International Business Machines Corporation

Emc IP Holding Company LLC

Kang Ed Zhang

Wen Jie Wang

Rong Fu

Jian Dong Yin

Hao Sheng

Zhuo Jp Cai

Yu Sun

Jian Wen Chi

Li Yue

Chuan Qing Yu

Liyi Zhou

Qing Shan Zhang

Yuheng Zhang

Gary Jialei Wu

Si Yuan Zhang

Yi Ming Wang

Ke Wen Lin

Jiu Fu Guo

Guang Qing Zhong

Wayne Wei Gao

Zixuan Wu

A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include calculating a priority factor with a node autonomous center in a node and computing a node service capability with the node autonomous center. The operations may further include selecting, with the node autonomous center, a task based on the priority factor and the node service capability. The operations may further include directing the task to the node.

Distributed system workload management via node autonomy

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.

Automatic appending of subtitles based on media context

Managing an image storage space is provided. A number of processor units identifies a benchmark image in a similar images group. A number of other images not identified in the similar images group as the benchmark image is a set of similar images. The number of processor units creates an image mapping tree. The image mapping tree has a root block for the benchmark image and blocks arranged in a set of layers below the root block based on the set of similar images; the blocks represent portions of the benchmark image; and a plurality of lower blocks in the blocks in a lower layer correspond to subdivisions in an upper block in the blocks in an upper layer. The number of processor units stores a set of selected blocks in the set of similar images that have differences from a set of corresponding blocks in image mapping tree for the benchmark image. The number of processor units store metadata for the set of selected blocks that describes set of paths in the image mapping tree from the set of corresponding blocks in the image mapping tree to the root block.

Image storage system for images with duplicate parts

A method and system for controlling elevator dispatch is provided. User data, including user behavior, is collected from a number of users over a specified time period. Elevator use data for a number of elevators in a building is also collected over the specified time period. Applying the user data and elevator use data, an elevator dispatch model is constructed that predicts future elevator use according to predicted user needs. An elevator control system dispatches the elevators according to the dispatch model. The elevator dispatch model is refined according to feedback data collected from users over a subsequent time period.

End-to-end cognitive elevator dispatching system

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.

Subtitle generation using background information

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.

Processing irregularly arranged characters

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.

Knowledge graph-based query in artificial intelligence chatbot with base query element detection and graph path generation

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.

Dynamic workflow with knowledge graphs

Embodiments of the present disclosure relate to runtime type identification (RTTI) of an object. In an embodiment, a computer-implemented method is disclosed. A class inheritance relationship between a plurality of classes in at least one source code section is generated. Respective type identifications are assigned to identify the classes in the class inheritance relationship. In accordance with presence of a first operation related to accessing a target pointer to an object of a target class of the classes, a type identification for the target class is caused to be recorded with at least one bit of a memory address of the target pointer that can be omitted in addressing the target pointer. RTTI is caused to be performed based on the class inheritance relationship and the at least one bit of the memory address of the target pointer. In other embodiments, a system and a computer program product are disclosed.

Runtime type identification of an object utilizing class inheritance relationships

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.

Real-time detection and visualization of potential impairments in under-floor appliances

A method for real-time cloud container communications routing is provided. The method monitors network traffic to a first network resource located within a first region. Based on monitoring the network traffic, the method determines a second region associated with at least a portion of the network traffic. The method generates a resource backup of the first network reference. The resource backup represents a current state of the first network resource. The method transfers the resource backup to a second network resource associated with the second region and redirects at least a portion of the network traffic to the second network resource.

Real-time cloud container communications routing

Techniques for monitoring an access request are described. For instance, a method comprises: obtaining a request parameter indicating a target storage space to which the access request is directed; determining a target address range of the target storage space based on the request parameter; determining, in a set of kernel logs, a target kernel log associated with the access request based on the target address range, the set of kernel logs recording operations that occur in a kernel of an operating system; and determining information of an operation of the access request based on the kernel log, the operation corresponding to the target kernel log.

Method, device and computer program product for monitoring access request

A method for controlling a compile a software application. The method includes at least one computer processor generating, from source code corresponding to a software application, a plurality of pre-optimization intermediate representations (IRs) of functions associated with the software application. The method further includes generating a plurality of post-optimization IRs of the functions associated with the software application by executing one or more optimization routines on the plurality of pre-optimization IRs of functions. The method further includes determining a set of IRs of functions, from the plurality of generated pre-optimization IRs of the functions associated with the software application and the generated plurality of post-optimization IRs of the functions associated with the software application. The method further includes converting a determined set of IRs of functions to an executable version of the software application.

Reducing compilation time for computer software

A method includes detecting, by a contact sensing layer, a position of one or more fingers of a mobile device user, the contact sensing layer is located in a back area of a mobile device and the one or more fingers of the mobile device user are in direct contact with the contact sensing layer, receiving the detected position of the one or more fingers, identifying a plurality of advanced features contained in at least one software application running on the mobile device, selecting a feedback type based on the plurality of advanced features, and sending the selected feedback type to an interactive layer of the mobile device causing the interactive layer to generate a notification which is detectable by the one or more fingers, the notification communicates at least one of the advanced features to the mobile device user.

Growing community of inventors

Shanghai, China

Kang Ed Zhang