公开(公告)号：US12224921B2

公开(公告)日：2025-02-11

申请号：US18429022

申请日：2024-01-31

Applicant: Cisco Technology, Inc.

Inventor： Navindra Yadav ,  Abhishek Ranjan Singh ,  Anubhav Gupta ,  Shashidhar Gandham ,  Jackson Ngoc Ki Pang ,  Shih-Chun Chang ,  Hai Trong Vu

IPC: G06F21/53 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04847 ,  G06F9/455 ,  G06F16/11 ,  G06F16/13 ,  G06F16/16 ,  G06F16/17 ,  G06F16/174 ,  G06F16/23 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/28 ,  G06F16/29 ,  G06F16/9535 ,  G06F21/55 ,  G06F21/56 ,  G06N20/00 ,  G06N99/00 ,  G06T11/20 ,  H04J3/06 ,  H04J3/14 ,  H04L1/24 ,  H04L7/10 ,  H04L9/08 ,  H04L9/32 ,  H04L9/40 ,  H04L41/046 ,  H04L41/0668 ,  H04L41/0803 ,  H04L41/0806 ,  H04L41/0816 ,  H04L41/0893 ,  H04L41/12 ,  H04L41/16 ,  H04L41/22 ,  H04L43/02 ,  H04L43/026 ,  H04L43/04 ,  H04L43/045 ,  H04L43/062 ,  H04L43/08 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/0864 ,  H04L43/0876 ,  H04L43/0882 ,  H04L43/0888 ,  H04L43/10 ,  H04L43/106 ,  H04L43/12 ,  H04L43/16 ,  H04L45/00 ,  H04L45/302 ,  H04L45/50 ,  H04L45/74 ,  H04L47/11 ,  H04L47/20 ,  H04L47/2441 ,  H04L47/2483 ,  H04L47/28 ,  H04L47/31 ,  H04L47/32 ,  H04L61/5007 ,  H04L67/01 ,  H04L67/10 ,  H04L67/1001 ,  H04L67/12 ,  H04L67/51 ,  H04L67/75 ,  H04L69/16 ,  H04L69/22 ,  H04W72/54 ,  H04W84/18 ,  H04L67/50

Abstract: Systems, methods, and computer-readable media for managing compromised sensors in multi-tiered virtualized environments. In some embodiments, a system can receive, from a first capturing agent deployed in a virtualization layer of a first device, data reports generated based on traffic captured by the first capturing agent. The system can also receive, from a second capturing agent deployed in a hardware layer of a second device, data reports generated based on traffic captured by the second capturing agent. Based on the data reports, the system can determine characteristics of the traffic captured by the first capturing agent and the second capturing agent. The system can then compare the characteristics to determine a multi-layer difference in traffic characteristics. Based on the multi-layer difference in traffic characteristics, the system can determine that the first capturing agent or the second capturing agent is in a faulty state.

公开(公告)号：US12086722B2

公开(公告)日：2024-09-10

申请号：US17154879

申请日：2021-01-21

Applicant: Twist Bioscience Corporation

Inventor： Brian Wayne Bramlett ,  Bill James Peck

IPC: G06N3/12 ,  B01J19/00 ,  C12N15/09 ,  C12N15/10 ,  C40B50/14 ,  G06F17/40 ,  G06N3/123 ,  G06N99/00 ,  G11C11/00 ,  G11C11/56 ,  G11C13/00 ,  G11C13/02 ,  G16B50/20 ,  C12Q1/6869 ,  G06F16/00 ,  G16B30/00

CPC classification number: G06N3/123 ,  B01J19/0046 ,  C12N15/09 ,  C12N15/1068 ,  C40B50/14 ,  G06F17/40 ,  G06N99/007 ,  G11C11/00 ,  G11C11/56 ,  G11C13/0019 ,  G11C13/02 ,  G16B50/20 ,  B01J2219/00313 ,  B01J2219/0059 ,  B01J2219/00653 ,  B01J2219/00722 ,  C12Q1/6869 ,  G06F16/00 ,  G16B30/00

Abstract: Provided herein are compositions, devices, systems and methods for generation and use of biomolecule-based information for storage. Further provided are devices-having addressable electrodes controlling polynucleotide synthesis (deprotection, extension, or cleavage, etc.) The compositions, devices, systems and methods described herein provide improved storage, density, and retrieval of biomolecule-based information.

公开(公告)号：US11968103B2

公开(公告)日：2024-04-23

申请号：US17153785

申请日：2021-01-20

Applicant: Cisco Technology, Inc.

Inventor： Sunil Kumar Gupta ,  Navindra Yadav ,  Michael Standish Watts ,  Ali Parandehgheibi ,  Shashidhar Gandham ,  Ashutosh Kulshreshtha ,  Khawar Deen

IPC: H04L43/0864 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04847 ,  G06F9/455 ,  G06F16/11 ,  G06F16/13 ,  G06F16/16 ,  G06F16/17 ,  G06F16/174 ,  G06F16/23 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/28 ,  G06F16/29 ,  G06F16/9535 ,  G06F21/53 ,  G06F21/55 ,  G06F21/56 ,  G06N20/00 ,  G06N99/00 ,  G06T11/20 ,  H04J3/06 ,  H04J3/14 ,  H04L1/24 ,  H04L9/08 ,  H04L9/32 ,  H04L9/40 ,  H04L41/046 ,  H04L41/0668 ,  H04L41/0803 ,  H04L41/0806 ,  H04L41/0816 ,  H04L41/0893 ,  H04L41/12 ,  H04L41/16 ,  H04L41/22 ,  H04L43/02 ,  H04L43/026 ,  H04L43/04 ,  H04L43/045 ,  H04L43/062 ,  H04L43/08 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/0876 ,  H04L43/0882 ,  H04L43/0888 ,  H04L43/10 ,  H04L43/106 ,  H04L43/12 ,  H04L43/16 ,  H04L45/00 ,  H04L45/302 ,  H04L45/50 ,  H04L45/74 ,  H04L47/11 ,  H04L47/20 ,  H04L47/2441 ,  H04L47/2483 ,  H04L47/28 ,  H04L47/31 ,  H04L47/32 ,  H04L61/5007 ,  H04L67/01 ,  H04L67/10 ,  H04L67/1001 ,  H04L67/12 ,  H04L67/50 ,  H04L67/51 ,  H04L67/75 ,  H04L69/16 ,  H04L69/22 ,  H04W72/54 ,  H04W84/18

CPC classification number: H04L43/045 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04847 ,  G06F9/45558 ,  G06F16/122 ,  G06F16/137 ,  G06F16/162 ,  G06F16/17 ,  G06F16/173 ,  G06F16/174 ,  G06F16/1744 ,  G06F16/1748 ,  G06F16/2322 ,  G06F16/235 ,  G06F16/2365 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/285 ,  G06F16/288 ,  G06F16/29 ,  G06F16/9535 ,  G06F21/53 ,  G06F21/552 ,  G06F21/556 ,  G06F21/566 ,  G06N20/00 ,  G06N99/00 ,  G06T11/206 ,  H04J3/0661 ,  H04J3/14 ,  H04L1/242 ,  H04L9/0866 ,  H04L9/3239 ,  H04L9/3242 ,  H04L41/046 ,  H04L41/0668 ,  H04L41/0803 ,  H04L41/0806 ,  H04L41/0816 ,  H04L41/0893 ,  H04L41/12 ,  H04L41/16 ,  H04L41/22 ,  H04L43/02 ,  H04L43/026 ,  H04L43/04 ,  H04L43/062 ,  H04L43/08 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0829 ,  H04L43/0841 ,  H04L43/0858 ,  H04L43/0864 ,  H04L43/0876 ,  H04L43/0882 ,  H04L43/0888 ,  H04L43/10 ,  H04L43/106 ,  H04L43/12 ,  H04L43/16 ,  H04L45/306 ,  H04L45/38 ,  H04L45/46 ,  H04L45/507 ,  H04L45/66 ,  H04L45/74 ,  H04L47/11 ,  H04L47/20 ,  H04L47/2441 ,  H04L47/2483 ,  H04L47/28 ,  H04L47/31 ,  H04L47/32 ,  H04L61/5007 ,  H04L63/0227 ,  H04L63/0263 ,  H04L63/06 ,  H04L63/0876 ,  H04L63/1408 ,  H04L63/1416 ,  H04L63/1425 ,  H04L63/1433 ,  H04L63/1441 ,  H04L63/145 ,  H04L63/1458 ,  H04L63/1466 ,  H04L63/16 ,  H04L63/20 ,  H04L67/01 ,  H04L67/10 ,  H04L67/1001 ,  H04L67/12 ,  H04L67/51 ,  H04L67/75 ,  H04L69/16 ,  H04L69/22 ,  H04W72/54 ,  H04W84/18 ,  G06F2009/4557 ,  G06F2009/45587 ,  G06F2009/45591 ,  G06F2009/45595 ,  G06F2221/033 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06F2221/2111 ,  G06F2221/2115 ,  G06F2221/2145 ,  H04L67/535

Abstract: An example method according to some embodiments includes receiving flow data for a packet traversing a network. The method continues by determining a source endpoint group and a destination endpoint group for the packet. The method continues by determining that a policy was utilized, the policy being applicable to the endpoint group. Finally, the method includes updating utilization data for the policy based on the flow data.

公开(公告)号：US11948045B2

公开(公告)日：2024-04-02

申请号：US18304253

申请日：2023-04-20

Applicant: Google LLC

Inventor： Julian Shaw Kelly

IPC: G06F11/07 ,  G06F11/08 ,  G06N10/00 ,  G06N99/00 ,  H01L29/66 ,  H10N60/80

CPC classification number: G06N10/00 ,  G06F11/0751 ,  G06F11/0787 ,  G06F11/08 ,  G06N99/00 ,  H01L29/66977 ,  H10N60/805

Abstract: Methods, systems, and apparatus for parallel optimization of continuously running quantum error correction by closed-loop feedback. In one aspect, a method includes continuously and effectively optimizing qubit performance in-situ whilst an error correction operation on the quantum system is running. The method directly monitors the output from error detection and provides this information as feedback to calibrate the quantum gates associated with the quantum system. In some implementations, the physical qubits are spatially partitioned into one or more independent hardware patterns, where the errors attributable to each hardware pattern are non-overlapping. The one or more different sets of hardware patterns are then temporarily interleaved such that all physical qubits and operations are optimized. The method allows for the optimization of each section of a hardware pattern to be performed individually and in parallel, and can result is O(1) scaling.

公开(公告)号：US11924073B2

公开(公告)日：2024-03-05

申请号：US17403026

申请日：2021-08-16

Applicant: Cisco Technology, Inc.

Inventor： Sunil Kumar Gupta ,  Navindra Yadav ,  Michael Standish Watts ,  Ali Parandehgheibi ,  Shashidhar Gandham ,  Ashutosh Kulshreshtha ,  Khawar Deen

IPC: G06F21/00 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04847 ,  G06F9/455 ,  G06F16/11 ,  G06F16/13 ,  G06F16/16 ,  G06F16/17 ,  G06F16/174 ,  G06F16/23 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/28 ,  G06F16/29 ,  G06F16/9535 ,  G06F21/53 ,  G06F21/55 ,  G06F21/56 ,  G06N20/00 ,  G06N99/00 ,  G06T11/20 ,  H04J3/06 ,  H04J3/14 ,  H04L1/24 ,  H04L9/08 ,  H04L9/32 ,  H04L9/40 ,  H04L41/046 ,  H04L41/0668 ,  H04L41/0803 ,  H04L41/0806 ,  H04L41/0816 ,  H04L41/0893 ,  H04L41/12 ,  H04L41/16 ,  H04L41/22 ,  H04L43/02 ,  H04L43/026 ,  H04L43/04 ,  H04L43/045 ,  H04L43/062 ,  H04L43/08 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0829 ,  H04L43/0852 ,  H04L43/0864 ,  H04L43/0876 ,  H04L43/0882 ,  H04L43/0888 ,  H04L43/10 ,  H04L43/106 ,  H04L43/12 ,  H04L43/16 ,  H04L45/00 ,  H04L45/302 ,  H04L45/50 ,  H04L45/74 ,  H04L47/11 ,  H04L47/20 ,  H04L47/2441 ,  H04L47/2483 ,  H04L47/28 ,  H04L47/31 ,  H04L47/32 ,  H04L61/5007 ,  H04L67/01 ,  H04L67/10 ,  H04L67/1001 ,  H04L67/12 ,  H04L67/51 ,  H04L67/75 ,  H04L69/16 ,  H04L69/22 ,  H04W72/54 ,  H04W84/18 ,  H04L67/50

CPC classification number: H04L43/045 ,  G06F3/0482 ,  G06F3/04842 ,  G06F3/04847 ,  G06F9/45558 ,  G06F16/122 ,  G06F16/137 ,  G06F16/162 ,  G06F16/17 ,  G06F16/173 ,  G06F16/174 ,  G06F16/1744 ,  G06F16/1748 ,  G06F16/2322 ,  G06F16/235 ,  G06F16/2365 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/285 ,  G06F16/288 ,  G06F16/29 ,  G06F16/9535 ,  G06F21/53 ,  G06F21/552 ,  G06F21/556 ,  G06F21/566 ,  G06N20/00 ,  G06N99/00 ,  G06T11/206 ,  H04J3/0661 ,  H04J3/14 ,  H04L1/242 ,  H04L9/0866 ,  H04L9/3239 ,  H04L9/3242 ,  H04L41/046 ,  H04L41/0668 ,  H04L41/0803 ,  H04L41/0806 ,  H04L41/0816 ,  H04L41/0893 ,  H04L41/12 ,  H04L41/16 ,  H04L41/22 ,  H04L43/02 ,  H04L43/026 ,  H04L43/04 ,  H04L43/062 ,  H04L43/08 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0829 ,  H04L43/0841 ,  H04L43/0858 ,  H04L43/0864 ,  H04L43/0876 ,  H04L43/0882 ,  H04L43/0888 ,  H04L43/10 ,  H04L43/106 ,  H04L43/12 ,  H04L43/16 ,  H04L45/306 ,  H04L45/38 ,  H04L45/46 ,  H04L45/507 ,  H04L45/66 ,  H04L45/74 ,  H04L47/11 ,  H04L47/20 ,  H04L47/2441 ,  H04L47/2483 ,  H04L47/28 ,  H04L47/31 ,  H04L47/32 ,  H04L61/5007 ,  H04L63/0227 ,  H04L63/0263 ,  H04L63/06 ,  H04L63/0876 ,  H04L63/1408 ,  H04L63/1416 ,  H04L63/1425 ,  H04L63/1433 ,  H04L63/1441 ,  H04L63/145 ,  H04L63/1458 ,  H04L63/1466 ,  H04L63/16 ,  H04L63/20 ,  H04L67/01 ,  H04L67/10 ,  H04L67/1001 ,  H04L67/12 ,  H04L67/51 ,  H04L67/75 ,  H04L69/16 ,  H04L69/22 ,  H04W72/54 ,  H04W84/18 ,  G06F2009/4557 ,  G06F2009/45587 ,  G06F2009/45591 ,  G06F2009/45595 ,  G06F2221/033 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06F2221/2111 ,  G06F2221/2115 ,  G06F2221/2145 ,  H04L67/535

Abstract: A method provides for receiving network traffic from a host having a host IP address and operating in a data center, and analyzing a malware tracker for IP addresses of hosts having been infected by a malware to yield an analysis. When the analysis indicates that the host IP address has been used to communicate with an external host infected by the malware to yield an indication, the method includes assigning a reputation score, based on the indication, to the host. The method can further include applying a conditional policy associated with using the host based on the reputation score. The reputation score can include a reduced reputation score from a previous reputation score for the host.

公开(公告)号：US11914851B2

公开(公告)日：2024-02-27

申请号：US17752068

申请日：2022-05-24

Applicant: NEC Corporation

Inventor： Yusuke Takahashi

IPC: G06F3/04845 ,  G06F3/0488 ,  G06V10/22 ,  G06F18/214 ,  G06V10/774 ,  G06V20/52 ,  G06F3/0354 ,  G06F3/04842 ,  G06F3/04847 ,  G06F3/04883 ,  G06N99/00 ,  G06N20/00

CPC classification number: G06F3/04845 ,  G06F3/03543 ,  G06F3/0488 ,  G06F3/04842 ,  G06F3/04847 ,  G06F3/04883 ,  G06F18/214 ,  G06N99/00 ,  G06V10/235 ,  G06V10/774 ,  G06V20/52 ,  G06N20/00

Abstract: Provided is an object detection device or the like which efficiently generates good-quality training data. This object detection device is provided with: a detection unit which uses a dictionary to detect objects from an input image; a reception unit which displays, on a display device, the input image accompanied by a display emphasizing partial areas of detected objects, and receives, from one operation of an input device, a selection of a partial area and an input of the class of the selected partial area; a generation unit which generates training data from the image of the selected partial area and the inputted class; and a learning unit which uses the training data to learn the dictionary.

公开(公告)号：US20240015084A1

公开(公告)日：2024-01-11

申请号：US18471125

申请日：2023-09-20

Applicant: Cisco Technology, Inc.

Inventor： Sunil Kumar Gupta ,  Navindra Yadav ,  Michael Standish Watts ,  Ali Parandehgheibi ,  Shashidhar Gandham ,  Ashutosh Kulshreshtha ,  Khawar Deen

IPC: H04L43/045 ,  H04L9/40 ,  G06F9/455 ,  G06N20/00 ,  G06F21/55 ,  G06F21/56 ,  G06F16/28 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/29 ,  G06F16/16 ,  G06F16/17 ,  G06F16/11 ,  G06F16/13 ,  G06F16/174 ,  G06F16/23 ,  G06F16/9535 ,  G06N99/00 ,  H04L9/32 ,  H04L41/0668 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0852 ,  H04L43/106 ,  H04L45/00 ,  H04L45/50 ,  H04L67/12 ,  H04L43/026 ,  H04L61/5007 ,  H04L67/01 ,  H04L67/51 ,  H04L67/75 ,  H04L67/1001 ,  H04W72/54 ,  H04L43/062 ,  H04L43/10 ,  H04L47/2441 ,  H04L41/0893 ,  H04L43/08 ,  H04L43/04 ,  H04W84/18 ,  H04L67/10 ,  H04L41/046 ,  H04L43/0876 ,  H04L41/12 ,  H04L41/16 ,  H04L41/0816 ,  G06F21/53 ,  H04L41/22 ,  G06F3/04842 ,  G06F3/04847 ,  H04L41/0803 ,  H04L43/0829 ,  H04L43/16 ,  H04L1/24 ,  H04L9/08 ,  H04J3/06 ,  H04J3/14 ,  H04L47/20 ,  H04L47/32 ,  H04L43/0864 ,  H04L47/11 ,  H04L69/22 ,  H04L45/74 ,  H04L47/2483 ,  H04L43/0882 ,  H04L41/0806 ,  H04L43/0888 ,  H04L43/12 ,  H04L47/31 ,  G06F3/0482 ,  G06T11/20 ,  H04L43/02 ,  H04L47/28 ,  H04L69/16 ,  H04L45/302

CPC classification number: H04L43/045 ,  H04L63/1425 ,  H04L63/1441 ,  H04L63/20 ,  G06F9/45558 ,  G06N20/00 ,  G06F21/552 ,  G06F21/566 ,  G06F16/285 ,  G06F16/288 ,  G06F16/24578 ,  G06F16/248 ,  G06F16/29 ,  G06F16/162 ,  G06F16/17 ,  G06F16/122 ,  G06F16/137 ,  G06F16/173 ,  G06F16/1744 ,  G06F16/2322 ,  G06F16/235 ,  G06F16/9535 ,  G06F16/1748 ,  G06F16/174 ,  G06N99/00 ,  H04L9/3239 ,  H04L41/0668 ,  H04L43/0805 ,  H04L43/0811 ,  H04L43/0858 ,  H04L43/106 ,  H04L45/46 ,  H04L45/507 ,  H04L63/1458 ,  H04L67/12 ,  H04L43/026 ,  H04L61/5007 ,  H04L67/01 ,  H04L67/51 ,  H04L67/75 ,  H04L67/1001 ,  G06F21/556 ,  H04W72/54 ,  H04L63/1416 ,  H04L63/145 ,  H04L43/062 ,  H04L43/10 ,  H04L47/2441 ,  H04L41/0893 ,  H04L43/08 ,  H04L43/04 ,  H04W84/18 ,  H04L67/10 ,  H04L41/046 ,  H04L43/0876 ,  H04L41/12 ,  H04L41/16 ,  H04L41/0816 ,  G06F21/53 ,  H04L63/16 ,  H04L41/22 ,  G06F3/04842 ,  G06F3/04847 ,  H04L41/0803 ,  H04L43/0829 ,  H04L43/16 ,  H04L1/242 ,  H04L9/0866 ,  H04L9/3242 ,  H04L63/06 ,  H04L63/0876 ,  H04J3/0661 ,  H04J3/14 ,  H04L47/20 ,  H04L47/32 ,  H04L43/0841 ,  H04L43/0864 ,  H04L47/11 ,  H04L63/1408 ,  H04L69/22 ,  H04L45/74 ,  H04L47/2483 ,  H04L43/0882 ,  H04L63/0227 ,  H04L63/0263 ,  H04L41/0806 ,  H04L43/0888 ,  H04L43/12 ,  H04L63/1433 ,  H04L47/31 ,  H04L45/38 ,  H04L45/66 ,  G06F3/0482 ,  G06T11/206 ,  H04L43/02 ,  H04L47/28 ,  H04L69/16 ,  H04L63/1466 ,  H04L45/306 ,  G06F16/2365 ,  G06F2009/45587 ,  G06F2009/45595 ,  G06F2221/033 ,  G06F2221/2101 ,  G06F2221/2105 ,  G06F2221/2111 ,  G06F2221/2115 ,  G06F2221/2145 ,  H04L67/535

Abstract: An example method according to some embodiments includes receiving flow data for a packet traversing a network. The method continues by determining a source endpoint group and a destination endpoint group for the packet. The method continues by determining that a policy was utilized, the policy being applicable to the endpoint group. Finally, the method includes updating utilization data for the policy based on the flow data.

公开(公告)号：US20230418725A1

公开(公告)日：2023-12-28

申请号：US16016026

申请日：2018-06-22

Applicant: Wells Fargo Bank, N.A.

Inventor： Nathan Charles Freeling ,  Catherine Guangning Li ,  Iain Thomas Raleigh

IPC: G06F11/36 ,  G06F8/20 ,  G06N99/00

CPC classification number: G06F11/3604 ,  G06F8/20 ,  G06N99/005

Abstract: The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods of reviewing submitted programming solutions in response to a requested task. The innovation receives a solution for a task that is part of a project. The innovation analyzes the solution and the user according to a set of predetermined rules. The innovation determines a set of predetermined rules based on an analysis of previously received solutions. The innovation determines similarities between the received solution to previously received solutions. The innovation determines a subset of previously received solutions that are most similar to the received solution. The innovation analyzes the subset of previously received solutions, including a history of each solution in the subset. The innovation determines a likelihood of faults in the received solution based on the analysis of the subset.

公开(公告)号：US20230306060A1

公开(公告)日：2023-09-28

申请号：US18327340

申请日：2023-06-01

Applicant: Google LLC

Inventor： Matthew H. Austern ,  James C. Dehnert ,  Aart J.c. Bik ,  Grzegorz J. Czajkowski ,  Grzegorz Malewicz

IPC: G06F16/901 ,  G06N20/00 ,  G06F16/00 ,  G06F16/22 ,  G06F9/46 ,  G06F16/23 ,  G06F8/41 ,  G06F15/173 ,  G06N99/00 ,  H04L5/00 ,  G06T11/20 ,  G06F11/14 ,  G06F9/50 ,  H04L67/10

CPC classification number: G06F16/9024 ,  G06N20/00 ,  G06F16/00 ,  G06F16/2282 ,  G06F9/46 ,  G06F16/23 ,  G06F16/2365 ,  G06F8/457 ,  G06F15/17312 ,  G06N99/00 ,  H04L5/0032 ,  G06T11/206 ,  G06F11/1464 ,  G06F11/1469 ,  G06F9/5005 ,  H04L67/10 ,  G06F11/1451 ,  G06F2221/0793 ,  G06F11/2082

Abstract: Data are maintained in a distributed computing system that describe a graph. The graph represents relationships among items. The graph has a plurality of vertices that represent the items and a plurality of edges connecting the plurality of vertices. At least one vertex of the plurality of vertices includes a set of label values indicating the at least one vertex's strength of association with a label from a set of labels. The set of labels describe possible characteristics of an item represented by the at least one vertex. At least one edge of the plurality of edges includes a set of label weights for influencing label values that traverse the at least one edge. A label propagation algorithm is executed for a plurality of the vertices in the graph in parallel for a series of synchronized iterations to propagate labels through the graph.

公开(公告)号：US11720618B2

公开(公告)日：2023-08-08

申请号：US17584179

申请日：2022-01-25

Applicant: Open Text Corporation

Inventor： Charles-Olivier Simard ,  Alex Bowyer ,  Daniel Leclerc ,  Steve Molloy

IPC: G06F16/35 ,  G06N20/00 ,  G06F16/93 ,  G06F16/25 ,  G06F16/28 ,  G06N99/00 ,  G06F3/0482 ,  G06F3/04842

CPC classification number: G06F16/35 ,  G06F3/0482 ,  G06F3/04842 ,  G06F16/258 ,  G06F16/285 ,  G06F16/93 ,  G06N20/00 ,  G06N99/00

Abstract: In an auto-classification system, example documents whose content exemplifies a content category or classification can be imported into a classification model. The classification model is tested to assess accuracy. Based on the testing, metrics or other information can be provided as feedback to a user. The user can iteratively refine the classification model and keep re-running the classifications to view how each change to the classification model improves accuracy. If no user refinement is desired, the auto-classification system classifies documents utilizing the classification model. This technology enhances the overall transparency and defensibility of the auto-classification process.