-
公开(公告)号：US12299589B2
公开(公告)日：2025-05-13
申请号：US17363249
申请日：2021-06-30
Applicant: International Business Machines Corporation
Inventor： Lijun Mei , Qi Cheng Li , Xue Han , Xin Zhou , Zi Ming Huang , Ya Bin Dang
IPC: G06N5/022 , G06F16/3329 , G06F16/9032 , G06F40/30 , G06N20/00
Abstract: New question and answer (QA) pairs can be automatically discovered from a corpus of data such as online chats and conversations. Newly discovered QA pairs can augment QA database, which can be used by a computer processor or device, e.g., by a chatbot, an automated machine, and/or another. Existing QA knowledge can be used to learn the structures of QA knowledge distribution in conversations, and new QA knowledge can be automatically learned through the structure of learned QA knowledge distribution in conversations. The structure of learned QA knowledge distribution can be refined by adding more semantics based on labeled data.
-
公开(公告)号：US11423235B2
公开(公告)日：2022-08-23
申请号：US16678563
申请日：2019-11-08
Applicant: International Business Machines Corporation
Inventor： Zi Ming Huang , Jie Ma , Christopher Jonathan Davis , Rachel Mohammed , Zhuoxuan Jiang , Qi Cheng Li , Xin Ni
Abstract: In embodiments, a reusable and adaptive multi-task orchestration dialogue system orchestrates a set of single-task dialogue systems to provide multi-scenario dialogue processing. In embodiments, for each question propounded by a user, using a deep learning predictive model, a best single-task dialogue system is chosen out of the set. In embodiments, multi-task orchestration is done without the need to change, or even understand, the inner workings or mechanisms of the individual single-task dialogue systems in the set. Moreover, the multi-task orchestration is also unconcerned with what rules are set in each individual single-task dialogue system. In embodiments, prior to selection of the best single-task dialogue system to return the best answer, new intents and entities are discovered and used to update an existing dialogue path. In embodiments, additional data is continually collected, and used to retrain model so as to further improve performance.
-
公开(公告)号：US11295213B2
公开(公告)日：2022-04-05
申请号：US16242516
申请日：2019-01-08
Applicant: International Business Machines Corporation
Inventor： Li Jun Mei , Qi Cheng Li , Xin Zhou , Ya Bin Dang , Shao Chun Li
Abstract: Embodiments of the present invention relate to computer-implemented methods, systems, and computer program products for managing a conversational system. In one embodiment, a computer-implemented method comprises: obtaining, by a device operatively coupled to one or more processors, a first message sequence comprising messages involved in a conversation between a user and a conversation server; obtaining, by the device, a conversation graph indicating an association relationship between messages involved in a conversation; and in response to determining that the first message sequence is not matched in the conversation graph, updating, by the device, the conversation graph with a second message sequence, the second message sequence being generated based on a knowledge library including expert knowledge that is associated with a topic of the conversation.
-
公开(公告)号：US20210383497A1
公开(公告)日：2021-12-09
申请号：US16894343
申请日：2020-06-05
Inventor： Ao Liu , Sijia Liu , Abhishek Bhandwaldar , Chuang Gan , Lirong Xia , Qi Cheng Li
Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.
-
公开(公告)号：US11159375B2
公开(公告)日：2021-10-26
申请号：US16430518
申请日：2019-06-04
Applicant: International Business Machines Corporation
Inventor： Lian Xue Hu , Qi Cheng Li , Soumitra Sarkar , Lijun Mei
Abstract: A method, computer program product, and system for upgrading an IT system are provided. The method comprises: determining a plurality of existing components of the IT system; determining at least one user component based on a user requirement; building a structural topology of the IT system in accordance with the plurality of existing components and the at least one user component, the structural topology comprising the plurality of existing components, at least one connection among the plurality of existing components, and the at least one user component with its conditional connection, the conditional connection comprising the dependency of the at least one user component; and providing at least one upgrade recommendation for the IT system in accordance with the structural topology.
-
Patent Agency Ranking
公开(公告)号：US10692486B2
公开(公告)日：2020-06-23
申请号：US16046301
申请日：2018-07-26
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Qi Cheng Li , David Nahamoo , Shao Chun Li , Li Jun Mei , Ya Bin Dang , Jie Ma , Xin Zhou , Jian Wang , Hao Chen , Yi Peng Yu
Abstract: A computer-implemented method, computer program product, and computer processing system are provided for generating inferences from a forest of predefined problem determination trees using a processor-based conversation platform. The method includes selecting a tree from among the forest of predefined problem determination trees, responsive to user utterances uttered during an inference generating session. The method further includes navigating the tree to allocate a relevant tree node to generate a problem diagnosis question or a problem resolution action by understanding the user utterances among common interaction patterns in problem diagnosis and problem resolution dialogs. The method also includes providing speech for uttering the problem diagnosis question or the problem resolution action to a user.
-
公开(公告)号：US20200156438A1
公开(公告)日：2020-05-21
申请号：US16742501
申请日：2020-01-14
Applicant: International Business Machines Corporation
Inventor： Hao Chen , Shao Chun Li , Qi Cheng Li , Jie Ma , Li Jun Mei , Jian Wang , Xin Zhou
Abstract: A vehicle occupant comfort system, comprises a processor that stores computer executable components stored in memory. A plurality of sensors sense ambient conditions associated with exterior and interior conditions of a vehicle. A context component infers or determines context of an occupant of the vehicle. A comfort model component implicitly and explicitly trained on occupant comfort related data analyzes information from the plurality of sensors and context component. A comfort controller adjusts environmental conditions of a passenger compartment of the vehicle based at least in part on output of the comfort model component.
-
公开(公告)号：US10529001B2
公开(公告)日：2020-01-07
申请号：US15652620
申请日：2017-07-18
Applicant: International Business Machines Corporation
Inventor： Xin Zhou , Li Jun Mei , Qi Cheng Li , Yan Gao
Abstract: In an approach for eliciting user demands for item recommendation, one or more computer processors retrieve one or more items based on a user demand. The one or more computer processors update the one or more items based on the user demand. The one or more computer processors extract the one or more representative words corresponding to the one or more items. The one or more computer processors build a candidate item list based on the one or more representative words. The one or more computer processors generate one or more eliciting questions to help a user select an item based on the candidate item list.
-
公开(公告)号：US10482227B2
公开(公告)日：2019-11-19
申请号：US15472072
申请日：2017-03-28
Applicant: International Business Machines Corporation
Inventor： Hao Chen , Ya Bin Dang , Qi Cheng Li , Shao Chun Li , Jie Ma , Lijun Mei , Jian Wang , Yipeng Yu , Xin Zhou
IPC: G06F21/32 , G06F3/01 , H04L29/06 , A61B5/0484 , A61B5/117
Abstract: An authentication method, system, and computer program product for decoding brain activity into a brain pattern sequence, applying brain dialog to interact with a user while the user is entering the brain pattern sequence, and matching the brain pattern sequence with a predetermined password to allow access to a system.
-
公开(公告)号：US20190114513A1
公开(公告)日：2019-04-18
申请号：US15782876
申请日：2017-10-13
Applicant: International Business Machines Corporation
Inventor： Li Jun Mei , Qi Cheng Li , Jian Wang , Yi Peng Yu , Xin Zhou
Abstract: In an approach for improving the identification of textual resources that contain unrelated and imprecise contents to improve a user's understanding of a conversational system, one or more computer processors extracts a domain keyword from a domain model and retrieves a distributed representation associated with the domain keyword. The one or more computer processors generates a cluster resource based on the distributed representation and creates a resource vector associated with the cluster resource by calculating the resource vector. The one or more computer processors applies the resource vector to a conversational system and simulates a runtime user interaction based on reinforcement learning of the resource vector to further label and refine resource vector. The one or more computer processors outputs a labeled and refined resource vector to aid in understanding of the conversational system.
-
-
-
-
-
-
-
-
-
Search Results
109
records
(took 0.024 seconds)
