WO2024083004A1

WO2024083004A1 - Ai model configuration method, terminal, and network side device

Info

Publication number: WO2024083004A1
Application number: PCT/CN2023/123880
Authority: WO
Inventors: 贾承璐; 邬华明; 孙鹏
Original assignee: 维沃移动通信有限公司
Priority date: 2022-10-17
Filing date: 2023-10-11
Publication date: 2024-04-25
Also published as: CN117938689A

Abstract

The present application relates to the technical field of communications, and discloses an AI model configuration method, a terminal, and a network side device. The AI model configuration method of embodiments of the present application comprises: a terminal receives configuration information from a network side device, the configuration information comprising at least two sets of configuration parameters, the configuration parameters comprising first information and model meta-information associated with the first information, the first information being used for constructing an AI model, and the model meta-information being used for representing a network environment in which the AI model constructed according to the first information runs; and according to the model meta-information, the terminal determines a target AI model to be used from the AI models constructed on the basis of the first information.

Description

AI model configuration method, terminal and network side equipment

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims priority to Chinese Patent Application No. 202211267696.5 filed in China on October 17, 2022, the entire contents of which are incorporated herein by reference.

Technical Field

The present application belongs to the field of communication technology, and specifically relates to an AI model configuration method, terminal and network side equipment.

Background technique

With the development of communication technology, artificial intelligence (AI) models have been introduced into communication systems. Terminals can perform corresponding operations, such as positioning, based on the AI models configured on the network side. After the AI model is configured, the reliability of the model output results may be poor due to the large difference between the current network environment and the environment during model training.

Summary of the invention

The embodiments of the present application provide an AI model configuration method, a terminal, and a network-side device, which can solve the problem of poor reliability of model output results.

In a first aspect, an AI model configuration method is provided, comprising:

The terminal receives configuration information from a network side device, the configuration information including at least two sets of configuration parameters, the configuration parameters including first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to indicate a network environment in which the AI model constructed by the first information runs;

The terminal determines, according to the model meta-information, a target AI model to be used in an AI model constructed based on the first information.

In a second aspect, an AI model configuration method is provided, including:

The network side device sends configuration information to the terminal, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to represent the network environment in which the AI model constructed by the first information runs.

In a third aspect, an AI model configuration device is provided, comprising:

A receiving module, configured to receive configuration information from a network side device, the configuration information including at least two sets of configuration parameters, the configuration parameters including first information and model meta-information associated with the first information, the first information being used to construct an AI model, and the model meta-information being used to indicate a network environment in which the AI model constructed by the first information runs;

A determination module is used to determine a target AI model to be used in an AI model constructed based on the first information according to the model meta-information.

In a fourth aspect, an AI model configuration device is provided, comprising:

A sending module is used to send configuration information to a terminal, wherein the configuration information includes at least two sets of configuration parameters, wherein the configuration parameters include first information and model meta-information associated with the first information, wherein the first information is used to construct an AI model, and the model meta-information is used to represent a network environment in which the AI model constructed by the first information runs.

In a fifth aspect, a terminal is provided, comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

In a sixth aspect, a terminal is provided, comprising a processor and a communication interface, wherein the communication interface is used to receive configuration information from a network side device, the configuration information comprising at least two sets of configuration parameters, the configuration parameters comprising first information and model meta-information associated with the first information, the first information being used to construct an AI model, and the model meta-information being used to represent the network environment in which the AI model constructed by the first information runs; the processor is used to determine, according to the model meta-information, a target AI model to be used in the AI model constructed based on the first information.

In the seventh aspect, a network side device is provided, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.

In the eighth aspect, a network side device is provided, including a processor and a communication interface, wherein the communication interface is used to send configuration information to a terminal, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to represent the network environment in which the AI model constructed by the first information runs.

In the ninth aspect, a communication system is provided, comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the AI model configuration method as described in the first aspect, and the network side device can be used to execute the steps of the AI model configuration method as described in the second aspect.

In the tenth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is 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.

In the eleventh aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions 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.

In the twelfth aspect, a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the computer 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.

In the embodiment of the present application, the terminal receives configuration information from the network side device, and the configuration information includes at least two sets of configuration parameters, and the configuration parameters include first information and model meta information associated with the first information, and the model meta information is used to represent the network environment in which the AI model constructed by the first information runs. In this way, the terminal can determine whether the current AI model is valid based on the model meta information and the current network environment information, and if the current AI model is invalid, it can further select a target AI model suitable for the current network environment information to perform corresponding operations, thereby avoiding Since the accuracy of AI model output results decreases due to changes in the network environment, the reliability of AI model use is improved.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a network structure applicable to an embodiment of the present application.

FIG2 is a schematic diagram of the structure of neurons of a neural network applicable to an embodiment of the present application;

FIG3 is a flow chart of an AI model configuration method provided in an embodiment of the present application;

FIG4 is a flow chart of another AI model configuration method provided in an embodiment of the present application;

FIG5 is a structural diagram of an AI model configuration device provided in an embodiment of the present application;

FIG6 is a structural diagram of another AI model configuration device provided in an embodiment of the present application;

FIG7 is a structural diagram of a communication device provided in an embodiment of the present application;

FIG8 is a structural diagram of a terminal provided in an embodiment of the present application;

FIG. 9 is a structural diagram of a network-side device provided in an embodiment of the present application.

Detailed ways

The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.

The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and/or" in the specification and claims represents at least one of the connected objects, and the character "/" generally represents that the objects associated with each other are in an "or" relationship.

It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE)/LTE-Advanced (LTE-A) system, but 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) and other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned systems and radio technologies as well as for other systems and radio technologies. The following description describes a new radio (NR) system for example purposes, and NR terms are used in most of the following descriptions, but these technologies can also be applied to applications other than NR system applications, such as the ^6th Generation (6G) communication system.

FIG1 shows a block diagram of a wireless communication system applicable to the embodiment of the present application. The wireless communication system includes a terminal 11 and a network side device 12. The terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer, or a network side device. Laptop Computer or laptop computer, Personal Digital Assistant (PDA), PDA, netbook, ultra-mobile personal computer (UMPC), mobile Internet Device (MID), augmented reality (AR)/virtual reality (VR) equipment, robot, wearable device (Wearable Device), vehicle user equipment (VUE), pedestrian terminal (Pedestrian User Equipment, PUE), smart home (home equipment with wireless communication function, such as refrigerator, TV, washing machine or furniture, etc.), game console, personal computer (personal computer, PC), teller machine or self-service machine and other terminal side equipment, wearable device includes: smart watch, smart bracelet, smart headset, smart glasses, smart jewelry (smart bracelet, smart bracelet, smart ring, smart necklace, smart anklet, smart anklet, etc.), smart wristband, smart clothing, etc. It should be noted that the specific type of terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network device, a radio access network (RAN), a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point or a wireless fidelity (WiFi) node, etc. The base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home B node, a home evolved B node, a transmitting receiving point (TRP) or other appropriate terms in the field, as long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary, it should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.

For ease of understanding, some contents involved in the embodiments of the present application are described below:

1. Artificial intelligence.

Artificial intelligence has been widely used in various fields. Integrating artificial intelligence into wireless communication networks and significantly improving technical indicators such as throughput, latency, and user capacity are important tasks for future wireless communication networks. There are many ways to implement AI modules, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application takes neural networks as an example for illustration, but does not limit the specific type of AI modules.

A neural network is composed of neurons, and a schematic diagram of a neuron is shown in Figure 2. In this diagram, z = a ₁ *w ₁ +···+a ₁ *w ₁ +···+a _k *w _k +b, a ₁ ,a ₂ ,…a _K are inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include the Sigmoid function, the hyperbolic tangent function (tanh), and the Rectified Linear Unit (ReLU).

The parameters of the neural network are optimized through optimization algorithms. Optimization algorithms are a type of algorithm that can help us minimize or maximize the objective function (sometimes called loss function). The objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f(.). With the model, we can get the predicted output f(x) based on the input x, and we can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find a suitable W,b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the actual situation.

At present, 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 the signal and the back propagation of the error. During the forward propagation, the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage. Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated. The process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.

Common optimization algorithms include Gradient Descent, Stochastic Gradient Descent (SGD), mini-batch gradient descent, Momentum, Stochastic Gradient Descent with momentum (also known as Nesterov), Adaptive Gradient Descent (Adagrad), Adaptive Delta (Adadelta), root mean square prop (RMSprop) and Adaptive Moment Estimation (Adam).

When these optimization algorithms backpropagate errors, they all calculate the derivative/partial derivative of the current neuron based on the error/loss obtained from the loss function, add the influence of the learning rate, the previous gradient/derivative/partial derivative, etc., get the gradient, and pass the gradient to the previous layer.

In related technologies, the actual network environment is ever-changing. After the AI model is configured, there may be a situation where the environment in which the model training data is collected does not match the current environment. For example, the positioning data is collected by the positioning reference unit (Positioning reference unit), and the signal-to-noise ratio (SNR) during collection is relatively high and the network synchronization error is very small. However, after the trained neural network model is deployed to the terminal, when the SNR is relatively low and the network synchronization error is large, the AI model cannot accurately locate the terminal. For this reason, an AI model configuration method of this application is proposed.

The following, in combination with the accompanying drawings, describes in detail the AI model configuration method provided in the embodiment of the present application through some embodiments and their application scenarios.

Referring to FIG. 3 , an embodiment of the present application provides an AI model configuration method. As shown in FIG. 3 , the AI model configuration method includes:

Step 301: The terminal receives configuration information from a network-side device, where the configuration information includes at least two sets of configuration parameters, where the configuration parameters include first information and model meta-information associated with the first information, where the first information is used to construct an AI model, and the model meta-information is used to indicate a network environment in which the AI model constructed by the first information runs;

Step 302: The terminal determines, according to the model meta-information, a target AI model to be used in an AI model constructed based on the first information.

In the embodiment of the present application, the above-mentioned model meta-information can be understood or replaced by network environment information. Specifically, the model meta-information can represent the network environment in which the AI model corresponding to the associated model identifier (Identifier, ID) runs during the training phase or actual use. The network environment may include network synchronization error, timing error, and communication link quality. The above-mentioned first information can be understood as the construction parameters for constructing the AI model. The specific content can refer to the relevant I will not go into details about the technology here.

It should be understood that each set of configuration parameters corresponds to an AI model, and the above-mentioned at least two sets of configuration parameters can be carried in one signaling (for example, configured through an information element (IE)), or carried in at least two signalings. That is to say, the network side device can deploy or configure at least two AI models for the terminal through configuration information at the same time or at different times.

Optionally, determining the target AI model to be used can be understood as determining the activated target AI model. For example, after the terminal determines the target AI model, it can activate the target AI model and perform corresponding operations (such as positioning operations) based on the target AI model.

In the embodiment of the present application, the terminal receives configuration information from the network side device, and the configuration information includes at least two sets of configuration parameters, and the configuration parameters include first information and model meta information associated with the first information, and the model meta information is used to represent the network environment in which the AI model constructed by the first information runs. In this way, the terminal can determine whether the current AI model is valid based on the model meta information and the current network environment information, and at the same time, if the current AI model is invalid, it can further select a target AI model suitable for the current network environment information to perform corresponding operations, thereby avoiding the reduction in the accuracy of the AI model output results due to changes in the network environment, thereby improving the reliability of the use of the AI model.

Optionally, in some embodiments, the terminal determines, according to the model meta-information, a target AI model to be used in an AI model constructed based on the first information, including:

The terminal receives second information from the network side device;

The terminal determines, according to the second information and the model meta-information, the target AI model in the AI model constructed based on the first information;

Among them, the second information is used to determine the target model meta-information, and the target model meta-information is the model meta-information associated with the model identifier of the target AI model.

In an embodiment of the present application, after receiving the above-mentioned second information, the terminal can determine the target model meta-information in the model meta-information associated with the first information that matches the second information, thereby determining the target AI model of the AI model constructed by the first information corresponding to the target model meta-information.

It should be understood that the second information can be understood as network environment information indicated by the network side device or a signal used by the terminal to determine the network environment information. That is, in some embodiments, the second information includes at least one of the following:

first indication information, where the first indication information is used to indicate relevant information of the model meta-information, and the relevant information is used to determine at least part of the model meta-information in the target model meta-information;

A first reference signal, wherein the first reference signal is used to determine at least part of the model meta-information in the target model meta-information.

In the embodiment of the present application, the model meta-information in the above configuration information can be understood as indicating the corresponding network environment during AI model training. The above first indication information is used to indicate the current actual network environment. By comparing the relationship between the content indicated by the first indication information and the model meta-information, it can be determined that the network environment corresponding to the training and the current actual network environment best match the target model meta-information. At this time, the corresponding operation is performed based on the target AI model corresponding to the target model meta-information, which can ensure the reliability of the output result of the target AI model.

Optionally, in some embodiments, the above-mentioned first indication information may be at least one of a meta-information identifier, a model-associated signal-to-noise ratio, a model-associated signal-to-interference-plus-noise ratio, a model-associated reference signal received power, a model-associated reference signal received quality, a model-associated network synchronization error, and a model-associated timing error.

For example, assuming that the above-mentioned model meta-information is the signal-to-noise ratio associated with the AI model, the second information may be the signal-to-noise ratio, that is, the actual signal-to-noise ratio in the current network environment. The terminal may select the model meta-information whose signal-to-noise ratio is closest to the current actual signal-to-noise ratio in the model meta-information as the target model meta-information, thereby using the target AI model suitable for the current signal-to-noise ratio environment to perform related operations, thereby improving the reliability of the output results of the AI model. Optionally, the network side device may obtain the above-mentioned signal-to-noise ratio based on the measurement of the uplink signal, and then indicate the signal-to-noise ratio to the terminal through the first indication information.

The above-mentioned first reference signal can be understood as a downlink reference signal, that is, the terminal can measure the first reference signal to obtain the current actual network environment information, and by comparing the relationship between the measurement result of the first reference signal and the model meta-information, the target model meta-information that best matches the corresponding network environment information during training and the current actual network environment information can be determined. At this time, the target AI model corresponding to the model ID associated with the target model meta-information performs corresponding operations to ensure the reliability of the output results of the target AI model. It should be noted that the above-mentioned model meta-information can usually be associated with the model ID, so that the target AI model to be used can be determined based on the model meta-information.

Optionally, in some embodiments, the model meta information includes at least one of the following:

a meta-information identifier, wherein the meta-information identifier is associated with third information, wherein the third information includes at least one of a model-associated signal-to-noise ratio, a model-associated signal-to-interference-plus-noise ratio, a model-associated reference signal received power, a model-associated reference signal received quality, a model-associated network synchronization error, and a model-associated timing error;

signal-to-noise ratio associated with the model;

Model-associated Signal to Interference plus Noise Ratio (SINR);

The reference signal received power (RSRP) associated with the model;

Model-associated Reference Signal Received Quality (RSRQ);

Model-associated network synchronization errors;

Model-associated timing errors.

In an embodiment of the present application, the above-mentioned meta-information identifier is also associated with the model ID. The terminal can obtain the SNR or SINR value of the first reference signal by measuring the first reference signal. The SNR or SINR value is associated with the channel estimation quality. For example, the larger the SINR, the more accurate the channel estimation. The estimated channel impulse response is used as the input of the AI model, and the positioning accuracy obtained is more accurate.

Optionally, the terminal obtains the RSRP or RSRQ value of the first reference signal by measuring the first reference signal. The RSRP or RSRQ value is associated with the channel estimation quality. For example, the larger the RSRQ, the more accurate the channel estimation. The estimated channel impulse response is used as the input of the AI model, and the obtained positioning accuracy is more accurate.

Optionally, the above-mentioned network synchronization error is used to indicate a network synchronization error range applicable to the AI model. For example, if the network synchronization error is 10ns, it indicates that a network synchronization error range applicable to the corresponding AI model is 0ns to 10ns.

Optionally, the above timing error is used to indicate a timing error range applicable to the AI model. For example, if the timing error is 10ns, it indicates that the timing error range applicable to the corresponding AI model is 0ns to 10ns.

Optionally, in some embodiments, the configuration parameters further include at least one of the following:

Label error of training data;

The inference error of the model.

In an embodiment of the present application, the label error is associated with the reasoning error of the model, and the reasoning error of the model can be represented by a cumulative distribution function (CDF). For example, the reasoning error of the model can be a 90% CDF positioning error (or a 90% error, or a 90% position error).

Since the configuration parameters carry at least one of the label error of the training data and the inference error of the model, the terminal can determine the performance of the model itself based on at least one of the label error and the inference error of the model to further determine whether the AI model is usable. This can further ensure the performance of the AI model used subsequently.

Optionally, in some embodiments, the target AI model is used for positioning.

In the embodiment of the present application, determining the target AI model to be used can be understood as determining the AI model used for positioning. By deploying multiple AI models, and associating different model metadata with the model ID of each AI model, when the environment changes, the terminal can dynamically select or switch the AI model according to the second indication information and/or the measurement result of the first reference signal, thereby improving the quality of positioning services.

In order to better understand the present application, some examples are provided below for illustration.

1. The impact of different label noises.

Add the same noise (Rayleigh distribution) to the real position label (x, y), that is, the noise in the two dimensions obeys the Gaussian distribution with a mean of 0 and a standard deviation of 0.5m, 1m, 2m, and 4m respectively; (90% position error = Gaussian distribution standard deviation * 1.645); the label after adding noise (x', y'):
(x',y')＝(x,y)+(e _x ,e _y );

Among them, e _x and e _y are Gaussian distributions with mean 0 and standard deviation σ respectively.

The above real location label can be called ground truth label. The test data of the indoor factory in the frequency range 1 is shown in Table 1 below.

Table I:

In the above Table 1, 50% can be understood as 50% CDF position error, which specifically means that in the corresponding cases, when the error is less than 0.35, 0.69, 1.06, 1.70 and 2.71, the proportion of users is 50%.

Based on Table 1, we can see that as the label noise standard (STD) increases, the performance will gradually decrease. Std = 4m (4*1.645 = 6.6m, 90% CDF position error is about 8.50m), at this time, after the neural network training, 90% The position error is 5.13m, which is smaller than the theoretical error of 8.50m, indicating that the neural network has a certain denoising effect and is robust to label annotation errors.

2. The impact of different channel estimation errors.

The test data of the indoor factory in the frequency range 1 is shown in Tables 2 and 3 below.

Table II:

Table 3:

Based on the above Table 2 and Table 3, we can know that:

1. As the CIR measurement noise increases, the positioning accuracy of the training model gradually decreases;

2. When the SINR of the CIR of the training set and the test set are different, the performance degradation is more serious. For example, if the training set is 30dB and the test set is -30Db, the positioning error is greater than 10m: When the SINR of the CIR of the training set is large and the SINR of the test set is small, the performance degrades sharply; that is, if the CIR noise measured by the device running the model is large, then the positioning performance is difficult to guarantee.

3. The impact of synchronization errors of different networks.

The test data of the indoor factory in the frequency range 1 is shown in Table 4 below.

Table 4:

Based on the above Table 4, it can be seen that the synchronization error will significantly affect the positioning performance of the AI model, and the larger the synchronization error of the test set, the greater the performance degradation.

Referring to FIG. 4 , an embodiment of the present application further provides an AI model configuration method. As shown in FIG. 4 , the AI model configuration method includes:

Step 401: The network side device sends configuration information to the terminal, wherein the configuration information includes at least two sets of configuration parameters. The configuration parameters include first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to represent a network environment in which the AI model constructed by the first information runs.

Optionally, after the network side device sends configuration information of at least two artificial intelligence AI models to the terminal, the method further includes:

The network side device sends second information to the terminal, where the second information is used to determine target model meta-information, and the target model meta-information is model meta-information associated with the model identifier of the target AI model.

Optionally, the second information includes at least one of the following:

Optionally, the model meta information includes at least one of the following:

signal-to-noise ratio associated with the model;

The signal-to-interference-noise ratio associated with the model;

the reference signal received power associated with the model;

the received quality of the reference signal associated with the model;

Model-associated network synchronization errors;

Model-associated timing errors.

Optionally, the configuration parameters also include at least one of the following:

Label error of training data;

The inference error of the model.

Optionally, the AI model is a model used for positioning.

The AI model configuration method provided in the embodiment of the present application can be executed by an AI model configuration device. In the embodiment of the present application, the AI model configuration device executing the AI model configuration method is taken as an example to illustrate the AI model configuration device provided in the embodiment of the present application.

Referring to FIG. 5 , an embodiment of the present application further provides an AI model configuration device. As shown in FIG. 5 , the AI model configuration device 500 includes:

A receiving module 501 is used to receive configuration information from a network side device, where the configuration information includes at least two sets of configuration parameters, where the configuration parameters include first information and model meta-information associated with the first information, where the first information is used to construct an AI model, and the model meta-information is used to indicate a network environment in which the AI model constructed by the first information runs;

The determination module 502 is used to determine, according to the model meta-information, a target AI model to be used in the AI model constructed based on the first information.

Optionally, the determining module 502 includes:

A receiving unit, configured to receive second information from a network side device;

a determining unit, configured to determine the target AI model in the AI model constructed based on the first information according to the second information and the model meta-information;

Optionally, the second information includes at least one of the following:

Optionally, the model meta information includes at least one of the following:

signal-to-noise ratio associated with the model;

The signal-to-interference-noise ratio associated with the model;

the reference signal received power associated with the model;

the received quality of the reference signal associated with the model;

Model-associated network synchronization errors;

Model-associated timing errors.

Label error of training data;

The inference error of the model.

Optionally, the target AI model is used for positioning.

6 , the embodiment of the present application further provides an AI model configuration device. As shown in FIG6 , the AI model configuration device 600 includes:

A sending module 601 is used to send configuration information to a terminal, where the configuration information includes at least two sets of configuration parameters, where the configuration parameters include first information and model meta-information associated with the first information, where the first information is used to construct an AI model, and the model meta-information is used to represent the network environment in which the AI model constructed by the first information runs.

Optionally, the sending module 601 is also used to: send second information to the terminal, the second information is used to determine target model meta-information, and the target model meta-information is model meta-information associated with the model identifier of the target AI model.

Optionally, the second information includes at least one of the following:

Optionally, the model meta information includes at least one of the following:

signal-to-noise ratio associated with the model;

The signal-to-interference-noise ratio associated with the model;

the reference signal received power associated with the model;

the received quality of the reference signal associated with the model;

Model-associated network synchronization errors;

Model-associated timing errors.

Label error of training data;

The inference error of the model.

Optionally, the AI model is a model used for positioning.

The AI model configuration 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. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of terminal 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.

The AI model configuration device provided in the embodiment of the present application can implement the various processes implemented by the method embodiments of Figures 3 to 4 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

As shown in Figure 7, an embodiment of the present application also provides a communication device 700, including a processor 701 and a memory 702, and the memory 702 stores a program or instruction that can be run on the processor 701. When the program or instruction is executed by the processor 701, the various steps of the above-mentioned AI model configuration device embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The embodiment of the present application also provides a terminal, including a processor and a communication interface, the communication interface is used to receive configuration information from a network side device, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta-information associated with the first information, the first information is used to build an AI model, and the model meta-information is used to represent the network environment in which the AI model built by the first information runs; the processor is used to determine the target AI model to be used in the AI model built based on the first information according to the model meta-information. This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the terminal embodiment and can achieve the same technical effect. Specifically, Figure 8 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application.

The terminal 800 includes but is not limited to: 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 at least some of the components of a processor 810.

Those skilled in the art will appreciate that the terminal 800 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 810 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system. The terminal structure shown in FIG8 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.

It should be understood that in the embodiment of the present application, the input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 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 a touch panel 8071 and at least one of 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. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

In the embodiment of the present application, after receiving downlink data from the network side device, the radio frequency unit 801 can transmit the data 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.

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, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 809 may include a volatile memory or a non-volatile memory, or the memory 809 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the above-mentioned modem processor The processor may not be integrated into the processor 810.

The radio frequency unit 801 is used to receive configuration information from a network side device, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta information associated with the first information, the first information is used to construct an AI model, and the model meta information is used to indicate a network environment in which the AI model constructed by the first information runs;

The processor 810 is used to determine, according to the model meta-information, a target AI model to be used in an AI model constructed based on the first information.

The embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is used to send configuration information to a terminal, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta-information associated with the first information, the first information is used to build an AI model, and the model meta-information is used to represent the network environment in which the AI model built by the first information runs. This network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this network side device embodiment, and can achieve the same technical effect.

Specifically, the embodiment of the present application also provides a network side device. As shown in Figure 9, the network side device 900 includes: an antenna 901, a radio frequency device 902, a baseband device 903, a processor 904 and a memory 905. The antenna 901 is connected to the radio frequency device 902. In the uplink direction, the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing. In the downlink direction, the baseband device 903 processes the information to be sent and sends it to the radio frequency device 902. The radio frequency device 902 processes the received information and sends it out through the antenna 901.

The method executed by the network-side device in the above embodiment may be implemented in the baseband device 903, which includes a baseband processor.

The baseband device 903 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 9, one of which is, for example, a baseband processor, which is connected to the memory 905 through a bus interface to call the program in the memory 905 and execute the network device operations shown in the above method embodiment.

The network side device may also include a network interface 906, which is, for example, a common public radio interface (CPRI).

Specifically, the network side device 900 of the embodiment of the present application also includes: instructions or programs stored in the memory 905 and executable on the processor 904. The processor 904 calls the instructions or programs in the memory 905 to execute the method executed by each module shown in Figure 6 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

The present application also provides a readable storage medium, wherein a program or instruction is stored on the readable storage medium. When the program or instruction is executed by the processor, the various processes of the above-mentioned AI model configuration method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

The embodiment of the present application further 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, implement the various processes of the above-mentioned AI model configuration method embodiment, and can achieve the same technical effect, to avoid repetition, it is not repeated here. It should be understood that the chip mentioned in the embodiment of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

The embodiments of the present application further provide a computer program/program product, which is stored in a storage medium, and is executed by at least one processor to implement the various processes of the above-mentioned AI model configuration method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

An embodiment of the present application also provides a communication system, including: a terminal and a network side device, wherein the terminal is used to execute the various processes as shown in Figure 3 and the various method embodiments on the terminal side mentioned above, and the network side device is used to execute the various processes as shown in Figure 4 and the various method embodiments on the network side device side mentioned above, and can achieve the same technical effect. In order to avoid repetition, it will not be repeated here.

It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be noted 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 reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

An AI model configuration method, comprising:

The terminal receives configuration information from a network side device, the configuration information including at least two sets of configuration parameters, the configuration parameters including first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to indicate a network environment in which the AI model constructed by the first information runs;

The terminal determines, according to the model meta-information, a target AI model to be used in an AI model constructed based on the first information.
The method according to claim 1, wherein the terminal determines, according to the model meta information, a target AI model to be used in an AI model constructed based on the first information, comprising:

The terminal receives second information from the network side device;

The terminal determines, according to the second information and the model meta-information, the target AI model in the AI model constructed based on the first information;

Among them, the second information is used to determine the target model meta-information, and the target model meta-information is the model meta-information associated with the model identifier of the target AI model.
The method according to claim 2, wherein the second information includes at least one of the following:

first indication information, where the first indication information is used to indicate relevant information of the model meta-information, and the relevant information is used to determine at least part of the model meta-information in the target model meta-information;

A first reference signal, wherein the first reference signal is used to determine at least part of the model meta-information in the target model meta-information.
The method according to any one of claims 1 to 3, wherein the model meta information includes at least one of the following:

a meta-information identifier, wherein the meta-information identifier is associated with third information, wherein the third information includes at least one of a model-associated signal-to-noise ratio, a model-associated signal-to-interference-plus-noise ratio, a model-associated reference signal received power, a model-associated reference signal received quality, a model-associated network synchronization error, and a model-associated timing error;

signal-to-noise ratio associated with the model;

The signal-to-interference-noise ratio associated with the model;

the reference signal received power associated with the model;

the received quality of the reference signal associated with the model;

Model-associated network synchronization errors;

Model-associated timing errors.
The method according to any one of claims 1 to 4, wherein the configuration parameters further include at least one of the following:

Label error of training data;

The inference error of the model.
The method according to any one of claims 1 to 5, wherein the target AI model is used for positioning.
An AI model configuration method, comprising:

The network side device sends configuration information to the terminal, the configuration information includes at least two sets of configuration parameters, the configuration parameters include first information and model meta-information associated with the first information, the first information is used to construct an AI model, and the model meta-information is used to represent the network environment in which the AI model constructed by the first information runs.
The method according to claim 7, wherein after the network side device sends configuration information of at least two artificial intelligence AI models to the terminal, the method further comprises:

The network side device sends second information to the terminal, where the second information is used to determine target model meta-information, and the target model meta-information is model meta-information associated with the model identifier of the target AI model.
The method according to claim 8, wherein the second information includes at least one of the following:

first indication information, where the first indication information is used to indicate relevant information of the model meta-information, and the relevant information is used to determine at least part of the model meta-information in the target model meta-information;

A first reference signal, wherein the first reference signal is used to determine at least part of the model meta-information in the target model meta-information.
The method according to any one of claims 7 to 9, wherein the model meta information includes at least one of the following:

a meta-information identifier, wherein the meta-information identifier is associated with third information, wherein the third information includes at least one of a model-associated signal-to-noise ratio, a model-associated signal-to-interference-plus-noise ratio, a model-associated reference signal received power, a model-associated reference signal received quality, a model-associated network synchronization error, and a model-associated timing error;

signal-to-noise ratio associated with the model;

The signal-to-interference-noise ratio associated with the model;

the reference signal received power associated with the model;

the received quality of the reference signal associated with the model;

Model-associated network synchronization errors;

Model-associated timing errors.
The method according to any one of claims 7 to 10, wherein the configuration parameters further include at least one of the following:

Label error of training data;

The inference error of the model.
The method according to any one of claims 7 to 11, wherein the AI model is a model for positioning.
An AI model configuration device, comprising:

A receiving module, configured to receive configuration information from a network side device, the configuration information including at least two sets of configuration parameters, the configuration parameters including first information and model meta-information associated with the first information, the first information being used to construct an AI model, and the model meta-information being used to indicate a network environment in which the AI model constructed by the first information runs;

A determination module is used to determine a target AI model to be used in an AI model constructed based on the first information according to the model meta-information.
An AI model configuration device, comprising:

A sending module is used to send configuration information to a terminal, wherein the configuration information includes at least two sets of configuration parameters, wherein the configuration parameters include first information and model meta-information associated with the first information, wherein the first information is used to construct an AI model, and the model meta-information is used to represent the network environment in which the AI model constructed by the first information runs.
A terminal comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the AI model configuration method as described in any one of claims 1 to 6 are implemented.
A network side device comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the AI model configuration method as described in any one of claims 6 to 12 are implemented.
A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the steps of the AI model configuration method as described in any one of claims 1 to 12.
A chip comprises a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the AI model configuration method as described in any one of claims 1 to 12.
A computer program/program product, wherein the computer program/program product is stored in a non-transitory readable storage medium, and the program/program product is executed by at least one processor to implement the steps of the AI model configuration method as described in any one of claims 1 to 12.
A communication device comprises a processor and a memory, wherein the memory stores a program or instruction that can be executed on the processor, and when the program or instruction is processed and executed, the steps of the AI model configuration method as described in any one of claims 1 to 12 are implemented.