专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20220414529A1 Federated Machine Learning Management 有权
公开(公告)号：US20220414529A1
公开(公告)日：2022-12-29
申请号：US17357626
申请日：2021-06-24
申请人： PayPal, Inc.
发明人： Abhishek Chhibber , Darshankumar Bhadrasinh Desai , Michael Charles Todasco , Vidyut Mukund Naware , Nitin S. Sharma
IPC分类号： G06N20/00 , G06F16/23
摘要： Techniques are disclosed in which a computer system receives, from a plurality of user computing devices, a plurality of device-trained models and obfuscated sets of user data stored at the plurality of user computing devices, where the device-trained models are trained at respective ones of the plurality of user computing devices using respective sets of user data prior to obfuscation. In some embodiments, the server computer system determines similarity scores for the plurality of device-trained models, wherein the similarity scores are determined based on a performance of the device-trained models. In some embodiments, the server computer system identifies, based on the similarity scores, at least one of the plurality of device-trained models as a low-performance model. In some embodiments, the server computer system transmits, to the user computing device corresponding to the low-performance model, an updated model.

42. 发明申请

US20220414447A1 IMPLICIT CURRICULUM LEARNING 有权
公开(公告)号：US20220414447A1
公开(公告)日：2022-12-29
申请号：US17356808
申请日：2021-06-24
申请人： PayPal, Inc.
发明人： Roi Spoliansky
IPC分类号： G06N3/08 , G06K9/62
摘要： Systems and techniques for facilitating implicit curriculum learning are provided. These allow for improved machine learning systems that can automatically execute curriculum learning without drawbacks such as pre-sorting data into different epochs which may have varying degrees of difficulty (e.g. easiest first, then harder epochs). Applicant's techniques can be executed more efficiently by automatically iterating over a data set, which need not be manually separated into different epochs. Thus, a system can access a neural network and a set of labeled data candidates. In various aspects, the system can perform a plurality of training epochs on the neural network based on the set of labeled data candidates. In various instances, the system can iteratively update the set of labeled data candidates as the plurality of training epochs are performed, by removing, after each training epoch, a dropout percentage of those labeled data candidates which the neural network correctly classified during the training epoch.

43. 发明申请

US20220413953A1 Updating Counters Distributed Across a Plurality of Nodes 有权
公开(公告)号：US20220413953A1
公开(公告)日：2022-12-29
申请号：US17356244
申请日：2021-06-23
申请人： PayPal, Inc.
发明人： Eric Leu
IPC分类号： G06F11/07 , G06F11/18
摘要： Techniques are disclosed relating to methods that include initializing, by a computer in a computer system, an event counter that includes a plurality of sub-counter groups, each plurality of sub-counter groups including at least two sub-counters located on different nodes of a plurality of nodes in the computer system. In response to an occurrence of an event associated with the event counter, the method may include the computer selecting a particular sub-counter group of the plurality of sub-counter groups to update, and sending, to sub-counters corresponding to the particular sub-counter group, a request to update a sub-counter value for the particular sub-counter group. In response to a request for a current count value of the event counter, the method may include outputting, by the computer, a sum of the sub-counter values for the plurality of sub-counter groups as the current count value.

44. 发明授权

US11538033B2 Dispute resolution cryptocurrency sidechain system 有权
公开(公告)号：US11538033B2
公开(公告)日：2022-12-27
申请号：US17035070
申请日：2020-09-28
申请人： PayPal, Inc.
发明人： Frank Anthony Nuzzi
IPC分类号： G06Q20/38 , G06Q20/06 , G06Q20/36
摘要： A dispute resolution cryptocurrency sidechain system includes a system provider that determines that a transaction amount for a transaction has been received at a first public ledger address on a public ledger from a second public ledger address and, in response, allocates a sidechain address on a dispute resolution sidechain ledger. The system provider then sends, through a network to a payer and a payee involved in the transaction, the sidechain address, and monitors the sidechain address for dispute communications. Based on detecting a first dispute communication that is received at the sidechain address and that is signed using a private key that identifies the payer, the system provider device causes a portion of the transaction amount that was received at the first public ledger address to be sent to the second public ledger address.

45. 发明授权

US11537736B2 System for detecting anomalous access to tables 有权
公开(公告)号：US11537736B2
公开(公告)日：2022-12-27
申请号：US16563877
申请日：2019-09-08
申请人： PayPal, Inc.
发明人： Liron Florens Ben Kimon , Yotam Perkal , Yuri Shafet
IPC分类号： G06F21/62 , G06F16/9035 , G06K9/62 , G06F17/18
摘要： A system and method for detecting anomalous access to tables is described. A query for accessing a table from a requesting user is received. A set of users similar to the requesting user is determined. The probability that the requesting user should access the table is calculated. Whether the user should be accessing the table based on the calculated probability is determined.

46. 发明申请

US20220405796A1 COMPUTATIONAL PLATFORM USING MACHINE LEARNING FOR INTEGRATING DATA SHARING PLATFORMS 有权
公开(公告)号：US20220405796A1
公开(公告)日：2022-12-22
申请号：US17897981
申请日：2022-08-29
申请人： PAYPAL, INC.
发明人： Nishanthi Yuvaraj
IPC分类号： G06Q30/02 , G06F9/54
摘要： There are provided systems and methods for a computational platform using machine learning for integration data sharing platforms. A user may engage in a transaction with another user, such as a purchase of goods, services, or other items from a merchant. A service provider may provide a data feed to the user via integrated computational platforms that allows the user to post data including information regarding the processed transaction. The post may include a share code that links back to the user and their corresponding transaction. Thereafter, the post may be viewed by other users and the share code may be used by the other users in order to perform similar transaction processing, where these later transactions are linked back to the original user. Tracking of these later transactions may be done through application extensions that allow the computational platforms to track user data over different online interactions.

47. 发明授权

US11533287B2 Mid-tier messaging system 有权
公开(公告)号：US11533287B2
公开(公告)日：2022-12-20
申请号：US17165871
申请日：2021-02-02
申请人： PAYPAL, INC.
发明人： Rahul Nair , Swati Baradia , Liang Xi , Ramakrishna Rosanuru , Billy Henry Runyan , Linu Varghese , Koteswara Pathuri
IPC分类号： G06F15/16 , H04L51/56 , H04L67/148 , H04L9/40 , H04W12/06 , G06F40/30 , H04L51/02
摘要： A mid-tier messaging system receives a request to initiate a communication session via a first messaging channel that includes a first messaging interface of a first messaging application provided at a user device and a first message provider of a plurality of message providers. The mid-tier messaging system establishes a first session that is mapped to the communication session. The mid-tier messaging system establishes the communication, using the first session, between the first messaging interface and the first message provider. The mid-tier messaging system provides, through the first session, first message communications between the first message provider and the first messaging interface. The mid-tier messaging system seamlessly switches to a second message provider service when the first message provider service cannot service an intent of the first communication session.

48. 发明申请

US20220400117A1 UNIFIED IDENTITY VERIFICATION 有权
公开(公告)号：US20220400117A1
公开(公告)日：2022-12-15
申请号：US17827901
申请日：2022-05-30
申请人： PayPal, Inc.
发明人： Rene M. Pelegero , Girish Balasubramanian , Rohan Mahadevan
IPC分类号： H04L9/40 , G06Q20/40 , G06Q20/10 , G06Q20/38 , G06F21/31 , H04L67/306
摘要： Apparatus, systems, and methods are disclosed that operate to receiving an authentication request at a server associated with an authenticating entity from a requesting party responsive to a request being provided to the requesting party by a client terminal associated with an unauthenticated individual purporting to be an individual account owner previously authenticated with the authenticating entity. A token, from the client terminal associated with the unauthenticated individual is received, and the token includes information associated with the unauthenticated individual and a user permission authorizing the authenticating entity to share a selected portion of the information with a plurality of selected requesting parties. The server associated with the authenticating entity authenticates the unauthenticated individual as the individual account owner based on, inter alia, matching the token to a pre-registered identity uniquely associated with the individual account owner. Additional apparatus, systems, and methods are disclosed.

49. 发明申请

US20220398843A1 TAGGING OBJECTS IN AUGMENTED REALITY TO TRACK OBJECT DATA 有权
公开(公告)号：US20220398843A1
公开(公告)日：2022-12-15
申请号：US17861486
申请日：2022-07-11
申请人： PayPal, Inc.
发明人： Yona Ju , Fun-Chen Jou
IPC分类号： G06V20/20 , G06K9/62 , G06Q30/06 , G06T11/00
摘要： There are provided systems and methods for tagging objects in augmented reality to track object data. A user may capture visual data utilizing a device at a location, where the visual data includes one or more objects that the user may wish to associate with a purchase or sell offer. A device may perform object recognition to identify the object and an identifying characteristic of the object. A service provider may then receive offer details and may generate a graphical object or other virtual data that can be displayed with the object in an augmented reality experience. Later, when the object is identified in another augmented reality experience on a different device, the virtual graphic may be displayed, which may show the offer for the object. Further, the augmented reality may be used to process a transaction for the object and track the object.

50. 发明申请

US20220398498A1 SHARED PREDICTION ENGINE FOR MACHINE LEARNING MODEL DEPLOYMENT 有权
公开(公告)号：US20220398498A1
公开(公告)日：2022-12-15
申请号：US17827241
申请日：2022-05-27
申请人： PayPal, Inc.
发明人： Sriharsha Vogeti , Anupam Tarsauliya , Ayaz Ahmad , Ravi Shanker Sandepudi
IPC分类号： G06N20/00 , G06F3/0482
摘要： There are provided systems and methods for a shared prediction engine for machine learning model deployment. A service provider may provide AI hosting platforms that allow for clients, customers, and other end users to upload AI models for execution, such as machine learning models. A user may utilize one or more user interfaces provided to a client device by the service provider to select machine learning models to perform predictive services based on input features provided in an input string. Thereafter, a machine learning engine may host and execute the models during an instance of the engine provided to the client device. The engine may then process the input features in a processing thread remotely from the client device during the instance so that machine learning predictions may be determined. Thereafter, an output string for the predictions and model explanations may be provided to the client device.

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