-
1.发明公开公开(公告)号：US20240185270A1
公开(公告)日：2024-06-06
申请号：US17972167
申请日：2022-10-24
Applicant: International Business Machines Corporation
Inventor： YADA ZHU , Zixuan Yuan , David Cox , Anna Wanda Topol
IPC: G06Q30/02 , G06F40/126 , G06F40/166 , G06F40/30
CPC classification number: G06Q30/0202 , G06F40/126 , G06F40/166 , G06F40/30
Abstract: Unsupervised cross-domain data augmentation techniques for long-text document based prediction and explanation are provided. In one aspect, a system for long-document based prediction includes: an encoder for creating embeddings of long-document texts with hierarchical sparse self-attention, and making predictions using the embeddings of the long-document texts; and a multi-source counterfactual augmentation module for generating perturbed long-document texts using unlabeled sentences from at least one external source to train the encoder. A method for long-document based prediction is also provided.
-
公开(公告)号：US20230070625A1
公开(公告)日：2023-03-09
申请号：US17404708
申请日：2021-08-17
Applicant: International Business Machines Corporation
Inventor： Nitin Gaur , YADA ZHU , Toyotaro Suzumura , Sachiko Yoshihama
Abstract: An example operation may include one or more of identifying a digital token issued via a blockchain, determining an asset that is linked to the digital token, a current custodian of the asset that is linked to the digital token, and a risk value associated with the asset based on attributes of the asset, generating a graph that comprises a path between a user that owns the digital token and the current custodian of the asset, embedding the graph within a field of a template and embedding the risk value within a second field of the template to generate a filled-in template, and displaying the filled-in template within a user interface.
-
公开(公告)号：US20240404106A1
公开(公告)日：2024-12-05
申请号：US18327608
申请日：2023-06-01
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Bo Wu , Chuang Gan , YADA ZHU , Pin-Yu Chen
Abstract: Provided are a computer program product, system, and method for training a pose estimation model to determine anatomy keypoints in images. A teacher network, implementing machine learning, processes images representing anatomies to produce heatmaps representing keypoints of the anatomies. An anatomy parsing network, implementing machine learning, processes the images to produce segmentation representations labeling anatomies represented in the images. The segmentation representations from the anatomy parsing network and the heatmaps from the teacher network are concatenated to produce mixed heatmaps. A pose estimation model, implementing machine learning, is trained to process the images to output predicted heatmaps to minimize a loss function of the output predicted heatmaps from the pose estimation model and the mixed heatmaps.
-
公开(公告)号：US20180204171A1
公开(公告)日：2018-07-19
申请号：US15836814
申请日：2017-12-08
Applicant: International Business Machines Corporation
Inventor： Lei Cao , Ajay Ashok Deshpande , ALI KOC , Yingjie Li , Xuan Liu , Brian Leo Quanz , YADA ZHU
IPC: G06Q10/08
CPC classification number: G06Q10/087
Abstract: Techniques for facilitating estimation of node processing capacity values for order fulfillment are provided. In one example, a computer-implemented method can comprise: generating, by a system operatively coupled to a processor, a current processing capacity value for an entity; and determining, by the system, a future processing capacity value for the entity based on the current processing capacity value and by using a future capacity model that has been explicitly trained to infer respective processing capacity values for the entity. The computer-implemented method can also comprise fulfilling an order of an item, by the system, based on the future processing capacity value.
-
Patent Agency Ranking
公开(公告)号：US20240160904A1
公开(公告)日：2024-05-16
申请号：US17979817
申请日：2022-11-03
Applicant: International Business Machines Corporation
Inventor： YADA ZHU , Mattson Thieme , ONKAR BHARDWAJ , David Cox
CPC classification number: G06N3/0481 , B60W60/00276 , G06N5/04 , G06Q20/4016
Abstract: A graph with a plurality of nodes, a plurality of edges, and a plurality of node features is obtained and node representations for the node features are generated. A plurality of structure learning scores is generated based on the node representations, each structure learning score corresponding to one of the plurality of edges. A subset of the plurality of edges that identify a subgraph is selected, each edge of the subset having a structure learning score that is greater than a given threshold. The subgraph is inputted to a representation learner and an inferencing operation is performed using the representation learner based on the subgraph.
-
公开(公告)号：US20180204169A1
公开(公告)日：2018-07-19
申请号：US15407736
申请日：2017-01-17
Applicant: International Business Machines Corporation
Inventor： Lei Cao , Ajay Ashok Deshpande , ALI KOC , Yingjie Li , Xuan Liu , Brian Leo Quanz , YADA ZHU
IPC: G06Q10/08
CPC classification number: G06Q10/087
Abstract: Techniques for facilitating estimation of node processing capacity values for order fulfillment are provided. In one example, a computer-implemented method can comprise: generating, by a system operatively coupled to a processor, a current processing capacity value for an entity; and determining, by the system, a future processing capacity value for the entity based on the current processing capacity value and by using a future capacity model that has been explicitly trained to infer respective processing capacity values for the entity. The computer-implemented method can also comprise fulfilling an order of an item, by the system, based on the future processing capacity value.
-
公开(公告)号：US20230085691A1
公开(公告)日：2023-03-23
申请号：US17483716
申请日：2021-09-23
Applicant: International Business Machines Corporation
Inventor： Nitin Gaur , Petr Novotny , Yacov Manevich , Artem Barger , YADA ZHU
Abstract: An example operation may include one or more of receiving, via a custodial service, a request to transact with a digital asset owned by a user and temporarily in custody of the custodial service, generating a blockchain transaction comprising an identifier of the digital asset on a blockchain ledger, an identifier of the custodial service, and an identifier of a recipient of the digital asset, signing the blockchain transaction with a key from a trifocal key which proves that the custodial service is authorized to transact with the digital asset on behalf of the user, and storing the signed blockchain transaction on a blockchain ledger.
-
公开(公告)号：US20220383096A1
公开(公告)日：2022-12-01
申请号：US17334897
申请日：2021-05-31
Applicant: International Business Machines Corporation
Inventor： YADA ZHU , WEI ZHANG , XIAODONG CUI , GUANGNAN YE
Abstract: Sample-based model explanation techniques are provided using arbitrary spans of training data at any granularity as an explanation with increased interpretability. In one aspect, a method for explaining a machine learning model {circumflex over (θ)} includes: training the machine learning model {circumflex over (θ)} with training data D; obtaining a decision of the machine learning model {circumflex over (θ)}; masking one or more datapoints in the training data D; determining whether a new decision of the machine learning model {circumflex over (θ)} obtained after the masking is same as the decision of the machine learning model {circumflex over (θ)} obtained prior to the masking; and using the masking to explain which of the one or more datapoints in the training data D are significant. Namely, the one or more datapoints in the training data D that, when masked, change the decision of the machine learning model {circumflex over (θ)} are significant.
-
公开(公告)号：US20210312388A1
公开(公告)日：2021-10-07
申请号：US16839197
申请日：2020-04-03
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： YINGJIE LI , AJAY ASHOK DESHPANDE , ALI KOC , HERBERT MCFADDIN , CHRISTOPHER SCOTT MILITE , JAE-EUN PARK , BRIAN QUANZ , YADA ZHU
Abstract: Aspects of the invention include obtaining product hierarchy information for an early lifecycle product offered for sale by a retailer and obtaining order data for each order of the early lifecycle product during an early lifecycle period. The aspects also include obtaining customer data for a customer associated with each order of the early lifecycle product during the early lifecycle period and determining an expected return rate for the early lifecycle product based by inputting the product hierarchy information, the order data and the customer data into a trained return prediction model. Aspects also include performing an action based on a stored profile of the retailer based on a determination that the expected return rate exceeds a threshold value.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.016 seconds)
