WO2024149156A1 - Procédé et appareil de transmission d'informations, et terminal et dispositif côté réseau - Google Patents

Procédé et appareil de transmission d'informations, et terminal et dispositif côté réseau Download PDF

Info

Publication number
WO2024149156A1
WO2024149156A1 PCT/CN2024/070706 CN2024070706W WO2024149156A1 WO 2024149156 A1 WO2024149156 A1 WO 2024149156A1 CN 2024070706 W CN2024070706 W CN 2024070706W WO 2024149156 A1 WO2024149156 A1 WO 2024149156A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
terminal
information
target
output
Prior art date
Application number
PCT/CN2024/070706
Other languages
English (en)
Chinese (zh)
Inventor
任千尧
谢天
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 WO2024149156A1 publication Critical patent/WO2024149156A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W76/00—Connection management
    • H04W76/10—Connection setup
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/02—Processing of mobility data, e.g. registration information at HLR [Home Location Register] or VLR [Visitor Location Register]; Transfer of mobility data, e.g. between HLR, VLR or external networks
    • H04W8/08—Mobility data transfer
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W80/00—Wireless network protocols or protocol adaptations to wireless operation
    • H04W80/06—Transport layer protocols, e.g. TCP [Transport Control Protocol] over wireless

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to an information transmission method, device, terminal and network side equipment.
  • AI artificial intelligence
  • communication data can be transmitted between network-side devices and terminals through AI network models.
  • Channel state information (CSI) compression based on AI models is divided into encoding models and decoding models.
  • the encoding model is on the terminal side and the decoding model is on the base station side. If the terminal does not have a decoding model, it cannot obtain the channel information recovered by the base station, and it cannot compare the original channel information with the recovered channel information. It is necessary to obtain the encoding model and the decoding model on one side at the same time to calculate the final inference result of the model. However, obtaining the encoding model and the decoding model on one side at the same time will cause a large transmission overhead between the terminal and the base station.
  • a method for transmitting information comprising:
  • the terminal acquires first information related to a target artificial intelligence AI unit, and obtains the target AI unit based on the first information;
  • the terminal obtains a first input and a first output of a first AI unit, inputs the first output into the target AI unit, and obtains a second output of the target AI unit;
  • the terminal obtains performance information of a second AI unit based on the first input and the second output, where the second AI unit is located in a network side device.
  • an information transmission method comprising:
  • the first information is used by the terminal to obtain the target AI unit, the terminal is used to input the first output of the first AI unit into the target AI unit, obtain the second output of the target AI unit, and obtain the performance information of the second AI unit based on the second output and the first input of the first AI unit, the first AI unit Located at the terminal, the second AI unit is located at the network side device.
  • an information transmission device comprising:
  • a first acquisition module configured to acquire first information related to a target AI unit, and obtain the target AI unit based on the first information
  • a second acquisition module configured to acquire a first input and a first output of a first AI unit, input the first output into the target AI unit, and acquire a second output of the target AI unit;
  • the third acquisition module is used to acquire performance information of a second AI unit based on the first input and the second output, where the second AI unit is located in a network side device.
  • a sending module configured to send first information related to a target AI unit to a terminal
  • the first information is used by the terminal to obtain the target AI unit, the terminal is used to input the first output of the first AI unit into the target AI unit, obtain the second output of the target AI unit, and obtain performance information of the second AI unit based on the second output and the first input of the first AI unit, the first AI unit is located in the terminal, and the second AI unit is located in the device.
  • a terminal comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.
  • a terminal comprising a processor and a communication interface, wherein the processor is used to obtain first information related to a target AI unit, and obtain the target AI unit based on the first information; obtain a first input and a first output of the first AI unit, input the first output into the target AI unit, and obtain a second output of the target AI unit, and obtain performance information of the second AI unit based on the first input and the second output, wherein the second AI unit is located in a network side device.
  • a network side device which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.
  • a network side device comprising a processor and a communication interface, wherein the communication interface is used to send first information related to a target AI unit to a terminal; wherein the first information is used by the terminal to obtain the target AI unit, and the terminal is used to input a first output of the first AI unit into the target AI unit, obtain a second output of the target AI unit, and obtain performance information of the second AI unit based on the second output and the first input of the first AI unit, wherein the first AI unit is located at the terminal, and the second AI unit is located at the network side device.
  • a communication system comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the information transmission method as described in the first aspect, and the network side device can be used to execute the steps of the information transmission method as described in the second aspect.
  • a readable storage medium wherein a program or instruction is stored on the readable storage medium, wherein the program When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second 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 method described in the first aspect, or to implement the method described in the second aspect.
  • a computer program product is provided, wherein the computer program product is stored in a storage medium, and the computer program product is executed by at least one processor to implement the method as described in the first aspect, or to implement the method as described in the second aspect.
  • the performance information of the second AI unit located in the network side device can be determined, and then the terminal can also know the degree of recovery of the channel characteristic information by the second AI unit. Therefore, when the terminal position, channel environment, etc.
  • the terminal can know the channel information recovered by the network side device based on the performance information of the second AI unit, which is more helpful for the transmission and processing of the channel information by the terminal and the network side device, and the terminal side can also know the performance of the second AI unit without obtaining the second AI unit of the network side device, which effectively saves the transmission overhead of the AI unit between the terminal and the network side device.
  • FIG1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied;
  • FIG2 is a flow chart of an information transmission method provided in an embodiment of the present application.
  • FIG3 is a flow chart of another information transmission method provided in an embodiment of the present application.
  • FIG4 is a structural diagram of an information transmission device provided in an embodiment of the present application.
  • FIG5 is a structural diagram of another information transmission device provided in an embodiment of the present application.
  • FIG6 is a structural diagram of a communication device provided in an embodiment of the present application.
  • FIG7 is a structural diagram of a terminal provided in an embodiment of the present application.
  • FIG8 is a structural diagram of a network side device provided in an embodiment of the present application.
  • first”, “second”, etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and "first”, “second”, etc. are not used to describe a specific order or sequence.
  • the object distinguished by “second” is usually a category, and the number of objects is not limited.
  • the first object can be one or more.
  • “and/or” in the specification and claims means at least one of the connected objects, and the character “/" generally means that the related objects are in 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
  • FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application.
  • the wireless communication system includes a terminal 11 and a network side device 12 .
  • the terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (AR)/virtual reality (VR) device, a robot, a wearable device (Wearable Device), a vehicle user equipment (VUE), a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (a home appliance with wireless communication function, such as a refrigerator, a television, a washing machine or furniture, etc.), a game console, a personal computer (personal computer, PC), a teller machine or a self-service machine and other terminal side devices, and the wearable device includes: a smart watch
  • the network side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network device, a radio access network (RAN), a radio access network function or a radio access network unit.
  • the access network device may include a base station, a wireless local area network (WLAN) access point or a WiFi node, etc.
  • WLAN wireless local area network
  • the base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home B node, a home evolved B node, a transmission reception 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 a 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 node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized Network Configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), Binding Support Function (BSF), Application Function (AF), etc.
  • MME mobility management entity
  • AMF Access and Mobility Management Function
  • UPF User Plane Function
  • PCF Policy Control Function
  • PCF Policy and Charging Rules Function
  • EASDF Edge Application Server Discovery Function
  • UDM Unified Data Management
  • UDR Unified Data Repository
  • HSS
  • the transmitter can optimize the signal transmission based on CSI to make it more compatible with the channel state.
  • the channel quality indicator CQI
  • MCS modulation and coding scheme
  • PMI precoding matrix indicator
  • MIMO multi-input multi-output
  • the base station sends a Channel State Information Reference Signal (CSI-RS) on certain time-frequency resources in a certain slot.
  • CSI-RS Channel State Information Reference Signal
  • the terminal performs channel estimation based on the CSI-RS, calculates the channel information on this time slot, and feeds back the PMI to the base station through the codebook.
  • the base station combines the channel information based on the codebook information fed back by the terminal, and uses this to perform data precoding and multi-user scheduling before the next CSI report.
  • the terminal can change the PMI reported for each subband to reporting the PMI according to the delay. Since the channels in the delay domain are more concentrated, the PMI of all subbands can be approximately represented by PMIs with fewer delays, that is, the delay domain information is compressed before reporting.
  • the base station can pre-code the CSI-RS in advance and send the encoded CSI-RS to the terminal.
  • the terminal sees the channel corresponding to the encoded CSI-RS.
  • the terminal only needs to select several ports with higher strength from the ports indicated by the network side and report the coefficients corresponding to these ports.
  • the terminal and the network side device may use a neural network or machine learning method to transmit the channel information.
  • the terminal compresses and encodes the channel information through the AI model, and the base station decodes the compressed content through the corresponding AI model to restore the channel information.
  • the AI model for decoding on the base station side and the AI model for encoding on the terminal side need to be jointly trained to achieve a reasonable match.
  • the input of the encoding AI model is the channel information
  • the output is the encoded information, that is, the channel characteristic information.
  • the input of the decoding AI model is the encoded information, and the output is the recovered channel information.
  • the main evaluation indicator of the AI model is the correlation between the input channel information and the recovered channel information. If the two are exactly the same, it means that the AI model has achieved perfect compression. Usually, the AI model can be considered effective if the correlation loss is within a certain degree. If the correlation loss exceeds the traditional non-AI method, such as the Type II codebook, the AI model can be replaced by the traditional codebook.
  • CSI compression based on AI models is divided into encoding AI models and decoding AI models.
  • the encoding AI model is on the terminal side
  • the decoding AI model is on the network side device. If the terminal does not have a decoding AI model, it will not be able to obtain the channel information restored by the network side device, and it will not be able to compare the original channel information with the restored channel information.
  • the terminal side needs to know both the encoding AI model and the decoding AI model to calculate the final inference result of the AI model; while for the network side device, it is necessary to obtain the original channel information before encoding on the terminal side, and combine it with the decoding result of its own decoding AI model to calculate the final inference result of the AI model.
  • the terminal side faces the following problems when knowing the complete AI model (encoding AI model and decoding AI model): 1. Due to the consideration of model privacy and compatibility, some model training collaboration methods (type2 or type3) do not support obtaining the encoding AI model and the decoding AI model at one end; 2.
  • an embodiment of the present application proposes an information transmission method.
  • Figure 2 is a flow chart of an information transmission method provided in an embodiment of the present application, and the method is applied to a terminal. As shown in Figure 2, the method includes the following steps:
  • Step 201 The terminal obtains first information related to a target AI unit, and obtains the target AI unit based on the first information.
  • AI unit described in the embodiments of the present application may also be called an AI model, AI structure, etc., or the AI unit may also refer to a processing unit that can implement specific algorithms, formulas, processing flows, etc. related to AI.
  • the embodiments of the present application do not make specific limitations on this.
  • the first AI unit involved in the embodiment of the present application may be an AI unit located on the terminal side for implementing the encoding function, which may also be referred to as an encoding model, an encoding AI model, an encoding AI structure, etc. in some scenarios.
  • the input of the first AI unit is the original channel information
  • the output is the encoded information after compression encoding by the first AI unit, or also referred to as channel feature information.
  • the second AI unit is an AI unit located on the network side device for implementing the decoding function, which may also be referred to as a decoding model, a decoding AI model, a decoding AI structure, etc. in some scenarios.
  • the input of the second AI unit is the output of the first AI unit, that is, the encoded information
  • the output of the second AI unit is the channel information recovered after decoding the encoded information.
  • the target AI unit may also be referred to as a target AI model, a target AI structure, etc.
  • the target AI unit can implement the same decoding function as the second AI unit, and can decode the input encoded information to output the recovered channel information.
  • the terminal obtains first information related to the target AI unit, and obtains the target AI unit based on the first information.
  • the first information may include weight parameters of the target AI unit
  • the terminal may determine the model structure information of the target AI unit based on a protocol agreement, or obtain the model structure information of the target AI unit from a third-party node (e.g., a manufacturer providing the target AI unit) in advance; further, the terminal can construct the target AI unit based on the weight parameters and model structure information of the target AI unit, thereby obtaining the target AI unit.
  • Step 202 The terminal obtains a first input and a first output of a first AI unit, inputs the first output into the target AI unit, and obtains a second output of the target AI unit.
  • the first AI unit is an AI unit located on the terminal side that can realize the encoding function.
  • the first input of the first AI unit is the original channel information
  • the first output is the encoded information output after being processed by the first AI unit, or channel characteristic information.
  • the terminal inputs the channel characteristic information into the target AI unit and obtains the output of the target AI unit, that is, the second output.
  • the target AI unit is used to realize the same decoding function as the second AI unit, and then the output of the target AI unit is the channel information recovered after decoding the output channel characteristic information.
  • Step 203 The terminal obtains performance information of a second AI unit based on the first input and the second output, where the second AI unit is located in a network side device.
  • the target AI unit is located on the terminal side, and the target AI unit can realize the same decoding function as the second AI unit, that is, it can simulate the decoding function of the second AI unit, and use the channel characteristic information output by the first AI unit as the input of the target AI unit, and then the target AI unit decodes the channel characteristic information to output the recovered channel information, that is, the second output.
  • the terminal can determine the performance information of the target AI unit based on the first input (that is, the original channel information) and the second output (that is, the recovered channel information output by the target AI unit) by comparing the first input and the second output, for example, comparing the similarity or correlation between the second output and the first input, and since the target AI unit can simulate the decoding function of the second AI unit, the performance information of the second AI unit can be determined based on the performance information of the target AI unit.
  • the performance information may include model loss information of the second AI unit, etc.
  • the performance information of the second AI unit located in the network side device can be determined, and then the terminal can also know the performance information of the second AI unit for the network side device.
  • the degree of recovery of channel characteristic information Therefore, when the terminal position, channel environment, etc.
  • the terminal can obtain the channel information recovered by the network side device based on the performance information of the second AI unit, which is more helpful for the terminal and the network side device to transmit and process the channel information, and the terminal side can also obtain the performance of the second AI unit without obtaining the second AI unit of the network side device, effectively saving the transmission overhead of the AI unit between the terminal and the network side device.
  • the target AI unit may have a smaller model structure and weight parameters than the second AI unit.
  • the target AI unit may be an AI unit obtained by proportionally scaling the second AI unit, and thus does not need to occupy a large space on the terminal side to ensure the compatibility of the target AI unit in the terminal.
  • the first information includes a weight parameter of the target AI unit and at least one of the following:
  • mapping relationship between the output of the target AI unit and the output of the second AI unit, and the input of the target AI unit matches the input of the second AI unit.
  • the first information includes weight parameters and model structure information of the target AI unit.
  • a network-side device or a third-party node may be pre-trained to obtain the target AI unit, and send the weight parameters and model structure information of the target AI unit to the terminal.
  • the terminal can construct the target AI unit based on the obtained weight parameters and model structure information of the target AI unit.
  • the input of the target AI unit matches the input of the second AI unit, for example, the inputs of the two are the same and are both the outputs of the first AI unit; or, the input of the target AI unit may be proportional to the input of the second AI unit, etc. It can be understood that both the target AI unit and the second AI unit are used to decode the input coded information to obtain the recovered channel information.
  • the first information may include the weight parameters of the target AI unit, and the mapping relationship between the output of the target AI unit and the output of the second AI unit.
  • the terminal constructs the target AI unit based on the weight parameters of the target AI unit and the model structure information (such as protocol agreement), it can determine the output of the second AI unit based on the output of the target AI unit based on the mapping relationship, thereby determining the performance of the second AI unit.
  • the model structure information such as protocol agreement
  • the terminal acquires first information related to the target AI unit, including:
  • the terminal obtains first information related to the target AI unit from a network side device or a third-party node.
  • the network side device may be pre-trained to obtain the target AI unit, and the first information may include weight parameters and model structure information of the target AI unit.
  • the network side device sends the first information to the terminal, that is, sends the complete target AI unit to the terminal, so that the terminal can directly decode and recover the input channel characteristic information based on the target AI unit, thereby eliminating the process of constructing the target AI unit by the terminal, and is more helpful to save the terminal overhead.
  • the first information when the model structure information of the target AI unit is agreed upon by protocol, the first information also includes an identifier of the target AI unit.
  • the protocol may stipulate a plurality of different target AI units, each of which includes a corresponding identity (ID); in this case, the first information may include the target AI unit weight parameter and the corresponding ID.
  • the terminal uses the ID of the target AI unit in the information to indicate which target AI unit to use.
  • the terminal determines the model structure information of the corresponding target AI unit based on the ID, and constructs the target AI unit in combination with the weight parameter indicated by the network side device.
  • the network side device does not need to send the model structure information of the target AI unit, which effectively saves the transmission overhead of the network side device.
  • the first AI unit and the target AI unit satisfy any one of the following conditions:
  • the first AI unit includes a quantization function
  • the target AI unit includes a dequantization function corresponding to the quantization function; in this case, the output of the first AI unit can be directly used as the input of the target AI unit.
  • the first AI unit includes a quantization function
  • the target AI unit does not include a dequantization function
  • the first output of the first AI unit is used as the input of the target AI unit after being dequantized.
  • the first AI unit does not include a quantization function, and the first output of the first AI unit serves as the input of the target AI unit; in this case, the output of the first AI unit can directly serve as the input of the target AI unit.
  • the first AI unit does not include a quantization function, and the first output of the first AI unit is used as the input of the target AI unit after quantization processing and dequantization processing.
  • the first information further includes any one of the following:
  • First indication information where the first indication information is used to instruct the terminal to use a dequantization method corresponding to the terminal quantization method.
  • the target AI unit does not include a dequantization function
  • the first AI unit includes a quantization function
  • the network side device may be to transmit the dequantization method information corresponding to the quantization function of the first AI unit to the terminal, so that the terminal can implement the dequantization processing of the input channel characteristic information based on the dequantization method information.
  • the network side device may also send the first indication information to instruct the terminal to use the dequantization method corresponding to the terminal quantization method, so as to ensure that the terminal can implement the dequantization processing of the input channel characteristic information based on the dequantization method.
  • the terminal obtains the performance information of the second AI unit based on the first input and the second output, including:
  • the terminal processes the relationship between the first input and the second output based on a first calculation rule to obtain performance information corresponding to the second AI unit, wherein the first calculation rule is determined by at least one of the following:
  • the terminal may process the relationship between the first input and the second output by using the first calculation rule agreed upon in the protocol, or the terminal may process the relationship between the first input and the second output by itself.
  • An appropriate first calculation rule is selected to calculate the relationship between the first input and the second output to obtain the performance information of the second AI unit; or, the relationship between the first input and the second output can be calculated according to the first calculation rule indicated by the network side device (i.e., the second indication information). In this way, the determination method of the first calculation rule is more flexible.
  • the first calculation rule matches the target AI unit.
  • different target AI units may be for different first calculation rules
  • the network side device may indicate the first calculation rule corresponding to the target AI unit of the terminal based on the different target AI units used by the terminal, so that the terminal can calculate the relationship between the second output of the target AI unit and the first input of the first AI unit based on the corresponding first calculation rule, so as to obtain the performance information of the second AI unit.
  • the method further includes:
  • third indication information used to indicate whether the first AI unit and/or the second AI unit is invalid
  • a third instruction for triggering deactivation of the first AI unit and/or the second AI unit is triggered by the first AI unit and/or the second AI unit.
  • the terminal may directly report the performance information to the network side device, so that the network side device can directly know the performance information of the second AI unit, so that the network side device can adjust the CSI feedback according to the performance information.
  • the terminal may also report the second output to the network side device, and the network side device may obtain the performance information of the second AI unit based on the second output and the channel information restored by the second AI unit.
  • the terminal may also include a mapping relationship between the output of the target AI unit and the output of the second AI unit, so that when the terminal obtains the second output of the target AI unit, it can estimate the output of the second AI unit based on the mapping relationship.
  • the terminal may also report the estimated output of the second AI unit to the network side device, and the network side device can obtain the performance of the second AI unit based on the relationship between the output and the actual output of the second AI unit.
  • the terminal can determine the degree of recovery of the second AI unit for the channel information based on the performance information, and judge whether the second AI unit is invalid based on the degree of recovery. For example, if the degree of recovery is high, it means that the performance of the second AI unit is good, and it is considered that the second AI unit is not invalid and can continue to be used; if the degree of recovery is low, or the degree of recovery is less than a preset threshold, Further, the terminal may report indication information of whether the second AI unit is invalid to the network side device, and the network side device may decide whether to continue to use the second AI unit based on the indication information.
  • the terminal may also report to the network side device instructions to trigger the first AI unit and/or the second AI unit to switch, activate, deactivate, etc.
  • the terminal reporting the second information to the network side device includes:
  • the terminal When receiving fourth indication information from the network side device, the terminal reports the second information to the network side device, where the fourth indication information is used to instruct the terminal to report the second information.
  • the reporting of the second information may be that the terminal reports the second information to the network side device when the network side device instructs the terminal to report. In this way, the reporting behavior of the terminal can be clarified through the network side device.
  • the fourth indication information is carried by at least one of the following:
  • DCI Downlink Control Information
  • the method may further include:
  • the terminal reports at least one of the following to the network side device:
  • the second information supported by the terminal can report content.
  • the content of the second information that can be reported by the terminal refers to which contents of the above-mentioned second information can be supported by the terminal for reporting, for example, the terminal supports reporting the second output, the performance information, or the terminal supports reporting the second output, the performance information, and the third indication information for indicating whether the first AI unit and/or the second AI unit are invalid, the output of the second AI unit estimated by the terminal based on the second output, or the content of the second information supported by the terminal for reporting may also include other possible situations, which are not specifically listed here.
  • the terminal reports the above content to the network side device, so that the network side device can learn the capabilities of the terminal.
  • the method before the terminal acquires the first information related to the target AI unit, the method further includes:
  • the terminal obtains high-level parameters of a network-side device, where the high-level parameters are used to configure the terminal to obtain performance information of the second AI unit based on the second output of the target AI unit and the first input of the first AI unit.
  • the network side device configures the terminal through the high-level parameters to obtain the performance information of the second AI unit through the second output of the target AI unit and the first input of the first AI unit, and then the terminal performs the corresponding operation through the high-level parameters, that is, the terminal selects the target AI unit, obtains the second output of the target AI unit and the first input of the first AI unit, and obtains the performance information of the second AI unit based on the second output and the first input to determine the first The degree of recovery of the second AI unit for channel information.
  • the terminal can obtain the performance information of the second AI unit through the target AI unit, which helps to improve the transmission performance of the AI unit for CSI between the terminal and the network side device.
  • the network-side device After the network-side device completes the training of the second AI unit based on different training cooperation levels, it then trains the target AI unit based on the same data set and the existing decoder AI unit.
  • the target AI unit adopts a simple structure and a small parameter scale. For example, for a Transformer structure decoder with 20M parameters, a model with a multilayer perceptron (MLP) structure (parameter scale ⁇ 100K) can be selected as the target AI unit.
  • MLP multilayer perceptron
  • the goal of training the target AI unit is to make the SGCS distribution of the target AI unit output as close as possible to the SGCS distribution of the second AI unit output (here, the close SGCS distribution of the two does not necessarily require the SGCS to be completely consistent, and the SGCS distribution of the two can be allowed to differ by a fixed constant or in a certain multiple relationship).
  • the training party needs to determine the usage method, that is, how to determine the performance of the second AI unit based on the inference results of the target AI unit.
  • the network-side device sends the target AI unit and its usage rules to the terminal, and instructs the terminal to report the predicted performance of the second AI unit during performance monitoring, that is, x_real.
  • the method of sending the target AI unit includes: 1) sending the complete target AI unit; 2) sending the model weight of the target AI unit, and the model structure is determined in advance by the manufacturer or according to the standard.
  • the terminal side uses the local encoder AI unit (that is, the first AI unit) and the target AI unit to calculate the SGCS output by the target AI unit, and calculates the SGCS of the second AI unit according to the mapping rule. Finally, the terminal reports the SGCS of the second AI unit to the network side device. The network side device determines whether the current performance of the second AI unit meets the standard based on the SGCS of the second AI unit, and decides whether to perform subsequent operations such as model reselection or fallback.
  • a target AI unit instead of a decoding AI unit
  • the terminal can obtain a recovered channel matrix or precoding matrix through the target AI unit, and the accuracy of the recovery has the same trend as the decoding AI unit of the network side device. Therefore, a simple target AI unit is used to enable the terminal to monitor the accuracy of the complete AI encoding and decoding unit, which can effectively reduce the transmission overhead and is more helpful to improve the transmission performance of CSI transmitted based on the AI unit between the terminal and the network side device.
  • Figure 3 is a flowchart of another information transmission method provided by an embodiment of the present application, and the method is applied to a network side device. As shown in Figure 3, the method includes the following steps:
  • Step 301 The network side device sends first information related to the target AI unit to the terminal;
  • the first information is used by the terminal to obtain the target AI unit, and the terminal is used to input the first output of the first AI unit into the target AI unit to obtain the second output of the target AI unit, and based on the second output and the first input of the first AI unit, obtain performance information of the second AI unit, the first AI unit is located in the terminal, and the second AI unit is located in the network side device.
  • the first information includes a weight parameter of the target AI unit and at least one of the following:
  • mapping relationship between the output of the target AI unit and the output of the second AI unit, and the input of the target AI unit matches the input of the second AI unit.
  • the method further comprises:
  • the network side device sends second indication information to the terminal, where the second indication information includes a first calculation rule, where the first calculation rule is used by the terminal to process the relationship between the first input and the second output to obtain performance information corresponding to the second AI unit.
  • the first calculation rule matches the target AI unit.
  • the method further comprises:
  • the network side device receives second information reported by the terminal, where the second information includes at least one of the following:
  • third indication information used to indicate whether the first AI unit and/or the second AI unit is invalid
  • a third instruction for triggering deactivation of the first AI unit and/or the second AI unit is triggered by the first AI unit and/or the second AI unit.
  • the method further includes:
  • the network side device sends fourth indication information to the terminal, where the fourth indication information is used to instruct the terminal to report the second information.
  • the fourth indication information is implemented by at least one of the following:
  • the method further comprises:
  • the network side device receives at least one of the following items reported by the terminal:
  • the second information supported by the terminal can report content.
  • the method before the network side device sends the first information related to the target AI unit to the terminal, the method further includes:
  • the network-side device sends high-level parameters to the terminal, where the high-level parameters are used to configure the terminal to obtain performance information of the second AI unit based on the second output of the target AI unit and the first input of the first AI unit.
  • the information transmission method provided in the embodiment of the present application is applied to the network side device, which corresponds to the above-mentioned method applied to the terminal side.
  • the relevant concepts and specific implementation processes involved in the embodiment of the present application can refer to the description in the above-mentioned terminal side embodiment. To avoid repetition, this embodiment will not be repeated.
  • the network side device sends first information related to the target AI unit to the terminal, so that the terminal can obtain the target AI unit based on the first information, and obtain the output of the target AI unit by taking the output of the first AI unit as the input of the target AI unit, and then through the correlation between the input of the first AI unit and the output of the target AI unit, the performance information of the second AI unit located in the network side device can be determined, and then the terminal can also know the degree of recovery of the channel characteristic information by the second AI unit, which is more helpful for the terminal and the network side device to transmit and process the channel information, and the terminal side does not need to obtain the second AI unit of the network side device and can also know the performance of the second AI unit, which effectively saves the transmission overhead of the AI unit between the terminal and the network side device.
  • the information transmission method provided in the embodiment of the present application can be executed by an information transmission device.
  • the information transmission device provided in the embodiment of the present application is described by taking the information transmission method executed by the information transmission device as an example.
  • FIG. 4 is a structural diagram of an information transmission device provided in an embodiment of the present application.
  • the information transmission device 400 includes:
  • a first acquisition module 401 is used to acquire first information related to a target AI unit, and obtain the target AI unit based on the first information;
  • a second acquisition module 402 is used to acquire a first input and a first output of a first AI unit, input the first output into the target AI unit, and acquire a second output of the target AI unit;
  • the third acquisition module 403 is used to acquire performance information of a second AI unit based on the first input and the second output, where the second AI unit is located in a network side device.
  • the first information includes a weight parameter of the target AI unit and at least one of the following:
  • mapping relationship between the output of the target AI unit and the output of the second AI unit, and the input of the target AI unit matches the input of the second AI unit.
  • the first acquisition module 401 is further used for:
  • the first information when the model structure information of the target AI unit is agreed upon by protocol, the first information also includes an identifier of the target AI unit.
  • the first AI unit and the target AI unit satisfy any one of the following conditions:
  • the first AI unit includes a quantization function
  • the target AI unit includes a dequantization function corresponding to the quantization function. Function
  • the first AI unit includes a quantization function, the target AI unit does not include a dequantization function, and the first output of the first AI unit is used as an input of the target AI unit after being dequantized;
  • the first AI unit does not include a quantization function, and the first output of the first AI unit is used as an input of the target AI unit;
  • the first AI unit does not include a quantization function, and the first output of the first AI unit is used as the input of the target AI unit after quantization processing and dequantization processing.
  • the first information further includes any one of the following:
  • First indication information where the first indication information is used to instruct the device to use a dequantization method corresponding to the terminal quantization method.
  • the third acquisition module 403 is further used to:
  • the relationship between the first input and the second output is processed based on a first calculation rule to obtain performance information corresponding to the second AI unit, wherein the first calculation rule is determined by at least one of the following:
  • the first calculation rule matches the target AI unit.
  • the device further comprises:
  • the first reporting module is configured to report second information to the network side device, where the second information includes at least one of the following:
  • third indication information used to indicate whether the first AI unit and/or the second AI unit is invalid
  • a third instruction for triggering deactivation of the first AI unit and/or the second AI unit is triggered by the first AI unit and/or the second AI unit.
  • the first reporting module is further used for:
  • the fourth indication information is used to instruct the apparatus to report the second information.
  • the fourth indication information is carried by at least one of the following:
  • the device further comprises:
  • the second reporting module is used to report at least one of the following to the network side device:
  • the second information supported by the device can report content.
  • the device further comprises:
  • the device can determine the performance information of the second AI unit located on the network side device through the target AI unit, and thus can know the degree of recovery of the channel characteristic information by the second AI unit, which is more helpful for the device and the network side device to transmit and process the channel information.
  • the device side does not need to obtain the second AI unit of the network side device and can also know the performance of the second AI unit, which effectively saves the transmission overhead of the AI unit between the device and the network side device.
  • the information transmission device 400 in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.
  • the electronic device can be a terminal, or it can be other devices other than a terminal.
  • the terminal can include but is not limited to the types of terminals 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.
  • the information transmission device 400 provided in the embodiment of the present application can implement each process implemented by the method embodiment described in Figure 2 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • FIG. 5 is a structural diagram of another information transmission device provided in an embodiment of the present application.
  • the information transmission device 500 includes:
  • a sending module 501 configured to send first information related to a target AI unit to a terminal;
  • the first information is used by the terminal to obtain the target AI unit, the terminal is used to input the first output of the first AI unit into the target AI unit, obtain the second output of the target AI unit, and obtain performance information of the second AI unit based on the second output and the first input of the first AI unit, the first AI unit is located in the terminal, and the second AI unit is located in the device.
  • the sending module 501 is further used for:
  • the second indication information including a first calculation rule, the first calculation rule being used by the terminal to process a relationship between the first input and the second output to obtain performance information corresponding to the second AI unit.
  • the first calculation rule matches the target AI unit.
  • the device further comprises:
  • the first receiving module is configured to receive second information reported by the terminal, where the second information includes at least one of the following:
  • third indication information used to indicate whether the first AI unit and/or the second AI unit is invalid
  • a third instruction for triggering deactivation of the first AI unit and/or the second AI unit is triggered by the first AI unit and/or the second AI unit.
  • the sending module 501 is further used for:
  • the fourth indication information is implemented by at least one of the following:
  • the device further comprises:
  • the second receiving module is configured to receive at least one of the following items reported by the terminal:
  • the second information supported by the terminal can report content.
  • the sending module 501 is further used for:
  • a high-level parameter is sent to the terminal, where the high-level parameter is used to configure the terminal to obtain performance information of the second AI unit based on the second output of the target AI unit and the first input of the first AI unit.
  • the device sends first information related to the target AI unit to the terminal, so that the terminal can obtain the target AI unit based on the first information, and obtain the output of the target AI unit by taking the output of the first AI unit as the input of the target AI unit, and then determine the performance information of the second AI unit through the correlation between the input of the first AI unit and the output of the target AI unit, so that the terminal can know the degree of recovery of the channel characteristic information by the second AI unit, which is more helpful for the terminal and the device to transmit and process the channel information, and the terminal side does not need to obtain the second AI unit on the device side and can also know the performance of the second AI unit, effectively saving the transmission overhead of the AI unit between the terminal and the device.
  • the information transmission device 500 provided in the embodiment of the present application can implement each process implemented by the method embodiment described in Figure 3 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application further provides a communication device 600, including a processor 601 and a memory 602, wherein the memory 602 stores a program or instruction that can be run on the processor 601, for example, the communication
  • the device 600 is a terminal
  • the program or instruction is executed by the processor 601 to implement the various steps of the method embodiment described in FIG. 2 above, and can achieve the same technical effect.
  • the communication device 600 is a network side device
  • the program or instruction is executed by the processor 601 to implement the various steps of the method embodiment described in FIG. 3 above, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application also provides a terminal, including a processor and a communication interface, the processor is used to obtain first information related to a target AI unit, and obtain the target AI unit based on the first information; obtain the first input and the first output of the first AI unit, input the first output into the target AI unit, and obtain the second output of the target AI unit, and obtain the performance information of the second AI unit based on the first input and the second output, wherein the second AI unit is located in a network side device.
  • This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the terminal embodiment and can achieve the same technical effect.
  • Figure 7 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application.
  • the terminal 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709 and at least some of the components of a processor 710.
  • the terminal 700 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 710 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 FIG7 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 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode.
  • the display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072.
  • the touch panel 7071 is also called a touch screen.
  • the touch panel 7071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 7072 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 701 can transmit the data to the processor 710 for processing; in addition, the RF unit 701 can send uplink data to the network side device.
  • the RF unit 701 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • the memory 709 can be used to store software programs or instructions and various data.
  • the memory 709 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 709 may include a volatile memory or a non-volatile memory, or the memory 709 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), or an erasable programmable read-only memory (EPROM).
  • ROM read-only memory
  • PROM programmable read-only memory
  • EPROM erasable programmable read-only memory
  • EPROM erasable programmable read-only memory
  • the volatile memory may be a random access memory (Random Access Memory, RAM), a static random access memory (Static RAM, SRAM), a dynamic random access memory (Dynamic RAM, DRAM), a synchronous dynamic random access memory (Synchronous DRAM, SDRAM), a double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), an enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), a synchronous connection dynamic random access memory (Synch link DRAM, SLDRAM) and a direct memory bus random access memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM, SLDRAM synchronous connection dynamic random access memory
  • Direct Rambus RAM Direct Rambus RAM
  • the processor 710 may include one or more processing units; optionally, the processor 710 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 710.
  • the processor 710 is used for:
  • performance information of a second AI unit is obtained, where the second AI unit is located in a network side device.
  • the terminal by acquiring the target AI unit, the terminal can determine the performance information of the second AI unit located in the network side device, and then the terminal can also know the degree of recovery of the channel characteristic information by the second AI unit. Therefore, when the terminal position, channel environment, etc. change, the terminal can obtain the channel information recovered by the network side device based on the performance information of the second AI unit, which is more helpful for the transmission and processing of the channel information between the terminal and the network side device, and the terminal side can also know the performance of the second AI unit without acquiring the second AI unit of the network side device, which effectively saves the transmission overhead of the AI unit between the terminal and the network side device.
  • the embodiment of the present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is used to send first information related to a target AI unit to a terminal; wherein the first information is used by the terminal to obtain the target AI unit, and the terminal is used to input the first output of the first AI unit into the target AI unit, obtain the second output of the target AI unit, and obtain the performance information of the second AI unit based on the second output and the first input of the first AI unit, wherein the first AI unit is located at the terminal, and the second AI unit is located at the network-side device.
  • This network-side device embodiment corresponds to the above-mentioned network-side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this network-side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 800 includes: an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85.
  • the antenna 81 is connected to the radio frequency device 82.
  • the radio frequency device 82 receives information through the antenna 81 and sends the received information to the baseband device 83 for processing.
  • the baseband device 83 processes the information to be sent and sends it to the radio frequency device 83.
  • Device 82, the radio frequency device 82 processes the received information and sends it out through the antenna 81.
  • the method executed by the network-side device in the above embodiment may be implemented in the baseband device 83, which includes a baseband processor.
  • the baseband device 83 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG8 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 85 through a bus interface to call a program in the memory 85 and execute the network device operations shown in the above method embodiment.
  • the network side device may also include a network interface 86, which is, for example, a common public radio interface (CPRI).
  • a network interface 86 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 800 of the embodiment of the present application also includes: instructions or programs stored in the memory 85 and executable on the processor 84.
  • the processor 84 calls the instructions or programs in the memory 85 to execute the methods executed by the modules shown in Figure 5 and 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 various processes of the method embodiment described in FIG. 2 or the various processes of the method embodiment described in FIG. 3 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 of the method embodiment described in FIG. 2 above, or to implement the various processes of the method embodiment described in FIG. 3 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.
  • An embodiment of the present application further provides a computer program product, which is stored in a storage medium.
  • the computer program product is executed by at least one processor to implement the various processes of the method embodiment described in FIG. 2 above, or to implement the various processes of the method embodiment described in FIG. 3 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 communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in FIG. 2 , and the network side device can be used to execute the steps of the method described in FIG. 3 above.
  • 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)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Electromagnetism (AREA)
  • Medical Informatics (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

La présente demande appartient au domaine technique des communications. Sont divulgués un procédé et un appareil de transmission d'informations, et un terminal et un dispositif côté réseau. Le procédé de transmission d'informations dans les modes de réalisation de la présente demande comprend les étapes suivantes : un terminal acquiert des premières informations associées à une unité d'intelligence artificielle (IA) cible, et obtient l'unité d'IA cible sur la base des premières informations (201) ; le terminal acquiert une première entrée et une première sortie d'une première unité d'IA, entre la première sortie dans l'unité d'IA cible, et acquiert une seconde sortie de l'unité d'IA cible (202) ; et le terminal acquiert des informations de performance d'une seconde unité d'IA sur la base de la première entrée et de la seconde sortie, la seconde unité d'IA étant située au niveau d'un dispositif côté réseau (203).
PCT/CN2024/070706 2023-01-12 2024-01-05 Procédé et appareil de transmission d'informations, et terminal et dispositif côté réseau WO2024149156A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310038706.6 2023-01-12
CN202310038706.6A CN118338469A (zh) 2023-01-12 2023-01-12 信息传输方法、装置、终端及网络侧设备

Publications (1)

Publication Number Publication Date
WO2024149156A1 true WO2024149156A1 (fr) 2024-07-18

Family

ID=91774864

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/070706 WO2024149156A1 (fr) 2023-01-12 2024-01-05 Procédé et appareil de transmission d'informations, et terminal et dispositif côté réseau

Country Status (2)

Country Link
CN (1) CN118338469A (fr)
WO (1) WO2024149156A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200366326A1 (en) * 2019-05-15 2020-11-19 Huawei Technologies Co., Ltd. Systems and methods for signaling for ai use by mobile stations in wireless networks
WO2022000365A1 (fr) * 2020-07-01 2022-01-06 Qualcomm Incorporated Estimation et prédiction de canal de liaison descendante basées sur l'apprentissage automatique
US20230403587A1 (en) * 2022-06-14 2023-12-14 Samsung Electronics Co., Ltd. Method and apparatus for monitoring and reporting ai model in wireless communication system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200366326A1 (en) * 2019-05-15 2020-11-19 Huawei Technologies Co., Ltd. Systems and methods for signaling for ai use by mobile stations in wireless networks
WO2022000365A1 (fr) * 2020-07-01 2022-01-06 Qualcomm Incorporated Estimation et prédiction de canal de liaison descendante basées sur l'apprentissage automatique
US20230403587A1 (en) * 2022-06-14 2023-12-14 Samsung Electronics Co., Ltd. Method and apparatus for monitoring and reporting ai model in wireless communication system

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
ERLIN ZENG, CATT: "Considerations on the use case specific aspects of AI/ML for NR air-interface", 3GPP TSG-RAN WG2 MEETING #120, R2-2211242, 4 November 2022 (2022-11-04), XP052215354 *
HUAWEI, HISILICON: "Discussion on AI/ML for CSI feedback enhancement", 3GPP TSG RAN WG1 MEETING #109-E, R1-2203141, 29 April 2022 (2022-04-29), XP052143959 *
HUAWEI, HISILICON: "Discussion on general aspects of AI/ML framework", 3GPP TSG-RAN WG1 MEETING #109-E, R1-2203139, 29 April 2022 (2022-04-29), XP052143957 *
MODERATOR (APPLE): "Summary 1 of Email discussion on other aspects of AI/ML for CSI", 3GPP TSG- RAN WG1 MEETING #109-E, R1-2205467, 18 May 2022 (2022-05-18), XP052192096 *
NOKIA SHANGHAI BELL, NOKIA, SAMSUNG: "Use case on shared AI/ML model monitoring", 3GPP TSG-SA WG1 MEETING #93E, S1-210410, 15 March 2021 (2021-03-15), XP051986514 *
VIVO: "Other aspects on AI/ML for CSI feedback enhancement", 3GPP TSG RAN WG1 #109-E, R1-2203551, 29 April 2022 (2022-04-29), XP052153026 *

Also Published As

Publication number Publication date
CN118338469A (zh) 2024-07-12

Similar Documents

Publication Publication Date Title
JP7369291B2 (ja) 符号化方法、復号方法、ユーザ機器及びネットワーク機器
WO2019223634A1 (fr) Procédé et appareil de traitement d'informations, terminal et dispositif de communication
US20230244911A1 (en) Neural network information transmission method and apparatus, communication device, and storage medium
WO2023246618A1 (fr) Procédé et appareil de traitement de matrice de canal, terminal et dispositif côté réseau
WO2024149156A1 (fr) Procédé et appareil de transmission d'informations, et terminal et dispositif côté réseau
WO2024149157A1 (fr) Procédé et appareil de transmission csi, terminal et dispositif côté réseau
WO2024055974A1 (fr) Procédé et appareil de transmission de cqi, terminal et dispositif côté réseau
WO2024055993A1 (fr) Procédé et appareil de transmission de cqi, et terminal et dispositif côté réseau
WO2023179460A1 (fr) Procédé et appareil de transmission d'informations de caractéristiques de canal, terminal, et dispositif côté réseau
WO2024164961A1 (fr) Procédé et appareil de traitement d'informations, terminal et dispositif côté réseau
WO2024140422A1 (fr) Procédé de surveillance de performance d'unité d'ia, terminal et dispositif côté réseau
WO2024007949A1 (fr) Procédé et appareil de traitement de modèle d'ia, terminal et dispositif côté réseau
WO2023185980A1 (fr) Procédé et appareil de transmission d'informations de caractéristique de canal, terminal et dispositif côté réseau
WO2023179570A1 (fr) Procédé et appareil de transmission d'informations de caractéristique de canal, terminal et dispositif côté réseau
WO2024037380A1 (fr) Procédés et appareil de traitement d'informations de canal, dispositif de communication et support de stockage
WO2023016339A1 (fr) Procédé et dispositif de rapport de csi, procédé et dispositif de réception de csi, terminal et dispositif côté réseau
WO2024051564A1 (fr) Procédé de transmission d'informations, procédé d'entraînement de modèle de réseau d'ia, appareil, et dispositif de communication
WO2024140578A1 (fr) Procédé de rétroaction de csi basé sur un modèle d'ia, terminal et dispositif côté réseau
WO2024104126A1 (fr) Procédé et appareil de mise à jour de modèle de réseau d'ia, et dispositif de communication
WO2024164962A1 (fr) Procédés et appareil de traitement de communication, dispositif et support de stockage lisible
WO2024032606A1 (fr) Procédé et appareil de transmission d'informations, dispositif, système et support de stockage
WO2024093999A1 (fr) Procédé de rapport d'informations de canal et procédé de réception, terminal et dispositif côté réseau
WO2023207920A1 (fr) Procédé de rétroaction d'informations de canal, terminal et dispositif côté réseau
WO2023179476A1 (fr) Procédés de rapport et de récupération d'informations de caractéristique de canal, terminal et dispositif côté réseau
WO2023185995A1 (fr) Procédé et appareil de transmission d'information de caractéristiques de canal, terminal et périphérique côté réseau

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: 24741155

Country of ref document: EP

Kind code of ref document: A1