Management method of artificial intelligence and communication device

Abstract

The invention provides an artificial intelligence management method and a communication device, and relates to the technical field of communication. The method provides a scheme capable of effectively reducing the identification overhead between the terminal equipment and the network equipment. Specifically, the method comprises: a terminal device sends a first identifier and a second identifier to a first network device, the first identifier being an identifier configured by a second network device for a first model successfully identified between the second network device and the terminal device, the second identifier being used for identifying a first area, and the first identifier being unique in the first area; and the first network device obtains model information of the first model according to the first identifier and the second identifier, determines whether the first model is available, and sends response information for indicating whether the first model is available to the terminal device. Therefore, the terminal equipment and the first network equipment do not carry out a complete identification process on the successfully identified model again, so that the identification overhead between the terminal equipment and the network equipment can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to an artificial intelligence management method and communication device. Background Art

[0002] Artificial intelligence (AI) has been widely used in the field of communication technology to improve the communication performance between terminal devices and network devices. In the specific application of AI, the terminal device and the network device will perform model recognition on a certain AI model so that the two can reach a common understanding of the AI ​​model. Exemplarily, the terminal device reports to the network device the AI ​​model it supports, the application scenario of the AI ​​model, and the corresponding parameter configuration information (this information can also be collectively referred to as model information), and the network device configures a model identifier for the AI ​​model, which is used to identify the AI ​​model.

[0003] However, the current identification process between terminal devices and network devices will result in a large identification overhead, so how to effectively reduce the identification overhead between terminal devices and network devices is a technical problem that needs to be solved urgently. Summary of the invention

[0004] The present application provides an artificial intelligence management method and communication device, which can effectively reduce the model recognition overhead between terminal devices and network devices.

[0005] In a first aspect, a method for managing artificial intelligence is provided, comprising: sending a first identifier and a second identifier to a first network device, the first identifier being an identifier configured for a first model and coming from the second network device, the first model being a model successfully identified between the second network device and a terminal device, the second identifier being used to identify a first area, the first identifier being unique within the first area, and the first identifier including at least one of a model identifier and a function identifier; receiving a response message from the first network device, the response message being used to indicate whether the first model is available.

[0006] The execution subject of the solution described in the first aspect may be a terminal device, or a module or chip used to execute the functions of the terminal device, etc., without limitation. For ease of description, the embodiments of the present application are described by taking a terminal device as an example.

[0007] Specifically, when the terminal device and the first network device identify the first model that has been successfully identified again, the terminal device and the first network device may not exchange complete information for identifying the first model (for example, the type of AI model supported by the terminal device, the application scenarios of the AI ​​model, and corresponding parameter configuration information), but only exchange the first identifier and the second identifier. The first network device can obtain the complete information of the first model based on the first identifier and the second identifier. In this way, the identification overhead between the terminal device and the first network device can be effectively reduced.

[0008] Through the above solution, the identification process between the terminal device and the network device can be simplified, and the identification overhead between the terminal device and the network device can be effectively reduced.

[0009] In a possible implementation manner, the response information is used to indicate that the first model is available, and the method further includes: receiving a third identifier from the first network device, where the third identifier is an identifier configured by the first network device for the first model.

[0010] In this way, the first network device can configure a new identifier for the model, thereby facilitating the terminal device and the first network device to identify and understand the first model.

[0011] In a possible implementation manner, the response information is used to indicate that the first model is available, including: the response information includes a third identifier.

[0012] In this way, by sending a new identifier, the terminal device can determine that the first model is available based on the new identifier.

[0013] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: receiving a second model from the first network device and at least one item of information of the second model, wherein the information of the second model is used to activate the second model.

[0014] In this way, the terminal device and the first network device can complete the recognition of the new model.

[0015] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: receiving information from the first network device instructing the terminal device to fall back to a non-artificial intelligence AI mode.

[0016] In this way, the indication that the first model is not available may be completed.

[0017] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: receiving information from the first network device instructing the terminal device to perform a complete identification process.

[0018] In this way, the indication that the first model is not available may be completed.

[0019] In a possible implementation manner, the response information is used to indicate that the first model is unavailable, including: the response information includes the second model and at least one item of information of the second model.

[0020] In this way, the indication that the first model is not available may be completed.

[0021] A possible implementation manner, where the response information is used to indicate that the first model is unavailable, includes: the response information includes information indicating that the terminal device falls back to a non-AI mode.

[0022] In this way, the indication that the first model is not available may be completed.

[0023] In a possible implementation, the response information is used to indicate that the first model is unavailable, including: the response information instructs the terminal device to perform a complete identification process.

[0024] In this way, the indication that the first model is not available may be completed.

[0025] In a possible implementation, the response information includes the first identifier, so as to indicate whether the first model is available.

[0026] In a possible implementation manner, the method further includes: receiving a first identifier from a second network device.

[0027] In this way, the terminal device can report the first identifier to the first network device.

[0028] In a possible implementation manner, the method further includes: receiving a second identifier from a second network device.

[0029] In this way, the terminal device can report the second identifier to the first network device.

[0030] In a second aspect, a method for managing artificial intelligence is provided, including: receiving a first identifier and a second identifier from a terminal device, the first identifier being an identifier configured by a first network device for a first model, the first model being a model successfully identified between the first network device and the terminal device, the second identifier being used to identify a first area, the first identifier being unique within the first area, and the first identifier including at least one of a model identifier and a function identifier; obtaining model information of the first model based on the first identifier and the second identifier, and determining whether the first model is available; and sending a response message to the terminal device, the response message being used to indicate whether the first model is available.

[0031] The execution subject of the solution described in the second aspect may be a second network device, or a module or chip for executing the function of the second network device, etc., which is not limited. For ease of description, the embodiment of the present application is described by taking the second network device as an example.

[0032] Specifically, the second network device may obtain the model information of model 1 according to identification 1 and identification 2, and complete the recognition processing of model 1 based on the model information of model 1. Among them, the second network device may not obtain the model information of model 1 from the terminal device, which can effectively reduce the recognition overhead between the terminal device and the second network device.

[0033] Through the above solution, the identification process between the terminal device and the network device can be simplified, and the identification overhead between the terminal device and the network device can be effectively reduced.

[0034] In a possible implementation manner, the response information is used to indicate that the first model is available, and the method further includes: sending a third identifier to the terminal device, where the third identifier is used to identify the first model.

[0035] In this way, the second network device can configure a new identifier for the first model, thereby facilitating the terminal device and the second network device to identify and understand the first model.

[0036] In a possible implementation manner, the response information is used to indicate that the first model is available, including: the response information includes a third identifier.

[0037] In this way, by sending a new identifier, the terminal device can determine that the first model is available based on the new identifier.

[0038] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: sending a second model and at least one item of information of the second model to the terminal device, the second model is different from the first model, and the information of the second model is used to activate the second model.

[0039] In this way, the terminal device and the network device can recognize the new model.

[0040] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: information indicating to the terminal device that the terminal device falls back to a non-artificial intelligence AI mode.

[0041] In this way, the indication that the first model is not available may be completed.

[0042] In a possible implementation, the response information is used to indicate that the first model is unavailable, and the method further includes: instructing the terminal device to perform a complete identification process.

[0043] In this way, the indication that the first model is not available may be completed.

[0044] In a possible implementation manner, the response information is used to indicate that the first model is unavailable, including: the response information includes the second model and at least one item of information of the second model.

[0045] In this way, the indication that the first model is not available may be completed.

[0046] A possible implementation manner, where the response information is used to indicate that the first model is unavailable, includes: the response information includes information indicating that the terminal device falls back to a non-AI mode.

[0047] In this way, the indication that the first model is not available may be completed.

[0048] In a possible implementation, the response information is used to indicate that the first model is unavailable, including: the response information instructs the terminal device to perform a complete identification process.

[0049] In this way, the indication that the first model is not available may be completed.

[0050] In a possible implementation manner, the response information includes a first identifier.

[0051] In combination with the scheme described in any one of the first aspect and the second aspect, the type of the second identifier includes at least one of the following: a cell identifier, a cell group identifier, a tracking area identifier, a service area identifier, or a time advance group identifier; wherein the type of the first area is associated with the type of the second identifier.

[0052] Exemplarily, the type of the second identifier is a cell identifier, and the first area includes one or more cells; the type of the second identifier is a cell group identifier, and the first area includes one or more cell groups; the type of the second identifier is a tracking area identifier, and the first area includes one or more tracking areas; the type of the second identifier is a service area identifier, and the first area includes one or more service areas; the type of the second identifier is a time advance group identifier, and the first area includes one or more time advance groups; when the type of the second identifier is a tracking area identifier and a service area identifier, the first area includes one or more tracking areas and one or more service areas, etc.

[0053] This allows compatibility with existing standards.

[0054] In combination with the solution described in any one of the first aspect and the second aspect, the area of ​​the first network device belongs to the first area.

[0055] In this way, identification conflict problems can be avoided.

[0056] In combination with the scheme described in any one of the first aspect and the second aspect, the first identifier is carried in at least one of the following messages: a random access message, a radio resource control RRC configuration request message, an RRC configuration completion message, an RRC reconfiguration completion message, an RRC reconstruction request message, or a physical layer message.

[0057] In this way, the above identification process can be completed through specific communication messages.

[0058] In combination with the scheme described in any one of the first aspect and the second aspect, the second identifier is carried in at least one of the following messages: a random access message, a radio resource control RRC configuration request message, an RRC configuration completion message, an RRC reconfiguration completion message, an RRC reconstruction request message, or a physical layer message.

[0059] In this way, the above identification process can be completed through specific communication messages.

[0060] In combination with the solution described in any one of the first aspect and the second aspect, the first network device manages a first cell, which is the current resident cell of the terminal device, and the second network device manages a second cell, which is the source cell of the terminal device.

[0061] In this way, when the terminal device switches to a new cell, the terminal device and the network device corresponding to the newly switched cell can be identified through the above solution, which can effectively reduce the identification overhead between the terminal device and the network device.

[0062] On the third aspect, a method for managing artificial intelligence is provided, including: receiving model information of a first model from a first network device, the first model being a model successfully identified between the first network device and a terminal device; identifying and processing the first model according to the model information of the first model, and determining whether the first model is available; and sending indication information to the terminal device, the indication information being used to indicate whether the first model is available.

[0063] In one possible implementation, the first network device manages a first cell, which is a source cell of the terminal device, and the second network device manages a second cell, which is a current resident cell of the terminal device.

[0064] The execution subject of the solution described in the third aspect may be the second network device, or a module or chip for executing the function of the second network device, etc., which is not limited. For ease of description, the embodiment of the present application is described by taking the second network device as an example.

[0065] Specifically, the second network device may obtain the model message of the first model from the first network device, and complete the recognition of the first model based on the model information of the first model. The second network device may not obtain the model information of the first model from the terminal device, which can effectively reduce the recognition overhead between the terminal device and the second network device.

[0066] Through the above solution, the identification process between the terminal device and the network device can be simplified, and the identification overhead between the terminal device and the network device can be effectively reduced.

[0067] In a possible implementation manner, the indication information is used to indicate that the first model is available, and the method further includes: sending a first identifier to the terminal device, where the first identifier is used to identify the first model.

[0068] In this way, the second network device can configure an identifier for the first model, thereby facilitating the terminal device and the second network device to identify and understand the first model.

[0069] In a possible implementation manner, the first identifier is unique in the first area. In other words, the area of ​​the second network device belongs to the first area.

[0070] In this way, identification conflict problems can be avoided.

[0071] In a possible implementation manner, the first identifier is carried in at least one of the following messages: a random access message, a radio resource control RRC configuration request message, an RRC configuration completion message, an RRC reconfiguration completion message, an RRC reconstruction request message, or a physical layer message.

[0072] In this way, the above identification process can be completed through specific communication messages.

[0073] In a possible implementation, the indication information is used to indicate that the first model is unavailable, and the method further includes: sending a second model and at least one item of the second model's information to the terminal device, the second model is different from the first model, and the second model's information is used to activate the second model.

[0074] In this way, the terminal device and the second network device can complete the recognition of the new model.

[0075] In a fourth aspect, an artificial intelligence management method is provided, comprising: sending indication information to a network device, the indication information being used to indicate that a first model has been updated, the first model being a model successfully identified between the network device and the terminal device.

[0076] The execution subject of the solution described in the fourth aspect may be a terminal device, or a module or chip used to execute the functions of the terminal device, etc., which is not limited to this. For ease of description, the embodiments of the present application are described by taking the terminal device as an example.

[0077] Specifically, the terminal device can use the indication information to let the network device know that a model that has been successfully identified has been updated, thereby effectively reducing the identification overhead between the terminal device and the network device. In addition, this can also avoid the terminal device and the network device from having to re-perform the complete identification process for the updated model.

[0078] In a possible implementation, the method further includes: receiving response information from a network device, the response information including an identifier of the network device configured for the updated first model, or the response information is used to indicate an identifier for continuing to use the first model.

[0079] In this way, the network device can feedback to the terminal device that it has sensed that the first model has been updated.

[0080] In a fifth aspect, a method for managing artificial intelligence is provided, comprising: receiving indication information from a terminal device, the indication information being used to indicate that a first model has been updated, and the first model is a model successfully identified between the terminal device and the network device; sending response information to the terminal device according to the indication information, the response information including an identifier configured by the network device for the updated first model, or the response information being used to indicate an identifier for continuing to use the first model.

[0081] The execution subject of the solution described in the fifth aspect may be a network device, or a module or chip for executing the function of the network device, etc., which is not limited. For ease of description, the embodiment of the present application is described by taking a network device as an example.

[0082] Through the above technical solution, the network device can sense that the model that has been successfully identified has been updated, and indicate to the terminal device that it has sensed that the first model has been updated.

[0083] In combination with the solution described in any one of the fourth aspect and the fifth aspect, a possible implementation method is that the indication information includes any one of the following: information on the performance of the updated first model, or an identifier of the first model.

[0084] In this way, the network device can sense that the first model has been updated.

[0085] In a sixth aspect, a method for managing artificial intelligence is provided, comprising: receiving indication information from a network device, the indication information being used to indicate the cancellation of an identification of at least one model; canceling the identification of the at least one model according to the indication information; wherein each model of the at least one model is a model that is successfully identified between the network device and the terminal device.

[0086] The execution subject of the solution described in the sixth aspect may be a terminal device, or a module or chip used to execute the functions of the terminal device, etc., which is not limited. For ease of description, the embodiments of the present application are described by taking the terminal device as an example.

[0087] Specifically, the terminal device cancels the identification of at least one model according to the instruction of the network device. In this way, the bit length of the identification of the model can be effectively reduced, which is conducive to reducing the identification overhead between the terminal device and the network device.

[0088] In a possible implementation manner, before receiving the indication information from the network device, the method further includes: sending request information to the network device, where the request information is used to request to cancel the identification of at least one model.

[0089] In this way, the terminal device can actively propose to cancel the identification of some models.

[0090] In a possible implementation manner, the method further includes: sending response information to the network device, where the response information is used to indicate whether the indication information is successfully received.

[0091] In this way, the network device can determine whether the terminal device has successfully received the indication information.

[0092] In the seventh aspect, a method for managing artificial intelligence is provided, comprising: sending indication information to a terminal device, the indication information being used to indicate the cancellation of an identification of at least one model, each of the at least one model being a model successfully identified between the terminal device and the network device.

[0093] In a possible implementation manner, the method further includes: receiving request information from the terminal device, where the request information is used to request to cancel the identification of the at least one model.

[0094] In a possible implementation manner, the method further includes: receiving response information from the terminal device, where the response information is used to indicate whether the indication information is successfully received.

[0095] In combination with the solution described in any one of the sixth aspect and the seventh aspect, a possible implementation method is that the indication information includes at least one of the following items: an identifier of each model in the at least one model, and model information of each model in the at least one model.

[0096] In combination with the solution described in any one of the sixth aspect and the seventh aspect, a possible implementation method is that the request information includes at least one of the following items: an identifier of each model in the at least one model, and model information of each model in the at least one model.

[0097] In an eighth aspect, a method for managing artificial intelligence is provided, including: receiving a first model configuration message and first wireless resource control configuration information from a network device, the first model configuration information being used to activate the first model, and the first wireless resource control configuration information being used to configure the first wireless resource control configuration; when there is a conflict between the first model configuration information and the first wireless resource control configuration information, determining whether to ignore the first model configuration information or the first wireless resource control configuration information based on the priority of the first model configuration information and the priority of the first wireless resource control configuration information.

[0098] The execution subject of the solution described in the eighth aspect may be a terminal device, or a module or chip used to execute the functions of the terminal device, etc., which is not limited to this. For ease of description, the embodiments of the present application are described by taking the terminal device as an example.

[0099] Through the above scheme, the terminal device can determine whether to ignore the first model configuration information or the first wireless resource control configuration information based on the priority of the first model configuration information and the priority of the first wireless resource control configuration information. In this way, the conflict problem between the first model configuration information and the first wireless resource control configuration information can be solved.

[0100] A possible implementation method is to determine whether to ignore the first model configuration information or the first wireless resource control configuration information based on the priority of the first model configuration information and the priority of the first wireless resource control configuration information, including: determining whether to ignore the first model configuration information or the first wireless resource control information based on the priority of the signaling used to carry the first model configuration information and the priority of the signaling used to carry the first wireless resource control configuration information.

[0101] In this way, the terminal device can handle the conflict between the first model configuration information and the first wireless resource control configuration information according to the priority between the signaling used to carry the first model configuration information and the signaling used to carry the first wireless resource control configuration information.

[0102] In a possible implementation, when the priority of the signaling used to carry the first model configuration information is higher than the priority of the signaling used to carry the first wireless resource control configuration information, the method includes: determining to ignore the first wireless resource control configuration information.

[0103] In a possible implementation, when the priority of the signaling used to carry the first radio resource control configuration information is higher than the priority of the signaling used to carry the first model configuration information, the method includes: determining to ignore the first model configuration information.

[0104] In a ninth aspect, a communication device is provided, which may be a terminal device, or a device in a terminal device (for example, a chip (also called a chip system) or a circuit), or a device that can be used in conjunction with a terminal device.

[0105] In one possible implementation, the communication device includes a module or unit corresponding to each of the methods / operations / steps / actions described in any one of the first aspects. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0106] In the tenth aspect, a communication device is provided, which may be a network device, or a device in a network device (for example, a chip (also known as a chip system), or a circuit), or a device that can be used in conjunction with a terminal device.

[0107] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in any one of the second aspects. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0108] In the eleventh aspect, a communication device is provided, which may be a network device, or a device in a network device (for example, a chip (also called a chip system) or a circuit), or a device that can be used in conjunction with a terminal device.

[0109] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in any one of the third aspects. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0110] In a twelfth aspect, a communication device is provided, which may be a terminal device, or a device in a terminal device (for example, a chip (also called a chip system) or a circuit), or a device that can be used in conjunction with a terminal device.

[0111] In one possible implementation, the communication device includes a module or unit corresponding to each of the methods / operations / steps / actions described in any one of the fourth aspects. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0112] In a thirteenth aspect, a communication device is provided, which may be a network device, or a device in a network device (for example, a chip (also known as a chip system), or a circuit), or a device that can be used in conjunction with a network device.

[0113] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the fifth aspect. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0114] In a fourteenth aspect, a communication device is provided, which may be a terminal device, or a device in a terminal device (for example, a chip (also called a chip system) or a circuit), or a device that can be used in conjunction with a terminal device.

[0115] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the sixth aspect. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0116] In a fifteenth aspect, a communication device is provided, which may be a network device, or a device in a network device (for example, a chip (also known as a chip system), or a circuit), or a device that can be used in conjunction with a network device.

[0117] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the seventh aspect. The module or unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0118] In the sixteenth aspect, a communication device is provided, which may be a terminal device, or a device in the terminal device (for example, a chip (also called a chip system) or a circuit), or a device that can be used in combination with the terminal device.

[0119] In one possible implementation, the communication device may include a module or unit corresponding to each of the methods / operations / steps / actions described in the eighth aspect. The module or unit may be a hardware circuit, software, or a combination of a hardware circuit and software.

[0120] In the seventeenth aspect, a communication device is provided, comprising a processor, wherein the processor is used to, by executing a computer program or instruction, or by a logic circuit, enable the communication device to execute the method described in the first aspect and any possibility of the first aspect; or enable the communication device to execute the method described in the second aspect and any possibility of the second aspect; or enable the communication device to execute the method described in the third aspect and any possibility of the third aspect; or enable the communication device to execute the method described in the fourth aspect and any possibility of the fourth aspect; or enable the communication device to execute the method described in the fifth aspect and any possibility of the fifth aspect; or enable the communication device to execute the method described in the sixth aspect and any possibility of the sixth aspect; or enable the communication device to execute the method described in the seventh aspect and any possibility of the seventh aspect; or enable the communication device to execute the method described in the eighth aspect and any possibility of the eighth aspect.

[0121] In a possible implementation, the communication device further includes a memory for storing the computer program or instruction.

[0122] In a possible implementation manner, the communication device further includes a communication interface, which is used to input and / or output signals.

[0123] In the eighteenth aspect, a communication device is provided, comprising a logic circuit and an input-output interface, the input-output interface being used to input and / or output signals, the logic circuit being used to execute the method described in the first aspect and any possibility of the first aspect; or, the logic circuit being used to execute the method described in the second aspect and any possibility of the second aspect; or, the logic circuit being used to execute the method described in the third aspect and any possibility of the third aspect; or, the logic circuit being used to execute the method described in the fourth aspect and any possibility of the fourth aspect; or, the logic circuit being used to execute the method described in the fifth aspect and any possibility of the fifth aspect; or, the logic circuit being used to execute the method described in the sixth aspect and any possibility of the sixth aspect; or, the logic circuit being used to execute the method described in the seventh aspect and any possibility of the seventh aspect; or, the logic circuit being used to execute the method described in the eighth aspect and any possibility of the eighth aspect.

[0124] In the nineteenth aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored, and when the computer program or the instruction is run on a computer, the method described in the first aspect and any possibility of the first aspect is executed; or, the method described in the second aspect and any possibility of the second aspect is executed; or, the method described in the third aspect and any possibility of the third aspect is executed; or, the method described in the fourth aspect and any possibility of the fourth aspect is executed; or, the method described in the fifth aspect and any possibility of the fifth aspect is executed; or, the method described in the sixth aspect and any possibility of the sixth aspect is executed; or, the method described in the seventh aspect and any possibility of the seventh aspect is executed; or, the method described in the eighth aspect and any possibility of the eighth aspect is executed.

[0125] In the twentieth aspect, a computer program product is provided, comprising instructions, which, when executed on a computer, cause the method described in the first aspect and any possibility of the first aspect to be executed; or, cause the method described in the second aspect and any possibility of the second aspect to be executed; or, cause the method described in the third aspect and any possibility of the third aspect to be executed; or, cause the method described in the fourth aspect and any possibility of the fourth aspect to be executed; or, cause the method described in the fifth aspect and any possibility of the fifth aspect to be executed; or, cause the method described in the sixth aspect and any possibility of the sixth aspect to be executed; or, cause the method described in the seventh aspect and any possibility of the seventh aspect to be executed; or, cause the method described in the eighth aspect and any possibility of the eighth aspect to be executed.

[0126] The description of the beneficial effects of the ninth to twentieth aspects may correspond to the description of the beneficial effects of the first to eighth aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0127] Figure 1 Schematic diagram of an application framework 100 in a communication system according to an embodiment of the present application.

[0128] Figure 2 It is a schematic diagram of an application framework 200 in a communication system in an embodiment of the present application.

[0129] Figure 3 is a schematic diagram of a communication system 300 applicable to an embodiment of the present application.

[0130] Figure 4 4 is a schematic diagram of a communication system 400 applicable to an embodiment of the present application.

[0131] Figure 5It is a schematic diagram of the interactive process of the artificial intelligence management method 500 of the embodiment of the present application.

[0132] Figure 6 It is a schematic diagram of the interactive process of the artificial intelligence management method 600 according to an embodiment of the present application.

[0133] Figure 7 It is a schematic diagram of the interactive process of the artificial intelligence management method 700 of the embodiment of the present application.

[0134] Figure 8 It is a schematic diagram of the interactive process of the artificial intelligence management method 800 of the embodiment of the present application.

[0135] Fig. 9 It is a schematic diagram of the interactive process of the artificial intelligence management method 900 according to an embodiment of the present application.

[0136] Fig.10 It is a schematic block diagram of a communication device 1000 according to an embodiment of the present application.

[0137] Fig.11 It is a schematic block diagram of a communication device 1100 according to an embodiment of the present application. DETAILED DESCRIPTION

[0138] In order to facilitate understanding of the embodiments of the present application, the following points are first explained.

[0139] 1. In this application, unless otherwise specified, "plurality" means two or more.

[0140] 2. In each embodiment of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form a new embodiment according to their internal logical relationships.

[0141] 3. The various digital numbers involved in this application are only used for the convenience of description and are not used to limit the scope of protection of this application. The size of the serial numbers involved in this application does not mean the order of execution. The execution order of each process should be determined by its function and internal logic. For example, the terms "first", "second", "third", "fourth" and other various terminology labels (if any) in the specification and claims and drawings of this application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. Among them, the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than what is illustrated or described here.

[0142] At the same time, any embodiment or design described in the present application as "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0143] 4. The terms "comprise", "include", "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such process, method, product or apparatus.

[0144] 5. In this application, "used to indicate" can be understood as "enable", and "enable" can include direct enablement and indirect enablement. When describing that a certain information is used to enable A, it can include that the information directly enables A or indirectly enables A, and it does not mean that the information must carry A.

[0145] The information enabled by the information is called information to be enabled. In the specific implementation process, there are many ways to enable the information to be enabled, such as but not limited to, the information to be enabled can be directly enabled, such as the information to be enabled itself or the index of the information to be enabled. The information to be enabled can also be indirectly enabled by enabling other information, wherein there is an association relationship between the other information and the information to be enabled. It is also possible to enable only a part of the information to be enabled, while the other parts of the information to be enabled are known or agreed in advance. For example, the enabling of specific information can also be achieved by means of the arrangement order of each piece of information agreed in advance (such as specified by the protocol), thereby reducing the enabling overhead to a certain extent. At the same time, the common parts of each piece of information can also be identified and enabled uniformly to reduce the enabling overhead caused by enabling the same information separately.

[0146] 6. In this application, "pre-configuration" may include pre-definition, such as protocol definition. Among them, "pre-definition" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including each network element), and this application does not limit its specific implementation method.

[0147] 7. The term "storage" or "saving" as used in this application may refer to saving in one or more memories. The one or more memories may be provided separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories may also be partially provided separately and partially integrated in a decoder, a processor, or a communication device. The type of memory may be any form of storage medium, without limitation.

[0148] 8. The “protocol” referred to in this application may refer to a standard protocol in the field of communications, such as the fourth generation (4G) network, the fifth generation (5G) network protocol, the new radio (NR) protocol, the 5.5G network protocol, the sixth generation (6 th The present application does not limit the network protocols used in future communication systems.

[0149] 9. The dotted arrows or boxes in the schematic diagrams of the drawings in the specification of this application represent optional steps or optional modules.

[0150] 10. In this application, unless otherwise specified, “ / ” indicates that the objects associated with each other are in an “or” relationship. For example, A / B can represent A or B. “And / or” in this application is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0151] First, a communication system to which the embodiments of the present application are applicable is described.

[0152] The technical solution provided in the present application can be applied to various communication systems, such as: the fifth generation (5th generation, 5G) or new radio (new radio, NR) system, long term evolution (long term evolution, LTE) system, LTE frequency division duplex (frequency division duplex, FDD) system, LTE time division duplex (time division duplex, TDD) system, wireless local area network (wireless local area network, WLAN) system, satellite communication system, future communication system, such as the sixth generation (6th generation, 6G) mobile communication system, or a fusion system of multiple systems, etc. The technical solution provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of things (IoT) communication system or other communication systems.

[0153] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal may include information, signaling, or data, etc. The network element may also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The embodiment of the present application is described by taking a network element as an example. For example, a communication system may include at least one terminal device and at least one network device. The network device may send a downlink signal to the terminal device, and / or the terminal device may send an uplink signal to the network device. It is understandable that the terminal device in the embodiment of the present application may be replaced by a first network element, and the network device may be replaced by a second network element, and the two perform the corresponding communication method in the embodiment of the present application.

[0154] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0155] The terminal device may be a device that provides voice / data, such as a handheld device or a vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication functions, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (public land mobile The embodiments of the present application do not limit this.

[0156] As an example but not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.

[0157] In the embodiment of the present application, the device for realizing the function of the terminal device may be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which may be installed in the terminal device or used in combination with the terminal device. In the embodiment of the present application, the chip system may be composed of a chip, or may include a chip and other discrete devices. In the embodiment of the present application, only the device for realizing the function of the terminal device is used as an example for explanation, and the scheme of the embodiment of the present application is not limited.

[0158] The network device in the embodiment of the present application may be a device for communicating with a terminal device, and the network device may also be referred to as an access network device or a wireless access network device, such as a base station. The network device in the embodiment of the present application may refer to a wireless access network (RAN) node (or device) that connects a terminal device to a wireless network. Base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station, auxiliary station, multi-standard wireless (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip used to be set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a network side device in a 6G network, and a device that performs the base station function in future communication systems. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0159] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0160] In some deployments, the network device mentioned in the embodiments of the present application may be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit control plane (central unit-control plane, CU-CP)) and a user plane CU node (central unit user plane (central unit-user plane, CU-UP)) and a DU node. For example, the network device may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0161] In some deployments, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes implement part of the functions of the base station. For example, the RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be set separately, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, AAU, or RRH.

[0162] The RAN node may support one or more types of fronthaul interfaces, and different fronthaul interfaces correspond to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, relative to the CPRI, part of the downlink and / or uplink baseband functions, such as, for downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / cyclic prefix (CP) are moved from the DU to the RU for implementation, and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) are moved from the DU to the RU for implementation. In a possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0163] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the division, the DU is configured to implement layer mapping and one or more functions before it (i.e., one or more functions of coding, rate matching, scrambling, modulation, and layer mapping), while other functions after layer mapping (e.g., RE mapping, BF, or one or more functions of IFFT / CP) are moved to the RU for implementation. For uplink transmission, with de-RE mapping as the division, the DU is configured to implement de-mapping and one or more functions before it (i.e., decoding, de-rate matching, de-scrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and one or more functions of de-RE mapping), while other functions after de-mapping (e.g., one or more functions of digital BF or fast Fourier transform (FFT) / de-CP) are moved to the RU for implementation. It can be understood that for the functional description of DU and RU corresponding to various types of eCPRI, please refer to the eCPRI protocol, which will not be repeated here.

[0164] In one possible design, the processing unit for implementing the baseband function in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing the baseband function in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0165] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any unit in the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0166] In the embodiments of the present application, the device for realizing the function of the network device may be a network device; or it may be a device capable of supporting the network device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The device may be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the device for realizing the function of the network device is a network device as an example for explanation, and the scheme of the embodiments of the present application is not limited.

[0167] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The scenarios in which the network device and the terminal device are located are not limited in the embodiments of the present application. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the network device.

[0168] In wireless communication networks, such as mobile communication networks, the services supported by the network are becoming more and more diverse, so the demands that need to be met are becoming more and more diverse. For example, the network needs to be able to support ultra-high speed, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling more and more complicated. In addition, as the network becomes more and more powerful, such as supporting higher and higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new requirements, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. In order to meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0169] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0170] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment, etc., or the AI ​​node can also be deployed separately, for example, deployed in a location other than any of the above devices, such as a host or cloud server in an over the top (OTT) system. The AI ​​node can communicate with other devices in the communication system, and the other devices can be, for example, one or more of the following: network equipment, terminal equipment, or network elements of the core network, etc.

[0171] It is understandable that the embodiments of the present application do not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes are responsible for different functions.

[0172] It can also be understood that AI nodes can be independent devices, or integrated into the same device to implement different functions, or network elements in hardware devices, or software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of AI nodes. Among them, AI nodes can be AI network elements or AI modules.

[0173] Figure 1 FIG. 1 is a schematic diagram of an application framework 100 in a communication system according to an embodiment of the present application. Figure 1 As shown, network elements in the communication system are connected through interfaces (e.g., NG, Xn) or air interfaces. One or more AI modules are set in one or more devices in these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or operation and maintenance management (OAM) (for clarity, Figure 1 Only one is shown in the figure). The access network node can be a separate RAN node or can include multiple RAN nodes, for example, including CU and DU. CU and / or DU can also be provided with one or more AI modules. Optionally, CU can also be split into CU-CP and CU-UP. One or more AI models are provided in CU-CP and / or CU-UP.

[0174] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the biases in the activation function), input parameters (such as the type of input parameters and / or the dimension of input parameters), or output parameters (such as the type of output parameters and / or the dimension of output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0175] An AI module can have one or more models. A model can be inferred to obtain an output, which includes one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0176] Figure 2 FIG. 2 is a schematic diagram of an application framework 200 in a communication system according to an embodiment of the present application. Figure 2As shown, the communication system includes a RAN intelligent controller (RAN intelligent controller, RIC). For example, the RIC can be Figure 1 The AI ​​modules 117 and 118 shown in the figure are used to implement AI-related functions. RIC includes near-real time RIC (near-real time RIC, near-RT RIC) and non-real time RIC (non-real time RIC, Non-RT RIC). Among them, non-real time RIC mainly processes non-real time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. Real-time RIC mainly processes near real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0177] Near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. Near real-time RIC can obtain information on the network side and / or the terminal side from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data. Optionally, near real-time RIC can submit the reasoning results to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and DU, and / or between the DU and RU. For example, the near real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0178] Non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. Non-real-time RIC can obtain information on the network side and / or the terminal side from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or the terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0179] The near real-time RIC and the non-real-time RIC may also be separately set as a network element. Optionally, the near real-time RIC and the non-real-time RIC may also be part of other devices, for example, the near real-time RIC is set in the RAN node (for example, in the CU, DU), and the non-real-time RIC is set in the OAM, the cloud server, the core network device, or other network devices.

[0180] Figure 3 3 is a schematic diagram of a communication system 300 applicable to an embodiment of the present application. Figure 3As shown, the communication system 300 may include at least one network device, for example, the network device 110; the communication system 100 may also include at least one terminal device, for example, the terminal device 120 and the terminal device 130. The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) may communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, may communicate via a multi-antenna technology.

[0181] Figure 4 4 is a schematic diagram of a communication system 400 applicable to an embodiment of the present application. Compared with the communication system 300, the communication system 400 further includes an AI network element 140. The AI ​​network element 140 is used to perform AI-related operations, such as building a training data set or training an AI model.

[0182] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a part of the trained AI model may be deployed on the network device 110, and another part may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0183] It should be understood that Figure 4 Only the example of the AI ​​network element 140 being directly connected to the network device 110 is used for illustration. In other scenarios, the AI ​​network element 140 may also be connected to the terminal device. Alternatively, the AI ​​network element 140 may be connected to the network device 110 and the terminal device at the same time. Alternatively, the AI ​​network element 140 may also be connected to the network device 110 through a third-party network element. The embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0184] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, Figure 3 In the network device 110 or terminal device shown.

[0185] It should be noted that Figure 3 and Figure 4This is a simplified schematic diagram for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices. Figure 3 and Figure 4 In practical applications, the communication system may include multiple network devices (such as network device 110 and network device 150 ( Figure 3 The embodiment of the present application does not limit the number of network devices and terminal devices included in the communication system.

[0186] Next, some technical concepts involved in this application are briefly described.

[0187] AI model: An AI model is an algorithm or computer program that can implement AI functions. The AI ​​model represents the mapping relationship between the input and output of the model. The type of AI model can be a neural network, linear regression model, decision tree model, support vector machine (SVM), Bayesian network, Q learning model or other machine learning (ML) model.

[0188] Two-end model: The two-end model can also be called a bilateral model, a collaborative model, a dual model, or a two-side model. The two-end model refers to a model composed of multiple sub-models. The multiple sub-models that constitute the model need to match each other. The multiple sub-models can be deployed in different nodes.

[0189] The AI ​​model of the embodiment of the present application can be a dual-end model or a single-end model, which can be deployed on terminal devices and / or network devices.

[0190] Model application: Use the trained model to solve practical problems.

[0191] AI function: does not specifically refer to a specific AI model, but refers to a class of AI models with the same function. For example, the AI ​​function can be channel state information (CSI) feedback, CSI prediction, beam prediction, positioning, channel estimation, etc., that is, the AI ​​function can correspond to multiple AI models.

[0192] It is understood that the implementation of the AI ​​model or AI function can be a hardware circuit, or software, or a combination of software and hardware, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application, or software application, etc.

[0193] AI model identification: is a process / method that enables the terminal device and the network device to reach a consensus on the identified AI model. In general, the terminal device 120 needs to register the AI ​​model with the network device 110, that is, the terminal device 120 informs the network device 110 that the terminal device 120 has an AI model, as well as the functions, application scenarios, corresponding parameter configurations and other information of the AI ​​model. The network device 110 can then configure a model identifier for the AI ​​model. In this way, the terminal device 120 and the network device 110 have a consistent understanding of the AI ​​model referred to by the model identifier (which can be called successful identification). Alternatively, the network device 110 sends an AI model to the terminal device 120, as well as information indicating the identifier, function, application scenario, corresponding parameter configuration and other information of the AI ​​model. In the subsequent management process of the AI ​​model, the terminal device 120 and the network device 110 can use the model identifier to indicate the AI ​​model corresponding to the model identifier.

[0194] AI function identification: is a process / method that enables the terminal device and the network device to reach a consensus on the identified AI function. In general, the terminal device 120 needs to report to the network device 110 the AI ​​functions supported by the terminal device 120, as well as the application scenarios of the AI ​​functions, the corresponding configuration and other information. The network device 110 can also configure a function identifier for the AI ​​function, or identify the AI ​​function through the application scenarios and / or corresponding configuration information of the AI ​​function. In this way, the terminal device 120 and the network device 110 have a consistent understanding of the AI ​​function referred to by the function identifier (which can be called successful identification). In the subsequent management process of the AI ​​function, the terminal device 120 and the network device 110 can use the function identifier to indicate the AI ​​function corresponding to the function identifier.

[0195] It should be noted that in the embodiment of the present application, indication includes direct indication (also called explicit indication) and implicit indication. Wherein, direct indication of information A means including the information A; implicit indication of information A means indicating information A through the correspondence between information A and information B and direct indication of information B. Wherein, the correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0196] It should be noted that in the embodiment of the present application, information C is used to determine information D, which includes information D being determined based only on information C, and information D being determined based on information C and other information. In addition, information C is used to determine information D, and it can also be indirectly determined, for example, information D is determined based on information E, and information E is determined based on information C.

[0197] In addition, in each embodiment of the present application, "network element A (which may be device A) sends information A to network element B (which may be device B)" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in the present application can be understood similarly and will not be repeated here.

[0198] At present, the identification process between the terminal device and the network device (regardless of whether it is an AI model identification process or an AI function identification process, collectively referred to as the identification process) will result in a large identification overhead. For example, the terminal device and the network device corresponding to cell 1 perform an identification process on model 1 (regardless of whether it is an AI model or an AI function, collectively referred to as model 1), and model 1 is a successfully identified model. When the terminal device switches from cell 1 to cell 2, the terminal device still needs to perform a complete identification process on model 1 again with the network device corresponding to cell 2, which increases the identification overhead; for another example, after the terminal device updates the successfully identified model 1, the terminal device still needs to perform a complete identification process on the updated model 1 with the network device corresponding to cell 1, which increases the identification overhead; for another example, the terminal device and the network device corresponding to cell 1 perform an identification process on multiple models, and the above-mentioned multiple models are all successfully identified models. The network device needs to configure an identifier for each of the multiple models. When the terminal device no longer uses some of the multiple models in the future, if the terminal device and the network device corresponding to cell 1 continue to perform identification processes on other models, the bit length of the model identifier will become longer and longer, which will also increase the identification overhead.

[0199] In view of the above problems, the present application provides an artificial intelligence management method and communication device, which can effectively reduce the identification overhead between terminal devices and network devices.

[0200] It should be uniformly explained that the embodiments provided in the present application can be used to solve the above-mentioned technical problems, but for the convenience of description and understanding, each embodiment will be described separately in combination with different scenarios below.

[0201] Next, the management method of artificial intelligence in the embodiment of the present application is described.

[0202] When the terminal device 120 is in cell 1 (such as the second cell) (cell 1 is the source cell of the terminal device 120), the terminal device 120 and the network device 110 corresponding to cell 1 perform an identification process on model 1, and model 1 is a model that is successfully identified. When the terminal device switches to cell 2 (such as the first cell) (cell 2 is the current resident cell of the terminal device 120), the terminal device 120 can Figure 5 The method shown in FIG. 1 is to perform an identification process of the network device 150 corresponding to the cell 2 on the model 1, which can effectively reduce the identification overhead between the terminal device 120 and the network device 150. For details, see Figure 5 .

[0203] Figure 5 : is an interactive flow diagram of an artificial intelligence management method 500 of an embodiment of the present application. Method 500 can be executed by terminal device 120, network device 110 and network device 150, or by a module and / or device (e.g., a chip or integrated circuit, etc.) with corresponding functions installed in terminal device 120, network device 110 and network device 150, or it may be completed by an AI entity or AI module, such as RIC, which is not limited to this. The following description will take terminal device 120, network device 110 and network device 150 as an example.

[0204] The method 200 includes:

[0205] S510, the terminal device 120 sends identification 1 (such as the first identification) and identification 2 (such as the second identification) to the network device 150, identification 1 is an identification configured for model 1 (such as the first model) and comes from the network device 110, model 1 is a model successfully identified between the network device 110 and the terminal device 120, identification 2 is used to identify area 1 (such as the first area), and identification 1 is unique within area 1. It can be understood that in the embodiments of the present application, "area" can be replaced by "range" or "scope of use". Identification 1 or the first identification can also be replaced by a "local identification". Identification 2 or the second identification can be replaced by a "regional identification".

[0206] Accordingly, the network device 150 receives the identifier 1 and the identifier 2 .

[0207] Specifically, the terminal device 120 and the network device 110 can perform an identification process for model 1. The specific content of the identification process can be found in the above description of AI model identification or AI function identification, which will not be repeated here. After completing the identification process for model 1, the network device 110 configures an identifier 1 for model 1 to identify model 1.

[0208] In one example, when model 1 is a model trained by the terminal device 120, the identification process of model 1 between the terminal device 120 and the network device 110 is as follows: the terminal device 120 reports at least one of the following information to the network device 110: functional information / characteristic information of model 1, that is, what function model 1 is used to achieve, such as one or more of CSI feedback or CSI prediction or beam prediction or positioning, etc.; application scenario / condition of model 1, that is, under what circumstances model 1 can be used, for example, one or more of indoor, outdoor, urban, suburban and other scenarios, or radio resource control (RRC) configurations supported by model 1, such as one or more of antennas, bandwidth, beam sets, etc.; performance of model 1, such as generalized cosine similarity (GCS), square generalized cosine similarity (SGCS), minimum mean square error (MSE), normalized mean square error (NMSE), throughput, spectrum efficiency, transmission rate, block error rate (BER), etc. One or more of the following: assumed BLER, assumed BLER, hybrid automatic repeat request (HARQ) confirmation / non-confirmation (HARQ ACK / NACK), signal to interference plus noise ratio (SINR), reference signal received power (RSRP), etc. The above information (which may also include information not mentioned, etc.) can be collectively referred to as model information of model 1. In other words, when model 1 is a model trained by the terminal device 120, when the terminal device 120 and the network device 110 perform an identification process for model 1, the terminal device 120 reports the model information of model 1 to the network device 110, so that the network device 110 and the terminal device 120 have a consistent understanding of model 1. Furthermore, the network device 110 configures identifier 1 for model 1.

[0209] In another example, when Model 1 is a model trained by the network device 110, the recognition process of Model 1 between the terminal device 120 and the network device 110 is as follows: the network device 110 sends the model information of Model 1 to the terminal device 120, and sends Model 1 to the terminal device 120. In this way, the terminal device 120 and the network device 110 can have a consistent understanding of Model 1. Furthermore, the network device 110 configures an identifier 1 for Model 1.

[0210] The above-mentioned “Model 1 is a model successfully identified between the network device 110 and the terminal device 120” can be: the terminal device 120 and the network device 110 have a consistent understanding of Model 1, which can indicate that Model 1 is a model successfully identified between the network device 110 and the terminal device 120; it can also be: the network device 110 configures identification 1 for Model 1, which can also indicate that Model 1 is a model successfully identified between the network device 110 and the terminal device 120.

[0211] The above-mentioned “successfully identified model” may also mean that: for the terminal device 120 and the network device 110, model 1 is available, that is, the terminal device 120 may perform communication tasks based on model 1, such as performing CSI feedback tasks or CSI prediction tasks based on model 1. Alternatively, model 1 may be used within the service range corresponding to the network device 110 (such as cell 1).

[0212] In a possible implementation, model 1 is at least one of an AI model and an AI function, that is, model 1 can be an AI model, an AI function, or an AI function and an AI model. Correspondingly, in a possible implementation, identifier 1 includes at least one of a model identifier and a function identifier, that is, identifier 1 includes a model identifier, or identifier 1 includes a function identifier, or identifier 1 includes both a model identifier (used to refer to a certain AI model so that the terminal device and the network device can determine the same AI model through the model identifier) ​​and a function identifier (used to refer to a certain AI function so that the terminal device and the network device can determine the same AI function through the model identifier). When identifier 1 includes a model identifier, model 1 is an AI model, when identifier 1 includes a function identifier, model 1 is an AI function, and when identifier 1 includes a model identifier and a function identifier, model 1 is both an AI model and an AI function.

[0213] In S510, the identifier 2 may come from the network device 110, or may be determined by the terminal device 120 itself. When the identifier 2 comes from the network device 110, the network device 110 may send the identifier 2 to the terminal device 120, and the identifier 2 is used to identify the area 1 where the network device 110 is located, so as to facilitate the network device 150 to determine the location of the network device 110 configured with the identifier 1 for the model 1. For example, the network device 110 may send the identifier 2 to the terminal devices in the area 1 through broadcast information. When the identifier 2 is determined by the terminal device 120 itself, the terminal device 120 may determine the identifier 2 based on the following parameters. For example, the terminal device 120 may determine its own cell identifier by measuring synchronization signals, such as the primary synchronization signal and the secondary synchronization signal, and then determine the identifier 2.

[0214] In a possible implementation, the type of identifier 2 includes at least one of the following: a cell identifier, a cell group identifier, a tracking area identifier, a service area identifier, or a time advance group identifier.

[0215] When the type of identifier 2 is a cell identifier, identifier 2 may be a cell global identifier (CGI), a base station identifier (gNB ID), or a physical cell identifier (PCI). When the type of identifier 2 is a tracking area identifier, identifier 2 may be a tracking area identifier (TAI) or a tracking area code (TAC). When the type of identifier 2 is a service area identifier, identifier 2 may be a service area identifier (SAI). When the type of identifier 2 is a timing advance group identifier, identifier 2 may be a timing advance group identifier (TAGI). The above-mentioned cell group identifier is used to identify a cell group including at least two cells. In addition, the present application does not limit the combination method between the types of identifier 2. For example, the type of identifier 2 may include a tracking area identifier and a service area identifier, etc. At the same time, there is an association between the type of area 1 and the type of identifier 2, or in other words, the type of area 1 is the same as the type of identifier 2.

[0216] Exemplarily, the type of identifier 2 is a cell identifier, and area 1 includes one or more cells. The type of identifier 2 is a cell group identifier, and area 1 includes one or more cell groups. The type of identifier 2 is a tracking area identifier, and area 1 includes one or more tracking areas. When the type of identifier 2 is a service area identifier, area 1 includes one or more service areas. The type of identifier 2 is a time advance group identifier, and area 1 includes one or more time advance groups. The type of identifier 2 is a tracking area identifier and a service area identifier, and area 1 includes one or more tracking areas and one or more service areas, etc.

[0217] In a possible implementation, area 1 includes multiple network devices, including network device 110. Area 1 may also be a valid identification area of ​​identifier 1, that is, the terminal devices and network devices in area 1 have the same understanding of model 1 indicated by identifier 1.

[0218] In a possible implementation, the identifier 1 is unique in the area 1. In this way, the identifier conflict problem can be avoided.

[0219] S520 : The network device 150 obtains model information of the model 1 according to the identifier 1 and the identifier 2 , and determines whether the model 1 is available.

[0220] Specifically, the network device 150 determines the area 1 according to the identifier 2. If the area of ​​the network device 150 does not belong to the area 1, the network device 150 can interact with the network devices in the area 1 to obtain the model information of the model 1. For example, the network device 150 can interact with one or more network devices in the area 1 to determine the network device 110 configured with the identifier 1 for the model 1, and obtain the model information of the model 1 from the network device 110, or obtain the model information of the model 1 from the network device that has the information in the area 1. If the network device 150 belongs to the area 1, the network device 150 can determine whether it has the model information of the model 1. If not, the model information of the model 1 is obtained from other network devices in the area 1.

[0221] Alternatively, in another possible implementation, regardless of whether the area of ​​network device 150 belongs to area 1, network device 150 can obtain model information of model 1 from a third-party device based on identifier 1 and identifier 2. For example, network device 150 obtains model information of model 1 from a third-party device that stores model information of area 1.

[0222] Further, the network device 150 may determine whether model 1 is available, that is, the network device 150 determines whether model 1 is available in cell 2. In one example, if model 1 is a model trained by the terminal device 120, the network device 150 may determine whether the RRC configuration supported by model 1 can be configured, or it may determine whether the scenario corresponding to cell 2 belongs to the scenario used by model 1. In another example, if model 1 is a bilateral model (i.e., a model jointly determined by the network device 110 and the terminal device 120), the network device 150 may determine whether there is a network-side model that can be paired with the model 1.

[0223] S530 . The network device 150 sends a response message 1 to the terminal device 120 . The response message 1 is used to indicate whether the model 1 is available.

[0224] Accordingly, the terminal device 120 receives the response information 1 and determines whether the model 1 is available based on the response information 1. Furthermore, the terminal device 120 determines whether the network device 150 successfully identifies the model 1 based on the response information 1.

[0225] In summary, when the terminal device 120 and the network device 150 re-identify the model 1 that has been successfully identified, the terminal device 120 and the network device 150 may not exchange the complete information for identifying the model 1 (the model information of the model 1) again, but only exchange the identifier 1 and the identifier 2. The network device 150 can obtain the complete information of the model 1 based on the identifier 1 and the identifier 2. In this way, the identification overhead between the terminal device 120 and the network device 150 can be effectively reduced.

[0226] Through the above solution, the identification process between the terminal device and the network device can be simplified, and the identification overhead between the terminal device and the network device can be effectively reduced.

[0227] In a possible implementation, method 500 may further include:

[0228] S530a: The network device 150 sends an identifier 3 to the terminal device 120 .

[0229] Correspondingly, the terminal device 120 receives identification 3.

[0230] Specifically, when the network device 150 determines that the model 1 is available and that the model 1 can use a new identifier, the network device 150 can send the identifier 3 configured by the network device 150 for the model 1 to the terminal device 120. In subsequent operations, the terminal device 120 and the network device 150 can use the identifier 3 to refer to the model 1. In this way, the network device 150 can configure a new identifier for the model 1, thereby facilitating the terminal device 120 and the network device 150 to identify and understand the model 1.

[0231] In a possible implementation, the network device 150 may also be configured with an identifier 4 for identifying area 2, and the network device 150 is located in area 2 (area 2 may be the same as area 1). When the terminal device 120 subsequently identifies model 1 (i.e., when switching from cell 2 to cell 3, the terminal device 120 and the network device corresponding to cell 3 identify model 1 again), the terminal device 120 may report identifiers 1 and 2 to other network devices (such as the network device corresponding to cell 3), or may report identifiers 3 and 4, without limitation.

[0232] In a possible implementation, when the network device 150 determines that the model 1 is available and that the model 1 can use a new identifier, the response information 1 can be identifier allocation information, which is used to indicate that the model 1 is available and can also be used to configure the identifier 3. In other words, the response information 1 can include the identifier 3. When the response information 1 includes the identifier 3, the terminal device 120 can confirm that the network device 150 successfully identifies the model 1 and that the model 1 uses the identifier 3.

[0233] In a possible implementation, when the network device 150 determines that the model 1 is available and the identifier 1 of the model 1 does not need to be changed, the response information 1 is confirmation information, which is used to confirm that the model 1 is successfully identified (or the model 1 is available), and can also be used to indicate that the identifier 1 can continue to be used. In subsequent operations, the terminal device 120 and the network device 150 can continue to use the identifier 1 to refer to the model 1.

[0234] In a possible implementation, the response information 1 may include an acknowledgement (ACK) message or an identifier 1. When the response information 1 includes the identifier 1, the terminal device 120 confirms that the network device 150 has successfully identified the model 1.

[0235] In a possible implementation, the network device 150 may also directly activate the model 1 through the identifier 1 without sending the response information 1 to the terminal device 120 .

[0236] In a possible implementation, method 500 may further include:

[0237] S530b: The network device 150 sends at least one of the model 2 and the information of the model 2 to the terminal device 120.

[0238] Accordingly, the terminal device 120 receives the model 2 and at least one of the information of the model 2.

[0239] Specifically, when the network device 150 determines that the model 1 is not available, the network device 150 sends the model 2 and at least one of the information of the model 2 to the terminal device 120. When the model 2 has been configured in the terminal device 120, the information of the model 2 may be activation information of the model 2, which is used to activate the model 2. In this way, the terminal device 120 and the network device 150 can complete the recognition of the new model.

[0240] Specifically, when the network device 150 determines that model 1 is unavailable, the response information 1 sent by the network device 150 to the terminal device 120 may include model 2 and at least one of the information of model 2, and the model 2 and at least one of the information of model 2 can be used to indicate that the network device 150 failed to successfully identify model 1 or that model 1 is unavailable.

[0241] In one possible implementation, when the network device 150 determines that model 1 is not available, the network device 150 may instruct the terminal device 120 to perform the complete recognition process of model 1 through response information 1, or the network device 150 may instruct the terminal device 120 to fall back to the non-AI mode through response information 1.

[0242] As a possible implementation, the response information 1 may include information indicating that the terminal device 120 falls back to the non-AI mode, or the response information 1 may include information indicating that the terminal device 120 performs a complete recognition process; or the response information 1 includes at least one of the information of Model 2 and the information of Model 2. In this way, the terminal device 120 can determine that Model 1 is unavailable based on the above information.

[0243] It should be noted that the network device 150 determines that Model 1 is unavailable, which may be: the network device 150 does not have an RRC configuration matching Model 1, or the network device 150 determines that the scenario corresponding to Cell 2 is not suitable for the application scenario of Model 1, etc., or when Model 1 belongs to a dual-end model, the network device 150 does not have a network-side model that can match Model 1.

[0244] In the above content, there may be more than one set of Identifier 1 and Identifier 2 reported by the terminal device 120 to the network device 150, that is, there is more than one model for the terminal device 120 to perform recognition. For example, 1 Identifier 2 and N Identifiers 1 are used to identify N models, and M (<N) Identifiers 2 and N Identifiers 1 are used to identify N models. Correspondingly, the response information 1 can be used to indicate at least one of the following: which models can be used, which models cannot be used; which models need to replace Identifier 1 (i.e., the local identifier); the updated Identifier 1 (i.e., the local identifier), the models for which the network device 150 does not obtain model information, which models are recognized successfully, and which models are recognized failed, etc.

[0245] In Method 500, Identifier 1 and Identifier 2 are carried in at least one of the following messages: random access messages, such as Message 1 (Msg1), Message 3 (Msg3), Message A (MsgA); RRC connection establishment / reestablishment / reconfiguration related information, such as RRC Setup Request message, RRC Setup Complete message, RRC Reconfiguration Complete message, RRC Reestablishment Request message, RRC Reestablishment Complete message; other RRC messages; physical layer messages, such as uplink control information (UCI); MAC layer messages, such as MAC CE. Identifier 1 and Identifier 2 can be carried in the same message or different messages.

[0246] It should be noted that the present application supports that response information 1 is only used to indicate whether model 1 is available, and does not carry other information. The present application also supports that response information 1 can carry other information, and can indicate whether model 1 is available through the other information. For example, response information 1 includes identification 3, and identification 3 is used to indicate that model 1 is available; for another example, response information 1 includes model 2 and at least one of the information of model 2, and at least one of the information of model 2 and model 2 is used to indicate that model 1 is not available, etc.

[0247] In addition, method 500 mainly focuses on describing the solution process initiated by the terminal device. Figure 6 Describes the content of the identification initiated by the network device.

[0248] Figure 6 6 is an interactive flow diagram of an artificial intelligence management method 600 of an embodiment of the present application. Method 600 can be executed by terminal device 120, network device 110 and network device 150, or by a module and / or device (e.g., a chip or integrated circuit, etc.) with corresponding functions installed in terminal device 120, network device 110 and network device 150, or it may be completed by an AI entity or AI module, such as RIC, which is not limited to this. The following description will be taken as an example of terminal device 120, network device 110 and network device 150.

[0249] The method 600 includes:

[0250] S610 , the network device 110 sends the model information of the model 1 to the network device 150 .

[0251] Correspondingly, the network device 150 receives the model information of model 1.

[0252] Specifically, when the terminal device 120 switches to the network device 150, or, when the network device 110 plans to switch the terminal device 130 to the network device 150, or, when the network device 150 requests the model information of the model 1 from the network device 110, the network device 110 sends the model information of the model 1 to the network device 150.

[0253] S620: The network device 150 identifies the model 1 according to the model information of the model 1, and determines whether the model 1 is available.

[0254] For the description of S620, reference may be made to the description of S520, which will not be repeated here.

[0255] S630. The network device 150 sends indication information 1 to the terminal device 120. The indication information 1 is used to indicate whether the model 1 is available.

[0256] Correspondingly, the terminal device 120 receives the indication information 1, and determines whether the model 1 is available according to the indication information 1.

[0257] For the description of S630, reference may be made to the description of S530, which will not be repeated here.

[0258] Specifically, the network device 150 may obtain the model message of the model 1 from the network device 110, and complete the recognition of the model 1 based on the model information of the model 1. The network device 150 may not obtain the model information of the model 1 from the terminal device 130, which can effectively reduce the recognition overhead between the terminal device 120 and the network device 150.

[0259] Through the above solution, the identification process between the terminal device and the network device can be simplified, and the identification overhead between the terminal device and the network device can be effectively reduced.

[0260] In a possible implementation, method 600 may further include:

[0261] S630a: The network device 110 sends an identifier 5 to the terminal device 120.

[0262] Accordingly, the terminal device 120 receives the identifier 5 from the network device 110. The identifier 5 is used to identify the model 1. For the description of the identifier 5, please refer to the description of the identifier 1, which will not be repeated here. In this way, the network device 150 can configure an identifier for the model 1, so as to facilitate the terminal device 120 and the network device 150 to identify and understand the model 1.

[0263] In a possible implementation, method 600 may further include:

[0264] S630b: The network device 110 sends at least one of the model 2 and the information of the model 2 to the terminal device 120.

[0265] For the description of S630b, reference may be made to the description of S530b, which will not be repeated here. In this way, the terminal device 120 and the network device 150 can complete the recognition of the new model.

[0266] After the terminal device 120 updates the model 1 that has been successfully identified, the terminal device 120 and the network device 110 perform a complete identification process on the updated model 1 again, which increases the identification overhead. Figure 7 The method shown in the figure and the network device 110 identify the updated model 1, thereby effectively reducing the identification overhead between the terminal device 120 and the network device 110. For details, see Figure 7 .

[0267] Figure 7 Schematic diagram of the interaction flow of the artificial intelligence management method 700 of the embodiment of the present application. The method 700 can be executed by the terminal device 120 and the network device 110, or by a module and / or device (for example, a chip or an integrated circuit, etc.) with corresponding functions installed in the terminal device 120 and the network device 110, or it may be completed by an AI entity or an AI module, such as RIC, which is not limited to this. The following is an example of the terminal device 120 and the network device 110. The method 700 includes:

[0268] Optionally, S710, the terminal device 120 and the network device 110 perform an identification process for model 1.

[0269] For the description of S710, reference may be made to the description of S510 above, which will not be repeated here.

[0270] S720. The terminal device 120 sends indication information 2 to the network device 110. The indication information 2 is used to indicate that the model 1 has been updated.

[0271] Correspondingly, the network device 110 receives the indication information 2 and determines, according to the indication information 2, that the model 1 has been updated.

[0272] After the terminal device 120 updates the successfully identified model 1, that is, after the structure and / or parameters of the model 1 are changed, the terminal device 120 and the network device 110 re-identify the model 1. The purpose of re-identification is to let the network device 110 perceive that the model 1 has been updated. If the network device 110 does not perceive that the model 1 has been updated, it may be impossible to determine whether the deterioration of network performance is caused by the model 1.

[0273] In a possible implementation, the indication information 2 may include any of the following: an identifier of model 1, information about the performance of the updated model 1 (which is used to indicate the performance of the model 1 after the update), or information about changes in the model information of model 1 due to the model update. When the indication information 2 includes the identifier of model 1, the network device 110 determines that the model 1 has been updated based on the identifier of model 1. When the indication information 2 includes information about the performance of the updated model 1, the network device 110 determines that the model 1 has been updated based on the information about the performance of the updated model 1. The information about the performance of the updated model 1 may also indicate a change in the performance of the updated model 1 compared to the model 1 before the update. The network device updates the corresponding model information of the model 1 stored in itself according to the received model information of the model 1, and for other model information of the model 1 not sent by the terminal device, it is assumed that there is no change.

[0274] S730 . The network device 110 sends a response message 2 to the terminal device 120 . The response message 2 includes an identifier configured by the network device 110 for the updated model 1 , or the response message 2 is used to indicate an identifier for continuing to use the model 1 .

[0275] Specifically, the network device 110 may reconfigure a new identifier for the updated model 1, or the network device 110 may determine to continue using the identifier of the model 1. In this way, the network device 100 may feedback to the terminal device 120 that it has sensed that the first model has been updated.

[0276] Understandably, Figure 7 The method shown can be used with Figure 5 or Figure 6 The methods shown can be combined with or, independently of Figure 5 or Figure 6 The method shown.

[0277] In summary, the terminal device can use the above technical solution to let the network device perceive that a model that has been successfully identified has been updated, thereby effectively reducing the identification overhead between the terminal device and the network device. In addition, this can also avoid the terminal device and the network device from having to re-perform a complete identification process for the updated model.

[0278] It should be noted that method 700 is described by taking the interaction between terminal device 120 and network device 110 as an example, but network device 110 may also be network device 150, and the behaviors of the two are basically the same. For ease of description, the interaction process between terminal device 120 and network device 150 as shown in method 700 will not be described in detail below.

[0279] When the terminal device 120 and the network device 110 identify multiple models, the network device 110 can configure an identifier for each successfully identified model. When the terminal device 120 no longer uses part of the successfully identified models in the subsequent use process, the part of the model will affect the bit length of the identifier of the subsequent successfully identified model, thereby increasing the identification overhead between the terminal device and the network device. Figure 8 The method shown in the figure can effectively reduce the recognition overhead. For details, please refer to Figure 8 .

[0280] Figure 8800 is an interactive flow diagram of an artificial intelligence management method 800 of an embodiment of the present application. The method 800 can be executed by the terminal device 120 and the network device 110, or by a module and / or device (for example, a chip or an integrated circuit, etc.) with corresponding functions installed in the terminal device 120 and the network device 110, or it may be completed by an AI entity or an AI module, such as RIC, which is not limited to this. The following is an example of the terminal device 120 and the network device 110. The method 800 includes:

[0281] S810. The network device 110 sends indication information 3 to the terminal device 120. The indication information 3 is used to indicate the deregistration of the identification of at least one model.

[0282] Correspondingly, the terminal device 120 receives indication information 3.

[0283] S820. The terminal device 120 cancels the identification of the at least one model according to the indication information 3.

[0284] Specifically, the terminal device 120 cancels the identification of at least one model according to the instruction of the network device 110. In this way, the bit length of the identification of the model can be effectively reduced, which is conducive to reducing the identification overhead between the terminal device and the network device.

[0285] In a possible implementation, the indication information 3 includes the identification of each model in the at least one model, or the indication information 3 includes the model information of each model in the at least one model. In this way, the terminal device 120 can cancel the identification of the at least one model according to the content included in the indication information 3.

[0286] It can be understood that the indication information 3 can take effect at time n+k, where time n is the time when the terminal device 120 receives the indication information 3, and the time n can be the first or last OFDM symbol or time slot or subframe or frame at which the terminal device 120 receives the indication information 3, and k is a predefined or preconfigured time offset. After the indication information 3 takes effect, the identifier of the deregistered model is no longer used for its corresponding indication original model.

[0287] In a possible implementation, method 800 may further include:

[0288] S810a. The terminal device 120 sends a request message 1 to the network device 110. The request message 1 is used to request to cancel the at least one model.

[0289] Correspondingly, the network device 110 receives the request information 1 and can determine the indication information 3 according to the request information 1. In this way, the terminal device 120 can actively propose to cancel the identification of some models.

[0290] Specifically, the request information 1 may include the identifier of each model in at least one model, or the request information 1 may include the model information of each model in at least one model. There is an association between the model information and the model identifier of the model. In this way, it is convenient for the network device 110 to determine the identifiers of the models that need to be deregistered.

[0291] In a possible implementation, method 800 may further include:

[0292] S820a, the terminal device 120 sends a response message 2 to the network device 110, where the response message 2 is used to indicate whether the indication message 3 is successfully received.

[0293] Correspondingly, the network device 110 receives the response information 2, and determines whether the terminal device 120 has successfully received the indication information 3 based on the response information 2. In this way, the network device 110 can determine whether the terminal device 120 has successfully received the indication information 3. It should be noted that the method 800 is described by taking the interaction between the terminal device 120 and the network device 110 as an example, but the network device 110 can also be the network device 150, and the behaviors of the two are basically the same. For the convenience of description, the interaction process between the terminal device 120 and the network device 150 as shown in the method 800 will not be repeated below.

[0294] Understandably, Figure 8 The method shown can be used with Figure 5 or Figure 6 The method shown or Figure 7 At least one of the methods shown is combined, or, independently, Figures 5 to 7 At least one of the methods shown.

[0295] in addition, Figures 5 to 8 The content is about how to reduce the identification overhead between the terminal device and the network device. However, after the model identification is completed between the terminal device and the network device, there may be a conflict between the model and the RRC configuration. Specifically, each model will have a matching RRC configuration, for example, the antenna port supports 32 ports, the bandwidth supports 10MHz, the feedback bit supports 100bits, etc. Since model activation and RRC configuration are two independent configurations, it is possible that the activated model does not match the RRC configuration. The terminal device 120 can Fig. 9 The method shown here is for situations where the activated model does not match the RRC configuration. For details, see Fig. 9 Understandably, Fig. 9 The method shown can be used with Figures 5 to 8 At least one combination of the methods shown can also be independent of Figures 5 to 8 At least one of the methods shown.

[0296] Fig. 9 1 is a schematic diagram of the interaction flow of the artificial intelligence management method 900 of the embodiment of the present application. The method 900 can be executed by the terminal device 120 and the network device 110, or by a module and / or device (for example, a chip or an integrated circuit, etc.) with corresponding functions installed in the terminal device 120 and the network device 110, or it may be completed by an AI entity or an AI module, such as RIC, which is not limited to this. The following is an example of the terminal device 120 and the network device 110. The method 900 includes:

[0297] S910, the network device 110 sends model configuration information 1 and RRC configuration information 1 to the terminal device 120.

[0298] Accordingly, the terminal device 120 receives model configuration information 1 and RRC configuration information 1. Model configuration information 1 is used to activate model 3, and RRC configuration information 1 is used to configure RRC configuration 1.

[0299] S920. When there is a conflict between model configuration information 1 and RRC configuration information 1, the terminal device 120 determines whether to ignore model configuration information 1 or RRC configuration information 1 according to the priority between model configuration information 1 and RRC configuration information 1.

[0300] Specifically, the conflict between model configuration information 1 and RRC configuration information 1 may be that: the model 3 used to activate by model configuration information 1 does not match the RRC configuration 1 used to configure by RRC configuration information 1, that is, RRC configuration 1 cannot be applied to model 3, or model 3 cannot support RRC configuration 1. When the priority of model configuration information 1 is higher than the priority of RRC configuration information 1, the terminal device 120 determines to ignore RRC configuration information 1 and use RRC configuration 2 that matches model 3 (RRC configuration 2 has been configured on the terminal device 120 side). When the priority of RRC configuration information 1 is higher than the priority of model configuration information 1, the terminal device 120 determines to ignore model configuration information 1 and continue to use the previous model, or the previous non-AI mode, or fall back to the non-AI mode.

[0301] In one possible implementation, the priority of the signaling used to carry model configuration information 1 is higher than the priority of the signaling used to carry RRC configuration information 1. Specifically, the terminal device 120 can make a selection based on the priority of the signaling used to carry model configuration information 1 being higher than the priority of the signaling used to carry RRC configuration information 1. For example, when the priority of the signaling used to carry model configuration information 1 is higher than the priority of the signaling used to carry RRC configuration information 1, the terminal device 120 determines to ignore RRC configuration information 1. In this way, the terminal device can handle the conflict between the first model configuration information and the first wireless resource control configuration information based on the priority between the signaling used to carry the first model configuration information and the signaling used to carry the first wireless resource control configuration information.

[0302] In one possible implementation, the priority of the signaling used to carry RRC configuration information 1 is higher than the priority of the signaling used to carry model configuration information 1. Specifically, the terminal device 120 can make a selection based on the priority of the signaling used to carry model configuration information 1 being higher than the priority of the signaling used to carry RRC configuration information 1. For example, when the priority of the signaling used to carry RRC configuration information 1 is higher than the priority of the signaling used to carry model configuration information 1, the terminal device 120 determines to ignore model configuration information 1. In this way, the terminal device can handle the conflict between the first model configuration information and the first wireless resource control configuration information based on the priority between the signaling used to carry the first model configuration information and the signaling used to carry the first wireless resource control configuration information.

[0303] In a possible implementation, the present application supports that the priority of the signaling received later is higher than the priority of the signaling received earlier. When the reception time of RRC configuration information 1 is after the reception time of model configuration information 1, the terminal device 120 determines to ignore model configuration information 1; when the reception time of RRC configuration information 1 is before the reception time of model configuration information 1, the terminal device 120 determines to ignore RRC configuration information 1.

[0304] In a possible implementation, the present application also supports that the priority of the signaling received first is higher than the priority of the signaling received later. When the reception time of RRC configuration information 1 is before the reception time of model configuration information 1, the terminal device 120 determines to ignore model configuration information 1; when the reception time of RRC configuration information 1 is after the reception time of model configuration information 1, the terminal device 120 determines to ignore model configuration information 1.

[0305] The terminal device 120 may also report to the network device 110 that the model configuration information 1 conflicts with the RRC configuration information 1. In this way, the network device 110 may process it.

[0306] Through the above scheme, the terminal device can determine whether to ignore the model configuration information or the RRC configuration information based on the priority of the model configuration information 1 and the priority of the RRC configuration information 1. In this way, the terminal device can resolve the conflict between the model configuration information 1 and the RRC configuration information 1.

[0307] It should be noted that method 900 is described by taking the interaction between terminal device 120 and network device 110 as an example, but network device 110 may also be network device 150, and the behaviors of the two are basically the same. For ease of description, the interaction process between terminal device 120 and network device 150 as shown in method 900 will not be described in detail below.

[0308] It should also be noted that, in the above scheme, this application supports the mutual combination of the embodiments, for example, Figure 5 The method shown is similar to Fig. 9 A combination of the methods shown, Figure 5 The method shown is similar to Figure 7 The combinations of the methods shown are not limited.

[0309] Finally, the device embodiment of the embodiment of the present application is introduced.

[0310] In order to implement the functions in the method provided in this application, the terminal device and the network device may include a hardware structure and / or a software module, and implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Whether one of the above functions is executed in the form of a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application and design constraints of the technical solution.

[0311] Fig.10 1 is a schematic block diagram of a communication device 1000 according to an embodiment of the present application. The communication device 1000 includes a processor 1010 and a communication interface 1020, and the processor 1010 and the communication interface 1020 may be interconnected via a bus 1030. The communication device 1000 may be a network device 110 or a network device 150, or a terminal device 120.

[0312] Optionally, the communication device 1000 may further include a memory 1040. The memory 1040 includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a portable read-only memory (CD-ROM), and the memory 1040 is used for related instructions and data.

[0313] The processor 1010 may be one or more central processing units (CPUs). In the case where the processor 1010 is a CPU, the CPU may be a single-core CPU or a multi-core CPU. The processor 1010 may be a signal processor, a chip, or other integrated circuit that can implement the method of the present application, or a portion of the circuit for processing functions in the aforementioned processor, chip, or integrated circuit. In addition, the communication interface 1020 may also be an input / output interface, which is used for input or output of signals or data, or may be an input / output circuit.

[0314] When the communication apparatus 1000 is a terminal device 120, illustratively, the processor 1010 is used to perform the following operations: sending identification 1 and identification 2 to the network device 150; receiving response information 1 from the network device 150, etc.

[0315] When the communication device 1000 is a network device 150, illustratively, the processor 1010 is used to perform the following operations: receive identification 1 and identification 2 from the terminal device 120; obtain model information of model 1 according to identification 1 and identification 2; send response information 1 to the terminal device 120, etc.

[0316] When the communication apparatus 1000 is a network device 110 , illustratively, the processor 1010 is configured to perform the following operations: sending an identifier 1 and an identifier 2 to the terminal device 120 .

[0317] When the communication device 1000 is the network device 110, the network device 150 or the terminal device 120, it will be responsible for executing the methods or steps related to the network device 110, the network device 150 or the terminal device 120 in the above method embodiments.

[0318] It is understandable that when the communication device 1000 is a terminal device 120 or a network device 110 or a network device 150, the communication interface 1020 may also be referred to as a transceiver. The above description is only an exemplary description. For specific content, please refer to the content shown in the above method embodiment. Fig.10 The implementation of each operation in can also refer to Figures 5 to 9 The corresponding description of the method embodiment shown.

[0319] Fig.11 1 is a schematic block diagram of a communication device 1100 according to an embodiment of the present application. The communication device 1100 may be a network device 110, a network device 150, or a terminal device 120, or may be a chip or module in the network device 110, a network device 150, or a terminal device 120, for implementing the method involved in the above embodiment. The communication device 1100 includes a transceiver unit 1110. The transceiver unit 1110 is exemplarily introduced below.

[0320] The transceiver unit 1110 may include a transmitting unit and a receiving unit. The transmitting unit is used to perform a transmitting action of the communication device, and the receiving unit is used to perform a receiving action of the communication device. For ease of description, the embodiment of the present application combines the transmitting unit and the receiving unit into one transceiver unit. A unified description is given here, and no further description is given later.

[0321] When the communication device 1100 is a terminal device 120, illustratively, the transceiver unit 1110 is used to send the identifier 1 and the identifier 2 to the network device 150. The transceiver unit 1110 is also used to receive response information 1 from the network device 150, etc.

[0322] Optionally, the communication device 1100 may further include a processing unit 1120, which is used to execute the content of the steps involving processing and coordination of the terminal device 120. For example, the processing unit 1120 is used to perform the recognition process of the model 1 with the network device 110.

[0323] When the communication device 1100 is a network device 110, illustratively, the transceiver unit 1110 is used to send identification 1 and identification 2, etc. to the terminal device.

[0324] Optionally, the communication device 1100 may further include a processing unit 1120, which is used to execute the content of the steps involving processing and coordination of the network device 110. For example, the processing unit 1120 is used to perform the recognition process of the model 1 with the terminal device 120.

[0325] When the communication device 1100 is the network device 110, the network device 150 or the terminal device 120, it will be responsible for executing the methods or steps related to the network device 110, the network device 150 or the terminal device 120 in the above method embodiments.

[0326] Optionally, the communication device 1100 further includes a storage unit 1130, where the storage unit 1130 is used to store a program or code for executing the aforementioned method.

[0327] Fig.10 and Fig.11 The device embodiment shown is used to implement Figures 5 to 9 The content described. Fig.10 and Fig.11 The specific execution steps and methods of the device shown can refer to the contents described in the aforementioned method embodiment.

[0328] The present application also provides a chip, including a processor, for calling and executing instructions stored in a memory from the memory, so that a communication device equipped with the chip executes the methods in the above examples.

[0329] The present application also provides another chip, including: an input interface, an output interface, and a processor, wherein the input interface, the output interface, and the processor are connected via an internal connection path, and the processor is used to execute the code in the memory, and when the code is executed, the processor is used to execute the method in each of the above examples. Optionally, the chip also includes a memory, and the memory is used to store computer programs or codes.

[0330] The present application also provides a processor, which is coupled to a memory and is used to execute the methods and functions involving a network device or a terminal device in any of the above-mentioned embodiments.

[0331] In another embodiment of the present application, a computer program product including instructions is provided. When the computer program product is run on a computer, the method of the above embodiment is implemented.

[0332] The present application also provides a computer program. When the computer program is executed in a computer, the method of the above embodiment is implemented.

[0333] In another embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a computer, the method described in the above embodiment is implemented.

[0334] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0335] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0336] In several embodiments provided in the present application, the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0337] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0338] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0339] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0340] The above are only specific implementations of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiments of the present application, which should be included in the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application shall be based on the protection scope of the claims.

Claims

1. An artificial intelligence management method, characterized in that: include: Sending a first identifier and a second identifier to a first network device, where the first identifier is an identifier configured for a first model and comes from a second network device, the first model is a model successfully identified between the second network device and a terminal device, the second identifier is used to identify a first area, the first identifier is unique within the first area, and the first identifier includes at least one of a model identifier and a function identifier; Response information is received from the first network device, where the response information is used to indicate whether the first model is available.

2. The method according to claim 1, characterized in that The response information is used to indicate that the first model is available, and the method further includes: receiving a third identifier from the first network device, where the third identifier is an identifier configured by the first network device for the first model; or, The response information is used to indicate that the first model is available, and includes: The response information includes the third identifier.

3. The method according to claim 1, characterized in that The response information is used to indicate that the first model is unavailable, and the method further includes: receiving at least one of a second model and second model information from the first network device, wherein the second model information is used to activate the second model; or, receiving information from the first network device indicating to fall back to a non-artificial intelligence AI mode; or, receiving information from the first network device instructing to complete the identification process; or, The response information is used to indicate that the first model is unavailable, and includes one of the following: The response information includes at least one of the second model and the information of the second model; or, The response information includes information indicating that the terminal device falls back to the non-AI mode; or, The response information indicates information that the terminal device performs a complete identification process.

4. The method according to any one of claims 1 to 3, characterized in that The response information includes the first identifier.

5. The method according to any one of claims 1 to 4, characterized in that The type of the second identifier includes at least one of the following: A cell identifier, a cell group identifier, a tracking area identifier, a service area identifier, or a time advance group identifier; The type of the first area is associated with the type of the second identifier.

6. The method according to any one of claims 1 to 5, characterized in that The area of ​​the second network device belongs to the first area.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Receive the first identifier from the second network device.

8. The method according to claim 7, characterized in that The first identifier is carried in at least one of the following messages: Random access message, radio resource control RRC configuration request message, RRC configuration complete message, RRC reconfiguration complete message, RRC reconstruction request message, or physical layer message.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: The second identifier is received from the second network device.

10. The method according to claim 9, characterized in that The second identifier is carried in at least one of the following messages: Random access message, radio resource control RRC configuration request message, RRC configuration complete message, RRC reconfiguration complete message, RRC reconstruction request message, or physical layer message.

11. The method according to any one of claims 1 to 10, characterized in that The first network device manages a first cell, where the first cell is a current resident cell of the terminal device. The second network device manages a second cell, and the second cell is a source cell of the terminal device.

12. An artificial intelligence management method, characterized in that: The method is performed by a second network device or a chip used for the second network device, and includes: receiving a first identifier and a second identifier from a terminal device, wherein the first identifier is an identifier configured by a first network device for a first model, the first model is a model successfully identified between the first network device and the terminal device, the second identifier is used to identify a first area, the first identifier is unique within the first area, and the first identifier includes at least one of a model identifier and a function identifier; Acquire model information of the first model according to the first identifier and the second identifier, and determine whether the first model is available; Sending response information to the terminal device, where the response information is used to indicate whether the first model is available.

13. The method according to claim 12, characterized in that The response information is used to indicate that the first model is available, and the method further includes: Sending a third identifier to the terminal device, where the third identifier is an identifier configured by the second network device for the first model; or, The response information is used to indicate that the first model is available, and includes: The response information includes the third identifier.

14. The method according to claim 12, characterized in that The response information is used to indicate that the first model is unavailable, and the method further includes: sending a second model or at least one of information of a second model to the terminal device, where the second model is different from the first model, and the information of the second model is used to activate the second model; or, Instructing the terminal device to return to a non-AI mode; or, instructing the terminal device to perform a complete identification process; or, The response information is used to indicate that the first model is unavailable, and includes: The response information includes at least one of the second model and the information of the second model; or, The response information includes information indicating that the terminal device falls back to the non-AI mode; or, The response information instructs the terminal device to perform a complete identification process.

15. The method according to any one of claims 12 to 14, characterized in that The response information includes the first identifier.

16. The method according to any one of claims 12 to 15, characterized in that The type of the second identifier includes at least one of the following: A cell identifier, a cell group identifier, a tracking area identifier, a service area identifier, or a time advance group identifier; The type of the first area is associated with the type of the second identifier.

17. The method according to any one of claims 12 to 16, characterized in that The area of ​​the first network device belongs to the first area.

18. The method according to any one of claims 12 to 17, characterized in that The first identifier is carried in at least one of the following messages: Random access message, radio resource control RRC configuration request message, RRC configuration complete message, RRC reconfiguration complete message, RRC reconstruction request message, or physical layer message.

19. The method according to any one of claims 12 to 18, characterized in that The second identifier is carried in at least one of the following messages: Random access message, radio resource control RRC configuration request message, RRC configuration complete message, RRC reconfiguration complete message, RRC reconstruction request message, or physical layer message.

20. The method according to any one of claims 12 to 19, characterized in that The second network device manages a first cell, where the first cell is a current resident cell of the terminal device. The first network device manages a second cell, and the second cell is a source cell of the terminal device.

21. A communication device, characterized in that: comprising a processor, the processor being configured to: By executing computer programs or instructions, or by logic circuits, enabling the communication device to perform the method according to any one of claims 1 to 11; or, The communication device is enabled to execute the method according to any one of claims 12 to 20.

Images