display. An advertisement presentation component displays an indication of the selected advertisement on the display during a simultaneous display of the video clip.

Video contextual advertisements using speech recognition

Computer-readable media, computer systems, and computing methods are provided for discovering applications using phone-number information. Initially, an application uploaded to an application marketplace is targeted. Phone numbers associated with the targeted application are discovered by identifying attributes of the targeted application from metadata associated therewith in the application marketplace, and identifying the phone numbers that reach at least one business affiliated with the targeted application or are relevant to the identified attributes of the targeted application. The associated phone numbers are mapped to the targeted application and maintained within an application manifest. Upon detecting user-initiated call-based operation(s) at a client device, the phone number(s) involved in the call-based operation(s) are compared against the application manifest to determine relevant applications. The relevant applications are distributed to the client device for presentation within a phone-number context, such as placing an outgoing call, receiving an incoming call, or reviewing a call-history log.

Surfacing business applications based on calling activities

Mobile communication devices, such as mobile phones, may be capable of recommending to a user various providers of one or more solicited services, e.g., by identifying a user location and identifying providers near the user location that provide the services, and by initiating a call between the user and a selected provider. However, the equipment and service costs of such devices may be prohibitive, particularly for mid-range mobile communication devices that may appeal to cost-conscious users. The prohibitive costs may be diminished by redirecting part or all of the cost of providing the recommendation service from the providers, e.g., by charging the provider a service cost upon initiating a call from the user to the provider, or upon representing the provider in a provider database. In one such embodiment, all service costs may be borne by providers, providing to the user a free recommendation service via the mobile communication device.

Commercially subsidized mobile communication devices and services

The claimed subject matter relates to an architecture that can mitigate privacy concerns in connection with ad targeting or data collection. In particular, architecture can be included in a personal mobile communication device such as a cell phone. During communication transactions between the host device and a peer device, shared information can be extracted either from content included in the communication or from metadata. Based upon the shared information, a social graph maintained on the host device can be updated. In addition, the host device can receive a large set of ads and select or tailor a custom ad from the set based upon the social graph.

Privacy-centric ad models that leverage social graphs

Described is a technology by which a communications identifier such as a telephone number is used in selecting relevant content (e.g., an advertisement) for outputting as audible and/or visible information to a destination device. The communications identifier is used like a search term/keyword to determine content relevant to that identifier. A telephone number may be the identifier, selected based on a partially-dialed or actually dialed number, or a user's current scrolling position among listed telephone numbers. A telephone number of an incoming call may be used as the identifier. Profile data and/or state data may be used in selecting relevant content. Some of the profile data may be mined based on previous user activities. In one example, the content may be provided via a remote source of the content, and used immediately or cached for later use (e.g., output).

Providing relevant advertisements or other content based on a communications identifier

Computer-readable media, computer systems, and computing methods are provided for implicitly discovering applications using a query or search results, where the query does not explicitly target a particular application. A search engine is used to receive a user-initiated query and to employ a keyword of the query to generate an initial set of search results. Characteristics of the search results are identified and applications that are relevant to the characteristics are determined. The determination of relevant applications include: accessing an application manifest that manages a mapping between applications and predefined characteristics; comparing the characteristics of the search results against the predefined characteristics of the application manifest to determine a match; and, when a match exists between the search-result characteristics and the predefined characteristics, identifying applications mapped to the matched characteristics as being relevant to the search results. These identified applications are presented in response to the query.

Integrating applications within search results

One feature of the present invention uses the parsing capabilities of a structured language model in the information extraction process. During training, the structured language model is first initialized with syntactically annotated training data. The model is then trained by generating parses on semantically annotated training data enforcing annotated constituent boundaries. The syntactic labels in the parse trees generated by the parser are then replaced with joint syntactic and semantic labels. The model is then trained by generating parses on the semantically annotated training data enforcing the semantic tags or labels found in the training data. The trained model can then be used to extract information from test data using the parses generated by the model.

Applying a structured language model to information extraction

Computer-readable media, computer systems, and computing methods are provided for implicitly discovering applications that have a corresponding location. Initially, an application manifest is constructed that maintains a mapping between apps and their respective geographic boundaries. In operation, upon detecting a location signal being transmitted from a mobile device, the location signal is employed to identify a set of valid applications. Generally, the location signal represents location-based information entered to or received from the mobile device. Identifying the set of valid applications involves comparing the location signal against the application manifest and, based on the comparison, designating those apps that are mapped to geographic boundaries that meet the location signal as the set of valid applications. Upon identifying the set of valid applications, a selection of apps included within the set of valid applications is sent to the mobile device for display to the user within a operational context.

Location-aware application searching

A conditional model is used in spoken language understanding. One such model is a conditional random field model.

Conditional model for natural language understanding

Methods are disclosed for estimating language models such that the conditional likelihood of a class given a word string, which is very well correlated with classification accuracy, is maximized. The methods comprise tuning statistical language model parameters jointly for all classes such that a classifier discriminates between the correct class and the incorrect ones for a given training sentence or utterance. Specific embodiments of the present invention pertain to implementation of the rational function growth transform in the context of a discriminative training technique for n-gram classifiers.

Discriminative training of language models for text and speech classification

Growing community of inventors

Redmond, WA, United States of America

Milind V Mahajan