System, apparatus, and method for updating user model

Abstract

Systems, devices, and methods for updating a user model are disclosed. In one embodiment, an electronic system may be configured to: receive model data characterizing an artificial intelligence model from a model management server; sending model difference data representing the model difference to a model management server; and receiving updated model data from the model management server, the updated model data characterizing an updated version of the artificial intelligence model, the updated version based at least in part on the model difference data.

Description

Technical Field

[0001] The present disclosure relates to the field of communications, and more particularly, to systems, devices, and methods for updating user models. Background Art

[0002] The application of Artificial Intelligence (AI) technology is becoming increasingly widespread. A model provider may deploy a trained AI model to a user's device or system for the user to use. Summary of the Invention

[0003] The present disclosure provides systems, devices, and methods for updating user models.

[0004] One aspect of the present disclosure relates to an electronic system, comprising: at least one processing unit and at least one storage unit, the at least one storage unit including computer program code, wherein the at least one storage unit and the computer program code are configured to, via the at least one processing unit, cause the electronic system to perform the following operations: receive model data representing an AI model from a model management server; send model difference data representing a model difference to the model management server; receive updated model data from the model management server, the updated model data representing an updated version of the AI model, the updated version being at least partially based on the model difference data.

[0005] Another aspect of the present disclosure relates to a method, comprising: receiving model data representing an AI model from a model management server; sending model difference data representing a model difference to the model management server; receiving updated model data from the model management server, the updated model data representing an updated version of the AI model, the updated version being at least partially based on the model difference data.

[0006] One aspect of the present disclosure relates to an electronic system, comprising: at least one processing unit and at least one storage unit, the at least one storage unit including computer program code, wherein the at least one storage unit and the computer program code are configured to, via the at least one processing unit, cause the electronic system to perform the following operations: send model data defining an AI model to a user system; receive model difference data representing a model difference from the user system; generate an updated version of the AI model at least partially based on the model difference data; send the updated model data representing the updated version of the AI model to the user system.

[0007] Another aspect of the present disclosure relates to a method, including: sending model data defining an artificial intelligence model to a user system; receiving model difference data characterizing a model difference from the user system; generating an updated version of the artificial intelligence model at least partially based on the model difference data; and sending updated model data to the user system, where the updated model data characterizes the updated version of the artificial intelligence model.

[0008] Another aspect of the present disclosure relates to a computer-readable storage medium storing one or more instructions, which, when executed by one or more processing circuits of an electronic device, cause the electronic device to execute any method as described in the present disclosure.

[0009] Another aspect of the present disclosure relates to a computer program product including a computer program, which, when executed by a processor, implements any method as described in the present disclosure.

[0010] Another aspect of the present disclosure relates to an apparatus including components for executing any method as described in the present disclosure. Description of the Drawings

[0011] The above and other objects and advantages of the present disclosure will be further described below in conjunction with specific embodiments and with reference to the drawings. In the drawings, the same or corresponding technical features or components will be denoted by the same or corresponding reference numerals.

[0012] Figure 1 A schematic diagram of an architecture according to an embodiment of the present disclosure is shown.

[0013] Figure 2 An exemplary block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0014] Figure 3 An exemplary block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0015] Figure 4 A flowchart of a method for updating a user model according to some embodiments of the present disclosure is shown.

[0016] Figure 5 A flowchart of a method for updating a user model according to some embodiments of the present disclosure is shown.

[0017] Figure 6 The application of the technology according to some embodiments of the present disclosure in a cellular network is shown.

[0018] Figure 7 A conventional beam selection process is shown.

[0019] Figure 8Shows an example of using a user model to predict the best beam pair according to some embodiments of the present disclosure.

[0020] Figure 9 Shows another example of using a user model to predict the best beam pair according to some embodiments of the present disclosure.

[0021] Figure 10 Shows the application of the technology according to some embodiments of the present disclosure in a vehicle-to-everything (V2X) network.

[0022] Figure 11 Is a block diagram showing a first example of an exemplary configuration of a gNB to which the technology of the present disclosure can be applied.

[0023] Figure 12 Is a block diagram showing a second example of an exemplary configuration of a gNB to which the technology of the present disclosure can be applied.

[0024] Figure 13 Is a block diagram showing an example of an exemplary configuration of a communication device to which the technology of the present disclosure can be applied.

[0025] Figure 14 Is a block diagram showing an example of an exemplary configuration of an in-vehicle navigation device to which the technology of the present disclosure can be applied.

[0026] Although the embodiments described in the present disclosure may be susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and are described in detail herein. It should be understood that the drawings and the detailed description thereof are not intended to limit the embodiments to the particular forms disclosed, but on the contrary, are intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the claims. Detailed Description of Specific Embodiments

[0027] Hereinafter, exemplary embodiments of the present disclosure will be described in conjunction with the accompanying drawings. For clarity and conciseness, not all features of the embodiments are described in the specification. However, it should be understood that many specific implementation-specific settings must be made during the implementation of the embodiments in order to achieve the specific goals of the developer, for example, to comply with those limitations related to the device and the service, and these limitations may vary with different implementation manners. In addition, it should also be understood that although the development work may be very complex and time-consuming, for those skilled in the art who benefit from the present disclosure, such development work is merely a routine task.

[0028] Here, it should also be noted that in order to avoid obscuring the present disclosure with unnecessary details, only the processing steps and / or device structures that are closely related to at least the solution of the present disclosure are shown in the drawings, and other details that are not closely related to the present disclosure are omitted.

[0029] Over time, artificial intelligence has been applied in various industries. From innovative applications in the healthcare industry to intelligent solutions in the financial services sector, and to efficient optimizations in the manufacturing and agricultural sectors, the popularization of artificial intelligence has become indispensable. At the current stage, enterprises can not only provide products and services to customers, but also integrate customized artificial intelligence models into them to further enhance the functions and performance of the products and services.

[0030] For example, in the field of communications, artificial intelligence is changing the way communication networks are managed and optimized. By analyzing a large amount of network data, artificial intelligence can predict network congestion, optimize bandwidth allocation, and even detect potential network failures in advance. This helps to provide more stable and efficient communication services, thus meeting the growing demand for connectivity in modern society.

[0031] Another example is in the field of autonomous driving, where artificial intelligence provides vehicles with intelligent decision-making and environmental perception capabilities. Through technologies such as deep learning and perception, vehicles can identify roads, vehicles, and pedestrians, thus enabling autonomous driving operations. This not only improves driving safety, but may also enhance traffic flow and energy utilization efficiency.

[0032] The fields of communications and autonomous driving are just examples of the areas where artificial intelligence can be applied. With the continuous progress of artificial intelligence technology, the application areas of this technology will continue to expand, thus bringing more innovation and change to all industries. However, the accompanying issues such as privacy, security, and ethics have also attracted wide attention. It is expected to improve the performance of artificial intelligence models while meeting privacy, security, and ethical requirements.

[0033] Generally, artificial intelligence models are generated and supplied by model providers. The model provider can be the provider of a product or service, or be associated with the provider of a product or service. The model provider can train an artificial intelligence model based on a training data set. The trained artificial intelligence model can be deployed to the user's device or system for the user to use. The deployed artificial intelligence model is referred to as the user model in this article.

[0034] The training data set used by the model provider to train the user model is usually limited. This training data set may not be optimally matched with the actual environment of the user who uses the user model. Therefore, the user may not be able to obtain the optimal performance of the user model in the actual environment. In some scenarios, it is expected to change (e.g., adjust or update) the deployed user model according to the user's actual environment.

[0035] However, it is not appropriate to leave the changes to the user model entirely to the user for implementation. Direct changes made by the user to the user model may degrade the performance of the model. For example, if the user autonomously changes the user model for autonomous driving, the changed user model may lead to accidents. If the user autonomously changes the user model for a communication network, the changed user model may lead to a decline in communication quality. The responsibility for such degradation will unreasonably fall on the user, while the model provider may evade any consequences caused by the degraded model.

[0036] On the other hand, it is also not appropriate to directly provide the user's local data to the model provider for updating the user model, as this may violate privacy or security requirements. Moreover, the user's local data may be voluminous and redundant, which brings a significant data transmission burden.

[0037] Therefore, the present disclosure provides improved systems, devices, and methods for updating user models. One or more embodiments of the present disclosure enable targeted updating of the user model using the user's local data while maintaining user privacy and security. In addition, one or more embodiments of the present disclosure can also address one or more other problems.

[0038] 1. Exemplary Architecture

[0039] Figure 1 A schematic diagram of an architecture 100 according to an embodiment of the present disclosure is shown. As shown, the architecture 100 may include a model management layer 110 and a model user layer 120.

[0040] The model management layer 110 may be associated with the provider of the artificial intelligence model. In some embodiments, the model management layer 110 may be implemented as one or more model management servers. These model management servers may be physical servers or servers hosted in the cloud. For example, the Figure 2 described electronic devices may be used to implement the model management servers.

[0041] According to some embodiments of the present disclosure, the model management layer 110 may be configured to maintain one or more artificial intelligence models. Maintenance may include generating, storing, and / or updating one or more artificial intelligence models. In some examples, the model management layer 110 may initially train one or more artificial intelligence models based on the training data sets it collects. The trained artificial intelligence models may be provided by the model management layer 110 to the model user layer 120 for deployment in the model user layer 120. In addition, the model management layer 110 may also update the one or more artificial intelligence models based on feedback from the model user layer 120 (e.g., model difference 113). The model management layer 110 may provide the updated version of the artificial intelligence model to the model user layer 120.

[0042] In Figure 1 the illustrated embodiment, the model management layer 110 may be configured to maintain a large model 112. The large model 112 may be an artificial intelligence model having a complexity exceeding a certain threshold. Such a large model 112 may not be suitable for running on a client device with limited processing capabilities. Therefore, the model management layer 110 may also be configured to reduce the large model 112 to generate a small model 111. The reduction may be performed by any suitable means such as knowledge distillation, model pruning, etc. The small model 111 may be provided to the model user layer 120 for deployment and use as a user model 121.

[0043] According to an embodiment of the present disclosure, the model management layer 110 may update the small model 111 based on feedback obtained from the model user layer 120 (e.g., model difference 113). In an embodiment where the model management layer 110 maintains the large model 112, the model management layer 110 may be configured to update the small model 111 based on a suitable method. In some examples, the model management layer 110 may first update the large model 112 and then generate an updated version of the small model 111 based on the reduction of the updated large model 112. In other examples, instead of first updating the large model 112, the model management layer 110 may directly update the small model 111.

[0044] In an alternative embodiment (not shown), instead of maintaining the large model 112, the model management layer 110 maintains one or more small models 111. The corresponding small models 111 among these small models 111 may be provided to the model user layer 120 for deployment in corresponding application scenarios. In this case, the model management layer 110 may directly update the corresponding small model 111 based on the model difference 113 obtained in the corresponding application scenario.

[0045] The model user layer 120 may be associated with users of the artificial intelligence model. The model user layer 120 may be referred to as a user system. In some embodiments, the model user layer 120 may include one or more client devices. The client devices may include, for example, UEs, in-vehicle devices, media devices, etc. The client devices in the model user layer 120 may be implemented using, for example, Figure 3 the described electronic devices. In some embodiments, the model user layer 120 may optionally further include an intermediate device (e.g., a base station device) between the client device and the model management server.

[0046] The model user layer 120 may be configured to execute one or more trained user models 121 provided by the model management layer 110. The model user layer 120 may be configured to provide local data as input data to the user model 121. The local data may include actual data associated with the client device in the model user layer 120 (which is also referred to as user data herein). The local data may include, but is not limited to, environmental data, operation data, measurement data, multimedia data, etc. associated with the client device. The user model 121 is a trained artificial intelligence model that may generate one or more output results based on the input local data. These output results may include various types of outputs, such as classification of the input data or predictions generated based on the input data. The client device in the model user layer 120 may also use the output results of the user model 121 to perform one or more actions, such as controlling the operation of the client device.

[0047] According to some embodiments of the present disclosure, the model user layer 120 may also be configured to determine a model difference 122 associated with the user model 121. The model difference 122 may be used to characterize the difference between the actual performance of the deployed user model 121 and the expected performance of the user model 121 in the deployed environment. In some embodiments, the model user layer 120 may include two tutoring models, such as tutoring model A 123 and tutoring model B 124. Each of the tutoring models A 123 and B 124 may be an artificial intelligence model different from the user model 121. The tutoring model A 123 may be configured to simulate the actual performance of the deployed user model 121. The tutoring model B 124 may be configured to simulate the expected performance of the user model 121. The expected performance may refer to the optimal performance of the user model 121 in the current environment. The difference between the tutoring model A 123 and the tutoring model B 124 may be used to characterize the model difference 122.

[0048] In some embodiments, the model user layer 120 may be configured to train one or more initial tutoring models to obtain a tutoring model A 123 and a tutoring model B 124. For example, the model user layer 120 may be configured to perform model training using local data and the actual output results generated by the user model 121 based on the local data, thereby obtaining the tutoring model A 123. The model user layer 120 may also be configured to perform model training using local data and the output results expected of the user model 121 for the local data, thereby obtaining the tutoring model B 124. The model user layer 120 may determine a model difference 122 based on the obtained tutoring model A 123 and tutoring model B 124. The model difference 122 may represent the difference between the actual performance and the expected performance of the user model 121. Any suitable manner may be used to characterize the model difference 122. For example, the model difference 122 may be represented as the difference between the model parameters, performance metrics, or output results of the tutoring model A 123 and the tutoring model B 124.

[0049] The model user layer 120 may also be configured to provide the determined model difference 122 to the model management layer 110 for updating the user model, as described above. In some embodiments, the model management layer 110 may aggregate multiple model differences 122 from the model user layer 120 to update the user model.

[0050] It should be understood that Figure 1 the architecture 100 is merely exemplary. Various modifications may be made to the architecture 100 without departing from the scope of the present disclosure. For example, although the architecture 100 is shown as including only one small model 111 and a corresponding user model 121, in other embodiments, the architecture 100 may include any number of small models 111 and user models 121 for deployment to multiple client devices. In some embodiments, a corresponding pair of tutoring models 123 and 124 may be trained for each client device among the multiple client devices. In other embodiments, a corresponding pair of tutoring models 123 and 124 may be trained for each subset of client devices among the multiple client devices. In this case, the pair of tutoring models 123 and 124 may be trained based on the actual output results and the expected output results of the user models from all the client devices in the subset. Other modifications are possible without departing from the scope of the present disclosure.

[0051] 2. Exemplary Device

[0052] Figure 2 An exemplary block diagram of an electronic device 200 according to some embodiments of the present disclosure is shown. The electronic device 200 may be implemented, for example, in Figure 1at the model management layer 110 of the described architecture 100. In some embodiments, the electronic device 200 may be implemented as a model management server. The electronic device 200 may be used to perform one or more operations described herein related to the model management layer 110 or the model management server. Specifically, the electronic device 200 may be implemented as the model management server itself, as part of the model management server, or as a control device for controlling the model management server. For example, the electronic device 200 may be implemented as a chip for controlling the model management server. In some embodiments herein, implementing the electronic device 200 as the model management server itself is merely for convenience of description and is not intended to be limiting.

[0053] According to some embodiments of the present disclosure, the electronic device 200 may include a communication unit 210, a storage unit 220, and a processing circuit 230.

[0054] The communication unit 210 of the electronic device 200 may be used to receive or send wired transmissions or radio transmissions. In some embodiments of the present disclosure, the communication unit 210 may perform functions such as upconversion, digital-to-analog conversion, etc. on the transmitted signal and / or perform functions such as downconversion, analog-to-digital conversion, etc. on the received signal. Various techniques may be used to implement the communication unit 210. For example, the communication unit 210 may be implemented as communication interface components such as antenna devices, radio frequency circuits, and part of the baseband processing circuit. In Figure 2 the figure, the communication unit 210 is drawn with a dashed line because the communication unit 210 may alternatively be located within the processing circuit 230 or outside the electronic device 200.

[0055] The storage unit 220 of the electronic device 200 may store information generated by the processing circuit 230, information received from other devices through the communication unit 210, or information to be sent to other devices, computer programs, machine codes, data, etc. for the operation of the electronic device 200. According to some embodiments of the present disclosure, the storage unit 220 may store one or more artificial intelligence models, model differences, updates to the artificial intelligence models, update logs or records, and / or other associated data. The storage unit 220 may be volatile memory and / or non-volatile memory. For example, the storage unit 220 may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The storage unit 220 is drawn with a dashed line because it may alternatively be located within the processing circuit 230 or outside the electronic device 200.

[0056] The processing circuit 230 of the electronic device 200 may be configured to perform one or more operations to provide various functions of the electronic device 200. For example, the processing circuit 230 may be configured to perform the steps of the method described with respect to Figure 4 The processing circuit 230 may perform corresponding operations by executing one or more executable instructions stored in the storage unit 220. The processing circuit 230 may be used to implement one or more steps performed by the model management server in various methods according to some embodiments of the present disclosure.

[0057] According to some embodiments of the present disclosure, the processing circuit 230 may be configured to perform the method for updating the user model described herein. For example, the processing circuit 230 may include a model management unit 231. Specifically, the model management unit 231 may be configured to send model data defining an artificial intelligence model to the user system. The user system is, for example, Figure 1 The model user layer 120 described above. The model management unit 231 may also be configured to receive model difference data characterizing the model difference from the user system. Then, the model management unit 231 may also be configured to generate an updated version of the artificial intelligence model at least partially based on the model difference data. The model management unit 231 may also be configured to send the updated model data, which characterizes the updated version of the artificial intelligence model, to the user system.

[0058] It should be understood that Figure 2 The processing circuit 230 in is merely exemplary. The processing circuit 230 may include one or more additional units for performing the techniques of the present disclosure and / or perform one or more additional steps of the techniques of the present disclosure.

[0059] Figure 3 FIG. shows an exemplary block diagram of an electronic device 300 according to some embodiments of the present disclosure. The electronic device 300 may be implemented at the model user layer 120 of the architecture 100 as described in Figure 1 In some embodiments, the electronic device 300 may be implemented as a client device. The electronic device 300 may be used to perform one or more operations related to the model user layer 120 or the client device described herein. Specifically, the electronic device 300 may be implemented as the client device itself, as part of the client device, or as a control device for controlling the client device. For example, the electronic device 300 may be implemented as a chip for controlling the client device. In some embodiments herein, implementing the electronic device 300 as the client device itself is merely for convenience of description and is not intended to be limiting.

[0060] According to some embodiments of the present disclosure, the electronic device 300 may include a communication unit 310, a storage unit 320, and a processing circuit 330.

[0061] The communication unit 310 of the electronic device 300 may be used to receive or send wired or wireless transmissions. In some embodiments of the present disclosure, the communication unit 310 may perform functions such as up-conversion, digital-to-analog conversion, etc. on the transmitted signal and / or perform functions such as down-conversion, analog-to-digital conversion, etc. on the received signal. Various techniques may be used to implement the communication unit 310. For example, the communication unit 310 may be implemented as communication interface components such as antenna devices, radio frequency circuits, and part of the baseband processing circuit. In Figure 3 the figure, the communication unit 310 is drawn with a dashed line because the communication unit 310 may alternatively be located within the processing circuit 330 or outside the electronic device 300.

[0062] The storage unit 320 of the electronic device 300 may store information generated by the processing circuit 330, information received from other devices through the communication unit 310, or information to be sent to other devices, computer programs, machine codes, data, etc. for the operation of the electronic device 300. According to some embodiments of the present disclosure, the storage unit 320 may store a user model and local data, actual output results, and expected output results for the user model. According to some embodiments of the present disclosure, the storage unit 320 may also store one or more tutoring models and model differences. The storage unit 320 may be a volatile memory and / or a non-volatile memory. For example, the storage unit 320 may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The storage unit 320 is drawn with a dashed line because it may alternatively be located within the processing circuit 330 or outside the electronic device 300.

[0063] The processing circuit 330 of the electronic device 300 may be configured to perform one or more operations to provide various functions of the electronic device 300. For example, the processing circuit 330 may be configured to perform the steps of the method described with respect to Figure 5 The processing circuit 330 may perform corresponding operations by executing one or more executable instructions stored in the storage unit 320. The processing circuit 330 may be used to implement one or more steps performed by the model user layer in various methods according to some embodiments of the present disclosure.

[0064] According to some embodiments of the present disclosure, the processing circuit 330 may be configured to execute the methods for updating the user model described herein. For example, the processing circuit 330 may be configured to receive model data characterizing an artificial intelligence model from a model management server. The processing circuit 330 may also be configured to send model difference data characterizing the model difference to the model management server. The processing circuit 330 may also be configured to receive updated model data from the model management server, where the updated model data characterizes an updated version of the artificial intelligence model, and the updated version is at least partially based on the model difference data.

[0065] According to some embodiments of the present disclosure, the processing circuit 330 may include a model execution unit 331 for executing or using the received artificial intelligence model. The model execution unit 331 may be configured to provide input data local to the user to the artificial intelligence model, thereby obtaining one or more output results of the artificial intelligence model. The obtained output result is the actual output result of the artificial intelligence model. The actual output result may be provided to the electronic device 300 for performing one or more actions. Optionally, as described below, the actual output result may also be used to train one or more tutoring models. The model execution unit 331 may also be configured to monitor the performance of the deployed artificial intelligence model. In response to the performance of the deployed artificial intelligence model being lower than a specific standard, the model execution unit 331 may send a message to trigger an update of the artificial intelligence model.

[0066] According to some embodiments of the present disclosure, the processing circuit 330 may further include a difference determination unit 332 for determining model difference data. According to some embodiments of the present disclosure, the model difference data represents the difference between the actual performance of the deployed artificial intelligence model and the desired performance of the artificial intelligence model. In some embodiments, the difference may be represented by the difference between two tutoring models (e.g., a first tutoring model and a second tutoring model), where the first tutoring model simulates the actual performance of the artificial intelligence model, and the second tutoring model simulates the desired performance of the artificial intelligence model. According to some embodiments of the present disclosure, the processing circuit 330 may further include a model training unit 333 for training the first tutoring model and the second tutoring model. The model training unit 333 may be configured to train the first tutoring model at least partially based on the input data and the actual output result of the artificial intelligence model. The model training unit 333 may also be configured to train the second tutoring model at least partially based on the input data and the desired output result of the artificial intelligence model. The difference determination unit 332 and the model training unit 333 are drawn with dashed lines because they may alternatively be located outside the processing circuit 330 or outside the electronic device 300.

[0067] It should be understood, Figure 3The processing circuit 330 therein is merely exemplary. The processing circuit 330 may include one or more additional units for performing the techniques of the present disclosure and / or one or more additional steps for performing the techniques of the present disclosure.

[0068] 3. Exemplary Method

[0069] Figure 4 A flowchart of a method 400 for updating a user model according to some embodiments of the present disclosure is shown. The method 400 may be executed at the model management layer. For example, the method 400 may be executed by a model management server. The model management server may be implemented by the aforementioned electronic device 200. Accordingly, the method 400 may be executed by the processing circuit 230 of the electronic device 200. Specifically, the processing circuit 230 of the electronic device 200 may execute the method 400 by executing a computer program.

[0070] The method 400 may start from step 410. In step 410, the model management server may be configured to send model data characterizing an artificial intelligence model to the user system. The artificial intelligence model sent to the user may be referred to as a user model.

[0071] According to an embodiment of the present disclosure, the sent user model may be generated by the model management server. In some embodiments, the user model may be a small model generated by reducing a large model. The large model may be an artificial intelligence model having a complexity threshold exceeding a certain level. The complexity of the model may be characterized, for example, by the complexity of the topological structure, the number of model parameters, or any suitable metric, including but not limited to the number of layers, nodes, etc. of the model. For example, the large model of the model management server may have millions or more model parameters. Such a large model may not be suitable for running on a client device with limited processing capabilities. The model management server may be configured to reduce the large model or a part thereof by any suitable means such as knowledge distillation, model pruning, etc., so as to generate a small model. The small model may have a complexity significantly lower than that of the large model. For example, the small model may have a simpler model topological structure and / or fewer model parameters. The model management server may generate different small models for different application scenarios. The small model may be application-scenario specific, for example, generated by specifically reducing the large model for a specific application scenario. Therefore, the model management server may generate multiple small models for different application scenarios based on the same large model. By way of example and not limitation, the large model may be a multi-modal model capable of processing various media types (pictures, audio, text, video, etc.), and the multiple small models may include a graphic classification model, a face recognition model, a language translation model, a music recognition model, etc. Other types or sizes of large models and small models are also possible.

[0072] It should be understood that the technology of the present disclosure can be applied to various types of artificial intelligence models, including models that have been developed and models that may be developed in the future. Exemplary artificial intelligence models include, but are not limited to, models trained by convolutional neural networks (CNNs), deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTMs), generative models, random forests, and their variants and enhanced algorithms.

[0073] According to an embodiment of the present disclosure, the model data defining the artificial intelligence model sent by the model management server can have various suitable forms. The model data enables the client device to deploy and use the artificial intelligence model based on this data. In some embodiments, the model data may include a set of model parameters of the artificial intelligence model. Each artificial intelligence model can be represented by a set of model parameters characterizing the model. For example, for a CNN model, the set of model parameters characterizing the model may include, but are not limited to, one or more parameters describing the number of layers of the neural network, the number and distribution of neurons in each layer, the connection relationship between neurons, the weights of each neuron connection, etc. For other types of models, other types of model parameter sets can be used to characterize. In some embodiments, the model data may include an identifier of the artificial intelligence model, and this identifier uniquely identifies the model to be deployed. The user system receiving the model data can use this identifier to retrieve the corresponding model from the model repository. Other forms of model data are also possible.

[0074] In some embodiments, the model management server may also send indication information to the user system. This indication information can notify the user system that the model sent in step 410 is the initial trained model. In addition, this indication information can also notify the user system that the model service management server can correct the model based on feedback from the user system.

[0075] Method 400 can then continue to step 420. In this step, the model management server can be configured to receive model difference data characterizing the model difference from the user system.

[0076] According to some embodiments of the present disclosure, the model difference data can represent the difference between the actual performance of the artificial intelligence model deployed at the user system and the expected performance of the artificial intelligence model. In some embodiments, this difference can be represented as the difference between a first tutoring model and a second tutoring model, where the first tutoring model simulates the actual performance of the user model deployed at the user system, and the second tutoring model simulates the expected performance of the user model deployed at the user system. Details regarding the model difference data will be further described later.

[0077] Method 400 can then proceed to step 430. In this step, the model management server can be configured to generate an updated version of the artificial intelligence model based at least in part on the model difference data.

[0078] According to some embodiments of the present disclosure, the model management server maintains a larger-scale model, while the user model is a reduced-scale smaller model. In this case, the model management server can update the larger-scale model based at least in part on the model difference data and generate a smaller-scale model based on the reduction of the updated larger-scale model as the updated version of the artificial intelligence model. Alternatively, the model management server can directly update the smaller-scale model based at least in part on the model difference data as the updated version of the artificial intelligence model. The update can include various adjustments to the artificial intelligence model, such as adjusting parameters (including topology and / or weights).

[0079] Method 400 can then proceed to step 440. In this step, the model management server can be configured to send the updated model data representing the updated version of the artificial intelligence model to the user system. The updated version of the artificial intelligence model can be deployed to the client device to replace the previous version of the user model.

[0080] It should be understood that only exemplary embodiments of method 400 are described above. Method 400 can include one or more additional steps performed by the model management server. Details of various embodiments of method 400 and additional or alternative embodiments will be further described below.

[0081] Figure 5 A flowchart of a method 500 for updating a user model according to some embodiments of the present disclosure is shown. Method 500 can be executed at the model user layer. For example, method 500 can be executed by a client device. The client device can be implemented by the aforementioned electronic device 300. Correspondingly, method 500 can be executed by the processing circuit 330 of the electronic device 300. Specifically, the processing circuit 330 of the electronic device 300 can execute method 500 by executing a computer program.

[0082] Method 500 can start from step 510. In step 510, the client device can be configured to receive model data representing the artificial intelligence model from the model management server.

[0083] As described above, the model data representing the artificial intelligence model can include the model parameters of the artificial intelligence model or the identifier of the artificial intelligence model. The client device can locally deploy the corresponding artificial intelligence model (i.e., the user model) based on the model data. The client device can use local data as input data to execute the user model and obtain the corresponding output result.

[0084] Method 500 can then proceed to step 520. In this step, the client device can be configured to send model difference data characterizing the model difference to the model management server.

[0085] In the present disclosure, the model difference data can be used to characterize the difference between the actual performance of the deployed user model and the expected performance of the user model in the deployed environment. The actual performance of the user model is associated with the actual output result provided by the user model based on local data. The expected performance of the user model is associated with the expected output result (e.g., the correct output result) that the user model should provide based on this local data. As previously mentioned, since the training data set used by the model provider (e.g., the model management layer) to train the user model may not optimally match the actual environment of the user using the user model, the user may not be able to obtain the optimal performance of the user model in this actual environment. In other words, since the performance of the user model is not perfect, the actual output result of the user model may be inconsistent with the expected output result of the user. This inconsistency is specific to the user's actual environment and reflects the defect of the deployed user model in this actual environment. The performance of the user model in this actual environment can be improved by discovering this inconsistency and providing it to the model management layer to update the user model.

[0086] According to an embodiment of the present disclosure, in order to characterize the aforementioned inconsistency from the perspective of the model, two tutoring models can be introduced, namely, the first tutoring model and the second tutoring model. The first tutoring model can be configured to simulate the actual performance of the user model. Given the same input data, the first tutoring model is expected to produce an output result that is the same as or similar to the actual output result of the user model. The second tutoring model can be configured to simulate the expected performance of the user model. Given the same input data, the second tutoring model is expected to produce an output result that is the same as or similar to the expected output result of the user model. The model difference data provided in step 520 can be characterized as the model difference between the first tutoring model and the second tutoring model. Providing the model difference data rather than the user data to the model management layer can protect the privacy and security of the user because the model difference data does not contain data directly associated with the user's actual environment.

[0087] According to some embodiments of the present disclosure, model difference data can be obtained based on one or more aspects of a first tutoring model and a second tutoring model. In some examples, the model difference data can represent the differences between one or more model parameters between the first tutoring model and the second tutoring model. In some other examples, the model difference data can represent the differences between one or more performance metrics between the first tutoring model and the second tutoring model. In still some other examples, the model difference data can represent the differences between one or more output results between the first tutoring model and the second tutoring model. In other examples, the model difference data can include combinations of the foregoing various forms. Other forms of model difference data are also possible.

[0088] According to some embodiments of the present disclosure, various metrics can be used to characterize model differences. Exemplary metrics can include one or several of gradient, weight, divergence, distance, eigenvalue, etc. In some embodiments, the values of the respective metrics characterizing the model differences can be the differences between the values of two corresponding parameters of the first tutoring model and the second tutoring model. For example, in the case where the corresponding parameter is the gradient of the weight of the model, the value characterizing the model difference between the two models can include the difference between the gradients associated with the two models. In some embodiments, the values of the respective metrics can be a distance metric or a similarity metric (such as Euclidean distance, KL divergence, normalized value, etc.) between the two parameters. In some embodiments, the features of the model differences can be used to represent the model differences to further reduce the amount of data. The features of the model differences can be represented by compression or enhancement of the model differences, including but not limited to distribution, eigenvalue, pruning of the model differences, top-k weights of the model differences, weights of the model differences above a certain threshold, certain layers of the model differences, and so on.

[0089] According to some embodiments of the present disclosure, the first tutoring model and the second tutoring model that meet the foregoing requirements can be obtained in various ways. Preferably, the first tutoring model and the second tutoring model can be obtained through model training. For example, the input data of the deployed user model and the actual output results of the user model can be used to construct a first training dataset. In the first training dataset, the actual output results of the user model can be labeled as facts. In addition, the input data of the deployed user model and the expected output results of the user model can be used to construct a second training dataset. In the second training dataset, the expected output results of the user model can be labeled as facts. The first training dataset can be used to perform model training to obtain the first tutoring model. The second training dataset can be used to perform model training to obtain the second tutoring model.

[0090] For purposes of explanation, by way of example and not limitation, the input data may be an image of a dog, the actual output result of the user model classifies the image as a cat, while the expected output result is a dog. Accordingly, in the first training dataset, the image is labeled as a cat (i.e., the actual output result of the user model), because it is desired that the output result of the first tutoring model for such an image be the same as the actual output result of the user model (even if the result is incorrect). In the second training dataset, the image is labeled as a dog, because it is desired that the output result of the second tutoring model for such an image be the same as the expected output result. Iteratively training the first tutoring model and the second tutoring model using the constructed first training dataset and second training dataset respectively can enable the two models to simulate the actual performance and the expected performance of the user model respectively.

[0091] According to an embodiment of the present disclosure, the data used to construct the first training dataset or the second training dataset may come from one or more clients where the user model is deployed. For example, in some embodiments, the input data and / or the output result (e.g., the actual output result and the expected output result of the user model) may come from a single client where the user model is deployed (e.g., a single UE or in-vehicle device). In other embodiments, the input data and / or the output result from multiple clients where the user model is deployed may be aggregated to construct the first training dataset for training the first tutoring model and the second training dataset for training the second tutoring model. For example, the multiple clients may include all the clients where the user model is deployed. Alternatively, the multiple clients may include a specific subset of all the clients where the user model is deployed, e.g., some clients sharing the same actual environment. In some examples, the specific subset may be identified based on the location of each client (e.g., cell, driving area, etc.). In some embodiments, the output result used to construct the training dataset (e.g., the actual output result and the expected output result of the user model) may come from a specific client, while the input data used to construct the training dataset may come from one or more other clients of the subset to which the specific client belongs.

[0092] According to some embodiments of the present disclosure, the first tutoring model and the second tutoring model may be based on the same initial tutoring model. In other words, the two tutoring models are obtained by separately training the same initial tutoring model using different first training datasets and second training datasets. In some embodiments, the model management layer may provide the initial tutoring model to the model user layer. As mentioned above, providing the initial tutoring model may include providing the model parameters or identifiers of the model. The initial tutoring model may have the same type as the user model.

[0093] In some embodiments, the training of the first tutoring model and the second tutoring model is initiated in response to the actual performance of the user model not meeting a specific standard. For example, the client device can monitor the performance of the deployed user model. When the performance of the deployed user model does not meet the specific standard, the client device can send a message to the model management layer to, for example, request an update to the deployed user model. In response to this message, the model management layer can trigger the training of the tutoring model. For example, the model management layer can provide the initial tutoring model to the model user layer. In addition, the model management layer can send a training data configuration to the model user layer, and the training data configuration can specify the composition and format of the first training dataset and the second training dataset. Based on the training data configuration, the model user layer can accordingly collect and save the actual output results, expected output results, and input data of the user model for constructing the first training dataset and the second training dataset.

[0094] According to some embodiments of the present disclosure, the first tutoring model and the second tutoring model can have a complexity different from that of the deployed user model. In some examples, the complexity of the first tutoring model and the second tutoring model can be lower than that of the user model, which can save the overhead of model training. In some examples, the complexity of the first tutoring model and the second tutoring model can be the same as that of the user model. For example, the initial tutoring model can be the same as the initial model on which the user model is based. In some examples, the first tutoring model and the second tutoring model can have a complexity higher than that of the deployed user model. For example, in the case of using a CNN model, the initial tutoring model used to train the first tutoring model and the second tutoring model can have more neural network layers and / or a larger number of neurons per layer than the deployed user model. The increased complexity allows for a higher-resolution characterization of the model differences.

[0095] Method 500 can then continue to step 530. In this step, the client device can be configured to receive updated model data from the model management server. The updated model data characterizes an updated version of the user model that is at least partially based on the model difference data in step 520.

[0096] According to some embodiments of the present disclosure, the user model deployed at the client is a smaller-scale model generated based on the reduction of a larger-scale model. In this case, the model management server can update the larger-scale model at least partially based on the model difference data and generate a smaller-scale model based on the reduction of the updated larger-scale model as the updated version of the user model. Alternatively, the model management server can directly update the smaller-scale model at least partially based on the model difference data as the updated version of the user model.

[0097] According to some embodiments of the present disclosure, a client device may be configured to deploy an updated version of a user model using updated model data. The client device may allow the updated version. If the performance of the updated version of the user model still does not meet a specific standard, the client device may send a message to the model management layer to request a further update of the user model. The further update of the user model may include repeating some or all of the foregoing steps, which will not be elaborated herein. The model management server may be configured to record each update of the model.

[0098] It should be understood that the above-described are merely exemplary embodiments of method 500. Method 500 may include one or more additional steps performed by the model user layer. Details of various embodiments of method 500 and additional or alternative embodiments will be further described below.

[0099] The functions of the elements disclosed herein may be implemented using circuitry or a processing circuit, which includes a general-purpose processor, a dedicated processor, an integrated circuit, an ASIC ("Application-Specific Integrated Circuit"), conventional circuitry, and / or a combination thereof that is configured or programmed to perform the disclosed functions. A processor is considered a processing circuit or circuitry because it includes transistors and other circuitry therein. In the present disclosure, a circuit, a unit, or a device is hardware that executes or is programmed to execute the described function. The hardware may be any hardware disclosed herein or otherwise known, which is programmed or configured to execute the described function. When the hardware is a processor that may be considered a type of circuitry, the circuit, device, or unit is a combination of hardware and software, and the software is used to configure the hardware and / or the processor.

[0100] 4. Exemplary Scenarios

[0101] The following combines Figures 6 to 10 to describe the application of the technology of the present disclosure in multiple exemplary scenarios. It should be understood that these exemplary scenarios are illustrative and not intended to be limiting.

[0102] Figure 6 Shows the application of the technology according to some embodiments of the present disclosure in a cellular network 600. The shown application scenario is associated with beam control. It is merely illustrative and not intended to be limiting.

[0103] The cellular network 600 may include a core network 610, a base station 620 (e.g., a gNB), and a UE 630. The model management layer 110 may be deployed at the core network 610. For example, the core network 610 may include a 5G core network (5GC). The model management layer 110 may be deployed in the cloud at the 5GC. In some embodiments, the model management layer 110 may be deployed at the Network Data Analytics Function (NWDAF).

[0104] The base station 620 can receive the user model 121 from the model management layer 110. The initial user model 121 can be trained by the model management layer 110 using training data. The base station 620 can also forward the user model 121 to the UE 630 for deployment at the UE 630. For example, the base station 620 can receive model data representing the user model 121 from the model management layer 110 and forward the model data to the UE 630.

[0105] The UE 630 can deploy the user model 121 based on the received model data. The UE 630 can use data specific to the UE 630 as input to run the deployed user model 121. The data specific to the UE 630 can be referred to as the local data of the UE 630, which includes but is not limited to environmental data, operation data, measurement data, multimedia data, and so on. Different UEs can have different local data.

[0106] The actual output result of the user model 121 deployed at the UE 630 can be used for one or more operations of the UE 630. In Figure 6 the example shown, the one or more operations include beam control. In a cellular network, the base station 620 may have multiple candidate beams, and the UE 630 may also have multiple candidate beams. These beams form multiple candidate beam pairs. Beam control is used to use the best beam pair among the multiple candidate beam pairs for communication between the base station 620 and the UE 630.

[0107] Traditionally, the best beam pair is selected through a beam selection process. Figure 7illustrates a conventional beam selection process. The UE 630 may include a conventional beam selection module 632 for performing the conventional beam selection process. In this example, the base station has 5 candidate beams, each beam pointing in a different direction. Additionally, the UE has 4 candidate beams, each beam pointing in a different direction. Thus, there are 20 candidate beam pairs between the base station and the UE. The number of candidate beams is exemplary and not restrictive. During the beam selection process, the base station and the UE need to measure each of these candidate beam pairs. For example, the reference signal received power (RSRP) or any other suitable parameter at the UE can be measured. Specifically, for each of the 4 candidate beams of the UE, the base station sequentially transmits 5 candidate beams. The conventional beam selection module 632 may perform 20 measurements to obtain the measurement results (e.g., RSRP) associated with each candidate beam pair. The beam pair with the best measurement result (e.g., the beam with the highest RSRP) can be considered the best beam pair. The conventional beam selection module 632 may provide this best beam pair to the beam control module 631. The beam control module 631 may control the UE 630 to communicate with the base station 620 using this best beam pair.

[0108] An artificial intelligence model (e.g., the user model 121) can be used to improve the selection process of the best beam pair. Figure 8 illustrates an example 800 of using the user model 121 to predict the best beam pair according to some embodiments of the present disclosure. In this example, the user model 121 is trained to predict the best beam pair based on a small number of beam measurements. In this example, the number of beam measurements can be reduced. For example, the base station may not transmit the candidate beams shown as blank, but only transmit candidate beams in a few predetermined specific directions. The results of the small number of beam measurements performed can be provided as input data to the user model 121. The user model 121 can infer the best beam pair based on this input data. This can reduce the overhead for beam measurements.

[0109] Figure 9 illustrates another example 900 of using the user model 121 to predict the best beam pair according to some embodiments of the present disclosure. In this example, the user model 121 is trained to predict the future best beam pair based on the previous beam selection sequence. The model is, for example, an LSTM model. The previous beam selection sequence may include the results of beam measurements and the determined best beam pairs at one or more previous time points (e.g., T, T + 1, ……, etc.). In this example, the previous beam selection sequence can be provided as input data to the user model 121. The user model 121 can predict the best beam pair at the current time or future time based on this input data.

[0110] In Figures 8 - 9In the example, the prediction result of the user model 121 (i.e., the predicted beam pair) can be provided to the beam control module 631 of the UE 630. The beam control module 631 can control the UE 630 to communicate with the base station 620 using the predicted beam pair. It should be understood that Figures 8 - 9 the example is merely illustrative and not intended to be limiting. In other examples, the user model 121 can predict the optimal beam pair based on other types of input data.

[0111] Although using the user model 121 to predict the optimal beam pair may have some advantages compared to conventional methods, the predicted optimal beam pair is affected by the actual environment where the UE is located (e.g., a specific cell environment). The user model 121 trained and provided by the model management layer may not exactly match this actual environment. Therefore, the techniques disclosed herein can be used to update the user model. For example, when it is detected that the performance of the user model 121 is below a specific standard, an update of the user model can be triggered. As an example, when the RSRP of the optimal beam pair predicted by the user model 121 is lower than a first predetermined threshold, or when the communication quality using the predicted beam pair is lower than a second predetermined threshold, the UE 630 (or the base station 620) can send a message or request for triggering an update to the model management layer 110. Other specific standards are also possible.

[0112] In response to triggering an update of the user model, the model management layer 110 can provide an initial tutoring model to the model user layer for training a first tutoring model (e.g., tutoring model A) and a second tutoring model (e.g., tutoring model B). The tutoring model can be trained at the UE 630 or the base station 620. In Figure 6In the example, tutoring models A 123 and B are trained at base station 620 because base station 620 has more processing power than UE 630. In this case, UE 630 can construct the input data and actual results of user model 121 into a first training data set for training tutoring model A. As described above, the input data can be the result of beam measurements (e.g., can be from beam measurements performed by a conventional beam selection module 632), or a previous beam selection sequence (can be from stored data), or other local data used as input to user model 121 to predict the best beam pair (e.g., measurement data associated with the channel environment). The actual result can be the predicted beam pair generated by user model 121 based on the corresponding input data. Additionally, UE 630 can also construct the input data and the desired results of user model 121 into a second training data set for training tutoring model B. For example, the desired result can be the best beam pair with the best beam measurement result. The best beam measurement result is, for example, the highest RSRP determined by measuring all candidate beam pairs. The best beam pair with the best beam measurement result can be provided by the conventional beam selection module 632.

[0113] In some embodiments, UE 630 can receive a training data configuration from base station 620, and the training data configuration can specify how UE constructs the first training data set and the second training data set. Specifically, the training data configuration can specify the input data, actual output results, and / or desired output results of the user model for transmission from UE 630 to base station 620. The training data configuration can be carried in one or more signaling from the base station to the UE, such as RRC, MAC CE, or DCI. For example, in a conventional beam selection process, UE 630 may only feedback a limited number of beam measurement results (e.g., 4 beam pairs with the highest RSRP) to base station 620. To use the techniques of the present disclosure, base station 620 can instruct UE 630 to feedback more beam measurement results (e.g., all measurement results used as the input data of user model 121). This can be indicated by the training data configuration sent to UE 630.

[0114] Base station 620 can train tutoring model A and tutoring model B respectively based on the received first training data set and second training data set. If there are multiple UEs 630 deployed with the same user model 121 in the cell served by base station 620, base station 620 can optionally aggregate the input data and output results of the user models from the multiple UEs 630 as training data to train the tutoring model. Various appropriate techniques can be used to train the corresponding tutoring models, including training techniques that have been developed and training techniques that may be developed in the future. The training can be an iterative process, which ends when a termination condition (e.g., convergence) is reached.

[0115] Since the tutoring model A is trained based on the input data and the actual output results of the user model 121, the tutoring model A can simulate the actual performance of the user model 121. The tutoring model A may have the same or approximate model parameters or topological structures as the user model 121. Since the tutoring model B is trained based on the input data and the expected output results of the user model 121, the tutoring model B can simulate the expected performance of the user model 121. The tutoring model B may have the same or approximate model parameters or topological structures as the expected version of the user model 121 in the current environment. In practical applications, due to security and confidentiality requirements, the user model 121 may be opaque to the UE 630, so the UE 630 cannot access or know the internal structure of the user model 121. However, by training the tutoring model A and the tutoring model B, the UE 630 can simulate the actual version and the expected version of the user model 121 without modifying the user model 121 itself. The difference between the actual version and the expected version of the user model 121 can reflect the defects of the user model 121 in the current environment to a certain extent. This defect is specific to the environment and can therefore be used to update the user model so that the updated user model better matches the current environment.

[0116] The model difference 122 can be determined based on the trained tutoring model A and tutoring model B. In some embodiments, the model difference 122 can be represented as the difference between one or more model parameters of the tutoring model A and the tutoring model B. In some embodiments, the model difference 122 can be represented as the difference between one or more output results of the tutoring model A and the tutoring model B. For example, when the same input data is provided, the difference between the first best beam pair predicted by the tutoring model A and the second best beam pair predicted by the tutoring model B can form part of the model difference 122. In some embodiments, the model difference 122 can be represented as the difference between one or more performance metrics of the tutoring model A and the tutoring model B. For example, the difference in RSRP between the first best beam pair and the second best beam pair can form part of the model difference 122. The model difference data can include combinations of the foregoing various forms. Other forms of model difference data are also possible.

[0117] The base station 620 may send the determined model difference 122 to the model management layer 110 for updating the user model 121. As previously described, the update of the user model 121 by the model management layer 110 may be direct or may be indirect (e.g., first update a larger-scale model). When the model management layer 110 is connected to multiple base stations 620, the model management layer 110 may perform an update based on multiple model differences 122 from the multiple base stations 620. For example, these model differences 122 may be combined. In some examples, the model management layer 110 may perform an update in a manner of federated learning. The updated version of the obtained user model 121 may be deployed to the UE 620 via the base station 620 to replace the previously deployed user model. An appropriate moment may be selected to send the updated version of the user model 121. For example, the updated version of the user model 121 may be sent at a moment when the UE 630 is not currently using the user model 121 to complete the replacement of the user model 121.

[0118] It should be understood that Figures 6 - 9 The illustrated embodiments are merely illustrative and are not intended to be limiting. In other embodiments, the artificial intelligence model may be used in other aspects different from beam control. For example, in some embodiments, the artificial intelligence model may be used to select a target cell. In some embodiments, the artificial intelligence model may be used to schedule transmission resources. In some embodiments, the artificial intelligence model may be used to predict network congestion. In some embodiments, the artificial intelligence model may be used for power adjustment. The technology of the present disclosure is not limited by the type and function of the artificial intelligence model used. Each type of artificial intelligence model may have corresponding input data and corresponding actual output results. In addition, the desired output result of the artificial intelligence model may be obtained in various suitable ways. For example, as described previously for beam control, the UE or the base station may have or execute a conventional method, and the result provided by the conventional method may be considered as the desired output result of the artificial intelligence model. In some examples, the desired output result of the artificial intelligence model may be provided by a person or other device that knows the desired output result. For example, in an example where the artificial intelligence model is used to predict the network rate, the actual network rate may be measured and provided as the desired output result of the artificial intelligence model.

[0119] In addition, it should also be understood that Figure 6The distribution of the various components or elements shown is merely illustrative and is not intended to be limiting. In other embodiments, the distribution of the components or elements associated with the technology of the present disclosure may be different. In some examples, one or both of the two tutoring models may alternatively be located at the UE. In other examples, one or both of the two tutoring models may alternatively be located at other devices (e.g., other network functions) in the cellular network 600 other than the base station and the UE.

[0120] It should be understood that Figures 6 - 9 the cellular network 600 shown may include cellular communication technologies that have been developed, are being developed, or will be developed, such as 2G, 3G, 4G, 5G, 6G, and so on. Similar technologies may also be implemented in other types of wireless networks, such as Wi-Fi networks.

[0121] Figure 10 The application of the technology according to some embodiments of the present disclosure in the vehicle-to-everything (V2X) network 1000 is shown. The application scenario shown is associated with vehicle control. It is merely illustrative and is not intended to be limiting.

[0122] The V2X network 1000 may include a cloud 1010, an access point (AP) 1020, and in-vehicle devices 1030. The model management layer 110 may be deployed at the cloud 1010.

[0123] The AP 1020 may be a Wi-Fi access point, a cellular base station, or any other suitable network access point. The AP 1020 may receive the user model 121 from the model management layer 110. The AP 1020 may also forward the user model 121 to the in-vehicle device 1030 for deployment at the in-vehicle device 1030. For example, the AP 1020 may receive model data representing the user model 121 from the model management layer 110 and forward the model data to the in-vehicle device 1030.

[0124] The in-vehicle device 1030 may deploy the user model 121 based on the received model data. The in-vehicle device 1030 may use data specific to the in-vehicle device 1030 as input to run the deployed user model 121. The data specific to the in-vehicle device 1030 may be referred to as the local data of the in-vehicle device 1030, which includes but is not limited to environmental data, operation data, measurement data, multimedia data, and so on. Different in-vehicle devices 1030 may have different local data.

[0125] The actual output result of the user model 121 deployed at the in-vehicle device 1030 may be used for one or more operations of the in-vehicle device 1030. In Figure 10In the illustrated example, the one or more operations include vehicle control. Vehicle control may include, but is not limited to, various vehicle actions such as starting, accelerating, decelerating, braking, lane changing, steering, etc. By way of example and not limitation, the user model 121 may be configured to control lane changes based on measurements from sensors mounted on the vehicle. In other embodiments, the actual output of the user model 121 may be used for other aspects of the in-vehicle device 1030 without limitation.

[0126] The actual output of the user model 121 may be provided to the vehicle control module 1031. The vehicle control module 1031 may control the vehicle based on this result. At the same time, the vehicle control module 1031 may also receive control commands from other sources, such as driving decisions from the driver of the vehicle or other control devices on the vehicle. If the actual output of the user model 121 does not meet a specific criterion (e.g., the degree or frequency of driver manual intervention exceeds a threshold), then the performance of the user model 121 may not reach the desired level. Accordingly, the in-vehicle device 1030 may initiate an update of the user model 121.

[0127] In Figure 10In the example shown, the tutoring model A 123 and the tutoring model B 124 can be trained at the in-vehicle device 1030. The in-vehicle device 1030 can be configured to construct different training data sets to train the tutoring model A 123 and the tutoring model B 124 respectively. For example, the in-vehicle device 1030 can use the input data from the user model 121 deployed at the in-vehicle device 1030 and the corresponding actual output results to train the tutoring model A 123. In the example of vehicle control, the input data can be the sensed data associated with the vehicle, such as the captured environmental images, the current location, the current speed, etc. The actual output results can include the autonomous driving decisions given by the user model 121, such as lane change instructions, which can include, for example, the lane change direction, the lane change speed, the turn signal actions, etc. In some embodiments, the in-vehicle device 1030 can use the manual driving decisions as the expected output results to train the tutoring model B 124. The manual decision-making module 1032 of the in-vehicle device 1030 can collect the manual driving decisions. In the example of vehicle control, the manual driving decisions can be the decisions actually made by the driver of the vehicle. For example, the manual driving decisions can include whether the driver allows the vehicle to operate based on the autonomous driving decisions given by the user model 121, or whether the driver makes driving actions different from the autonomous driving decisions. The in-vehicle device 1030 can also be configured to determine the model difference 122 based on the trained tutoring model A 123 and the tutoring model B 124, and send the determined model difference 122 to the model management layer 110 via the AP 1020 for updating the user model 121. The updated version of the user model 121 can also be forwarded to the in-vehicle device 1030 via the AP 1020 for deployment.

[0128] It should be understood that Figure 10 the embodiments shown are merely illustrative and are not intended to be limiting. In other embodiments, the artificial intelligence model can be used for other aspects of vehicle control. For example, in some embodiments, the artificial intelligence model can be used for air conditioning control. In some embodiments, the artificial intelligence model can be used for gasoline or battery control. Other functions of the artificial intelligence model are also possible. In addition, Figure 10 the distribution of the various components or elements shown is merely illustrative and is not intended to be limiting. In other embodiments, the distribution of the components or elements associated with the technology of the present disclosure can be different.

[0129] In still other examples, the techniques according to some embodiments of the present disclosure can be used in media devices. For example, an artificial intelligence model can be deployed in a media device and configured to classify media data. For example, the media device can be a camera with an artificial intelligence model that can classify the captured images. Accordingly, the input data of the artificial intelligence model can include media data, and the actual output result of the artificial intelligence model includes a predicted classification generated based on the media data. The expected data result of the artificial intelligence model includes the true classification of the media data, which can be obtained in various ways. For example, the true classification can be obtained through user feedback.

[0130] It should be understood that the exemplary scenarios described above are illustrative and not intended to be limiting. The techniques disclosed herein can also be used in other suitable scenarios.

[0131] 5. Application Product Examples

[0132] The techniques of the present disclosure can be applied to various products.

[0133] For example, the control device / base station mentioned in the present disclosure can be implemented as any type of base station, such as an eNB, such as a macro eNB and a small eNB. A small eNB can be an eNB that covers a cell smaller than a macro cell, such as a pico eNB, a micro eNB, and a home (femto) eNB. Also for example, it can be implemented as a gNB, such as a macro gNB and a small gNB. A small gNB can be a gNB that covers a cell smaller than a macro cell, such as a pico gNB, a micro gNB, and a home (femto) gNB. Instead, the base station can be implemented as any other type of base station, such as a NodeB and a Base Transceiver Station (BTS). The base station can include: a main body configured to control wireless communication (also referred to as a base station device); and one or more Remote Radio Heads (RRHs) provided in a place different from the main body. Additionally, various types of terminals described below can all act as a base station by temporarily or semi-persistently performing base station functions. For example, the terminal device mentioned in the present disclosure can be implemented as a mobile terminal (such as a smart phone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital imaging device) or a vehicle-mounted terminal (such as an automotive navigation device) in some embodiments. The terminal device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also referred to as a machine type communication (MTC) terminal). Furthermore, the terminal device can be a wireless communication module (such as an integrated circuit module including a single wafer) installed on each of the above terminals.

[0134] Application examples according to the present disclosure will be described below with reference to the accompanying drawings.

[0135] [Example of Base Station]

[0136] It should be understood that the term "base station" in the present disclosure has the full breadth of its ordinary meaning and at least includes a wireless communication station used as part of a wireless communication system or radio system to facilitate communication. Examples of base stations can be, for example, but not limited to the following: A base station can be one or both of a base transceiver station (BTS) and a base station controller (BSC) in a GSM system, one or both of a radio network controller (RNC) and a Node B in a WCDMA system, an eNB in LTE and LTE-Advanced systems, or a corresponding network node in a future communication system (such as a gNB, eLTE eNB, etc. that may appear in a 5G communication system). Some functions of the base stations in the present disclosure can also be implemented as an entity having a control function for communication in D2D, M2M, and V2V communication scenarios, or as an entity that plays a role in spectrum coordination in a cognitive radio communication scenario.

[0137] First Example

[0138] Figure 11 FIG. is a block diagram of a first example showing an exemplary configuration of a gNB to which the technology of the present disclosure can be applied. The gNB 2100 includes a plurality of antennas 2110 and a base station device 2120. The base station device 2120 and each antenna 2110 can be connected to each other via RF cables. In one implementation, the gNB 2100 (or the base station device 2120) here can correspond to the control-side electronic device described above.

[0139] Each of the antennas 2110 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for the base station device 2120 to transmit and receive wireless signals. As Figure 11 shown, the gNB 2100 can include a plurality of antennas 2110. For example, the plurality of antennas 2110 can be compatible with a plurality of frequency bands used by the gNB 2100.

[0140] The base station device 2120 includes a controller 2121, a memory 2122, a network interface 2123, and a wireless communication interface 2125.

[0141] The controller 2121 can be, for example, a CPU or a DSP, and operates various functions of the higher layers of the base station device 2120. For example, the controller 2121 determines the location information of the target terminal device among at least one terminal device based on the location information of at least one terminal device on the terminal side in the wireless communication system and the specific location configuration information of at least one terminal device obtained by the wireless communication interface 2125. The controller 2121 can have a logical function to execute control such as radio resource control, radio bearer control, mobility management, access control, and scheduling. This control can be executed in combination with a nearby gNB or a core network node. The memory 2122 includes a RAM and a ROM, and stores programs executed by the controller 2121 and various types of control data (such as a terminal list, transmission power data, and scheduling data).

[0142] The network interface 2123 is a communication interface for connecting the base station device 2120 to the core network 2124. The controller 2121 can communicate with a core network node or another gNB via the network interface 2123. In this case, the gNB 2100 and the core network node or other gNBs can be connected to each other through logical interfaces (such as the S1 interface and the X2 interface). The network interface 2123 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 2123 is a wireless communication interface, compared with the frequency band used by the wireless communication interface 2125, the network interface 2123 can use a higher frequency band for wireless communication.

[0143] The wireless communication interface 2125 supports any cellular communication scheme (such as Long-Term Evolution (LTE) and LTE-Advanced), and provides a wireless connection to terminals located in the cell of the gNB 2100 via the antenna 2110. The wireless communication interface 2125 generally can include, for example, a baseband (BB) processor 2126 and an RF circuit 2127. The BB processor 2126 can execute, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and execute various types of signal processing of layers (such as L1, Media Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP)). Instead of the controller 2121, the BB processor 2126 can have a part or all of the above logical functions. The BB processor 2126 can be a memory storing a communication control program, or a module including a processor configured to execute the program and related circuits. The update program can change the function of the BB processor 2126. The module can be a card or a blade inserted into a slot of the base station device 2120. Alternatively, the module can also be a chip mounted on the card or the blade. At the same time, the RF circuit 2127 can include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 2110. AlthoughFigure 11 An example is shown where an RF circuit 2127 is connected to an antenna 2110. However, the present disclosure is not limited to this illustration, and an RF circuit 2127 can be connected to multiple antennas 2110 simultaneously.

[0144] As Figure 11 shown, the wireless communication interface 2125 can include multiple BB processors 2126. For example, the multiple BB processors 2126 can be compatible with multiple frequency bands used by the gNB 2100. As Figure 11 shown, the wireless communication interface 2125 can include multiple RF circuits 2127. For example, the multiple RF circuits 2127 can be compatible with multiple antenna elements. Although Figure 11 an example is shown where the wireless communication interface 2125 includes multiple BB processors 2126 and multiple RF circuits 2127, the wireless communication interface 2125 can also include a single BB processor 2126 or a single RF circuit 2127.

[0145] Second Example

[0146] Figure 12 is a block diagram of a second example showing an exemplary configuration of a gNB to which the techniques of the present disclosure can be applied. The gNB 2200 includes multiple antennas 2210, RRH 2220, and base station equipment 2230. The RRH 2220 and each antenna 2210 can be connected to each other via RF cables. The base station equipment 2230 and the RRH 2220 can be connected to each other via a high-speed line such as an optical fiber cable. In one implementation, the gNB 2200 (or the base station equipment 2230) here can correspond to the control-side electronic device described above.

[0147] Each of the antennas 2210 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used to transmit and receive wireless signals for the RRH 2220. As Figure 12 shown, the gNB 2200 can include multiple antennas 2210. For example, the multiple antennas 2210 can be compatible with multiple frequency bands used by the gNB 2200.

[0148] The base station equipment 2230 includes a controller 2231, a memory 2232, a network interface 2233, a wireless communication interface 2234, and a connection interface 2236. The controller 2231, the memory 2232, and the network interface 2233 are the same as the controller 2121, the memory 2122, and the network interface 2123 described with reference to Figure 11 above.

[0149] The wireless communication interface 2234 supports any cellular communication scheme (such as LTE and LTE-Advanced), and provides wireless communication to terminals located in the sector corresponding to the RRH 2220 via the RRH 2220 and the antenna 2210. The wireless communication interface 2234 generally may include, for example, a BB processor 2235. Except that the BB processor 2235 is connected to the RF circuit 2222 of the RRH 2220 via the connection interface 2236, the BB processor 2235 is the same as the BB processor 2126 described with reference to Figure 11 As Figure 12 shown, the wireless communication interface 2234 may include multiple BB processors 2235. For example, multiple BB processors 2235 may be compatible with multiple frequency bands used by the gNB 2200. Although Figure 12 shows an example in which the wireless communication interface 2234 includes multiple BB processors 2235, the wireless communication interface 2234 may also include a single BB processor 2235.

[0150] The connection interface 2236 is an interface for connecting the base station device 2230 (wireless communication interface 2234) to the RRH 2220. The connection interface 2236 may also be a communication module for communication in the above-mentioned high-speed line for connecting the base station device 2230 (wireless communication interface 2234) to the RRH 2220.

[0151] The RRH 2220 includes a connection interface 2223 and a wireless communication interface 2221.

[0152] The connection interface 2223 is an interface for connecting the RRH 2220 (wireless communication interface 2221) to the base station device 2230. The connection interface 2223 may also be a communication module for communication in the above-mentioned high-speed line.

[0153] The wireless communication interface 2221 transmits and receives wireless signals via the antenna 2210. The wireless communication interface 2221 generally may include, for example, an RF circuit 2222. The RF circuit 2222 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 2210. Although Figure 12 shows an example in which one RF circuit 2222 is connected to one antenna 2210, the present disclosure is not limited to this illustration, but one RF circuit 2222 may be connected to multiple antennas 2210 simultaneously.

[0154] As Figure 12 shown, the wireless communication interface 2221 may include multiple RF circuits 2222. For example, multiple RF circuits 2222 may support multiple antenna elements. Although Figure 12An example is shown in which the wireless communication interface 2221 includes a plurality of RF circuits 2222, but the wireless communication interface 2221 may also include a single RF circuit 2222.

[0155] [Examples of user equipment / terminal equipment]

[0156] First example

[0157] Figure 13 FIG. is a block diagram of an example showing an exemplary configuration of a communication device 2300 (e.g., a smart phone, a communicator, etc.) to which the techniques of the present disclosure may be applied. The communication device 2300 includes a processor 2301, a memory 2302, a storage device 2303, an external connection interface 2304, a camera device 2306, a sensor 2307, a microphone 2308, an input device 2309, a display device 2310, a speaker 2311, a wireless communication interface 2312, one or more antenna switches 2315, one or more antennas 2316, a bus 2317, a battery 2318, and an auxiliary controller 2319. In one implementation, the communication device 2300 (or the processor 2301) here may correspond to the above-described transmitting device or the terminal-side electronic device.

[0158] The processor 2301 may be, for example, a CPU or a system-on-chip (SoC), and controls the functions of the application layer and other layers of the communication device 2300. The memory 2302 includes RAM and ROM, and stores data and programs executed by the processor 2301. The storage device 2303 may include a storage medium such as a semiconductor memory and a hard disk. The external connection interface 2304 is an interface for connecting an external device (such as a memory card and a universal serial bus (USB) device) to the communication device 2300.

[0159] The camera device 2306 includes an image sensor (such as a charge-coupled device (CCD) and a complementary metal oxide semiconductor (CMOS)), and generates a captured image. The sensor 2307 may include a set of sensors such as a measurement sensor, a gyro sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 2308 converts the sound input to the communication device 2300 into an audio signal. The input device 2309 includes, for example, a touch sensor configured to detect a touch on the screen of the display device 2310, a keypad, a keyboard, a button, or a switch, and receives operations or information input from a user. The display device 2310 includes a screen (such as a liquid crystal display (LCD) and an organic light-emitting diode (OLED) display), and displays the output image of the communication device 2300. The speaker 2311 converts the audio signal output from the communication device 2300 into sound.

[0160] The wireless communication interface 2312 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2312 generally may include, for example, a BB processor 2313 and an RF circuit 2314. The BB processor 2313 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. At the same time, the RF circuit 2314 may include, for example, mixers, filters, and amplifiers, and transmit and receive wireless signals via an antenna 2316. The wireless communication interface 2312 may be a single chip module on which the BB processor 2313 and the RF circuit 2314 are integrated. As Figure 13 shown, the wireless communication interface 2312 may include a plurality of BB processors 2313 and a plurality of RF circuits 2314. Although Figure 13 an example in which the wireless communication interface 2312 includes a plurality of BB processors 2313 and a plurality of RF circuits 2314 is shown, the wireless communication interface 2312 may also include a single BB processor 2313 or a single RF circuit 2314.

[0161] In addition, in addition to cellular communication schemes, the wireless communication interface 2312 may support other types of wireless communication schemes, such as short-range wireless communication schemes, near-field communication schemes, and wireless local area network (LAN) schemes. In this case, the wireless communication interface 2312 may include a BB processor 2313 and an RF circuit 2314 for each wireless communication scheme.

[0162] Each of the antenna switches 2315 switches the connection destination of the antenna 2316 among a plurality of circuits (for example, circuits for different wireless communication schemes) included in the wireless communication interface 2312.

[0163] Each of the antennas 2316 includes a single or a plurality of antenna elements (such as a plurality of antenna elements included in a MIMO antenna) and is used for the wireless communication interface 2312 to transmit and receive wireless signals. As Figure 13 shown, the communication device 2300 may include a plurality of antennas 2316. Although Figure 13 an example in which the communication device 2300 includes a plurality of antennas 2316 is shown, the communication device 2300 may also include a single antenna 2316.

[0164] In addition, the communication device 2300 may include an antenna 2316 for each wireless communication scheme. In this case, the antenna switch 2315 may be omitted from the configuration of the communication device 2300.

[0165] The bus 2317 connects the processor 2301, the memory 2302, the storage device 2303, the external connection interface 2304, the imaging device 2306, the sensor 2307, the microphone 2308, the input device 2309, the display device 2310, the speaker 2311, the wireless communication interface 2312, and the auxiliary controller 2319 to each other. The battery 2318 supplies power to Figure 13 each block of the communication device 2300 shown via a feeder line, which is partially shown as a dashed line in the figure. The auxiliary controller 2319 operates the minimum necessary functions of the communication device 2300, for example, in the sleep mode.

[0166] Second example

[0167] Figure 14 is a block diagram showing an example of an exemplary configuration of an in-vehicle navigation device 2400 to which the technology of the present disclosure can be applied. The in-vehicle navigation device 2400 includes a processor 2401, a memory 2402, a Global Positioning System (GPS) module 2404, a sensor 2405, a data interface 2406, a content player 2407, a storage medium interface 2408, an input device 2409, a display device 2510, a speaker 2411, a wireless communication interface 2413, one or more antenna switches 2416, one or more antennas 2417, and a battery 2418. In one implementation, the in-vehicle navigation device 2400 (or the processor 2401) here can correspond to a transmitting device or a terminal-side electronic device.

[0168] The processor 2401 can be, for example, a CPU or an SoC, and controls the navigation function and other functions of the in-vehicle navigation device 2400. The memory 2402 includes a RAM and a ROM, and stores data and programs executed by the processor 2401.

[0169] The GPS module 2404 measures the position (such as latitude, longitude, and altitude) of the in-vehicle navigation device 2400 using GPS signals received from GPS satellites. The sensor 2405 can include a set of sensors, such as a gyro sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 2406 is connected to, for example, an in-vehicle network 2421 via a terminal (not shown), and acquires data generated by the vehicle (such as vehicle speed data).

[0170] The content player 2407 reproduces content stored in a storage medium (such as a CD and a DVD) inserted into the storage medium interface 2408. The input device 2409 includes, for example, a touch sensor, a button, or a switch configured to detect a touch on the screen of the display device 2510, and receives operations or information input from the user. The display device 2510 includes a screen such as an LCD or an OLED display, and displays an image of a navigation function or reproduced content. The speaker 2411 outputs a sound of the navigation function or reproduced content.

[0171] The wireless communication interface 2413 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 2413 generally may include, for example, a BB processor 2414 and an RF circuit 2415. The BB processor 2414 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 2415 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 2417. The wireless communication interface 2413 may also be a single chip module on which the BB processor 2414 and the RF circuit 2415 are integrated. As Figure 14 shown, the wireless communication interface 2413 may include a plurality of BB processors 2414 and a plurality of RF circuits 2415. Although Figure 14 an example in which the wireless communication interface 2413 includes a plurality of BB processors 2414 and a plurality of RF circuits 2415 is shown, the wireless communication interface 2413 may also include a single BB processor 2414 or a single RF circuit 2415.

[0172] In addition, in addition to the cellular communication scheme, the wireless communication interface 2413 may support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near-field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 2413 may include a BB processor 2414 and an RF circuit 2415.

[0173] Each of the antenna switches 2416 switches the connection destination of the antenna 2417 among a plurality of circuits (such as circuits for different wireless communication schemes) included in the wireless communication interface 2413.

[0174] Each of the antennas 2417 includes a single or a plurality of antenna elements (such as a plurality of antenna elements included in a MIMO antenna), and is used for the wireless communication interface 2413 to transmit and receive wireless signals. As Figure 14 shown, the car navigation device 2400 may include a plurality of antennas 2417. Although Figure 14An example is shown in which the vehicle navigation device 2400 includes a plurality of antennas 2417, but the vehicle navigation device 2400 may also include a single antenna 2417.

[0175] In addition, the vehicle navigation device 2400 may include an antenna 2417 for each wireless communication scheme. In this case, the antenna switch 2416 may be omitted from the configuration of the vehicle navigation device 2400.

[0176] The battery 2418 supplies power to each block of the vehicle navigation device 2400 shown via a feeder line, which is partially shown as a dashed line in the figure. The battery 2418 accumulates the power supplied from the vehicle. Figure 14 The battery 2418 supplies power to each block of the vehicle navigation device 2400 shown via a feeder line, which is partially shown as a dashed line in the figure. The battery 2418 accumulates the power supplied from the vehicle.

[0177] The technology of the present disclosure may also be implemented as a vehicle system (or vehicle) 2420 including one or more blocks of the vehicle navigation device 2400, the in-vehicle network 2421, and the vehicle module 2422. The vehicle module 2422 generates vehicle data (such as vehicle speed, engine speed, and fault information), and outputs the generated data to the in-vehicle network 2421.

[0178] The exemplary embodiments of the present disclosure have been described above with reference to the drawings, but the present disclosure is of course not limited to the above examples. Those skilled in the art can obtain various changes and modifications within the scope of the appended claims, and it should be understood that these changes and modifications will naturally fall within the technical scope of the present disclosure.

[0179] It should be understood that machine-executable instructions in a machine-readable storage medium or program product according to an embodiment of the present disclosure may be configured to perform operations corresponding to the above device and method embodiments. When referring to the above device and method embodiments, the embodiments of the machine-readable storage medium or program product are clear to those skilled in the art, and thus will not be described repeatedly. The machine-readable storage medium and program product for carrying or including the above machine-executable instructions also fall within the scope of the present disclosure. Such a storage medium may include, but is not limited to, a floppy disk, an optical disk, a magneto-optical disk, a memory card, a storage stick, and the like.

[0180] In addition, it should be understood that the above series of processes and devices may also be implemented by software and / or firmware. In the case of implementation by software and / or firmware, corresponding programs constituting the corresponding software are stored in the storage medium of the relevant device, and when the program is executed, various functions can be performed.

[0181] For example, a plurality of functions included in one unit in the above embodiments may be implemented by separate devices. Alternatively, a plurality of functions implemented by a plurality of units in the above embodiments may be respectively implemented by separate devices. In addition, one of the above functions may be implemented by a plurality of units. Needless to say, such a configuration is included in the technical scope of the present disclosure.

[0182] In this specification, the steps described in the flowcharts include not only processes executed sequentially in a time series, but also processes executed in parallel or individually, not necessarily in a time series. Furthermore, even in the steps of processing in a time series, needless to say, the order can be appropriately changed.

[0183] 6. Exemplary Embodiments of the Present Disclosure

[0184] 1. An electronic system, comprising: at least one processing unit; and at least one storage unit including computer program code, wherein the at least one storage unit and the computer program code are configured to cause the electronic system to perform the following operations through the at least one processing unit: receive model data representing an artificial intelligence model from a model management server; send model difference data representing a model difference to the model management server; and receive updated model data from the model management server, the updated model data representing an updated version of the artificial intelligence model, the updated version being at least partially based on the model difference data.

[0185] 2. The electronic system according to Embodiment 1, wherein the model difference data represents a difference between the actual performance of the artificial intelligence model and the expected performance of the artificial intelligence model.

[0186] 3. The electronic system according to Embodiment 2, wherein the model difference data represents a model difference between a first tutoring model and a second tutoring model, wherein the first tutoring model simulates the actual performance of the artificial intelligence model, and wherein the second tutoring model simulates the expected performance of the artificial intelligence model.

[0187] 4. The electronic system according to Embodiment 3, wherein the model difference data represents at least one of the following differences between the first tutoring model and the second tutoring model: a difference between one or more model parameters; a difference between one or more performance metrics; or a difference between one or more output results.

[0188] 5. The electronic system according to Embodiment 3, wherein the at least one storage unit and the computer program code are further configured to cause the electronic system to perform the following operations through the at least one processing unit: train the first tutoring model at least partially based on the input data and the actual output results of the artificial intelligence model; and train the second tutoring model at least partially based on the input data and the expected output results of the artificial intelligence model.

[0189] 6. The electronic system as described in Embodiment 5, wherein the first tutoring model and the second tutoring model are based on the same initial tutoring model.

[0190] 7. The electronic system as described in Embodiment 5, wherein the first tutoring model and the second tutoring model have a complexity higher than that of the artificial intelligence model.

[0191] 8. The electronic system as shown in Embodiment 5, wherein the training of the first tutoring model and the second tutoring model is initiated in response to the actual performance of the artificial intelligence model not meeting a specific standard.

[0192] 9. The electronic system as described in Embodiment 1, wherein the model data characterizing the artificial intelligence model includes at least one of the following: the model parameters of the artificial intelligence model; or the identifier of the artificial intelligence model.

[0193] 10. The electronic system as described in Embodiment 1, wherein the artificial intelligence model is a smaller-scale model generated based on the reduction of a larger-scale model.

[0194] 11. The electronic system as described in Embodiment 10, wherein the updated version is generated based on one of the following operations: directly updating the artificial intelligence model at least partially based on the model difference data; or updating the larger-scale model at least partially based on the model difference data and generating the updated version of the artificial intelligence model based on the reduction of the updated larger-scale model.

[0195] 12. The electronic system as described in Embodiment 5, wherein the artificial intelligence model is deployed at a user equipment UE in a cellular network.

[0196] 13. The electronic system as described in Embodiment 12, wherein the first tutoring model and the second tutoring model are trained at a network device of the cellular network.

[0197] 14. The electronic system as described in Embodiment 13, wherein the UE receives a training data configuration from the cellular network, and the training data configuration specifies the input data, the actual output result, and / or the desired output result of the artificial intelligence model for sending from the UE to the network device.

[0198] 15. The electronic system as described in Embodiment 13, wherein the artificial intelligence model is configured to predict the best beam pair between the UE and a base station of the cellular network, and wherein: the actual output result includes the predicted beam pair output by the artificial intelligence model; the desired output result includes the best beam pair with the best beam measurement result.

[0199] 16. An electronic system as in Embodiment 5, wherein the electronic system is associated with a vehicle, and the artificial intelligence model is configured to generate driving decisions for the vehicle, and wherein: the input data at least includes sensing data associated with the vehicle; the actual output result includes an autonomous driving decision generated by the artificial intelligence model based on the environmental sensing data; and the expected output result includes a manual driving decision made by the vehicle driver.

[0200] 17. An electronic system as in Embodiment 5, wherein the electronic system is associated with a media device, and the artificial intelligence model is configured to generate a classification of media data of the media device, and wherein: the input data includes the media data; the actual output result includes a predicted classification generated by the artificial intelligence model based on the media data; and the expected output result includes the true classification of the media data.

[0201] 18. An electronic system includes: at least one processing unit; and at least one storage unit, the at least one storage unit including computer program code, wherein the at least one storage unit and the computer program code are configured, through the at least one processing unit, to cause the electronic system to perform the following operations: send model data defining an artificial intelligence model to a user system; receive model difference data characterizing a model difference from the user system; generate an updated version of the artificial intelligence model at least partially based on the model difference data; and send updated model data to the user system, the updated model data characterizing the updated version of the artificial intelligence model.

[0202] 19. The electronic system as in Embodiment 18, wherein the model difference data represents the difference between the actual performance and the expected performance of the artificial intelligence model.

[0203] 20. The electronic system as in Embodiment 19, wherein the model difference data represents the model difference between a first tutoring model and a second tutoring model, wherein the first tutoring model simulates the actual performance of the artificial intelligence model deployed in the user system, and wherein the second tutoring model simulates the expected performance of the artificial intelligence model deployed in the user system.

[0204] 21. The electronic system as in Embodiment 20, wherein the model difference data represents at least one of the following differences between the first tutoring model and the second tutoring model: the difference between one or more model parameters; the difference between one or more performance metrics; or the difference between one or more output results.

[0205] 22. The electronic system as described in Embodiment 20, wherein generating the updated version of the artificial intelligence model includes one of the following operations: directly updating the artificial intelligence model at least partially based on the model difference data; or updating a larger-scale model at least partially based on the model difference data, and generating a smaller-scale model based on the reduction of the updated larger-scale model as the updated version of the artificial intelligence model.

[0206] 23. A method includes: receiving model data representing an artificial intelligence model from a model management server; sending model difference data representing model differences to the model management server; and receiving updated model data from the model management server, the updated model data representing the updated version of the artificial intelligence model, the updated version being at least partially based on the model difference data.

[0207] 24. A method includes: sending model data defining an artificial intelligence model to a user system; receiving model difference data representing model differences from the user system; generating the updated version of the artificial intelligence model at least partially based on the model difference data; and sending the updated model data representing the updated version of the artificial intelligence model to the user system.

[0208] 25. A computer-readable storage medium storing one or more instructions, which when executed by one or more processing circuits of an electronic device, cause the electronic device to perform the method as described in any one of Embodiments 23-24.

[0209] 26. A computer program product includes a computer program, which when executed by a processor, performs the method as described in any one of Embodiments 23-24.

[0210] 27. An apparatus including components for performing the method as described in any one of Embodiments 23-24.

Claims

1. An electronic system, comprising: at least one processing unit; and at least one storage unit, the at least one storage unit including computer program code, wherein the at least one storage unit and the computer program code are configured to, by means of the at least one processing unit, cause the electronic system to perform the following operations: receive model data representing an artificial intelligence model from a model management server; send model difference data representing a model difference to the model management server; and receive updated model data from the model management server, the updated model data representing an updated version of the artificial intelligence model, the updated version being at least partially based on the model difference data.

2. The electronic system according to claim 1, wherein, the model difference data represents the difference between the actual performance of the artificial intelligence model and the expected performance of the artificial intelligence model.

3. The electronic system according to claim 2, wherein, the difference is described by the difference between a first tutoring model and a second tutoring model, wherein the first tutoring model simulates the actual performance of the artificial intelligence model, and wherein the second tutoring model simulates the expected performance of the artificial intelligence model.

4. The electronic system according to claim 3, wherein, the model difference data represents at least one of the following differences between the first tutoring model and the second tutoring model: the difference between one or more model parameters; the difference between one or more performance metrics; or the difference between one or more output results.

5. The electronic system according to claim 3, wherein, the at least one storage unit and the computer program code are further configured to, by means of the at least one processing unit, cause the electronic system to perform the following operations: train the first tutoring model at least partially based on the input data and the actual output results of the artificial intelligence model; and train the second tutoring model at least partially based on the input data and the expected output results of the artificial intelligence model.

6. The electronic system according to claim 5, wherein, the first tutoring model and the second tutoring model are based on the same initial tutoring model.

7. The electronic system according to claim 5, wherein, the first tutoring model and the second tutoring model have a higher complexity than the artificial intelligence model.

8. The electronic system according to claim 5, wherein, the training of the first tutoring model and the second tutoring model is initiated in response to the actual performance of the artificial intelligence model not meeting a specific standard.

9. The electronic system according to claim 1, wherein, the model data representing the artificial intelligence model includes at least one of the following: the model parameters of the artificial intelligence model; or the identifier of the artificial intelligence model.

10. The electronic system according to claim 1, wherein, the artificial intelligence model is a smaller-scale model generated based on the reduction of a larger-scale model.

Images