Abstract: Technology for inspection for detecting a defect of a printed matter using machine logic informed by machine learning. Some embodiments of the present invention may include one, or more, of the following features: (i) generates defect datasets; (ii) generates defect libraries; (iii) uses the generated defect libraries for deep learning training; and (iv) uses machine learning to detect defects using computer code (for example, a *.jpg format file) corresponding to an image of a piece of printed matter instead of using a visual image (that is, an image of the type that is created when a person takes a picture using a traditional film camera).

Abstract: A processor may automatically generate one or more transcripts based on a media context. The processor may append at least one of the one or more transcripts to the media. The processor may modify the at least one of the one or more transcripts based on an adjustment to a weight factor.

Abstract: A method, computer system, and a computer program product for blockchain based resource predictions and management is provided. Embodiments of the present invention may include receiving a request for a prediction of a future resource requirement. Embodiments of the present invention may include loading data structures. Embodiments of the present invention may include classifying collected data. Embodiments of the present invention may include predicting the future resource requirement. Embodiments of the present invention may include adjusting the priority of the future resource requirement. Embodiments of the present invention may include providing notifications.

Abstract: A video is received. One or more subtitles are determined for the video. Whether a word found in a background of the video is similar to a word found in the one or more subtitles is determined. Responsive to determining the word found in the background of the video is similar to the word found in the one or more subtitles, one or more updated subtitles are generated. The one or more updated subtitles include the word found in the background of the video and remove the word found in the one or more subtitles that is similar. A metric for the one or more updated subtitles is calculated. Whether the metric is larger than a threshold is determined. Responsive to determining the metric is larger than the threshold, the video is updated to include the one or more updated subtitles.

Abstract: Aspects of the present disclosure relate to processing irregularly arranged characters. An image is received. An irregularly arranged character within the image is detected. A direction of the irregularly arranged character is modified to a proper direction to obtain a properly oriented character. The properly oriented character is recognized to obtain a first identified character. The image is then rebuilt by replacing the irregularly arranged character with the first identified character, the first identified character in a machine-encoded format.

Abstract: Embodiments of the present disclosure relate to logical channel management in a communication network. In an embodiment, a mapping between a plurality of logical channels of at least one terminal device and a plurality of resource sets of a network device is determined. The resource sets are assigned for communication between the at least one terminal device and the network device via the logical channels. If at least one resource set is overloaded, at least one of the plurality of logical channels is determined based on the mapping. Status information indicating that the at least one logical channel is in a congestion status is caused to be transmitted to a target terminal device of the at least one terminal device, the target terminal device communicating with the network device via the at least one logical channel.

Abstract: A processor may automatically generate one or more transcripts based on a media context. The processor may append at least one of the one or more transcripts to the media. The processor may modify the at least one of the one or more transcripts based on an adjustment to a weight factor.

Abstract: Technology for inspection for detecting a defect of a printed matter using machine logic informed by machine learning. Some embodiments of the present invention may include one, or more, of the following features: (i) generates defect datasets; (ii) generates defect libraries; (iii) uses the generated defect libraries for deep learning training; and (iv) uses machine learning to detect defects using computer code (for example, a *.jpg format file) corresponding to an image of a piece of printed matter instead of using a visual image (that is, an image of the type that is created when a person takes a picture using a traditional film camera).

Abstract: In an approach for a text block recognition in a document, a processor detects characters in the document using an object detection technique. A processor identifies positions of the detected characters in the document. A processor analyzes semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters. A processor recognizes text blocks of related characters based on the semantic connectivity analysis. A processor outputs the text blocks associated with the related characters.

Abstract: Computer automated interactive activity recognition based on keypoint detection includes retrieving, by one or more processors, a temporal sequence of image frames from a video recording. The one or more processors identify first and second keypoints in each of the image frames in the temporal sequence using machine learning techniques. The first keypoints are associated with an object in the temporal sequence of image frames while the second keypoints are associated with an individual interacting with the object. The one or more processors combine the first keypoints with the second keypoints and extract spatial-temporal features from the combination that are used to train a classification model based on which interactive activities can be recognized.

Abstract: Generating a query result utilizing a knowledge graph in an artificial intelligence chatbot is provided. Characteristics of a query are identified. The characteristics of the query are mapped to base elements of the knowledge graph in the artificial intelligence chatbot. A set of query paths are generated in the knowledge graph based on the mapping of the characteristics of the query to the base elements of the knowledge graph. One or more query paths in the set of query paths in the knowledge graph are validated based on a respective score of each query path. A query result corresponding to the query is generated based on the validated one or more query paths in the knowledge graph.

Abstract: A method, computer system, and a computer program product for analyzing visual defects is provided. The present invention may include generating a template image. The present invention may include capturing a test image. The present invention may include performing an image registration between the template image and the test image. The present invention may include generating a registered test image. The present invention may include performing an image difference analysis between the registered test image and the template image. The present invention may include generating a differential image. The present invention may include synthesizing the registered, differential image, and template image. The present invention may include generating a synthetic image. The present invention may include inputting the synthetic image into a multi-scale detection network. The present invention may include generating a defect map.

Abstract: Disclosed embodiments provide techniques for computerized technical support. A knowledge graph for a computer application is established. An input query from a user is processed to extract entities used as action identifiers. One or more nodes within the knowledge graph are identified, along with corresponding relationship edges leading to the nodes. When multiple candidate nodes are found that contain information relevant to the input query, a custom clarification statement is created based on the one or more identified relationship edges. The user provides answers to the clarification statement to narrow down which nodes contain the most relevant information. This process may continue, eliminating nodes based on user responses, until a single node remains, corresponding to an action identifier. The action identifier includes action description information that provides technical assistance to a user.

Abstract: Computer automated interactive activity recognition based on keypoint detection includes retrieving, by one or more processors, a temporal sequence of image frames from a video recording. The one or more processors identify first and second keypoints in each of the image frames in the temporal sequence using machine learning techniques. The first keypoints are associated with an object in the temporal sequence of image frames while the second keypoints are associated with an individual interacting with the object. The one or more processors combine the first keypoints with the second keypoints and extract spatial-temporal features from the combination that are used to train a classification model based on which interactive activities can be recognized.

Abstract: Embodiments of the present disclosure relate to logical channel management in a communication network. In an embodiment, a mapping between a plurality of logical channels of at least one terminal device and a plurality of resource sets of a network device is determined. The resource sets are assigned for communication between the at least one terminal device and the network device via the logical channels. If at least one resource set is overloaded, at least one of the plurality of logical channels is determined based on the mapping. Status information indicating that the at least one logical channel is in a congestion status is caused to be transmitted to a target terminal device of the at least one terminal device, the target terminal device communicating with the network device via the at least one logical channel.

Abstract: In an approach for a text block recognition in a document, a processor detects characters in the document using an object detection technique. A processor identifies positions of the detected characters in the document. A processor analyzes semantic connectivity among the detected characters based on the positions and semantic connectivity of the characters. A processor recognizes text blocks of related characters based on the semantic connectivity analysis. A processor outputs the text blocks associated with the related characters.

Abstract: A method, computer system, and a computer program product for analyzing visual defects is provided. The present invention may include generating a template image. The present invention may include capturing a test image. The present invention may include performing an image registration between the template image and the test image. The present invention may include generating a registered test image. The present invention may include performing an image difference analysis between the registered test image and the template image. The present invention may include generating a differential image. The present invention may include synthesizing the registered, differential image, and template image. The present invention may include generating a synthetic image. The present invention may include inputting the synthetic image into a multi-scale detection network. The present invention may include generating a defect map.

Abstract: A video is received. One or more subtitles are determined for the video. Whether a word found in a background of the video is similar to a word found in the one or more subtitles is determined. Responsive to determining the word found in the background of the video is similar to the word found in the one or more subtitles, one or more updated subtitles are generated. The one or more updated subtitles include the word found in the background of the video and remove the word found in the one or more subtitles that is similar. A metric for the one or more updated subtitles is calculated. Whether the metric is larger than a threshold is determined. Responsive to determining the metric is larger than the threshold, the video is updated to include the one or more updated subtitles.

Abstract: An aspect of the present invention discloses a method for extracting content from a document. The method includes one or more processors identifying a visual anchor corresponding to a text element depicted in a first document utilizing an edge detection analysis. The method further includes determining edge coordinates of the text element depicted in the first document. The method further includes determining text at a leading edge of the text element depicted in the first document and text at a trailing edge of the text element depicted in the first document, based on the determined edge coordinates. The method further includes extracting a complete version of the text element depicted in the first document, from a plain text version of the first document, utilizing the determined text at the leading edge of the text element and the determined text at the trailing edge of the text element.

Abstract: A method, computer system, and a computer program product for predictive maintenance is provided. The present invention may include recording, using an autonomous robot moving along a surface through a plurality of positions in a room, a plurality of data associated with an under-floor appliance provided beneath the surface of the room. The present invention may also include calculating, based on the recorded plurality of data associated with the under-floor appliance provided beneath the surface of the room, a material composition associated with the plurality of positions in the room. The present invention may further include generating, based on the calculated material composition associated with the plurality of positions in the room, a layout diagram for visualizing a layout of the under-floor appliance provided beneath the surface of the room.