International Business Machines Corporation

Stefan Van Der Stockt

Rahul P Akolkar

Joseph Lindsey Sharpe, Iii

Kristi A Farinelli

Brian E Bissell

Manali Jairam Chanchlani

Sarah Lynch

Craig M Trim

Aaron K Baughman

Alexander Block

Sihang B Fang

Anna Chaney

Brian M O'Connell

Xinyun Zhao

Kai G H Young

Jeremy R Fox

John Michael Ganci, Jr

Zachary A Silverstein

Stephen Carl Hammer

John Coleman Newell

Joel Russell Huffman

Sambit Pattnaik

Randall J Gregory, Ii

Frances Kim

Clay Crenshaw

A computer-implemented method includes monitoring, by a computing device, sensor data during gameplay of a sporting event; determining, by the computing device, predictive factors associated with a target based on the monitoring the sensor data; determining, by the computing device, a real-time region of effectiveness for the target based on the predictive factors and training data identifying historical effectiveness of the target; and outputting, by the computing device, the real-time region of effectiveness for displaying the real-time region of effectiveness around the target.

Dynamically determining a region of effectiveness of athletes during game play based on predictive factors

Consensus vehicular collision properties determination is provided by a method that receives mobile device sensor data from mobile device(s) of vehicle occupant(s). The vehicle is a vehicle of multiple vehicles involved in a collision, and the sensor data indicates movement and position information pertaining to the collision. The method shares the packaged sensor data to a decentralized ledger that stores this as part of a collection of sensor data from across multiple mobile devices of different vehicle occupants in the vehicles involved in the collision. Extraction and correlation of data from the ledger is used to determine consensus properties of the collision. The method determines, based on the consensus properties of the collision, which of the different vehicle occupants were driving the multiple vehicles involved in the collision and behavior of those occupants driving the multiple vehicles at the time of, and following, the collision.

Consensus vehicular collision properties determination

A computer-implemented method according to one embodiment includes identifying a first classifier training data element and a second classifier training data element, calculating a similarity metric between the first classifier training data element and the second classifier training data element, and determining a classification for the first classifier training data element and the second classifier training data element, utilizing the similarity metric between the first classifier training data element and the second classifier training data element.

Automatically curating ground truth data while avoiding duplication and contradiction

An approach is provided in which an information handling system analyzes a set of historical form data corresponding to a set of completed forms. The set of historical form data includes information indicating a historical order at which a set of fields were completed in the set of completed forms. Next, the information handling system determines, based on the set of historical form data, a current order at which to complete a set of incomplete fields included in a current form. In turn, the information handling system displays the current form and a user interface on a display that indicates the current order at which to complete the incomplete fields on the current form.

Dynamic field entry permutation sequence guidance based on historical data analysis

A prescriptive meeting resource recommendation engine automatically learns participant and resource preferences in the context of given meeting input data using natural language features, and automatically recommends all relevant participants and resources (teleconferences, web meetings, links, etc.) to the meeting creator. The engine uses a feature data store to associate historical persons and historical resources with various natural language features, e.g., chargrams. As the host enters text in an invitation template (such as in the title field), the engine extracts current natural language features and computes current participant scores and current resource scores based on the current natural language features. A 'forgetfulness' routine is applied to the feature data store to phase out the influence of stale data. After receiving user confirmation, the system takes appropriate action such as electronically sending invitations to the recommended participants and making reservations for the recommended resources.

Prescriptive meeting resource recommendation engine using calendar invite content

A method, system, and computer program product are provided for classifying spoken audio content with a cognitive audio classifier by applying a set of distorted audio resources through a set of speech-to-text models STTi (STT. . . STTn) to get a set of interference coherence scores based on the transcript for each speech-to-text model STTi, thereby generating a measured baseline Mi (M. . . Mn) and a practical baseline Pi (P. . . Pn) that is associated with a coherence matrix for the audio effects AEj (AE. . . AEk) that were used to generate the distorted audio resources, thereby generating training data for use in training a cognitive audio classifier which classifies input spoken audio content to measure a quality of detected vocabulary elements from the spoken audio content under the set of audio distortion effects for each speech-to-text model STTi.

Cognitive audio classifier

A system, computer program product, and method are provided to leverage a taxonomy service to format ground truth data. An artificial intelligence platform processes ground truth data, including identification of one or more applicable taxonomy tags. The identified tags are filtered and applied to the ground truth data, thereby constructing an output string that incorporates the ground truth data together with one or more of the identified tags, effectively transforming the ground truth data. Application of the transformed ground truth data is employed to accurately identify the source and/or meaning of the natural language, and in one embodiment, to produce a physical action or transformation of a physical hardware device.

Natural language processing and classification

An approach for pathing users of an AR (Augmented Reality) software event is provided. The approach includes retrieving a matched pair of users based on a social media and game profile. The approach determines the current event of the matched pair and creates a new event, requiring cooperative engagement between the matched pair. Based on the status notification from the matched pair associated with the created new event, the approach re-match the pairs for future and new AR event.

Connectivity mechanism utilizing augmented reality

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining an input text for an output speech. The number of words and syllables are counted in each sentence, and a mean sentence length of the input text is calculated. Each sentence length is checked against the mean sentence length and a variation for each sentence is calculated. For the input text, the consumability-readability score is produced as an average of variations for all sentences in the input text. The consumability-readability score indicates the level of satisfaction for the listener of the output speech based on the input text.

Assessment of speech consumability by text analysis

Embodiments provide a computer implemented method in a data processing system including a processor and memory storing instructions, which are executed by the processor to cause the processor to implement the method for providing an annotation policy for annotating a corpus including a plurality of electronic documents. The method includes: annotating an occurrence of a first term with a class in an electronic document; recommending a new annotation policy based on at least one annotation for the occurrence of first term; and storing the new annotation policy in a storage device.

Annotation policies for annotation consistency

A mechanism is provided in a data processing system for assessing question answering system performance. The mechanism receives question answering system results. The question answering system results comprise questions posed to the question answering system, answers returned by the question answering system for each question posed to the question answering system, and a confidence value for each answer. The question answering system is trained or tested using the ground truth questions and answers. The mechanism performs a matching operation comparing each question in the question answering system results to questions in the ground truth. A given question is determined to be on-topic or off-topic based on results of the matching operation. For a plurality of confidence threshold values, the mechanism determines a rightness or wrongness of each answer in the question answering system results. The mechanism generates performance statistics for the plurality of confidence threshold values based on whether each question is on-topic or off-topic and whether each answer is right or wrong. The mechanism presents the performance statistics to the user via a user interface.

Automatically assessing question answering system performance across possible confidence values

A system, computer program product, and method are provided to leverage a taxonomy service to format ground truth data. An artificial intelligence platform processes ground truth data, including identification of one or more applicable taxonomy tags. The identified tags are filtered and applied to the ground truth data, thereby constructing an output string that incorporates the ground truth data together with one or more of the identified tags, effectively transforming the ground truth data. Application of the transformed ground truth data is employed to accurately identify the source and/or meaning of the natural language, and in one embodiment, to product a physical action or transformation of a physical hardware device.

Augmentation of a run-time query

A mechanism is provided in a data processing system for comparing similarity of questioning answer system ground truth answers to question answering system result answers. The mechanism receives question answering system results. The question answering system results comprise questions posed to the question answering system, answers returned by the question answering system for each question posed to the question answering system, and a confidence value for each answer. The question answering system is trained or tested using the ground truth questions and answers. The mechanism performs a matching operation comparing each result answer in the question answering system results to a corresponding ground truth answer. The matching operation is an asymmetric containment comparison and wherein the matching operation determines similarity of each result answer to the corresponding ground truth answer. The mechanism determines whether each result answer is right or wrong based on results of the matching operation.

Automated similarity comparison of model answers versus question answering system output

In a multi-tiered simulation configuration, a combination of predictive models is executed such that each tier in the multi-tiered simulation configuration executes at least one predictive model to produce a corresponding set of predicted events, and a predicted event from a first tier in the configuration forms an input to a next tier in the configuration. Using a subset of a selected set of predicted events outputted from a corresponding selected tier in the multi-tiered simulation configuration, a set of features is extracted, each feature in the set of features having an effect on an outcome of the simulated process. The set of features is used in a demand level prediction model to predict a threshold demand, wherein reaching the threshold demand in an actual utilization of a computing resource is indicative of a likelihood of an unforeseen rise in a demand for the computing resource after a period.

Adjusting cloud resource allocation

A method, system, and computer program product for adjusting cloud resource allocation using n-tier simulation are provided in the illustrative embodiments. In a multi-tiered simulation configuration, a combination of predictive models is executed such that each tier executes at least one predictive model to produce a corresponding set of predicted events. Each tier simulates a process that is consuming a computing resource. Using a subset of a selected set of predicted events outputted from a corresponding selected tier, a set of features is extracted. each feature in the set of features has an effect on an outcome of the simulated process. The set of features is used in a demand level prediction model to predict a threshold demand. Reaching the threshold demand in an actual utilization of the computing resource is indicative of a likelihood of an unforeseen rise in a demand for the computing resource after a period.

Growing community of inventors

Austin, TX, United States of America

Stefan Van Der Stockt