Patents by Inventor ADI MILLER
ADI MILLER 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: 11914644Abstract: Systems and methods for surfacing natural language queries from one or more transcripts. An example method may include converting received audio to text, through automated speech recognition, to form a transcript of the audio, wherein the transcript includes text of the audio and identifications of speakers associated with portions of the text corresponding to utterances from the respective speakers; generating input signals based on at least the transcript; executing at least one of one or more heuristics or a trained machine-learning (ML) model, using the generated input signals as an input, to generate at least one of a suggested natural language query for searching the transcript or a key moment within the received audio; and causing at least one of the suggested natural language query or the key moment to be surfaced on one or more remote devices.Type: GrantFiled: October 11, 2021Date of Patent: February 27, 2024Assignee: Microsoft Technology Licensing, LLCInventors: Adi Miller, Haim Somech, Michael Sterenberg
-
Publication number: 20240037343Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.Type: ApplicationFiled: October 12, 2023Publication date: February 1, 2024Inventors: Adi MILLER, Shira Weinberg, Haim Somech, Hen Fitoussi
-
Patent number: 11822859Abstract: A response activity pattern may be ascertained from a set of computing devices obtained during a monitoring mode of operation. The monitoring mode of operation can be initiated when a user command is determined to be a new or unknown command. The response activity pattern may be used to generate a response profile indicating an activity to carry out using one or more user devices to perform a task associated with the user command. When an indication of a previously unknown user command to perform a task is received, the generated response profile can be used to perform the designed task by carrying out the activity using the one or more user device. In this way, the activity that should be carried out to perform the task can be learned based on the monitored user activity related to the one or more user devices.Type: GrantFiled: November 16, 2022Date of Patent: November 21, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Adi Miller, Roni Karassik, Danny Avigdor
-
Patent number: 11809829Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.Type: GrantFiled: March 6, 2020Date of Patent: November 7, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Adi Miller, Shira Weinberg, Haim Somech, Hen Fitoussi
-
Patent number: 11699039Abstract: Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.Type: GrantFiled: June 28, 2017Date of Patent: July 11, 2023Assignee: Microsoft Technology Licensing, LLCInventors: Haim Somech, Shira Weinberg, Adi Miller
-
Publication number: 20230115098Abstract: Systems and methods for surfacing natural language queries from one or more transcripts. An example method may include converting received audio to text, through automated speech recognition, to form a transcript of the audio, wherein the transcript includes text of the audio and identifications of speakers associated with portions of the text corresponding to utterances from the respective speakers; generating input signals based on at least the transcript; executing at least one of one or more heuristics or a trained machine-learning (ML) model, using the generated input signals as an input, to generate at least one of a suggested natural language query for searching the transcript or a key moment within the received audio; and causing at least one of the suggested natural language query or the key moment to be surfaced on one or more remote devices.Type: ApplicationFiled: October 11, 2021Publication date: April 13, 2023Applicant: Microsoft Technology Licensing, LLCInventors: Adi Miller, Haim Somech, Michael Sterenberg
-
Publication number: 20230082609Abstract: A response activity pattern may be ascertained from a set of computing devices obtained during a monitoring mode of operation. The monitoring mode of operation can be initiated when a user command is determined to be a new or unknown command. The response activity pattern may be used to generate a response profile indicating an activity to carry out using one or more user devices to perform a task associated with the user command. When an indication of a previously unknown user command to perform a task is received, the generated response profile can be used to perform the designed task by carrying out the activity using the one or more user device. In this way, the activity that should be carried out to perform the task can be learned based on the monitored user activity related to the one or more user devices.Type: ApplicationFiled: November 16, 2022Publication date: March 16, 2023Inventors: Adi MILLER, Roni Karassik, Danny Avigdor
-
Patent number: 11537359Abstract: A response activity pattern may be ascertained from a set of computing devices obtained during a monitoring mode of operation. The monitoring mode of operation can be initiated when a user command is determined to be a new or unknown command. The response activity pattern may be used to generate a response profile indicating an activity to carry out using one or more user devices to perform a task associated with the user command. When an indication of a previously unknown user command to perform a task is received, the generated response profile can be used to perform the designed task by carrying out the activity using the one or more user device. In this way, the activity that should be carried out to perform the task can be learned based on the monitored user activity related to the one or more user devices.Type: GrantFiled: March 28, 2019Date of Patent: December 27, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Adi Miller, Roni Karassik, Danny Avigdor
-
Publication number: 20200394366Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.Type: ApplicationFiled: March 6, 2020Publication date: December 17, 2020Inventors: Adi MILLER, Shira WEINBERG, Haim SOMECH, Hen FITOUSSI
-
Publication number: 20200310749Abstract: A response activity pattern may be ascertained from a set of computing devices obtained during a monitoring mode of operation. The monitoring mode of operation can be initiated when a user command is determined to be a new or unknown command The response activity pattern may be used to generate a response profile indicating an activity to carry out using one or more user devices to perform a task associated with the user command. When an indication of a previously unknown user command to perform a task is received, the generated response profile can be used to perform the designed task by carrying out the activity using the one or more user device. In this way, the activity that should be carried out to perform the task can be learned based on the monitored user activity related to the one or more user devices.Type: ApplicationFiled: March 28, 2019Publication date: October 1, 2020Inventors: Adi MILLER, Roni KARASSIK, Danny AVIGDOR
-
Patent number: 10762900Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for executing a command by a digital assistant in a group device environment are presented. A plurality of devices with digital assistants may be clustered for the duration of an event. One of the devices of the cluster may be assigned as an arbitrator device for the cluster. A user may issue a verbal command executable by a digital assistant of the cluster. The user that issued the verbal command may be identified via voice analysis. A determination may be made as to whether the verbal command corresponds to an intent to share content with a plurality of members of the cluster, or a specific member of the cluster, and a device of the cluster may be selected for executing a reply to the verbal command based on the determined intent and the executing device's presentation capabilities.Type: GrantFiled: March 7, 2018Date of Patent: September 1, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Karen Master Ben-dor, Roni Karassik, Adi Diamant, Adi Miller
-
Patent number: 10728200Abstract: Various embodiments, methods, and systems for implementing message management are provided. Message management includes assisting with selecting recipients for messages, and generating, tracking, personalizing, and optimizing messages. The messaging system provides message operations for cycle messages, message tracking interface features, and automatically generating message feature values. In operation, for automatically generating message feature values, a first message to be generated is determined to correspond to a message type. The message type comprises one or more message features, where the one or more messaging features are generated based on customary messaging data. A machine-learning model supports identifying the automatically generated message feature value.Type: GrantFiled: March 12, 2018Date of Patent: July 28, 2020Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Adi Miller, Haim Somech, Ido Priness
-
Patent number: 10585991Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.Type: GrantFiled: June 29, 2017Date of Patent: March 10, 2020Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Adi Miller, Shira Weinberg, Haim Somech, Hen Fitoussi
-
Publication number: 20190281001Abstract: Various embodiments, methods, and systems for implementing message management are provided. Message management includes assisting with selecting recipients for messages, and generating, tracking, personalizing, and optimizing messages. The messaging system provides message operations for cycle messages, message tracking interface features, and automatically generating message feature values. In operation, for automatically generating message feature values, a first message to be generated is determined to correspond to a message type. The message type comprises one or more message features, where the one or more messaging features are generated based on customary messaging data. A machine-learning model supports identifying the automatically generated message feature value.Type: ApplicationFiled: March 12, 2018Publication date: September 12, 2019Inventors: Adi MILLER, Haim SOMECH, Ido PRINESS
-
Publication number: 20190279615Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for executing a command by a digital assistant in a group device environment are presented. A plurality of devices with digital assistants may be clustered for the duration of an event. One of the devices of the cluster may be assigned as an arbitrator device for the cluster. A user may issue a verbal command executable by a digital assistant of the cluster. The user that issued the verbal command may be identified via voice analysis. A determination may be made as to whether the verbal command corresponds to an intent to share content with a plurality of members of the cluster, or a specific member of the cluster, and a device of the cluster may be selected for executing a reply to the verbal command based on the determined intent and the executing device's presentation capabilities.Type: ApplicationFiled: March 7, 2018Publication date: September 12, 2019Inventors: Karen Master BEN-DOR, Roni KARASSIK, Adi DIAMANT, Adi MILLER
-
Publication number: 20190005024Abstract: Methods for providing enhanced services to users participating in communication sessions (CS), via a virtual assistant, are disclosed. One method receives content that is exchanged by users participating in the CS. The content includes natural language expressions that encode a conversation carried out by users. The method determines content features based on natural language models. The content features indicate intended semantics of the natural language expressions. The method determines a relevance of the content and identifies portions of the content that are likely relevant to the user. Determining the relevance is based on the content features, a context of the CS, a user-interest model, and a content-relevance model of the natural language models. Identifying the likely relevant content is based on the determined relevance of the content and a relevance threshold. A summary of the CS is automatically generated from summarized versions of the likely relevant portions of the content.Type: ApplicationFiled: June 28, 2017Publication date: January 3, 2019Inventors: Haim SOMECH, Shira WEINBERG, Adi MILLER
-
Publication number: 20190005021Abstract: Intelligent agents (IA) for automatically generating responses to content within a communication session (CS) are disclosed. An IA is trained to target the responses to a user and the user's context within the CS. An IA receives CS content that includes natural language expressions encoding users' conversations and determines content features based on natural language models. The content features indicate intended semantics of the expressions. The IA identifies likely-relevant content to the targeted user, to generate a response for. Identifying such content includes determining a relevance of the content based on content features, a context of the CS, a user-interest model, and a content-relevance model. Identifying the likely-relevant content to respond to is based on the determined relevance of the content and relevance thresholds. Various responses to the identified portions of the content are automatically generated and provided based on a natural language response-generation model targeted to the user.Type: ApplicationFiled: June 29, 2017Publication date: January 3, 2019Inventors: Adi MILLER, Shira WEINBERG, Haim SOMECH, Hen FITOUSSI
-
Publication number: 20170308866Abstract: Meeting scheduling resources are provided including systems and methods for optimizing proposed meeting details using historical information derived from meeting invitees. A statistical analysis, which may employ machine-learning techniques, may be used to determine a meeting attendance model based on past meetings and/or events, user activity, or other information associated with a user. Meeting patterns and availability for the user also may be used to generate the meeting attendance model. A meeting manager service may implement the meeting attendance models to facilitate schedule future meetings. The meeting manager service may also determine an attendance importance for invitees, a likelihood of attending the proposed meeting, given specific meeting features of the proposed meeting (such as time, location, or other meeting features) and recommend optimal meeting features for the proposed meeting.Type: ApplicationFiled: April 22, 2016Publication date: October 26, 2017Inventors: Dikla Dotan-Cohen, Adi Miller, Haim Somech, Oded Nahir
-
Publication number: 20170017928Abstract: A most probable physical meeting location is provided to a user or third-party in response to receiving a subjective reference to the physical meeting location. A collection of physical meeting location values, or objective references to one or more physical meeting locations, are collected based at least in part on sensor data associated with the user. For each subjective reference to a physical meeting location, one or more location clusters comprising objective references to one or more physical meeting locations is generated. As a response to receiving the subjective reference to the physical meeting location, a probable meeting location generated based on cluster density associated with each of the one or more location clusters is provided to the user or third-party.Type: ApplicationFiled: July 15, 2015Publication date: January 19, 2017Inventors: ADI MILLER, SHIRA WEINBERG, ADI GERZI
-
Publication number: 20160267439Abstract: An electronic calendaring system provides contextual calendar conflict resolution by dynamically evaluating the contexts of a user's obligations and offering the user assistance in scheduling non-conflicting events in a calendar. The electronic calendaring system generates one or more electronic calendar conflict resolution options based on contextual information associated with conflicting calendar events. An event conflict evaluator identifies a calendar conflict between at least two calendar events within received calendar event information. An event context evaluator collects contextual information about the conflicting calendar events. A conflict resolution mediator ranks available time slots to which at least one of the conflicting calendar events can be rescheduled based on the collected contextual information. The conflict resolution mediator further communicates a conflict resolution option message via a user interface of a computing device.Type: ApplicationFiled: March 11, 2015Publication date: September 15, 2016Inventors: Hadas Bitran, Delia Koren, Omri Koshorek, Elinor Axelrod, Limor Lahiani, Uri Barash, Ido Priness, Dikla Dotan-Cohen, Adi Miller, Haim Somech