Patents by Inventor Haoyu Wang
Haoyu Wang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11379666Abstract: A mechanism is provided to implement suggestion of new entity types with discriminative importance analysis. The mechanism obtains a list of predefined intents from a chatbot designer. The mechanism receives an input sentence having a target intent within the list of predefined intents. The mechanism performs intent-specific importance analysis on the input sentence to generate an importance score for each token in the input sentence. The mechanism ranks the tokens in the input sentence by importance score and outputs a token with a highest importance score as a candidate entity type.Type: GrantFiled: April 8, 2020Date of Patent: July 5, 2022Assignee: International Business Machines CorporationInventors: Haode Qi, Ming Tan, Yang Yu, Navneet N. Rao, Saloni Potdar, Haoyu Wang
-
Publication number: 20220183631Abstract: An automatic test device and method for auditory brainstem response (ABR) collects an ABR dataset at a plurality of sound loudness levels, increases the times of level averaging by iteration based on an adaptive average method, and improves a signal-to-noise ratio until ABR signal detection conditions are met. Signal detection includes determining that the time lag between average curves obtained from the ABR dataset is within a specified range. Iteration is terminated when the ABR signal is detected or a maximum number of iterations is reached. A minimum loudness level required to detect the ABR signal is used as a hearing threshold. An accurate loudness level corresponding to the hearing threshold is obtained by function fitting on the number of iterations used at each loudness level and interpolation. The threshold detection can effectively reduce the number of times that an ABR recording needs to be acquired.Type: ApplicationFiled: September 17, 2019Publication date: June 16, 2022Inventors: Yunfeng HUA, Hao WU, Haoyu WANG, Bei LI, Xu DING, Zhiwu HUANG, Xueling WANG
-
Patent number: 11328221Abstract: A method of text classification includes generating a text embedding vector representing a text sample and applying weights of a regression layer to the text embedding vector to generate a first data model output vector. The method also includes generating a plurality of prototype embedding vectors associated with a respective classification labels and comparing the plurality of prototype embedding vectors to the text embedding vector to generate a second data model output vector. The method further includes assigning a particular classification label to the text sample based on the first data model output vector, the second data model output vector, and one or more weighting values.Type: GrantFiled: April 9, 2019Date of Patent: May 10, 2022Assignee: International Business Machines CorporationInventors: Yang Yu, Ming Tan, Ravi Nair, Haoyu Wang, Saloni Potdar
-
Patent number: 11314910Abstract: The present disclosure relates to a discrete element method (DEM)-based simulation method and system for acoustic emission (AE). The simulation method includes: arranging a monitoring point on a surface of a numerical model; monitoring a velocity waveform of the monitoring point; and analyzing the velocity waveform to obtain a hit, energy, and a b-value of AE. The method in the present disclosure can resolve problems of principle incompliance, poor authenticity, and high occupation of calculation resources in a traditional simulation method for AE.Type: GrantFiled: July 26, 2021Date of Patent: April 26, 2022Assignee: INSTITUTE OF GEOLOGY AND GEOPHYSICS, CHINESE ACADEMY OF SCIENCESInventors: Lei Xue, Fengchang Bu, Mengyang Zhai, Xiaolin Huang, Chao Xu, Haoyu Wang
-
Patent number: 11308944Abstract: A mechanism is provided for implementing an intent segmentation mechanism that segments intent boundaries for multi-intent utterances in a conversational agent. For each term of a set of terms in the utterance from a real-time chat session, a set of adversarial utterances is generated for the utterance. An influence of changing each term is determined so as to identify a term importance value. Utilizing the term importance value, one or more of a change in ranking of the intent of the utterance or a change in confidence with regard to the intent of the utterance is identified. An entropy-based segmentation of the utterance into a plurality of candidate partitions is performed. An associated intent and entropy value are then assigned. Based on a segment with minimum entropy, a call associated with the real-time chat session is directed to an operation associated with an intent of the segment with minimum entropy.Type: GrantFiled: March 12, 2020Date of Patent: April 19, 2022Assignee: International Business Machines CorporationInventors: Ming Tan, Haoyu Wang, Saloni Potdar, Yang Yu, Navneet N. Rao, Haode Qi
-
Patent number: 11301626Abstract: Provided is a method, system, and computer program product for context-dependent spellchecking. The method comprises receiving context data to be used in spell checking. The method further comprises receiving a user input. The method further comprises identifying an out-of-vocabulary (OOV) word in the user input. An initial suggestion pool of candidate words is identified based, at least in part, on the context data. The method then comprises using a noisy channel approach to evaluate a probability that one or more of the candidate words of the initial suggestion pool is an intended word and should be used as a candidate for replacement of the OOV word. The method further comprises selecting one or more candidate words for replacement of the OOV word. The method further comprises outputting the one or more candidates.Type: GrantFiled: November 11, 2019Date of Patent: April 12, 2022Assignee: International Business Machines CorporationInventors: Panos Karagiannis, Ladislav Kune, Saloni Potdar, Haoyu Wang, Navneet N. Rao
-
Patent number: 11288578Abstract: A computer system identifies threads in a communication session. A feature vector is generated for a message in a communication session, wherein the feature vector includes elements for features and contextual information of the message. The message feature vector and feature vectors for a plurality of threads are processed using machine learning models each associated with a corresponding thread to determine a set of probability values for classifying the message into at least one thread, wherein the threads include one or more pre-existing threads and a new thread. A classification of the message into at least one of the threads is indicated based on the set of probability values. Classification of one or more prior messages is adjusted based on the message's classification. Embodiments of the present invention further include a method and program product for identifying threads in a communication session in substantially the same manner described above.Type: GrantFiled: October 10, 2019Date of Patent: March 29, 2022Assignee: International Business Machines CorporationInventors: Dakuo Wang, Ming Tan, Mo Yu, Haoyu Wang, Yupeng Gao, Chuang Gan
-
Patent number: 11270077Abstract: A computing device receives a natural language input from a user. The computing device routes the natural language input from an active domain node of multiple domain nodes of a multi-domain context-based hierarchy to a leaf node of the domain nodes by selecting a parent domain node in the hierarchy until an off-topic classifier labels the natural language input as in-domain and then selecting a subdomain node in the hierarchy until an in-domain classifier labels the natural language input with a classification label, each of the plurality of domain nodes comprising a respective off-topic classifier and a respective in-domain classifier trained for a respective domain node. The computing device outputs the classification label determined by the leaf node.Type: GrantFiled: May 13, 2019Date of Patent: March 8, 2022Assignee: International Business Machines CorporationInventors: Ming Tan, Ladislav Kunc, Yang Yu, Haoyu Wang, Saloni Potdar
-
Patent number: 11263402Abstract: Techniques facilitating detection of conversation threads in unstructured channels are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an extraction component that employs a model to detect conversation messages based on a defined confidence level and assigns the conversation messages to respective conversation thread categories. The computer executable components also can comprise a model component that trains the model on conversation messages that comprise respective text data, wherein the model is trained to detect the respective text data to the defined confidence level.Type: GrantFiled: May 6, 2019Date of Patent: March 1, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ming Tan, Dakuo Wang, Mo Yu, Chuang Gan, Haoyu Wang, Shiyu Chang
-
Patent number: 11238236Abstract: Systems and methods provide for automated messaging summarization and ranking. The systems and methods may use an integrated machine learning model to perform thread detection, thread summarization, and summarization ranking. The messages may be received from a team chat application, organized, summarized and ranked by the machine learning model, and the results may be returned to the team chat application. In some cases, the ranking may be different for different users of the team chat application.Type: GrantFiled: October 8, 2019Date of Patent: February 1, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Dakuo Wang, Ming Tan, Chuang Gan, Haoyu Wang
-
Patent number: 11216619Abstract: A mechanism is provided to implement a text classifier training augmentation mechanism for incorporating unlabeled data into the generation of a text classifier. For each term of a plurality of terms in each document of a plurality of documents in a set of unlabeled data, a term frequency value is determined. The term is normalized by dividing the term frequency value by a total number of terms in the document. An inverse document frequency (idf) value is determined for each term based on the term frequency value. A subset of terms is filtered from the plurality of terms based the determined idf values. The idf values for the remaining terms are transformed into feature weights. Terms from a set of labeled data are re-weighted based on the feature weights determined from the set of unlabeled data. The text classifier is then generated using the re-weighted labeled data.Type: GrantFiled: April 28, 2020Date of Patent: January 4, 2022Assignee: International Business Machines CorporationInventors: Yang Yu, Haode Qi, Haoyu Wang, Ming Tan, Navneet N. Rao, Saloni Potdar, Robert Leslie Yates
-
Publication number: 20210334468Abstract: A mechanism is provided to implement a text classifier training augmentation mechanism for incorporating unlabeled data into the generation of a text classifier. For each term of a plurality of terms in each document of a plurality of documents in a set of unlabeled data, a term frequency value is determined. The term is normalized by dividing the term frequency value by a total number of terms in the document. An inverse document frequency (idf) value is determined for each term based on the term frequency value. A subset of terms is filtered from the plurality of terms based the determined idf values. The idf values for the remaining terms are transformed into feature weights. Terms from a set of labeled data are re-weighted based on the feature weights determined from the set of unlabeled data. The text classifier is then generated using the re-weighted labeled data.Type: ApplicationFiled: April 28, 2020Publication date: October 28, 2021Inventors: Yang Yu, Haode Qi, Haoyu Wang, Ming Tan, Navneet N. Rao, Saloni Potdar, Robert Leslie Yates
-
Publication number: 20210319182Abstract: A mechanism is provided to implement suggestion of new entity types with discriminative importance analysis. The mechanism obtains a list of predefined intents from a chatbot designer. The mechanism receives an input sentence having a target intent within the list of predefined intents. The mechanism performs intent-specific importance analysis on the input sentence to generate an importance score for each token in the input sentence. The mechanism ranks the tokens in the input sentence by importance score and outputs a token with a highest importance score as a candidate entity type.Type: ApplicationFiled: April 8, 2020Publication date: October 14, 2021Inventors: Haode Qi, Ming Tan, Yang Yu, Navneet N. Rao, Saloni Potdar, Haoyu Wang
-
Publication number: 20210287667Abstract: A mechanism is provided for implementing an intent segmentation mechanism that segments intent boundaries for multi-intent utterances in a conversational agent. For each term of a set of terms in the utterance from a real-time chat session, a set of adversarial utterances is generated for the utterance. An influence of changing each term is determined so as to identify a term importance value. Utilizing the term importance value, one or more of a change in ranking of the intent of the utterance or a change in confidence with regard to the intent of the utterance is identified. An entropy-based segmentation of the utterance into a plurality of candidate partitions is performed. An associated intent and entropy value are then assigned. Based on a segment with minimum entropy, a call associated with the real-time chat session is directed to an operation associated with an intent of the segment with minimum entropy.Type: ApplicationFiled: March 12, 2020Publication date: September 16, 2021Inventors: Ming Tan, Haoyu Wang, Saloni Potdar, Yang Yu, Navneet N. Rao, Haode Qi
-
Patent number: 11120225Abstract: An online version of a sentence representation generation module updated by training a first sentence representation generation module using first labeled data of a first corpus. After training the first sentence representation generation module using the first labeled data, a second corpus of second labeled data is obtained. The second corpus is distinct from the first corpus. A subset of the first labeled data is identified based on similarities between the first corpus and the second corpus. A second sentence representation generation module is trained using the second labeled data of the second corpus and the subset of the first labeled data.Type: GrantFiled: February 5, 2019Date of Patent: September 14, 2021Assignee: International Business Machines CorporationInventors: Ming Tan, Ladislav Kunc, Yang Yu, Haoyu Wang, Saloni Potdar
-
Patent number: 11120072Abstract: A computer transforms high-dimensional data into low-dimensional data. (A) A distance matrix is computed from observation vectors. (B) A kernel matrix is computed from the distance matrix using a bandwidth value. (C) The kernel matrix is decomposed using an eigen decomposition to define eigenvalues. (D) A predefined number of largest eigenvalues are selected from the eigenvalues. (E) The selected largest eigenvalues are summed. (F) A next bandwidth value is computed based on the summed eigenvalues. (A) through (F) are repeated with the next bandwidth value until a stop criterion is satisfied. Each observation vector of the observation vectors is transformed into a second space using a kernel principal component analysis with the next bandwidth value and the kernel matrix. The second space has a dimension defined by the predefined number of first eigenvalues. Each transformed observation vector is output.Type: GrantFiled: February 23, 2021Date of Patent: September 14, 2021Assignee: SAS Institute Inc.Inventors: Kai Shen, Haoyu Wang, Arin Chaudhuri
-
Publication number: 20210266282Abstract: A deep learning module classifies messages received from a plurality of entities into one or more conversation threads. In response to receiving a subsequent message, the deep learning module determines which of the one or more conversation threads and a new conversation thread is contextually a best fit for the subsequent message. The subsequent message is added to the determined conversation thread.Type: ApplicationFiled: May 6, 2021Publication date: August 26, 2021Inventors: Ming Tan, Haoyu Wang, Dakuo Wang, Chuang Gan
-
Publication number: 20210221613Abstract: A management method applied to the goods-to-person system includes: in response to a task of putting products on shelves, calculating popularity of a product to be put on shelf according to historical sales order data of the product to be put on shelf, and matching the popularity of the product to be put on shelf with popularity of a shelf to determine a shelf area; selecting a goods location with space randomly in the determined shelf area, wherein the goods location is used for storing the product to be put on shelf; and controlling a mobile robot to transport a shelf where the goods location is located to a work station.Type: ApplicationFiled: May 30, 2019Publication date: July 22, 2021Applicant: BEIJING GEEKPLUS TECHNOLOGY CO., LTD.Inventors: Kai LIU, Haoyu WANG, Xun WU, Kai SUN
-
Patent number: 11057330Abstract: A deep learning module classifies messages received from a plurality of entities into one or more conversation threads. In response to receiving a subsequent message, the deep learning module determines which of the one or more conversation threads and a new conversation thread is contextually a best fit for the subsequent message. The subsequent message is added to the determined conversation thread.Type: GrantFiled: August 26, 2019Date of Patent: July 6, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Ming Tan, Haoyu Wang, Dakuo Wang, Chuang Gan
-
Patent number: 11023683Abstract: A computer-implemented method includes obtaining a training data set including text data indicating one or more phrases or sentences. The computer-implemented method includes training a classifier using supervised machine learning based on the training data set and additional text data indicating one or more out-of-domain phrases or sentences. The computer-implemented method includes training an autoencoder using unsupervised machine learning based on the training data. The computer-implemented method further includes combining the classifier and the autoencoder to generate the out-of-domain sentence detector configured to generate an output indicating a classification of whether input text data corresponds to an out-of-domain sentence. The output is based on a combination of a first output of the classifier and a second output of the autoencoder.Type: GrantFiled: March 6, 2019Date of Patent: June 1, 2021Assignee: International Business Machines CorporationInventors: Inkit Padhi, Ruijian Wang, Haoyu Wang, Saloni Potdar