WO2024067281A1 - Ai模型的处理方法、装置及通信设备 - Google Patents

Ai模型的处理方法、装置及通信设备 Download PDF

Info

Publication number
WO2024067281A1
WO2024067281A1 PCT/CN2023/119939 CN2023119939W WO2024067281A1 WO 2024067281 A1 WO2024067281 A1 WO 2024067281A1 CN 2023119939 W CN2023119939 W CN 2023119939W WO 2024067281 A1 WO2024067281 A1 WO 2024067281A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
information
target
identifier
terminal
Prior art date
Application number
PCT/CN2023/119939
Other languages
English (en)
French (fr)
Inventor
杨昂
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2024067281A1 publication Critical patent/WO2024067281A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00—Arrangements affording multiple use of the transmission path
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to a processing method, device and communication equipment for an artificial intelligence (AI) model.
  • AI artificial intelligence
  • AI is currently widely used in various fields. There are many ways to implement AI models, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc.
  • the model is updated by transmitting the AI model.
  • this update method has a large network signaling overhead.
  • the embodiments of the present application provide an AI model processing method, device, and communication equipment to solve the problem of large network signaling overhead in the existing AI model update method.
  • a method for processing an AI model comprising:
  • the terminal acquires at least one AI model information, where the AI model information carries or is associated with a model identifier of the AI model, where the model identifier indicates, includes or is associated with first information, where the first information is used to represent information related to an environment in which the terminal is located, a working state of the terminal, or an operating parameter of the terminal;
  • the terminal activates, switches or updates a target AI model, and the model identifier of the target AI model indicates, includes or is associated with the first information related to the new environment, working state or operating parameters;
  • the terminal when the terminal identifies the model identifier of the target AI model, the terminal activates, switches or updates the target AI model, and the model identifier of the target AI model indicates, includes or is associated with the identification information of the terminal.
  • a processing device for an AI model comprising:
  • an acquisition module configured to acquire at least one AI model information, where the AI model information carries or is associated with a model identifier of the AI model, where the model identifier indicates, includes or is associated with first information, where the first information is used to represent information related to an environment in which the terminal is located, a working state of the terminal, or an operating parameter of the terminal;
  • a first processing module is used to activate, switch or update a target AI model when an environment or working state or operating parameter associated with the first information changes, wherein the model identifier of the target AI model indicates or includes or is associated with first information related to the new environment or working state or operating parameters;
  • the second processing module is used to activate, switch or update the target AI model when the terminal identifies the model identifier of the target AI model, and the model identifier of the target AI model indicates, includes or is associated with the identification information of the terminal.
  • a communication device comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.
  • a readable storage medium on which a program or instruction is stored.
  • the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.
  • a chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method described in the first aspect.
  • a computer program/program product is provided, wherein the computer program/program product is stored in a non-volatile storage medium, and the program/program product is executed by at least one processor to implement the steps of the method described in the first aspect.
  • a communication system comprising a terminal and a network side device, the terminal being used to execute the steps of the method described in the first aspect.
  • the terminal when the environment, working state, or operating parameters associated with the first information changes, or when the terminal recognizes the model identifier of the target AI model, the terminal can automatically activate, switch, or update the target AI model, saving system signaling overhead.
  • Figure 1 is a schematic diagram of a neural network
  • Figure 2 is a schematic diagram of a neuron
  • FIG3 is a schematic diagram of the architecture of a wireless communication system according to an embodiment of the present application.
  • FIG4 is a flow chart of a processing method of an AI model according to an embodiment of the present application.
  • FIG5 is a schematic diagram of a processing device of an AI model according to an embodiment of the present application.
  • FIG6 is a schematic diagram of a terminal according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a communication device according to an embodiment of the present application.
  • first, second, etc. in the specification and claims of this application are used to distinguish between similar environments or processes.
  • the term “first” or “second” is used to refer to an operating state or operating parameter, and is not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the environment or operating state or operating parameter distinguished by “first” and “second” is usually a class, and the number of environments or operating states or operating parameters is not limited.
  • the first environment or operating state or operating parameter can be one or more.
  • “and/or” in the specification and claims represents at least one of the connected environments or operating states or operating parameters, and the character “/" generally represents that the front and back associated environments or operating states or operating parameters are an "or” relationship.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR New Radio
  • 6G 6th Generation
  • This application uses a neural network as an example for illustration, but does not limit the specific type of AI module.
  • the structure of the neural network is shown in FIG1 .
  • the neural network is composed of neurons, and a schematic diagram of neurons is shown in Figure 2.
  • a 1 , a 2 , ... a K are inputs
  • w is the weight (multiplicative coefficient)
  • b is the bias (additive coefficient)
  • ⁇ (.) is the activation function
  • z a 1 w 1 + ... + a k w k + ... + a K w K + b.
  • Common activation functions include Sigmoid function, tanh function, Rectified Linear Unit (ReLU), etc.
  • the parameters of a neural network can be optimized using an optimization algorithm.
  • An optimization algorithm is a type of algorithm that can minimize or maximize an objective function (sometimes called a loss function).
  • the objective function is often a mathematical combination of model parameters and data. For example, given data x and its corresponding label Y, a neural network model f(.) is constructed. With the model, the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated. This is the loss function. If suitable w and b are found to minimize the value of the above loss function, the smaller the loss value, the closer the model is to the actual situation.
  • BP error back propagation
  • the basic idea of the BP algorithm is that the learning process consists of two processes: forward propagation of the signal and back propagation of the error.
  • forward propagation the input sample is passed from the input layer, processed by each hidden layer layer by layer, and then passed to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage.
  • Error back propagation is to convert the output error into a certain value.
  • the error is propagated back through the hidden layer to the input layer layer by layer, and the error is apportioned to all units in each layer, thereby obtaining the error signal of each layer unit, which is used as the basis for correcting the weight of each unit.
  • This process of adjusting the weights of each layer with forward propagation of signals and reverse propagation of errors is repeated over and over again.
  • the process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the preset number of learning times is reached.
  • the selected AI algorithms and models vary depending on the type of solution.
  • the main way to improve the network performance of the fifth generation mobile communication technology (5th Generation, 5G) with the help of AI is to enhance or replace existing algorithms or processing modules through algorithms and models based on neural networks.
  • algorithms and models based on neural networks can achieve better performance than those based on deterministic algorithms.
  • the more commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks.
  • FIG3 shows a block diagram of a wireless communication system applicable to the embodiment of the present application.
  • the wireless communication system includes a terminal 31 and a network side device 32 .
  • the terminal 31 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR)/virtual reality (virtual reality, VR) device , robots, wearable devices (Wearable Device), vehicle user equipment (VUE), pedestrian user equipment (PUE), smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), game consoles, personal computers (personal computers, PCs), teller machines or self-service machines and other terminal-side devices, wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wrist
  • the terminal involved in this application can also be a chip in the terminal, such as a modem chip, a system-on-chip (SoC). It should be noted that the specific type of terminal 31 is not limited in the embodiment of this application.
  • the network side device 32 may include an access network device or a core network device, wherein the access network device may also be referred to as a wireless Wireless access network equipment, radio access network (Radio Access Network, RAN), radio access network function or radio access network unit.
  • Access network equipment may include base stations, WLAN access points or WiFi nodes, etc.
  • the base station may be called node B, evolved node B (Evolved Node B, eNB), access point, base transceiver station (Base Transceiver Station, BTS), radio base station, radio transceiver, basic service set (Basic Service Set, BSS), extended service set (Extended Service Set, ESS), home B node, home evolved B node, transmitting and receiving point (Transmitting Receiving Point, TRP) or other appropriate terms in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary, it should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.
  • the core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, mobility management entity (Mobility Management Entity, MME), access and mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unifie
  • the present invention relates to a plurality of network functions, including but not limited to: network access function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function (AF), non-3GPP interworking function (N3IWF), etc.
  • NRF network access function
  • NEF network exposure function
  • L-NEF local NEF
  • BSF binding support function
  • AF application function
  • an embodiment of the present application provides a method for processing an AI model, which is applied to a terminal.
  • the method includes: step 401, step 402 or step 403.
  • the specific steps are as follows:
  • Step 401 The terminal obtains at least one AI model information, where the AI model information carries or is associated with a model identifier (Identity, ID) of the AI model, where the model identifier indicates or includes or is associated with first information, where the first information is used to represent information related to an environment in which the terminal is located, a working state of the terminal, or an operating parameter of the terminal;
  • a model identifier Identity, ID
  • the model identifier indicates or includes or is associated with first information
  • the first information is used to represent information related to an environment in which the terminal is located, a working state of the terminal, or an operating parameter of the terminal;
  • the AI model information carrying the model ID of the AI model means that the AI model information can contain the model ID of the AI model, that is, the AI model information explicitly includes the model ID of the AI model; the AI model information is associated with the model ID of the AI model means that the AI model information and the model ID of the AI model have a mapping relationship, and after obtaining the AI model information, the terminal can determine the model ID of the AI model based on the AI model information and the mapping relationship, that is, the AI model information implicitly includes the model ID of the AI model.
  • the model ID indicating the first information means that the model ID is directly used to indicate the first information; the model ID containing the first information means that the model ID directly contains the first information; the model ID associated with the first information means that the model ID is associated with the first information.
  • One piece of information has a mapping relationship.
  • the first information includes one or more of the following: cell identifier; network operator identifier; network equipment vendor identifier; location information; channel quality information; partial bandwidth (Bandwidth Part, BWP) information; frequency information; public land mobile network (Public Land Mobile Network, PLMN) information; and timestamp information.
  • Step 402 When the environment, working state or operating parameter associated with the first information changes, the terminal activates, switches or updates a target AI model, and the model identifier of the target AI model indicates, includes or is associated with the first information related to the new environment, working state or operating parameter;
  • the environment or working state or operating parameter may include but is not limited to at least one of the following: a cell, a service area of a network operator, a service area of a network equipment provider, a location area, a channel quality interval, a BWP, a working frequency, a PLMN, a time interval, etc. It is understandable that when the terminal moves or the working state of the terminal changes or the environment of the terminal changes, the above environment or working state or operating parameter will change.
  • the first information related to the new environment or working state or operating parameters refers to the mapping relationship between the new environment or working state or operating parameters and the first information.
  • the first information related to the new environment refers to the cell identifier of the new cell.
  • the first information related to the new environment refers to the identifier of the network operator in the service area of the new network operator.
  • the first information related to the new environment refers to the network equipment vendor identifier of the service area of the new network equipment vendor.
  • the first information related to the new environment refers to the location information of the new location area.
  • the new working state or operating parameters are new
  • the first information related to the new working state or operating parameter refers to the channel quality information of the new channel quality interval.
  • the new working state or operating parameter is a new BWP
  • the first information related to the new working state or operating parameter refers to the BWP information of the new BWP.
  • the new working state or operating parameter is a new working frequency
  • the first information related to the new working state or operating parameter refers to the frequency information of the new working frequency.
  • the first information related to the new working state or operating parameter refers to the PLMN information of the new PLMN.
  • the new operating parameter is a new time interval
  • the first information related to the new operating parameter refers to the timestamp information of the new time interval.
  • the terminal activates the target AI model means that the terminal activates the target AI model that was previously in an inactivated state, so that the terminal can use the target AI model;
  • the terminal switches the AI model means that the terminal switches from the current AI model to the target AI model, so that the terminal can use the target AI model;
  • the terminal updates the target AI model means that the terminal updates the AI model to obtain the target AI model, wherein updating the AI model may include but is not limited to updating the AI model information of the AI model or the model ID of the AI model.
  • the model identifier of the AI model can indicate, include or be associated with the first information.
  • the terminal can automatically activate, switch or update the target AI model, thereby improving the environmental intelligence of the AI model and saving system signaling overhead.
  • Step 403 When the terminal identifies the model identifier of the target AI model, the terminal activates, switches or updates the target AI model, and the model identifier of the target AI model indicates, includes or is associated with the identifier of the terminal. information.
  • the terminal identifying the model identifier of the target AI model in step 403 means that the terminal can correctly parse and obtain the model identifier of the target AI model. For example, the terminal obtains the model identifier of the target AI model, and then parses and obtains all information or implicit information of the model identifier. Since the model identifier of the target AI model indicates or contains or is associated with the identification information of the terminal, the terminal can understand that the target AI model is an AI model that can be used by the terminal. At this time, the terminal can activate, switch or update the target AI model.
  • the identification information includes one or more of the following: a terminal identification; a terminal equipment vendor identification.
  • the model identifier of the AI model can indicate, include or be associated with the first information.
  • the terminal can automatically activate, switch or update the target AI model, thereby improving the environmental intelligence of the AI model and saving system signaling overhead.
  • the terminal obtains at least one AI model information, including: the terminal receives at least one AI model information sent by a first node, and the first node includes at least one of the following: (1) core network equipment, such as network data analysis function (Network Data Analytics Function, NWDAF), location management function (Location Management Function, LMF) or neural network processing node, etc., (2) access network equipment, such as base station or newly defined neural network processing node, (3) third-party equipment, such as OTT (over the top) server.
  • NWDAF Network Data Analytics Function
  • LMF Location Management Function
  • OTT over the top server.
  • the first node sends or broadcasts at least one AI model information to the terminal.
  • the terminal obtains at least one AI model information, including: the terminal obtains the at least one AI model information locally, that is, the terminal can carry at least one AI model information.
  • the terminal updates and obtains a target AI model
  • the model identifier of the target AI model indicates or includes or is associated with first information related to a new environment or working state or operating parameter, including:
  • the terminal updates the first information indicated or included or associated by the model identifier of the target AI model to the first information related to the new environment, working state or operating parameters; or, the terminal obtains the target AI model through the first AI model update, the target AI model is a new AI model, and the model identifier of the target AI model indicates or includes or is associated with the first information related to the new environment, working state or operating parameters, wherein the first AI model can be understood as the AI model currently used by the terminal, that is, the AI model currently used by the terminal is updated to the target AI model, and the first AI model can also be referred to as the source AI model during the AI model update process.
  • the first information indicated, included or associated by the model identifier of the first AI model remains unchanged.
  • the terminal can update the target AI model in two ways:
  • Mode 1 The terminal updates the parameters of the currently used AI model to obtain a target AI model.
  • the target AI model is regarded as the same AI model as the currently used AI model, and the first information indicated, included or associated with the model identifier of the target AI model is updated to the first information related to the new environment or working state or operating parameters (or described as the first information in the current situation);
  • Method 2 The terminal updates the parameters of the currently used AI model to obtain a target AI model, where the target AI model is a new AI model.
  • the model identifier of the target AI model indicates, includes, or is associated with first information related to the new environment, working state, or operating parameters (or is described as the first information in the current situation).
  • the first information indicated, included, or associated with the model identifier of the AI model before the update remains unchanged.
  • the cell identifier includes at least one of the following: a physical cell identifier; a serving cell identifier; a transmission and receiving point (TRP) identifier; a tracking area identifier; a cell group identifier; and a reference signal identifier associated with the cell.
  • TRP transmission and receiving point
  • the terminal when the environment, working state, or operating parameter associated with the first information changes, the terminal activates or switches the target AI model, including at least one of the following:
  • the first information is a cell identifier.
  • the terminal moves to a new cell, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the cell identifier of the new cell;
  • the first information is an identifier of a network operator.
  • the terminal moves to a service area of a new network operator, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the identifier of the new network operator.
  • the first information is a network equipment vendor identifier.
  • the terminal moves to a service area of a new network equipment vendor, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the new network equipment vendor identifier;
  • the first information is a network equipment vendor identifier.
  • the terminal moves to a service area of a new network equipment vendor, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the new network equipment vendor identifier;
  • the first information is location information.
  • the terminal moves to a new location area, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the location information of the new location area;
  • the first information is channel quality information
  • the terminal activates or switches a target AI model, and a model identifier of the target AI model indicates, includes, or is associated with the channel quality information of the new channel quality interval;
  • the channel quality information may include but is not limited to at least one of the following: signal-to-noise ratio (Signal to Noise Ratio, SNR), reference signal received power (Reference Signal Receiving Power, RSRP), signal to interference plus noise ratio (Signal to Interference plus Noise Ratio, SINR) and reference signal received quality (Reference Signal Receiving Quality, RSRQ).
  • SNR Signal-to-noise ratio
  • RSRP Reference Signal Receiving Power
  • SINR Signal to Interference plus Noise Ratio
  • RSRQ Reference Signal Receiving Quality
  • the first information is BWP information.
  • the terminal When the terminal switches to a new BWP, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the BWP information of the new BWP;
  • the first information is frequency information.
  • the terminal When the terminal switches to a new operating frequency, the terminal The terminal activates or switches a target AI model, wherein the model identifier of the target AI model indicates or includes or is associated with frequency information of the new operating frequency;
  • the first information is PLMN information.
  • the terminal moves to a new PLMN, the terminal activates or switches a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the PLMN information of the new PLMN;
  • the first information is timestamp information.
  • the terminal When the terminal operates in a new time interval, the terminal activates or switches the target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the timestamp information of the new time interval.
  • the terminal when the environment, working state, or operating parameter associated with the first information changes, the terminal activates, switches, or updates a target AI model, and the model identifier of the target AI model indicates, includes, or is associated with the first information related to the new environment, working state, or operating parameter, including:
  • the terminal activates or switches the target AI model, and the first information indicated or contained or associated by the model identifier of the target AI model best matches (or is closest to) the first information related to the current environment, working state or operating parameters.
  • the first information is a cell identifier
  • the cell identifier indicated or contained or associated by the model identifier of the current AI model of the terminal does not match the cell identifier of the current cell.
  • the AI model whose corresponding cell identifier in the AI model most closely matches (or is closest to) the cell identifier of the current cell is used as the target AI model, and the target AI model is activated or switched.
  • the first information is the network operator's identifier
  • the model identifier of the terminal's current AI model indicates or contains or is associated with a network operator identifier that does not match the current network operator's identifier.
  • the AI model whose corresponding network operator identifier in the AI model most closely matches (or is closest to) the current network operator's identifier is used as the target AI model, and the target AI model is activated or switched.
  • the first information is the network equipment vendor identifier
  • the model identifier of the current AI model of the terminal indicates or contains or is associated with a network equipment vendor identifier that does not match the identifier of the current network device.
  • the AI model in the AI model whose corresponding network equipment vendor identifier most closely matches (or is closest to) the identifier of the current network equipment vendor is used as the target AI model, and the target AI model is activated or switched.
  • the first information is channel quality information
  • the channel quality information indicated or contained or associated by the model identifier of the current AI model of the terminal does not match the channel quality information of the current channel quality.
  • the AI model whose corresponding channel quality information in the AI model most closely matches (or is closest to) the channel information of the current channel quality is used as the target AI model, and the target AI model is activated or switched.
  • the AI model update condition, or the AI model activation or switching condition includes at least one of the following:
  • a second condition wherein the second condition includes that the terminal obtains a first indication, and the first indication is used to indicate deactivation of the current AI model, for example, the terminal, the network side or other node indicates deactivation of the current AI model, wherein when The previous AI model refers to the AI model currently used by the terminal;
  • a third condition wherein the third condition includes that the terminal obtains a second indication, where the second indication is used to indicate a new AI model, for example, the terminal, the network side, or other nodes indicate the new AI model.
  • the AI model includes a first functional module, and the first functional module is used for at least one of the following:
  • signal processing including but not limited to at least one of the following: signal detection, filtering, equalization, etc.
  • the signal includes but is not limited to at least one of the following: demodulation reference signal (DMRS), sounding reference signal (SRS), synchronization signal block (Synchronization Signal and PBCH block, SSB), tracking reference signal (TRS), phase tracking reference signals (PTRS), channel state information reference signal (CSI-RS), etc.;
  • DMRS demodulation reference signal
  • SRS sounding reference signal
  • SSB synchronization signal block
  • TRS tracking reference signal
  • PTRS phase tracking reference signals
  • CSI-RS channel state information reference signal
  • channel transmission, channel reception, channel demodulation or channel transmission where the channel includes but is not limited to at least one of the following: Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (PUSCH), Physical Random Access Channel (PRACH), Physical Broadcast Channel (PBCH);
  • PDCCH Physical Downlink Control Channel
  • PDSCH Physical Downlink Shared Channel
  • PUCCH Physical Uplink Control Channel
  • PUSCH Physical Uplink Shared Channel
  • PRACH Physical Broadcast Channel
  • PBCH Physical Broadcast Channel
  • channel state information feedback includes but is not limited to at least one of the following: channel-related information, channel matrix-related information, channel characteristic information, channel matrix characteristic information, precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CSI-RS Resource Indicator, CRI), channel quality indicator (CQI), layer indicator (LI), etc.
  • PMI precoding matrix indicator
  • RI rank indicator
  • CSI-RS resource indicator CSI-RS Resource Indicator
  • CQI channel quality indicator
  • LI layer indicator
  • Another example is the partial reciprocity of uplink and downlink in frequency division multiplexing (FDD).
  • FDD frequency division multiplexing
  • the base station obtains angle and delay information based on the uplink channel, and can notify the terminal of the angle and delay information through CSI-RS precoding or direct indication.
  • the terminal reports according to the indication of the base station or selects and reports within the indication range of the base station, thereby reducing the terminal's calculation workload and the CSI reporting overhead.
  • beam management including but not limited to at least one of the following: beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, and new beam indication during beam failure recovery;
  • channel prediction including but not limited to at least one of the following: prediction of channel state information and beam prediction;
  • Interference suppression including but not limited to at least one of the following: intra-cell interference, inter-cell interference, out-of-band interference, and intermodulation interference;
  • Positioning such as estimating the specific position (including horizontal position and/or vertical position) or possible future trajectory of the terminal through a reference signal (such as SRS), or estimating information of auxiliary position estimation or trajectory estimation of the terminal;
  • predicting or managing high-level services and/or high-level parameters including but not limited to at least one of the following: throughput, required packet size, service demand, mobile speed, noise information, etc.;
  • control signaling including but not limited to at least one of the following: power control related signaling, beam management related signaling.
  • the terminal when the environment, working status, or operating parameters associated with the first information changes, or when the terminal recognizes the model identifier of the target AI model, the terminal can automatically activate, switch, or update the target AI model, thereby improving the environmental intelligence of the AI model and saving system signaling overhead.
  • an embodiment of the present application provides an AI model processing device, which is applied to a terminal.
  • the device 500 includes: an acquisition module 501 , and a first processing module 502 or a second processing module 503 .
  • An acquisition module 501 is used to acquire at least one AI model information, where the AI model information carries or is associated with a model identifier of the AI model, where the model identifier indicates, includes or is associated with first information, where the first information is used to represent information related to an environment in which the terminal is located, a working state of the terminal, or an operating parameter of the terminal;
  • a first processing module 502 is used to activate, switch or update a target AI model when the environment, working state or operating parameters associated with the first information change, wherein the model identifier of the target AI model indicates, includes or is associated with the first information related to the new environment, working state or operating parameters;
  • the second processing module 503 is used to activate, switch or update the target AI model when the terminal identifies the model identifier of the target AI model, and the model identifier of the target AI model indicates, includes or is associated with the identification information of the terminal.
  • the acquisition module 501 is further used to: receive at least one AI model information sent by a first node, wherein the first node includes: at least one of a core network device, an access network device, and a third-party device; or, obtain the at least one AI model information locally.
  • the first processing module 502 is further configured to:
  • the terminal obtains the target AI model through the first AI model update, the target AI model is a new AI model, and the model identifier of the target AI model indicates, includes or is associated with the first information related to the new environment, working state or operating parameters.
  • the first information indicated, included or associated by the model identifier of the first AI model remains unchanged.
  • the first information includes one or more of the following: cell identifier; network operator identifier; network equipment vendor identifier; location information; channel quality information; BWP information; frequency information; PLMN information; and timestamp information.
  • the cell identifier includes at least one of the following: a physical cell identifier; a serving cell identifier; a TRP identifier; a tracking area identifier; a cell group identifier; and a reference signal identifier associated with the cell.
  • the first processing module 502 is further configured to perform at least one of the following:
  • the first information is a cell identifier, and when the terminal moves to a new cell, a target AI model is activated or switched, and the model identifier of the target AI model indicates, includes or is associated with the cell identifier of the new cell;
  • the first information is the identifier of the network operator.
  • the target AI model is activated or switched, and the model identifier of the target AI model indicates or includes or is associated with the new network operator identifier;
  • the first information is a network equipment vendor identifier.
  • the target AI model is activated or switched, and the model identifier of the target AI model indicates, includes, or is associated with the new network equipment vendor identifier.
  • the first information is location information.
  • a target AI model is activated or switched, and a model identifier of the target AI model indicates, includes or is associated with the location information of the new location area;
  • the first information is channel quality information, and when the channel quality of the terminal is in a new channel quality interval, the target AI model is activated or switched, and the model identifier of the target AI model indicates or includes or is associated with the channel quality information of the new channel quality interval;
  • the first information is BWP information.
  • a target AI model is activated or switched.
  • the model identifier of the target AI model indicates, includes or is associated with BWP information of the new BWP.
  • the first information is frequency information.
  • the target AI model is activated or switched, and the model identifier of the target AI model indicates, includes or is associated with the frequency information of the new operating frequency;
  • the first information is PLMN information.
  • a target AI model is activated or switched, and a model identifier of the target AI model indicates or includes or is associated with PLMN information of the new PLMN;
  • the first information is timestamp information.
  • the target AI model is activated or switched, and the model identifier of the target AI model indicates, includes or is associated with the timestamp information of the new time interval.
  • the first processing module 502 is further used to: when the conditions for activating or switching the AI model are met, and the first information indicated or contained or associated by the model identifier of the current AI model of the terminal does not match the first information related to the current environment, working state or operating parameters, the terminal activates or switches the target AI model, and the first information indicated or contained or associated by the model identifier of the target AI model is the most matched (or closest) to the first information related to the current environment, working state or operating parameters.
  • the AI model update condition, or the AI model activation or switching condition includes at least one of the following:
  • a first condition wherein the first condition includes that the performance of the current AI model does not meet the requirements of the terminal;
  • a second condition wherein the second condition includes that the terminal obtains a first indication, where the first indication is used to instruct to deactivate the current AI model;
  • the third condition includes that the terminal obtains a second indication, and the second indication is used to indicate a new AI model.
  • the identification information includes one or more of the following: a terminal identification; a terminal equipment vendor identification.
  • the AI model includes a first functional module, and the first functional module is used for at least one of the following:
  • the device provided in the embodiment of the present application can implement each process implemented by the method embodiment of Figure 4 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • Fig. 6 is a schematic diagram of the hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 600 includes but is not limited to: a radio frequency unit 601, a network module 602, an audio output unit 603, an input unit 604, a sensor 605, a display unit 606, a user input unit 607, an interface unit 608, a memory 609, and at least some of the components in the processor 610.
  • the terminal 600 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 610 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system.
  • a power source such as a battery
  • the terminal structure shown in FIG6 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.
  • the input unit 604 may include a graphics processing unit (GPU) 6041 and a microphone 6042, and the graphics processor 6041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode.
  • the display unit 606 may include a display panel 6061, and the display panel 6061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 607 includes a touch panel 6071 and at least one of other input devices 6072.
  • the touch panel 6071 is also called a touch screen.
  • the touch panel 6071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 6072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.
  • the RF unit 601 after receiving downlink data from the network side device, can transmit the data to the processor 610 for processing; in addition, the RF unit 601 can send uplink data to the network side device.
  • the RF unit 601 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • the memory 609 can be used to store software programs or instructions and various data.
  • the memory 609 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc.
  • the memory 609 may include a volatile memory or a non-volatile memory, or the memory 609 may include both volatile and non-volatile memories.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.
  • the volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM).
  • the memory 609 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
  • the processor 610 may include one or more processing units; optionally, the processor 610 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 610.
  • the terminal provided in the embodiment of the present application can implement each process implemented by the method embodiment of Figure 4 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • an embodiment of the present application also provides a communication device 700, including a processor 701 and a memory 702, and the memory 702 stores programs or instructions that can be executed on the processor 701.
  • the communication device 700 is a terminal
  • the program or instruction is executed by the processor 701 to implement the various steps of the method embodiment of Figure 4 above and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored.
  • a program or instruction is stored.
  • the method of Figure 4 and the various processes of the above-mentioned embodiments are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
  • the processor is the processor in the terminal described in the above embodiment.
  • the readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.
  • An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes shown in Figure 4 and the various method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
  • the embodiments of the present application further provide a computer program/program product, which is stored in a storage medium, and is executed by at least one processor to implement the various processes shown in FIG. 4 and in the various method embodiments described above, and can achieve the same technical effect. To avoid repetition, it will not be described here.
  • An embodiment of the present application further provides a communication system, which includes a terminal and a network-side device.
  • the terminal is used to execute the various processes as shown in Figure 4 and the above-mentioned method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.) to execute the methods described in each embodiment of the present application.
  • a storage medium such as ROM/RAM, magnetic disk, optical disk
  • a terminal which can be a mobile phone, computer, server, air conditioner, or network equipment, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Neurology (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种AI模型的处理方法、装置及通信设备，该方法包括：终端获取至少一个AI模型信息，AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；或者，在所述终端识别目标AI模型的模型标识的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。

Description

AI模型的处理方法、装置及通信设备
相关申请的交叉引用
本申请主张在2022年9月26日在中国提交的中国专利申请No.202211177514.5的优先权，其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域，具体涉及一种人工智能(Artificial Intelligence，AI)模型的处理方法、装置及通信设备。
背景技术
AI目前在各个领域获得了广泛的应用。AI模型有多种实现方式，例如神经网络、决策树、支持向量机、贝叶斯分类器等。
相关技术中通过传输AI模型进行模型更新，然而这种更新方式网络信令开销较大。
发明内容
本申请实施例提供一种AI模型的处理方法、装置及通信设备，解决现有的AI模型更新方式网络信令开销较大的问题。
第一方面，提供一种AI模型的处理方法，包括：
终端获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；
在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；
或者，在所述终端识别目标AI模型的模型标识的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。
第二方面，提供一种AI模型的处理装置，包括：
获取模块，用于获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；
第一处理模块，用于在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，激活或切换或更新目标AI模型，所述目标AI模型的模型标识指示或包含或关联 与新环境或工作状态或者运行参数相关的第一信息；
或者，第二处理模块，用于在所述终端识别目标AI模型的模型标识的情况下，激活或切换或更新目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。
第三方面，提供了一种通信设备，包括：处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第四方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤。
第五方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法的步骤。
第六方面，提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在非瞬态的存储介质中，所述程序/程序产品被至少一个处理器执行以实现如第一方面所述的方法的步骤。
第七方面，提供一种通信***，所述通信***包括终端与网络侧设备，所述终端用于执行如第一方面所述的方法的步骤。
在本申请实施例中，在第一信息关联的环境或工作状态或者运行参数发生变化的情况下，或者在终端识别目标AI模型的模型标识的情况下，终端可以自动激活或切换或更新得到目标AI模型，节省***信令开销。
附图说明
图1为神经网络的示意图；
图2为神经元的示意图；
图3为本申请实施例的无线通信***的架构示意图；
图4为本申请实施例的AI模型的处理方法的流程图；
图5为本申请实施例的AI模型的处理装置的示意图；
图6为本申请实施例的终端的示意图；
图7为本申请实施例的通信设备的示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的环境或工 作状态或者运行参数，而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”所区别的环境或工作状态或者运行参数通常为一类，并不限定环境或工作状态或者运行参数的个数，例如第一环境或工作状态或者运行参数可以是一个，也可以是多个。此外，说明书以及权利要求中“和/或”表示所连接环境或工作状态或者运行参数的至少其中之一，字符“/”一般表示前后关联环境或工作状态或者运行参数是一种“或”的关系。
值得指出的是，本申请实施例所描述的技术不限于长期演进型(Long Term Evolution，LTE)/LTE的演进(LTE-Advanced，LTE-A)***，还可用于其他无线通信***，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access，SC-FDMA)和其他***。本申请实施例中的术语“***”和“网络”常被可互换地使用，所描述的技术既可用于以上提及的***和无线电技术，也可用于其他***和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)***，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR***应用以外的应用，如第6代(6th Generation，6G)通信***。
为了便于理解本申请的实施方式，下面先介绍以下技术点。
1、关于神经网络的介绍
本申请以神经网络为例进行说明，但是并不限定AI模块的具体类型，神经网络的结构如图1所示。
其中，神经网络由神经元组成，神经元的示意图如图2所示。其中a1,a2,…aK为输入，w为权值(乘性系数)，b为偏置(加性系数)，σ(.)为激活函数，z＝a1w1+…+akwk+…+aKwK+b。常见的激活函数包括Sigmoid函数、tanh函数、修正线性单元(Rectified Linear Unit，ReLU)等等。
神经网络的参数可以通过优化算法进行优化。优化算法就是一种能够最小化或者最大化目标函数(有时候也叫损失函数)的一类算法。而目标函数往往是模型参数和数据的数学组合。例如给定数据x和其对应的标签Y，构建一个神经网络模型f(.)，有了模型后，根据输入x就可以得到预测输出f(x)，并且可以计算出预测值和真实值之间的差距(f(x)-Y)，这个就是损失函数。如果找到合适的w和b使上述的损失函数的值达到最小，损失值越小，则说明模型越接近于真实情况。
目前常见的优化算法，基本都是基于误差反向传播(error Back Propagation，BP)算法。BP算法的基本思想是，学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时，输入样本从输入层传入，经各隐藏层逐层处理后，传向输出层。若输出层的实际输出与期望的输出不符，则转入误差的反向传播阶段。误差反传是将输出误差以某种 形式通过隐藏层向输入层逐层反传，并将误差分摊给各层的所有单元，从而获得各层单元的误差信号，此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程，是周而复始地进行的。权值不断调整的过程，也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度，或进行到预先设定的学习次数为止。
一般而言，根据解决类型不同，选取的AI算法和采用的模型也有所差别。根据相关技术，借助AI提升第五代移动通信技术(5th Generation，5G)网络性能的主要方法是通过基于神经网络的算法和模型增强或者替代目前已有的算法或处理模块。在特定场景下，基于神经网络的算法和模型可以取得比基于确定性算法更好的性能。比较常用的神经网络包括深度神经网络、卷积神经网络和循环神经网络等。借助已有AI工具，可以实现神经网络的搭建、训练与验证工作。
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent，SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、Nesterov(发明者的名字，具体为带动量的随机梯度下降)、自适应梯度下降(Adaptive Gradient Descent，AdaGrad)、自适应调整梯度下降(Adaptive Delta Gradient Descent，AdaDelta)、均方根误差降速(Root Mean Square prop，RMSprop)、自适应动量估计(Adaptive Moment Estimation，Adam)等。
这些优化算法在误差反向传播时，都是根据损失函数得到的误差/损失，对当前神经元求导数/偏导，加上学习速率、之前的梯度/导数/偏导等影响，得到梯度，将梯度传给上一层。
图3示出本申请实施例可应用的一种无线通信***的框图。无线通信***包括终端31和网络侧设备32。
其中，终端31可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer，UMPC)、移动上网装置(Mobile Internet Device，MID)、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(Vehicle User Equipment，VUE)、行人终端(Pedestrian User Equipment，PUE)、智能家居(具有无线通信功能的家居设备，如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer，PC)、柜员机或者自助机等终端侧设备，可穿戴式设备包括：智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。除了上述终端设备，本申请涉及的终端也可以是终端内的芯片，例如调制解调器(Modem)芯片，***级芯片(System on Chip，SoC)。需要说明的是，在本申请实施例并不限定终端31的具体类型。
网络侧设备32可以包括接入网设备或核心网设备，其中，接入网设备也可以称为无 线接入网设备、无线接入网(Radio Access Network，RAN)、无线接入网功能或无线接入网单元。接入网设备可以包括基站、WLAN接入点或WiFi节点等，基站可被称为节点B、演进节点B(Evolved Node B，eNB)、接入点、基收发机站(Base Transceiver Station，BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set，BSS)、扩展服务集(Extended Service Set，ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point，TRP)或所述领域中其他某个合适的术语，只要达到相同的技术效果，所述基站不限于特定技术词汇，需要说明的是，在本申请实施例中仅以NR***中的基站为例进行介绍，并不限定基站的具体类型。
核心网设备可以包含但不限于如下至少一项：核心网节点、核心网功能、移动管理实体(Mobility Management Entity，MME)、接入和移动管理功能(Access and Mobility Management Function，AMF)、会话管理功能(Session Management Function，SMF)、用户平面功能(User Plane Function，UPF)、策略控制功能(Policy Control Function，PCF)、策略与计费规则功能单元(Policy and Charging Rules Function，PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function，EASDF)、统一数据管理(Unified Data Management，UDM)，统一数据仓储(Unified Data Repository，UDR)、归属用户服务器(Home Subscriber Server，HSS)、集中式网络配置(Centralized network configuration，CNC)、网络存储功能(Network Repository Function，NRF)，网络开放功能(Network Exposure Function，NEF)、本地NEF(Local NEF，或L-NEF)、绑定支持功能(Binding Support Function，BSF)、应用功能(Application Function，AF)、非3GPP互通功能(Non-3GPP Inter Working Function，N3IWF)等。需要说明的是，在本申请实施例中仅以NR***中的核心网设备为例进行介绍，并不限定核心网设备的具体类型。
下面结合附图，通过一些实施例及其应用场景对本申请实施例提供的AI模型的处理方法、装置、通信设备及可读存储介质进行详细地说明。
参见图4，本申请实施例提供一种AI模型的处理方法，应用于终端，该方法包括：步骤401、步骤402或步骤403，具体步骤如下：
步骤401：终端获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识(Identity，ID)，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；
其中，AI模型信息携带AI模型的模型ID是指该AI模型信息中可以包含AI模型的模型ID，即AI模型信息显式包含AI模型的模型ID；AI模型信息关联AI模型的模型ID是指该AI模型信息与AI模型的模型ID具有映射关系，终端在获取该AI模型信息之后，可以基于AI模型信息和映射关系，确定AI模型的模型ID，即AI模型信息隐式包含AI模型的模型ID。
其中，模型ID指示第一信息是指该模型ID直接用于指示第一信息；模型ID包含第一信息是指该模型ID中直接包含该第一信息；模型ID关联第一信息是指该模型ID与第 一信息有映射关系。
在本申请的一种实施方式中，所述第一信息包括以下一项或多项：小区标识；网络运营商的标识；网络设备商标识；位置信息；信道质量信息；部分带宽(Bandwidth Part，BWP)信息；频率信息；公共陆地移动网(Public Land Mobile Network，PLMN)信息；时间戳信息。
步骤402：在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；
其中，环境或工作状态或者运行参数可以包括但不限于以下至少一项：小区、网络运营商的服务区域、网络设备商的服务区域、位置区域、信道质量区间、BWP、工作频率、PLMN、时间区间等。可以理解的是，在终端发生移动或者终端的工作状态发生变化或者终端的环境发生变化时，会引起上述环境或工作状态或者运行参数发生变化。
其中，新环境或工作状态或者运行参数相关的第一信息是指新环境或工作状态或者运行参数与第一信息具有映射关系，比如，新环境为新小区时，新环境相关的第一信息是指新小区的小区标识，又比如，新环境为新网络运营商的服务区域时，新环境相关的第一信息是指新新网络运营商的服务区域的网络运营商的标识，又比如，新环境为新网络设备商的服务区域时，新环境相关的第一信息是指新网络设备商的服务区域的网络设备商标识，又比如，新环境为新位置区域时，新环境相关的第一信息是指新位置区域的位置信息，又比如，新工作状态或者运行参数为新信道质量区间时，新工作状态或者运行参数相关的第一信息是指新信道质量区间的信道质量信息，又比如，新工作状态或者运行参数为新BWP时，新工作状态或者运行参数相关的第一信息是指新BWP的BWP信息，又比如，新工作状态或者运行参数为新工作频率时，新工作状态或者运行参数相关的第一信息是指新工作频率的频率信息，又比如，新工作状态或者运行参数为新PLMN时，新工作状态或者运行参数相关的第一信息是指新PLMN的PLMN信息，又比如，新运行参数为新时间区间时，新运行参数相关的第一信息是指新时间区间的时间戳信息。
其中，终端激活目标AI模型是指终端将之前处于非激活态的目标AI模型进行激活，使得终端可以使用该目标AI模型；终端切换AI模型是指终端由当前AI模型切换到目标AI模型，使得终端可以使用该目标AI模型；终端更新得到目标AI模型是指对终端对AI模型进行更新，得到目标AI模型，其中，对AI模型进行更新可以包括但不限于对AI模型的AI模型信息或者AI模型的模型ID进行更新。
在本实施例中，AI模型的模型标识能够指示或包含或关联第一信息，在第一信息关联的环境或工作状态或者运行参数发生变化的情况下，终端可以自动激活或切换或更新得到目标AI模型，从而提升AI模型的环境智能化，节省***信令开销。
步骤403：在所述终端识别目标AI模型的模型标识的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识 信息。
步骤403中的终端识别目标AI模型的模型标识是指终端能够正确解析得到目标AI模型的模型标识，比如终端获取目标AI模型的模型标识，然后解析得到该模型标识的所有信息或隐含信息，由于该目标AI模型的模型标识指示或包含或关联该终端的标识信息，因此终端可以理解为该目标AI模型是该终端可以使用的AI模型，此时该终端可以激活或切换或更新得到目标AI模型。
在本申请的一种实施方式中，所述标识信息包括以下一项或多项：终端标识；终端设备商标识。
在本实施例中，AI模型的模型标识能够指示或包含或关联第一信息，在所述终端识别目标AI模型的模型标识的情况下，终端可以自动激活或切换或更新得到目标AI模型，从而提升AI模型的环境智能化，节省***信令开销。
在本申请的一种实施方式中，所述终端获取至少一个AI模型信息，包括：所述终端接收第一节点发送的至少一个AI模型信息，所述第一节点包括以下至少一项：(1)核心网设备，比如网络数据分析功能(Network Data Analytics Function，NWDAF)，位置管理功能(Location Management Function，LMF)或神经网络处理节点等，(2)接入网设备，比如基站或新定义的神经网络处理节点，(3)第三方设备，比如，OTT(over the top)服务器。
比如，第一节点向终端发送或广播至少一个AI模型信息。
在本申请的另一种实施方式中，所述终端获取至少一个AI模型信息，包括：所述终端从本地获取所述至少一个AI模型信息，也就是终端可以自带至少一个AI模型信息。
在本申请的一种实施方式中，所述终端更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息，包括：
在满足AI模型更新条件的情况下，所述终端将所述目标AI模型的模型标识指示或包含或关联的第一信息更新为与新环境或工作状态或者运行参数相关的第一信息；或者，所述终端通过第一AI模型更新得到目标AI模型，所述目标AI模型为新的AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息，其中，第一AI模型可以理解为终端当前使用的AI模型，即将终端当前使用的AI模型更新为目标AI模型，在AI模型更新过程中该第一AI模型也可以称为源AI模型。
在本申请的一种实施方式中，第一AI模型的模型标识指示或包含或关联的第一信息不变。
也就是，终端更新得到目标AI模型的方式可以包括两种：
方式1：终端对当前使用的AI模型的参数进行更新得到目标AI模型，该目标AI模型与当前使用的AI模型视为同一个AI模型，该目标AI模型的模型标识指示或包含或关联的第一信息更新为与新环境或工作状态或者运行参数相关的第一信息(或者描述为当前情况下的第一信息)；
方式2：终端对当前使用的AI模型的参数进行更新得到目标AI模型，该目标AI模型为新的AI模型，该目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息(或者描述为当前情况下的第一信息)，可选地，更新前的AI模型的模型标识指示或包含或关联的第一信息不变。
在本申请的一种实施方式中，所述小区标识包括以下至少一项：物理小区标识；服务小区标识；传输接收点(Transmission and Receiving Point，TRP)标识；跟踪区标识；小区组标识；与小区关联的参考信号标识。
在本申请的一种实施方式中，在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换目标AI模型，包括以下至少一项：
(1)所述第一信息为小区标识，在所述终端移动到新小区的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新小区的小区标识；
(2)所述第一信息为网络运营商的标识，在所述终端移动到新的网络运营商的服务区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的网络运营商标识；
(3)所述第一信息为网络设备商标识，在所述终端移动到新网络设备商的服务区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新网络设备商标识；
(4)所述第一信息为网络设备商标识，在所述终端移动到新网络设备商的服务区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新网络设备商标识；
(5)所述第一信息为位置信息，在所述终端移动到新位置区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新位置区域的位置信息；
(6)所述第一信息为信道质量信息，在所述终端的信道质量位于新信道质量区间的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新信道质量区间的信道质量信息；
其中，信道质量信息可以包括但不限于以下至少一项：信噪比(Signal to Noise Ratio，SNR)、参考信号接收功率(Reference Signal Receiving Power，RSRP)、信号与干扰加噪声比(Signal to Interference plus Noise Ratio，SINR)和参考信号接收质量(Reference Signal Receiving Quality，RSRQ)。
(7)所述第一信息为BWP信息，在所述终端切换到新BWP的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联新BWP的BWP信息；
(8)所述第一信息为频率信息，在所述终端切换到新的工作频率的情况下，所述终 端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的工作频率的频率信息；
(9)所述第一信息为PLMN信息，在所述终端移动到新PLMN的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新PLMN的PLMN信息；
(10)所述第一信息为时间戳信息，在所述终端工作在新时间区间的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新时间区间的时间戳信息。
在本申请的一种实施方式中，所述在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息，包括：
在满足激活或切换AI模型条件，且所述终端的当前AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息不匹配的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息最匹配(或者最接近)。
例如，第一信息为小区标识，终端的当前AI模型的模型标识指示或包含或关联的小区标识与当前小区的小区标识不匹配的情况，将AI模型中对应小区标识相对最匹配(或者最接近)当前小区的小区标识的AI模型作为目标AI模型，激活或切换该目标AI模型。
又例如，第一信息为网络运营商的标识，终端的当前AI模型的模型标识指示或包含或关联的网络运营商的标识与当前网络运营商的标识不匹配的情况，将AI模型中对应网络运营商的标识相对最匹配(或者最接近)当前网络运营商的标识的AI模型作为目标AI模型，激活或切换该目标AI模型。
又例如，第一信息为网络设备商标识，终端的当前AI模型的模型标识指示或包含或关联的网络设备商标识与当前网络设备的标识不匹配的情况，将AI模型中对应网络设备商标识相对最匹配(或者最接近)当前网络设备商的标识的AI模型作为目标AI模型，激活或切换该目标AI模型。
又例如，所述第一信息为信道质量信息，终端的当前AI模型的模型标识指示或包含或关联的信道质量信息与当前信道质量的信道质量信息不匹配的情况，将AI模型中对应信道质量信息相对最匹配(或者最接近)当前信道质量的信道信息的AI模型作为目标AI模型，激活或切换该目标AI模型。
在本申请的一种实施方式中，所述AI模型更新条件，或者，所述激活或切换AI模型条件，包括以下至少一项：
(1)第一条件，所述第一条件包括当前AI模型的性能不满足所述终端的需求；
(2)第二条件，所述第二条件包括所述终端获取到第一指示，所述第一指示用于指示去激活当前AI模型，比如，终端、网络侧或其他节点指示当前AI模型去激活，其中当 前AI模型是指终端当前使用的AI模型；
(3)第三条件，所述第三条件包括所述终端获取到第二指示，所述第二指示用于指示新的AI模型，比如，终端、网络侧或其他节点指示新的AI模型。
在本申请的一种实施方式中，所述AI模型包括第一功能模块，所述第一功能模块用于以下至少一项：
(1)信号处理，包括但不限于以下至少一项：信号检测、滤波、均衡等，其中信号包括但不限于以下至少一项：解调参考信号(Demodulation Reference Signal，DMRS)、探测参考信号(Sounding Reference Signal，SRS)、同步信号块(Synchronization Signal and PBCH block，SSB)、跟踪参考信号(Tracking Reference Signal，TRS)、相位跟踪参考信号(Phase-tracking reference signals，PTRS)、信道状态信息参考信号(Channel-State-Information Reference Signal，CSI-RS)等；
(2)信道传输、信道接收、信道解调或信道发送，其中信道包括但不限于以下至少一项：物理下行控制信道(Physical Downlink Control Channel，PDCCH)、物理下行共享信道(Physical Downlink Shared Channel，PDSCH)、物理上行控制信道(Physical Uplink Control Channel，PUCCH)、物理上行共享信道(Physical Uplink Shared Channel，PUSCH)、物理随机接入信道(Physical Random Access Channel，PRACH)、物理广播信道(Physical Broadcast Channel，PBCH)；
(3)处理信道状态信息；
比如，信道状态信息反馈，包括但不限于以下至少一项：信道相关信息、信道矩阵相关信息、信道特征信息、信道矩阵特征信息、预编码矩阵指示(Precoding matrix indicator，PMI)、秩指示(Rank indicator，RI)、CSI-RS资源指示(CSI-RS Resource Indicator，CRI)、信道质量指示(Channel quality indicator，CQI)、层指示(Layer Indicator，LI)等。
又比如，频分复用(Frequency Division Duplex，FDD)上下行部分互易性。对于FDD***，根据部分互异性，基站根据上行信道获取角度和时延信息，可以通过CSI-RS预编码或者直接指示的方法，将角度信息和时延信息通知终端，终端根据基站的指示上报或者在基站的指示范围内选择并上报，从而减少终端的计算量和CSI上报的开销。
(4)波束管理，包括但不限于以下至少一项：波束测量、波束上报、波束预测、波束失败检测、波束失败恢复、波束失败恢复中的新波束指示；
(5)信道预测，包括但不限于以下至少一项：信道状态信息的预测、波束预测；
(6)干扰抑制，包括但不限于以下至少一项：小区内干扰、小区间干扰、带外干扰、交调干扰等；
(7)定位，比如通过参考信号(例如SRS)，估计出终端的具***置(包括水平位置和/或垂直位置)或未来可能的轨迹，或估计出终端的辅助位置估计或轨迹估计的信息；
(8)预测或管理高层业务和/或高层参数，包括但不限于以下至少一项：吞吐量、所需数据包大小、业务需求、移动速度、噪声信息等；
(9)解析控制信令，包括但不限于以下至少一项：功率控制的相关信令，波束管理的相关信令。
在本申请实施例中，在第一信息关联的环境或工作状态或者运行参数发生变化的情况下，或者在终端识别目标AI模型的模型标识的情况下，终端可以自动激活或切换或更新得到目标AI模型，从而提升AI模型的环境智能化，节省***信令开销。
参见图5，本申请实施例提供一种AI模型的处理装置，应用于终端，装置500包括：获取模块501、以及第一处理模块502或第二处理模块503。
获取模块501，用于获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；
第一处理模块502，用于在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；
第二处理模块503，用于在所述终端识别目标AI模型的模型标识的情况下，激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。
在本申请的一种实施方式中，获取模块501进一步用于：接收第一节点发送的至少一个AI模型信息，所述第一节点包括：核心网设备、接入网设备、第三方设备中的至少一项；或者，从本地获取所述至少一个AI模型信息。
在本申请的一种实施方式中，第一处理模块502进一步用于：
在满足AI模型更新条件的情况下，将所述目标AI模型的模型标识指示或包含或关联的第一信息更新为与新环境或工作状态或者运行参数相关的第一信息；或者，所述终端通过第一AI模型更新得到目标AI模型，所述目标AI模型为新的AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息。
在本申请的一种实施方式中，所述第一AI模型的模型标识指示或包含或关联的第一信息不变。
在本申请的一种实施方式中，所述第一信息包括以下一项或多项：小区标识；网络运营商的标识；网络设备商标识；位置信息；信道质量信息；BWP信息；频率信息；PLMN信息；时间戳信息。
在本申请的一种实施方式中，所述小区标识包括以下至少一项：物理小区标识；服务小区标识；TRP标识；跟踪区标识；小区组标识；与小区关联的参考信号标识。
在本申请的一种实施方式中，第一处理模块502进一步用于执行以下至少一项：
所述第一信息为小区标识，在所述终端移动到新小区的情况下激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新小区的小区标识；
所述第一信息为网络运营商的标识，在所述终端移动到新的网络运营商的服务区域的 情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的网络运营商标识；
所述第一信息为网络设备商标识，在所述终端移动到新网络设备商的服务区域的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新网络设备商标识；
所述第一信息为位置信息，在所述终端移动到新位置区域的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新位置区域的位置信息；
所述第一信息为信道质量信息，在所述终端的信道质量位于新信道质量区间的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新信道质量区间的信道质量信息；
所述第一信息为BWP信息，在所述终端切换到新BWP的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联新BWP的BWP信息；
所述第一信息为频率信息，在所述终端切换到新的工作频率的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的工作频率的频率信息；
所述第一信息为PLMN信息，在所述终端移动到新PLMN的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新PLMN的PLMN信息；
所述第一信息为时间戳信息，在所述终端工作在新时间区间的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新时间区间的时间戳信息。
在本申请的一种实施方式中，第一处理模块502进一步用于：在满足激活或切换AI模型条件，且所述终端的当前AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息不匹配的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息最匹配(或者最接近)。
在本申请的一种实施方式中，所述AI模型更新条件，或者，所述激活或切换AI模型条件，包括以下至少一项：
第一条件，所述第一条件包括当前AI模型的性能不满足所述终端的需求；
第二条件，所述第二条件包括所述终端获取到第一指示，所述第一指示用于指示去激活当前AI模型；
第三条件，所述第三条件包括所述终端获取到第二指示，所述第二指示用于指示新的AI模型。
在本申请的一种实施方式中，所述标识信息包括以下一项或多项：终端标识；终端设备商标识。
在本申请的一种实施方式中，所述AI模型包括第一功能模块，所述第一功能模块用于以下至少一项：
信号处理；
信道传输、信道接收、信道解调或信道发送；
处理信道状态信息；
波束管理；
信道预测；
干扰抑制；
定位；
预测或管理高层业务和/或高层参数；
解析控制信令。
本申请实施例提供的装置能够实现图4的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
图6为实现本申请实施例的一种终端的硬件结构示意图。该终端600包括但不限于：射频单元601、网络模块602、音频输出单元603、输入单元604、传感器605、显示单元606、用户输入单元607、接口单元608、存储器609以及处理器610等中的至少部分部件。
本领域技术人员可以理解，终端600还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理***与处理器610逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。图6中示出的终端结构并不构成对终端的限定，终端可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
应理解的是，本申请实施例中，输入单元604可以包括图形处理单元(Graphics Processing Unit，GPU)6041和麦克风6042，图形处理器6041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元606可包括显示面板6061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板6061。用户输入单元607包括触控面板6071以及其他输入设备6072中的至少一种。触控面板6071，也称为触摸屏。触控面板6071可包括触摸检测装置和触摸控制器两个部分。其他输入设备6072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。
本申请实施例中，射频单元601接收来自网络侧设备的下行数据后，可以传输给处理器610进行处理；另外，射频单元601可以向网络侧设备发送上行数据。通常，射频单元601包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器609可用于存储软件程序或指令以及各种数据。存储器609可主要包括存储程序或指令的第一存储区和存储数据的第二存储区，其中，第一存储区可存储操作***、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器609可以包括易失性存储器或非易失性存储器，或者，存储器609可以包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。 易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synch link DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本申请实施例中的存储器609包括但不限于这些和任意其它适合类型的存储器。
处理器610可包括一个或多个处理单元；可选地，处理器610集成应用处理器和调制解调处理器，其中，应用处理器主要处理涉及操作***、用户界面和应用程序等的操作，调制解调处理器主要处理无线通信信号，如基带处理器。可以理解的是，上述调制解调处理器也可以不集成到处理器610中。
本申请实施例提供的终端能够实现图4的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
可选地，如图7所示，本申请实施例还提供一种通信设备700，包括处理器701和存储器702，存储器702上存储有可在所述处理器701上运行的程序或指令，例如，该通信设备700为终端时，该程序或指令被处理器701执行时实现上述图4方法实施例的各个步骤且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现图4方法及上述各个实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现图4所示及上述各个方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为***级芯片，***芯片，芯片***或片上***芯片等。
本申请实施例另提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现图4所示及上述各个方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例另提供一种通信***，所述通信***包括终端与网络侧设备，所述终端用于执行如图4及上述各个方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他 性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (19)

  1. 一种人工智能AI模型的处理方法，包括：
    终端获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与所述终端所处环境或工作状态或者运行参数相关的信息；
    在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；
    或者，在所述终端识别目标AI模型的模型标识的情况下，所述终端激活或切换或更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。
  2. 根据权利要求1所述的方法，其中，所述终端获取至少一个AI模型信息，包括：
    所述终端接收第一节点发送的至少一个AI模型信息，所述第一节点包括：核心网设备、接入网设备、第三方设备中的至少一项；
    或者，
    所述终端从本地获取所述至少一个AI模型信息。
  3. 根据权利要求1所述的方法，其中，所述终端更新得到目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息，包括：
    在满足AI模型更新条件的情况下，所述终端将所述目标AI模型的模型标识指示或包含或关联的第一信息更新为与新环境或工作状态或者运行参数相关的第一信息；或者，所述终端通过第一AI模型更新得到目标AI模型，所述目标AI模型为新的AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息。
  4. 根据权利要求3所述的方法，其中，所述第一AI模型的模型标识指示或包含或关联的第一信息不变。
  5. 根据权利要求1所述的方法，其中，所述第一信息包括以下一项或多项：小区标识；网络运营商的标识；网络设备商标识；位置信息；信道质量信息；部分带宽BWP信息；频率信息；公共陆地移动网PLMN信息；时间戳信息。
  6. 根据权利要求5所述的方法，其中，所述小区标识包括以下至少一项：物理小区标识；服务小区标识；传输接收点TRP标识；跟踪区标识；小区组标识；与小区关联的参考信号标识。
  7. 根据权利要求5所述的方法，其中，在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换目标AI模型，包括以下至少一项：
    所述第一信息为小区标识，在所述终端移动到新小区的情况下，所述终端激活或切换 目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新小区的小区标识；
    所述第一信息为网络运营商的标识，在所述终端移动到新的网络运营商的服务区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的网络运营商标识；
    所述第一信息为网络设备商标识，在所述终端移动到新网络设备商的服务区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新网络设备商标识；
    所述第一信息为位置信息，在所述终端移动到新位置区域的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新位置区域的位置信息；
    所述第一信息为信道质量信息，在所述终端的信道质量位于新信道质量区间的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新信道质量区间的信道质量信息；
    所述第一信息为BWP信息，在所述终端切换到新BWP的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联新BWP的BWP信息；
    所述第一信息为频率信息，在所述终端切换到新的工作频率的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的工作频率的频率信息；
    所述第一信息为PLMN信息，在所述终端移动到新PLMN的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新PLMN的PLMN信息；
    所述第一信息为时间戳信息，在所述终端工作在新时间区间的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新时间区间的时间戳信息。
  8. 根据权利要求1所述的方法，其中，所述在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，所述终端激活或切换或更新目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息，包括：
    在满足激活或切换AI模型条件，且所述终端的当前AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息不匹配的情况下，所述终端激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联的第一信息与所述当前环境或工作状态或者运行参数相关的第一信息最匹配。
  9. 根据权利要求3或8所述的方法，其中，所述AI模型更新条件，或者，所述激活或切换AI模型条件，包括以下至少一项：
    第一条件，所述第一条件包括当前AI模型的性能不满足所述终端的需求；
    第二条件，所述第二条件包括所述终端获取到第一指示，所述第一指示用于指示去激活当前AI模型；
    第三条件，所述第三条件包括所述终端获取到第二指示，所述第二指示用于指示新的AI模型。
  10. 根据权利要求1所述的方法，其中，所述终端的标识信息包括以下一项或多项：终端标识；终端设备商标识。
  11. 根据权利要求1所述的方法，其中，所述AI模型包括第一功能模块，所述第一功能模块用于以下至少一项：
    信号处理；
    信道传输、信道接收、信道解调或信道发送；
    处理信道状态信息；
    波束管理；
    信道预测；
    干扰抑制；
    定位；
    预测或管理高层业务和/或高层参数；
    解析控制信令。
  12. 一种AI模型的处理装置，包括：
    获取模块，用于获取至少一个AI模型信息，所述AI模型信息携带或关联AI模型的模型标识，所述模型标识指示或包含或关联第一信息，所述第一信息用于表示与终端所处环境或所述终端的工作状态或者所述终端的运行参数相关的信息；
    第一处理模块，用于在所述第一信息关联的环境或工作状态或者运行参数发生变化的情况下，激活或切换或更新目标AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息；
    或者，第二处理模块，用于在终端识别目标AI模型的模型标识的情况下，激活或切换或更新目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述终端的标识信息。
  13. 根据权利要求12所述的装置，其中，所述获取模块进一步用于：接收第一节点发送的至少一个AI模型信息，所述第一节点包括：核心网设备、接入网设备、第三方设备中的至少一项；或者，从本地获取所述至少一个AI模型信息。
  14. 根据权利要求12所述的装置，其中，所述第一处理模块进一步用于：
    在满足AI模型更新条件的情况下，将所述目标AI模型的模型标识指示或包含或关联的第一信息更新为与新环境或工作状态或者运行参数相关的第一信息；或者，更新目标AI模型，所述目标AI模型为新的AI模型，所述目标AI模型的模型标识指示或包含或关联与新环境或工作状态或者运行参数相关的第一信息。
  15. 根据权利要求12所述的装置，其中，所述第一处理模块进一步用于以下至少一项：
    所述第一信息为小区标识，在所述终端移动到新小区的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新小区的小区标识；
    所述第一信息为网络运营商的标识，在所述终端移动到新的网络运营商的服务区域的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的网络运营商标识；
    所述第一信息为网络设备商标识，在所述终端移动到新网络设备商的服务区域的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新网络设备商标识；
    所述第一信息为位置信息，在所述终端移动到新位置区域的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新位置区域的位置信息；
    所述第一信息为信道质量信息，在所述终端的信道质量位于新信道质量区间的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新信道质量区间的信道质量信息；
    所述第一信息为BWP信息，在所述终端切换到新BWP的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联新BWP的BWP信息；
    所述第一信息为频率信息，在所述终端切换到新的工作频率的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新的工作频率的频率信息；
    所述第一信息为PLMN信息，在所述终端移动到新PLMN的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新PLMN的PLMN信息；
    所述第一信息为时间戳信息，在所述终端工作在新时间区间的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联所述新时间区间的时间戳信息。
  16. 根据权利要求12所述的装置，其中，所述第一处理模块进一步用于：
    在满足激活或切换AI模型条件，且所述终端的当前AI模型的模型标识指示或包含或关联的第一信息与当前环境或工作状态或者运行参数相关的第一信息不匹配的情况下，激活或切换目标AI模型，所述目标AI模型的模型标识指示或包含或关联的第一信息与所述当前环境或工作状态或者运行参数相关的第一信息最匹配。
  17. 一种通信设备，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至11中任一项所述的方法的步骤。
  18. 一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1至11中任一项所述的方法的步骤。
  19. 一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如权利要求1至11中任一项所述的方法的步骤。
PCT/CN2023/119939 2022-09-26 2023-09-20 Ai模型的处理方法、装置及通信设备 WO2024067281A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211177514.5A CN117835262A (zh) 2022-09-26 2022-09-26 Ai模型的处理方法、装置及通信设备
CN202211177514.5 2022-09-26

Publications (1)

Publication Number Publication Date
WO2024067281A1 true WO2024067281A1 (zh) 2024-04-04

Family

ID=90476183

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/119939 WO2024067281A1 (zh) 2022-09-26 2023-09-20 Ai模型的处理方法、装置及通信设备

Country Status (2)

Country Link
CN (1) CN117835262A (zh)
WO (1) WO2024067281A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112399499A (zh) * 2019-08-16 2021-02-23 ***通信有限公司研究院 一种信息处理方法、切换控制方法、服务网络设备及终端
CN113498137A (zh) * 2020-04-08 2021-10-12 华为技术有限公司 获取小区关系模型、推荐小区切换指导参数的方法及装置
CN114666875A (zh) * 2020-12-23 2022-06-24 维沃移动通信有限公司 上行定位处理方法及相关设备
WO2022188855A1 (zh) * 2021-03-12 2022-09-15 维沃移动通信有限公司 路径切换方法、装置、终端及存储介质
CN116017493A (zh) * 2021-10-21 2023-04-25 维沃移动通信有限公司 模型请求方法、模型请求处理方法及相关设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112399499A (zh) * 2019-08-16 2021-02-23 ***通信有限公司研究院 一种信息处理方法、切换控制方法、服务网络设备及终端
CN113498137A (zh) * 2020-04-08 2021-10-12 华为技术有限公司 获取小区关系模型、推荐小区切换指导参数的方法及装置
CN114666875A (zh) * 2020-12-23 2022-06-24 维沃移动通信有限公司 上行定位处理方法及相关设备
WO2022188855A1 (zh) * 2021-03-12 2022-09-15 维沃移动通信有限公司 路径切换方法、装置、终端及存储介质
CN116017493A (zh) * 2021-10-21 2023-04-25 维沃移动通信有限公司 模型请求方法、模型请求处理方法及相关设备

Also Published As

Publication number Publication date
CN117835262A (zh) 2024-04-05

Similar Documents

Publication Publication Date Title
WO2023066288A1 (zh) 模型请求方法、模型请求处理方法及相关设备
WO2023040887A1 (zh) 信息上报方法、装置、终端及可读存储介质
WO2024067281A1 (zh) Ai模型的处理方法、装置及通信设备
WO2024067280A1 (zh) 更新ai模型参数的方法、装置及通信设备
WO2024125525A1 (zh) Ai算力上报方法、终端及网络侧设备
WO2024032695A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024032694A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024067434A1 (zh) Rs配置方法、装置、终端及网络侧设备
WO2023040885A1 (zh) 参数选择方法、参数配置方法、终端及网络侧设备
WO2024067665A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024093713A1 (zh) 资源配置方法、装置、通信设备及可读存储介质
WO2023103911A1 (zh) 测量方法、装置、设备及存储介质
WO2023040888A1 (zh) 数据传输方法及装置
WO2023179540A1 (zh) 信道预测方法、装置及无线通信设备
WO2024120409A1 (zh) Ai网络模型的确定方法、信息传输方法、装置和通信设备
WO2023155839A1 (zh) Ai模型的在线学习方法、装置、通信设备及可读存储介质
WO2023125951A1 (zh) 通信模型配置方法、装置和通信设备
WO2024099091A1 (zh) 波束预测方法、装置、终端、网络侧设备及存储介质
WO2024008111A1 (zh) 数据采集方法及装置
WO2024099094A1 (zh) 波束测量方法、装置、终端、网络侧设备及存储介质
WO2023186099A1 (zh) 信息反馈方法、装置及设备
WO2024083004A1 (zh) Ai模型配置方法、终端及网络侧设备
US20240224082A1 (en) Parameter selection method, parameter configuration method, terminal, and network side device
WO2023186091A1 (zh) 样本确定方法、装置及设备
WO2024125391A2 (zh) Ai模型监测方法、ai模型性能的测量方法、装置及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23870513

Country of ref document: EP

Kind code of ref document: A1