Abstract: A communication method is provided. The method includes: A terminal device obtains an interruption period of the AI function, where the terminal device supports the artificial intelligence AI function, and the interruption period includes a start time point and interruption duration. The terminal device skips sending the first report to the network device within the interruption period according to a preconfigured rule, or sends a second report to the network device within the interruption period according to a preconfigured rule. The first report is associated with the AI function, and the second report is not associated with the AI function.

Abstract: This application provides a communication method and a communication apparatus. The method includes: A first device obtains a first function used to evaluate a resource consumed by a second device for executing an artificial intelligence AI model, and determines, based on the first function and information about a first AI model, a first resource consumed by the second device for executing the first AI model. The first device determines, based on the first resource, whether to send the first AI model or a manner of obtaining the first AI model to the second device. The first device evaluates, by using the first function, the resource consumed by the second device for executing the AI model, and determines, based on the resource consumed by the second device for executing the first AI model, whether to send the first AI model to the second device.

Abstract: This application relates to the field of communication technologies, and specifically, discloses a communication method, apparatus and system. The method includes: A first terminal device obtains first feature distribution information from a network device, and sends the first feature distribution information to a first server associated with the first terminal device. The first feature distribution information indicates feature distribution of data that is collected in a first time period by a terminal device located in a first region. In this way, after receiving the first feature distribution information, the first server can use the first feature distribution information as auxiliary information for generating an AI model, so that an AI model generated by the first server based on training data is close to an AI model generated based on total training data in the first region.

Abstract: This application provides a method and an apparatus for determining an artificial intelligence AI model. To construct, for a scenario, a scenario identifier corresponding to the scenario, in this application, an AI model corresponding to the scenario identifier can be quickly and accurately obtained. The method includes: A terminal device obtains a first identifier, where the first identifier indicates a first scenario. The terminal device obtains a first AI model, where the first AI model corresponds to the first scenario.

Abstract: A terminal device sends information to a network device, where the information indicates a capability that is of the terminal device to detect an interference signal and that is in multi-user multiple-input multiple-output pairing transmission. After the terminal device sends the information to the network device, the terminal device receives indication information from the network device, where the indication information indicates data transmission information of a second terminal device. The terminal device detects and eliminates the interference signal based on the indication information. According to the embodiments, the network device determines, based on the information, that the capability of the terminal device to detect the interference signal meets a preset condition, and sends the indication information to the terminal device.

Abstract: The technology of this application relates to an artificial intelligence algorithm model obtaining method that includes a network device determining N artificial intelligence algorithm models in M artificial intelligence algorithm models based on data feature information and M pieces of model feature information, and sending, to a terminal device, configuration information corresponding to at least one of the N artificial intelligence algorithm models. The M pieces of model feature information may correspond one-to-one to the M artificial intelligence algorithm models, the N artificial intelligence algorithm models are more suitable for processing data than remaining (M?N) artificial intelligence algorithm models of the M artificial intelligence algorithm models, an ith piece of model feature information in the M pieces of model feature information includes a feature of an ith artificial intelligence algorithm model, and the data feature information includes a feature of first data.

Abstract: An artificial intelligence AI communication method. A first apparatus receives AI model information sent by a second apparatus. The AI model information includes M groups of AI model complexity information corresponding to M AI models. Each of the M groups of AI model complexity information is time and/or energy consumption of executing one of the M AI models in each of N reference AI execution environments, wherein M and N are positive integers. The first apparatus sends feedback information to the second apparatus.

Abstract: Embodiments of this application provide a communication method and a communication apparatus. The communication method includes: A first apparatus receives first configuration information from a second apparatus, where the first configuration information indicates the first apparatus to send CSI reports in a hybrid mode of a first mode and a second mode. The first apparatus receives first information from the second apparatus, where the first information indicates the first apparatus to adjust a proportion of sending a CSI report in the first mode and/or a proportion of sending a CSI report in the second mode, and the first information is determined by the second apparatus based on first communication performance and second communication performance.

Abstract: Embodiments of this disclosure provide a channel state feedback method and apparatus. The method includes: A terminal device receives first indication information from a network device. The terminal device reduces a first value of first information to a second value based on the first indication information. The second value is used to determine channel state feedback information. The first information includes channel state indicator CQI information or signal-to-interference-plus-noise ratio SINR information. The channel state feedback information determined based on the second value is more accurate than channel state feedback information determined based on the first value. This can improve accuracy of the channel state feedback information.

Abstract: An information encoding control method includes: receiving first configuration information, where the first configuration information is used to configure N groups of parameters of N artificial intelligence (AI) encoders or an AI decider, and the AI decider is configured to determine an AI encoder that is in the N AI encoders and to which first information is applicable, and/or is configured to determine that none of the N AI encoders is applicable to encoding the first information; and sending first indication information to a network device, where the first indication information indicates that a first encoder is used for encoding the first information, the first encoder is determined based on the first configuration information and the first information, and the first encoder is an encoder in the N AI encoders, or is a second encoder different from the N AI encoders.

Abstract: This application provides an information transmission method and apparatus. The method includes: receiving first indication information from a network device, where the first indication information indicates an association relationship between a plurality of branch networks in an artificial intelligence AI network and channel state information CSI measurement configuration information; and obtaining first quantization information based on a first branch network and channel information, where the first branch network is associated with current CSI measurement configuration information, and the first branch network belongs to the plurality of branch networks in the AI network.

Abstract: This application provides a method. The method may include: a transmit-side device determines frequency-domain positions of reference signals that are used for phase noise estimation and that are on a plurality of resource blocks, where there are a plurality of reference signals on at least one resource block in the plurality of resource blocks, the reference signals occupy consecutive frequency-domain resources on the at least one resource block, for example, occupy a plurality of consecutive subcarriers; the transmit-side device maps, based on the frequency-domain positions of the reference signals on the plurality of resource blocks, the reference signals to one or more symbols, and sends, to a receive-side device, the one or more symbols to which the reference signals are mapped; and the receive-side device performs phase noise estimation based on the reference signals.

Abstract: The method includes: An access network device performs first encoding on a channel state information-reference signal CSI-RS, to generate first information, where the CSI-RS is used to obtain channel state information CSI corresponding to a channel between the access network device and a terminal device; the access network device sends the first information to the terminal device over N radio frequency links, where N is a positive integer; the access network device receives third information from the terminal device, where the third information is generated by the terminal device after the terminal device performs second encoding on second information, and the second information is determined by the terminal device based on the first information and the CSI-RS; and the access network device performs first decoding on the third information, to generate the CSI, where the first decoding includes decoding corresponding to the first encoding.

Abstract: An image processing method includes a first device extracting feature information of a to-be-processed image using a feature extraction network model; the first device identifying the extracted feature information to obtain identification information of the feature information; and the first device sending the feature information of the to-be-processed image and the identification information of the feature information to a second device. After receiving the feature information and the corresponding identification information that are sent by the first device, the second device selects a feature analysis network model corresponding to the identification information to process the received feature information.

Abstract: A method for soft switch call control and a soft switch device therefore are provided. The soft switch device acquires an initial address message (IAM) at a calling side, analyzes information of the calling party and the called party based on the acquired initial address message (IAM), and informs the media gateways to create a context and to add TDM semi-permanent physical terminations of time slots corresponding to the calling party and the called party into the context when the calling party and the called party are controlled by the same media gateway. Thus, it can implement a local loop of TDM voice, reduce IP loop of RTP streams and efficiently reduces network resources such as steps for digital signal processing, echo elimination and etc.

Abstract: Disclosed is a method, apparatus and computer-readable medium for selecting a root bridge when a spanning tree is configured in an Ethernet network including a plurality of legacy switches and a plurality of synchronous switches. The method comprises the steps of providing in advance identification information in a configuration BPDU message of the synchronous switch, the identification information representing that a corresponding switch is an AV switch, broadcasting configuration BPDU messages by the legacy switches and the synchronous switches; and receiving configuration BPDU messages by the synchronous switch from other switches, confirming bridge priorities according to the synchronous switches through the received configuration BPDU message and the identification information to select a synchronous root bridge, receiving configuration BPDU messages by the legacy switch from other switches, and confirming bridge priorities through the received configuration BPDU messages to select a legacy root bridge.

Abstract: Disclosed is a method for approval of a time-dependent stream input to a predetermined node in a residential Ethernet system, the method including the steps of receiving a transmission request of the time-dependent stream by the predetermined node, extracting a pacing parameter and a cycle number, which are a delay value of the predetermined node and a transmission period of the time-dependent stream, respectively, from the transmission-requested time-dependent stream, calculating a transmission bandwidth of an entire time-dependent stream to be transmitted through the predetermined node, by taking into consideration the pacing parameter and the cycle number, determining if the transmission bandwidth, which includes the transmission-requested time-dependent stream, satisfies a total transmission bandwidth based on the pacing parameter and the cycle number and determining whether to approve the transmission-requested time-dependent stream.

Abstract: A residential Ethernet node device for transmitting synchronous data uses a counter in a residential Ethernet system. The device includes a parser for receiving residential Ethernet data from external other node devices, and parsing the received Ethernet data as synchronous data and asynchronous data. An asynchronous switch switches and transmits the parsed asynchronous data. A synchronous switch switches and transmits the parsed synchronous data. A multiplexer is connected with the asynchronous switch and the synchronous switch, and multiplexes the asynchronous and synchronous data. A synchronous data band assignment unit for, by the count of a counter, indicating synchronous data bandwidth information determined from a synchronous data bandwidth reservation process, and transmitting the indicated bandwidth information to the multiplexer, thereby determining a multiplex position for synchronous data transmission.

Abstract: A Residential Ethernet switching apparatus for performing time slot switching includes an input unit for receiving frames as input, and a parser for parsing the received frames into asynchronous Ethernet frames (AsyncE frames) and Residential Ethernet frames (ResE frames). An AsyncE switching processor performs a switching operation for an AsyncE frame parsed by the parser. A ResE switching processor performs, according to positions of time slots included in a ResE frame parsed, a virtual MAC (VMAC) processing for the ResE frame The ResE switching processor also performs a switching operation based on a result of the VMAC processing. A multiplexer multiplexes the AsyncE frame switched by the AsyncE switching processor, and the ResE frame switched by the ResE switching processor, for output.

Abstract: A method for generating a super frame of a predetermined size in a a residential Ethernet system for separately transmitting isochronous data and asynchronous data includes the steps of: receiving by the residential Ethernet system the isochronous data and the asynchronous data to be transmitted through the residential Ethernet system; dividing the received isochronous data into a plurality of sub-frames according to synchronous links; inserting an Ethernet header into each of the sub-frames, thereby generating a plurality of isochronous packets; and employing a remaining area, which is obtained by excepting an area of the isochronous packets from the predetermined size, as an asynchronous packet area, and inserting asynchronous packets including the asynchronous data into the asynchronous packet area.