Abstract: A method for removing etchant byproduct from an etch reactor and discharging a substrate from an electrostatic chuck of the etch reactor is provided. A substrate may be electrostatically secured to an electrostatic chuck within a chamber of an etch reactor. A first plasma may be provided into the chamber to etch the substrate, causing an etchant byproduct to be generated. After the etching is complete, a second plasma may be provided into the chamber, wherein the second plasma is an oxygen containing plasma. The etchant byproduct may be removed and the first substrate may be discharged using the second plasma. The first substrate may be removed from the chamber and a second substrate may be inserted into the chamber without first performing an in-situ cleaning between the removal of the first substrate and the insertion of the second substrate.

Abstract: A method, a computer system, and a computer program product are provided for federated learning. An aggregator may receive cluster information from distributed computing devices. The cluster information may relate to identified clusters in sample data of the distributed computing devices. The cluster information may include centroid information per cluster. The aggregator may include a processor. The aggregator may integrate the cluster information to define data classes for machine learning classification. The integrating may include computing a respective distance between centroids of the clusters in order to determine a total number of the data classes. The aggregator may send a deep learning model that includes an output layer that has a total number of nodes equal to the total number of the data classes. The deep learning model may be for the distributed computing devices to perform machine learning classification in federated learning.

Abstract: A method, charging device, and non-transitory computer readable medium for detecting charging state comparing obtaining data packages from a chargeable electrical device, each of the data packages comprising a first transmitting power; counting a quantity of the data packages of the first transmitting power data package being smaller than a theoretical transmitting power in a predetermined time period; and based on the quantity of the data packages, determining whether the chargeable electrical device is fully charged.

Abstract: Methods of semiconductor processing may include performing a first plasma treatment within a processing chamber to remove a first carbon-containing material. The methods may include performing a second plasma treatment within the processing chamber to remove a first silicon-containing material. The methods may include depositing a second silicon-containing material on surfaces of the processing chamber. The methods may include depositing a second carbon-containing material overlying the second silicon-containing material.

Abstract: The present disclosure relates to the field of intelligent lawn mowers and logic control technologies thereof, and discloses a path planning method for an intelligent lawn mower. The path planning method includes: starting a touch panel of the intelligent lawn mower; entering a path planning setting interface, which displays a schematic diagram of a region to be mowed, a path angle indicating image and a path angle setting image; receiving a touch input of a user with respect to the path angle setting image to set a path angle; adjusting, based on the set path angle, the path angle indicating image for display; and re-planning a path of the intelligent lawn mower based on the set path angle and a preset algorithm. The present disclosure further provides a path planning system for the intelligent lawn mower.

Abstract: A method, a computer system, and a computer program product are provided for federated learning enhanced with semantic learning. An aggregator may receive cluster information from distributed computing devices. The cluster information may relate to identified clusters in sample data of the distributed computing devices. The aggregator may integrate the cluster information to define classes. The integrating may include identifying any redundant clusters amongst the identified clusters. A number of the classes may correspond to a total number of the clusters from the distributed computing devices reduced by any redundant clusters. A deep learning model may be sent from the aggregator to the distributed computing devices. The deep learning model may include an output layer having nodes that may correspond to the defined classes. The aggregator may receive results of federated learning performed by the distributed computing devices. The federated learning may train the deep learning model.

Abstract: The present invention provides a multi-material 3D object printing method and a print control apparatus. The multi-material 3D object printing method includes: a. randomly generating at least one group of area print data based on each group of area information of a target object, then correspondingly generating layer print data according to multiple groups of area information of each layer of the target object, and forming the multiple groups of layer print data into 3D object print data; b. performing layer-by-layer printing based on the 3D object print data; and c. stacking layer-by-layer printing products from the step b to form a 3D object. As disclosed, a texture of a 3D object generated by means of printing is homogeneous, thereby expanding the application scope of manufacturing a 3D object by using an inkjet printing technology, and implementing smooth transition between materials in different areas of a same 3D object.

Abstract: Cable manufacturing method and cable assembly, comprising a transmission wire, a first metal covering layer, an inner insulating layer, a second metal covering layer, an outer insulating layer, an insulating protective layer, and an outer metal layer. The transmission wire extends along a first direction. The first metal covering layer extends along the first direction and covers the transmission wire. The first metal covering layer comprises a first axial end part. The inner insulating layer extends along the first direction and coves the first metal covering layer. The inner insulating layer comprises a second axial end part. The second metal covering layer extends along the first direction and covers the inner insulating layer. The second metal covering layer comprises a third axial end part. The outer insulating layer extends along the first direction and covers the second metal covering layer. The outer insulating layer comprises a fourth axial end part.

Abstract: The disclosure provides a method for testing a vehicle-mounted voice device, an electronic device and a storage medium. The method includes: obtaining a test corpus and a data label corresponding to the test corpus; parsing the test corpus based on the data label corresponding to the test corpus to obtain audio data corresponding to each channel included in the test corpus; adjusting a working mode of each playback channel in a voice playback device based on the audio data corresponding to each channel included in the test corpus, to play the audio data corresponding to the test corpus; obtaining a recognition result of a vehicle-mounted voice device; and determining a performance of the vehicle-mounted voice device based on the recognition result and the data label.

Abstract: A method for processing an audio signal, a method for training a voice recognition model, a method for training a semantic recognition model, an electronic device and a storage medium are provided, which relate to a field of artificial intelligence, and in particular to fields of voice recognition, natural language processing and deep learning. The method for processing an audio signal includes: recognizing an audio signal to obtain a target voice segment and a first sentence associated with the target voice segment, the audio signal is obtained based on a predetermined text; determining a second sentence associated with the target voice segment in the predetermined text; comparing the first sentence with the second sentence; and labeling the target voice segment based on the second sentence and the comparison result. The labeling data includes the second sentence and a first data indicating the first comparison result.

Abstract: A method of performing a voice wake-up in multiple speech zones is provided, which relates to a field of artificial intelligence, in particular to fields of speech technology, natural language processing, speech interaction, etc., and may be used in Internet of vehicles, autonomous driving, and other scenarios. A specific implementation scheme includes: acquiring N channels of audio signals, wherein each channel of audio signal corresponds to one of N speech zones; inputting, based on a corresponding relationship between the N channels of audio signals and N synchronous audio processing threads in a wake-up engine, each channel of audio signal into a corresponding audio processing thread; and determining, in response to a thread with a wake-up result occurring in the N synchronous audio processing threads, a speech zone corresponding to the thread with the wake-up result as an awakened speech zone in the N speech zones.

Abstract: Various disclosed embodiments are directed to estimating that a first vertex of a patch will change from a first position to a second position (the second position being at least partially indicative of secondary motion) based at least in part on one or more features of: primary motion data, one or more material properties, and constraint data associated with the particular patch. Such estimation can be made for some or all of the patches of an entire volumetric mesh in order to accurately predict the overall secondary motion of an object. This, among other functionality described herein resolves the inaccuracies, computer resource consumption, and the user experience of existing technologies.

Abstract: A method for TTS includes: acquiring, TTS tasks to be processed and software identifiers corresponding to the TTS tasks, on a terminal device; determining a current scene of the terminal device and priorities corresponding to the software identifiers in the current scene; acquiring a sorting result by sorting the TTS tasks based on the priorities corresponding to the software identifiers; and executing the TTS tasks based on the sorting result.

Abstract: The present disclosure provides a method for controlling a vehicle, an apparatus for controlling a vehicle, a device, a medium, and a program product, and relates to the field of artificial intelligence, such as deep learning, autonomous driving, and intelligent transport. An embodiment of the method includes: acquiring a traffic parameter of a target vehicle and traffic parameters of other vehicles; inputting the traffic parameter of the target vehicle into a pre-trained behavior predicting model to obtain a predicted behavior; determining a matching target driving behavior based on the traffic parameter of the target vehicle and the traffic parameters of the other vehicles; and controlling, in response to the predicted behavior mismatching the target driving behavior, the target vehicle to travel in accordance with a traffic parameter of the target driving behavior.

Abstract: Embodiments of the present disclosure include a federated learning method by a federated learning aggregator. The method may comprise creating a log of previously provided gradients from a plurality of workers, receiving updated gradients from the plurality of workers, calculating a vulnerability weight for each layer of a global machine learning model using the updated gradients, calculating an aggregated gradient using the vulnerability weight and the updated gradients, and updating the global machine learning model using the aggregated gradient. Some embodiments may also determine whether a Byzantine attack is occurring based upon the calculated aggregated gradient.

Abstract: An indication of availability over time and resource usage is maintained for each computing device of a plurality of computing devices. An optimal combination of a subset of the plurality of computing devices is determined for each round of one or more rounds of training based on the availability over time and the resource usage for each computing device. A global model is generated utilizing the one or more optimal combinations of the plurality of computing devices and a query is performed utilizing the global model.

Abstract: A method of processing a voice for a vehicle, a device, and a medium are provided, which relate to a field of voice recognition technology. The method of processing a voice for a vehicle includes: separating an initial voice data in response to receiving the initial voice data from a plurality of regions inside the vehicle, so as to obtain a plurality of voice sub-data and a description information for each voice sub-data of the plurality of voice sub-data, the plurality of voice sub-data correspond to the plurality of regions respectively, and the description information for each voice sub-data indicates the region corresponding to the each voice sub-data in the plurality of regions; and determining a voice working mode of the vehicle based on the plurality of voice sub-data.

Abstract: A whole vehicle in-loop test system of an intelligent automobile, including: a rotary drum platform, used for simulating a longitudinal movement of a test vehicle; an environment perception platform, disposed at a front end of the rotary drum platform, used for simulating a transverse movement of a test vehicle, and including a support base at a lower portion and a vehicle placing platform at an upper portion, where a transverse drive wheel is mounted at the lower portion of the support base, and the transverse drive wheel moves along a transverse track disposed on the ground; and a target vehicle simulation unit, disposed at a periphery of the environment perception platform, and configured to simulate a target vehicle.