Abstract: Techniques are provided to allow a user to interact with a computer to automatically analyze a transcript and provide interactive feedback pertaining to interactions between the user and other parties. This may be accomplished by dividing the transcript into text sequences, such as sentences, and matching each text sequence against a set of rules that define patterns that relate text sequences to particular characteristic categories. These matches can be further scored and ranked to allow particular text sequences to be interactively displayed to the user in response to selection of a particular categorization.

Abstract: Techniques for real-time generation and customization of text classification models. An initial dataset of input text samples are manually assigned labels, and the labeled input text samples are tokenized and provided as training data to train machine learning classifiers for various classes or categories of the input text samples. As the machine learning classifiers train with the training data, feedback in the form of suggestions (or predictions) are provided in real time by the text classification models regarding which label(s) to assign to any input text sample(s) currently in the training data or any new input text sample(s) further provided as training data for the respective machine learning classifiers. The suggested (or predicted) label(s) can be manually assigned to the input text sample(s), if deemed appropriate, and the newly labeled input text sample(s) can be provided to supplement the existing training data for the respective machine learning classifiers.

Abstract: Technology for generating a consistently labeled training dataset. For each one of multiple previously labeled texts, a distance between the previously labeled text and a current text to be labeled is generated by comparing a list of tokens for the previously labeled text to a list of tokens for the current text to determine an overlap value equal to a number of tokens that match between the list of tokens for the previously labeled text and the list of tokens for the current text, and using the overlap value to calculate a distance between the previously labeled text and the current text that is inversely correlated to the overlap value. Previously labeled texts that are most similar to the current text are identified as those previously labeled texts having the shortest distances to the current text, and are displayed with their previously assigned labels in a label selection user interface.

Abstract: Techniques for managing a user's tasks based on the user's focus level. High focus time slots are identified during which the user has a high level of focus, as well as low focus time slots during which the user has a low level of focus. Tasks for completion by the user are scheduled such that the high focus time slots are allocated to tasks that require a high level of user focus, and the low focus time slots are allocated to tasks that require a low level of user focus. High focus times may be identified based on user indications and/or on biometric data describing the user's physical state. Interruption requests may also be managed based on the user's focus level. Necessary resources may be pre-loaded prior to the high focus time periods, and breaks may be automatically scheduled to maintain the user's high level of focus.

Abstract: A computer-implemented technique provides electronic text recommendations to a user. The technique involves capturing content from a conference among multiple participants. The technique further involves receiving electronic typing input from the user while the user is typing to document the conference. The technique further involves outputting, in response to the electronic typing input from the user, electronic text recommendations to the user based on the captured content. Such recommendations can take the form of predictive typing for taking notes based on content shared during an online meeting. The words and/or phrases in the predictive typing may be derived from the words spoken and/or from visual data displayed during the conference. Accordingly, a user is able to document what is discussed with minimal typing and thus reduced distraction. Furthermore, the information that is documented can be made more on-point and less verbose than a lengthy transcription of an audio feed.

Abstract: In a distributed computing system, clients of a communications application are deployed on user devices. The clients on target user devices collect and report context information for a target user such as location and application-in-use. Reported context information is associated with response time information describing time to respond to initiation of communications in respective contexts, and a predictive model is maintained and used to obtain an estimate for a response time of the target user to respond to a new initiation of communications in a current context. A presence indicator on an initiator user device provides a presence indicator for the target user, and is generated and updated by obtaining current context of the target user and applying it to the predictive model to obtain an estimate of a current response time of the target user, and setting a value of the presence indicator according to the estimate.

Abstract: Techniques are provided to allow a user to interact with a computer to automatically analyze a transcript and provide interactive feedback pertaining to interactions between the user and other parties. This may be accomplished by dividing the transcript into text sequences, such as sentences, and matching each text sequence against a set of rules that define patterns that relate text sequences to particular characteristic categories. These matches can be further scored and ranked to allow particular text sequences to be interactively displayed to the user in response to selection of a particular categorization.

Abstract: Technology for generating a consistently labeled training dataset. For each one of multiple previously labeled texts, a distance between the previously labeled text and a current text to be labeled is generated by comparing a list of tokens for the previously labeled text to a list of tokens for the current text to determine an overlap value equal to a number of tokens that match between the list of tokens for the previously labeled text and the list of tokens for the current text, and using the overlap value to calculate a distance between the previously labeled text and the current text that is inversely correlated to the overlap value. Previously labeled texts that are most similar to the current text are identified as those previously labeled texts having the shortest distances to the current text, and are displayed with their previously assigned labels in a label selection user interface.

Abstract: Techniques for real-time generation and customization of text classification models. An initial dataset of input text samples are manually assigned labels, and the labeled input text samples are tokenized and provided as training data to train machine learning classifiers for various classes or categories of the input text samples. As the machine learning classifiers train with the training data, feedback in the form of suggestions (or predictions) are provided in real time by the text classification models regarding which label(s) to assign to any input text sample(s) currently in the training data or any new input text sample(s) further provided as training data for the respective machine learning classifiers. The suggested (or predicted) label(s) can be manually assigned to the input text sample(s), if deemed appropriate, and the newly labeled input text sample(s) can be provided to supplement the existing training data for the respective machine learning classifiers.

Abstract: A technique provides a sync notification to indicate when a shared screen view of a presenter device has been delivered to an audience. The technique involves generating a sync time estimation based on communications with a set of audience devices, and detecting occurrence of an update to the shared screen view of the presenter device. The technique further involves outputting, after the sync time estimation has elapsed since the detected occurrence of the update, the sync notification on the presenter device to indicate when the shared screen view of the presenter device has been delivered to the audience. Such a technique is well suited for a variety of online collaboration systems such as online conference systems, online webinar systems, online meeting systems, and so on.

Abstract: Item classification rules are created based on examples selected by a user, such as by selecting a subset of emails, and the rule is used across a larger set of items to obtain automatic classification of similar items according to the rule. Based on an analysis, a candidate classification rule is generated identifying text-based features shared among the items of the subset. The user can review the candidate rule as well as a resultant subset of items generated by the rule, and either accept the candidate rule or make an adjustment to the examples and then perform one or more iterations of the analysis to refine the rule. Adjustments can be made by removing items incorrectly included in a resultant subset and/or adding items incorrectly excluded from a resultant subset, and using the adjusted subset in a next iteration.

Abstract: A technique for acquiring information about entities includes receiving starting data including an entity name and/or email address, generating a URL (Uniform Resource Locator) from the starting data, and downloading content from a website at the generated URL. Downloaded content from the website is analyzed to generate a set of entity-specific information and a confidence score. The confidence score specifies a likelihood that the entity-specific information pertains to the same entity that was described in the starting data. Using the improved technique, persons are able to obtain information about entities, even small, private entities about which information online is sparse, along with a measure of quality of the information obtained.

Abstract: A technique provides, to a user, a set of diagram views of a diagram model stored in memory. The technique involves obtaining, by processing circuitry, electronic access to the diagram model stored in the memory. The diagram model includes a group of objects. Each object has a defined object size. The technique further involves, after obtaining electronic access to the diagram model stored in the memory, performing, by the processing circuitry, an object selection operation that selects an initial set of objects from the group of objects based on the defined object size of each object of the group of objects. The technique further involves, after performing the object selection operation, rendering, by the processing circuitry, an initial diagram view of the diagram model on an electronic display to the user, the initial diagram view including the initial set of objects.

Abstract: In a distributed computing system, clients of a communications application are deployed on user devices. The clients on target user devices collect and report context information for a target user such as location and application-in-use. Reported context information is associated with response time information describing time to respond to initiation of communications in respective contexts, and a predictive model is maintained and used to obtain an estimate for a response time of the target user to respond to a new initiation of communications in a current context. A presence indicator on an initiator user device provides a presence indicator for the target user, and is generated and updated by obtaining current context of the target user and applying it to the predictive model to obtain an estimate of a current response time of the target user, and setting a value of the presence indicator according to the estimate.

Abstract: Improved techniques of identifying when a device needs of service involve using data analytics to determine conditions when a device administrator of a computerized device is to be sent an alert regarding that device. Along these lines, a device monitoring system receives state data from a device that indicates the device is in a particular state, e.g., running certain applications, using some percentage of the processor and memory capacity, etc. The device monitoring system maps the device state data to a decision of whether or not to send a device administrator an alert concerning the device. The decision itself is a result of applying a model to the state data that is derived from the application of data analytics on historical device state data and administrator login data.

Abstract: Screenshots are captured for a visual summary of an online meeting using a dynamically determined inactivity threshold time period. The inactivity threshold time period may be the sum of i) an average time interval between arrival times of screen update messages in a set of received screen update messages, and ii) a multiple of the standard deviation of such time intervals. If no significant updates to a shared screen occur during the inactivity threshold time period, a screenshot may be captured for the online meeting visual summary. A premature screenshot threshold time period may also be determined. If significant visual data is received during the premature screenshot threshold time period, the previously captured screenshot is replaced with an updated screenshot.

Abstract: Techniques for managing a user's tasks based on the user's focus level. High focus time slots are identified during which the user has a high level of focus, as well as low focus time slots during which the user has a low level of focus. Tasks for completion by the user are scheduled such that the high focus time slots are allocated to tasks that require a high level of user focus, and the low focus time slots are allocated to tasks that require a low level of user focus. High focus times may be identified based on user indications and/or on biometric data describing the user's physical state. Interruption requests may also be managed based on the user's focus level. Necessary resources may be pre-loaded prior to the high focus time periods, and breaks may be automatically scheduled to maintain the user's high level of focus.

Abstract: A computer-implemented technique provides electronic text recommendations to a user. The technique involves capturing content from a conference among multiple participants. The technique further involves receiving electronic typing input from the user while the user is typing to document the conference. The technique further involves outputting, in response to the electronic typing input from the user, electronic text recommendations to the user based on the captured content. Such recommendations can take the form of predictive typing for taking notes based on content shared during an online meeting. The words and/or phrases in the predictive typing may be derived from the words spoken and/or from visual data displayed during the conference. Accordingly, a user is able to document what is discussed with minimal typing and thus reduced distraction. Furthermore, the information that is documented can be made more on-point and less verbose than a lengthy transcription of an audio feed.

Abstract: A computer system executing a computer audio application such as video conferencing applies audio detection and speech recognition to an input audio stream to generate respective audio detection and speech recognition signals. A function is applied to the audio detection and speech recognition signals to generate a non-speech audio detection signal identifying presence of non-speech audio in the input audio stream when the audio detection signal is asserted and the speech recognition signal is not asserted. A control or indication action is performed in the computer system based on assertion of the non-speech audio detection signal.

Abstract: A technique provides, to a user, a set of diagram views of a diagram model stored in memory. The technique involves obtaining, by processing circuitry, electronic access to the diagram model stored in the memory. The diagram model includes a group of objects. Each object has a defined object size. The technique further involves, after obtaining electronic access to the diagram model stored in the memory, performing, by the processing circuitry, an object selection operation that selects an initial set of objects from the group of objects based on the defined object size of each object of the group of objects. The technique further involves, after performing the object selection operation, rendering, by the processing circuitry, an initial diagram view of the diagram model on an electronic display to the user, the initial diagram view including the initial set of objects.