Communication method and device, storage medium and program product

Abstract

The embodiment of the invention provides a communication method and device, a storage medium and a program product, relates to the technical field of communication, and is used for reducing system resource consumption, and the method comprises the steps that first information is sent aperiodically, and the first information is used for assisting a second node in information processing mode management.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular, to a communication method, apparatus, storage medium, and program product. Background Art

[0002] With the development of communication technologies, it is a future development trend to combine mobile communication systems with artificial intelligence (AI) / machine learning (ML). For example, in the fifth-generation mobile communication technology (5G), 5G-Advanced (5G-A), and sixth-generation mobile communication technology (6G), AI models are the key to AI / ML technologies. Currently, the management methods for AI models result in high system resource consumption. Summary of the Invention

[0003] Embodiments of the present disclosure provide a communication method, apparatus, storage medium, and program product for reducing system resource consumption.

[0004] To achieve the above object, the present disclosure adopts the following technical solutions:

[0005] In a first aspect, a communication method is provided, which is applied to a first node. The method includes:

[0006] Non-periodically sending first information, where the first information is used to assist a second node in managing an information processing manner.

[0007] In a second aspect, a communication method is provided, which is applied to a second node. The method includes:

[0008] Receiving first information, where the first information is non-periodically sent by the first node and is used to assist the second node in managing an information processing manner.

[0009] In a third aspect, a communication apparatus is provided, which is applied to a first node and includes:

[0010] A sending unit, configured to non-periodically send first information, where the first information is used to assist a second node in managing an information processing manner.

[0011] In a fourth aspect, a communication apparatus is provided, which is applied to a second node and includes:

[0012] A receiving unit, configured to receive first information, where the first information is non-periodically sent by the first node and is used to assist the second node in managing an information processing manner.

[0013] In a fifth aspect, a communication device is provided, including: a processor and a memory; the memory is coupled to the processor; the memory is used for storing instructions executable by the processor, and the memory stores instructions executable by the processor; when the processor is configured to execute the instructions, the communication device implements the method provided in any one of the first aspect or the second aspect as described above.

[0014] In a sixth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores computer instructions. When the computer instructions are run on a computer, the computer executes the method provided in any one of the first aspect or the second aspect.

[0015] In a seventh aspect, a computer program product including a computer program is provided. When the computer program is run on a computer, the computer executes the method provided in any one of the first aspect or the second aspect.

[0016] In the embodiments of the present disclosure, the first node sends the first information aperiodically, reducing the system resource consumption. Description of the Drawings

[0017] The drawings are used to provide a further understanding of the technical solutions of the present invention, and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the technical solutions of the present invention, and do not constitute a limitation to the technical solutions of the present invention.

[0018] Figure 1 It is a schematic diagram of an AI / ML framework provided for the embodiments of the present disclosure;

[0019] Figure 2 It is a schematic diagram of a positioning method provided for the embodiments of the present disclosure;

[0020] Figure 3 It is a schematic diagram of another positioning method provided for the embodiments of the present disclosure;

[0021] Figure 4 It is a schematic diagram of another positioning method provided for the embodiments of the present disclosure;

[0022] Figure 5 It is a schematic diagram of the structure of a communication system provided for the embodiments of the present disclosure;

[0023] Figure 6 It is a schematic diagram of the flow of a communication method provided for the embodiments of the present disclosure;

[0024] Figure 7 It is a schematic diagram of the flow of another communication method provided for the embodiments of the present disclosure;

[0025] Figure 8 It is a schematic diagram of the flow of another communication method provided for the embodiments of the present disclosure;

[0026] Figure 9 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0027] Figure 10 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0028] Figure 11 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0029] Figure 12 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0030] Figure 13 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0031] Figure 14 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0032] Figure 15 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0033] Figure 16 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0034] Figure 17 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0035] Figure 18 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0036] Figure 19 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0037] Figure 20 Schematic flowchart of another communication method provided by an embodiment of the present disclosure;

[0038] Figure 21 Schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure;

[0039] Figure 22 Schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure;

[0040] Figure 23 Schematic diagram of the structure of a communication device provided by an embodiment of the present disclosure. Detailed implementation manners

[0041] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0042] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and its other forms such as the third-person singular form "comprises" and the present participle form "comprising" are interpreted as open and inclusive, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples", etc. are intended to indicate that the specific features, structures, materials or characteristics related to the embodiment or example are included in at least one embodiment or example of the present disclosure. The schematic representations of the above terms are not necessarily referring to the same embodiment or example. In addition, the specific features, structures, materials or characteristics may be included in any one or more embodiments or examples in any appropriate manner.

[0043] The terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more.

[0044] In the embodiments of the present disclosure, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present disclosure should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0045] In addition, the use of "based on" means open and inclusive, because a process, step, calculation or other action "based on" one or more of the stated conditions or values may in practice be based on additional conditions or values beyond those stated.

[0046] AI includes devices, components, software, and modules with self-learning capabilities such as ML, deep learning, reinforcement learning, transfer learning, deep reinforcement learning, and meta-learning. In some cases, AI is implemented through an artificial intelligence network (or neural network), which consists of multiple layers, with each layer including at least one node. Exemplarily, a neural network includes an input layer, an output layer, and at least one hidden layer, where each layer of the neural network includes, but is not limited to, at least one of a fully connected layer, a dense layer, a convolutional layer, a transposed convolutional layer, a direct connection layer, an activation function, a normalization layer, a pooling layer, etc. In some other cases, each layer of the neural network can include a sub-neural network, such as a residual network block (or resnet block), a densenet block, a recurrent neural network (RNN), etc. An artificial intelligence network includes a neural network model and / or the neural network parameters corresponding to the neural network model. Herein, the neural network model can be abbreviated as the network model, and the neural network parameters can be abbreviated as network parameters. A network model defines the architecture of the neural network, including the number of layers, the size of each layer, the activation function, the connection situation, the convolution kernel and its size, the convolution stride, the convolution type (such as 1D convolution, 2D convolution, 3D convolution, dilated convolution, transposed convolution, separable convolution, grouped convolution, depthwise convolution, etc.), etc. The network parameters are the weights and / or biases of each layer in the network model and their values. A network model can correspond to multiple sets of different neural network parameter values to adapt to different scenarios. The values of the network parameters can be obtained through offline training and / or online training. For example, by inputting at least one sample and label, the neural network model is trained to obtain the neural network parameters. A neural network model can correspond to multiple different neural network parameter values.

[0047] AI / ML is a promising enhancement direction for mobile communication systems. Introducing AI / ML technologies into mobile communication systems, such as 5G (fifth generation), 5G-A (5G-Advanced), and 6G (sixth generation), can improve the system's operating efficiency. For example, by means of AI / ML inference and prediction, it can reduce the overhead of reference signals, reduce the overhead of channel state information feedback, or improve the accuracy of terminal positioning, etc.

[0048] In the embodiments of the present disclosure, for a communication system adopting AI / ML technologies, "model" refers to a general term used to describe the capabilities of devices in the communication system to execute processing methods, functions, features, or groups of features. A "model" can be a function, a functional module, a processing method, an information processing method, an implementation, a group of functions, a configuration, a set of configurations, a data set (e.g., for model training), or a data-driven algorithm.

[0049] The basic AI / ML framework used in a communication system can be as follows Figure 1 as shown in Figure 1 , the basic AI / ML framework includes a data collection module, a model training module, a model management module, a model inference module, and a model storage module. The module can also be replaced by a function. For example, the data collection module can also be called the data collection function.

[0050] Among them, the data collection module is used to provide input data for the model training module, the model management module, and the model inference module. The input data required by the model training module is training data. The input data required by the model management module is monitoring data. The input data required by the model inference module is inference data. The collected monitoring data may be label data that provides a calibration-like function and is sent to the model management module for comparison with the inference output to output corresponding adjudication commands or management commands.

[0051] The model training function module performs the functions of AI / ML model training, verification, and testing.

[0052] The management function module can perform the following functions: (1) indicating related operations of the AI / ML model, such as selection / activation / deactivation / switching / rollback, etc. for the model. (2) monitoring the model performance. (3) making decisions or instructions to ensure correct inference operations based on the data received from the data collection module and the model inference module. (4) being responsible for requesting the model from the model storage module for model transfer / delivery requests. (5) inputting performance feedback / retraining requests to the model training module for model (re)training or updating.

[0053] The model inference module takes the data provided by the data collection module as input and provides the output from the applied AI / ML model or function. The output of the model inference module is the final output of the entire AI / ML model or function and is used for other units in the mobile system. The output data can also be input to the model management module for internally monitoring the performance of the AI / ML model or the AI / ML function.

[0054] The model storage module is a function responsible for storing the trained / updated model that can be used to perform the inference function.

[0055] In one example, a device for AI / ML model training and inference is used to assist in positioning and output the final positioning of the user equipment (UE). Exemplarily, the following 3 scenarios and instances are used to describe AI / ML positioning:

[0056] Scenario 1: See Figure 2 , based on the positioning method of the terminal UE, the AI / ML model directly outputs the positioning result on the UE side. Among them, Figure 2The LMF in it is the Location Management Function (LMF), and the PRS is the Positioning Reference Signal (PRS).

[0057] Scenario 2: Refer to Figure 3 , for the positioning method based on the LMF, the AI / ML model on the UE side assists in outputting the positioning result.

[0058] Scenario 3: Refer to Figure 4 , for the positioning method based on the LMF, the AI / ML model on the base station side assists in outputting the positioning result. Among them, Figure 4 the SRS in it is the Sounding Reference Signal (SRS).

[0059] In Scenario 2, the AI / ML model is located in the UE. The final location information is output by the LMF. The UE-side model only assists in the positioning mode, that is, the model in the UE outputs intermediate parameters, and the LMF performs the final calculation (position estimation) and outputs the final positioning result based on the intermediate parameters. In Scenario 3, the AI / ML model is located in the base station. The AI / ML model in the base station outputs intermediate parameters, and the LMF performs the final calculation (position estimation) and outputs the final positioning result based on the intermediate parameters.

[0060] Based on the above description of the model management module and combining the above three scenarios, it is a reasonable assumption to place the management function module of the AL / ML model in an entity device similar to the LMF or other core network side. Because the LMF itself is the calculation unit for UE positioning, responsible for summarizing and outputting the final positioning result. Even in the UE-side positioning scenario, the final result calculated by the UE needs to be summarized to the LMF, and the LMF distributes the result to the required entity units. At the same time, the LMF is responsible for managing the model, which is beneficial to the fairness of all users. There is also a special case where the model management module is placed in the Operation, Administration and Maintenance (OAM) entity, that is, placed on the network management unit, which can also aggregate the reported information from multiple base stations and multiple terminals and make relevant model management decisions.

[0061] The operation of the model management module of the AL / ML model, such as model performance monitoring, commonly uses the method of periodic performance monitoring. Once the monitoring period is set, there is no need for further intervention, which has the advantages of convenience and simplicity. However, performance monitoring itself consumes a certain amount of system resources. For example, it is required to measure the output of the measurement unit with the ground truth label and then compare and calculate it with the output of the model or the positioning value output by the model assistance to obtain the model performance parameters as input for subsequent model-related operations of the performance monitoring function, such as the basis for model selection / activation / deactivation / switching / rollback / re-training / updating. If it is periodic performance monitoring, the accumulated system resource consumption is a significant burden. That is to say, the current method for managing AI models is to perform model management periodically, which consumes a high level of system resources. Based on this, how to reduce system resource consumption is an urgent problem to be solved.

[0062] Based on this, the embodiments of the present disclosure provide a communication method, device, storage medium, and program product. The first node sends the first information non-periodically, and the first information is used to assist the second node in managing the information processing method. That is, the first node sends the first information for assisting the second node in managing the information processing method in a demand-driven manner, which can reduce system resource consumption.

[0063] The solutions of the embodiments of the present disclosure will be introduced below with reference to the accompanying drawings.

[0064] The technical solutions provided by the embodiments of the present disclosure can be applied to various mobile communication networks. For example, the NR mobile communication network using 5G, future mobile communication networks (such as 6G wireless communication systems), or various communication convergence systems, etc. The embodiments of the present disclosure do not make any limitations in this regard.

[0065] Figure 5 Shown is a schematic structural diagram of a communication system provided by an embodiment of the present disclosure. As Figure 5 shown, the communication system includes, but is not limited to, a management device 10, a terminal 20, and a base station 30. Among them, wireless signals can be sent, received, and related interactions can be carried out among the management device 10, the terminal 20, and the base station 30.

[0066] In some embodiments, the management device 10 may be a device with management computing functions, such as LMF, OAM, etc. Among them, the LMF is a core network element responsible for providing positioning services for the communication system. The LMF mainly provides the required location estimation for the positioning service based on the measurement information collected from the user equipment (UE) and / or the radio access network (RAN). The OAM is used to divide the network management work according to the actual needs of the operator network operation, mainly including three categories: operation, management, and maintenance. The OAM entity has multiple key functions, such as connectivity detection, fault detection, fault location, and error recovery. By using the OAM technology, network administrators can effectively manage and maintain network devices, greatly simplifying the daily network management tasks. For example, administrators can conveniently configure and control devices through the OAM function, including setting network parameters, enabling / disabling interfaces, implementing traffic control, etc.

[0067] As a possible example, the management device 10 may be a physical device that integrates the functions of the LMF and the OAM.

[0068] In some embodiments, the above terminal 20 may be a device with wireless transceiver functions, such as a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The specific types of the terminal are not limited in the embodiments of the present disclosure.

[0069] In some embodiments, the above base station 30 may be any one of an evolved Node B (eNB), a next-generation Node B (gNB), a transmission receive point (TRP), a transmission point (TP), and some other access nodes. According to the size of the service coverage area provided, the base station can be further divided into a macro base station for providing a macro cell, a micro base station for providing a picocell, and a femto base station for providing a femto cell. With the continuous evolution of wireless communication technology, future base stations may also adopt other names.

[0070] It should be understood that Figure 5is an exemplary structural diagram Figure 5 The number of devices included in the shown communication system is not limited. For example, the number of terminals and base stations is not limited. And, in addition to Figure 5 the shown devices Figure 5 the shown communication system may also include other devices, which is not limited herein.

[0071] Next, as Figure 6 shown, an embodiment of the present disclosure provides a communication method, which is applied to a first node. The first node may be the management device 10 shown above Figure 5 and this is not limited in the embodiment of the present disclosure. The method includes the following steps:

[0072] S101. Periodically send first information. The first information is used to assist a second node in managing an information processing method.

[0073] Wherein, the information processing method includes a model, and the management of the information processing method can be understood as model management. The second node may be the terminal 20 or the base station 30 shown above Figure 5 and this is not limited in the embodiment of the present disclosure. The first node can be understood as the entity where the adjudication institution is located, and the second node can be understood as the entity where the monitoring institution is located. The adjudication institution is used to adjudicate the model management, and the monitoring institution is used to monitor the running process of the model and send the parameters monitored during the running process of the model to the adjudication institution, and the adjudication institution makes an adjudication based on the parameters.

[0074] As a possible example, the second node may also be an over the top server (OTT), that is, the service provider uses the OTT to train the model in the terminal, and the trained model is used in the terminal.

[0075] It should be understood that since management devices such as LMF and OAM where the adjudication institution is located (i.e., the first node) and base stations, terminals, etc. (i.e., the second node) are generally provided by different manufacturers, when the AI model is in the base station or the terminal, the protection of model privacy results in the first node not fully knowing the specific situation of the model. Due to privacy reasons, the second node is not willing to carry model parameters such as the preferred model identifier in the performance metric report. In this way, the first node cannot give relatively accurate information processing method management instructions, such as model selection / switching / reselection instructions, and can only be forced to execute relatively simple model activation / rollback and other functions, which limits the function of information processing method management.

[0076] Therefore, in order to balance model privacy protection, the first node can send the first information non-periodically based on performance monitoring. The first information is used to assist the second node in managing the information processing method, that is, to assist the base station or terminal in managing the information processing method. The second node can determine whether to perform information processing method management based on the operating conditions of the second node.

[0077] In some embodiments, when a preset condition is met, the first node sends the first information non-periodically, where the preset condition includes one of the following:

[0078] Receiving control signaling for instructing non-periodic transmission of the first information;

[0079] The duration of periodically sending the first information reaches a preset duration;

[0080] Detecting that the deviation between the position of the terminal output by the model on the second node side and the actual position of the terminal is greater than a preset threshold.

[0081] In some embodiments, the first information includes status information for assisting the second node in managing the information processing method.

[0082] As an example, in combination with Scenario 2 shown above Figure 3 The model is trained in the terminal or OTT (i.e., the second node). The trained model is executed in the terminal and outputs intermediate results such as downlink reference signal time difference (DL RSTD) values or other parameters for assisting positioning to the LMF (i.e., the first node). After obtaining the intermediate results, the first node is responsible for positioning calculations and outputs the final results. The adjudication function of the model management module is implemented in the first node to obtain the adjudication signaling. The first node sends the adjudication signaling to the second node, and the adjudication signaling may require the second node to activate, deactivate, retrain, or replace the model. For a relatively complex management function such as replacing the model, the premise is that the first node needs to know the specific situation of the model library of the second node under different state conditions, such as how to classify, etc., in order to indicate which target model the model in the second node should switch to. This indication of the target model can be understood as model transmission / delivery. However, it is very likely that the first node does not know the information of the model library in the second node. Therefore, the first node can send some status conditions for assisting model management to the second node to assist the model in the second node in model management, such as performing model switching and other operations.

[0083] As another example, in combination with the above Figure 4Scenario 3 shown in the figure is described as follows. In Scenario 3, the base station (i.e., the second node) side model outputs intermediate parameters, such as uplink relative time of arrival (UL RTOA), uplink angle of arrival (UL-AOA), or other parameters for assisting positioning. The intermediate parameters are reported to the first node. The first node aggregates the intermediate parameters output by the models of multiple second nodes and calculates the final positioning result. The adjudication function of the model management module is implemented within the first node to obtain the adjudication signaling. Then, the first node sends the adjudication signaling to the second node, and the adjudication signaling may require the model within the second node to be activated, deactivated, retrained, or replaced. For a relatively complex model replacement management function like this, the prerequisite is that the first node needs to know the specific situation of the model library in the second node under different state conditions, such as how to classify, etc., in order to indicate which target model the model in the second node should switch to. This indication of the target model can be understood as model transmission. However, it is very likely that the first node does not know the information of the model library in the second node. Therefore, the first node can send the state conditions for assisting model management to the second node to assist the model in the second node with model management, such as performing operations like model switching.

[0084] In some embodiments, the state information includes at least one of the following:

[0085] Information 1, speed information.

[0086] As a possible example, assume that the second node has trained two targeted models for the constant speed (walking speed) state and the high speed (vehicle moving speed) state respectively. Then, there is a problem of switching models according to different speed information. The first node can effectively obtain or calculate the moving speed of the terminal and send the state conditions related to the speed information to the second node. The second node itself determines whether to switch between the constant speed model and the high speed model under the current state conditions related to the speed information. The speed information can be direct vehicle speed information or indirect vehicle speed information. For example, the speed information only indicates high speed or low speed, or the speed information indicates multiple levels of vehicle speed. The speed information can also be an instruction requiring the second node to switch to the constant speed model or the high speed model.

[0087] In some embodiments, taking the management of information processing mode as an example of information processing mode switching, the first information further includes a switching threshold of the information processing mode. It should be understood that, in order to assist the second node in determining whether to perform the switching of the information processing mode, the first node can also inform the second node of a switching threshold in a predefined, preconfigured or dynamically indicated manner, and the switching threshold can be carried in the first information. Among them, the dynamic indication can refer to the control information of the physical layer, and the preconfiguration can refer to the radio resource control (RRC) information. That is to say, the first information can be the control information of the physical layer or the RRC information.

[0088] Information 2, distance information.

[0089] As a possible example, assume that the second node has trained two targeted models for the intermediate variable UL RTOA output in the time domain and the intermediate variable UL-AOA output in the angle domain respectively, and the two models have performance advantages at different distances, where the distance is the distance between the terminal and the base station. Assume that when the distance is less than a preset distance threshold, the positioning accuracy obtained by using the intermediate variable of UL-AOA output by the model is higher, then it is recommended to use the model based on UL-AOA; otherwise, it is recommended to use the model based on UL RTOA. That is, the model can be switched according to the distance information between the terminal and the base station in the cell.

[0090] The first node can effectively obtain or calculate the distance between the terminal and the base station, and send the status condition related to the distance information to the second node. The model in the second node itself determines whether to switch between the model based on UL-AOA and the model based on UL RTOA under such a status condition related to the distance information. The distance information can be the distance value itself, or indirect distance information, such as only prompting simple information of "far" or "near", such as prompting multiple relative levels of the distance; the distance information can also be an instruction for the second node to switch to any one of the two models.

[0091] Information 3, terrain information.

[0092] The first node can manage the information processing method according to the state condition of the fuzzy landform of the terminal in the cell. For example, taking the information processing method as a model, when the terminal is mainly in dense building scenarios such as commercial buildings in the cell, the positioning accuracy calculated based on the intermediate variable of UL-AOA is higher, so it is recommended to use the model based on UL-AOA. If the terminal is mainly active in sparse scenarios such as low-rise buildings or large flat lands in the cell, the positioning accuracy calculated based on the intermediate variable of UL-RTOA is higher, then it is recommended to switch to the model based on UL-RTOA. The first node can infer the landform information by combining the rough position information of the terminal with the electronic map, and then send the landform information to the second node. The second node determines whether to manage the information processing method based on the landform information, such as whether to switch the model.

[0093] The landform information can be position fuzzy information, and the position fuzzy information can be classification information of typical landform information. The classification information includes the classified number. The first node can send the classified number to the second node so that the second node can determine the landform information based on the classified number. In this way, the amount of information transmission can be reduced.

[0094] It should be understood that the above state information can be applied to any one of the above Scenarios 1 to 3.

[0095] Based on Figure 6 In the illustrated embodiment, the first node sends the first information non-periodically. The first information is used to assist the second node in managing the information processing method, that is, the first node sends the first information for assisting the second node in managing the information processing method in a demand-driven manner. Compared with the related art where the first node sends the first information periodically, the system resource consumption is reduced.

[0096] In some embodiments, as Figure 7 shown, after non-periodically sending the first information, that is, after step S101, the method may further include the following steps:

[0097] S102. Receive the second information sent by the second node.

[0098] In some embodiments, after the second node receives the first information sent by the first node, it can manage the information processing method based on the first information. After the second node manages the information processing method based on the first information, the second node can send the second information to the first node. Correspondingly, the first node receives the second information sent by the second node. Among them, the second information is used to represent the result of the second node managing the information processing method based on the first information. That is to say, after the second node manages the information processing method based on the first information, it can send the result of the information processing method management to the first node.

[0099] In some embodiments, the result of the information processing method management may be whether the second node has completed the management of the information processing method.

[0100] In some embodiments, as Figure 8 shown, before step S101, the method may further include the following steps:

[0101] S201. Receive the third information sent by the second node.

[0102] Wherein, the third information is used to request assistance in the information processing method management of the second node.

[0103] In some embodiments, the above Figure 6 illustrated embodiment is described by taking the first node actively sending the first information to the second node as an example. In some embodiments, the second node may actively send the third information to the first node to request the first node to assist the second node in the information processing method management. Accordingly, the first node receives the third information sent by the second node and, in response to the first information, sends the first information to the second node.

[0104] In some embodiments, the third information is further used to request the status information for assisting the second node in the information processing method management. That is to say, the third information can also be used to request what the specific status information is. In this way, it is convenient for the second node to set the status information required by the second node according to the capabilities of the second node.

[0105] In some embodiments, the third information is further used to request the parameters for determining the performance of the information processing method. The parameters include at least one of the following: true value label, calibration data. The calibration data or the true value label may be generated and sent by the first node or obtained by the first node from other network devices and then forwarded to the second node.

[0106] In some embodiments, as Figure 9 shown, the method may further include the following steps:

[0107] S301. Send the fourth information non-periodically.

[0108] Wherein, the fourth information is used to instruct the second node to perform the information processing method management, and it can be understood that the fourth information is used to guide the second information to perform the information processing method management. In some embodiments, step S301 may be before the above step S101 or after the above step 101, and the embodiments of the present disclosure do not limit this.

[0109] The above Figures 6 to 8In any of the embodiments shown, the second node passively or actively triggers the notification of the status condition, and then the first node determines whether to perform information processing mode management, such as model switching, etc. If so, the second node performs information processing mode management. The above Figures 6 to 8 The problems to be solved in any of the embodiments shown are what the transmitted status information is and how the second node responds to the status information. The status information is an input that triggers the execution management of the information processing mode within the second node and is applicable to functions such as activation / deactivation / rollback / information processing mode switching, etc., in response to the status information.

[0110] For functions such as information processing mode update / information processing mode retraining in information processing mode management, it is not enough to simply respond to the input status information. Information processing mode update or information processing mode retraining requires more inputs to guide how to perform information processing mode update or information processing mode retraining, or in which direction to perform information processing mode update or information processing mode retraining. Based on this, the embodiments of the present disclosure propose that the first node non-periodically sends the fourth information to the second node to instruct the second node to perform information processing mode management.

[0111] In some embodiments, the fourth information includes at least one of the following: the training direction of the information processing mode; data credibility, where the data credibility is used to represent the credibility of the input data of the information processing mode.

[0112] Exemplarily, in scenario 2, the LMF / OAM can indicate the true value label to the model in the UE, or the difference between the true value label calculated within the LMF / OAM and the calculated positioning, so that the UE can determine the retraining direction according to the accuracy difference. For another example, the LMF / OAM can indicate to the model in the UE which input data of the model is more credible. For example, in the measured time-domain data, is the currently measured data more credible, or the historically measured data more credible, or the future predicted measured data more credible? The model can force the most credible measured data to be focused on during the retraining process, assign higher priority or weight to the corresponding measured data, thereby changing or updating the model.

[0113] In some embodiments, as Figure 10 shown, after step S301, the method may further include the following steps:

[0114] S302. Receive the fifth information sent by the second node.

[0115] Wherein, the fifth information includes the management result of the second node performing information processing mode management based on the fourth information.

[0116] In some embodiments, after receiving the fourth information sent by the first node, the second node may manage the information processing method based on the fourth information. After obtaining a management result by managing the information processing method based on the fourth information, the second node may send the fifth information to the first node. Correspondingly, the first node receives the fifth information sent by the second node.

[0117] In some embodiments, as Figure 11 shown, before step S301, the method may further include the following steps:

[0118] S401. Receive the sixth information sent by the second node.

[0119] Wherein, the sixth information is used to request to instruct the second node to manage the information processing method.

[0120] The above Figure 9 illustrated embodiments are described by taking the first node's active and aperiodic sending of the fourth information as an example. In some embodiments, the second node may actively send the sixth information to the second node to request the first node to instruct (which may also be referred to as guiding) the second node to manage the information processing method. After receiving the sixth information sent by the second node, the first node, in response to the sixth information, sends the fourth information to the first node.

[0121] Based on Figure 11 the illustrated embodiments, the first node may send the fourth information to the second node when receiving the sixth information sent by the second node. In this way, the first node may send the corresponding fourth information to the second node based on the requirements of the second node, which can improve the accuracy of sending the fourth information.

[0122] In some embodiments, as Figure 12 shown, the method may further include the following steps:

[0123] S501. Send the seventh information aperiodically.

[0124] In the above scenarios 1, 2, and 3, the model adjudication entity exists in devices such as the LMF on the core network side and the OAM device on the radio network side, while the basic functions such as model training and inference exist in the base station or UE. Since the monitoring entity needs to output the performance metrics of the model, it is a reasonable assumption that the monitoring entity exists in the same network devices as the model, such as the base station or the terminal, because performance metrics often require extensive use of the input, output, or intermediate variables of the model, and this data is not suitable for aggregation into the LMF or OAM. Based on this, the embodiments of the present disclosure propose that the first node sends the seventh information to the second node non-periodically or on demand, and the seventh information is used to request the reporting of performance metrics, that is, to request the second node to report performance metrics. Step S501 may be before the above step S101 or after the above step S101, and the embodiments of the present disclosure do not limit this.

[0125] In some embodiments, the seventh information includes at least one of the following:

[0126] The reporting type of the performance metric;

[0127] The data structure of the performance metric;

[0128] The reporting quantity of the performance metric;

[0129] The reporting time of the performance metric;

[0130] The reporting accuracy of the performance metric, where the reporting accuracy of the performance metric can also be referred to as the reporting accuracy of the performance metric.

[0131] In some embodiments, in order to facilitate the second node to determine the performance metrics to be reported, the seventh information further includes parameters of the performance for determining the information processing method, and the parameters include at least one of the following: true value label, calibration data. The calibration data or the true value label can be generated and sent by the first node or obtained by the first node from other network devices and then forwarded to the second node. The parameters of the performance for determining the information processing method can be carried in the above seventh information or in the eleventh information different from the seventh information. That is, after the first node sends the seventh information to the second node non-periodically, the first node can send the eleventh information to the second node. The eleventh information is used to assist the second node in reporting the performance metrics, and the eleventh information can also have other names, such as information for assisting the reporting request of the performance metrics.

[0132] S502. Receive the eighth information sent by the second node.

[0133] In some embodiments, after receiving the seventh information, the second node sends the eighth information to the first node in response to the seventh information. Correspondingly, the first node receives the eighth information sent by the second node. Among them, the eighth information includes the performance metrics requested by the seventh information.

[0134] In some embodiments, the performance metrics included in the eighth information are used to indicate at least one of the following:

[0135] The first item: Whether the performance of the information processing method of the second node is acceptable, that is, the conventional judgment result (boolean value), which is provided to the first node for reference. If the performance of the information processing method of the second node is unacceptable, the first node may request the second node to deactivate or fallback the information processing method to a non-AI / ML mode. However, since in principle, it is more in line with the principle of global overall control for an entity outside the model to judge whether the performance of the information processing method is acceptable, a judgment criterion is required for the second node to output whether the ability of the information processing method is acceptable. For example, the performance threshold is sent by the adjudication entity to the monitoring entity. This judgment criterion can also be one of the information assisting in reporting the performance metric request, that is, this judgment criterion (such as the performance threshold) can be carried in the eleventh information or in the above-mentioned seventh information. Whether the performance of the information processing method is acceptable, the second node can report it in a soft decision manner, such as in percentage or in levels (from 1 to 10). This way of reporting in percentage or levels is also suitable for feedback on the accuracy or confidence of the performance metric results.

[0136] In some embodiments, the performance metrics can be reported in a variety of ways, such as prompting the first node on how to select / activate / deactivate / switch / fallback / retrain the information processing method, etc. Exemplarily, it can include the following items:

[0137] The second item: The training direction of the information processing method, such as indicating the bias of the input parameters of the information processing method (such as a model), for example, the input parameters are biased towards time-based measurements, beam-based measurements, or angle-based measurements, etc.

[0138] The third item: The management method of the information processing method;

[0139] The fourth item: The parameters of the target information processing method that the second node should use, where the parameters include at least one of the following: the identification of the target information processing method, the type of the target information processing method, the limiting conditions of the target information processing method, and the parameters for assisting in determining the information processing method. The target information processing method that the second node should use can be called the target information processing method preferred by the second node.

[0140] In some embodiments, the information processing method includes a first information processing method, and the performance metrics included in the eighth information include the performance metrics related to the first information processing method.

[0141] In some embodiments, the information processing method further includes a second information processing method, and the performance metrics included in the eighth information further include performance metrics related to the second information processing method.

[0142] Among them, the first information processing method may be an AI-based information processing method, and the second information processing method may be a traditional non-AI information processing method.

[0143] In some embodiments, the number of the first information processing method and the second information processing method is plural. That is to say, the performance metrics included in the eighth information may include multiple performance metrics related to the first information processing method, or may include multiple performance metrics related to the first information processing method and multiple performance metrics related to the second information processing method. The embodiments of the present disclosure do not limit this.

[0144] In some embodiments, as Figure 13 shown, after step S502, the method may further include the following steps:

[0145] S503. Send the ninth information.

[0146] In some embodiments, after receiving the eighth information sent by the second node, the first node may determine a management decision of the information processing method based on the eighth information, and then send the ninth information to the second node. The first information includes the management decision of the information processing method determined by the first node based on the performance metrics included in the eighth information. The management decision includes at least one of the following: selection / activation / deactivation / switching / fallback / retraining, etc. of the information processing method (such as a model).

[0147] In some embodiments, as Figure 14 shown, before step S501, the method may further include the following steps:

[0148] S601. Receive the tenth information sent by the second node.

[0149] Among them, the tenth information is used to indicate the capabilities supported by the second node.

[0150] It should be understood that the support for reporting different types of performance metrics depends on the capabilities of the terminal or the base station. Before the process of non-periodic (on-demand) triggering of performance metric reporting, the LMF or OAM where the adjudication entity is located needs to know whether the capabilities of the base station and the terminal support it, and the base station and the terminal need to cooperate to report their own relevant capabilities to the adjudication entity.

[0151] Based on this, before the first node sends the seventh information to the second node non-periodically to request the reporting of performance metrics, the second node may send the tenth information to the first node to report the capabilities supported by the second node. Correspondingly, the first node receives the tenth information sent by the second node, and then determines the capabilities supported by the second node based on the tenth information.

[0152] Exemplarily, in combination with the above scenario 3, the base station where the AI / ML model is located outputs intermediate parameters, such as UL RTOA values or other parameters for assisting positioning, and reports them to the LMF / OAM. The LMF / OAM aggregates the intermediate parameters output by the models of multiple base stations and calculates the final positioning result. When performance monitoring is required, the LMF / OAM non-periodically triggers a performance metric reporting request for some or all of the models in the base stations. For example, the reporting type is whether the currently used model can continue to be used or is still acceptable. Along with the performance metric reporting request, calibration data or ground truth labels for assisting the base station in performance comparison can also be sent. The calibration data or ground truth labels can be the UL RTOA calculated by the LMF / OAM based on a special UE with a known position, namely the positioning reference unit (PRU). The base station compares the true UL RTOA with the intermediate parameters output by the model, and combines a threshold set in advance, configured in advance, or notified by the LMF / OAM to determine whether the current model can continue to be used, and feeds back the determined result to the LMF / OAM where the adjudication entity is located, so that the LMF / OAM where the adjudication entity is located can make a further judgment. The base station where the monitoring entity is located can also report the accuracy or confidence level of the intermediate parameters as needed to assist the adjudication entity in making a judgment. The base station where the monitoring entity is located can also report the model identifier of the preferred model as needed, provided that the base station and the LMF / OAM need to coordinate and calibrate the understanding of the model identifier in advance. Based on this, in the embodiments of the present disclosure, the second node pre-sends the tenth information to the first node to report the capabilities supported by the second node to the first node, so that the first node can determine the capabilities supported by the second node based on the tenth information.

[0153] In combination with Figure 1For the frame shown, the management function module of the communication system's AL / ML model involves functions related to adjudication in a broad sense, including operations related to the AI / ML model, such as model selection / activation / deactivation / switching / rollback, etc.; making decisions or instructions to ensure correct inference operations based on the data received from the data collection function and the inference function; being responsible for requesting models from the model storage module for model transfer / delivery requests; inputting performance feedback / re-training requests to the model training module for model (re)training or updating, etc. These multiple functions must, to a certain extent, be based on the results of model performance monitoring, otherwise there is no basis for the corresponding adjudication. A very important output of model performance monitoring is the performance metrics or indicators, which are derived based on calculations within the monitoring entity. The monitoring entity and the adjudication entity in a broad sense may not be the same or may exist in different network devices. If the adjudication entity of the model is different from the monitoring entity responsible for deriving performance metrics, relevant auxiliary information is required between the entities to support necessary interactions, such as what performance metrics the adjudication entity requests the monitoring entity to feedback; how the monitoring entity organizes the feedback of performance metrics; what the data structure of the performance metrics is; how the adjudication entity makes appropriate adjudications based on the received performance metrics and notifies or instructs other entities to work in a signaling manner.

[0154] The performance metric is a necessary condition for triggering model adjudication. The above multiple embodiments establish an explicit connection between the model monitoring entity that outputs performance metrics and the model adjudication entity. There are several forms of aperiodic or on-demand triggered model or function management methods, based on performance metrics, based on status information, or based on model or function management suggestions. Combining the above multiple embodiments, in the embodiments of the present disclosure, the first node sends at least one of the first information, the fourth information, and the seventh information aperiodically, so as to establish an explicit connection between the first node and the second node, and the above information can all be sent aperiodically, which reduces the system resource consumption compared to the related art where the above information is sent periodically.

[0155] It should be noted that the communication methods provided in the embodiments of the present disclosure are applicable to any one of the above scenarios 1 to 3, and this is not limited herein.

[0156] In some embodiments, as Figure 15 shown, the embodiments of the present disclosure provide a communication method, which is referred to the second node. The second node may be the terminal 20 or the base station 30 shown above Figure 5 shown, and this method may include the following steps:

[0157] S701. Receive the first information.

[0158] Among them, the first information is sent non-periodically by the first node, and the first information is used to assist the second node in managing the information processing method. For the description of the first information and the information processing method, reference can be made to the corresponding description in the above Figure 6 illustrated embodiments, which will not be elaborated here.

[0159] In some embodiments, the first information includes status information for assisting the second node in managing the information processing method. Among them, the status information includes at least one of the following:

[0160] Speed information;

[0161] Distance information;

[0162] Geomorphic information.

[0163] In some embodiments, the first information further includes a switching threshold for the information processing method.

[0164] In some embodiments, after receiving the first information, the second node can manage the information processing method based on the first information to obtain a management result. Then, the second node can send second information to the first node, and the second information includes the management result of the second node managing the information processing method based on the first information.

[0165] In some embodiments, before receiving the first information, the second node can send third information to the first node, and the third information is used to request assistance in managing the information processing method of the second node.

[0166] In some embodiments, the third information is further used to request status information for assisting the second node in managing the information processing method.

[0167] In some embodiments, the third information is further used to request parameters for determining the performance of the information processing method, and the parameters include at least one of the following: true value label, calibration data.

[0168] In some embodiments, the second node receives fourth information, which is sent non-periodically by the first node, and the fourth information is used to instruct the second node to manage the information processing method. For the description of the fourth information, reference can be made to the corresponding description in the above examples, which will not be elaborated here.

[0169] In some embodiments, the fourth information includes at least one of the following:

[0170] The training direction of the information processing method;

[0171] Data credibility, which is used to represent the credibility of the input data for the information processing method. In some embodiments, after receiving the fourth information, the second node may manage the information processing method based on the fourth information to obtain a management result. Then, the second node may send the fifth information to the first node, where the fifth information includes the management result of the second node's management of the information processing method based on the fourth information, so as to facilitate the first node to determine a further information processing method management decision based on the fifth information.

[0172] In some embodiments, in order to improve the accuracy of the first node instructing the second node to manage the information processing method, before the second node receives the fourth information, the second node may send the sixth information to the first node, where the sixth information is used to request instructions to manage the information processing method of the second node.

[0173] In some embodiments, the second node receives the seventh information, which is sent by the first node non-periodically, and the seventh information is used to request reporting of performance metrics. For the description of performance metrics, reference may be made to the description of performance metrics in the above embodiments, which will not be elaborated here. The seventh information includes at least one of the following:

[0174] The reporting type of the performance metric;

[0175] The data structure of the performance metric;

[0176] The reporting quantity of the performance metric;

[0177] The reporting time of the performance metric;

[0178] The reporting accuracy of the performance metric.

[0179] In some embodiments, the seventh information further includes parameters for determining the performance of the information processing method, and the parameters include at least one of the following: true value label, calibration data.

[0180] In some embodiments, after the second node receives the seventh information, in response to the seventh information, the second node sends the eighth information to the first node, and the eighth information includes the performance metric requested by the seventh information.

[0181] In some embodiments, the performance metric is used to indicate at least one of the following:

[0182] Whether the performance of the second node's information processing method is acceptable;

[0183] The training direction of the information processing method;

[0184] The management method of the information processing method;

[0185] Parameters of the target information processing method to be used by the second node, where the parameters include at least one of the following: the identifier of the target information processing method, the type of the target information processing method, the limiting conditions of the target information processing method, and the parameters for assisting in determining the information processing method.

[0186] In some embodiments, the information processing method includes a first information processing method, and the performance metric includes a performance metric related to the first information processing method.

[0187] In some embodiments, the information processing method further includes a second information processing method, and the performance metric further includes a performance metric related to the second information processing method.

[0188] For the descriptions of the first information processing method and the second information processing method, reference may be made to the corresponding descriptions of the first information processing method and the second information processing method in the above embodiments, which will not be elaborated here.

[0189] In some embodiments, after the first node determines the management decision of the information processing method based on the performance metric included in the eighth information, the first node sends the ninth information to the second node; correspondingly, the second node receives the ninth information sent by the first node, and the ninth information includes the management decision of the information processing method determined by the first node based on the performance metric.

[0190] In some embodiments, after the second node receives the ninth information, it may determine whether to execute the management decision indicated by the ninth information. In the case of determining to execute the management decision indicated by the ninth information, after obtaining the management result by executing the management decision indicated by the ninth information, it may send the twelfth information to the first node, and the twelfth information includes the management result obtained by executing the management decision indicated by the ninth information.

[0191] In some embodiments, in order for the first node to know the capabilities supported by the second node and issue corresponding management instructions (management decisions), the second node may send the tenth information to the first node, and the tenth information is used to represent the capabilities supported by the second node.

[0192] The above embodiments respectively illustrate a communication method provided by the embodiments of the present disclosure from the perspectives of the first node and the second node. Next, a communication method provided by the embodiments of the present disclosure will be illustrated from the perspective of the interaction between the first node and the second node.

[0193] In some embodiments, as Figure 16 shown, the embodiments of the present disclosure provide a communication method, and the method includes the following steps:

[0194] S801. The first node sends the first information non-periodically.

[0195] S802. The second node manages the information processing method based on the first information to obtain a management result.

[0196] S803. The second node sends second information to the first node. The second information is used to represent the management result of the second node's management of the information processing method based on the first information.

[0197] In some embodiments, as Figure 17 shown, before step S801, the method may further include the following steps:

[0198] S800. The second node sends third information to the first node. The third information is used to request assistance for the second node to manage the information processing method.

[0199] In some embodiments, as Figure 18 shown, an embodiment of the present disclosure provides a communication method, and the method includes the following steps:

[0200] S901. The first node sends fourth information non-periodically.

[0201] The fourth information is used to instruct the second node to manage the information processing method.

[0202] S902. The second node manages the information processing method based on the fourth information to obtain a management result.

[0203] S903. The second node sends fifth information to the first node. The fifth information includes the management result of the second node's management of the information processing method based on the fourth information.

[0204] In some embodiments, as Figure 19 shown, before step S901, the method may further include the following steps:

[0205] S900. The second node sends sixth information to the first node.

[0206] The sixth information is used to request an instruction to instruct the second node to manage the information processing method.

[0207] In some embodiments, as Figure 20 shown, an embodiment of the present disclosure provides a communication method, and the method includes the following steps:

[0208] S1001. The first node sends seventh information non-periodically.

[0209] The seventh information is used to request reporting of performance metrics.

[0210] S1002. The second node sends eighth information to the first node.

[0211] The eighth information includes the performance metrics requested by the seventh information.

[0212] S1003. The first node sends the ninth information to the second node.

[0213] The ninth information includes a management decision on the information processing method determined by the first node based on the performance metrics included in the eighth information.

[0214] In the embodiments of the present disclosure, the first node sends at least one of the first information, the fourth information, and the seventh information to the second node aperiodically, so as to establish an explicit connection between the first node and the second node, and the above information can all be sent aperiodically. Compared with the related art where the above information is sent periodically, the system resource consumption is reduced.

[0215] The above mainly introduces the solution provided by the present disclosure from the perspective of the interaction between each node. It can be understood that each node, such as the first node or the second node, includes the corresponding hardware structure and / or software module for implementing the above functions. Those skilled in the art should easily realize that, combined with the algorithm steps of each example described in the embodiments disclosed herein, the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0216] The embodiments of the present disclosure can divide the functional modules of the first node or the second node according to the above method embodiments. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one functional module. The above integrated module can be implemented in the form of hardware or in the form of software. It should be noted that the division of modules in the embodiments of the present disclosure is illustrative, only a logical function division, and there can be other division methods in actual implementation. The following takes the example of dividing each functional module corresponding to each function for illustration.

[0217] Figure 21 It is a schematic diagram of the composition of a communication device provided by an embodiment of the present disclosure. As Figure 21 shown, the communication device 110 includes a sending unit 1101. In some embodiments, the communication device 110 further includes a receiving unit 1102.

[0218] The communication device 110 can be the above-mentioned first node or a chip in the first node. When the communication device 110 is used to implement the functions of the first node in the above embodiments, each unit is specifically used to implement the following functions.

[0219] A sending unit 1101, configured to send first information non-periodically, where the first information is used to assist a second node in managing an information processing manner.

[0220] In some embodiments, a receiving unit 1102 is configured to receive second information sent by the second node, where the second information is used to indicate a management result of the second node in managing an information processing manner based on the first information.

[0221] In some embodiments, the receiving unit 1102 is further configured to receive third information sent by the second node, where the third information is used to request assistance in managing an information processing manner for the second node.

[0222] In some embodiments, the sending unit 1101 is further configured to send fourth information non-periodically, where the fourth information is used to instruct the second node to manage an information processing manner.

[0223] In some embodiments, the receiving unit 1102 is further configured to receive fifth information sent by the second node, where the fifth information includes a management result of the second node in managing an information processing manner based on the fourth information.

[0224] In some embodiments, the receiving unit 1102 is further configured to receive sixth information sent by the second node, where the sixth information is used to request an instruction for the second node to manage an information processing manner.

[0225] In some embodiments, the sending unit 1101 is further configured to send seventh information non-periodically, where the seventh information is used to request reporting of performance metrics;

[0226] The receiving unit 1102 is further configured to receive eighth information sent by the second node, where the eighth information includes the performance metrics requested by the seventh information.

[0227] In some embodiments, the sending unit 1101 is further configured to send ninth information, where the ninth information includes a management decision on an information processing manner determined by the first node based on the performance metrics.

[0228] In some embodiments, the receiving unit 1102 is further configured to receive tenth information sent by the second node, where the tenth information is used to indicate capabilities supported by the second node.

[0229] Figure 22 A schematic diagram of the composition of another communication device provided by an embodiment of the present disclosure. As Figure 22 shown, the communication device 120 includes a receiving unit 1201. In some embodiments, the communication device 120 may further include a sending unit 1202.

[0230] The communication device 120 may be the above-mentioned second node or a chip in the second node. When the communication device 120 is used to implement the functions of the second node in the above embodiments, each unit is specifically used to implement the following functions.

[0231] A receiving unit 1201, configured to receive first information, where the first information is sent by the first node in an aperiodic manner, and the first information is used to assist the second node in managing the information processing method.

[0232] In some embodiments, a sending unit 1202 is configured to send second information to the first node, where the second information is used to represent the management result of the second node in managing the information processing method based on the first information.

[0233] In some embodiments, the sending unit 1202 is further configured to send third information to the first node, where the third information is used to request assistance in managing the information processing method of the second node.

[0234] In some embodiments, the receiving unit 1201 is further configured to send fifth information to the first node, where the fifth information includes the management result of the second node in managing the information processing method based on the fourth information.

[0235] In some embodiments, the sending unit 1202 is further configured to send sixth information to the first node, where the sixth information is used to request an indication to the second node to manage the information processing method.

[0236] In some embodiments, the receiving unit 1201 is further configured to receive seventh information, where the seventh information is sent by the first node in an aperiodic manner, and the seventh information is used to request reporting of performance metrics;

[0237] The sending unit 1202 is further configured to, in response to the seventh information, send eighth information to the first node, where the eighth information includes the performance metrics requested by the seventh information.

[0238] It should be noted that Figure 21 and Figure 22 The units in Figure 21 and Figure 22 may also be referred to as modules. For example, the sending unit may be referred to as a sending module. Additionally, in the embodiments shown in Figure 21 and Figure 22 , the names of the respective units may not be the names shown in the figure. For example, the sending unit may also be referred to as a communication unit, and the receiving unit may also be referred to as a communication unit.

[0239] Figure 21 and Figure 22When each unit in [the above] is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present disclosure. The storage medium storing the computer software product includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0240] In the case where the above communication device 110 or communication device 120 implements the functions of the above integrated modules in the form of hardware, the embodiments of the present disclosure provide a structural schematic diagram of a communication device. As Figure 23 shown, the communication device 130 includes: a processor 1302, a communication interface 1303, and a bus 1304. Optionally, the communication device 130 may further include a memory 1301.

[0241] The processor 1302 can be a device that implements or executes various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present disclosure. The processor 1302 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in connection with the disclosure of the present disclosure. The processor 1302 can also be a combination that implements computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0242] The communication interface 1303 is used to connect to other devices through a communication network. The communication network can be an Ethernet, a wireless access network, a wireless local area network (WLAN), etc.

[0243] The memory 1301 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0244] As a possible implementation, the memory 1301 can exist independently of the processor 1302. The memory 1301 can be connected to the processor 1302 through the bus 1304 for storing instructions or program code. When the processor 1302 calls and executes the instructions or program code stored in the memory 1301, the communication method provided by the embodiments of the present disclosure can be implemented.

[0245] In another possible implementation, the memory 1301 can also be integrated with the processor 1302.

[0246] The bus 1304 can be an extended industry standard architecture (EISA) bus, etc. The bus 1304 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 23 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0247] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the first node or the second node is divided into different functional modules to complete all or part of the functions described above.

[0248] Embodiments of the present disclosure also provide a computer-readable storage medium. All or part of the processes in the above method embodiments may be completed by computer instructions instructing relevant hardware. The program may be stored in the above computer-readable storage medium. When the program is executed, it may include the processes of the above method embodiments. The above computer-readable storage medium may also be an external storage device of the above first node or second node, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the above first node or second node. Further, the above computer-readable storage medium may also include both the internal storage unit of the above first node or second node and the external storage device. The above computer-readable storage medium is used to store the above computer program and other programs and data required by the above first node or second node. The above computer-readable storage medium may also be used to temporarily store the data that has been output or will be output.

[0249] Embodiments of the present disclosure also provide a computer program product. The computer product includes a computer program. When the computer program product runs on a computer, it causes the computer to execute any one of the communication methods provided in the above embodiments.

[0250] Although the present disclosure has been described in conjunction with various embodiments, however, in the process of implementing the claimed present disclosure, those skilled in the art can understand and realize other changes of the embodiments of the disclosure by viewing the drawings, the disclosure content, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality of cases. A single processor or other unit may implement several functions recited in the claims. Certain measures are recited in mutually different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0251] Although the present disclosure has been described in conjunction with specific features and their embodiments, it is obvious that various modifications and combinations can be made without departing from the spirit and scope of the present disclosure. Accordingly, the present specification and the drawings are only exemplary descriptions of the present disclosure defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present disclosure. Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalent technologies, the present disclosure is also intended to include these changes and modifications.

[0252] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present disclosure should be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that: Applied to the first node, the method comprises: The first information is sent aperiodically, where the first information is used to assist the second node in managing the information processing mode.

2. The method according to claim 1, characterized in that The method further comprises: Second information sent by the second node is received, where the second information is used to indicate a management result of the information processing mode management performed by the second node based on the first information.

3. The method according to claim 1, characterized in that The first information includes status information for assisting the second node in managing the information processing mode.

4. The method according to claim 3, characterized in that The status information includes at least one of the following: Speed ​​information; Distance information; Geomorphic information.

5. The method according to claim 3, characterized in that: The first information also includes a switching threshold of the information processing mode.

6. The method according to claim 1, characterized in that The method further comprises: Receive third information sent by the second node, where the third information is used to request assistance to the second node in managing the information processing mode.

7. The method according to claim 6, characterized in that The third information is also used to request status information for assisting the second node in managing the information processing mode.

8. The method according to claim 6, characterized in that The third information is also used to request parameters for determining the performance of the information processing method, and the parameters include at least one of the following: a true value label and calibration data.

9. The method according to claim 1, characterized in that: The method further comprises: The fourth information is sent aperiodically, where the fourth information is used to instruct the second node to manage the information processing mode.

10. The method according to claim 9, characterized in that The method further comprises: Fifth information sent by the second node is received, where the fifth information includes a management result of the second node managing the information processing mode based on the fourth information.

11. The method according to claim 9, characterized in that The method further comprises: Receive sixth information sent by the second node, where the sixth information is used to request and instruct the second node to manage the information processing mode.

12. The method according to claim 9, characterized in that The fourth information includes at least one of the following: Training direction of information processing methods; Data credibility, the data credibility is used to indicate the credibility of input data of the information processing method.

13. The method according to claim 1, characterized in that The method further comprises: aperiodically sending seventh information, where the seventh information is used to request reporting of performance metrics; Eighth information sent by the second node is received, where the eighth information includes the performance metric requested by the seventh information.

14. The method according to claim 13, characterized in that The seventh information includes at least one of the following: The reporting type of performance metrics; Data structures for performance metrics; The number of performance metrics reported; The reporting time of performance metrics; The reporting accuracy of performance metrics.

15. The method according to claim 13, characterized in that The performance metric is used to indicate at least one of the following: Whether the performance of the information processing method of the second node is acceptable; Training direction of information processing methods; how information is processed; Parameters of the target information processing method that the second node should use, wherein the parameters include at least one of the following: an identifier of the target information processing method, a type of the target information processing method, restrictions on the target information processing method, and parameters that assist in determining the information processing method.

16. The method according to claim 13, characterized in that The information processing method includes a first information processing method, and the performance metric includes a performance metric related to the first information processing method.

17. The method according to claim 16, characterized in that The information processing method further includes a second information processing method, and the performance metric further includes a performance metric related to the second information processing method.

18. The method according to claim 13, characterized in that The seventh information also includes parameters for determining the performance of the information processing method, and the parameters include at least one of the following: a true value label and calibration data.

19. The method according to claim 13, characterized in that The method further comprises: Ninth information is sent, where the ninth information includes a management decision of the information processing manner determined by the first node based on the performance metric.

20. The method according to claim 13, characterized in that The method further comprises: The tenth information sent by the second node is received, where the tenth information is used to indicate a capability supported by the second node.

21. A communication method, characterized in that: Applied to the second node, the method comprises: Receive first information, wherein the first information is sent non-periodically by the first node, and the first information is used to assist the second node in managing the information processing method.

22. The method according to claim 21, characterized in that The method further comprises: Sending second information to the first node, where the second information is used to indicate a management result of the second node managing the information processing mode based on the first information.

23. The method according to claim 21, characterized in that The method further comprises: Sending third information to the first node, where the third information is used to request assistance to the second node in managing the information processing mode.

24. The method according to claim 21, characterized in that The method further comprises: Receive fourth information, where the fourth information is sent aperiodically by the first node, and the fourth information is used to instruct the second node to manage the information processing mode.

25. The method according to claim 24, characterized in that The method further comprises: Sending fifth information to the first node, the fifth information including a management result of the second node managing the information processing mode based on the fourth information.

26. The method according to claim 24, characterized in that The method further comprises: Send sixth information to the first node, where the sixth information is used to request and instruct the second node to manage the information processing mode.

27. The method according to claim 21, characterized in that The method further comprises: receiving seventh information, where the seventh information is sent aperiodically by the first node, and the seventh information is used to request reporting of performance metrics; In response to the seventh information, eighth information is sent to the first node, the eighth information including the performance metric requested by the seventh information.

28. A communication device, characterized in that: include: Memory and processor; Memory and processor coupling; The memory is used to store instructions executable by the processor; When the processor executes the instructions, the method according to any one of claims 1 to 27 is performed.

29. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 27.

30. A computer program product, characterized in that The computer program product comprises computer instructions, which, when executed on a computer, cause the computer to perform the method according to any one of claims 1 to 27.

Images