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. 发明申请

WO2023022754A1 AI MODEL USED IN AN AI INFERENCE ENGINE CONFIGURED TO PREDICT HARDWARE FAILURES 审中-公开
公开(公告)号：WO2023022754A1
公开(公告)日：2023-02-23
申请号：PCT/US2022/015430
申请日：2022-02-07
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE USA LLC
发明人： KESAVAN, Krishnakumar , SUTHAR, Manish
IPC分类号： G06F11/00 , G06F11/07
摘要： Server hardware failure is predicted, with a probability estimate, of a possible future server failure along with an estimated cause of the future server failure. Based on the prediction, the particular server can be evaluated and if the risk is confirmed, load balancing can be performed to move a load (e.g., virtual machines (VMs)) off of the at-risk server onto low-risk servers. High availability of deployed load (e.g., VMs) is then achieved. A flow of big data may be on the order of 1,000,000 parameters per minute. A scalable tree-based AI inference engine processes the flow. One or more leading indicators are identified (including server parameters and statistic types) which reliably predict hardware failure. This allows a telco operator to monitor cloud-based VMs and perform a hot-swap on virtual machines if needed by shifting virtual machines VMs from the at-risk server to low-risk servers. Servers having a health score indicating high risk are indicated on a visual display called a heat map. The heat map quickly provides a visual indication to the telco person of identities of at-risk servers. The heat map can also indicate commonalities between at-risk servers, such as if the at-risk servers are correlated in terms of protocols in use, if the at-risk servers are correlated in terms of geographic location, server manufacturer, server OS load, or the particular hardware failure mechanism predicted for the at-risk servers.

2. 发明申请

WO2023091187A1 DATA STANDARDIZATION SYSTEM AND METHODS OF OPERATING THE SAME 审中-公开
公开(公告)号：WO2023091187A1
公开(公告)日：2023-05-25
申请号：PCT/US2022/029357
申请日：2022-05-16
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE USA LLC
发明人： SISWANTO, Dewa , NATARAJAN, Murugavel
IPC分类号： G06F16/215 , G06F16/21 , G06F16/20 , G06F16/00
摘要： Embodiments of a method of standardizing data are disclosed. In some embodiments, first data structures are obtained at a computer device in multiple database formats. A standardized database format is defined at the computer device. In some embodiments, the first data structures are converted into second data structures, wherein each of the second data structures are each in the standardized database format.

3. 发明申请

WO2022013635A1 DETECTING OF SLEEPING CELL IN A MOBILE NETWORK 审中-公开
公开(公告)号：WO2022013635A1
公开(公告)日：2022-01-20
申请号：PCT/IB2021/054894
申请日：2021-06-04
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD.
发明人： WASNIK, Pankaj , KUMAR, Uttam , CHANDRASHEKHAR, Shashank , DESHPANDE, Atul
IPC分类号： H04W24/04 , H04W24/08
摘要： A method includes collecting data related to a key performance indicator (KPI) for a cell in a mobile network. The method includes aggregating the collected data for the KPI into a plurality of groups, wherein a first group of the plurality of groups comprises values of the KPI during a time period in a first day, a second group of the plurality of groups comprises values of the KPI during the time period in a second day preceding the first day, and a third group of the plurality of groups comprises values of the KPI during the time period in a third day preceding the second day. The method includes determining whether the cell is a sleeping cell based on a comparison of the first, second and third groups. The method includes labelling the cell as sleeping in response to a determination that the cell is sleeping.

4. 发明申请

WO2023022755A1 INFERENCE ENGINE CONFIGURED TO PROVIDE A HEAT MAP INTERFACE 审中-公开
公开(公告)号：WO2023022755A1
公开(公告)日：2023-02-23
申请号：PCT/US2022/015431
申请日：2022-02-07
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE USA LLC
发明人： KESAVAN, Krishnakumar , SUTHAR, Manish
IPC分类号： H04W24/02 , G06F15/173
摘要： Server hardware failure is predicted, with a probability estimate, of a possible future server failure along with an estimated cause of the future server failure. Based on the prediction, the particular server can be evaluated and if the risk is confirmed, load balancing can be performed to move a load (e.g., virtual machines (VMs)) off of the at-risk server onto low-risk servers. High availability of deployed load (e.g., VMs) is then achieved. A flow of big data may be on the order of 1,000,000 parameters per minute. A scalable tree-based AI inference engine processes the flow. One or more leading indicators are identified (including server parameters and statistic types) which reliably predict hardware failure. This allows a telco operator to monitor cloud-based VMs and perform a hot-swap on virtual machines if needed by shifting virtual machines VMs from the at-risk server to low-risk servers. Servers having a health score indicating high risk are indicated on a visual display called a heat map. The heat map quickly provides a visual indication to the telco person of identities of at-risk servers. The heat map can also indicate commonalities between at-risk servers, such as if the at-risk servers are correlated in terms of protocols in use, if the at-risk servers are correlated in terms of geographic location, server manufacturer, server OS load, or the particular hardware failure mechanism predicted for the at-risk servers.

5. 发明申请

WO2023022753A1 FEATURE IDENTIFICATION METHOD FOR TRAINING OF AI MODEL 审中-公开
公开(公告)号：WO2023022753A1
公开(公告)日：2023-02-23
申请号：PCT/US2022/015429
申请日：2022-02-07
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE USA LLC
发明人： KESAVAN, Krishnakumar , SUTHAR, Manish
IPC分类号： G06N20/00 , G06F30/00
摘要： Server hardware failure is predicted, with a probability estimate, of a possible future server failure along with an estimated cause of the future server failure. Based on the prediction, the particular server can be evaluated and if the risk is confirmed, load balancing can be performed to move a load (e.g., virtual machines (VMs)) off of the at-risk server onto low-risk servers. High availability of deployed load (e.g., VMs) is then achieved. A flow of big data may be on the order of 1,000,000 parameters per minute. A scalable tree-based AI inference engine processes the flow. One or more leading indicators are identified (including server parameters and statistic types) which reliably predict hardware failure. This allows a telco operator to monitor cloud-based VMs and perform a hot-swap on virtual machines if needed by shifting virtual machines VMs from the at-risk server to low-risk servers. Servers having a health score indicating high risk are indicated on a visual display called a heat map. The heat map quickly provides a visual indication to the telco person of identities of at-risk servers. The heat map can also indicate commonalities between at-risk servers, such as if the at-risk servers are correlated in terms of protocols in use, if the at-risk servers are correlated in terms of geographic location, server manufacturer, server OS load, or the particular hardware failure mechanism predicted for the at-risk servers.

6. 发明公开

US20240265122A1 SYSTEM AND METHOD FOR AUTHORIZING AN ACCESS TOKEN USING A DISTRIBUTED CACHE 审中-公开
公开(公告)号：US20240265122A1
公开(公告)日：2024-08-08
申请号：US18012038
申请日：2022-10-11
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD.
发明人： Manoj ASWANI , Hemant SHARMA , Ayus KUMAR , Shudhanshu SHEKHAR , Arpit CHOUKSEY
IPC分类号： G06F21/62 , G06F21/64
CPC分类号： G06F21/62 , G06F21/64
摘要： A method for authorizing a client application to access resources using a distributed cache is provided. The method includes: receiving, from the client application, a login request at an identity management (IDM) tool; providing, by the IDM tool to the distributed cache, a token session state of a first access token and permission information of the first access token; masking the permission information from the first access token and providing an updated access token to the client application with the permission information masked; receiving, at an application programming interface (API) gateway from the client application, a service request comprising the updated access token; validating the updated access token using the distributed cache; and providing a response to the client application based on the validation.

7. 发明公开

US20240250875A1 O-CLOUD NODE UNCORDON 审中-公开
公开(公告)号：US20240250875A1
公开(公告)日：2024-07-25
申请号：US18013777
申请日：2022-11-29
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE, INC.
发明人： Mohit LUTHRA , Awn MUHAMMAD , Pankaj SHETE , Puneet DEVADIGA
IPC分类号： H04L41/0823
CPC分类号： H04L41/0823
摘要： A method includes receiving a request to change a deployable state of an open radio access network (O-RAN) cloud (O-Cloud) node, changing the deployable state of the O-Cloud node in response to receiving the request, and transmitting an indication that the deployable state of the O-Cloud node has been modified in response to changing the deployable state.

8. 发明公开

US20240244437A1 SYSTEMS AND METHODS FOR HANDLING ABNORMAL ACTIVITY IN O-RAN NEAR REAL TIME RIC PLATFORM 审中-公开
公开(公告)号：US20240244437A1
公开(公告)日：2024-07-18
申请号：US18012483
申请日：2022-11-14
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD. , RAKUTEN MOBILE, INC.
发明人： Prabhu KALISWAMY , Raghavendran RAMIYA , Ritesh Kumar KALLE
IPC分类号： H04W12/128
CPC分类号： H04W12/128
摘要： A method performed by at least one processor includes detecting an onboarding of an application. The method further includes determining one or more application properties of the application in response to the detecting. The method further includes generating a protection program based on the one or more application properties. The method further includes deploying the protection program. The protection program provides a mitigation action in response to a detection of an attack on the application.

9. 发明公开

US20240242068A1 SYSTEM, METHOD, DEVICE, AND PROGRAM FOR ENHANCED GRAPH-BASED NODE CLASSIFICATION 审中-公开
公开(公告)号：US20240242068A1
公开(公告)日：2024-07-18
申请号：US18010163
申请日：2022-09-30
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD.
发明人： Xiaohui RONG , Allan Kiplangat CHEPKOY , Yulong WANG
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： System, method, device, and program for graph embedding based on graph data and non-graph data are provided. The method and processes may be executed by at least one processor and may include receiving graph data associated with one or more users, and receiving classification data associated with the one or more users, wherein the classification data comprises non-graph data associated with the one or more users. The method and processed may further include generating an accuracy parameter based on the classification data associated with the one or more users, wherein the accuracy parameter indicates an accuracy of neural network-based classification results based on the classification data; and generating numerical node representation using a neural network-based graph embedding model associated with the one or more users based on the graph data, the classification data, and the accuracy parameter.

10. 发明公开

US20240224061A1 METHOD AND APPARATUS FOR AUTO PRIORITIZATION OF PLANNED NETWORK SITES 审中-公开
公开(公告)号：US20240224061A1
公开(公告)日：2024-07-04
申请号：US17923737
申请日：2022-09-07
申请人： RAKUTEN SYMPHONY SINGAPORE PTE. LTD.
发明人： Prithvi Raj DHAKA
IPC分类号： H04W16/18 , H04L41/14
CPC分类号： H04W16/18 , H04L41/145
摘要： A method for planning network sites includes receiving a dataset of a plurality of planned network sites. The method further includes executing a coverage availability microservice to determine coverage availability for each planned network site in the plurality of planned network sites. The method further includes executing one or more microservices to determine geographic conditions for each planned network site in the plurality of network sites. The method further includes executing a priority microservice to assign one or more priority levels to each planned network site of the plurality of planned network sites based on at least the determined coverage availability for each planned network site and the determined geographic conditions for each planned network site. The method further includes executing a report generating microservice to generate a report for each planned network site of the plurality of network sites.

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