Microsoft Technology Licensing, LLC

Other

David Shigeru Taniguchi

Todd D Newman

Cezary Antoni Marcjan

Eric J Horvitz

Heung-Yeung Shum

Xuedong D Huang

Lili Cheng

Christopher Lee Mullins

Gueorgui Chkodrov

Hung-Chih Yang

Kong-Kat Wong

James H Lewallen

John David Ballard

Eric Anthony Reel

Richard Zachary Jason

Tien Widya Suwandy

Ahmed M S A W Moustafa

Representative embodiments disclose mechanisms to create analytic metrics for bots. In one set of embodiments, the system creates a custom URI that encodes bot specific information in a URI format. An analytic record is created based on the URI and the analytic record can be logged and/or sent directly to an analytic platform designed to provide analytic metrics for websites. In this fashion, website analytic platforms can be used to provide analytic metrics for bots. In another set of embodiments, analytic records are created that are logged and/or sent directly to a bot specific analytic platform. Such a platform may help derive bot specific analytic metrics.

Network mapping and analytics for bots

In non-limiting examples of the present disclosure, systems, methods and devices for training conversational language models are presented. An embedding library may be generated and maintained. Exemplary target inputs and associated intent types may be received. The target inputs may be encoded into contextual embeddings. The embeddings may be added to the embedding library. When a conversational entity receives a new natural language input, that new input may be encoded into a contextual embedding. The new embedding may be added to the embedding library. A similarity score model may be applied to the new embedding and one or more embeddings for the exemplary target inputs. Similarity scores may be calculated based on the application of the similarity score model. A response may be generated by the conversational entity for an intent type for which a similarity score exceeds a threshold value.

Natural language processing models for conversational computing

A unified search service may collect information related to an enterprise from at least one of publicly available data and private enterprise data. In some implementations, crowd sourcing may be used to determine a source list of one or more sources of information. Authored content can be generated, such as by combining one or more items of information from the public data with one or more items of information from the private enterprise data. Further, in some implementations, a public index may be generated from the public data, and one or more affiliation indexes may be generated from the private enterprise data. For example, a first affiliation index may contain confidential enterprise information, while a second affiliation index may contain non-confidential enterprise information. A user's affiliation to the enterprise may be taken into consideration when determining which indexes to use when responding to a search request from the user.

Enterprise search over private and public data

A state affinitized system comprises worker computing devices uniquely affinitized with one or more states such that only those worker computing devices maintain local copies of the states with which they are affinitized. Requests and data relevant to a state are directed to the worker computing device affinitized with that state, such as by front-end computing devices. A centralized persistent storage can maintain a copy of each state and can modify the states in response to newly received information in the same manner as the worker computing devices. Such maintenance can be performed by coalescer computing devices, which can also derive second order data from the states in the centralized persistent storage, which can be further added to the state and also communicated to the worker computing device affinitized with that state. Crawler computing devices can obtain additional information for incorporation into states from network-based information repositories and services.

Scalable affinitized state management

System and method for notifying a user of an occurrence of a defined condition in a process. The process includes a plurality of event records associated with the process; each of the plurality of event records includes a plurality of data fields having data relating to the process. A subset of the plurality of event records is defined where the subset relates to the defined condition. The data in the defined subset is updated at a predetermined time interval. The user is notified when the updated data of the defined subset indicates that the defined condition has occurred. The subset may alternatively be defined as a function of a current time, a last run time and the defined condition.

Business alerts on process instances based on defined conditions

A path calculation report is derived from a Web log having therein a plurality of Universal Resource Identifiers (URI) each corresponding to a request made by a user to a server of a Web site containing one or more web pages. The report displays, in sequential order, all of the URI that correspond to each click path through the Web Site by one or more users during one or more visits to the Web site. Each URI corresponding to each click path is derived by decompressing a fixed length number representing a compressed URI that corresponds to each request of the corresponding click path through the Web Site.

Click stream analysis

A system and method for performing click stream analysis is described. In one implementation, a Web log is processed to reconstruct a visit made by a user to a Web site. The Web log contains records representing actions performed by the user during the visit including any actions that may be designated a commerce event. A sequential identification is assigned to each record and the sequential identification is stored with the associated record in a database. Any records representing actions performed by the user that are designated as a commerce event are identified. The database is queried for a certain quantity of records representing actions performed by the user prior to and/or subsequent to the commerce event, based on the sequential identification assigned to each record.

Growing community of inventors

Kirkland, WA, United States of America

David Shigeru Taniguchi