International Business Machines Corporation

Xiao Feng Ji

Dan Zhang

Yuan Jin

Wei Jun Zheng

Jun Zhou

Xiao Xia Mao

Qing Lu

Ziqiumin Wang

Yuan Jie Song

Meng Chai

Min Huang

Li Ping Wang

Michael R O'Brien

Shi Kun Li

Ying Li

Li Bo Zhang

Molly Chang

Di Li Hu

Xiao Rui Shao

Yu Li

Xin Che

Liu Yao He

Ya Ju Yan

Shi Hui Gui

Jialei Ma

Wen Ting Su

Nan Nan Li

Zhong Gang Shen

A present invention embodiment analyzes documents. A first document is received comprising a plurality of sentences that each include one or more words. A matrix is populated with the plurality of sentences, wherein each of the one or more words of each sentence in the matrix is encoded as a numerical value. The matrix is processed using a machine learning model to generate a first feature map. The first feature map is compared to a second feature map of a corresponding second document to identify a shared document element between the first document and the second document based on a common feature in the first feature map and the second feature map. The shared document element is indicated via a user interface.

Method implemented in computer system for analyzing document versions to identify shared document elements using machine learning, and non-transitory computer-readable storage medium

A method, computer system, and a computer program product for text corpus concreteness modification are provided. A computer performs natural language processing to determine a concreteness level of a first individual sentence of a text corpus. The computer generates, based on the natural language processing, a proposed change of the individual sentence. The individual sentence with the proposed change includes a modified concreteness level and preserves a general meaning of the individual sentence. The computer transmits the proposed change for presentation of the proposed change.

Automated identification of sentence concreteness and concreteness conversion

A method of generating a prototype of a graphical user interface (GUI). The method includes acquiring a draft wireframe representing a GUI design, the draft wireframe including one or more wireframe components, and decomposing the draft wireframe into one or more component slices, each component slice including a respective wireframe component of the one or more wireframe components. The method also includes generating a component slice sequence including the one or more component slices and at least one additional component slice selected based on the draft wireframe, constructing a wireframe based on the component slice sequence, and generating a prototype of the GUI design based on the constructed wireframe.

Generation of graphical user interface prototypes

According to one embodiment, a method, computer system, and computer program product for adjusting an audible area of an avatar's voice is provided. The present invention may include receiving, at a microphone, a source audio; creating a received audio; calculating, by a generative model, a voice propagation distance of a user based on the source audio, the received audio, and a templated text sentence describing a category of a mixed reality environment experienced by the user; drawing a virtual circle within the mixed reality environment centered on a user avatar representing the user and with a radius equal to the voice propagation distance; and transmitting the source audio to one or more participants within the mixed-reality environment represented by one or more participant avatars located within the virtual circle.

Adjusting audible area of avatar's voice

A method, computer system, and a computer program product are provided for training a neural network for finding queried videos. Two pairs of video clips and associated text are obtained from a first dataset and a second dataset. The first dataset is used to train two video encoders by providing the video clips to the encoders as input and providing the outputs to a cosine similarity calculator. The second dataset is used to train a multi-mentor paradigm with two mentors. A first mentor and a second mentor are each provided the pair of textual data inputs. The first mentor provides a similarity value comparison, and the second mentor provides a word mover distance. Using the output from the multi-mentor paradigm and the encoders, a contrastive loss is calculated and used to provide contrastive learning of video features by differentiating similarity and dissimilarity of the video clips.

Video retrieval techniques using video contrastive learning

Embodiments of the invention are directed to automatically capturing user interface screenshots for use in documentation of a software product. Aspects include identifying a user interface window of the software product and creating a degree-of-completion graph for the user interface window. Aspects also include capturing a plurality of screenshots of the user interface window during use of the software product and calculating a degree-of-completion percentage for each of the plurality of screenshots. Aspects further include identifying a subset of the plurality of screenshots to be included in the software product documentation based on the degree-of-completion percentage.

Automatic capture of user interface screenshots for software product documentation

Video analysis by receiving video data associated with a multi-participant meeting, identifying a first participant viewpoint, a related argument and an authority level of a viewpoint-argument, from the video data using a machine learning model, identifying a first topic within the video data, correlating the first participant viewpoint to the first topic, determining a distance between the first participant viewpoint and a second participant viewpoint, the second participant viewpoint correlated to the first topic, and providing a depiction of a relationship between the first participant viewpoint and the second participant viewpoint according to the distance.

Viewpoint analysis of video data

Embodiments relate to decoding communications with token sky maps. At least one electronic communication including emoticons having a non-original meaning is received. A candidate meaning is determined for the emoticons having the non-original meaning in the at least one electronic communication based at least in part on token neighborhood distribution structures. The candidate meaning for the emoticons having the non-original meaning is caused to be displayed on at least one device.

Decoding communications with token sky maps

Aspects of the present disclosure relate to automatically generating a user manual using a technique that includes training a first model with a first set of training data. The technique further includes generating, by the first model, a set of operations and a set of windows, where the set of operations and the set of windows are functions of the program. The technique further includes, generating a plurality of tasks, where a first task comprises a first operation being performed on a first window. The technique further includes determining an order of the plurality of tasks and calculating a level score for the first operation of the first window. The technique further includes assembling the user manual having the plurality of tasks in the determined order.

Intelligent generation and organization of user manuals

A method for processing software layout can include exporting layout setting information from design elements of a software; formatting the layout setting information, and storing it in a layout characteristic file; and importing the layout setting information in the layout characteristic file into design elements of another software. Layout information of each language can be stored in a customizable layout characteristic file.

Software layout processing localization

A method for navigating is provided. The method comprises, in response to input on user equipment of a first member of a group who is travelling to a destination, one or more processors acquiring current position information of the user equipment of the first member. The method further includes one or more processors sending a first message to a server. The first message includes the current position information indicating an area where the first member was when the first message was sent. The first message is for directing a member of the group, who receives the first message when passing the area, to the same destination as the first member.

Navigation by using instant messaging

Synchronizing a Graphical User Interface (GUI) operation includes receiving operation information of the GUI operation performed on a first machine. The operation information includes object information and action information. The object information is in a first language and indicates a GUI object to which the GUI operation is directed. The action information indicates an action performed by the GUI operation on the GUI object. The object information in the first language is converted to object information in a second language. A GUI object in a GUI displayed on a second machine is identified according to the object information in the second language. The action indicated by the action information is performed on the identified GUI object.

Growing community of inventors

Beijing, China

Xiao Feng Ji