公开(公告)号：US20230230166A1

公开(公告)日：2023-07-20

申请号：US16009698

申请日：2018-06-15

Applicant: State Farm Mutual Automobile Insurance Company

Inventor： Shane Tomlinson ,  Jennifer Malia Andrus ,  Marigona Bokshi-Drotar ,  Holly Lambert ,  Daniel J. Green ,  Michael Bernico ,  Bradley A. Sliz ,  He Yang

IPC: G06Q40/08 ,  G06N99/00

CPC classification number: G06Q40/08 ,  G06N99/005

Abstract: A system and computer-implemented method for classifying a level of vehicle damage includes receiving, at a remote server, captured image data of a vehicle from a user electronic device. The user electronic device has an orientation model configured to assist image capture. The image data is processed by the remote server using a damage assessment model. In addition, the remote server determines a classification for a level of damage to the vehicle based on the processed image data.

公开(公告)号：US20230169388A1

公开(公告)日：2023-06-01

申请号：US16016321

申请日：2018-06-22

Applicant: Meta Platforms, Inc.

Inventor： Lin Huang ,  Ying Zhang

IPC: G06N99/00 ,  G06F17/28

CPC classification number: G06N99/005 ,  G06F17/28 ,  G06Q50/01

Abstract: Systems, methods, and non-transitory computer readable media can train a machine learning model for a first language to determine a classification for a content item in the first language. Machine translation can be performed to generate respective machine translations of a plurality of content items in a second language into the first language. Respective classifications for the plurality of content items in the second language can be determined based on the machine translations of the plurality of content items in the second language and the machine learning model for the first language. Training data in the second language can be automatically generated, where the training data in the second language includes the plurality of content items in the second language and the respective classifications.

公开(公告)号：US20180359523A1

公开(公告)日：2018-12-13

申请号：US16003049

申请日：2018-06-07

Applicant: Silveredge Technologies Pvt. Ltd.

Inventor： Debasish MITRA ,  Hitesh CHAWLA

IPC: H04N21/44 ,  H04H60/37 ,  H04N21/81 ,  H04N21/466 ,  G06Q30/02

CPC classification number: H04N21/44008 ,  G06N99/005 ,  G06Q30/0242 ,  G06Q30/0264 ,  H04H60/375 ,  H04N21/466 ,  H04N21/812

Abstract: The present disclosure provides a computer-implemented method and system for progressive penalty and reward based ad scoring for real time supervised detection of televised video ads in televised media content. The method includes reception of the media content and selection of a set of frames per second from the media content. The method includes extraction of key points from each selected frame and derivation of binary descriptors from extracted key points. The method includes assignment of weight value to each binary descriptor and creation of a special pyramid of the binary descriptors. The method includes obtaining a first vocabulary of binary descriptors for each selected frame and accessing a second vocabulary of binary descriptors. The method includes comparison of each binary descriptor in the first vocabulary with binary descriptors in second vocabulary. The method includes progressively scoring each selected frame of the media content for detection of a first ad.

公开(公告)号：US20180359199A1

公开(公告)日：2018-12-13

申请号：US15620671

申请日：2017-06-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Amy Huyen Phuoc NGUYEN ,  Chia-Jung LEE ,  Ivan Valeryevich ZHIBOEDOV ,  Philipp CANNONS ,  Rachel Imogen SOLIMENO ,  Dong Hwi YOO ,  Yamin WANG ,  Milad SHOKOUHI

IPC: H04L12/58 ,  G06F17/30 ,  G06N99/00

CPC classification number: H04L51/02 ,  G06F17/30371 ,  G06F17/30654 ,  G06N99/005 ,  G06Q10/107

Abstract: Systems and methods are provided that automatically process message input and provide action responses according to the processing results. The automatic action response system may leverage at least one machine-learning algorithm that is trained using a dataset. The provided action responses may comprise of default action responses and/or intelligent action responses that are based at least in part on prior conversational data between a user and a sender. Some intelligent action responses may include text-based replies, which eliminate the need for a user to type a reply on a device screen, thereby saving previous time, conserving device battery life, and preserving the integrity of the device hardware. A portion of a message may be highlighted manually by a user or automatically by the action response system to initiate the automatic action response system. In this way, a more efficient and productive user experience across various devices and applications is achieved.

公开(公告)号：US20180359172A1

公开(公告)日：2018-12-13

申请号：US15620247

申请日：2017-06-12

Applicant: Juniper Networks, Inc.

Inventor： Alam YADAV

IPC: H04L12/751 ,  H04L12/851 ,  G06N99/00 ,  G06N5/04

CPC classification number: H04L45/08 ,  G06N5/04 ,  G06N99/005 ,  H04L41/12 ,  H04L41/145 ,  H04L41/147 ,  H04L41/5045 ,  H04L43/08 ,  H04L45/00 ,  H04L47/2483

Abstract: A network administration device may include one or more processors to receive operational information regarding a plurality of network devices; receive flow information relating to at least one traffic flow; input the flow information to a model, where the model is generated based on a machine learning technique, and where the model is configured to identify predicted performance information of one or more network devices with regard to the at least one traffic flow based on the operational information; determine path information for the at least one traffic flow with regard to the one or more network devices based on the predicted performance information; and/or configure the one or more network devices to implement the path information for the traffic flow.

公开(公告)号：US20180359078A1

公开(公告)日：2018-12-13

申请号：US15620090

申请日：2017-06-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Prateek Jain ,  Ramarathnam Venkatesan ,  Jonathan Lee ,  Kartik Gupta

IPC: H04L9/00 ,  H04L29/06 ,  G06N99/00

CPC classification number: H04L9/008 ,  G06F21/602 ,  G06N99/005 ,  H04L63/0428

Abstract: Systems, methods, and computer-executable instructions for homomorphic data analysis. Encrypted data is received, from a remote system, that has been encrypted with an encryption key. A number of iterations to iterate over the encrypted data is determined. A model is iterated over by the number of iterations to create an intermediate model. Each iteration updates the model, and the model and the intermediate model encrypted with the encryption key. The intermediate model is provided to the remote system. An updated model based upon the intermediate model is received from the remote system. The updated model is iterated over until a predetermined precision is reached to create a final model. The final model is provided to the remote system. The final model is encrypted with the encryption key.

公开(公告)号：US20180357654A1

公开(公告)日：2018-12-13

申请号：US15617363

申请日：2017-06-08

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yifei Huang ,  Xinying Song ,  Ankit Gupta ,  Jianfeng Gao ,  Prabhdeep Singh ,  Salman Mukhtar

IPC: G06Q30/02 ,  G06N5/04 ,  G06F17/11 ,  G06F17/18 ,  G06N99/00

CPC classification number: G06Q30/0206 ,  G06F17/11 ,  G06F17/18 ,  G06N5/04 ,  G06N99/005 ,  G06Q30/0202

Abstract: Methods, systems, and computer programs are presented for evaluating the accuracy of predictive systems and quantifiable measures of incremental value. One method provides a scientific solution to test and evaluate predictive systems in a transparent, rigorous, and verifiable way to allow decision-makers to better decide whether to adopt a new predictive system. In one example, objects to be evaluated are assigned to a control group or an experiment group. The testing provides an equal or better distribution of scores in the control group for the scores obtained with the first predictor, but the method aims at maximizing the scores of objects obtained with the second predictor in the experiment group. Since the first scores are evenly distributed in both groups, any result improvements may be attributed to the better accuracy of the second predictor when the results of the experiment group are better than the results of the control group.

公开(公告)号：US20180357571A1

公开(公告)日：2018-12-13

申请号：US16006213

申请日：2018-06-12

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Ke Sun ,  Shiqi Zhao ,  Dianhai Yu ,  Haifeng Wang

IPC: G06N99/00 ,  G06F7/14 ,  G06F17/27

CPC classification number: G06N99/005 ,  G06F7/14 ,  G06F17/2785

Abstract: A conversation processing method and apparatus based on artificial intelligence, a device and a computer-readable storage medium. The disclosure embodiments, enable the user feedback information provided by conversation service conducted by the user to model conversation understanding system, then according to the user feedback information, perform adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system so that it is possible to execute the conversation service with the model conversation understanding system, based on the adjustment state. Since a fault-tolerant and fault-correcting mechanism is provided, it is possible to adjust the understanding capability of the model conversation understanding system in real time and thereby effectively improve the reliability of conversation by collecting the user's user feedback information, and then adjusting the service state of the model conversation understanding system in time based on the user feedback information.

公开(公告)号：US20180357570A1

公开(公告)日：2018-12-13

申请号：US16006208

申请日：2018-06-12

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Ke SUN ,  Shiqi ZHAO ,  Dianhai YU ,  Haifeng WANG

IPC: G06N99/00 ,  G06F7/14 ,  G06F17/27

CPC classification number: G06N99/005 ,  G06F7/14 ,  G06F17/2785

Abstract: A method and apparatus for building a conversation understanding system based on artificial intelligence, a device and a computer-readable storage medium. In embodiments of the present disclosure, it is feasible to obtain the training feedback information provided by conversation service conducted by the user and the basic conversation understanding system, then according to the training feedback information, perform adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system. It is possible to perform data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system. This method does not require persons to participate in annotation operations of the training data, exhibits simple operations and a high correctness rate, improving the efficiency and reliability of the conversation understanding system.

公开(公告)号：US20180357558A1

公开(公告)日：2018-12-13

申请号：US15617860

申请日：2017-06-08

Applicant: International Business Machines Corporation

Inventor： Jing Ding ,  Jing Li ,  Ji Jiang Song ,  Jian Wang

IPC: G06N99/00 ,  G06F17/30 ,  G06N5/04

CPC classification number: G06N99/005 ,  G06F17/30312 ,  G06F17/30371 ,  G06N5/047

Abstract: The subject disclosure relates to employing grouping and selection components to facilitate a grouping of failure data associated with oil and gas exploration equipment into one or more equipment failure type groups. In an example, a method comprises grouping, by a system operatively coupled to a processor, training data of a set of equipment failure data into one or more failure type groups based on one or more determined failure criteria, wherein the one or more failure type groups represent equipment failure classifications associated with energy exploration processes; and selecting, by the system, first ungrouped data from the set of equipment failure data based on a level of similarity between the first ungrouped data and the training data.