Patents by Inventor Dan Teodosiu

Dan Teodosiu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10360305
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: February 16, 2016
    Date of Patent: July 23, 2019
    Assignee: VirtuOz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 10290032
    Abstract: Described are methods, systems, and apparatus for recommending catalog items for blacklisting. For each of a plurality of catalog items: image features are extracted; image features are associated with the catalog item; and user purchase events, user view events, a textual description, and categories are associated with the catalog item by the recommendation system. An identification of a first blacklisted catalog item is received. A catalog item is identified by the recommendation system based on i) a similarity between the image features associated with the first blacklisted catalog item and the image features associated with the catalog item, and ii) a correspondence between at least one of the user purchase events, the user view events, the textual description, or the categories associated with the blacklisted catalog item and the user purchase events, the user view events, the textual description, or the categories associated with the catalog item.
    Type: Grant
    Filed: March 31, 2016
    Date of Patent: May 14, 2019
    Assignee: Criteo SA
    Inventors: Olivier Koch, Pierre-Emmanuel Mazaré, Romain Lerallut, Dan Teodosiu
  • Patent number: 10216637
    Abstract: In order to provide a more efficient persistent storage device, one or more long-term storage media are included along with a non-volatile memory. In one embodiment, one portion of the non-volatile memory is used as a write buffer and a read cache for writes and reads to the long-term storage media. Interfaces are provided for controlling the use of the non-volatile memory as a write buffer and a read cache. Additionally, a portion of the non-volatile memory is used to provide a direct mapping for specified sectors of the long-term storage media. Descriptive data regarding the persistent storage device is stored in another portion of the non-volatile memory.
    Type: Grant
    Filed: July 21, 2016
    Date of Patent: February 26, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Cenk Ergan, Clark D. Nicholson, Dan Teodosiu, Dean L. DeWhitt, Emily Nicole Wilson, Hanumantha R. Kodavalla, Michael J. Zwilling, John M. Parchem, Michael R. Fortin, Nathan Steven Obr, Rajeev Y. Nagar, Surenda Verma, Therron Powell, William J. Westerinen, Mark Joseph Zbikowski, Patrick L. Stemen
  • Publication number: 20180150879
    Abstract: A computer accesses a multidimensional vector space that comprises embeddings of catalog item embeddings, each catalog item having one or more item attributes and corresponding item attribute values, and embeddings of associated item attribute values. An identification of one or more seed catalog items is received. Embeddings of each of one or more seed catalog items and embeddings of associated item attribute values are identified within the vector space. For each one of the seed catalog items, for each of the item attributes of the seed catalog item, an item representation in the vector space is located based upon a combination of the embedding of the seed catalog item and of an embedding of an item attribute value representing an item attribute value that is similar to the corresponding item attribute value of the seed catalog item. For each item representation, one or more embeddings of candidate catalog items that are close to the product representation are selected.
    Type: Application
    Filed: November 25, 2016
    Publication date: May 31, 2018
    Inventors: Flavian Vasile, Clement Calauzenes, Dan Teodosiu
  • Publication number: 20170287023
    Abstract: Described are methods, systems, and apparatus for recommending catalogue items for blacklisting. For each of a plurality of catalog items: image features are extracted; image features are associated with the catalog item; and user purchase events, user view events, a textual description, and categories are associated with the catalog item by the recommendation system. An identification of a first blacklisted catalog item is received. A catalog item is identified by the recommendation system based on i) a similarity between the image features associated with the first blacklisted catalog item and the image features associated with the catalog item, and ii) a correspondence between at least one of the user purchase events, the user view events, the textual description, or the categories associated with the blacklisted catalog item and the user purchase events, the user view events, the textual description, or the categories associated with the catalog item.
    Type: Application
    Filed: March 31, 2016
    Publication date: October 5, 2017
    Inventors: Olivier Koch, Pierre-Emmanuel Mazaré, Romain Lerallut, Dan Teodosiu
  • Patent number: 9524291
    Abstract: Techniques involving visual display of information related to matching user utterances against graph patterns are described. In one or more implementations, an utterance of a user is obtained that has been indicated as corresponding to a graph pattern through linguistic analysis. The utterance is displayed in a user interface as a representation of the graph pattern.
    Type: Grant
    Filed: October 6, 2010
    Date of Patent: December 20, 2016
    Assignee: Virtuoz SA
    Inventors: Dan Teodosiu, Elizabeth Ireland Powers, Pierre Serge Vincent LeRoy, Sebastien Jean-Marie Christian Saunier
  • Publication number: 20160239480
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Application
    Filed: February 16, 2016
    Publication date: August 18, 2016
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 9378202
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: March 26, 2010
    Date of Patent: June 28, 2016
    Assignee: VirtuOz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 9275042
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: January 24, 2014
    Date of Patent: March 1, 2016
    Assignee: VirtuOz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 9196245
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: January 21, 2014
    Date of Patent: November 24, 2015
    Assignee: VirtuOz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Publication number: 20150324854
    Abstract: A method is performed by a computing device. A request is sent comprising request data, the request data comprising one or more identifiers. Payload data is received, where the payload data includes advertising creative retrieval data and application retrieval data for downloading one or more application installation files for an application, where the advertising creative is associated with the application. The advertising creative is downloaded. If the application is not installed on the computing device, the one or more application installation files are downloaded. An advertising creative display opportunity is generated. The advertising creative is displayed in the advertising creative display opportunity. If a user interaction with the advertising creative is detected and the application is not installed on the computing device, the application is installed from the downloaded one or more application files.
    Type: Application
    Filed: November 26, 2014
    Publication date: November 12, 2015
    Inventors: Alix Mougenot, Dan Teodosiu
  • Patent number: 8996682
    Abstract: Embodiments of the invention provide a method and system for automatically instrumenting a set of web documents, such as web pages, as well as embedding structures that present advertising content via the web pages. The instrumentation automatically embeds tags that enable usage information associated with the web documents to be tracked and recorded. Many hundreds or thousands of web pages can be automatically modified without user intervention, enabling comprehensive reporting and tracking to be performed on each page. The web pages are analyzed and insertion points intelligently located. Changes can be verified to ensure that no undesirable effects resulted from embedding the content. The tags can receive parameters customized to the level of users and pages. The tags, insertion information, and other configuration information can be stored in a central repository to make subsequent tagging easier.
    Type: Grant
    Filed: October 12, 2007
    Date of Patent: March 31, 2015
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Daniel C. Stevenson, Olivier Dabrowski, Kresimir Bozic, Dan Teodosiu, Paolo Severini, Cristian Costache, Euan Grant, Erik Zigman
  • Publication number: 20140207441
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Application
    Filed: January 24, 2014
    Publication date: July 24, 2014
    Applicant: VirtuOz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, ELIZABETH IRELAND POWERS, FREYA KATE RECKSIEK, DAN TEODOSIU
  • Publication number: 20140200891
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Application
    Filed: January 21, 2014
    Publication date: July 17, 2014
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 8781479
    Abstract: The described implementations relate to automatic network selection in relation to wireless mobile devices. One method can be applied to a mobile device that has both Wi-Fi and cellular capabilities. The method can attempt to identify Wi-Fi network availability for the mobile device. This method also evaluates whether to configure the mobile device to accomplish data communication over an identified Wi-Fi network or a cellular network.
    Type: Grant
    Filed: January 22, 2009
    Date of Patent: July 15, 2014
    Assignee: Microsoft Corporation
    Inventors: Zhihong Mao, Stephen Goggin, Attila Pall, Grzegorz Lapinski, Kresimir Bozic, Dan Stevenson, Dan Teodosiu
  • Patent number: 8694304
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: March 26, 2010
    Date of Patent: April 8, 2014
    Assignee: Virtuoz SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 8676565
    Abstract: Semantic clustering techniques are described. In various implementations, a conversational agent is configured to perform semantic clustering of a corpus of user utterances. Semantic clustering may be used to provide a variety of functionality, such as to group a corpus of utterances into semantic clusters in which each cluster pertains to a similar topic. These clusters may then be leveraged to identify topics and assess their relative importance, as for example to prioritize topics whose handling by the conversation agent should be improved. A variety of utterances may be processed using these techniques, such as spoken words, textual descriptions entered via live chat, instant messaging, a website interface, email, SMS, a social network, a blogging or micro-blogging interface, and so on.
    Type: Grant
    Filed: March 26, 2010
    Date of Patent: March 18, 2014
    Assignee: VIRTUOZ SA
    Inventors: Jean-Marie Henri Daniel Larcheveque, Elizabeth Ireland Powers, Freya Kate Recksiek, Dan Teodosiu
  • Patent number: 8331560
    Abstract: Published resources are made available in an encrypted form, using corresponding resource keys, published through resource key files, with the publications effectively restricted to authorized peer systems only by encrypting the resource keys in a manner only the authorized peer systems are able to recover them. In one embodiment, the resource keys are encrypted using encryption public keys of the authorized peer systems or the groups to which the authorized peer system are members. In one embodiment, the encryption public keys of individual or groups of authorized peer systems are published for resource publishing peer systems through client and group key files respectively. Group encryption private keys are made available to the group members through published group key files. Further, advanced features including but not limited to resource key file inheritance, password protected publication, obfuscated publication, content signing, secured access via gateways, and secured resource search are supported.
    Type: Grant
    Filed: February 9, 2009
    Date of Patent: December 11, 2012
    Assignee: Microsoft Corporation
    Inventors: Xavier Boyen, Zhenyu Qian, Dan Teodosiu
  • Publication number: 20120290785
    Abstract: In order to provide a more efficient persistent storage device, one or more long-term storage media are included along with a non-volatile memory. In one embodiment, one portion of the non-volatile memory is used as a write buffer and a read cache for writes and reads to the long-term storage media. Interfaces are provided for controlling the use of the non-volatile memory as a write buffer and a read cache. Additionally, a portion of the non-volatile memory is used to provide a direct mapping for specified sectors of the long-term storage media. Descriptive data regarding the persistent storage device is stored in another portion of the non-volatile memory.
    Type: Application
    Filed: July 23, 2012
    Publication date: November 15, 2012
    Applicant: Microsoft Corporation
    Inventors: Cenk Ergan, Clark D. Nicholson, Dan Teodosiu, Dean L. DeWhitt, Emily Nicole Hill, Hanumantha R. Kodavalla, Michael J. Zwilling, John M. Parchem, Michael R. Fortin, Nathan Steven Obr, Rajeev Y. Nagar, Surenda Verma, Therron Powell, William J. Westerinen, Mark Joseph Zbikowski, Patrick L. Stemen
  • Patent number: 8255645
    Abstract: In order to provide a more efficient persistent storage device, one or more long-term storage media are included along with a non-volatile memory. In one embodiment, one portion of the non-volatile memory is used as a write buffer and a read cache for writes and reads to the long-term storage media. Interfaces are provided for controlling the use of the non-volatile memory as a write buffer and a read cache. Additionally, a portion of the non-volatile memory is used to provide a direct mapping for specified sectors of the long-term storage media. Descriptive data regarding the persistent storage device is stored in another portion of the non-volatile memory.
    Type: Grant
    Filed: September 13, 2011
    Date of Patent: August 28, 2012
    Assignee: Microsoft Corporation
    Inventors: Cenk Ergan, Clark D. Nicholson, Dan Teodosiu, Dean L. DeWhitt, Emily Nicole Hill, Hanumantha R. Kodavalla, Michael J. Zwilling, John M. Parchem, Michael R. Fortin, Nathan Steven Obr, Rajeev Y. Nagar, Surenda Verma, Therron Powell, William J. Westerinen, Mark Joseph Zbikowski, Patrick L. Stemen