63 results about "Cognitive analysis" patented technology

A cognitive and / or motor skill testing system and method may include a processor that records respective time information for each of multiple positions of a display device that are traced during administration of a test, that determines speed and / or velocity values based on the recorded time information, and that outputs test result information based on the determined values. The test result information may be based on a comparison between a graphed curve of such values to an ideal curve. The positions may correspond to a path between displayed targets whose size and / or distance therebetween depend on past test performance. The system and / or method may output a change expected with a change to therapy parameters for a patient, where the expected change is determined based on changes which occurred in other patients having similar test results and therapy parameters as those of the patient.

An automated method for processing security event data in association with a cybersecurity knowledge graph having nodes and edges. It begins by receiving from a security system (e.g., a SIEM) information representing an offense. An offense context graph is built. Thereafter, and to enhance the offense context graph, given nodes and edges of the knowledge graph are prioritized for traversal based on an encoding captured from a security analyst workflow. This prioritization is defined in a set of weights associated to the graph nodes and edges, and these weights may be derived using machine learning. The offense context graph is then refined by traversing the nodes and edges of the knowledge graph according to a prioritization tailored at least in part by the encoding. In addition to using security analyst workflow to augment generation of weights, preferably the machine learning system provides recommendations back to the security analysts to thereby influence their workflow.

The embodiment of the invention relates to the field of data analysis and processing, and discloses a cognitive analysis method and system based on interaction. The method includes the steps: outputting interactive output information to interact with a user in at least one preset interaction manner, and obtaining the interactive input information of the user; performing the content recognition andanalysis of interactive input information to obtain cognitive analysis data; constructing a user's personal cognitive structure model based on cognitive analysis data. By implementing the embodimentsof the present invention, the user's personal cognitive information can be analyzed, thereby providing more powerful help for the user's mental health service.

Accurate and concise summarization of a media production is achieved using cognitive analysis which groups segments of the production into clusters based on extracted features, selects a representative segment for each cluster, and combines the representative segments to form a summary. The production is separated into a video stream, a speech stream and an audio stream, from which the cognitive analysis extracts visual features, textual features, and aural features. The clustering groups segments together whose visual and textual features most closely match. Selection of the representative segments derives a score for each segment based on factors including a distance to a centroid of the cluster, an emotion level, an audio uniqueness, and a video uniqueness. Each of these factors can be weighted, and the weights can be adjusted in accordance with user input. The factors can have initial weights which are based on statistical attributes of historical media productions.

The invention discloses a human brain language cognition modeling method. The human brain language cognition modeling method comprises the following steps of initialization of a cognitive state example, mapping of probability distribution between activation characteristics and observation data, definition of a brain tacit cognition model and parameter analysis of the tacit cognition model. In the cognition modeling process, input stimulation, the observation result and the tacit cognition state are defined as triple time sequences related to a dynamic event, namely a cognition stimulation task time sequence, an observation characteristic time sequence and a tacit cognition state time sequence, the triple time sequences are related to one another through a set of probability distribution, and not all collected brain data are treated as static information for statistics. Therefore, the human brain language cognition modeling method does not need to meet the basic assumption based on statistics, is established under a small sample data condition, and guarantees the correctness of the cognition analysis result, thereby achieving cognition modeling under the small sample data condition. The human brain language cognition modeling method improves the accuracy of cognition modeling, and provides an effective approach for complex cognition analysis.

The invention discloses a cognitive analysis-oriented Chinese event representation method, provides a structured event representation model and provides a Chinese text analytic processing-based assignment method of key attributes of the event type and the like. The cognitive analysis-oriented Chinese event representation method supports attribute extraction and presentation of social events in the fields of politics, military, diplomacy and the like; and the realistic feasibility is provided for representation, organization, storage management and cognitive analysis application of massive event data.

Cognitive analysis using applied analog circuits including receiving, by a circuit, a first set of data results and a second set of data results; charging a first capacitor on the circuit with a first unit of charge for each of the first set of data results that indicates a positive data point; charging a second capacitor on the circuit with a second unit of charge for each of the second set of data results that indicates a positive data point; applying a charge from the first capacitor and a charge from the second capacitor to an analog unit of the circuit; and generating a signal on a circuit output indicating that a ratio of the positive data points in the first set of data results to the positive data points in the second set of data results is greater than a statistical significance.

An approach is provided in which a network bandwidth manager receives a first request to access site content from a source site over a computer network. The network bandwidth manager analyzes the site content against a domain corpora that corresponds to one or more organizational needs of an organization. When the network bandwidth manager receives a second request corresponding to the source site, the network bandwidth manager modifies a quality of service of the computer network to access the source site based upon the previous analysis. In turn, the network bandwidth manager provides access to the source site over the computer network utilizing the modified quality of service.

The most likely path for an underground utility having an unknown location is predicted using artificial intelligence. A cognitive system is trained with details associated with historical utility installations whose underground paths are known. The system is applied to whatever installation details are available for the unknown underground utility such as geographic features which are subjected to spatial correlation to derive geographic locations relative to a region of interest for the underground utility. Cognitive analysis is performed on the locations in association with the features to generate candidate paths for the utility. The candidate paths are presented to the user along with computed confidence scores. The installation details may further include nongeographic features used in the cognitive analysis such as a date of installation of the utility or an entity associated with the utility.

The invention relates to in-set access control improved by fully utilizing natural language processing. Natural language processing is enhanced by linguistically extracting intelligence about a user.A history of user queries is analyzed by a natural language classifier to determine various user intents, and these intents are combined to form a user intent profile. The profile includes elements ofsentiment, emotion and tone. The profile can be used in various ways including restricting access to documents in a collection, or refining a cognitive analysis of a query. For access restriction, adetermination is made that the user intent is inconsistent with a document, and the user is denied access to the document. This determination involves a user intent score which is compared to a scoreof the document. For cognitive analysis, searching of reference documents is filtered by excluding documents based on the user intent. The searching includes a comparison of meta-data tags of the documents to the user intent.

An automated method for processing security event data in association with a cybersecurity knowledge graph having nodes and edges. It begins by receiving from a security system (e.g., a SIEM) information representing an offense. An offense context graph is built. Thereafter, and to enhance the offense context graph, given nodes and edges of the knowledge graph are prioritized for traversal based on an encoding captured from a security analyst workflow. This prioritization is defined in a set of weights associated to the graph nodes and edges, and these weights may be derived using machine learning. The offense context graph is then refined by traversing the nodes and edges of the knowledge graph according to a prioritization tailored at least in part by the encoding. In addition to using security analyst workflow to augment generation of weights, preferably the machine learning system provides recommendations back to the security analysts to thereby influence their workflow.

One or more embodiments include a cognition analysis system for determining a cognitive reaction to a software application update. The cognition analysis system determines that a software applicationexecuting on a computing device has been modified into an updated software application. The cognition analysis system acquires, via at least one sensor, sensor data associated with a user of the updated software application. The cognition analysis system determines, based on the sensor data, at least one of a cognitive workload and an emotional state associated with a user interaction with a feature of the updated software application.

Resolving software patch issues is provided. Recorded activities performed by users to resolve an issue with a patch applied to an application on a group of client devices are compared. A set of common user activities are identified within the recorded activities performed by the users. A subset of highest ranking common user activities is selected from the set of common user activities. A fix for the issue with the patch is generated based on the subset of highest ranking common user activities. Corrective action based on the fix is taken to resolve the issue with the patch on a client device, the client device experiencing the issue resolved by users on the group of client devices.

A method, system and a computer program product are provided for obscuring web searches by performing cognitive analysis on the one or more user search inquiries to identify a user search behavior profile and user characterization information for the first user and generating or retrieving one or more simulated user search behavior profiles for one or more simulated users, and then generating one or more obfuscating search inquiries consistent with the one or more simulated user search behavior profiles for issuance with the user search inquiries to impair the search engine from accurately determining the user characterization information for the first user.

Accurate and concise summarization of a media production is achieved using cognitive analysis which groups segments of the production into clusters based on extracted features, selects a representative segment for each cluster, and combines the representative segments to form a summary. The production is separated into a video stream, a speech stream and an audio stream, from which the cognitive analysis extracts visual features, textual features, and aural features. The clustering groups segments together whose visual and textual features most closely match. Selection of the representative segments derives a score for each segment based on factors including a distance to a centroid of the cluster, an emotion level, an audio uniqueness, and a video uniqueness. Each of these factors can be weighted, and the weights can be adjusted in accordance with user input. The factors can have initial weights which are based on statistical attributes of historical media productions.