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

Ai model configuration method, terminal, and network side device Download PDF

Info

Publication number
WO2024083004A1
WO2024083004A1 PCT/CN2023/123880 CN2023123880W WO2024083004A1 WO 2024083004 A1 WO2024083004 A1 WO 2024083004A1 CN 2023123880 W CN2023123880 W CN 2023123880W WO 2024083004 A1 WO2024083004 A1 WO 2024083004A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
information
meta
configuration
target
Prior art date
Application number
PCT/CN2023/123880
Other languages
French (fr)
Chinese (zh)
Inventor
贾承璐
邬华明
孙鹏
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2024083004A1 publication Critical patent/WO2024083004A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to an AI model configuration method, terminal and network side equipment.
  • AI artificial intelligence
  • 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.
  • 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.
  • an AI model configuration method 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.
  • 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 a network environment in which the AI model constructed by the first information runs.
  • a terminal comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.
  • a terminal comprising a processor and a communication interface, wherein the 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.
  • a network side device which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the second aspect are implemented.
  • a network side device 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.
  • a communication system 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.
  • a readable storage medium on which a program or instruction is stored.
  • the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.
  • a chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • the first object can be one or more.
  • “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.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR new radio
  • FIG1 shows a block diagram of a wireless communication system applicable to 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.
  • PDA Personal Digital Assistant
  • PDA netbook
  • ultra-mobile personal computer UMPC
  • MID mobile Internet Device
  • MID augmented reality
  • AR augmented reality
  • VR virtual reality
  • robot wearable device
  • VUE vehicle user equipment
  • 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 personal computer, PC
  • 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.
  • 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.
  • WLAN wireless local area network
  • WiFi wireless fidelity
  • 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.
  • 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.
  • 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)
  • ⁇ (.) 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.
  • the common optimization algorithms are basically based on the error back propagation (BP) algorithm.
  • BP error back propagation
  • 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.
  • 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.
  • the actual network environment is ever-changing.
  • 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.
  • 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.
  • the SNR signal-to-noise ratio
  • the AI model cannot accurately locate the terminal. For this reason, an AI model configuration method of this application is proposed.
  • an embodiment of the present application provides an AI model configuration method.
  • 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.
  • the above-mentioned model meta-information can be understood or replaced by network environment information.
  • 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.
  • each set of configuration parameters corresponds to an AI model
  • 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.
  • IE information element
  • determining the target AI model to be used can be understood as determining the activated target AI model.
  • 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.
  • 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.
  • 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.
  • 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;
  • the second information is used to determine the target model meta-information
  • the target model meta-information is the model meta-information associated with the model identifier of the target AI model.
  • the terminal after receiving the above-mentioned second information, 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • the model meta information includes at least one of the following:
  • 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;
  • SINR Signal to Interference plus Noise Ratio
  • 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.
  • 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.
  • 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.
  • 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.
  • the configuration parameters further include at least one of the following:
  • 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).
  • CDF cumulative distribution function
  • the reasoning error of the model can be a 90% CDF positioning error (or a 90% error, or a 90% position error).
  • 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.
  • the target AI model is used for positioning.
  • determining the target AI model to be used can be understood as determining the AI model used for positioning.
  • 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.
  • e x and e y are Gaussian distributions with mean 0 and standard deviation ⁇ 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.
  • 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%.
  • test data of the indoor factory in the frequency range 1 is shown in Tables 2 and 3 below.
  • the positioning error is greater than 10m:
  • 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.
  • test data of the indoor factory in the frequency range 1 is shown in Table 4 below.
  • an embodiment of the present application further provides an AI model configuration method.
  • 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.
  • 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.
  • 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.
  • model meta information includes at least one of the following:
  • 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;
  • the signal-to-interference-noise ratio associated with the model is the signal-to-interference-noise ratio associated with the model
  • the reference signal received power associated with the model
  • the configuration parameters also include at least one of the following:
  • 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.
  • 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.
  • an embodiment of the present application further provides an AI model configuration device.
  • 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.
  • 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
  • the second information is used to determine the target model meta-information
  • the target model meta-information is the model meta-information associated with the model identifier of the target AI model.
  • 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.
  • model meta information includes at least one of the following:
  • 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;
  • the signal-to-interference-noise ratio associated with the model is the signal-to-interference-noise ratio associated with the model
  • the reference signal received power associated with the model
  • the configuration parameters also include at least one of the following:
  • the target AI model is used for positioning.
  • the embodiment of the present application further provides an AI model configuration device.
  • 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.
  • 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.
  • 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.
  • model meta information includes at least one of the following:
  • 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;
  • the signal-to-interference-noise ratio associated with the model is the signal-to-interference-noise ratio associated with the model
  • the reference signal received power associated with the model
  • the configuration parameters also include at least one of the following:
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • a power source such as a battery
  • 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.
  • 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.
  • the radio frequency unit 801 after receiving downlink data from the network side device, 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.
  • 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.
  • 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.
  • 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 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.
  • 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.
  • 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.
  • the embodiment of the present application also provides a network side device.
  • 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.
  • the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing.
  • 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).
  • a network interface 906 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • 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.
  • a program or instruction is stored on the readable storage medium.
  • 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.
  • 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.
  • the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, 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.
  • a storage medium such as ROM/RAM, a magnetic disk, or an optical disk
  • a terminal which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

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模型配置方法、终端及网络侧设备AI model configuration method, terminal and network side equipment
相关申请的交叉引用CROSS-REFERENCE TO RELATED APPLICATIONS
本申请主张在2022年10月17日在中国提交的中国专利申请No.202211267696.5的优先权,其全部内容通过引用包含于此。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.
技术领域Technical Field
本申请属于通信技术领域,具体涉及一种AI模型配置方法、终端及网络侧设备。The present application belongs to the field of communication technology, and specifically relates to an AI model configuration method, terminal and network side equipment.
背景技术Background technique
随着通信技术的发展,在通信系统中引入了人工智能(Artificial Intelligence,AI)模型,终端可以基于网络侧设备配置的AI模型执行相应的操作,例如进行定位。由于AI模型配置后,可能会由于当前的网络环境与模型训练时的环境差异较大,从而导致模型输出结果的可靠性较差。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.
发明内容Summary of the invention
本申请实施例提供一种AI模型配置方法、终端及网络侧设备,能够解决模型输出结果的可靠性较差的问题。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.
第一方面,提供了一种AI模型配置方法,包括:In a first aspect, an AI model configuration method is provided, comprising:
终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
所述终端根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
第二方面,提供了一种AI模型配置方法,包括:In a second aspect, an AI model configuration method is provided, including:
网络侧设备向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
第三方面,提供了一种AI模型配置装置,包括:In a third aspect, an AI model configuration device is provided, comprising:
接收模块,用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
确定模块,用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
第四方面,提供了一种AI模型配置装置,包括: In a fourth aspect, an AI model configuration device is provided, comprising:
发送模块,用于向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
第五方面,提供了一种终端,该终端包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。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.
第六方面,提供了一种终端,包括处理器及通信接口,其中,所述通信接口用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;所述处理器用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
第七方面,提供了一种网络侧设备,该网络侧设备包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第二方面所述的方法的步骤。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.
第八方面,提供了一种网络侧设备,包括处理器及通信接口,其中,所述通信接口用于向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
第九方面,提供了一种通信系统,包括:终端及网络侧设备,所述终端可用于执行如第一方面所述的AI模型配置方法的步骤,所述网络侧设备可用于执行如第二方面所述的AI模型配置方法的步骤。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.
第十方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤,或者实现如第二方面所述的方法的步骤。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.
第十一方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面所述的方法的步骤,或实现如第二方面所述的方法的步骤。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.
第十二方面,提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面所述的方法的步骤,或实现如第二方面所述的方法的步骤。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.
本申请实施例通过终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。这样,终端可以根据模型元信息和当前的网络环境信息,确定当前的AI模型是否有效,同时在当前AI模型无效的情况下可以进一步选择适用于当前的网络环境信息的目标AI模型执行相应的操作,从而避免了 由于网络环境变化导致AI模型输出结果的精度降低,因此提高了AI模型使用的可靠性。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.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是本申请实施例可应用的网络结构示意图。FIG1 is a schematic diagram of a network structure applicable to an embodiment of the present application.
图2是本申请实施例可应用的神经网络的神经元的结构示意图;FIG2 is a schematic diagram of the structure of neurons of a neural network applicable to an embodiment of the present application;
图3是本申请实施例提供的一种AI模型配置方法的流程图;FIG3 is a flow chart of an AI model configuration method provided in an embodiment of the present application;
图4是本申请实施例提供的另一种AI模型配置方法的流程图;FIG4 is a flow chart of another AI model configuration method provided in an embodiment of the present application;
图5是本申请实施例提供的一种AI模型配置装置的结构图;FIG5 is a structural diagram of an AI model configuration device provided in an embodiment of the present application;
图6是本申请实施例提供的另一种AI模型配置装置的结构图;FIG6 is a structural diagram of another AI model configuration device provided in an embodiment of the present application;
图7是本申请实施例提供的通信设备的结构图;FIG7 is a structural diagram of a communication device provided in an embodiment of the present application;
图8是本申请实施例提供的终端的结构图;FIG8 is a structural diagram of a terminal provided in an embodiment of the present application;
图9是本申请实施例提供的网络侧设备的结构图。FIG. 9 is a structural diagram of a network-side device provided in an embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。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.
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。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.
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)系统,还可用于其他无线通信系统,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access,TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access,SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的系统和无线电技术,也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio,NR)系统,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR系统应用以外的应用,如第6代(6th Generation,6G)通信系统。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.
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中,终端11可以是手机、平板电脑(Tablet Personal Computer)、膝 上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、增强现实(augmented reality,AR)/虚拟现实(virtual reality,VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(Vehicle User Equipment,VUE)、行人终端(Pedestrian User Equipment,PUE)、智能家居(具有无线通信功能的家居设备,如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer,PC)、柜员机或者自助机等终端侧设备,可穿戴式设备包括:智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是,在本申请实施例并不限定终端11的具体类型。网络侧设备12可以包括接入网设备或核心网设备,其中,接入网设备也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备可以包括基站、无线局域网(Wireless Local Area Network,WLAN)接入点或无线保真(Wireless Fidelity,WiFi)节点等,基站可被称为节点B、演进节点B(Evolved Node B,eNB)、接入点、基收发机站(Base Transceiver Station,BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set,BSS)、扩展服务集(Extended Service Set,ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point,TRP)或所属领域中其他某个合适的术语,只要达到相同的技术效果,所述基站不限于特定技术词汇,需要说明的是,在本申请实施例中仅以NR系统中的基站为例进行介绍,并不限定基站的具体类型。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.
为了方便理解,以下对本申请实施例涉及的一些内容进行说明:For ease of understanding, some contents involved in the embodiments of the present application are described below:
一、人工智能。1. Artificial intelligence.
人工智能目前在各个领域获得了广泛的应用。将人工智能融入无线通信网络,显著提升吞吐量、时延以及用户容量等技术指标是未来的无线通信网络的重要任务。AI模块有多种实现方式,例如神经网络、决策树、支持向量机、贝叶斯分类器等。本申请以神经网络为例进行说明,但是并不限定AI模块的具体类型。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.
神经网络由神经元组成,神经元的示意图如图2所示。其中,z=a1*w1+···+a1*w1+···+ak*wk+b,a1,a2,…aK为输入,w为权值(乘性系数),b为偏置(加性系数),σ(.)为激活函数。常见的激活函数包括S型函数(Sigmoid)、双曲正切函数(tanh)和线性整流函数(Rectified Linear Unit,ReLU)等。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).
神经网络的参数通过优化算法进行优化。优化算法就是一种能够帮我们最小化或者最大化目标函数(有时候也叫损失函数)的一类算法。而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y,我们构建一个神经网络模型f(.),有了模型后,根据输入x就可以得到预测输出f(x),并且可以计算出预测值和真实值之间的差距(f(x)-Y),这个就是损失函数。我们的目的是找到合适的W,b使上述的损失函数的值达到最小,损失值越小,则说明我们的模型越接近于真实情况。 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.
目前常见的优化算法,基本都是基于误差反向传播(error Back Propagation,BP)算法。BP算法的基本思想是,学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时,输入样本从输入层传入,经各隐层逐层处理后,传向输出层。若输出层的实际输出与期望的输出不符,则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传,并将误差分摊给各层的所有单元,从而获得各层单元的误差信号,此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程,是周而复始地进行的。权值不断调整的过程,也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度,或进行到预先设定的学习次数为止。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.
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent,SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、带动量的随机梯度下降(也可以称之为Nesterov)、自适应梯度下降(ADAptive GRADient descent,Adagrad)、自适应增量(Adaptive Delta,Adadelta)、均方根误差降速(root mean square prop,RMSprop)和自适应动量估计(Adaptive Moment Estimation,Adam)。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).
这些优化算法在误差反向传播时,都是根据损失函数得到的误差/损失,对当前神经元求导数/偏导,加上学习速率、之前的梯度/导数/偏导等影响,得到梯度,将梯度传给上一层。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.
相关技术中,实际网络环境千变万化,在AI模型配置之后,可能会出现由于模型训练数据采集的环境与当前环境不匹配的情况。比如定位数据由定位参考单元(Positioning reference unit)采集,采集时的信噪比(Signal Noise Ratio,SNR)比较高以及网络同步误差很小,但训练的神经网络模型部署到终端之后,当遇到SNR比较低以及网络同步误差较大的情况,此时通过AI模型就无法准确定位。为此提出了本申请的AI模型配置方法。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.
下面结合附图,通过一些实施例及其应用场景对本申请实施例提供的AI模型配置方法进行详细地说明。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.
参照图3,本申请实施例提供了一种AI模型配置方法,如图3所示,该AI模型配置方法包括: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:
步骤301,终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
步骤302,所述终端根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
本申请实施例中,上述模型元信息可以理解或替换为网络环境信息。具体地,该模型元信息可以表示关联的模型标识(Identifier,ID)所对应的AI模型在训练阶段或者实际使用时所运行的网络环境,该网络环境可以包括网络同步误差、定时误差和通信链路质量等。上述第一信息可以理解为用于构建AI模型的构建参数,具体包含的内容可以参照相 关技术,在此不再赘述。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.
应理解,每一套配置参数对应一个AI模型,上述至少两套配置参数可以承载在一个信令中(例如,通过一个信息元素(Information element,IE)配置),或者承载在至少两个信令中,也就是说,网络侧设备可以同时或在不同的时刻通过配置信息为终端部署或配置至少两个AI模型。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.
可选地,确定使用的目标AI模型可以理解为确定激活的目标AI模型,例如,终端确定目标AI模型后,可以激活该目标AI模型,并基于该目标AI模型执行相应的操作(如定位操作)。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.
本申请实施例通过终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。这样,终端可以根据模型元信息和当前的网络环境信息,确定当前的AI模型是否有效,同时在当前AI模型无效的情况下可以进一步选择适用于当前的网络环境信息的目标AI模型执行相应的操作,从而避免了由于网络环境变化导致AI模型输出结果的精度降低,因此提高了AI模型使用的可靠性。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.
可选地,在一些实施例中,所述终端根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型,包括: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:
所述终端从网络侧设备接收第二信息;The terminal receives second information from the network side device;
所述终端根据所述第二信息和所述模型元信息,在基于所述第一信息构建的AI模型中确定所述目标AI模型;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;
其中,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
本申请实施例中,终端接收到上述第二信息后,可以确定第一信息关联的模型元信息中与第二信息匹配的目标模型元信息,从而将该目标模型元信息对应的第一信息构建的AI模型确定的目标AI模型。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.
应理解,上述第二信息可以理解为网络侧设备指示的网络环境信息或者用于终端确定网络环境信息的信号。也就是说,在一些实施例中,上述第二信息包括以下至少一项: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:
第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息;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;
第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
本申请实施例中,上述配置信息中的模型元信息可以理解为表示AI模型训练时对应的网络环境。上述第一指示信息用于指示当前实际的网络环境,通过比较第一指示信息指示的内容与模型元信息之间的关系,从而可以确定训练时对应的网络环境与当前实际的网络环境最匹配目标模型元信息,此时,基于该目标模型元信息对应的目标AI模型执行相应的操作,可以保证目标AI模型输出结果的可靠性。 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.
可选地,在一些实施例中,上述第一指示信息可以元信息标识、模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项。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.
例如,假设上述模型元信息是AI模型关联的信噪比,则该第二信息可以为信噪比,即当前网络环境下的实际信噪比。终端可以选择模型元信息中信噪比与当前实际的信噪比最接近的模型元信息确定为目标模型元信息,从而使用适于当前信噪比环境的目标AI模型执行相关操作,进而提高了AI模型输出结果的可靠性。可选地,网络侧设备可以基于上行信号的测量获得上述信噪比,然后通过第一指示信息向终端指示该信噪比。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.
上述第一参考信号可以理解为下行参考信号,即终端可以对第一参考信号进行测量从而获得当前实际的网络环境信息,通过比较第一参考信号的测量结果与模型元信息之间的关系,从而可以确定训练时对应的网络环境信息与当前实际的网络环境信息最匹配的目标模型元信息,此时,基于该目标模型元信息关联的模型ID所对应的目标AI模型执行相应的操作,可以保证目标AI模型输出结果的可靠性。需要说明的是,上述模型元信息通常可以与模型ID关联,从而基于模型元信息可以确定使用的目标AI模型。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.
可选地,在一些实施例中,所述模型元信息包括以下至少一项:Optionally, in some embodiments, the model meta information includes at least one of the following:
元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
模型关联的信噪比;signal-to-noise ratio associated with the model;
模型关联的信干噪比(Signal to Interference plus Noise Ratio,SINR);Model-associated Signal to Interference plus Noise Ratio (SINR);
模型关联的参考信号接收功率(Reference Signal Received Power,RSRP);The reference signal received power (RSRP) associated with the model;
模型关联的参考信号接收质量(Reference Signal Received Quality,RSRQ);Model-associated Reference Signal Received Quality (RSRQ);
模型关联的网络同步误差;Model-associated network synchronization errors;
模型关联的定时误差。Model-associated timing errors.
本申请实施例中,上述元信息标识同时还与模型ID关联。终端可以通过测量第一参考信号,获得第一参考信号的SNR或SINR值,SNR或SINR值与信道估计质量关联,如SINR越大,信道估计越准确,将估计的信道脉冲响应作为AI模型的输入,得到的定位精度越准确。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.
可选地,终端通过测量第一参考信号,获得第一参考信号的RSRP或RSRQ值,RSRP或RSRQ值与信道估计质量关联,如RSRQ越大,信道估计越准确,将估计的信道脉冲响应作为AI模型的输入,得到的定位精度越准确。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.
可选地,上述网络同步误差用于表示AI模型所适用的网络同步误差范围,如网络同步误差为10ns,则表示对应的AI模型所适用的网络同步误差范围为0ns~10ns。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.
可选地,上述定时误差用于表示AI模型所适用的定时误差范围,如定时误差为10ns,则表示对应的AI模型所适用的定时误差范围为0ns~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.
可选地,在一些实施例中,所述配置参数还包括以下至少一项:Optionally, in some embodiments, the configuration parameters further include at least one of the following:
训练数据的标签误差;Label error of training data;
模型的推理误差。The inference error of the model.
本申请实施例中,标签误差与模型的推理误差关联,模型的推理误差可以采用累积分布函数(cumulative distribution function,CDF)表示,如模型的推理误差可以为90%CDF定位误差(或者称之为90%误差,或90%位置误差)。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).
由于在配置参数中携带训练数据的标签误差和模型的推理误差中的至少一项,终端可以基于该标签误差和模型的推理误差中的至少一项确定模型本身的性能,以进一步决定AI模型是否可用。这样可以进一步保证后续使用的AI模型的性能。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.
可选地,在一些实施例中,所述目标AI模型用于定位。Optionally, in some embodiments, the target AI model is used for positioning.
本申请实施例中,确定使用的目标AI模型可以理解为,确定用于定位的AI模型。通过部署多种AI模型,并且每种AI模型的模型ID关联不同的模型元信息,当环境发生变化时,终端可根据第二指示信息和/或第一参考信号的测量结果动态地选择或切换AI模型,从而提升定位服务的质量。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.
为了更好的理解本申请,以下通过一些实例进行说明。In order to better understand the present application, some examples are provided below for illustration.
一、不同标签噪声的影响。1. The impact of different label noises.
对真实位置标签(x,y)分别添加相同的噪声(瑞利分布),即两个维度的噪声分别服从均值为0,标准差为0.5m、1m、2m、4m的高斯分布;(90%位置误差=高斯分布标准差*1.645);添加噪声后的标签(x',y'):
(x',y')=(x,y)+(ex,ey);
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 );
其中,ex,ey分别为均值为0,标准差为σ的高斯分布。Among them, e x and e y are Gaussian distributions with mean 0 and standard deviation σ respectively.
上述真实位置标签可以称之为ground truth label。在频段为频率范围1的室内工厂的测试数据如下表一所示。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.
表一:
Table I:
其中,上述表一中,50%可以理解为50%CDF位置误差,具体是指对应的情况下,误差小于0.35、0.69、1.06、1.70和2.71时用户的占比为50%。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%.
基于表一可知:随着标签噪声标准(standard,STD)的增加,性能会逐渐下降。Std=4m(4*1.645=6.6m,90%CDF位置误差约为8.50m),此时经过神经网络训练之后的90% 位置误差为5.13m,小于理论误8.50m,说明神经网络起到了一定的去噪作用,对于标签标注误差具有一定的鲁棒性。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.
二、不同信道估计误差的影响。2. The impact of different channel estimation errors.
在频段为频率范围1的室内工厂的测试数据如下表二和表三所示。The test data of the indoor factory in the frequency range 1 is shown in Tables 2 and 3 below.
表二:
Table II:
表三:
Table 3:
基于上述表二和标三可知:Based on the above Table 2 and Table 3, we can know that:
1、随着CIR测量噪声的增加,训练模型的定位精度逐渐下降;1. As the CIR measurement noise increases, the positioning accuracy of the training model gradually decreases;
2、当训练集和测试集的CIR的SINR不同时,性能下降更加严重,如训练集是30dB,测试集是-30Db,定位误差大于10m:当训练集的CIR的SINR较大,而测试集的SINR较小,性能剧烈下降;也就是说,如果模型运行的设备测量的CIR噪声很大,那么定位性能是难以保证的。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.
三、不同网络同步误差的影响。3. The impact of synchronization errors of different networks.
在频段为频率范围1的室内工厂的测试数据如下表四所示。The test data of the indoor factory in the frequency range 1 is shown in Table 4 below.
表四:
Table 4:
基于上述表四可知:同步误差会显著影响AI模型的定位性能,且测试集的同步误差越大,性能下降幅度越大。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.
参照图4,本申请实施例还提供了一种AI模型配置方法,如图4所示,该AI模型配置方法包括: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:
步骤401,网络侧设备向终端发送配置信息,所述配置信息包括至少两套配置参数, 所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
可选地,所述网络侧设备向终端发送至少两个人工智能AI模型的配置信息之后,所述方法还包括:Optionally, after the network side device sends configuration information of at least two artificial intelligence AI models to the terminal, the method further includes:
所述网络侧设备向终端发送第二信息,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
可选地,所述第二信息包括以下至少一项:Optionally, the second information includes at least one of the following:
第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息;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;
第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
可选地,所述模型元信息包括以下至少一项:Optionally, the model meta information includes at least one of the following:
元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
模型关联的信噪比;signal-to-noise ratio associated with the model;
模型关联的信干噪比;The signal-to-interference-noise ratio associated with the model;
模型关联的参考信号接收功率;the reference signal received power associated with the model;
模型关联的参考信号接收质量;the received quality of the reference signal associated with the model;
模型关联的网络同步误差;Model-associated network synchronization errors;
模型关联的定时误差。Model-associated timing errors.
可选地,所述配置参数还包括以下至少一项:Optionally, the configuration parameters also include at least one of the following:
训练数据的标签误差;Label error of training data;
模型的推理误差。The inference error of the model.
可选地,所述AI模型为用于定位的模型。Optionally, the AI model is a model used for positioning.
本申请实施例提供的AI模型配置方法,执行主体可以为AI模型配置装置。本申请实施例中以AI模型配置装置执行AI模型配置方法为例,说明本申请实施例提供的AI模型配置装置。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.
参照图5,本申请实施例还提供了一种AI模型配置装置,如图5所示,该AI模型配置装置500包括: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:
接收模块501,用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
确定模块502,用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。 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.
可选地,所述确定模块502包括:Optionally, the determining module 502 includes:
接收单元,用于从网络侧设备接收第二信息;A receiving unit, configured to receive second information from a network side device;
确定单元,用于根据所述第二信息和所述模型元信息,在基于所述第一信息构建的AI模型中确定所述目标AI模型;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;
其中,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
可选地,所述第二信息包括以下至少一项:Optionally, the second information includes at least one of the following:
第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息;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;
第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
可选地,所述模型元信息包括以下至少一项:Optionally, the model meta information includes at least one of the following:
元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
模型关联的信噪比;signal-to-noise ratio associated with the model;
模型关联的信干噪比;The signal-to-interference-noise ratio associated with the model;
模型关联的参考信号接收功率;the reference signal received power associated with the model;
模型关联的参考信号接收质量;the received quality of the reference signal associated with the model;
模型关联的网络同步误差;Model-associated network synchronization errors;
模型关联的定时误差。Model-associated timing errors.
可选地,所述配置参数还包括以下至少一项:Optionally, the configuration parameters also include at least one of the following:
训练数据的标签误差;Label error of training data;
模型的推理误差。The inference error of the model.
可选地,所述目标AI模型用于定位。Optionally, the target AI model is used for positioning.
参照图6,本申请实施例还提供了一种AI模型配置装置,如图6所示,该AI模型配置装置600包括: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:
发送模块601,用于向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
可选地,所述发送模块601还用于:向终端发送第二信息,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
可选地,所述第二信息包括以下至少一项:Optionally, the second information includes at least one of the following:
第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息; 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;
第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
可选地,所述模型元信息包括以下至少一项:Optionally, the model meta information includes at least one of the following:
元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
模型关联的信噪比;signal-to-noise ratio associated with the model;
模型关联的信干噪比;The signal-to-interference-noise ratio associated with the model;
模型关联的参考信号接收功率;the reference signal received power associated with the model;
模型关联的参考信号接收质量;the received quality of the reference signal associated with the model;
模型关联的网络同步误差;Model-associated network synchronization errors;
模型关联的定时误差。Model-associated timing errors.
可选地,所述配置参数还包括以下至少一项:Optionally, the configuration parameters also include at least one of the following:
训练数据的标签误差;Label error of training data;
模型的推理误差。The inference error of the model.
可选地,所述AI模型为用于定位的模型。Optionally, the AI model is a model used for positioning.
本申请实施例中的AI模型配置装置可以是电子设备,例如具有操作系统的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是终端,也可以为除终端之外的其他设备。示例性的,终端可以包括但不限于上述所列举的终端11的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例不作具体限定。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.
本申请实施例提供的AI模型配置装置能够实现图3至图4的方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。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.
如图7所示,本申请实施例还提供一种通信设备700,包括处理器701和存储器702,存储器702上存储有可在所述处理器701上运行的程序或指令,该程序或指令被处理器701执行时实现上述AI模型配置装置实施例的各个步骤,且能达到相同的技术效果,为避免重复,这里不再赘述。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.
本申请实施例还提供一种终端,包括处理器和通信接口,所述通信接口用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;所述处理器用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。该终端实施例与上述终端侧方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该终端实施例中,且能达到相同的技术效果。具体地,图8为实现本申请实施例的一种终端的硬件结构示意图。 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.
该终端800包括但不限于:射频单元801、网络模块802、音频输出单元803、输入单元804、传感器805、显示单元806、用户输入单元807、接口单元808、存储器809以及处理器810等中的至少部分部件。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.
本领域技术人员可以理解,终端800还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理系统与处理器810逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图8中示出的终端结构并不构成对终端的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。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.
应理解的是,本申请实施例中,输入单元804可以包括图形处理器(Graphics Processing Unit,GPU)8041和麦克风8042,图形处理器8041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元806可包括显示面板8061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板8061。用户输入单元807包括触控面板8071以及其他输入设备8072中的至少一种。触控面板8071,也称为触摸屏。触控面板8071可包括触摸检测装置和触摸控制器两个部分。其他输入设备8072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。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.
本申请实施例中,射频单元801接收来自网络侧设备的下行数据后,可以传输给处理器810进行处理;另外,射频单元801可以向网络侧设备发送上行数据。通常,射频单元801包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。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.
存储器809可用于存储软件程序或指令以及各种数据。存储器809可主要包括存储程序或指令的第一存储区和存储数据的第二存储区,其中,第一存储区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外,存储器809可以包括易失性存储器或非易失性存储器,或者,存储器809可以包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(Read-Only Memory,ROM)、可编程只读存储器(Programmable ROM,PROM)、可擦除可编程只读存储器(Erasable PROM,EPROM)、电可擦除可编程只读存储器(Electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory,RAM),静态随机存取存储器(Static RAM,SRAM)、动态随机存取存储器(Dynamic RAM,DRAM)、同步动态随机存取存储器(Synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM,DDRSDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(Synch link DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DRRAM)。本申请实施例中的存储器809包括但不限于这些和任意其它适合类型的存储器。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.
处理器810可包括一个或多个处理单元;可选地,处理器810集成应用处理器和调制解调处理器,其中,应用处理器主要处理涉及操作系统、用户界面和应用程序等的操作,调制解调处理器主要处理无线通信信号,如基带处理器。可以理解的是,上述调制解调处 理器也可以不集成到处理器810中。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.
其中,所述射频单元801用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
所述处理器810用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
本申请实施例通过终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。这样,终端可以根据模型元信息和当前的网络环境信息,确定当前的AI模型是否有效,同时在当前AI模型无效的情况下可以进一步选择适用于当前的网络环境信息的目标AI模型执行相应的操作,从而避免了由于网络环境变化导致AI模型输出结果的精度降低,因此提高了AI模型使用的可靠性。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.
本申请实施例还提供一种网络侧设备,包括处理器和通信接口,所述通信接口用于向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。该网络侧设备实施例与上述网络侧设备方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中,且能达到相同的技术效果。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.
具体地,本申请实施例还提供了一种网络侧设备。如图9所示,该网络侧设备900包括:天线901、射频装置902、基带装置903、处理器904和存储器905。天线901与射频装置902连接。在上行方向上,射频装置902通过天线901接收信息,将接收的信息发送给基带装置903进行处理。在下行方向上,基带装置903对要发送的信息进行处理,并发送给射频装置902,射频装置902对收到的信息进行处理后经过天线901发送出去。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.
以上实施例中网络侧设备执行的方法可以在基带装置903中实现,该基带装置903包括基带处理器。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.
基带装置903例如可以包括至少一个基带板,该基带板上设置有多个芯片,如图9所示,其中一个芯片例如为基带处理器,通过总线接口与存储器905连接,以调用存储器905中的程序,执行以上方法实施例中所示的网络设备操作。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.
该网络侧设备还可以包括网络接口906,该接口例如为通用公共无线接口(common public radio interface,CPRI)。The network side device may also include a network interface 906, which is, for example, a common public radio interface (CPRI).
具体地,本申请实施例的网络侧设备900还包括:存储在存储器905上并可在处理器904上运行的指令或程序,处理器904调用存储器905中的指令或程序执行图6所示各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。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.
本申请实施例还提供一种可读存储介质,所述可读存储介质上存储有程序或指令,该 程序或指令被处理器执行时实现上述AI模型配置方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。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.
其中,所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质,包括计算机可读存储介质,如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。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.
本申请实施例另提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现上述AI模型配置方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。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.
本申请实施例另提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现上述AI模型配置方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。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.
本申请实施例还提供了一种通信系统,包括:终端及网络侧设备,所述终端用于执行如图3及上述终端侧各个方法实施例的各个过程,所述网络侧设备用于执行如图4及上述网络侧设备侧各个方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。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.
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。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.
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。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.
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。 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 (20)

  1. 一种AI模型配置方法,包括:An AI model configuration method, comprising:
    终端从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
    所述终端根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
  2. 根据权利要求1所述的方法,其中,所述终端根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型,包括: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:
    所述终端从网络侧设备接收第二信息;The terminal receives second information from the network side device;
    所述终端根据所述第二信息和所述模型元信息,在基于所述第一信息构建的AI模型中确定所述目标AI模型;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;
    其中,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
  3. 根据权利要求2所述的方法,其中,所述第二信息包括以下至少一项:The method according to claim 2, wherein the second information includes at least one of the following:
    第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息;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;
    第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
  4. 根据权利要求1至3任一项所述的方法,其中,所述模型元信息包括以下至少一项:The method according to any one of claims 1 to 3, wherein the model meta information includes at least one of the following:
    元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
    模型关联的信噪比;signal-to-noise ratio associated with the model;
    模型关联的信干噪比;The signal-to-interference-noise ratio associated with the model;
    模型关联的参考信号接收功率;the reference signal received power associated with the model;
    模型关联的参考信号接收质量;the received quality of the reference signal associated with the model;
    模型关联的网络同步误差;Model-associated network synchronization errors;
    模型关联的定时误差。Model-associated timing errors.
  5. 根据权利要求1至4任一项所述的方法,其中,所述配置参数还包括以下至少一项:The method according to any one of claims 1 to 4, wherein the configuration parameters further include at least one of the following:
    训练数据的标签误差;Label error of training data;
    模型的推理误差。The inference error of the model.
  6. 根据权利要求1至5任一项所述的方法,其中,所述目标AI模型用于定位。The method according to any one of claims 1 to 5, wherein the target AI model is used for positioning.
  7. 一种AI模型配置方法,包括: An AI model configuration method, comprising:
    网络侧设备向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
  8. 根据权利要求7所述的方法,其中,所述网络侧设备向终端发送至少两个人工智能AI模型的配置信息之后,所述方法还包括: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:
    所述网络侧设备向终端发送第二信息,所述第二信息用于确定目标模型元信息,所述目标模型元信息为与所述目标AI模型的模型标识关联的模型元信息。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.
  9. 根据权利要求8所述的方法,其中,所述第二信息包括以下至少一项:The method according to claim 8, wherein the second information includes at least one of the following:
    第一指示信息,所述第一指示信息用于指示所述模型元信息的相关信息,所述相关信息用于确定所述目标模型元信息中的至少部分模型元信息;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;
    第一参考信号,所述第一参考信号用于确定所述目标模型元信息中的至少部分模型元信息。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.
  10. 根据权利要求7至9任一项所述的方法,其中,所述模型元信息包括以下至少一项:The method according to any one of claims 7 to 9, wherein the model meta information includes at least one of the following:
    元信息标识,所述元信息标识与第三信息关联,所述第三信息包括模型关联的信噪比、模型关联的信干噪比、模型关联的参考信号接收功率、模型关联的参考信号接收质量、模型关联的网络同步误差和模型关联的定时误差中的至少一项;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;
    模型关联的信噪比;signal-to-noise ratio associated with the model;
    模型关联的信干噪比;The signal-to-interference-noise ratio associated with the model;
    模型关联的参考信号接收功率;the reference signal received power associated with the model;
    模型关联的参考信号接收质量;the received quality of the reference signal associated with the model;
    模型关联的网络同步误差;Model-associated network synchronization errors;
    模型关联的定时误差。Model-associated timing errors.
  11. 根据权利要求7至10任一项所述的方法,其中,所述配置参数还包括以下至少一项:The method according to any one of claims 7 to 10, wherein the configuration parameters further include at least one of the following:
    训练数据的标签误差;Label error of training data;
    模型的推理误差。The inference error of the model.
  12. 根据权利要求7至11任一项所述的方法,其中,所述AI模型为用于定位的模型。The method according to any one of claims 7 to 11, wherein the AI model is a model for positioning.
  13. 一种AI模型配置装置,包括:An AI model configuration device, comprising:
    接收模块,用于从网络侧设备接收配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境;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;
    确定模块,用于根据所述模型元信息,在基于所述第一信息构建的AI模型中确定使用的目标AI模型。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.
  14. 一种AI模型配置装置,包括: An AI model configuration device, comprising:
    发送模块,用于向终端发送配置信息,所述配置信息包括至少两套配置参数,所述配置参数包括第一信息和与所述第一信息关联的模型元信息,所述第一信息用于构建AI模型,所述模型元信息用于表示所述第一信息构建的AI模型运行的网络环境。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.
  15. 一种终端,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至6任一项所述的AI模型配置方法的步骤。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.
  16. 一种网络侧设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求6至12任一项所述的AI模型配置方法的步骤。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.
  17. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1至12任一项所述的AI模型配置方法的步骤。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.
  18. 一种芯片,包括处理器和通信接口,其中,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如权利要求1至12任一项所述的AI模型配置方法的步骤。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.
  19. 一种计算机程序/程序产品,其中,所述计算机程序/程序产品被存储在非瞬态的可读存储介质中,所述程序/程序产品被至少一个处理器执行以实现如权利要求1至12任一项所述的AI模型配置方法的步骤。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.
  20. 一种通信设备,包括处理器和存储器,存储器上存储有可在所述处理器上运行的程序或指令,该程序或指令被处理执行时实现如权利要求1至12任一项所述的AI模型配置方法的步骤。 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.
PCT/CN2023/123880 2022-10-17 2023-10-11 Ai model configuration method, terminal, and network side device WO2024083004A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211267696.5 2022-10-17
CN202211267696.5A CN117938689A (en) 2022-10-17 2022-10-17 AI model configuration method, terminal and network equipment

Publications (1)

Publication Number Publication Date
WO2024083004A1 true WO2024083004A1 (en) 2024-04-25

Family

ID=90736869

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/123880 WO2024083004A1 (en) 2022-10-17 2023-10-11 Ai model configuration method, terminal, and network side device

Country Status (2)

Country Link
CN (1) CN117938689A (en)
WO (1) WO2024083004A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022145551A1 (en) * 2020-12-29 2022-07-07 엘지전자 주식회사 Intelligent signal transmission or reception method and device therefor
CN114826941A (en) * 2022-04-27 2022-07-29 中国电子科技集团公司第五十四研究所 AI model configuration method for wireless communication network
CN115150847A (en) * 2021-03-31 2022-10-04 华为技术有限公司 Model processing method, communication device and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022145551A1 (en) * 2020-12-29 2022-07-07 엘지전자 주식회사 Intelligent signal transmission or reception method and device therefor
CN115150847A (en) * 2021-03-31 2022-10-04 华为技术有限公司 Model processing method, communication device and system
CN114826941A (en) * 2022-04-27 2022-07-29 中国电子科技集团公司第五十四研究所 AI model configuration method for wireless communication network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
VIVO: "Discussions on AI/ML framework", 3GPP DRAFT; R1-2206031, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG1, no. Toulouse, France; 20220822 - 20220826, 12 August 2022 (2022-08-12), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052273964 *

Also Published As

Publication number Publication date
CN117938689A (en) 2024-04-26

Similar Documents

Publication Publication Date Title
US20240267761A1 (en) Model request method, model request processing method, and related device
WO2023143572A1 (en) Positioning method based on artificial intelligence (ai) model, and communication device
WO2023134650A1 (en) Information interaction method and apparatus, and communication device
WO2024083004A1 (en) Ai model configuration method, terminal, and network side device
CN111091180B (en) Model training method and related device
WO2024120444A1 (en) Model supervision method and apparatus, terminal, network side device and readable storage medium
WO2024120445A1 (en) Model input information determination method, apparatus, device and system, and storage medium
WO2024067281A1 (en) Ai model processing method and apparatus, and communication device
WO2024008111A1 (en) Data acquisition method and device
WO2024067280A1 (en) Method and apparatus for updating ai model parameter, and communication device
WO2023098662A1 (en) Positioning method and communication device
WO2023098661A1 (en) Positioning method and communication device
WO2024125525A1 (en) Ai computing power reporting method, and terminal and network-side device
WO2023125951A1 (en) Communication model configuration method and apparatus, and communication device
WO2024093997A1 (en) Method and apparatus for determining model applicability, and communication device
US20240323741A1 (en) Measurement method and apparatus, device, and storage medium
WO2023151657A1 (en) Information processing method and communication device
WO2023179540A1 (en) Channel prediction method and apparatus, and wireless communication device
WO2024093799A1 (en) Data labeling method and apparatus, terminal device, and network side device
WO2023186090A1 (en) Verification method, apparatus and device
WO2024027576A1 (en) Performance supervision method and apparatus for ai network model, and communication device
WO2023185865A1 (en) Model validation feedback method and apparatus, terminal, and network side device
WO2023186091A1 (en) Sample determination method, apparatus and device
WO2024169796A1 (en) Model supervision method and apparatus, and communication device
WO2024067665A1 (en) Csi prediction processing method and apparatus, and communication device and readable storage medium

Legal Events

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

Ref document number: 23878996

Country of ref document: EP

Kind code of ref document: A1