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

WO2017107173A1 TECHNOLOGIES FOR AUTOMATED APPLICATION TESTING COVERAGE AND RESULTS EVALUATION 审中-公开
标题翻译：自动化应用测试覆盖和结果评估技术
公开(公告)号：WO2017107173A1
公开(公告)日：2017-06-29
申请号：PCT/CN2015/098840
申请日：2015-12-25
申请人： INTEL CORPORATION , DENG, Tao , SHEN, Haihao , WANG, Yun , GONG, Jiong , HUANG, Zao
发明人： DENG, Tao , SHEN, Haihao , WANG, Yun , GONG, Jiong , HUANG, Zao
IPC分类号： G06F11/36
CPC分类号： G06F11/3664
摘要： Technologies for application testing include a host computing device (102) and a test computing device (104, 104a, 104b). The host computing device (102) captures a frame of a display interface generated by an application executed by the test computing device (104, 104a, 104b). The host computing device (102) may detect a crash indication as a function of the captured frame. In response to detecting the crash indication, the host computing device (102) may detect an application crash based on an error log and in response report a test failure. The host computing device (102) may capture a scene of the display interface, recognize one or more user interface objects of the scene, select a test action based on the scene, and perform the test action. The test action and a user interface object may be selected probabilistically. The host computing device (102) records test coverage data in response to performing the test action.
摘要翻译：用于应用测试的技术包括主机计算设备（102）和测试计算设备（104,104a，104b）。主机计算设备（102）捕捉由测试计算设备（104,104a，104b）执行的应用程序生成的显示界面的帧。主机计算设备（102）可以根据所捕获的帧来检测碰撞指示。响应于检测到崩溃指示，主机计算设备（102）可以基于错误日志检测应用程序崩溃并且作为响应报告测试失败。主计算设备（102）可捕捉显示界面的场景，识别场景的一个或多个用户界面对象，基于场景选择测试动作，并执行测试动作。测试操作和用户界面对象可以概率性地选择。主机计算设备（102）响应于执行测试动作而记录测试覆盖数据。

2. 发明申请

WO2016206113A1 TECHNOLOGIES FOR DEVICE INDEPENDENT AUTOMATED APPLICATION TESTING 审中-公开
标题翻译：独立自动化应用测试技术
公开(公告)号：WO2016206113A1
公开(公告)日：2016-12-29
申请号：PCT/CN2015/082542
申请日：2015-06-26
申请人： INTEL CORPORATION , GONG, Jiong , WANG, Yun , SHEN, Haihao
发明人： GONG, Jiong , WANG, Yun , SHEN, Haihao
IPC分类号： G06F11/36
CPC分类号： G06F11/3664 , G06F3/04817 , G06F11/36 , G06F11/3688
摘要： Technologies for device-independent application testing include a host computing device and one or more test computing devices. The host computer device records user interface events generated by an application of the test computing device and video data indicative of the display interface of the application. The host computing device detects user interface objects in the video data that correspond to user interface events using a computer vision algorithm, which may include image feature detection or optical character recognition. The host computing device generates an object-based test script that identifies the user interface object and a user interaction. The host computing device may identify the user interface object in the display interface of an application executed by a different test computing device using the computer vision algorithm. The host computing device performs the specified user interaction on the detected user interface object. Other embodiments are described and claimed.
摘要翻译：用于与设备无关的应用测试的技术包括主机计算设备和一个或多个测试计算设备。主计算机设备记录由测试计算设备的应用产生的用户界面事件和表示应用的显示界面的视频数据。主计算设备使用计算机视觉算法来检测与用户界面事件相对应的视频数据中的用户界面对象，其可以包括图像特征检测或光学字符识别。主机计算设备生成标识用户界面对象和用户交互的基于对象的测试脚本。主计算设备可以使用计算机视觉算法来识别由不同测试计算设备执行的应用的显示界面中的用户界面对象。主机计算设备在检测到的用户界面对象上执行指定的用户交互。描述和要求保护其他实施例。

3. 发明申请

WO2017049649A1 TECHNOLOGIES FOR AUTOMATED APPLICATION EXPLORATORY TESTING 审中-公开
标题翻译：自动化应用探测技术
公开(公告)号：WO2017049649A1
公开(公告)日：2017-03-30
申请号：PCT/CN2015/090852
申请日：2015-09-26
申请人： INTEL CORPORATION , SHEN, Haihao , WANG, Yun , CHENG, Wenhua , GONG, Jiong
发明人： SHEN, Haihao , WANG, Yun , CHENG, Wenhua , GONG, Jiong
IPC分类号： G06F9/44
CPC分类号： G06F11/3664
摘要： Technologies for automated application exploratory testing include a host computing device and a test computing device. The host computing device captures a frame of a display interface of a test application executed by the test computing device. The host computing device determines whether the captured frame matches video data associated with predefined test scripts. The host computing device may detect still features of the video data and compare the captured frame to the still features. The host computing device may schedule a test script for execution that is associated with a matching video. The host computing device may continue executing a currently executing test script if it is associated with a matching video. If no video matches the captured frame, the host computing device performs exploratory execution of the application and may dismiss a transient user interface. Other embodiments are described and claimed.
摘要翻译：用于自动化应用探索性测试的技术包括主机计算设备和测试计算设备。主计算设备捕获由测试计算设备执行的测试应用的显示界面的帧。主机计算设备确定捕获的帧是否匹配与预定义测试脚本相关联的视频数据。主计算设备可以检测视频数据的静态特征，并将捕获的帧与静态特征进行比较。主计算设备可以安排与匹配视频相关联的用于执行的测试脚本。主机计算设备如果与匹配的视频相关联，则可以继续执行当前正在执行的测试脚本。如果没有视频与捕获的帧匹配，则主机计算设备执行应用的探索性执行，并且可以忽略临时用户界面。描述和要求保护其他实施例。

4. 发明申请

WO2021179281A1 OPTIMIZING LOW PRECISION INFERENCE MODELS FOR DEPLOYMENT OF DEEP NEURAL NETWORKS 审中-公开
公开(公告)号：WO2021179281A1
公开(公告)日：2021-09-16
申请号：PCT/CN2020/079161
申请日：2020-03-13
申请人： INTEL CORPORATION , GONG, Jiong , WU, Yong , SHEN, Haihao , LIN, Xiao Dong , ZHANG, Guoming , YUAN, Feng
发明人： GONG, Jiong , WU, Yong , SHEN, Haihao , LIN, Xiao Dong , ZHANG, Guoming , YUAN, Feng
IPC分类号： G06N3/04
摘要： Systems, apparatuses and methods may provide technology for optimizing an inference neural network model that performs asymmetric quantization by generating a quantized neural network, wherein model weights of the neural network are quantized as signed integer values, and wherein an input layer of the neural network is configured to quantize input values as unsigned integer values, generating a weights accumulation table based on the quantized model weights and a kernel size for the neural network, and generating an output restoration function for an output layer of the neural network based on the weights accumulation table and the kernel size. The technology may also perform per-input channel quantization. The technology may also perform mixed-precision auto-tuning.

5. 发明申请

WO2020024093A1 METHOD AND APPARATUS FOR KEEPING STATISTICAL INFERENCE ACCURACY WITH 8-BIT WINOGRAD CONVOLUTION 审中-公开
公开(公告)号：WO2020024093A1
公开(公告)日：2020-02-06
申请号：PCT/CN2018/097730
申请日：2018-07-30
申请人： INTEL CORPORATION , GONG, Jiong , SHEN, Haihao , LIN, Xiao Dong , LIU, Xiaoli
发明人： GONG, Jiong , SHEN, Haihao , LIN, Xiao Dong , LIU, Xiaoli
IPC分类号： G06N3/04
摘要： A method and apparatus for keeping statistical inference accuracy with 8-bit winograd convolution. A calibration dataset and a pretrained CNN comprising 32-bit floating point weight values may be sampled to generate an input activation tensor and a weight tensor. A transformed input activation tensor may be generated by multiplying the input activation tensor and an input matrix to generate a transformed input activation tensor. A transformed weight tensor may be generated by multiplying the weight tensor and a weight matrix. A scale factor may be computed for each transformed tensor. An 8-bit CNN model including the scale factors may be generated.

6. 发明申请

WO2023077320A1 APPARATUS, METHOD, DEVICE AND MEDIUM FOR LABEL-BALANCED CALIBRATION IN POST-TRAINING QUANTIZATION OF DNN 审中-公开
公开(公告)号：WO2023077320A1
公开(公告)日：2023-05-11
申请号：PCT/CN2021/128507
申请日：2021-11-03
申请人： INTEL CORPORATION , SHEN, Haihao , TIAN, Feng , CHEN, Xi , ABIDI, Huma , ZHOU, Yuwen
发明人： SHEN, Haihao , TIAN, Feng , CHEN, Xi , ABIDI, Huma , ZHOU, Yuwen
IPC分类号： G06N3/02
摘要： Apparatus, a method (100), a device and a medium for label-balanced calibration in post-training quantization of DNNs, the apparatus includes interface circuitry (820) configured to receive a training dataset and processor circuitry coupled to the interface circuitry (820). The processor circuitry is configured to generate a small ground truth dataset by selecting images with a ground truth number of 1 from the training dataset (110); generate a calibration dataset randomly from the training dataset (120); if any image in the calibration dataset has the ground truth number of 1, remove the image from the small ground truth dataset (130); generate a label balanced calibration dataset by replacing an image with a ground truth number greater than a preset threshold in the calibration dataset with a replacing image selected randomly from the small ground truth dataset (140); and perform calibration using the label balanced calibration dataset in post-training quantization of the DNN (150).

7. 发明申请

WO2023070324A1 METHOD AND APPARATUS FOR OPTIMIZING INFERENCE OF DEEP NEURAL NETWORKS 审中-公开
公开(公告)号：WO2023070324A1
公开(公告)日：2023-05-04
申请号：PCT/CN2021/126456
申请日：2021-10-26
申请人： INTEL CORPORATION , SHEN, Haihao , MENG, Hengyu , TIAN, Feng
发明人： SHEN, Haihao , MENG, Hengyu , TIAN, Feng
IPC分类号： G06N3/063
摘要： The present disclosure discloses a hardware-aware cost model for optimizing inference of a deep neural network (DNN) comprising: a computation cost estimator configured to compute estimated computation cost based on input tensor, weight tensor and output tensor from the DNN; and a memory/cache cost estimator configured to perform memory/cache cost estimation strategy based on hardware specifications, wherein the hardware-aware cost model is used to perform performance simulation on target hardware to provide dynamic quantization knobs to quantization as required for converting a conventional precision inference model to an optimized inference model based on the result of the performance simulation.

8. 发明公开

EP3314440A1 TECHNOLOGIES FOR DEVICE INDEPENDENT AUTOMATED APPLICATION TESTING 审中-公开
标题翻译：设备独立自动化应用测试技术
公开(公告)号：EP3314440A1
公开(公告)日：2018-05-02
申请号：EP15896009.6
申请日：2015-06-26
申请人： Intel Corporation
发明人： GONG, Jiong , WANG, Yun , SHEN, Haihao
IPC分类号： G06F11/36
CPC分类号： G06F11/3664 , G06F3/04817 , G06F11/36 , G06F11/3688
摘要： Technologies for device-independent application testing include a host computing device and one or more test computing devices. The host computer device records user interface events generated by an application of the test computing device and video data indicative of the display interface of the application. The host computing device detects user interface objects in the video data that correspond to user interface events using a computer vision algorithm, which may include image feature detection or optical character recognition. The host computing device generates an object-based test script that identifies the user interface object and a user interaction. The host computing device may identify the user interface object in the display interface of an application executed by a different test computing device using the computer vision algorithm. The host computing device performs the specified user interaction on the detected user interface object. Other embodiments are described and claimed.

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