Method and apparatus for configuring ai function

Abstract

This application provides a method and apparatus for configuring AI functions. The method includes: a terminal device receiving first configuration information sent by a network device, the first configuration information being used to configure at least one AI function of the terminal device; and the terminal device configuring the at least one AI function according to the first configuration information. According to this application, the network device can, to a certain extent, control the model activated on the terminal device side in a function-based LCM, or the network device can sense the model information activated on the terminal device side in a function-based LCM, thereby better achieving function / model control.

Description

Method and device for configuring AI function Technical Field

[0001] The embodiments of the present application relate to the field of communication technologies. Background Art

[0002] The 3GPP R18 artificial intelligence / machine learning (AI / ML) project defines multiple scenarios or sub-scenarios, such as CSI enhancement (which may also include at least one sub-scenario of CSI compression and CSI prediction), beam management, positioning or other scenarios. Different scenarios or sub-scenarios may correspond to one or more features / feature groups. Applying AI / ML to the above feature / feature group is called AI / ML-based / enabled feature / feature group. An AI / ML-based / enabled feature / feature group may correspond to one or more AI functions and / or one or more AI models. One AI function may correspond to one or more AI models. The possible logic is shown in Figure 1.

[0003] Among them, the life cycle management (LCM) corresponding to AI / ML-based / enabled features / feature groups can be divided into functionality-based LCM and model-ID-based LCM, depending on whether it is at the functionality granularity or model (model-ID) granularity. LCM may include at least one of the following: data collection, model training, model inference, model monitoring, model / functionality control, model update, model transfer / delivery, model storage, terminal capability reporting, or other processes. Among them, model / functionality control includes at least one of the following AI operations: model / function selection, activation, deactivation, switch, fallback, release, and suspend. Among them, fallback refers to falling back to a mode where AI is not applied.

[0004] It should be noted that the above introduction to the technical background is merely intended to provide a clear and complete description of the technical solutions of this application and facilitate understanding by those skilled in the art. Simply because these solutions are described in the background technology section of this application, it should not be assumed that the above technical solutions are well known to those skilled in the art.

[0005] Summary of the Invention

[0006] The inventors discovered that in a function-based LCM mechanism, if the AI ​​model corresponding to a feature / feature group is deployed on one side of a terminal device, that is, the AI ​​model is a UE-sided model, when the network device configures an AI operation, the network device can only perceive the AI ​​operation at the function level, and not the model-level operation within the terminal device. That is, the network device only needs to perceive whether the terminal device has performed an AI operation for the feature / feature group and what AI operation has been performed, but does not perceive the model information that the terminal device runs after enabling AI for the feature / feature group. For example, the AI ​​models corresponding to feature / feature group 1 include model 1, model 2, and model 3. When the network device sends configuration information corresponding to feature / feature group 1 to instruct the terminal device to activate function 1, that is, to instruct the terminal device to activate AI based / enabled feature / feature group 1, the terminal device can choose to activate model 1, or deactivate model 1 and switch to activating model 2. The above-mentioned model-level operations are transparent to the network device. In other words, the network device can configure the AI ​​operation, and the terminal device selects the model within the activated function.

[0007] It can be seen that in the existing function-based LCM, the network device cannot participate in the model selection within the function on the terminal device side, which may cause the model selected by the terminal device to not meet the expectations of the network device.

[0008] In response to at least one of the above problems or other similar problems, an embodiment of the present application provides a configuration method and device for an AI function, so that the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or enable the network device to perceive the model information activated on the terminal device side in the function-based LCM, so as to better realize the control of the function / model.

[0009] According to one aspect of an embodiment of the present application, there is provided an AI function configuration device, configured in a terminal device, wherein the device includes:

[0010] a receiving unit configured to receive first configuration information sent by a network device, where the first configuration information is used to configure at least one AI function of the terminal device;

[0011] A configuration unit configured to configure the at least one AI function according to the first configuration information.

[0012] According to another aspect of an embodiment of the present application, there is provided an AI function configuration device configured in a network device, wherein the device includes:

[0013] a first sending unit configured to send first configuration information to a terminal device, where the first configuration information is used to configure at least one AI function of the terminal device;

[0014] A second sending unit sends first indication information and / or second indication information to the terminal device, wherein the first indication information is used to indicate the model configuration information under the at least one AI function that the network device prefers, and the second indication information is used to instruct the terminal device to send the activated model information under the at least one AI function to the network device.

[0015] One of the beneficial effects of the embodiments of the present application is that: according to the embodiments of the present application, the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or the network device can perceive the model information activated on the terminal device side in the function-based LCM, thereby better realizing the control of the function / model.

[0016] With reference to the following description and accompanying drawings, specific embodiments of the present application are disclosed in detail, indicating the manner in which the principles of the present application can be employed. It should be understood that the embodiments of the present application are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present application include many variations, modifications and equivalents.

[0017] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0018] It should be emphasized that the term "include / comprising" when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The elements and features described in one figure or one embodiment of the present application can be combined with the elements and features shown in one or more other figures or embodiments. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one embodiment.

[0020] FIG1 is a logical diagram of AI functions and their corresponding AI models;

[0021] FIG2 is a schematic diagram of a configuration method of an AI function according to an embodiment of the first aspect of the present application;

[0022] FIG3 is a schematic diagram of information interaction between a terminal device and a network device according to the method of the above embodiment;

[0023] FIG4 is another schematic diagram of information interaction between a terminal device and a network device according to the method of the above embodiment;

[0024] FIG5 is a schematic diagram of a configuration method of an AI function according to an embodiment of the second aspect of the present application;

[0025] FIG6 is a schematic diagram of a configuration device for AI functions according to an embodiment of the third aspect of the present application;

[0026] FIG7 is another schematic diagram of a device for configuring an AI function according to an embodiment of the third aspect of the present application;

[0027] FIG8 is a schematic diagram of a communication system according to an embodiment of the present application;

[0028] FIG9 is a schematic diagram of a terminal device according to an embodiment of the present application;

[0029] FIG10 is a schematic diagram of a network device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The above and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are disclosed in detail, which illustrate some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents that fall within the scope of the appended claims.

[0031] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements from the name, but do not indicate the spatial arrangement or temporal order of these elements, and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0032] In the embodiments of this application, the singular forms "a," "the," etc. include plural forms and should be broadly understood to mean "a" or "a type" rather than being limited to "one." Furthermore, the term "said" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. Furthermore, the term "according to" should be understood to mean "at least in part based on...", and the term "based on" should be understood to mean "at least in part based on...", unless the context clearly indicates otherwise.

[0033] In the embodiments of the present application, a scenario involving network devices and / or terminal devices is taken as an example.

[0034] In the above scenario, the network device may include at least one of a core network device, a third-party application device, an operation administration and maintenance (OAM), and an access network device.

[0035] The core network device may refer to a device in the core network (CN) that provides service support for the terminal device. As some examples, the core network device may be at least one of the following: a mobility and management entity (MME), an access and mobility management function (AMF) entity, a session management function (SMF) entity, a user plane function (UPF) entity, a location management function (LMF) entity, and the like, which are not listed here one by one. Among them, the AMF entity may be responsible for the access management and mobility management of the terminal, the SMF entity may be responsible for session management, such as the establishment of a user session, and the UPF entity may be a functional entity of the user plane, mainly responsible for connecting to the external network. The LMF entity may manage the overall coordination and scheduling of resources required for the location of the terminal device registered with the core network device or accessing the core network device. It should be noted that in the embodiment of the present application, the entity may also be referred to as a network element or a functional entity, such as the AMF entity may also be referred to as an AMF network element or an AMF functional entity, and so on.

[0036] The third-party application device can be an OTT service (over the top server) or other third-party device.

[0037] OAM is a network device that performs operations, management, and maintenance on the network according to the actual needs of the operator's network operations.

[0038] The access network device is an access device that the terminal device uses to access the communication system wirelessly. The access network device can be a base station (BS), an evolved NodeB (eNodeB), a transmission reception point (TRP), a base station (next generation NodeB, gNB) in the fifth generation (5G) mobile communication system, a base station in the sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. The access network device can also be a module or unit that completes part of the functions of the base station. For example, it can be at least one of the following modules or units: a centralized unit (CU), a distributed unit (DU), a centralized unit control plane (CU control plane, CU-CP), a centralized unit user plane (CU user plane, CU-CP), an integrated access backhaul (IAB) or other modules or units. The embodiments of the present application do not limit the specific technology and / or specific device form adopted by the access network device. The access network equipment can be deployed on land, including indoors / outdoors, and can be handheld or vehicle-mounted; it can also be deployed on the water, on an airplane, on a balloon or on a satellite; the access network equipment can be deployed in a fixed location or on a mobile carrier, and the embodiments of the present application do not limit this.

[0039] In the above scenarios, a terminal device can be a device with wireless transceiver capabilities that can send signals to and / or receive signals from an access network device. A terminal device can also be referred to as a terminal, mobile station, or mobile terminal. A terminal device can be a mobile phone, tablet, or other device with wireless intelligent transceiver capabilities. Terminal devices can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, and various smart scenarios.

[0040] In the above scenarios, access network devices and terminal devices, and terminal devices and terminal devices can communicate via licensed spectrum, unlicensed spectrum, or both. The embodiments of this application do not limit the spectrum resources used for wireless communications.

[0041] The following describes embodiments of the present application with reference to the accompanying drawings and detailed descriptions. For ease of description, the following description uses a base station as an example of an access network device. In the following description, "if," "under the circumstances," and "when" can be used interchangeably to avoid confusion.

[0042] Embodiments of the first aspect

[0043] An embodiment of the present application provides a method for configuring an AI function, which is described from the perspective of a terminal device.

[0044] FIG2 is a schematic diagram of a method for configuring an AI function according to an embodiment of the present application. As shown in FIG2 , the method includes:

[0045] 210: The terminal device receives first configuration information sent by the network device, where the first configuration information is used to configure at least one AI function of the terminal device.

[0046] 220: The terminal device configures the at least one AI function according to the first configuration information.

[0047] It is worth noting that FIG2 above only schematically illustrates an embodiment of the present application, and the present application is not limited thereto. For example, other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above content, and are not limited to the description of FIG2 above.

[0048] According to the above embodiment, the terminal device configures the corresponding AI function according to the first configuration information sent by the network device. Thus, the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or the network device can perceive the model information activated on the terminal device side in the function-based LCM, thereby better realizing function / model control.

[0049] In the above embodiment, the first configuration information, for example, includes configuration information corresponding to the following AI operations: at least one of activation, deactivation, switching, rollback, release, and suspension of an AI function. Accordingly, the terminal device can configure the at least one AI function based on the first configuration information, for example, to activate the corresponding AI function, deactivate the corresponding AI function, switch the corresponding AI function, roll back the corresponding AI function to a non-AI configuration, release the corresponding AI function, suspend the corresponding AI function, and so on. The above description of the first configuration information is merely illustrative; other configurations may be performed on the corresponding AI function as needed. For details, please refer to related technologies and are not described here.

[0050] In some embodiments, the terminal device may also receive first indication information, which is used to indicate the model configuration information of the at least one AI function that the network device prefers. It is understandable that the network device can inform the terminal device of its preferred model configuration information through the first indication information, thereby allowing the terminal device to determine the corresponding model based on the indication of the network device.

[0051] In the above embodiment, there is no limitation on the manner in which the first configuration information and the first indication information are sent. For example, the first configuration information and the first indication information may be sent via the same message or via different messages. For another example, the first configuration information may include the first indication information, or the first configuration information and the first indication information may be two parallel pieces of information within the same message, etc.

[0052] In the above embodiment, the model configuration information preferred by the network device may include at least one of the following information:

[0053] Model information of network device tendencies;

[0054] Network configuration information of the model favored by the network device;

[0055] Inference accuracy configuration information of network device tendencies;

[0056] Inferred latency configuration information of network devices;

[0057] Inference output information about network device tendencies;

[0058] Reasoning credibility configuration information of network device tendencies;

[0059] Network device vendor information corresponding to the network device preference model;

[0060] The terminal device manufacturer information corresponding to the network device preference model;

[0061] Chip device manufacturer information corresponding to the model favored by the network model.

[0062] Based on the above information, the terminal device can determine the model preferred by the network device, and then refer to the model configuration information to make corresponding model selection when selecting the model under at least one AI function.

[0063] In the above information, the model information that the network device tends to have may be at least one piece of identification information, which is used to identify the model that the network device tends to have.

[0064] In the above information, the network configuration information of the model preferred by the network device may include, for example, at least one of the following:

[0065] Network antenna configuration, such as antenna tilt information, number of antennas, configuration information of analog antennas, digital antennas, physical antennas, etc.

[0066] Network beam configuration, such as beam width information, number of beams, beam scanning information, and other configuration information;

[0067] Network coverage configuration, such as frequency information, coverage range information, indoor and outdoor configuration information;

[0068] Network status information, such as whether network energy saving is enabled for capacity stations and coverage stations, and network energy saving configuration information.

[0069] In the above information, the inference accuracy configuration information that the network device tends to have may be, for example, inference accuracy threshold information; correspondingly, the terminal device may determine a model whose inference accuracy that the network device tends to have is higher than or equal to the inference accuracy threshold.

[0070] In the above information, the inference delay configuration information that the network device tends to use may be, for example, inference delay threshold information; correspondingly, the terminal device may determine a model in which the network device tends to use an inference delay that is less than or equal to the inference delay threshold.

[0071] In the above information, the inference output result information of the network device tendency may be, for example, if the inference output results of the models under the same function are not completely the same, the inference output result information is used to indicate the inference output result of the network device tendency;

[0072] In the above information, the network device tends to configure the inference credibility, for example, the inference credibility threshold information; correspondingly, the terminal device can determine the model whose inference credibility of the network device tends to be higher than or equal to the inference credibility threshold.

[0073] In the above information, the manufacturer information may be manufacturer identification information, which may be used to indicate the manufacturer of the training model, or may be used to indicate the manufacturer when the terminal device receives the model.

[0074] The above is just an example, and this application does not limit the specific implementation of the network configuration information and other information in the above model configuration information.

[0075] In the above embodiment, the terminal device configures at least one AI function according to the first configuration information. For example, the terminal device determines information of available models under the at least one AI function according to the first configuration information and the first indication information.

[0076] According to the above embodiment, the model configuration information under the at least one AI function that the network device tends to indicate as the first indication information is used as the basis for screening the model on the terminal device side. As a result, the network device can control the model configured on the terminal device side in the function-based LCM (which can also be called the model for the terminal device to perform AI operations) to a certain extent, thereby improving the flexibility of the network device in the function-based LCM to control the model on the terminal device.

[0077] Optionally, in the above embodiment, the terminal device may further send a first response message to the network device, indicating through the first response message whether the terminal device has successfully configured the above at least one AI function according to the first configuration information and the first indication information.

[0078] In the above embodiment, the first response message may include information about the successfully configured AI function among the above at least one AI function, and may also include information about the unsuccessfully configured AI function among the above at least one AI function. The present application is not limited to this. The first response message may include both of the aforementioned information, that is, information about the successfully configured AI function among the above at least one AI function, and information about the unsuccessfully configured AI function among the above at least one AI function.

[0079] In the above embodiment, if the terminal device fails to successfully configure at least one AI function among the above at least one function, the first response message may further include a failure reason of the at least one unsuccessfully configured AI function to notify the network device.

[0080] In the above embodiment, the cause of failure may be, for example, the absence of an available model, or the inability to determine an available model based on the first indication information, or the unsupported configuration sent by the network device, or insufficient AI resources, or information about insufficient AI resources, etc.

[0081] FIG3 is a schematic diagram of information exchange between a terminal device and a network device according to the method of the above embodiment. In the example of FIG3 , the AI ​​operation configured by the first configuration information is "activate" as an example, but the present application is not limited thereto. The AI ​​operation configured by the first configuration information may also be any one or more of the above-listed operations. As shown in FIG3 , the information exchange process includes:

[0082] 310: The network device receives first information, where the first information is used to indicate information related to the AI ​​function.

[0083] 320: The network device sends first configuration information to the terminal device, where the first configuration information includes first indication information, where the first indication information is used to indicate the model configuration information of the AI ​​function preferred by the network device;

[0084] 330: The terminal device activates the model under the above-mentioned AI function according to the first configuration information;

[0085] 340: The terminal device sends a first response message to the network device, indicating through the first response message whether the terminal device has successfully activated the above-mentioned AI function.

[0086] It is worth noting that FIG3 above only schematically illustrates an embodiment of the present application, and the present application is not limited thereto. For example, other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above content, and are not limited to the description of FIG3 above.

[0087] In operation 310, the first information is used to indicate information related to the AI ​​function. The first information may include at least one of the following information:

[0088] For example, identification information of the functions of the AI / ML-based feature / feature group supported by the terminal device. The identification information can be an identification ID (identity or identifier), an index, or other information used to identify the function. For example, when the bit information in the bit string corresponds to the function, at least one bit in the bit string can indicate the corresponding function. For example, the maximum number of functions of the AI / ML-based feature / feature group supported by the terminal device or standard is 8, and the bit string includes 8 bits. As an example, the first bit of the bit string corresponds to the function with the smallest or largest identification information, the second bit of the bit string corresponds to the function with the second smallest or second largest identification information, and so on. It will not be repeated here.

[0089] Optionally, the first information may also indicate information about at least one model under the function. The information of the model may include at least one of the following information: model identification information, model operation information. Among them, the model identification information is used to identify the model, and the model operation information is used to indicate the requirement information for running the model. The requirement information can be used to indicate the AI ​​resource information required to run the model, and can also be used to indicate the network configuration information required to run the model, for example, at least one of the network equipment manufacturer information, terminal equipment manufacturer information, and chip equipment manufacturer information corresponding to the model. Furthermore, the first information may also indicate the storage information of the above-mentioned model. It can be understood that the storage information of the model can be at the model level, that is, indicating whether the terminal device has stored the model.

[0090] It can be understood that when the first information includes at least one of the above information, the network device can receive the first information through the same message or through different messages.

[0091] In the example of FIG3 , the network device receives the first information from the terminal device as an example, but the present application is not limited thereto. The network device may also receive the first information from the access network device and / or the core network device.

[0092] In operation 320, the model configuration information is a restriction condition for configuring the AI ​​function of the terminal device. The network device uses this model configuration information to restrict the terminal device when configuring the AI ​​function, thereby implementing the network device's control over the model selection for the terminal device's AI function in the function-based LCM. The relevant content of this model configuration information can be found in operation 210 and will not be repeated here.

[0093] In operation 320, the first configuration information may further include identification information of the activated AI function, that is, the network device configures the activated AI function for the terminal device through the first configuration information. For details, please refer to operation 210 and will not be repeated here.

[0094] Therefore, the terminal device can determine whether there is an available model that the network device tends to use under the AI ​​function configured by the network device based on the first configuration information and the first indication information. If so, perform operation 330.

[0095] In operation 330, the terminal device activates the AI ​​function as an example for description. As other possible implementation methods, the terminal device may also deactivate the AI ​​function, or switch the AI ​​function, or roll back the AI ​​function to a non-AI configuration, or release the AI ​​function, or suspend the AI ​​function, and so on.

[0096] In operation 340, the terminal device may inform the network device via a first response message whether it has successfully activated the network device's preferred available model for the activated AI function configured by the network device. If the terminal device fails to successfully activate the network device's preferred available model for the AI ​​function, the terminal device may also indicate the reason for the failure in the first response message. The reason for the failure has been described above and will not be repeated here.

[0097] If, in 320, the first configuration information sent by the network device is associated with multiple AI functions, for example, the first configuration information includes identification information of two activated AI functions, and the terminal device only activates some of the AI ​​functions in operation 330, for example, only activates the model under one of the AI ​​functions, in operation 340, the terminal device may indicate information about the successfully activated AI functions and / or information about the unsuccessfully activated AI functions through a first response message. For example, if the first response message includes information about the unsuccessfully activated AI function, it may further include a failure reason. The description of the failure reason is described in other embodiments of the present application and will not be repeated here.

[0098] In the above example, operation 340 is optional. For example, when the model of the network device preference under the activated AI function configured in the network device is successfully activated, the terminal device may not feed back the response message to the network device.

[0099] According to the above example, the network device uses the first indication information to indicate to the terminal device the configuration information (model configuration information) of the preferred model under its configured AI function, thereby being able to control the model selection under the activated AI function to a certain extent, thereby improving the flexibility of network control.

[0100] In other embodiments, the terminal device receives second indication information sent by the network device, where the second indication information is used to instruct the terminal device to send activated model information under at least one AI function to the network device.

[0101] In the above embodiment, the network device instructs the terminal device to report the activated model information under the above-mentioned at least one AI function to the network device through the second indication information. Thus, the terminal device can send the information of the activated model under the above-mentioned at least one AI function to the network device according to the second indication information. Then, the network device can perform corresponding control according to the model under the AI ​​function activated by the terminal device, thereby improving the flexibility of control.

[0102] In the above embodiment, if the terminal device changes the activated model under at least one of the above AI functions, the terminal device can report the latest activated model information to the network device. As a result, the terminal device can promptly report the latest activated model information to the network device when the activated model is updated, further improving the flexibility of network control.

[0103] In the above embodiment, the terminal device may also send the AI ​​function associated with the activated model information to the network device. Thus, if the network device is configured with multiple activated AI functions, the terminal device can obtain the relevant information of the model under each activated AI function and control the selection of the model under each AI function in a targeted manner.

[0104] FIG4 is a schematic diagram of information exchange between a terminal device and a network device according to the method of the above embodiment. In the example of FIG4 , the AI ​​operation configured by the first configuration information is "activate" as an example, but the present application is not limited thereto. The AI ​​operation configured by the first configuration information may also be any one or more of the above-listed operations. As shown in FIG4 , the information exchange process includes:

[0105] 410: The network device receives first information, where the first information is used to indicate information related to the AI ​​function.

[0106] 420: The terminal device receives first configuration information sent by the network device, where the first configuration information includes second indication information, where the second indication information is used to instruct the terminal device to report information about the activated model to the network device.

[0107] In the above embodiment, if the terminal device can successfully apply the first configuration information, step 430 is executed; if the terminal device cannot apply at least part of the configuration corresponding to the first configuration information, step 460 is executed.

[0108] 430: The terminal device performs a corresponding AI operation according to the first configuration information;

[0109] 440: The terminal device sends information about the activated model to the network device;

[0110] 450: When the terminal device changes the activated model, the terminal device indicates the latest activated model information to the network device;

[0111] 460: The terminal device sends a first response message to the network device, indicating through the first response message that the terminal device cannot apply at least part of the configuration corresponding to the above-mentioned first configuration information.

[0112] It is worth noting that FIG4 above only schematically illustrates an embodiment of the present application, and the present application is not limited thereto. For example, other operations may be added or some operations may be reduced. Those skilled in the art may make appropriate modifications based on the above content, and are not limited to the description of FIG4 above.

[0113] In operation 410, the content related to the first information is the same as that in operation 310 and will not be repeated here.

[0114] In operation 420, the content related to the first configuration information is the same as that of operation 320, for example, it is used to configure the AI ​​operation. As an example, the first configuration information is used to instruct the terminal device to activate a certain AI function, such as activating function 1.

[0115] In operation 420, the second indication information is used to instruct the terminal device to report the information of the activated model to the network device. Correspondingly, after executing operation 430, the terminal device can execute operation 440, that is, send the information of the activated model to the network device. As another possible implementation method, in operation 420, the second indication information can be used to instruct the terminal device to report the latest information of the activated model. Correspondingly, after executing operation 430, the terminal device can execute operation 440 according to the second indication information, that is, send the information of the activated model to the network device; when the activated model on the terminal device side changes, the terminal device can execute operation 450 according to the second indication information, that is, indicate the latest information of the activated model to the network device. For the relevant content of the information of the model, please refer to the description in the above embodiment and will not be repeated here.

[0116] In operation 430, the terminal device may perform a corresponding AI operation (ie, configure the AI ​​function) according to the first configuration information. For example, the terminal device activates function 1 according to the first configuration information. In addition, through specific implementation, the terminal device may also select and activate a model under function 1.

[0117] In operation 440, the terminal device may send information about the activated model to the network device based on the second indication information. It is understood that the terminal device may also indicate to the network device information about the function associated with the activated model information. For example, if the terminal device activates Model 1 under Function 1, it indicates to the network device that the activated model is Model 1 under Function 1. Thus, if there are multiple activated functions on the terminal device side, this method allows the network device to determine the information about the activated model under the activated function.

[0118] In operation 450, the terminal device may indicate the latest activated model information to the network device when changing the activated model. For example, when the terminal device deactivates model 1 and activates model 2, it may indicate to the network device that the currently activated model is model 2. This facilitates the network device to understand the latest activated model information under the AI ​​function. In the above example, operation 450 is optional. In some embodiments, the terminal device may not report the latest activated model information to the network device.

[0119] According to the above example, the network device instructs the terminal device to report the information of the model under the activated AI function through the second indication information, thereby being able to control the model selection under the activated AI function to a certain extent, thereby improving the flexibility of network control.

[0120] The above embodiments are only illustrative of the methods of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined. For example, the network device not only indicates the model configuration information under at least one AI function that the network device tends to use a first indication information, but also indicates the terminal device to send the activated model information under at least one AI function to the network device through a second indication information. The specific implementation process is as described above and will not be repeated here.

[0121] According to the method of the embodiment of the present application, the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or the network device can perceive the model information activated on the terminal device side in the function-based LCM, so as to better realize function / model control.

[0122] Embodiments of the second aspect

[0123] An embodiment of the present application provides a configuration method for an AI function, which is described from the perspective of a network device. The principle of solving the problem by this method is the same as that of the embodiment of the first aspect, and the same contents will not be repeated here.

[0124] FIG5 is a schematic diagram of a method for configuring an AI function according to an embodiment of the present application. As shown in FIG5 , the method includes:

[0125] 510: The network device sends first configuration information to the terminal device, where the first configuration information is used to configure at least one AI function of the terminal device.

[0126] 520: The network device sends first indication information and / or second indication information to the terminal device.

[0127] In some embodiments, the network device also receives a first response message sent by the terminal device, where the first response message is used to indicate whether the terminal device has successfully configured the at least one AI function according to the first configuration information and the first indication information.

[0128] In some embodiments, the network device also receives information about the model activated under the at least one AI function sent by the terminal device according to the second indication information.

[0129] In the above embodiment, the network device may also receive information of the latest activated model reported by the terminal device when the activated model under the above at least one AI function is changed.

[0130] In the above embodiment, the network device may also receive the AI ​​function associated with the information of the above activated model sent by the terminal device.

[0131] In the above embodiment, the relevant contents of the above-mentioned first configuration information, first indication information, second indication information, and first response message are the same as those in the embodiment of the first aspect, and their contents are merged here and will not be repeated here.

[0132] The above embodiments are only illustrative of the methods of the embodiments of the present application, but the present application is not limited thereto, and appropriate modifications can be made on the basis of the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined. For example, the network device not only indicates the model configuration information under at least one AI function that the network device tends to use a first indication information, but also indicates the terminal device to send the activated model information under at least one AI function to the network device through a second indication information. The specific implementation process is as described above and will not be repeated here.

[0133] According to the method of the embodiment of the present application, the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or the network device can perceive the model information activated on the terminal device side in the function-based LCM, so as to better realize function / model control.

[0134] Embodiments of the third aspect

[0135] An embodiment of the present application provides a device for configuring an AI function.

[0136] FIG6 is a schematic diagram of a configuration device for AI functions according to an embodiment of the present application. The device may be, for example, a terminal device, or one or more components or assemblies configured on the terminal device. Since the principle of solving the problem of the device is the same as that of the embodiment of the first aspect, its specific implementation can refer to the implementation of the method of the embodiment of the first aspect, and the same contents will not be repeated. As shown in FIG6, the device 600 includes:

[0137] A receiving unit 610 receives first configuration information sent by a network device, where the first configuration information is used to configure at least one AI function of a terminal device;

[0138] The configuration unit 620 configures the at least one AI function according to the first configuration information.

[0139] In some embodiments, the receiving unit 610 further receives first indication information sent by the network device, where the first indication information is used to indicate model configuration information under at least one of the above-mentioned AI functions that the network device tends to.

[0140] In the above embodiment, the model configuration information preferred by the network device may include at least one of the following:

[0141] Model information of network device tendencies;

[0142] Network configuration information of the model favored by the network device;

[0143] Inference accuracy configuration information of network device tendencies;

[0144] Inferred latency configuration information of network devices;

[0145] Inference output information about network device tendencies;

[0146] Reasoning credibility configuration information of network device tendencies;

[0147] Network device vendor information corresponding to the network device preference model;

[0148] The terminal device manufacturer information corresponding to the network device preference model;

[0149] Chip device manufacturer information corresponding to the model favored by the network model.

[0150] In some embodiments, the configuration unit 620 configures the at least one AI function according to the first configuration information, including:

[0151] The configuration unit 620 determines information about available models under the at least one AI function based on the first configuration information and the first indication information.

[0152] In the above embodiment, as shown in FIG6 , the apparatus 600 may further include:

[0153] The first sending unit 630 sends a first response message to the network device, where the first response message is used to indicate whether the terminal device has successfully configured the at least one AI function according to the first configuration information and the first indication information.

[0154] In the above embodiment, the first response message may include information about a successfully configured AI function among the at least one AI function, and / or information about an unsuccessfully configured AI function among the at least one AI function.

[0155] In the above embodiment, if the terminal device fails to successfully configure at least one of the at least one AI function, the first response message may further include a failure reason of the at least one AI function that was not successfully configured.

[0156] In the above embodiment, the failure reason may include at least one of the following:

[0157] No models available;

[0158] An available model cannot be determined according to the first indication information;

[0159] The configuration sent by the network device is not supported;

[0160] Insufficient AI resources;

[0161] Information on insufficient AI resources.

[0162] In some embodiments, the receiving unit 610 further receives second indication information sent by the network device, where the second indication information is used to instruct the terminal device to send activated model information under the above-mentioned at least one AI function to the network device.

[0163] In the above embodiment, as shown in FIG6 , the apparatus 600 may further include:

[0164] The second sending unit 640 sends information about the model activated under the at least one AI function to the network device according to the second indication information.

[0165] In the above embodiment, the second sending unit 640 may also send the AI ​​function associated with the information of the activated model to the network device.

[0166] In the above embodiment, as shown in FIG6 , the apparatus 600 may further include:

[0167] The third sending unit 650 may also report the latest activated model information to the network device if the terminal device changes the activated model under the at least one AI function.

[0168] In the above embodiment, the third sending unit 650 may also send the AI ​​function associated with the information of the activated model to the network device.

[0169] In an embodiment of the present application, the first configuration information may include but is not limited to: at least one of activation, deactivation, modification, rollback to non-AI configuration, release, and suspension of the AI ​​function.

[0170] FIG7 is another schematic diagram of a configuration device for AI functions according to an embodiment of the present application. The device may be, for example, a network device, or a component or components configured on the network device. Since the principle of solving the problem of the device is the same as that of the embodiment of the second aspect, its specific implementation can refer to the implementation of the method of the embodiment of the second aspect, and the same contents will not be repeated. As shown in FIG7 , the device 700 includes:

[0171] A first sending unit 710 is configured to send first configuration information to a terminal device, where the first configuration information is used to configure at least one AI function of the terminal device;

[0172] The second sending unit 720 sends the first indication information and / or the second indication information to the terminal device, wherein the first indication information is used to indicate the model configuration information under the above-mentioned at least one AI function that the network device tends to use, and the second indication information is used to instruct the terminal device to send the activated model information under the above-mentioned at least one AI function to the network device.

[0173] In the above embodiment, as shown in FIG7 , the apparatus 700 may further include:

[0174] The first receiving unit 730 receives a first response message sent by the terminal device, where the first response message is used to indicate whether the terminal device successfully configures the at least one AI function according to the first configuration information and the first indication information.

[0175] In the above embodiment, as shown in FIG7 , the apparatus 700 may further include:

[0176] The second receiving unit 740 receives information about the model activated under the at least one AI function sent by the terminal device according to the second indication information.

[0177] In the above embodiment, the second receiving unit 740 may also receive information of the latest activated model reported by the terminal device when the activated model under the above at least one AI function is changed.

[0178] In the above embodiment, the second receiving unit 740 may also receive the AI ​​function associated with the information of the above activated model sent by the terminal device.

[0179] The above embodiments of the present application are illustrative, but the present application is not limited thereto, and appropriate modifications can be made based on the above embodiments. For example, the above embodiments can be used alone, or one or more of the above embodiments can be combined.

[0180] It is worth noting that the above description only describes the components or modules related to this application, but this application is not limited thereto. The above-mentioned device may also include other components or modules. For the specific content of these components or modules, please refer to the relevant art. In addition, the above-mentioned components or modules can be implemented by hardware facilities such as processors, memories, transmitters, and receivers; the implementation of this application is not limited to this.

[0181] According to the apparatus of the embodiment of the present application, the network device can control the model activated on the terminal device side in the function-based LCM to a certain extent, or the network device can perceive the model information activated on the terminal device side in the function-based LCM, thereby better realizing function / model control.

[0182] Embodiments of the fourth aspect

[0183] An embodiment of the present application also provides a communication system, including a network device and a terminal device.

[0184] FIG8 is a schematic diagram of a communication system according to an embodiment of the present application, schematically illustrating a situation using a terminal device and a network device as an example. As shown in FIG8 , a communication system 800 may include a network device 801 and terminal devices 802 and 803. For simplicity, FIG8 illustrates only two terminal devices and one network device as an example, but the embodiments of the present application are not limited thereto.

[0185] In the embodiment of the present application, existing services or future services can be transmitted between the network device 801 and the terminal devices 802 and 803. For example, these services may include but are not limited to: enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable and low-latency communication (URLLC), etc.

[0186] It is worth noting that FIG8 shows that both terminal devices 802 and 803 are within the coverage range of network device 801, but the present application is not limited thereto. Both terminal devices 802 and 803 may not be within the coverage range of network device 801, or one terminal device 802 may be within the coverage range of network device 801 while the other terminal device 803 is outside the coverage range of network device 801.

[0187] In some embodiments, the terminal device includes the apparatus 600 described in the embodiment of the third aspect, and is configured to perform the method described in the embodiment of the first aspect. Since the method has been described in detail in the embodiment of the first aspect, its content is incorporated herein and will not be repeated.

[0188] In some embodiments, the network device includes the apparatus 700 described in the embodiment of the third aspect, configured to perform the method described in the embodiment of the second aspect. Since the method has been described in detail in the embodiment of the second aspect, its content is incorporated herein and will not be repeated.

[0189] An embodiment of the present application further provides a terminal device, which may be, for example, a UE, but the present application is not limited thereto and may also be other terminal devices.

[0190] Figure 9 is a schematic diagram of a terminal device according to an embodiment of the present application. As shown in Figure 9 , terminal device 900 may include a processor 901 and a memory 902. Memory 902 stores data and programs and is coupled to processor 901. It should be noted that this diagram is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunication or other functions.

[0191] In some embodiments, the functions of the device 600 of the embodiment of the third aspect can be integrated into the processor 901, wherein the processor 901 can be configured to execute a program to implement the method described in the embodiment of the first aspect, the content of which is incorporated herein and will not be repeated here.

[0192] In other embodiments, the apparatus 600 of the embodiment of the third aspect may be configured separately from the processor 901. For example, the apparatus 600 of the embodiment of the third aspect may be configured as a chip connected to the processor 901, and the functions of the apparatus 600 of the embodiment of the third aspect may be implemented through the control of the processor 901.

[0193] As shown in Figure 9 , the terminal device 900 may further include: a communication module 903, an input unit 904, a display 905, and a power supply 906. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that the terminal device 900 does not necessarily include all of the components shown in Figure 9 , and these components are not essential. Furthermore, the terminal device 900 may also include components not shown in Figure 9 , for which reference may be made to related art.

[0194] An embodiment of the present application further provides a network device, which may be, for example, a base station, but the present application is not limited thereto and may also be other network devices.

[0195] Figure 10 is a schematic diagram of a network device according to an embodiment of the present application. As shown in Figure 10 , network device 1000 may include a processor 1001 and a memory 1002 ; the memory 1002 is coupled to the processor 1001 . The memory 1002 may store various data and information processing programs, which are executed under the control of the processor 1001 .

[0196] In some embodiments, the functions of the device 700 of the embodiment of the third aspect can be integrated into the processor 1001, wherein the processor 1001 can be configured to execute a program to implement the method of the embodiment of the second aspect, the content of which is incorporated herein and will not be repeated here.

[0197] In other embodiments, the apparatus 700 of the embodiment of the third aspect may be configured separately from the processor 1001. For example, the apparatus 700 of the embodiment of the third aspect may be configured as a chip connected to the processor 1001, and the functions of the apparatus 700 of the embodiment of the third aspect may be implemented through the control of the processor 1001.

[0198] Furthermore, as shown in FIG10 , network device 1000 may further include transceivers 1003 and 1004. The functions of these components are similar to those in the prior art and are not described in detail here. It is worth noting that network device 1000 does not necessarily include all of the components shown in FIG10 ; furthermore, network device 1000 may also include components not shown in FIG10 , for which reference may be made to the prior art.

[0199] An embodiment of the present application further provides a computer program, wherein when the program is executed in a terminal device, the program causes the terminal device to execute the method described in the embodiment of the first aspect.

[0200] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a terminal device to execute the method described in the embodiment of the first aspect.

[0201] An embodiment of the present application further provides a computer program, wherein when the program is executed in a network device, the program causes the network device to execute the method described in the embodiment of the second aspect.

[0202] An embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables a network device to execute the method described in the embodiment of the second aspect.

[0203] The above devices and methods of the present application can be implemented by hardware or by a combination of hardware and software. The present application relates to such a computer-readable program that, when executed by a logic component, enables the logic component to implement the devices or components described above, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0204] The method / device described in conjunction with the embodiments of the present application can be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of functional block diagrams can correspond to various software modules of the computer program flow or to various hardware modules. These software modules can respectively correspond to the various steps shown in the figure. These hardware modules can be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0205] The software module may be located in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in the memory of the mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if the device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0206] One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may be implemented as a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or any appropriate combination thereof for performing the functions described in this application. One or more of the functional blocks and / or one or more combinations of functional blocks described in the accompanying drawings may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0207] The present application has been described above in conjunction with specific embodiments. However, those skilled in the art should understand that these descriptions are merely illustrative and are not intended to limit the scope of protection of the present application. Those skilled in the art may make various modifications and variations to the present application based on the spirit and principles of the present application, and such modifications and variations are also within the scope of the present application.

Claims

1. A configuration device for AI function, configured in a terminal device, wherein: The device comprises: A receiving unit, configured to receive first configuration information sent by a network device, where the first configuration information is used to configure at least one AI function of the terminal device; A configuration unit configured to configure the at least one AI function according to the first configuration information.

2. The device according to claim 1, wherein: The receiving unit also receives first indication information sent by the network device, where the first indication information is used to indicate model configuration information under the at least one AI function that the network device prefers.

3. The device according to claim 2, wherein: The model configuration information preferred by the network device includes at least one of the following: Model information preferred by the network device; Network configuration information of the model preferred by the network device; Configuration information of the inference accuracy preferred by the network device; The inference delay configuration information preferred by the network device; The inference output result information of the network device tendency; Inference credibility configuration information of the network device tendency; The network device manufacturer information corresponding to the model preferred by the network device; The terminal device manufacturer information corresponding to the model preferred by the network device; The chip device manufacturer information corresponding to the model that the network model tends to be.

4. The device according to claim 2, wherein: The configuration unit configures the at least one AI function according to the first configuration information, including: The configuration unit determines information of available models under the at least one AI function according to the first configuration information and the first indication information.

5. The device according to claim 4, wherein: The device also includes: A first sending unit is configured to send a first response message to the network device, where the first response message is used to indicate whether the terminal device successfully configures the at least one AI function according to the first configuration information and the first indication information.

6. The device according to claim 5, wherein: The first response message includes information about an AI function that is successfully configured among the at least one AI function, and / or information about an AI function that is not successfully configured among the at least one AI function.

7. The device according to claim 6, wherein: If the configuration unit fails to successfully configure at least one of the at least one AI function, the first response message further includes a failure reason of the at least one AI function that was not successfully configured.

8. The device according to claim 7, wherein: The failure reason includes at least one of the following: No models available; An available model cannot be determined according to the first indication information; The configuration sent by the network device is not supported; Insufficient AI resources; Information about insufficient AI resources.

9. The device according to claim 1, wherein: The receiving unit also receives second indication information sent by the network device, where the second indication information is used to instruct the terminal device to send activated model information under the at least one AI function to the network device.

10. The device according to claim 9, wherein: The device also includes: A second sending unit sends information about the model activated under the at least one AI function to the network device according to the second indication information.

11. The device according to claim 9, wherein: The device also includes: The third sending unit reports the latest activated model information to the network device if the terminal device changes the activated model under the at least one AI function.

12. The device according to claim 10, wherein: The second sending unit also sends the AI ​​function associated with the information of the activated model to the network device.

13. The device according to claim 1, wherein: The first configuration information includes at least one of activation, deactivation, modification, rollback to non-AI configuration, release, and suspension of the AI ​​function.

14. A configuration device for AI function, configured in a network device, wherein: The device comprises: A first sending unit, which sends first configuration information to a terminal device, where the first configuration information is used to configure at least one AI function of the terminal device; a second sending unit, which sends first indication information and / or second indication information to the terminal device, wherein the first indication information is used to indicate the model configuration information under the at least one AI function that the network device tends to use, and the The second indication information is used to instruct the terminal device to send the activated model information under the at least one AI function to the network device.

15. The device according to claim 14, wherein: The device also includes: A first receiving unit receives a first response message sent by the terminal device, where the first response message is used to indicate whether the terminal device successfully configures the at least one AI function according to the first configuration information and the first indication information.

16. The device according to claim 14, wherein: The device also includes: A second receiving unit receives information about the model activated under the at least one AI function sent by the terminal device according to the second indication information.

17. The device according to claim 16, wherein: The second receiving unit also receives information of the latest activated model reported by the terminal device when changing the activated model under the at least one AI function.

18. The device according to claim 16, wherein: The device also includes: The second receiving unit also receives the AI ​​function associated with the information of the activated model sent by the terminal device.

19. A terminal device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: The processor is configured to execute the computer program to implement the following method: Receiving first configuration information sent by a network device, where the first configuration information is used to configure at least one AI function of the terminal device; Configure the at least one AI function according to the first configuration information.

20. The terminal device according to claim 19, characterized in that: The processor is further configured to execute the computer program to implement the following method: receiving first indication information sent by the network device, where the first indication information is used to indicate model configuration information of at least one AI function preferred by the network device; and / or, Receive second indication information sent by the network device, where the second indication information is used to instruct the terminal device to send activated model information under the at least one AI function to the network device.

Images