专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11657629B2 Content extraction based on graph modeling 有权
公开(公告)号：US11657629B2
公开(公告)日：2023-05-23
申请号：US17077211
申请日：2020-10-22
申请人： PAYPAL, INC.
发明人： Xiaodong Yu , Hewen Wang
IPC分类号： G06K9/20 , G06K9/46 , G06K9/62 , G06Q10/08 , G06Q20/40 , G06F16/901 , G06N3/04 , G06V10/22 , G06Q10/0833 , G06Q10/083 , G06V10/44 , G06V10/46 , G06V30/10
CPC分类号： G06V10/22 , G06F16/9024 , G06K9/6256 , G06N3/04 , G06Q10/0833 , G06Q10/0838 , G06Q20/407 , G06V10/457 , G06V10/464 , G06V30/10
摘要： Methods and systems are presented for extracting categorizable information from an image using a graph that models data within the image. Upon receiving an image, a data extraction system identifies characters in the image. The data extraction system then generates bounding boxes that enclose adjacent characters that are related to each other in the image. The data extraction system also creates connections between the bounding boxes based on locations of the bounding boxes. A graph is generated based on the bounding boxes and the connections such that the graph can accurately represent the data in the image. The graph is provided to a graph neural network that is configured to analyze the graph and produce an output. The data extraction system may categorize the data in the image based on the output.

2. 发明授权

US11741139B2 Systems and methods for determining a response to a user query 有权
公开(公告)号：US11741139B2
公开(公告)日：2023-08-29
申请号：US17317805
申请日：2021-05-11
申请人： PayPal, Inc.
发明人： Yuzhen Zhuo , Sandro Cavallari , Van Hoang Nguyen , Kim Dung Bui , Rey Neo , Harsha Singalreddy , Lei Xu , Hewen Wang , Quan Jin Ferdinand Tang , Chun Kiat Ho
IPC分类号： G06F16/332 , G06F16/33 , G06N20/00 , H04L51/02
CPC分类号： G06F16/3322 , G06F16/3334 , G06F16/3338 , G06N20/00 , H04L51/02
摘要： Systems and methods are presented for providing a response to a user query. Reception of a user query is detected. An augmentation machine learning model is utilized to determine one or more variations of the user query that correspond to a semantic meaning of the user query. A plurality of response candidates is determined that correspond to the user query by comparing the user query and the one or more variations of the user query to a plurality of documents. A final response candidate is determined from the plurality of response candidates based on utilizing a semantic machine learning model to perform a semantic comparison between the plurality of response candidates and at least the user query.

3. 发明申请

US20220358289A1 USER-AGENT ANOMALY DETECTION USING SENTENCE EMBEDDING 有权
公开(公告)号：US20220358289A1
公开(公告)日：2022-11-10
申请号：US17308931
申请日：2021-05-05
申请人： PayPal, Inc.
发明人： Zhe Chen , Hewen Wang , Yuzhen Zhuo , Solomon kok how Teo , Shanshan Peng , Quan Jin Ferdinand Tang , Serafin Trujillo , Kenneth Bradley Snyder , Mandar Ganaba Gaonkar , Omkumar Mahalingam
IPC分类号： G06F40/284 , G06F40/30 , G06K9/62
摘要： Systems and methods for user-agent anomaly detection are disclosed. In one embodiment, a user-agent string may be embedded into a numerical data vector representation using a sentence embedding algorithm (e.g., FastText). A predictive score may be calculated based on the numerical data vector representation and using a probability distribution function model that models a likelihood of occurrence of the observed user-agent based on patterns learned from historic payload data (e.g., a Gaussian Mixture Model). The predictive score may be compared to a threshold and, based on the comparison, it may be determined whether the user-agent is fraudulent.

4. 发明申请

US20220129688A1 CONTENT EXTRACTION BASED ON GRAPH MODELING 有权
公开(公告)号：US20220129688A1
公开(公告)日：2022-04-28
申请号：US17077211
申请日：2020-10-22
申请人： PAYPAL, INC.
发明人： Xiaodong Yu , Hewen Wang
IPC分类号： G06K9/20 , G06K9/46 , G06K9/62 , G06Q10/08 , G06Q20/40 , G06F16/901 , G06N3/04
摘要： Methods and systems are presented for extracting categorizable information from an image using a graph that models data within the image. Upon receiving an image, a data extraction system identifies characters in the image. The data extraction system then generates bounding boxes that enclose adjacent characters that are related to each other in the image. The data extraction system also creates connections between the bounding boxes based on locations of the bounding boxes. A graph is generated based on the bounding boxes and the connections such that the graph can accurately represent the data in the image. The graph is provided to a graph neural network that is configured to analyze the graph and produce an output. The data extraction system may categorize the data in the image based on the output.

5. 发明授权

US11907658B2 User-agent anomaly detection using sentence embedding 有权
公开(公告)号：US11907658B2
公开(公告)日：2024-02-20
申请号：US17308931
申请日：2021-05-05
申请人： PayPal, Inc.
发明人： Zhe Chen , Hewen Wang , Yuzhen Zhuo , Solomon kok how Teo , Shanshan Peng , Quan Jin Ferdinand Tang , Serafin Trujillo , Kenneth Bradley Snyder , Mandar Ganaba Gaonkar , Omkumar Mahalingam
IPC分类号： G06F40/279 , G06F21/55 , G06F21/56 , G06F40/284 , G06F40/30 , G06F18/2321 , G06F18/2415
CPC分类号： G06F40/284 , G06F18/2321 , G06F18/2415 , G06F40/30
摘要： Systems and methods for user-agent anomaly detection are disclosed. In one embodiment, a user-agent string may be embedded into a numerical data vector representation using a sentence embedding algorithm (e.g., FastText). A predictive score may be calculated based on the numerical data vector representation and using a probability distribution function model that models a likelihood of occurrence of the observed user-agent based on patterns learned from historic payload data (e.g., a Gaussian Mixture Model). The predictive score may be compared to a threshold and, based on the comparison, it may be determined whether the user-agent is fraudulent.

6. 发明公开

US20230260302A1 CONTENT EXTRACTION BASED ON GRAPH MODELING 审中-公开
公开(公告)号：US20230260302A1
公开(公告)日：2023-08-17
申请号：US18300131
申请日：2023-04-13
申请人： PAYPAL, INC.
发明人： Xiaodong Yu , Hewen Wang
IPC分类号： G06V30/18 , G06Q20/40 , G06Q10/0833 , G06F16/901 , G06N3/04 , G06Q10/083 , G06V10/44 , G06V10/46 , G06F18/214 , G06V30/14
CPC分类号： G06V30/18181 , G06Q20/407 , G06Q10/0833 , G06F16/9024 , G06N3/04 , G06Q10/0838 , G06V10/457 , G06V10/464 , G06F18/214 , G06V30/1444
摘要： Methods and systems are presented for extracting categorizable information from an image using a graph that models data within the image. Upon receiving an image, a data extraction system identifies characters in the image. The data extraction system then generates bounding boxes that enclose adjacent characters that are related to each other in the image. The data extraction system also creates connections between the bounding boxes based on locations of the bounding boxes. A graph is generated based on the bounding boxes and the connections such that the graph can accurately represent the data in the image. The graph is provided to a graph neural network that is configured to analyze the graph and produce an output. The data extraction system may categorize the data in the image based on the output.

7. 发明公开

US20230186668A1 POLAR RELATIVE DISTANCE TRANSFORMER 审中-公开
公开(公告)号：US20230186668A1
公开(公告)日：2023-06-15
申请号：US17547680
申请日：2021-12-10
申请人： PayPal, Inc.
发明人： Yanfei Dong , Yuan Deng , Hewen Wang , Xiaodong Yu
IPC分类号： G06V30/414 , G06V30/148 , G06F40/106 , G06F40/114
CPC分类号： G06V30/414 , G06F40/106 , G06F40/114 , G06V30/153
摘要： A system can comprise a processor that can facilitate performance of operations, comprising accessing a document comprising a plurality of text bounding boxes, wherein each respective text bounding box of the plurality of text bounding boxes comprises respective text, for each respective text bounding box, determining respective text bounding box coordinates and respective text bounding box input embeddings, based on the respective text bounding box coordinates, determining respective text bounding box positional encodings for each respective text bounding box, based on a transformer-based deep learning model applied to the respective text bounding box input embeddings, respective text bounding box coordinates, respective text bounding box positional encodings, and bias information representative of a modification to an attention weight of the transformer-based deep learning model, determining respective output embeddings for each respective text bounding box, and based on the respective output embeddings, generating respective bounding box labels for each respective bounding box.

8. 发明授权

US11907954B2 Transaction anomaly detection 有权
公开(公告)号：US11907954B2
公开(公告)日：2024-02-20
申请号：US17240247
申请日：2021-04-26
申请人： PayPal, Inc.
发明人： Hewen Wang
IPC分类号： G06Q20/40 , G06N20/00 , H04L9/40
CPC分类号： G06Q20/4016 , G06N20/00
摘要： Techniques are disclosed in which a computer system generates a transaction network graph from an initial set of transactions including known labels and attributes. The computer system may generate first and second matrices using first and second graph embedding routines from a training set of transactions that includes a first subset of transactions in the network graph. The first routine is based on anomalies in related transactions occurring at nodes in the transaction network graph that are multiple hops away while the second routine is based on anomalies in neighborhoods of similar transactions. In some embodiments, the computer system generates a final embedded matrix from the first and second matrices and uses the final matrix and a testing set of transactions that includes a second subset of transactions in the graph to train a machine learning model, where the trained model usable to determine whether unlabeled transactions are anomalous.

9. 发明授权

US11695763B2 System and method for fingerprinting a device based on sensor data 有权
公开(公告)号：US11695763B2
公开(公告)日：2023-07-04
申请号：US17018924
申请日：2020-09-11
申请人： PayPal, Inc.
发明人： Zhe Chen , Hewen Wang
IPC分类号： H04L9/40 , G06N3/08
CPC分类号： H04L63/0876 , G06N3/08
摘要： Methods and systems are presented for generating a device fingerprint based on data obtained from one or more sensors on a device. A plurality of data points corresponding to sensor readings are obtained from the one or more sensors on the device. A set of time-domain features and a set of frequency-domain features are extracted from the plurality of data points and inputted to a neural network trained using a triplet network. A device fingerprint that may be used to identify the device is obtained from the neural network.

10. 发明申请

US20220343329A1 Transaction Anomaly Detection 有权
公开(公告)号：US20220343329A1
公开(公告)日：2022-10-27
申请号：US17240247
申请日：2021-04-26
申请人： PayPal, Inc.
发明人： Hewen Wang
IPC分类号： G06Q20/40 , G06N20/00
摘要： Techniques are disclosed in which a computer system generates a transaction network graph from an initial set of transactions including known labels and attributes. The computer system may generate first and second matrices using first and second graph embedding routines from a training set of transactions that includes a first subset of transactions in the network graph. The first routine is based on anomalies in related transactions occurring at nodes in the transaction network graph that are multiple hops away while the second routine is based on anomalies in neighborhoods of similar transactions. In some embodiments, the computer system generates a final embedded matrix from the first and second matrices and uses the final matrix and a testing set of transactions that includes a second subset of transactions in the graph to train a machine learning model, where the trained model usable to determine whether unlabeled transactions are anomalous.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式