Reporting method and device, transmission method and device, terminal and network side equipment

Abstract

The invention discloses a reporting method, a transmission method, a device, a terminal and network side equipment, and belongs to the technical field of communication, and the reporting method comprises the steps that the terminal reports a first monitoring result to the network side equipment, and the first monitoring result is used for indicating a monitoring result of the terminal on an AI unit of a terminal side.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a reporting method, a transmission method, a device, a terminal, and a network-side device. Background Art

[0002] With the development of Artificial Intelligence (AI) technology, AI units (which can also be referred to as AI models) have also been applied to communication systems. Currently, in a communication system, a fixed computing resource is allocated for a single AI unit for model inference. However, some AI units have a high frequency of computing resource invocation, while some have a low frequency. This approach can cause AI units with low requirements to occupy computing resources for a long time, while AI units with high requirements cannot operate effectively due to insufficient computing resources, resulting in waste of computing resources. Summary of the Invention

[0003] Embodiments of this application provide a reporting method, a transmission method, a device, a terminal, and a network-side device, which can solve the problem of waste of transmission resources in related technologies.

[0004] In a first aspect, a reporting method is provided, which is executed by a terminal. The method includes:

[0005] The terminal reports a first monitoring result to a network-side device, where the first monitoring result is used to indicate the monitoring result of the terminal for an AI unit on the terminal side.

[0006] In a second aspect, a transmission method is provided, which is executed by a network-side device. The method includes:

[0007] The network-side device receives the first monitoring result reported by the terminal, where the first monitoring result is used to indicate the monitoring result of the terminal for the AI unit on the terminal side.

[0008] In a third aspect, a reporting device is provided, including:

[0009] A reporting module, configured to report a first monitoring result to a network-side device, where the first monitoring result is used to indicate the monitoring result of the terminal for the AI unit on the terminal side.

[0010] In a fourth aspect, a transmission device is provided, including:

[0011] A second receiving module, configured to receive the first monitoring result reported by the terminal, where the first monitoring result is used to indicate the monitoring result of the terminal for the AI unit on the terminal side.

[0012] Fifth aspect, a terminal is provided, which includes a processor and a memory. The memory stores a program or instructions that can run on the processor. When the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0013] Sixth aspect, a terminal is provided, which includes a processor and a communication interface. The communication interface is used to report a first monitoring result to a network-side device, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

[0014] Seventh aspect, a network-side device is provided, which includes a processor and a memory. The memory stores a program or instructions that can run on the processor. When the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

[0015] Eighth aspect, a network-side device is provided, which includes a processor and a communication interface. The communication interface is used to receive the first monitoring result reported by the terminal, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

[0016] Ninth aspect, a readable storage medium is provided. A program or instructions are stored on the readable storage medium. When the program or instructions are executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.

[0017] Tenth aspect, a wireless communication system is provided, which includes: a terminal and a network-side device. The terminal can be used to execute the steps of the method described in the first aspect, and the network-side device can be used to execute the steps of the method described in the second aspect.

[0018] Eleventh aspect, a chip is provided. The chip includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instructions to implement the method described in the first aspect, or to implement the method described in the second aspect.

[0019] Twelfth aspect, a computer program / program product is provided. The computer program / program product is stored in a storage medium. The program / program product is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0020] In an embodiment of the present application, the terminal reports a first monitoring result to the network-side device, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side. Thereby, the network-side device can timely learn about the usage of the AI unit on the terminal side, which helps the network-side device to adjust the usage of the AI unit on the terminal side. For example, deactivate some currently running AI units with low computing resource requirements and activate AI units with high computing resource requirements, etc., to avoid resource waste caused by long-term occupation of resources by low-demand AI units, thereby improving the resource utilization rate on the terminal side. Description of the Drawings

[0021] Figure 1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied;

[0022] Figure 2 is one of the flowcharts of a reporting method provided by an embodiment of the present application;

[0023] Figure 3a is the second flowchart of a reporting method provided by an embodiment of the present application;

[0024] Figure 3b is the third flowchart of a reporting method provided by an embodiment of the present application;

[0025] Figure 3c is the fourth flowchart of a reporting method provided by an embodiment of the present application;

[0026] Figure 4 is the flowchart of a transmission method provided by an embodiment of the present application;

[0027] Figure 5 is the structural diagram of a reporting device provided by an embodiment of the present application;

[0028] Figure 6 is the structural diagram of a transmission device provided by an embodiment of the present application;

[0029] Figure 7 is the structural diagram of a communication device provided by an embodiment of the present application;

[0030] Figure 8 is the structural diagram of a terminal provided by an embodiment of the present application;

[0031] Figure 9 is the structural diagram of a network-side device provided by an embodiment of the present application. Detailed Embodiments

[0032] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0033] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are usually of the same category, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "or" in the present application means at least one of the connected objects. For example, "A or B" covers three scenarios, namely, Scenario 1: including A and not including B; Scenario 2: including B and not including A; Scenario 3: including both A and B. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0034] The term "indicate" in the present application can be either a direct indication (or an explicit indication) or an indirect indication (or an implicit indication). Among them, a direct indication can be understood as that the sender clearly informs the recipient of specific information, operations to be performed, or request results, etc. in the sent indication; an indirect indication can be understood as that the recipient determines the corresponding information according to the indication sent by the sender, or makes a judgment and determines the operations to be performed or request results, etc. according to the judgment result.

[0035] It should be noted that the technology described in the embodiments of this application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, and can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in the embodiments of this application are often used interchangeably, and the described technology can be used not only in the systems and radio technologies mentioned above, but also in other systems and radio technologies. The following description describes the New Radio (NR) system for example purposes, and the NR terminology is used in most of the following descriptions, but these technologies can also be applied to systems other than the NR system, such as the 6th Generation (6 th Generation, 6G) communication system.

[0036] Figure 1Block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. Among them, the terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer, a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device, a flight vehicle, a vehicle user equipment (VUE), a shipborne device, a pedestrian user equipment (PUE), a smart home (home devices with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), a game console, a personal computer (PC), a teller machine or a self-service machine, etc. Wearable devices include: smart watches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart ankle chains, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle user equipment can also be called a vehicle terminal, a vehicle controller, a vehicle module, a vehicle component, a vehicle chip or a vehicle unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. Among them, the access network device can also be called a radio access network (RAN) device, a radio access network function or a radio access network unit. The access network device can include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home Node B (HNB), home evolved Node B, Transmission Reception Point (TRP), or some other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiments of this application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0037] For better understanding, the following explains the related concepts that may be involved in the embodiments of this application.

[0038] Artificial intelligence has currently been widely applied in various fields. There are various implementation methods for the AI module, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. In this application, a neural network is taken as an example for illustration, but the specific type of the AI module is not limited.

[0039] The parameters of the neural network are optimized through an optimization algorithm. The optimization algorithm is a type of algorithm that can help us minimize or maximize the objective function (sometimes also called the loss function). And the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). After having the model, according to the input x, we can obtain the predicted output f(x), and we can calculate the gap between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find the appropriate weights (multiplicative coefficients) and biases (additive coefficients) to minimize the value of the above loss function. The smaller the loss value, the closer our AI model is to the real situation.

[0040] Currently, the common optimization algorithms are basically based on the error Back Propagation (BP) algorithm. The basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of signals and the backward propagation of errors. During forward propagation, the input samples are fed into the input layer and processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it enters the backward propagation stage of errors. The error backpropagation is to transmit the output error back layer by layer through the hidden layer to the input layer in a certain form, and distribute the error to all units of each layer, so as to obtain the error signals of each layer unit. This error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer in the forward propagation of signals and the backward propagation of errors is carried out cyclically. The process of continuously adjusting the weights is also the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until a pre-set number of learning times is reached.

[0041] Generally speaking, according to different types of problems to be solved, the selected AI algorithms and the adopted AI models are also different. At present, the main method to improve the performance of 5G networks with the help of AI is to enhance or replace the existing algorithms or processing modules through algorithms and AI models based on neural networks. In specific scenarios, algorithms and AI models based on neural networks can achieve better performance than deterministic algorithms. Commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks, etc. With the help of existing AI tools, the construction, training, and verification of neural networks can be realized.

[0042] Replacing modules in the existing system through AI / Machine Learning (ML) methods can effectively improve the system performance. For example, for Channel State Information (CSI) prediction, the historical CSI is input into the AI model, and the AI model analyzes the time-domain change characteristics of the channel and outputs the future CSI. By monitoring and analyzing the system performance, the CSI prediction has a very large performance gain compared to the non-prediction scheme. At the same time, the prediction accuracy that can be achieved is also different for different predicted future times.

[0043] In addition to the CSI prediction use case based on AI, various use cases such as CSI compression, positioning enhancement, beam management, load balancing, resource allocation, channel estimation, power amplifier nonlinearity suppression, and signal demodulation can also be realized based on AI. Specific discussions are not made here.

[0044] Currently, in a communication system, when using an AI-based solution, a fixed computing resource (also known as computing power resource) is allocated for a single AI unit or use case for model inference. However, this fixed matching method can lead to waste of computing resources. For example, some AI units have a high frequency of calling computing resources, while some have a low frequency. The terminal reports the calling situation of each AI unit's computing resources to the network side respectively, resulting in waste of transmission resources.

[0045] It should be noted that the AI unit mentioned in this application can also be referred to as an AI model, AI structure, etc. Or the AI unit can be a processing unit that can implement specific algorithms, formulas, processing flows, capabilities, etc. related to AI. Or the AI unit can be a processing method, algorithm, function, module or unit for a specific data set. Or the AI unit can be a processing method, algorithm, function, module or unit running on AI-related hardware such as GPU, NPU, TPU, ASIC, etc. This application does not make specific limitations in this regard. Optionally, the specific data set includes the input and / or output of the AI unit.

[0046] Optionally, the identifier of the AI unit can be an AI model identifier, AI structure identifier, AI algorithm identifier, functionality ID, physical identifier, logical identifier, global identifier, local identifier, or the identifier of the specific data set associated with the AI unit, or the identifier of the specific scenario, environment, channel characteristics, device related to the AI, or the identifier of the function, feature, ability or module related to the AI. This application does not make specific limitations in this regard.

[0047] Next, with reference to the accompanying drawings, through some embodiments and their application scenarios, the reporting method, device, terminal, network side device, etc. provided by the embodiments of this application will be described in detail.

[0048] Please refer to Figure 2 , Figure 2 which is a flowchart of a reporting method provided by an embodiment of this application. As Figure 2 shown, the method includes the following steps:

[0049] Step 201: The terminal reports a first monitoring result to the network side device, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side.

[0050] Optionally, the first monitoring result may be used to indicate the monitoring result of one or more AI units on the terminal side of the terminal, or the monitoring result of all AI units on the terminal side of the terminal (such as the overall monitoring result for all AI units on the terminal side), or the overall monitoring result of the AI units being used on the terminal side of the terminal. It should be noted that the terminal may monitor the number of AI units being used on the terminal side, the consumed resources, the remaining available resources, etc., to obtain the first monitoring result.

[0051] In the embodiments of the present application, the terminal reports the first monitoring result to the network-side device. The first monitoring result is used to indicate the monitoring result of the AI units on the terminal side of the terminal, such as the overall monitoring result of all AI units or the AI units being used on the terminal side. Thus, the terminal can reflect the usage situation of the AI units on the terminal side to the network-side device through one report, without the terminal reporting the monitoring results for each AI unit separately, effectively saving the reporting resources of the terminal, and also helping the network-side device to timely learn about the usage situation of the AI units on the terminal side, enabling the network-side device to adjust the AI units on the terminal side according to the first monitoring result, such as deactivating some AI units with low computing resource requirements that are running, activating AI units with high computing resource requirements, etc., avoiding the waste of computing resources caused by the long-term occupation of computing resources by low-demand AI units, thereby improving the utilization rate of computing resources on the terminal side.

[0052] Optionally, the first monitoring result includes at least one of the following:

[0053] The number of AI units activated by the terminal;

[0054] The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal;

[0055] The number of AI units not activated by the terminal currently;

[0056] The ratio of the number of AI units not activated by the terminal currently to the total number of AI units that can be activated by the terminal;

[0057] The size of the computing resources of the terminal occupied by the AI units activated by the terminal;

[0058] The ratio of the size of the computing resources of the terminal occupied by the AI units activated by the terminal to the size of the computing resources available for AI functions of the terminal. For example, it may be the ratio of the size of the computing resources of the terminal occupied by the AI units activated by the terminal within a first preset time period to the size of the computing resources available for AI functions of the terminal within the first preset time period;

[0059] The storage size of the terminal occupied by the AI units activated by the terminal;

[0060] The ratio of the storage size occupied by the activated AI units of the terminal to the storage size available for AI functions of the terminal. For example, it can be calculated as the ratio of the storage size occupied by the activated AI units of the terminal within a second preset time period to the storage size available for AI functions of the terminal within the second preset time period;

[0061] The power consumption size occupied by the activated AI units of the terminal;

[0062] The ratio of the power consumption size occupied by the activated AI units of the terminal to the power consumption size available for AI functions of the terminal. For example, it can be calculated as the ratio of the power consumption size occupied by the activated AI units of the terminal within a third preset time period to the power consumption size available for AI functions of the terminal within the third preset time period.

[0063] Wherein, the number of non-activated AI units of the terminal can be the difference between the total number of AI units that can be activated by the terminal and the number of activated AI units of the terminal.

[0064] In addition, it should be noted that the computing resources described in the embodiments of the present application can be video memory, computing units (described by floating-point operations per second (FLOPS)), memory access cost (MAC), etc.

[0065] Exemplarily, the first monitoring result includes the number of activated AI units of the terminal and the computing resource size occupied by the activated AI units in the terminal. Furthermore, based on this first monitoring result, the network side can also know the number of currently activated or in-use AI units on the terminal side and the computing resource size occupied by these AI units in the terminal. Thus, the network side device can perform relevant operations on the AI units on the terminal side according to the first monitoring result, such as deactivating certain AI units and / or activating certain AI units, etc. Of course, the content included in the first monitoring result can also be at least one of the above, and no specific enumeration is made here.

[0066] In the embodiments of the present application, the terminal reports the first monitoring result, so that the network-side device can perform corresponding operations on the AI unit on the terminal side according to the first monitoring result. For example, if the first monitoring result indicates that the AI units activated by the terminal occupy a large amount of storage of the terminal, the network-side device may instruct the terminal to deactivate some AI units, so as to reduce the storage size occupied by the AI units on the terminal; for another example, if the first monitoring result indicates that the number of AI units not currently activated by the terminal is large and / or the ratio of the number of AI units not currently activated by the terminal to the number of AI units that can be activated by the terminal is large, the network-side device may instruct the terminal to activate some or all of the currently unactivated AI units, so as to make full use of the computing resources on the terminal side, etc., and avoid resource waste caused by long-term occupation of computing resources, storage resources, etc. by low-demand AI units, thereby improving the utilization rate of resources on the terminal side. Of course, the first monitoring result may also be other possible situations, and the corresponding operations performed by the network-side device according to the first monitoring result may also be other possible situations, which are not specifically listed here.

[0067] Optionally, before the terminal reports the first monitoring result to the network side, the method further includes:

[0068] The terminal receives configuration information sent by the network-side device, and the configuration information is used to instruct the terminal to report the first monitoring result.

[0069] Exemplarily, the network-side device first sends configuration information to the terminal, and the configuration information is used to instruct the terminal to report the monitoring result for the AI unit on the terminal side. Then the terminal monitors the usage situation of the AI unit on the terminal side according to the configuration information, obtains the first monitoring result and reports it to the network-side device. In this way, it also makes the reporting behavior of the terminal can be executed based on the configuration information sent by the network-side device, which helps to standardize the reporting behavior of the terminal.

[0070] Optionally, the configuration information includes at least one of the following:

[0071] The reporting type of the first monitoring result, and the reporting type includes periodic reporting, aperiodic reporting, semi-persistent reporting, etc.;

[0072] The reporting condition of the first monitoring result;

[0073] The stop reporting condition of the first monitoring result;

[0074] The reporting resource of the first monitoring result, and the reporting resource includes time domain resource, frequency domain resource, space domain resource, etc.;

[0075] The bearer channel of the first monitoring result.

[0076] Exemplarily, the configuration information includes the reporting type of the first monitoring result. Then, based on the configuration information, the terminal can know which reporting type to use for reporting the first monitoring result, such as periodic reporting, aperiodic reporting, semi-persistent reporting, etc. of the first monitoring result. Alternatively, the first configuration information includes the reporting condition and / or the stop reporting condition of the first monitoring result. Then, based on the configuration information, the terminal can know when to report and / or stop reporting the first monitoring result. Alternatively, the configuration information may also include the reporting resource and the bearer channel of the first monitoring result, so that the terminal can clarify the transmission resource or the bearer channel corresponding to the first monitoring result according to the configuration information.

[0077] In the embodiments of the present application, the network-side device sends configuration information to the terminal. The configuration information includes at least one of the reporting type, reporting condition, stop reporting condition, reporting resource, and bearer channel of the first monitoring result. Then, it effectively standardizes the reporting behavior of the terminal for the first monitoring result, which helps to improve the transmission performance between the terminal and the network-side device.

[0078] Optionally, the reporting condition of the first monitoring result includes at least one of the following:

[0079] The reporting period of the first monitoring result;

[0080] The reporting trigger condition of the first monitoring result;

[0081] A preset reporting condition, which is related to at least one of the following: a preset time, a preset area, and a preset event.

[0082] In one implementation, when the reporting type of the first monitoring result is periodic reporting, the reporting condition is the reporting period of the first monitoring result.

[0083] In another implementation, when the reporting type of the first monitoring result is aperiodic reporting, the reporting condition is the reporting trigger condition of the first monitoring result, or the reporting trigger threshold. For example, the reporting trigger condition or the reporting trigger threshold may be: the number of AI units activated on the terminal side exceeds a preset number, the power consumption occupied by the AI units on the terminal side exceeds a preset power consumption, etc. When the reporting trigger condition or the reporting trigger threshold is met, the terminal is triggered to report the first monitoring result.

[0084] In yet another implementation, when the reporting type of the first monitoring result is semi-persistent reporting, the reporting condition may also be the reporting trigger condition of the first monitoring result, or the reporting trigger threshold, and may also include the reporting period after the first monitoring result starts to be reported.

[0085] In another implementation manner, the reporting condition of the first monitoring result may be a preset reporting condition. For example, the preset reporting condition is related to a preset time, that is, the terminal reports the first monitoring result at the preset time; or the preset reporting condition is related to a preset area, that is, the terminal reports the first monitoring result in the preset area; or the preset reporting condition is related to a preset event. For example, the terminal reports the first monitoring result when connected to WiFi. Optionally, the preset reporting condition may be configured by a network-side device, agreed upon by a protocol, or pre-configured.

[0086] In the embodiments of the present application, the reporting condition of the first monitoring result includes at least one of the above, so that the terminal can clearly know under what circumstances to report the first monitoring result according to the reporting condition, and also makes the reporting behavior of the terminal for the first monitoring result more flexible.

[0087] Optionally, before the terminal reports the first monitoring result to the network-side device, the method further includes:

[0088] The terminal reports a first capability to the network-side device, and the first capability is related to the AI unit of the terminal.

[0089] For example, the first capability may be related to the number of AI units of the terminal. For example, the first capability is used to indicate the total number of AI units that can be activated by the terminal; or the first capability may be related to the storage, power consumption, or computing resources available for the AI function of the terminal, etc.

[0090] Optionally, the first capability includes at least one of the following:

[0091] A first number, the first number is used to indicate the total number of AI units that can be activated by the terminal. For example, the first number may be the maximum value of the number of AI units that can be activated on the terminal side within a fourth preset time period. The fourth preset time period may be agreed upon by a protocol, configured by a network-side device, or pre-configured. The first number may be determined based on factors such as the computing resources, storage, power consumption, and management overhead of the AI units of the terminal;

[0092] The binding information between the AI unit and the AI resource. For example, some AI units may require dedicated AI resources for processing. The binding information may be described by a judgment information (such as whether the AI unit has binding information with the AI resource), or it may also be a specific description of the binding information, such as which AI unit and which part of the AI resource are bound, etc.;

[0093] The storage size available for the AI function of the terminal;

[0094] The computing resource size available for the AI function of the terminal;

[0095] The terminal can be used for the power consumption of AI functions.

[0096] In the embodiments of the present application, the terminal can report a first capability to the network-side device. The first capability includes at least one of the above. Furthermore, based on the first capability, the network-side device can know the total number of AI units that the terminal can activate and the relevant restriction information of the AI units (such as the storage size, power consumption size, computing resource size available for AI functions in the terminal, and the binding information between AI units and AI resources, etc.). This helps the network-side device perform relevant operations on the AI units on the terminal side, such as activating or deactivating some AI units, canceling some AI units, or turning off the AI functions of some AI units.

[0097] Optionally, the terminal reports a first monitoring result to the network-side device, including:

[0098] When the terminal receives a start reporting instruction sent by the network-side device, it reports the first monitoring result to the network-side device.

[0099] In the embodiments of the present application, the terminal may start reporting the first monitoring result to the network-side device when it receives a start reporting instruction sent by the network-side device, thus effectively standardizing the reporting behavior on the terminal side.

[0100] It should be noted that before receiving the start reporting instruction sent by the network-side device, the terminal may have already performed monitoring on the AI units on the terminal side to obtain the first monitoring result. Or, the terminal may also perform monitoring on the AI units on the terminal side after receiving the start reporting instruction sent by the network-side device to obtain the first monitoring result.

[0101] Optionally, after the terminal reports the first monitoring result to the network-side device, the method further includes:

[0102] When the terminal receives a stop reporting instruction sent by the network-side device, it stops reporting the first monitoring result to the network-side device.

[0103] It should be noted that if the terminal does not receive the stop reporting instruction sent by the network-side device, the terminal may report the first monitoring result to the network-side device according to its reporting type, such as periodic reporting, aperiodic reporting, or semi-persistent reporting, etc. When the terminal receives the stop reporting instruction sent by the network-side device, it stops reporting the first monitoring result to the network-side device, thus effectively standardizing the reporting behavior on the terminal side.

[0104] Optionally, when the terminal stops reporting the first monitoring result to the network device, it can still perform overall monitoring of the AI unit on the terminal side; when the terminal receives a start reporting instruction sent by the network device, the terminal can report the first monitoring result obtained from its overall monitoring of the AI unit to the network device.

[0105] In the embodiments of this application, after the terminal reports the first monitoring result to the network device, the method further includes at least one of the following:

[0106] The terminal receives an activation instruction or a deactivation instruction for the first AI unit sent by the network device;

[0107] The terminal activates or deactivates the first AI unit;

[0108] Wherein, the first AI unit is the AI unit on the terminal side. Optionally, the first AI unit can be one or more.

[0109] In one implementation manner, the terminal receives an activation instruction or a deactivation instruction for the first AI unit sent by the network device, and activates the first AI unit according to the activation instruction, or deactivates the first AI unit according to the deactivation instruction. That is to say, in this implementation manner, it is the network device that decides the activation or deactivation of the first AI unit. Alternatively, when the terminal receives an activation instruction or a deactivation instruction, it may also not execute the activation instruction or the deactivation instruction. For example, if the network device sends an activation instruction for the first AI unit, and the computing resources currently available for the AI function of the terminal are small, the terminal may not execute the activation of the first AI unit to avoid excessive occupation of the computing resources of the terminal.

[0110] In another implementation manner, the terminal activates or deactivates the first AI unit. For example, the terminal may actively activate or deactivate the first AI unit according to factors such as its own storage size, computing resource size, or power consumption size, that is, without executing based on relevant instructions from the network device. Alternatively, the terminal may also activate or deactivate the first AI unit when it receives an activation instruction or a deactivation instruction for the first AI unit sent by the network device.

[0111] In the embodiments of this application, the activation or deactivation of the first AI unit by the terminal can be performed independently, or can also be performed based on an activation instruction or a deactivation instruction sent by the network device, which makes the activation or deactivation behavior of the AI unit on the terminal side by the terminal more flexible.

[0112] Among them, the activation instruction or deactivation instruction sent by the network-side device can be sent to a specific terminal in unicast form, or can be sent to multiple terminals in broadcast or multicast form. In addition, the deactivation in the embodiments of the present application enables the terminal to free up resources or overhead to support the inference or operation of other AI units, effectively improving the utilization rate of resources on the terminal side.

[0113] Optionally, after the terminal activates or deactivates the first AI unit, the method further includes:

[0114] The terminal reports activation information or deactivation information to the network-side device;

[0115] Among them, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit.

[0116] In the embodiments of the present application, after the terminal activates the first AI unit, the terminal reports activation information to the network-side device, so that the network-side device can know that the terminal has activated the first AI unit based on the activation information. Or, after the terminal deactivates the first AI unit, the terminal reports deactivation information to the network-side device, so that the network-side device can know that the terminal has deactivated the first AI unit based on the deactivation information. Furthermore, the network-side device can timely know the behavior of the terminal on the first AI unit according to the activation information or deactivation information, which also helps the network-side device to perform subsequent related operations on the AI unit on the terminal side.

[0117] Optionally, the terminal activates or deactivates the first AI unit, including:

[0118] The terminal receives the priority information and the activation instruction or deactivation instruction for the first AI unit sent by the network-side device;

[0119] The terminal activates or deactivates the first AI unit according to the priority information and the activation instruction or deactivation instruction.

[0120] Exemplarily, the network-side device sends the priority information of the first AI unit and an activation instruction or a deactivation instruction for the first AI unit to the terminal, where the priority information may be used to indicate the processing priority of the first AI unit; the terminal determines whether to activate or deactivate the first AI unit according to the priority level indicated by the priority information of the first AI unit, as well as its own computing resources, storage, power consumption, and AI unit management overhead, etc. For example, it activates or deactivates the first AI unit, or it may also not activate or deactivate the first AI unit. In the embodiments of the present application, when the terminal receives the activation instruction or deactivation instruction for the first AI unit sent by the network-side device, it also needs to determine whether to activate or deactivate the first AI unit according to the priority information of the first AI unit sent by the network-side device, thereby making the processing method of the terminal for the first AI unit more flexible.

[0121] Further, the terminal may send activation information or deactivation information to the network-side device according to the activation status of the first AI unit.

[0122] Optionally, the terminal activates or deactivates the first AI unit, including:

[0123] The terminal receives the priority information of the first AI unit sent by the network-side device;

[0124] The terminal sends a first request message to the network-side device according to the priority information, where the first request message is used to request to activate or deactivate the first AI unit;

[0125] The terminal receives the activation indication or deactivation indication of the first AI unit sent by the network-side device;

[0126] The terminal activates or deactivates the first AI unit according to the activation indication or deactivation indication.

[0127] Exemplarily, when the terminal receives the priority information of the first AI unit sent by the network-side device, it determines whether to activate or deactivate the first AI unit according to the priority level indicated by the priority information, as well as its own computing resources, storage, power consumption, and AI unit management overhead, etc., and then determines the first request information and sends the first request information to the network-side device; the network-side device sends an activation instruction or a deactivation instruction for the first AI unit to the terminal according to the first request information. For example, if the first request information requests to activate the first AI unit, the network-side device sends an activation instruction to the terminal; if the first request information requests to deactivate the first AI unit, the network-side device sends a deactivation instruction to the terminal. The terminal performs corresponding activation or deactivation on the first AI unit according to the activation instruction or deactivation instruction. In this way, the activation or deactivation of the first AI unit is realized through the interaction between the terminal and the network-side device, effectively expanding the processing methods and processing flexibility for the first AI unit.

[0128] For better understanding, the reporting method provided in this application will be explained below through several specific embodiments.

[0129] Embodiment 1:

[0130] As Figure 3a shown, the method includes the following steps:

[0131] Step 311, the terminal reports the first capability to the network-side device, and the first capability is related to the AI unit of the terminal;

[0132] Step 312, the network-side device sends configuration information to the terminal, and the configuration information is used to instruct the terminal to report the first monitoring result for the AI unit on the terminal side;

[0133] Step 313, the terminal reports the first monitoring result to the network-side device.

[0134] It should be noted that the content included in the first capability, the content of the configuration information, and the content included in the first monitoring result can be referred to the description in the above Figure 2 embodiment, which will not be elaborated here.

[0135] Embodiment 2:

[0136] As Figure 3b shown, the method includes the following steps:

[0137] Step 321, the terminal reports the first monitoring result to the network-side device;

[0138] Step 322, the network-side device determines whether to activate or deactivate the first AI unit according to the first monitoring result and the priority of the first AI unit;

[0139] Step 323: The network device sends an activation or deactivation instruction for the first AI unit to the terminal.

[0140] Embodiment 3:

[0141] As Figure 3c shown, the method includes the following steps:

[0142] Step 331: The network device sends the priority information of the first AI unit to the terminal;

[0143] Step 332: The network device sends an activation instruction or a deactivation instruction for the first AI unit to the terminal;

[0144] Step 333: The terminal decides whether to activate the first AI unit according to the above priority information and the activation instruction or deactivation instruction;

[0145] Step 334: The terminal sends an activation confirmation message of the first AI unit to the network device according to the activation situation of the first AI unit, such as a confirmation message for activating the first AI unit;

[0146] Step 335: The terminal determines whether to deactivate the first AI unit;

[0147] Step 336: The terminal sends a deactivation request message or a deactivation notification message for the first AI unit to the network device;

[0148] Step 337: The network device sends a deactivation indication for the first AI unit to the terminal, and the terminal can deactivate the first AI unit based on this indication.

[0149] It should be noted that the relevant concepts and specific implementation processes involved in the above embodiments can be referred to Figure 2 the description in the method embodiment, which will not be elaborated here.

[0150] Please refer to Figure 4 , Figure 4 is a flowchart of a transmission method provided by an embodiment of the present application, and the method is applied to a network device. As Figure 4 shown, the method includes the following steps:

[0151] Step 401: The network device receives the first monitoring result reported by the terminal, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

[0152] Optionally, the first monitoring result includes at least one of the following:

[0153] The number of AI units activated by the terminal;

[0154] The ratio of the number of activated AI units of the terminal to the total number of AI units that can be activated by the terminal;

[0155] The number of AI units that are currently not activated by the terminal;

[0156] The ratio of the number of AI units that are currently not activated by the terminal to the total number of AI units that can be activated by the terminal;

[0157] The size of the computing resources of the terminal occupied by the activated AI units of the terminal;

[0158] The ratio of the size of the computing resources of the terminal occupied by the activated AI units of the terminal to the size of the computing resources available for the AI function of the terminal;

[0159] The storage size of the terminal occupied by the activated AI units of the terminal;

[0160] The ratio of the storage size of the terminal occupied by the activated AI units of the terminal to the storage size available for the AI function of the terminal;

[0161] The power consumption size of the terminal occupied by the activated AI units of the terminal;

[0162] The ratio of the power consumption size of the terminal occupied by the activated AI units of the terminal to the power consumption size available for the AI function of the terminal.

[0163] Optionally, before the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0164] The network-side device sends configuration information to the terminal, and the configuration information is used to instruct the terminal to report the first monitoring result.

[0165] Optionally, the configuration information includes at least one of the following:

[0166] The reporting type of the first monitoring result;

[0167] The reporting condition of the first monitoring result;

[0168] The stop reporting condition of the first monitoring result;

[0169] The reporting resource of the first monitoring result;

[0170] The bearer channel of the first monitoring result.

[0171] Optionally, the reporting condition of the first monitoring result includes at least one of the following:

[0172] The reporting period of the first monitoring result;

[0173] Report triggering conditions for the first monitoring result;

[0174] A preset reporting condition, which is related to at least one of the following: a preset time, a preset area, and a preset event.

[0175] Optionally, before the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0176] The network-side device receives the first capability reported by the terminal, and the first capability is related to the AI unit of the terminal.

[0177] Optionally, the first capability includes at least one of the following:

[0178] A first number, which is used to indicate the total number of AI units that can be activated by the terminal;

[0179] Binding information between the AI unit and the AI resource;

[0180] The storage size available for the AI function of the terminal;

[0181] The computing resource size available for the AI function of the terminal;

[0182] The power consumption size available for the AI function of the terminal.

[0183] Optionally, before the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0184] The network-side device sends a start reporting instruction to the terminal, and the start reporting instruction is used to instruct the terminal to start reporting the first monitoring result.

[0185] Optionally, after the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0186] The network-side device sends a stop reporting instruction to the terminal, and the stop reporting instruction is used to instruct the terminal to stop reporting the first monitoring result.

[0187] Optionally, after the network-side device receives the first monitoring result reported by the terminal, the method further includes any one of the following:

[0188] The network-side device sends an activation instruction or a deactivation instruction for the first AI unit to the terminal;

[0189] The network-side device sends priority information and an activation instruction or a deactivation instruction for the first AI unit to the terminal.

[0190] Wherein, the first AI unit is the AI unit on the terminal side.

[0191] Optionally, after the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0192] The network-side device sends priority information for the first AI unit to the terminal;

[0193] The network-side device receives first request information sent by the terminal, where the first request information is used to request activation or deactivation of the first AI unit;

[0194] The network-side device sends an activation instruction or a deactivation instruction for the first AI unit to the terminal.

[0195] Optionally, after the network-side device receives the first monitoring result reported by the terminal, the method further includes:

[0196] The network-side device receives activation information or deactivation information reported by the terminal;

[0197] Wherein, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit.

[0198] It should be noted that the transmission method applied to the network-side device provided in the embodiments of the present application corresponds to the above-mentioned reporting method applied to the terminal side. The specific implementation processes and related concepts involved in the embodiments of the present application can refer to the descriptions in the above-mentioned terminal-side method embodiments, and will not be specifically described in this embodiment.

[0199] In the embodiments of the present application, the network-side device receives the first monitoring result reported by the terminal. The first monitoring result is used to indicate the monitoring result of the terminal-side AI unit by the terminal, for example, the overall monitoring result of all terminal-side AI units or the AI units in use. Thus, the terminal can reflect the usage situation of the terminal-side AI unit to the network-side device through one report, without the terminal reporting the monitoring results for each AI unit separately, and the network-side device does not need to receive the monitoring results for each AI unit on the terminal side multiple times, effectively saving transmission resources; it also enables the network-side device to timely learn about the usage situation of the terminal-side AI unit, which helps the network-side device to adjust the usage of the terminal-side AI unit, such as deactivating some running AI units with low computing resource requirements and activating AI units with high computing resource requirements, etc., avoiding the waste of computing resources caused by the long-term occupation of computing resources by low-demand AI units, thereby improving the utilization rate of terminal-side computing resources.

[0200] For the reporting method provided in the embodiments of the present application, the execution subject may be a reporting device. In the embodiments of the present application, the reporting method is executed by the reporting device as an example to illustrate the reporting device provided in the embodiments of the present application.

[0201] Please refer to Figure 5 , Figure 5 which is the structural diagram of a reporting device provided by an embodiment of the present application. As Figure 5 shown, the reporting device 500 includes:

[0202] A reporting module 501, configured to report a first monitoring result to a network-side device, where the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

[0203] Optionally, the first monitoring result includes at least one of the following:

[0204] The number of AI units activated by the terminal;

[0205] The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal;

[0206] The number of AI units not currently activated by the terminal;

[0207] The ratio of the number of AI units not currently activated by the terminal to the total number of AI units that can be activated by the terminal;

[0208] The size of the computing resources occupied by the AI units activated by the terminal on the terminal;

[0209] The ratio of the size of the computing resources occupied by the AI units activated by the terminal on the terminal to the size of the computing resources available for the AI function on the terminal;

[0210] The size of the storage occupied by the AI units activated by the terminal on the terminal;

[0211] The ratio of the size of the storage occupied by the AI units activated by the terminal on the terminal to the size of the storage available for the AI function on the terminal;

[0212] The power consumption size occupied by the AI units activated by the terminal on the terminal;

[0213] The ratio of the power consumption size occupied by the AI units activated by the terminal on the terminal to the power consumption size available for the AI function on the terminal.

[0214] Optionally, the device further includes:

[0215] A first receiving module, configured to receive configuration information sent by a network-side device, where the configuration information is used to instruct the terminal to report the first monitoring result.

[0216] Optionally, the configuration information includes at least one of the following:

[0217] The reporting type of the first monitoring result;

[0218] Reporting conditions for the first monitoring result;

[0219] Stop reporting conditions for the first monitoring result;

[0220] Reporting resources for the first monitoring result;

[0221] Bearer channels for the first monitoring result.

[0222] Optionally, the reporting conditions for the first monitoring result include at least one of the following:

[0223] Reporting period for the first monitoring result;

[0224] Reporting trigger conditions for the first monitoring result;

[0225] Preset reporting conditions, which are related to at least one of the following: preset time, preset area, and preset event.

[0226] Optionally, the reporting module 501 is further configured to:

[0227] Report a first capability to a network-side device, where the first capability is related to the AI unit of the terminal.

[0228] Optionally, the first capability includes at least one of the following:

[0229] A first number, which is used to indicate the total number of AI units that can be activated by the terminal;

[0230] Binding information between the AI unit and the AI resource;

[0231] Storage size available for the AI function of the terminal;

[0232] Computing resource size available for the AI function of the terminal;

[0233] Power consumption size available for the AI function of the terminal.

[0234] Optionally, the reporting module 501 is further configured to:

[0235] When receiving a start reporting instruction sent by the network-side device, report the first monitoring result to the network-side device.

[0236] Optionally, the device further includes:

[0237] A stop module, configured to stop reporting the first monitoring result to the network-side device when receiving a stop reporting instruction sent by the network-side device.

[0238] Optionally, the device further includes a first execution module, configured to execute at least one of the following:

[0239] Receive an activation instruction or a deactivation instruction for the first AI unit sent by the network-side device;

[0240] Activate or deactivate the first AI unit;

[0241] Wherein, the first AI unit is the AI unit on the terminal side.

[0242] Optionally, the reporting module 501 is further configured to:

[0243] Report activation information or deactivation information to the network-side device;

[0244] Wherein, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit.

[0245] Optionally, the first execution module is further configured to:

[0246] Receive priority information, an activation instruction or a deactivation instruction for the first AI unit sent by the network-side device;

[0247] Activate or deactivate the first AI unit according to the priority information and the activation instruction or the deactivation instruction.

[0248] Optionally, the first execution module is further configured to:

[0249] Receive priority information for the first AI unit sent by the network-side device;

[0250] Send a first request message to the network-side device according to the priority information, where the first request message is used to request to activate or deactivate the first AI unit;

[0251] Receive an activation indication or a deactivation indication for the first AI unit sent by the network-side device;

[0252] Activate or deactivate the first AI unit according to the activation indication or the deactivation indication.

[0253] The device provided by the embodiment of the present application can report a first monitoring result to a network-side device, where the first monitoring result is used to indicate the monitoring result of the terminal for the AI units on the terminal side. For example, it can be the overall monitoring result of all AI units or the in-use AI units on the terminal side. Thus, it can reflect the usage situation of the AI units on the terminal side to the network-side device through one report, without separately reporting the monitoring results for each AI unit, effectively saving reporting resources. It also helps the network-side device make adjustments to the AI units on the terminal side according to the first monitoring result, which is conducive to improving the resource utilization rate on the terminal side.

[0254] The reporting device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. This electronic device can be a terminal or other devices other than the terminal. Exemplarily, the terminal can include, but is not limited to, the types of the terminal 11 listed above, and other devices can be a server, a Network Attached Storage (NAS), etc. The embodiment of the present application does not make specific limitations.

[0255] The reporting device provided by the embodiment of the present application can implement Figure 2 each process implemented by the method embodiment and achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0256] Please refer to Figure 6 , Figure 6 which is a structural diagram of a transmission device provided by the embodiment of the present application. As Figure 6 shown, the transmission device 600 includes:

[0257] A second receiving module 601, configured to receive the first monitoring result reported by the terminal, where the first monitoring result is used to indicate the monitoring result of the terminal for the AI units on the terminal side.

[0258] Optionally, the first monitoring result includes at least one of the following:

[0259] The number of AI units activated by the terminal;

[0260] The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal;

[0261] The number of AI units not activated by the terminal currently;

[0262] The ratio of the number of AI units not activated by the terminal currently to the total number of AI units that can be activated by the terminal;

[0263] The size of the computing resources occupied by the AI units activated by the terminal on the terminal;

[0264] The ratio of the computing resource size occupied by the activated AI unit of the terminal to the computing resource size available for the AI function of the terminal;

[0265] The storage size occupied by the activated AI unit of the terminal;

[0266] The ratio of the storage size occupied by the activated AI unit of the terminal to the storage size available for the AI function of the terminal;

[0267] The power consumption size occupied by the activated AI unit of the terminal;

[0268] The ratio of the power consumption size occupied by the activated AI unit of the terminal to the power consumption size available for the AI function of the terminal.

[0269] Optionally, the device further includes:

[0270] A first sending module, configured to send configuration information to the terminal, where the configuration information is used to instruct the terminal to report the first monitoring result.

[0271] Optionally, the configuration information includes at least one of the following:

[0272] The reporting type of the first monitoring result;

[0273] The reporting condition of the first monitoring result;

[0274] The stop reporting condition of the first monitoring result;

[0275] The reporting resource of the first monitoring result;

[0276] The bearer channel of the first monitoring result.

[0277] Optionally, the reporting condition of the first monitoring result includes at least one of the following:

[0278] The reporting period of the first monitoring result;

[0279] The reporting trigger condition of the first monitoring result;

[0280] A preset reporting condition, which is related to at least one of the following: a preset time, a preset area, and a preset event.

[0281] Optionally, the second receiving module is further configured to:

[0282] Optionally, the first capability includes at least one of the following:

[0283] A first number, which is used to indicate the total number of AI units that can be activated by the terminal;

[0284] Binding information of the AI unit and AI resources;

[0285] The storage size available for the AI function in the terminal;

[0286] The computing resource size available for the AI function in the terminal;

[0287] The power consumption size available for the AI function in the terminal.

[0288] Receive the first capability reported by the terminal, where the first capability is related to the AI unit of the terminal.

[0289] Optionally, the device further includes:

[0290] A third sending module, configured to send a start reporting instruction to the terminal, where the start reporting instruction is used to instruct the terminal to start reporting the first monitoring result.

[0291] Optionally, the device further includes:

[0292] A fourth sending module, configured to send a stop reporting instruction to the terminal, where the stop reporting instruction is used to instruct the terminal to stop reporting the first monitoring result.

[0293] Optionally, the device further includes a second sending module, configured to perform at least one of the following:

[0294] Send an activation instruction or a deactivation instruction for the first AI unit to the terminal;

[0295] Send the priority information and the activation instruction or deactivation instruction for the first AI unit to the terminal.

[0296] Wherein, the first AI unit is the AI unit on the terminal side.

[0297] Optionally, the device further includes a fifth sending module, configured to:

[0298] Send the priority information for the first AI unit to the terminal;

[0299] The second receiving module is further configured to: receive the first request information sent by the terminal, where the first request information is used to request to activate or deactivate the first AI unit;

[0300] The fifth sending module is further configured to: send an activation indication or a deactivation indication for the first AI unit to the terminal.

[0301] Optionally, the second receiving module is further configured to:

[0302] Receive the activation information or deactivation information reported by the terminal;

[0303] Among them, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit.

[0304] The device provided by the embodiments of the present application does not need to receive the monitoring results of each AI unit on the terminal side multiple times, effectively saving transmission resources.

[0305] The transmission device provided by the embodiments of the present application can implement Figure 4 each process implemented by the method embodiments and achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0306] Such as Figure 7 shown, the embodiments of the present application also provide a communication device 700, including a processor 701 and a memory 702. A program or instruction that can run on the processor 701 is stored on the memory 702. For example, when the communication device 700 is a terminal, when the program or instruction is executed by the processor 701, it implements each step of the above reporting method embodiment and can achieve the same technical effects. When the communication device 700 is a network-side device, when the program or instruction is executed by the processor 701, it implements each step of the above transmission method embodiment and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0307] The embodiments of the present application also provide a terminal, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps in the method embodiment as Figure 2 shown. This terminal embodiment corresponds to the above terminal-side method embodiment. Each implementation process and implementation manner of the above method embodiment can be applied to this terminal embodiment and can achieve the same technical effects. Specifically, Figure 8 is a schematic diagram of the hardware structure of a terminal for implementing the embodiments of the present application.

[0308] The terminal 800 includes but is not limited to at least some components such as a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and a processor 810.

[0309] Those skilled in the art can understand that the terminal 800 may further include a power supply (such as a battery) for supplying power to each component. The power supply can be logically connected to the processor 810 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 8The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0310] It should be understood that in the embodiments of the present application, the input unit 804 may include a Graphics Processing Unit (GPU) 8041 and a microphone 8042. The graphics processor 8041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 807 includes at least one of a touch panel 8071 and other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. The other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, which will not be elaborated here.

[0311] In the embodiments of the present application, after the radio frequency unit 801 receives downlink data from a network-side device, it can be transmitted to the processor 810 for processing; in addition, the radio frequency unit 801 can send uplink data to the network-side device. Generally, the radio frequency unit 801 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[0312] The memory 809 can be used to store software programs or instructions and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 809 may include volatile memory or non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static RAM (SRAM), a dynamic RAM (DRAM), a synchronous DRAM (SDRAM), a double data rate SDRAM (DDR SDRAM), an enhanced SDRAM (ESDRAM), a synch link DRAM (SLDRAM), and a direct rambus RAM (DRRAM). The memory 809 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[0313] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor may not be integrated into the processor 810 either.

[0314] Among them, the radio frequency unit 801 is used to report a first monitoring result to a network-side device, and the first monitoring result is used to indicate the monitoring result of the terminal for the AI unit on the terminal side.

[0315] In the embodiments of the present application, the terminal can report a first monitoring result to the network-side device, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side. For example, it is the overall monitoring result of all AI units or the AI units in use on the terminal side. Thus, the terminal can reflect the usage situation of the AI units on the terminal side to the network-side device through one report, without the terminal reporting the monitoring results for each AI unit separately, effectively saving the reporting resources of the terminal.

[0316] It can be understood that the implementation processes of the various implementation manners mentioned in this embodiment can refer to the relevant descriptions of the above method embodiments on the terminal side and achieve the same or corresponding technical effects. To avoid repetition, they will not be elaborated here.

[0317] The embodiments of the present application further provide a network-side device, including a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the method embodiment as Figure 4 shown. This embodiment of the network-side device corresponds to the above method embodiment of the network-side device. Each implementation process and implementation manner of the above method embodiment can be applied to this embodiment of the network-side device and can achieve the same technical effects.

[0318] Specifically, the embodiments of the present application further provide a network-side device. As Figure 9 shown, the network-side device 900 includes: an antenna 91, a radio frequency device 92, a baseband device 93, a processor 94, and a memory 95. The antenna 91 is connected to the radio frequency device 92. In the uplink direction, the radio frequency device 92 receives information through the antenna 91 and sends the received information to the baseband device 93 for processing. In the downlink direction, the baseband device 93 processes the information to be sent and sends it to the radio frequency device 92. After processing the received information, the radio frequency device 92 sends it out through the antenna 91.

[0319] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 93, and the baseband device 93 includes a baseband processor.

[0320] The baseband device 93 may include, for example, at least one baseband board, and multiple chips are arranged on the baseband board. As Figure 9 shown, one of the chips is, for example, a baseband processor, which is connected to the memory 95 through a bus interface to call the programs in the memory 95 and execute the operations of the network device shown in the above method embodiments.

[0321] The network-side device may further include a network interface 96, and this interface is, for example, a Common Public Radio Interface (CPRI).

[0322] Specifically, the network-side device 900 according to an embodiment of the present invention further includes: instructions or programs stored in the memory 95 and executable on the processor 94. The processor 94 calls the instructions or programs in the memory 95 to execute Figure 6 the methods executed by the modules shown, and achieves the same technical effects. To avoid repetition, they will not be elaborated here.

[0323] An embodiment of the present application further provides a readable storage medium. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, each process of the above reporting method or transmission method embodiment is implemented, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0324] Wherein, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0325] Another embodiment of the present application provides a chip. The chip includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above reporting method or transmission method embodiment, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0326] It should be understood that the chip mentioned in the embodiment of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0327] Another embodiment of the present application provides a computer program / program product. The computer program / program product is stored in a storage medium. The computer program / program product is executed by at least one processor to implement each process of the above reporting method or transmission method embodiment, and the same technical effects can be achieved. To avoid repetition, they will not be elaborated here.

[0328] An embodiment of the present application further provides a communication system, including: a terminal and a network-side device. The terminal can be used to execute the steps of the reporting method as described above, and the network-side device can be used to execute the steps of the transmission method as described above.

[0329] It should be noted that in this text, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0330] From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions for causing a terminal or a network-side device to execute the methods described in the various embodiments of the present application.

[0331] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms of embodiments without departing from the purpose of the present application and the scope protected by the claims. These embodiments are all within the protection scope of the present application.

Claims

1. A reporting method, characterized in that, Including: The terminal reports a first monitoring result to the network-side device, and the first monitoring result is used to indicate the monitoring result of the artificial intelligence (AI) unit on the terminal side.

2. The method according to claim 1, characterized in that, The first monitoring result includes at least one of the following: The number of AI units activated by the terminal; The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal; The number of AI units not currently activated by the terminal; The ratio of the number of AI units not currently activated by the terminal to the total number of AI units that can be activated by the terminal; The size of the computing resources occupied by the AI units activated by the terminal on the terminal; The ratio of the size of the computing resources occupied by the AI units activated by the terminal on the terminal to the size of the computing resources available for the AI function on the terminal; The size of the storage occupied by the AI units activated by the terminal on the terminal; The ratio of the size of the storage occupied by the AI units activated by the terminal on the terminal to the size of the storage available for the AI function on the terminal; The power consumption size occupied by the AI units activated by the terminal on the terminal; The ratio of the power consumption size occupied by the AI units activated by the terminal on the terminal to the power consumption size available for the AI function on the terminal.

3. The method according to claim 1, characterized in that, Before the terminal reports the first monitoring result to the network-side device, the method further includes: The terminal receives configuration information sent by the network-side device, and the configuration information is used to instruct the terminal to report the first monitoring result.

4. The method according to claim 3, characterized in that The configuration information includes at least one of the following: The reporting type of the first monitoring result; The reporting condition of the first monitoring result; The stop reporting condition of the first monitoring result; The reporting resource of the first monitoring result; The bearer channel of the first monitoring result.

5. The method according to claim 4, wherein The reporting condition of the first monitoring result includes at least one of the following: The reporting period of the first monitoring result; The reporting trigger condition of the first monitoring result; A preset reporting condition, which is related to at least one of the following: a preset time, a preset area, and a preset event.

6. The method according to any one of claims 1-5, characterized in that, Before the terminal reports the first monitoring result to the network-side device, the method further includes: The terminal reports a first capability to the network-side device, and the first capability is related to the AI unit of the terminal.

7. The method according to claim 6, characterized in that, The first capability includes at least one of the following: A first number, which is used to indicate the total number of AI units that can be activated by the terminal; The binding information between the AI unit and the AI resource; The size of the storage available for the AI function on the terminal; The size of the computing resources available for the AI function on the terminal; The power consumption size available for the AI function on the terminal.

8. The method according to any one of claims 1-7, characterized in that, The terminal reports the first monitoring result to the network-side device, including: The terminal reports the first monitoring result to the network-side device when receiving a start reporting instruction sent by the network-side device.

9. The method according to any one of claims 1 - 8, characterized in that, After the terminal reports the first monitoring result to the network-side device, the method further includes: The terminal stops reporting the first monitoring result to the network-side device when receiving a stop reporting instruction sent by the network-side device.

10. The method according to any one of claims 1-9, characterized in that, After the terminal reports the first monitoring result to the network-side device, the method further includes at least one of the following: The terminal receives an activation instruction or a deactivation instruction for a first AI unit sent by a network-side device; The terminal activates or deactivates the first AI unit; Wherein, the first AI unit is an AI unit on the terminal side.

11. The method according to claim 10, wherein After the terminal activates or deactivates the first AI unit, the method further includes: The terminal reports activation information or deactivation information to the network-side device; Wherein, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit.

12. The method according to claim 10, wherein The terminal activates or deactivates the first AI unit, including: The terminal receives priority information for the first AI unit and an activation instruction or a deactivation instruction sent by the network-side device; The terminal activates or deactivates the first AI unit according to the priority information and the activation instruction or the deactivation instruction.

13. The method according to claim 10, wherein The terminal activates or deactivates the first AI unit, including: The terminal receives priority information for the first AI unit sent by the network-side device; The terminal sends a first request message to the network-side device according to the priority information, and the first request message is used to request to activate or deactivate the first AI unit; The terminal receives an activation indication or a deactivation indication for the first AI unit sent by the network-side device; The terminal activates or deactivates the first AI unit according to the activation indication or the deactivation indication.

14. A transmission method, characterized in that, Including: The network-side device receives a first monitoring result reported by the terminal, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

15. The method according to claim 14, characterized in that The first monitoring result includes at least one of the following: The number of AI units activated by the terminal; The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal; The number of AI units not activated by the terminal currently; The ratio of the number of AI units not activated by the terminal currently to the total number of AI units that can be activated by the terminal; The size of the computing resources occupied by the AI units activated by the terminal on the terminal; The ratio of the size of the computing resources occupied by the AI units activated by the terminal on the terminal to the size of the computing resources available for AI functions on the terminal; The size of the storage occupied by the AI units activated by the terminal on the terminal; The ratio of the size of the storage occupied by the AI units activated by the terminal on the terminal to the size of the storage available for AI functions on the terminal; The size of the power consumption occupied by the AI units activated by the terminal on the terminal; The ratio of the size of the power consumption occupied by the AI units activated by the terminal on the terminal to the size of the power consumption available for AI functions on the terminal.

16. The method according to claim 14, wherein Before the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device sends configuration information to the terminal, and the configuration information is used to instruct the terminal to report the first monitoring result.

17. The method according to claim 16, characterized in that The configuration information includes at least one of the following: The reporting type of the first monitoring result; The reporting condition of the first monitoring result; The stop reporting condition of the first monitoring result; The reporting resource of the first monitoring result; The bearer channel of the first monitoring result.

18. The method according to claim 17, wherein The reporting conditions of the first monitoring result include at least one of the following: The reporting period of the first monitoring result; The reporting trigger condition of the first monitoring result; A preset reporting condition, which is related to at least one of the following: a preset time, a preset area, and a preset event.

19. The method according to any one of claims 14 - 18, characterized in that, Before the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device receives the first capability reported by the terminal, and the first capability is related to the AI unit of the terminal.

20. The method according to claim 19, wherein The first capability includes at least one of the following: A first number, which is used to indicate the total number of AI units that can be activated by the terminal; The binding information between the AI unit and the AI resource; The storage size available for the AI function of the terminal; The computing resource size available for the AI function of the terminal; The power consumption size available for the AI function of the terminal.

21. The method according to any one of claims 14 - 20, characterized in that, Before the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device sends a start reporting instruction to the terminal, and the start reporting instruction is used to instruct the terminal to start reporting the first monitoring result.

22. The method according to any one of claims 14-21, characterized in that, After the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device sends a stop reporting instruction to the terminal, and the stop reporting instruction is used to instruct the terminal to stop reporting the first monitoring result.

23. The method according to any one of claims 14-22, characterized in that After the network-side device receives the first monitoring result reported by the terminal, the method further includes any one of the following: The network-side device sends an activation instruction or a deactivation instruction for the first AI unit to the terminal; The network-side device sends the priority information and an activation instruction or a deactivation instruction for the first AI unit to the terminal; Wherein, the first AI unit is the AI unit on the terminal side.

24. The method according to any one of claims 14-22, characterized in that, After the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device sends the priority information for the first AI unit to the terminal; The network-side device receives the first request information sent by the terminal, and the first request information is used to request to activate or deactivate the first AI unit; The network-side device sends an activation indication or a deactivation indication for the first AI unit to the terminal; Wherein, the first AI unit is the AI unit on the terminal side.

25. The method according to any one of claims 14-24, characterized in that, After the network-side device receives the first monitoring result reported by the terminal, the method further includes: The network-side device receives the activation information or the deactivation information reported by the terminal; Wherein, the activation information is used to indicate that the terminal has activated the first AI unit, and the deactivation information is used to indicate that the terminal has deactivated the first AI unit, and the first AI unit is the AI unit on the terminal side.

26. A reporting device, characterized in that, Includes: A reporting module, which is used to report the first monitoring result to the network-side device, and the first monitoring result is used to indicate the monitoring result of the AI unit on the terminal side by the terminal.

27. The device according to claim 26, characterized in that, The first monitoring result includes at least one of the following: The number of AI units activated by the terminal; The ratio of the number of AI units activated by the terminal to the total number of AI units that can be activated by the terminal; The number of AI units that are not currently activated in the terminal; The ratio of the number of AI units that are not currently activated in the terminal to the total number of AI units that can be activated in the terminal; The size of the computing resources occupied by the AI units that are activated in the terminal; The ratio of the size of the computing resources occupied by the AI units that are activated in the terminal to the size of the computing resources available for AI functions in the terminal; The size of the storage occupied by the AI units that are activated in the terminal; The ratio of the size of the storage occupied by the AI units that are activated in the terminal to the size of the storage available for AI functions in the terminal; The power consumption size occupied by the AI units that are activated in the terminal; The ratio of the power consumption size occupied by the AI units that are activated in the terminal to the power consumption size available for AI functions in the terminal.

28. The device according to claim 26, characterized in that, The device further includes: A first receiving module, configured to receive configuration information sent by a network-side device, where the configuration information is used to instruct the terminal to report the first monitoring result.

29. The device according to claim 26, wherein The reporting module is further configured to: Report a first capability to a network-side device, where the first capability is related to the AI units of the terminal.

30. The device according to any one of claims 26 - 29, characterized in that, The device further includes a first execution module, configured to perform at least one of the following: Receive an activation instruction or a deactivation instruction for a first AI unit sent by a network-side device; Activate or deactivate the first AI unit; Wherein, the first AI unit is an AI unit on the terminal side.

31. A transmission device, characterized in that, Includes: A second receiving module, configured to receive a first monitoring result reported by a terminal, where the first monitoring result is used to indicate the monitoring result of the AI units on the terminal side by the terminal.

32. The device according to claim 31, characterized in that, The first monitoring result includes at least one of the following: The number of AI units that are activated in the terminal; The ratio of the number of AI units that are activated in the terminal to the total number of AI units that can be activated in the terminal; The number of AI units that are not currently activated in the terminal; The ratio of the number of AI units that are not currently activated in the terminal to the total number of AI units that can be activated in the terminal; The size of the computing resources occupied by the AI units that are activated in the terminal; The ratio of the size of the computing resources occupied by the AI units that are activated in the terminal to the size of the computing resources available for AI functions in the terminal; The size of the storage occupied by the AI units that are activated in the terminal; The ratio of the size of the storage occupied by the AI units that are activated in the terminal to the size of the storage available for AI functions in the terminal; The power consumption size occupied by the AI units that are activated in the terminal; The ratio of the power consumption size occupied by the AI units that are activated in the terminal to the power consumption size available for AI functions in the terminal.

33. The device according to claim 31, characterized in that, The device further includes: A first sending module, configured to send configuration information to a terminal, where the configuration information is used to instruct the terminal to report the first monitoring result.

34. The device according to claim 31, characterized in that, The second receiving module is further configured to: Receive a first capability reported by a terminal, where the first capability is related to the AI units of the terminal.

35. The device according to any one of claims 31-34, characterized in that The device further includes a second sending module, configured to perform at least one of the following: Send an activation instruction or a deactivation instruction for a first AI unit to a terminal; Send priority information for a first AI unit and an activation instruction or a deactivation instruction to a terminal; Among them, the first AI unit is the AI unit on the terminal side.

36. A terminal, characterized in that, It includes a processor and a memory. The memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the reporting method described in any one of claims 1-13 are implemented.

37. A network-side device, characterized in that, It includes a processor and a memory. The memory stores programs or instructions that can run on the processor. When the programs or instructions are executed by the processor, the steps of the transmission method described in any one of claims 14-25 are implemented.

38. A readable storage medium, characterized in that, Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by the processor, the steps of the reporting method described in any one of claims 1-13 are implemented, or the steps of the transmission method described in any one of claims 14-25 are implemented.

Images