Model transmission method, device, and storage medium

Abstract

Embodiments of the present application relate to the technical field of communications, and provide a model transmission method, a device, and a storage medium. A network device multicasts first information, the first information being used for indicating model data and / or a model identifier of an AI algorithm model; and a terminal device obtains, from the multicast first information, the model data and / or model identifier of the AI algorithm model. Thus, by employing a point-to-multipoint multicast method, repeated transmission of the AI algorithm model is avoided or reduced, thereby reducing waste of air interface resources.

Description

Model transmission method, device and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on February 8, 2024, with application number 202410177380.X and application name “Model Transmission Method, Device and Storage Medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a model transmission method, device and storage medium. Background Art

[0003] In communication systems, artificial intelligence (AI) algorithms are used to replace traditional algorithms for local air interface transmission to improve algorithm performance in complex scenarios.

[0004] In a communication system, terminal devices can serve as execution nodes for AI algorithm models, using them to perform operations. Network devices or servers can serve as training nodes for AI algorithm models, providing a large amount of computing power for training them. Because the use and training of AI algorithm models are not performed on the same node, the AI ​​algorithm model needs to be transmitted. The air interface transmission of AI algorithm models is still under discussion, and the solutions being discussed include network devices sending AI models to multiple terminal devices via radio resource control (RRC) messages or user plane (UP) data.

[0005] However, when different terminal devices use the same AI model, the network device sends the AI ​​model to the terminal device through RRC messages or UP data, which causes the same data to be transmitted repeatedly, resulting in a waste of air interface resources. Summary of the Invention

[0006] The embodiments of the present application provide a model transmission method, device, and storage medium, which are applied to the field of communication technology. By multicasting the AI ​​algorithm model, repeated transmission of AI algorithm model data is reduced or avoided, thereby saving air interface resources.

[0007] In a first aspect, an embodiment of the present application provides a model transmission method. The method includes: multicasting first information, where the first information is used to indicate model data of an AI algorithm model and / or a model identifier of the AI ​​algorithm model. In this embodiment, a network device can transmit the same AI algorithm model to multiple terminal devices by multicasting the model data and / or model identifier of the AI ​​algorithm model, thereby avoiding or reducing repeated transmission of the same AI algorithm model and saving air interface resources.

[0008] In an optional embodiment of the first aspect, before multicasting the first information, the method further includes: obtaining second information, the second information being used to indicate algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; and indicating third information, the third information being used to distribute configuration information related to the multicast of the AI ​​algorithm model. In this embodiment, based on the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device, the accuracy of distributing the configuration information related to the multicast of the AI ​​algorithm model is improved, so that terminal devices that support the algorithm capabilities related to the AI ​​algorithm model can receive the AI ​​algorithm model based on the configuration information.

[0009] In an optional embodiment of the first aspect, the configuration information related to the multicast of the AI ​​algorithm model includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and a group identifier of the multicast group corresponding to the first information, and the first information is transmitted by scheduling the group identifier. In this embodiment, based on one or more configuration information including RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and group identifiers, the success rate of receiving the AI ​​algorithm model by terminal devices that support algorithm capabilities related to the AI ​​algorithm model is improved; different multicast groups are distinguished by the group identifier corresponding to the multicast group and the first information is transmitted by scheduling the group identifier, so that the terminal devices belonging to the multicast group can accurately obtain the first information of the multicast based on the group identifier in the configuration information, thereby improving the accuracy of the AI ​​algorithm model transmission.

[0010] In an optional embodiment of the first aspect, after indicating the third information, the further embodiment includes: indicating fourth information, where the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating an effective time range of the group identifier, indicating an index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, and deactivating monitoring of the group identifier, and the first information is scheduled for transmission via the group identifier. In this embodiment, the terminal device accurately obtains the first information multicasted by the network device based on the indication of the fourth information, effectively improving the accuracy of the transmission of the AI ​​algorithm model.

[0011] In an optional embodiment of the first aspect, indicating the fourth information includes: indicating the fourth information through a MAC CE and / or a PDCCH DCI, thereby accurately sending the fourth information to the terminal device through the MAC CE and / or the PDCCH DCI.

[0012] In an optional embodiment of the first aspect, the multicast group corresponding to the first information includes terminal devices in a connected state and / or terminal devices in an inactive state. In this embodiment, the network device can transmit the AI ​​algorithm model to the terminal devices in a connected state and / or the terminal devices in an inactive state via multicast.

[0013] In an optional embodiment of the first aspect, for a terminal device in an inactive state, before multicasting the first information, it also includes: within the RAN-based notification area, indicating a fifth information at the paging opportunity, the fifth information is used to wake up the terminal device in the inactive state and / or instruct to multicast the AI ​​algorithm model, and when the fifth information is used to instruct to multicast the AI ​​algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information. In this embodiment, before performing the multicast, the network device may first use the fifth information to wake up the terminal device in the inactive state and / or inform the terminal device in the inactive state that the model data of the AI ​​algorithm model is about to be multicast, so that the terminal device in the inactive state is ready to obtain the multicast first information, thereby improving the success rate of the AI ​​algorithm model transmission.

[0014] In an optional embodiment of the first aspect, for a terminal device in an inactive state, the method further includes: indicating third information before the terminal device migrates from a connected state to an inactive state. In this embodiment, the network device may pre-configure configuration information related to multicasting of the AI ​​algorithm model to the terminal device via the third information, so that after the terminal device migrates to the inactive state, it can still obtain the first information broadcast by the network device based on the configuration information.

[0015] In an optional embodiment of the first aspect, the third information is an RRC connection release message for instructing the terminal device to migrate from a connected state to an inactive state, or the third information is an RRC message other than the RRC connection release message obtained by the terminal device in the connected state. In this embodiment, the network device obtains other RRC messages through the RRC connection release message, and configures the configuration information related to the multicast of the AI ​​algorithm model to the terminal device, so that after the terminal device migrates to the inactive state, it can also obtain the first information broadcast by the network device based on the configuration information.

[0016] In an optional embodiment of the first aspect, after multicasting the first information, the method further includes: obtaining sixth information, the sixth information being used to indicate that a data packet corresponding to the model data of the AI ​​algorithm model has failed to be transmitted; and retransmitting the data packet on a unicast channel corresponding to the terminal device to which the data packet failed to be transmitted. In this embodiment, in the event of a data packet transmission failure, there is no need to broadcast the model data of the AI ​​algorithm model. Instead, the data packet that failed to be transmitted is sent separately to the terminal device via a unicast channel to conserve air interface resources used for transmission of the AI ​​algorithm model.

[0017] In an optional embodiment of the first aspect, the multicast range of the first information includes one or more of the following: a cell in which the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device. In this embodiment, multiple multicast ranges of the first information are provided, and terminal devices within the multicast range can obtain the first information.

[0018] In a second aspect, an embodiment of the present application proposes a model transmission method. The method includes: obtaining a first multicast message, the first information being used to indicate the model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model; and obtaining the model data and / or the model identifier from the first message. In this embodiment, the terminal device can obtain the model data and / or model identifier of the AI ​​algorithm model from the first message multicast by the network device, thereby avoiding or reducing the repeated transmission of the same AI algorithm model through multicast, thereby saving air interface resources.

[0019] In an optional embodiment of the second aspect, before obtaining the first multicast information, the method further includes: sending second information, the second information being used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; and obtaining third information, the third information being used to distribute configuration information related to the multicast of the AI ​​algorithm model. In this embodiment, based on the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device, the accuracy of distributing the configuration information related to the multicast of the AI ​​algorithm model is improved, so that terminal devices that support the algorithm capabilities related to the AI ​​algorithm model can receive model data of the AI ​​algorithm model based on the configuration information.

[0020] In an optional embodiment of the second aspect, the configuration information related to the multicast of the AI ​​algorithm model also includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and a group identifier of the multicast group corresponding to the first information, and the first information is transmitted by scheduling the group identifier. In this embodiment, based on one or more configuration information including RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and group identifiers, the success rate of receiving model data of the AI ​​algorithm model by terminal devices that support algorithm capabilities related to the AI ​​algorithm model is improved; different multicast groups are distinguished by the group identifier corresponding to the multicast group and the first information is transmitted by scheduling the group identifier, so that the terminal devices belonging to the multicast group can accurately obtain the first information of the multicast based on the group identifier in the configuration information, thereby improving the accuracy of the AI ​​algorithm model transmission.

[0021] In an optional embodiment of the second aspect, obtaining the multicast first information includes: monitoring and obtaining the first information based on configuration information related to the multicast of the AI ​​algorithm model. In this embodiment, after obtaining the third information, the terminal device may monitor the first information based on the configuration information related to the multicast of the AI ​​algorithm model to successfully obtain the first information.

[0022] In an optional embodiment of the second aspect, after obtaining the third information, the further step includes: obtaining fourth information, where the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating a valid time range for the group identifier, indicating an index corresponding to the bearer resource information used for multicast, activating a monitoring group identifier, and deactivating a monitoring group identifier, wherein the first information is transmitted via group identifier scheduling. In this embodiment, the terminal device accurately obtains the first information multicasted by the network device based on the indication of the fourth information, effectively improving the accuracy of the transmission of the AI ​​algorithm model.

[0023] In an optional embodiment of the second aspect, obtaining the fourth information includes: obtaining the fourth information through MAC CE and / or PDCCH DCI, thereby accurately sending the fourth information to the terminal device through MAC CE and / or PDCCH DCI.

[0024] In an optional embodiment of the second aspect, the terminal device is in a connected state or an inactive state. In this embodiment, the network device can transmit the AI ​​algorithm model to the terminal device in the connected state and / or the terminal device in the inactive state by multicast. When the terminal device is in the inactive state, before obtaining the first information, it also includes: obtaining the fifth information at the paging time, the fifth information is used to wake up the terminal device in the inactive state and / or instruct to multicast the AI ​​algorithm model. When the fifth information is used to instruct to multicast the AI ​​algorithm model, the fifth information contains the group identifier of the multicast group corresponding to the first information. In this embodiment, before performing the multicast, the network device can first wake up the terminal device in the inactive state and / or inform the terminal device in the inactive state that the model data of the AI ​​algorithm model will be multicasted through the fifth information, so that the terminal device in the inactive state is ready to obtain the first information of the multicast, thereby improving the success rate of the AI ​​algorithm model transmission.

[0025] In an optional embodiment of the second aspect, after obtaining the fifth information during the paging occasion, the method further includes: sending an RRC recovery establishment request message to request migration from the inactive state to the connected state. In this embodiment, after obtaining the fifth information, the terminal device in the inactive state can migrate from the inactive state to the connected state to transmit the AI ​​algorithm model in the connected state.

[0026] In an optional embodiment of the second aspect, the RRC recovery establishment request message carries indication information, where the indication information is used to indicate that the terminal device supports receiving model data of the AI ​​algorithm model. In this embodiment, the terminal device indicates through the RRC recovery establishment request message that it supports receiving model data of the AI ​​algorithm model, so that the network device can perform multicast of the model data of the AI ​​algorithm model when the terminal supports receiving model data of the AI ​​algorithm model.

[0027] In an optional embodiment of the second aspect, obtaining the third information includes: obtaining the third information before the terminal device migrates from a connected state to an inactive state. In this embodiment, the network device can configure the configuration information related to the multicast of the AI ​​algorithm model to the terminal device in advance through the third information, so that after the terminal device migrates to the inactive state, it can also obtain the first information broadcast by the network device based on the configuration information. The third information is an RRC connection release message for indicating that the terminal device migrates from a connected state to an inactive state, or the third information is an RRC message other than the RRC connection release message obtained by the terminal device in the connected state. In this embodiment, the network device obtains other RRC messages through the RRC connection release message, and configures the configuration information related to the multicast of the AI ​​algorithm model to the terminal device, so that after the terminal device migrates to the inactive state, it can also obtain the first information broadcast by the network device based on the configuration information.

[0028] An optional embodiment of the second aspect further includes: sending sixth information indicating that the data packet corresponding to the model data has failed to be transmitted; and obtaining a retransmitted data packet on a unicast channel corresponding to the terminal device. In this embodiment, if data packet transmission fails, there is no need to broadcast the model data of the AI ​​algorithm model. Instead, the data packet that failed to be transmitted is sent separately to the terminal device via a unicast channel to conserve air interface resources used for transmission of the AI ​​algorithm model.

[0029] In an optional embodiment of the second aspect, the first information is multicast in the form of multicast user plane data or multicast signaling. In this embodiment, two multicast modes of the first information are provided.

[0030] In an optional embodiment of the second aspect, the multicast range of the first information includes one or more of the following: a cell in which the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device. In this embodiment, multiple multicast ranges of the first information are provided, and terminal devices within the multicast range can obtain the first information.

[0031] In a third aspect, an embodiment of the present application provides a network device, including: a multicast module, used to multicast first information, where the first information is used to indicate model data of an AI algorithm model and / or a model identifier of the AI ​​algorithm model.

[0032] In an optional embodiment of the third aspect, the network device also includes: an algorithm capability acquisition module for acquiring second information, the second information being used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; and a configuration module for indicating third information, the third information being used to allocate configuration information related to multicast of the AI ​​algorithm model.

[0033] In an optional embodiment of the third aspect, the configuration information related to the multicast of the AI ​​algorithm model includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is transmitted through the group identifier scheduling.

[0034] In an optional embodiment of the third aspect, the configuration module is also used to: indicate fourth information, the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating an effective time range of the group identifier, indicating an index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, and deactivating monitoring of the group identifier, and the first information is scheduled for transmission through the group identifier.

[0035] In an optional embodiment of the third aspect, the configuration module is specifically used to indicate the fourth information through MAC CE and / or through DCI of PDCCH during the process of indicating the fourth information.

[0036] In an optional embodiment of the third aspect, the multicast group corresponding to the first information includes terminal devices in a connected state and / or terminal devices in an inactive state.

[0037] In an optional embodiment of the third aspect, for a terminal device in an inactive state, the network device further includes: a first indication module, used to indicate fifth information at a paging occasion within a RAN-based notification area, the fifth information being used to wake up the terminal device in an inactive state and / or to indicate multicasting of an AI algorithm model. When the fifth information is used to indicate multicasting of an AI algorithm model, the fifth information includes a group identifier of the multicast group corresponding to the first information.

[0038] In an optional embodiment of the third aspect, for a terminal device in an inactive state, the network device further includes: a second indication module, configured to indicate third information before the terminal device migrates from a connected state to an inactive state.

[0039] In an optional embodiment of the third aspect, the third information is an RRC connection release message used to instruct the terminal device to migrate from a connected state to an inactive state, or the third information is other RRC messages other than the RRC connection release message obtained by the terminal device in the connected state.

[0040] In an optional embodiment of the third aspect, the network device also includes a retransmission module, which is used to: obtain sixth information, where the sixth information is used to indicate that the data packet corresponding to the model data of the AI ​​algorithm model has failed to be transmitted; and retransmit the data packet on the unicast channel corresponding to the terminal device where the data packet transmission failed.

[0041] In an optional embodiment of the third aspect, the multicast range of the first information includes one or more of the following: a cell where the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device.

[0042] It should be understood that the technical solution of the third aspect of the present application corresponds to the technical solution of the first aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated.

[0043] In a fourth aspect, an embodiment of the present application proposes a terminal device, comprising: an information acquisition module for acquiring first multicast information, the first information being used to indicate model data of an AI algorithm model and / or a model identifier of the AI ​​algorithm model; a model data acquisition module for acquiring the model data and / or the model identifier from the first information.

[0044] In an optional embodiment of the fourth aspect, the terminal device also includes: a first sending module for sending second information, the second information is used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; the information acquisition module is also used to: obtain third information, the third information is used to allocate configuration information related to multicast of the AI ​​algorithm model.

[0045] In an optional embodiment of the fourth aspect, the configuration information related to the multicast of the AI ​​algorithm model also includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is transmitted through the group identifier scheduling.

[0046] In an optional embodiment of the fourth aspect, the information acquisition module is specifically used to: monitor and obtain the first information based on configuration information related to the multicast of the AI ​​algorithm model.

[0047] In an optional embodiment of the fourth aspect, the information acquisition module is also used to: obtain fourth information, and the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating the effective time range of the group identifier, indicating the index corresponding to the bearer resource information used for multicast, activating the monitoring group identifier, and deactivating the monitoring group identifier. The first information is transmitted via group identifier scheduling.

[0048] In an optional embodiment of the fourth aspect, the information acquisition module is specifically used to: monitor and obtain the first information based on one or more of the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information used for multicast, as well as the configuration information.

[0049] In an optional embodiment of the fourth aspect, the information acquisition module is specifically used to: acquire the fourth information through MAC CE and / or PDCCH DCI during the process of acquiring the fourth information.

[0050] In an optional embodiment of the fourth aspect, the terminal device is in a connected state or an inactive state. When the terminal device is in the inactive state, the information acquisition module is further used to: obtain fifth information at a paging opportunity, the fifth information being used to wake up the terminal device in the inactive state and / or instruct to perform multicast of the AI ​​algorithm model; when the fifth information is used to instruct to perform multicast of the AI ​​algorithm model, the fifth information includes a group identifier of the multicast group corresponding to the first information.

[0051] In an optional embodiment of the fourth aspect, the terminal device further includes: a second sending module, configured to send an RRC recovery establishment request message to request migration from an inactive state to a connected state.

[0052] In an optional embodiment of the fourth aspect, the RRC recovery establishment request message carries indication information, which is used to indicate that the terminal device supports receiving model data of the AI ​​algorithm model.

[0053] In an optional embodiment of the fourth aspect, the information acquisition module, during the process of acquiring the third information, is specifically configured to: acquire the third information before the terminal device migrates from a connected state to an inactive state. The third information is an RRC connection release message used to instruct the terminal device to migrate from the connected state to the inactive state, or the third information is an RRC message other than the RRC connection release message obtained by the terminal device in the connected state.

[0054] In an optional embodiment of the fourth aspect, the terminal device also includes a retransmission module, which is used to: send sixth information, where the sixth information is used to indicate that the data packet corresponding to the model data has failed to be transmitted; and obtain the retransmitted data packet on the unicast channel corresponding to the terminal device.

[0055] In an optional embodiment of the fourth aspect, the multicast range of the first information includes one or more of the following: a cell where the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device.

[0056] It should be understood that the technical solution of the fourth aspect of the present application corresponds to the technical solution of the second aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated.

[0057] In a fifth aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, the memory being used to store computer-executable instructions, the processor executing the computer-executable instructions stored in the memory, so that the electronic device performs the method described in the first aspect or any possible implementation of the first aspect, or the electronic device performs the method described in the second aspect or any possible implementation of the second aspect.

[0058] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the method described in the first aspect or any possible implementation of the first aspect is implemented; alternatively, when the computer program or instruction is executed by a processor, the method described in the second aspect or any possible implementation of the second aspect is implemented.

[0059] In a seventh aspect, the present application provides a chip or chip system, which includes at least one processor and a communication interface, the communication interface and the at least one processor being interconnected by a line, and the at least one processor being used to run a computer program or instruction to execute the method described in the first aspect or any possible implementation of the first aspect, or to execute the method described in the second aspect or any possible implementation of the second aspect. The communication interface in the chip can be an input / output interface, a pin, or a circuit, etc.

[0060] In one possible implementation, the chip or chip system described above in this application further includes at least one memory, in which instructions are stored. The memory may be a storage unit within the chip, such as a register, a cache, etc., or a storage unit of the chip (e.g., a read-only memory, a random access memory, etc.).

[0061] In an eighth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, which, when run, enables a computer to execute the method described in the first aspect or any possible implementation of the first aspect, or enables a computer to execute the method described in the second aspect or any possible implementation of the second aspect.

[0062] It should be understood that the fifth to eighth aspects of the present application correspond to the technical solutions of the first to second aspects of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation methods are similar and will not be repeated here.

[0063] An embodiment of the present application provides a model transmission method, device, and storage medium. A network device multicasts first information, where the first information is used to indicate model data of an AI algorithm model and / or a model identifier of an AI algorithm model. A terminal device can obtain the model data and / or model identifier of the AI ​​algorithm model from the multicast first information. Thus, through a point-to-multipoint multicast method, the network device can send the same AI algorithm model to multiple terminal devices, thereby avoiding or reducing repeated transmission of the same AI algorithm model and saving air interface resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 is a logical block diagram of data collection, model training, model monitoring, model reasoning, and model storage for AI algorithm models;

[0065] FIG2 is a diagram of a communication system architecture provided in an embodiment of the present application;

[0066] FIG3 is a schematic diagram of a model transmission method provided in an embodiment of the present application;

[0067] FIG4 is a schematic diagram of a model transmission method provided in yet another embodiment of the present application;

[0068] FIG5 is a schematic diagram of a model transmission method provided in yet another embodiment of the present application;

[0069] FIG6 is a schematic diagram of a model transmission method provided in yet another embodiment of the present application;

[0070] FIG7 is a schematic diagram of a model transmission method provided in yet another embodiment of the present application;

[0071] FIG8 is a schematic diagram of a network device provided in an embodiment of the present application;

[0072] FIG9 is a schematic diagram of a terminal device provided in an embodiment of the present application;

[0073] FIG10 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] To facilitate a clear description of the technical solutions of the embodiments of the present application, some of the terms and technologies involved in the embodiments of the present application are briefly introduced below:

[0075] Artificial intelligence (AI) algorithm model: An algorithm model with a certain learning ability. By training the AI ​​algorithm model, the AI ​​algorithm model can learn to process massive amounts of data and complex tasks, such as the neural network model in the machine learning (ML) model.

[0076] Figure 1 is a logical block diagram of data collection, model training, model monitoring, model reasoning, and model storage of an AI algorithm model. This logical block diagram shows the life cycle of an AI algorithm model.

[0077] As shown in Figure 1, the life cycle of an AI algorithm model may include a data collection stage 101, a model training stage 102, a model monitoring stage 103, a model reasoning stage 104, and a model storage stage 105: In the data collection stage 101, data collection can obtain training data for model training, monitoring data for model monitoring (i.e., model management), and reasoning data for model reasoning (i.e., model reasoning operations); in the model training stage 102, the training data can be used to train the AI ​​algorithm model to obtain a trained or updated AI algorithm model; in the model monitoring stage 103, the effect of the AI ​​algorithm model can be monitored based on the monitoring data and the parameters output by the model reasoning stage 104. The model effect is fed back to the model training stage 102, or a retraining request is sent to the model training stage 102 to retrain the AI ​​algorithm model; in the model inference stage 104, the AI ​​algorithm model can be inferred based on the inference data to obtain corresponding parameters, and the parameters are output to the model monitoring stage 103. The model monitoring stage 103 can determine the AI ​​algorithm model for model inference in the model inference stage 104 from the stored AI algorithm models through model selection, activation, switching or fallback; in the model storage stage 105, the trained or updated AI algorithm model can be stored, and the AI ​​algorithm model with better model effect in the model monitoring stage 103 can also be stored.

[0078] The training of AI algorithm models requires a lot of computing power support, so in communication scenarios, the training of AI algorithm models can be deployed on the network side or on the server; the application scenarios of AI algorithm models may include the channel state information (CSI) prediction scenario on the terminal device side, and the beam prediction scenario in the time domain and frequency domain. These application scenarios require the terminal device to act as an AI algorithm execution node to perform operations, so the trained AI algorithm model can be deployed on the terminal device side. In this way, when the training and use of the AI ​​algorithm model are not on the same node, the AI ​​algorithm model needs to be transmitted. The embodiment of the present application solves how to transmit the AI ​​algorithm model from the network device to the terminal device.

[0079] It should be noted that in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. For example, the first information and the second information are merely used to distinguish different information and do not limit their order. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean that they are different.

[0080] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0081] It should be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, a--c, bc, or abc, where a, b, c can be single or multiple.

[0082] In order to better understand the model transmission method provided in the embodiment of the present application, the communication system architecture of the embodiment of the present application is described below in conjunction with Figure 1.

[0083] For example, Figure 2 is a diagram of the communication system architecture provided by an embodiment of the present application. As shown in Figure 2, the communication system includes a terminal device 201 and a network device 202, and the terminal device 201 communicates with the network device 202 wirelessly.

[0084] In an embodiment of the present application, the network device 202 transmits the AI ​​algorithm model to the terminal device 201 via multicast.

[0085] The terminal device involved in the embodiments of the present application can also be referred to as a terminal, which can be a device with wireless transceiver function, which can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface (such as a ship, etc.); it can also be deployed in the air (for example, on an airplane, a balloon, and a satellite, etc.). The terminal device can be a user equipment (UE), wherein the UE includes a handheld device, a vehicle-mounted device, a wearable device, or a computing device with wireless communication function. Exemplarily, the UE can be a mobile phone, a tablet computer, or a computer with wireless transceiver function. The terminal device can also be a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a mixed reality (MR) terminal device, a wireless terminal in industrial control, a wireless terminal in unmanned driving, a wireless terminal in telemedicine, a wireless terminal in a smart grid, a wireless terminal in a smart city, a wireless terminal in a smart home, and the like. In an embodiment of the present application, the device for realizing the function of the terminal device may be the terminal device; or it may be a device that can support the terminal device to realize the function, such as a chip system, which may be installed in the terminal device.

[0086] The network device 202 involved in the embodiment of the present application includes an access network device 2021 and a core network device 2022. Among them, the training of the AI ​​terminal model can be performed on the access network device 2021 and / or the core network device 2022.

[0087] Access network (RAN) equipment is the intermediate device that connects terminal devices to core network equipment via wireless communication. It is primarily responsible for radio resource management, quality of service (QoS) management, data compression and encryption, etc. on the air interface side. Examples include NodeBs, evolved eNodeBs, gNodeBs in 5G mobile communication systems or next-generation radio (NR) communication systems, and base stations in future mobile communication systems.

[0088] Core network (CN) equipment includes user plane function (UPF) network elements, access and mobility management function (AMF) network elements, session management function (SMF) network elements, policy control function (PCF) network elements, etc. Among them, the UPF network element is mainly responsible for the transmission of user data, while the other network elements can be called control plane function network elements, which are mainly responsible for authentication, authorization, registration management, session management, mobility management, and policy control to ensure the reliable and stable transmission of user data.

[0089] In an embodiment of the present application, the device for implementing the function of the network device may be a network device, or a device that can support the network device to implement the function, such as a chip system, which may be installed in the network device.

[0090] The technical solutions provided in the embodiments of the present application can be applied to the long term evolution (LTE) architecture, and can also be applied to the universal mobile telecommunications system (UMTS) terrestrial radio access network (UTRAN) architecture, or the global system for mobile communication (GSM) / enhanced data rate for GSM evolution (EDGE) system radio access network (GSM EDGE radio access network, GERAN) architecture. In addition, the technical solutions provided in the embodiments of the present application can also be applied to any other wireless communication system with similar structure and function, such as a public land mobile network (PLMN) system, a 5G communication system or a communication system after 5G, etc., and the embodiments of the present application do not impose any restrictions on this.

[0091] Wireless communication between communication devices may include: wireless communication between network devices and terminal devices, wireless communication between network devices and network devices, and wireless communication between terminal devices. In the embodiments of the present application, the term "wireless communication" may also be referred to as "communication", and the term "communication" may also be described as "data transmission", "information transmission" or "transmission". Those skilled in the art may apply the technical solutions provided in the embodiments of the present application to wireless communication between network devices and terminal devices, such as wireless communication between access network devices and terminal devices.

[0092] In related technologies, in a mobile communication network, terminal devices with the same characteristics in the same cell or the same network device may use the same AI algorithm model. When the network device transmits the AI ​​algorithm model to the terminal device, the same AI algorithm model may be transmitted repeatedly. For example, the network device transmits the AI ​​algorithm model to terminal device A separately, and also transmits the AI ​​algorithm model to terminal device B separately, resulting in a waste of air interface resources.

[0093] In view of the above problems, the present invention proposes a model transmission method, the main inventive ideas of which are as follows:

[0094] Network devices transmit AI algorithm models to terminal devices via multicast. Multicast is a point-to-multipoint transmission method. A single transmission from a network device can transmit the AI ​​algorithm model to multiple terminal devices, avoiding or reducing repeated transmissions of the AI ​​algorithm model and conserving air interface resources.

[0095] The model transmission method provided in the embodiment of the present application is applicable to any AI algorithm task or service including channel state information (CSI) processing, beam processing, and positioning processing on the terminal device side.

[0096] Optionally, CSI processing may include CSI prediction and / or CSI feedback enhancement; beam processing may include beam management and / or beam prediction; and positioning processing may include positioning accuracy enhancement.

[0097] It should be noted that the model transmission method provided in the embodiment of the present application is not limited to the above tasks or services.

[0098] The technical solutions shown in this application are described in detail below through specific embodiments. It should be noted that the following embodiments can exist independently or in combination with each other. For the same or similar content, such as the explanation of terms or nouns, and the explanation of steps, etc., different embodiments can refer to each other and will not be repeated.

[0099] FIG3 is a schematic diagram of a model transmission method provided in an embodiment of the present application. As shown in FIG3 , the model transmission method provided in this embodiment includes:

[0100] S301, a network device multicasts first information, where the first information is used to indicate model data of an AI algorithm model and / or a model identifier of the AI ​​algorithm model.

[0101] Exemplarily, the model data of the AI ​​algorithm model may include weight parameters of the AI ​​algorithm model, model structure parameters, required input data, data format of input data, data format of output data, inference formulas, etc.

[0102] Among them, considering that the data volume of the model data of the AI ​​algorithm model may be large, in the first information, the model data of the AI ​​algorithm model may be presented in the form of one or more data packets.

[0103] The model identifier of the AI ​​algorithm model is used to uniquely identify the AI ​​algorithm model. Based on the model identifier of the AI ​​algorithm model, the terminal device can accurately determine the AI ​​algorithm model transmitted by the network device via multicast.

[0104] Exemplarily, when the first information is used to indicate the model identifier of the AI ​​algorithm model, the terminal device can obtain the model data of the AI ​​algorithm model from the server based on the model identifier of the AI ​​algorithm model.

[0105] As another example, when the first information is used to indicate the model data of the AI ​​algorithm model and the model identifier of the AI ​​algorithm model, the terminal device can determine the AI ​​algorithm model to which the model data in the first information belongs based on the model identifier in the first information, thereby improving the accuracy of the transmission and application of the AI ​​algorithm model.

[0106] Optionally, the first information is used to indicate the model data corresponding to multiple AI algorithm models and the model identifiers corresponding to multiple AI algorithm models, thereby realizing the transmission of multiple AI algorithm models by multicasting the first information, thereby improving the transmission efficiency of the AI ​​algorithm models, and distinguishing the model data corresponding to the multiple AI algorithm models through the model identifiers corresponding to the multiple AI algorithm models, thereby improving the transmission accuracy of the AI ​​algorithm models.

[0107] Among them, the training of AI algorithm models can be performed on RAN equipment (such as gNodeB), CN equipment and / or operation administration and maintenance (OAM).

[0108] In this embodiment, the network device may broadcast the first information after training or updating the AI ​​algorithm model, or after obtaining the trained or updated AI algorithm model, or when the network device is ready to transmit the AI ​​algorithm model.

[0109] S302, the terminal device obtains the first multicast information, and obtains the model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model from the first information.

[0110] In this embodiment, a terminal device in the multicast group corresponding to the first information can receive the first information multicasted by the network device and obtain the model data and / or model identifier of the AI ​​algorithm model from the first information. The terminal device can then deploy and execute the AI ​​algorithm model according to business needs.

[0111] In an embodiment of the present application, the network device can transmit the model data and / or model identifier of the same AI algorithm model to multiple terminal devices at one time through a point-to-multipoint multicast method, thereby avoiding or reducing multiple repeated transmissions of the AI ​​algorithm model and saving air interface resources.

[0112] Optionally, the first information is multicast in a manner of multicasting user plane (UP) data or multicast signaling. In other words, the network device multicasts the first information in a manner of multicasting UP data or multicast signaling.

[0113] Exemplarily, the first information is service data transmitted on the UP, and the network device multicasts the first information on the UP.

[0114] As another example, the first information is control signaling transmitted on the control plane, and the network device multicasts the first information on the control plane.

[0115] Optionally, the multicast range of the first information may include one or more of the following: the cell where the network device is located, the configured cell list, the notification area based on the radio access network (RAN), and the tracking area (TA) corresponding to the terminal device. The network device may multicast the first information within one or more of the cell where the network device is located, the configured cell list, the notification area based on RAN, and the TA corresponding to the terminal device. Thus, the repeated transmission of the AI ​​algorithm model in the cell where the network device is located, the configured cell list, the notification area based on RAN, and the TA corresponding to the terminal device can be reduced or avoided, saving air interface resources.

[0116] Among them, the cell where the network device is located is the cell corresponding to the network device and the cell managed by the network device. One network device can correspond to one or more cells. The configured cell list can be understood as a specified cell list, which is composed of several cells. The RAN-based notification area (RNA) can contain one or more cells. Terminal devices in an inactive state moving within the RNA do not need to report their location to the network device. The RNA can be configured by the network device. The TA corresponding to the terminal device refers to the free movement area where the terminal device does not need to update the location service. The network device can multicast the first information within the TA corresponding to the terminal device.

[0117] Among them, the terminal device is in an inactive state means that the radio resource control (RRC) of the terminal device is in an inactive state (inactive), that is, the terminal device is in an RRC inactive state; the terminal device is in a connected state means that the RRC of the terminal device is in a connected state (connected), that is, the terminal device is in an RRC connected state.

[0118] Optionally, the first information is also used to indicate the group identifier of the multicast group corresponding to the first information. The group identifier corresponding to the multicast group is used to uniquely identify the multicast group, that is, the group identifier corresponds to the multicast group one-to-one. The network device can multicast one or more AI algorithm models to a multicast group. In order to facilitate the terminal devices in the multicast group to obtain the multicast AI algorithm model, the network device can use the group identifier for the scheduling transmission of the multicast information, that is, the first information is scheduled and transmitted through the group identifier of the multicast group corresponding to the first information. Specifically, the network device multicasts the first information to the multicast group. The first information can indicate the group identifier corresponding to the multicast group. The group identifier corresponding to the multicast group has been assigned to the terminal devices in the multicast group. The terminal devices in the multicast group can listen to the first information containing the group identifier based on the assigned group identifier to accurately obtain the model data and / or model identifier of the AI ​​algorithm model multicasted by the network device to the multicast group where the terminal device is located. For example, if the terminal device is assigned a group identifier a1, it can obtain the first information indicating the group identifier a1 and the model data of the AI ​​algorithm model.

[0119] Optionally, the group identifier corresponding to the multicast group is a radio network temporary identifier (RNTI) corresponding to the multicast group, so that different multicast groups are distinguished by the RNTI corresponding to the multicast group.

[0120] Optionally, the group identifier corresponding to the multicast group is assigned to the terminal device based on the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device. For terminal devices supporting the same algorithm capabilities, the same group identifier can be assigned, and for terminal devices supporting different algorithm capabilities, different group identifiers can be assigned, so that terminal devices supporting the same algorithm capabilities are located in the same multicast group. The network device can distribute the same AI algorithm model to multiple terminal devices in the multicast group through multicast, thereby reducing or avoiding repeated transmission of the AI ​​algorithm model and saving air interface resources.

[0121] FIG4 is a schematic diagram of a model transmission method provided by another embodiment of the present application. As shown in FIG4 , the model transmission method provided by this embodiment includes:

[0122] S401, the terminal device sends second information, where the second information is used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device.

[0123] In this embodiment, the terminal device can obtain the algorithm capabilities related to the AI ​​algorithm model that it supports, generate second information based on the algorithm capabilities related to the AI ​​algorithm model that it supports, and send the second information to the network device.

[0124] Optionally, the second information indicates the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device, including one or more of the following: application scenarios related to the AI ​​algorithm model supported by the terminal device, computing capabilities related to the AI ​​algorithm model supported by the terminal device, and model information of the AI ​​algorithm model supported by the terminal device (such as model identification and model type). Among them, the computing capabilities related to the AI ​​algorithm model supported by the terminal device include, for example, the model scale of the AI ​​algorithm model supported by the terminal device and the hardware resources of the terminal device used to calculate the AI ​​algorithm model.

[0125] Furthermore, when the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device include application scenarios related to the AI ​​algorithm model supported by the terminal device, the second information may be used to indicate the scenario identifier of the application scenario related to the AI ​​algorithm model supported by the terminal device, so as to indicate the application scenario related to the AI ​​algorithm model supported by the terminal device through the scenario identifier. If the second information sent by different terminal devices indicates the same scenario identifier, then the different terminal devices have the same algorithm capabilities related to the AI ​​algorithm model.

[0126] Furthermore, application scenarios related to AI algorithm models may include one or more of the following: CSI processing scenarios, beam processing scenarios, and positioning processing scenarios. CSI processing scenarios may include CSI prediction and / or CSI feedback enhancement; beam processing may include beam management and / or beam prediction; and positioning processing may include positioning accuracy enhancement.

[0127] Optionally, the second information is used to indicate that the terminal device supports algorithm capabilities related to the AI ​​algorithm model and the model identification of the AI ​​algorithm model, and / or, the second information is used to indicate that the terminal device does not support algorithm capabilities related to the AI ​​algorithm model and the model identification of the AI ​​algorithm model.

[0128] S402, the network device indicates third information, where the third information is used to distribute configuration information related to multicast of the AI ​​algorithm model.

[0129] In this embodiment, the network device determines the configuration information related to the multicast of the AI ​​algorithm model assigned to the terminal device based on the second information. After determining the configuration information related to the multicast of the AI ​​algorithm model assigned to the terminal device, the network device may indicate the third information, that is, send the third information to the terminal device to assign the configuration information related to the multicast of the AI ​​algorithm model to the terminal device. For multiple terminal devices with the same algorithm capability related to the AI ​​algorithm model, the network device may assign the same configuration information so that the multiple terminal devices can receive the same AI algorithm model via multicast; for multiple terminal devices with different algorithm capabilities related to the AI ​​algorithm model, the network device may assign different configuration information so that the multiple terminal devices can accurately receive the corresponding AI algorithm model via multicast.

[0130] The network device determines, based on the second information, the configuration information related to the multicast of the AI ​​algorithm model to be allocated to the terminal device, which may include one or more of the following optional implementations:

[0131] In an optional implementation, if the second information indicates an application scenario related to an AI algorithm model supported by the terminal device, the network device may determine the AI ​​algorithm model corresponding to the application scenario and determine configuration information related to multicasting of the AI ​​algorithm model. The same configuration information may be allocated to terminal devices supporting the same application scenario.

[0132] Exemplarily, for multiple terminal devices that support CSI prediction through the AI ​​algorithm model, configuration information related to the multicast of the AI ​​algorithm model used for CSI prediction can be allocated. For example, the second information indicates the scenario identifier corresponding to the CSI prediction. The network device can determine, based on the scenario identifier, that the AI ​​algorithm model to be transmitted to the terminal device is the AI ​​algorithm model used for CSI prediction, and then determine the configuration information related to the multicast of the AI ​​algorithm model; similarly, for multiple terminal devices that support beam prediction through the AI ​​algorithm model, configuration information related to the multicast of the AI ​​algorithm model used for beam prediction can be allocated; for multiple terminal devices that support positioning accuracy enhancement through the AI ​​algorithm model, configuration information related to the AI ​​algorithm model used for positioning accuracy enhancement can be allocated.

[0133] In another optional implementation, if the second information indicates the computing capability related to the AI ​​algorithm model supported by the terminal device, the network device can determine the AI ​​algorithm model running within the computing capability and determine the configuration information related to the multicast of the AI ​​algorithm model.

[0134] In another optional implementation, if the second information indicates the model information of the AI ​​algorithm model supported by the terminal device, the network device may determine the configuration information related to the multicast of the AI ​​algorithm model based on the model information. For example, the network device determines the configuration information related to the multicast of the AI ​​algorithm model based on the model identifier of the AI ​​algorithm model.

[0135] In another optional implementation, if the second information indicates that the terminal device supports the algorithm capabilities related to the AI ​​algorithm model and the model identifier of the AI ​​algorithm model, the network device may determine the configuration information related to the multicast of the AI ​​algorithm model based on the model identifier of the AI ​​algorithm model; and / or, if the second information indicates that the terminal device does not support the algorithm capabilities related to the AI ​​algorithm model and the model identifier of the AI ​​algorithm model, the network device may not allocate the configuration information related to the multicast of the AI ​​algorithm model to the terminal device.

[0136] Among them, the configuration information related to the multicast of the AI ​​algorithm model can be the configuration information of the resources used for multicast, or the configuration information of the model data of the AI ​​algorithm model.

[0137] Optionally, the configuration information related to the multicast of the AI ​​algorithm model includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information.

[0138] Exemplarily, RRC parameters may include configuration parameters such as signaling radio bearer (SRB) and data radio bearer (DRB); channel resource information for multicast, such as physical channel resource information, transport channel resource information, and logical channel resource information; bearer resource information for multicast may include configuration information of resources allocated for multicast on one or more protocol entities, such as configuration information of resources allocated on the service data adaptation protocol (SDAP) entity and configuration information of resources allocated on the packet data convergence protocol (PCDP) entity; bearer resource information for multicast may or may not include channel resource information for multicast; air interface resource information for multicast refers to time-frequency resource information at the physical layer. Security parameters for data security, for example, encryption parameters and / or decryption parameters for model data of an AI algorithm model.

[0139] Exemplarily, the channel resource information may include one or more of the time-frequency resources corresponding to the physical downlink control channel (PDCCH), the parameter configuration corresponding to the PDCCH, the time-frequency resources of the physical downlink shared channel (PDSCH), and the parameter configuration corresponding to the PDSCH; the bearer resource information may be user bearer plane information and / or control plane bearer information. The user plane bearer information may include the parameter configuration corresponding to each layer of the DRB protocol stack, such as the parameter configuration corresponding to the PDCP layer, the parameter configuration corresponding to the radio link layer control protocol (RLC), and the parameter configuration corresponding to the media access control (MAC) layer. It may also include one or more of the parameter configurations corresponding to the logical channel. The control plane bearer information may include one or more of the parameter configurations corresponding to the SRB, the parameter configurations corresponding to each layer of the protocol stack (PDCP / RLC / MAC), the parameter configuration corresponding to the logical channel, and the parameter configuration corresponding to the transmission channel.

[0140] S403, the network device multicasts first information according to configuration information related to multicast of the AI ​​algorithm model, where the first information is used to indicate model data of the AI ​​algorithm model and / or a model identifier of the AI ​​algorithm model.

[0141] In this embodiment, since the network device has distributed configuration information related to multicast of the AI ​​algorithm model to the terminal device through the third information, in order to facilitate the terminal device to obtain the first information, the network device can multicast the first information according to the configuration information.

[0142] Optionally, the network device multicasts the first information according to one or more of RRC parameters for multicast, channel resources for multicast, bearer resources for multicast, air interface resources for multicast, and security parameters for data security.

[0143] S404, the terminal device obtains first information based on configuration information related to the multicast of the AI ​​algorithm model, and obtains model data of the AI ​​algorithm model and / or a model identifier of the AI ​​algorithm model from the first information.

[0144] In this embodiment, the terminal device obtains first information on corresponding resources and / or through corresponding data security processing operations in accordance with the configuration information related to the multicast of the AI ​​algorithm model, and obtains model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model from the first information.

[0145] Optionally, the terminal device obtains the first information according to one or more of the RRC parameters for multicast, channel resources for multicast, bearer resources for multicast, air interface resources for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information.

[0146] Optionally, when the configuration information related to the multicast of the AI ​​algorithm model includes the group identifier of the multicast group corresponding to the first information, the first information is scheduled for transmission using the group identifier. The network device uses the third information to pre-assign the group identifier of the multicast group corresponding to the first information to a terminal device within the multicast group corresponding to the first information. The terminal device can obtain the first information based on the assigned group identifier, thereby improving the accuracy of obtaining the first information.

[0147] In one possible implementation, the terminal device can monitor and obtain the first information based on the configuration information related to the multicast of the AI ​​algorithm model.

[0148] In this implementation, after the terminal device obtains the third information indicated by the network device, it can monitor the first information based on the configuration information related to the multicast of the AI ​​algorithm model until the first information is obtained. In the case where the third information indicates that the allocated configuration information related to the multicast of the AI ​​algorithm model includes one or more of RRC parameters, channel resources for multicast, bearer resources for multicast, air interface resources for multicast, and security parameters for data security, the terminal device can monitor the first information based on the one or more parameters. In the case where the third information indicates that the allocated configuration information related to the multicast of the AI ​​algorithm model includes the group identifier of the multicast group corresponding to the first information, the terminal device can monitor the first information based on the allocated group identifier until the first information containing the group identifier is obtained.

[0149] Optionally, when the configuration information related to the multicast of the AI ​​algorithm model includes the group identifier of the multicast group corresponding to the first information, the configuration information may also include an effective time range of the group identifier. The network device allocates the group identifier of the multicast group corresponding to the first information and the effective time range of the group identifier to the terminal device in the multicast group corresponding to the first information in advance through the third information. The terminal device can obtain the first information within the effective time range of the group identifier based on the allocated group identifier and the group identifier in the first information, thereby reducing the complexity of the terminal device monitoring the first information through the effective time range.

[0150] In an embodiment of the present application, a terminal device reports its own algorithmic capabilities related to the AI ​​algorithm model to a network device. Based on the algorithmic capabilities of the terminal device, the network device allocates appropriate configuration information related to the multicast of the AI ​​algorithm model to the terminal device. Based on the configuration information, the terminal device obtains the first information multicasted by the network device and obtains the model data of the AI ​​algorithm model from the first information. In this way, by reporting the algorithmic capabilities, the rationality and accuracy of the configuration information allocation are improved, so that terminal devices with the same algorithmic capabilities can obtain the model data of the same AI algorithm model multicast, avoiding or reducing the repeated transmission of the AI ​​algorithm model and saving air interface resources.

[0151] As an example, after accessing the cell corresponding to the network device, the terminal device may report to the network device the algorithm capabilities related to the AI ​​algorithm model that it supports. After receiving the algorithm capabilities reported by the terminal device, the network device may configure the terminal device with one or more parameters including RRC parameters, channel resources for multicast, bearer resources for multicast, air interface resources for multicast, and security parameters for data security based on the algorithm capabilities of the terminal device. The terminal device may also allocate a group identifier to the terminal device. The group identifier is used to represent a multicast group. The same group identifier is allocated to terminal devices with the same algorithm capabilities, so that terminal devices with the same algorithm capabilities are located in the same multicast group. Terminal devices with the same algorithm capabilities can obtain model data of the same AI algorithm model through multicast, such as placing all terminal devices that support beam management through the AI ​​algorithm model into the same multicast group, and placing all terminal devices that support CSI feedback enhancement through the AI ​​algorithm model into the same multicast group. After obtaining the allocated group identifier, the terminal device can continuously monitor the first multicast information on the PDCCH based on the configured parameters and the allocated group identifier.

[0152] FIG5 is a schematic diagram of a model transmission method provided by another embodiment of the present application. As shown in FIG5 , the model transmission method provided by this embodiment includes:

[0153] S501, the terminal device sends second information, where the second information is used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device.

[0154] S502, the network device indicates third information, where the third information is used to distribute configuration information related to multicast of the AI ​​algorithm model.

[0155] The implementation principles and technical effects of S501 and S502 may refer to the aforementioned embodiments and will not be described in detail.

[0156] S503, the network device indicates the fourth information, and the fourth information is used for one or more of the following: allocating the group identifier of the multicast group corresponding to the first information, indicating the effective time range of the group identifier, indicating the index corresponding to the bearer resource information used for multicast, activating the monitoring group identifier, and deactivating the monitoring group identifier.

[0157] The group identifier of the multicast group corresponding to the first information may refer to the above embodiment and will not be described in detail.

[0158] Among them, the group identifier is valid within the effective time range. Within the effective time range of the group identifier, the terminal device can obtain the first information based on the assigned group identifier and the group identifier indicated by the first information. Outside the effective time range of the group identifier, the group identifier cannot be used to obtain the first information. The effective time range of the group identifier can be indicated by the third information or the fourth information, which is equivalent to the network device providing the terminal device with a time range for monitoring the first information. The terminal device monitors the first information within the effective time range of the group identifier, and does not need to monitor the first information after receiving the third information or the fourth information. This reduces the complexity of the terminal device in obtaining the first information and improves the transmission efficiency of the AI ​​algorithm model.

[0159] Among them, when the third information indicates that the allocated configuration information includes bearer resources for multicast, the fourth information can be used to indicate the index corresponding to the bearer resource information for multicast. Compared with indicating the bearer resources for multicast in the fourth information, indicating the index corresponding to the bearer resource information for multicast can reduce the amount of information in the fourth information.

[0160] Exemplarily, the bearer resource used for multicast is a radio bearer (RB) used for multicast, and the third information indicates the RB used for multicast. The fourth information may indicate an index corresponding to the RB, i.e., the RB number. Furthermore, if the third information indicates an SRB used for multicast, the fourth information may indicate an index corresponding to the SRB, i.e., the SRB number.

[0161] Among them, when the fourth information indicates to activate the monitoring group identifier, the terminal device can start to monitor the group identifier after obtaining the fourth information; when the fourth information indicates to deactivate the monitoring group identifier, the terminal device can stop monitoring the group identifier after obtaining the fourth information, thereby controlling the terminal device to start or stop monitoring the group identifier in a timely manner through the fourth information.

[0162] In this embodiment, the network device can determine one or more of the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast, and generate fourth information based on the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast, and indicate the fourth information to the terminal device to configure the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast to the terminal device, and / or activate the monitoring group identifier to the terminal device or deactivate the monitoring group identifier.

[0163] Among them, S503 is an optional step.

[0164] Optionally, the third information indicates that the allocated configuration information includes the group identifier of the multicast group corresponding to the first information, or the third information indicates that the allocated configuration information includes the group identifier of the multicast group corresponding to the first information and the effective time range corresponding to the group identifier, and the network device may not indicate the fourth information. After obtaining the third information, the terminal device may monitor the first information based on one or more of the RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, and security parameters for data security, as well as the group identifier and the effective time range of the group identifier in the configuration information allocated as indicated by the third information.

[0165] Optionally, the third information indicates that the allocated configuration information includes a group identifier of the multicast group corresponding to the first information, and the fourth information can be used to indicate the effective time range of the group identifier and / or indicate the index corresponding to the bearer resource information used for multicast. Wherein, in the case where the fourth information is used to indicate the effective time range of the group identifier, after the terminal device obtains the fourth information, the terminal device can monitor the first information within the effective time range of the group identifier based on the configuration information allocated by the third information; in the case where the fourth information is used to indicate the index corresponding to the bearer resource information used for multicast, after the terminal device obtains the fourth information, the terminal device can monitor the first information based on the configuration information allocated by the third information and the index corresponding to the bearer resource information used for multicast; in the case where the fourth information is used to indicate the effective time range of the group identifier and the index corresponding to the bearer resource information used for multicast, after the terminal device obtains the fourth information, the terminal device can monitor the first information within the effective time range of the group identifier based on the configuration information allocated by the third information and the index corresponding to the bearer resource information used for multicast.

[0166] Optionally, the third information indicates that the allocated configuration information contains the group identifier of the multicast group corresponding to the first information, and the fourth information can be used to indicate activation or deactivation of listening to the group identifier, so as to activate or deactivate the terminal device to listen to the group identifier, so as to control the terminal device to promptly start or stop listening to the group identifier.

[0167] Optionally, the third information indicates that the allocated configuration information does not contain the group identifier of the multicast group corresponding to the first information, and the fourth information can be used to indicate the group identifier of the multicast group corresponding to the first information. After obtaining the fourth information, the terminal device can monitor the first information based on the configuration information allocated as indicated by the third information and the group identifier allocated as indicated by the fourth information.

[0168] Optionally, the third information indicates that the allocated configuration information does not contain the group identifier of the multicast group corresponding to the first information, and the fourth information can be used to indicate the group identifier of the multicast group corresponding to the first information and the effective time range of the group identifier. After obtaining the fourth information, the terminal device can monitor the first information within the effective time range of the group identifier based on the configuration information allocated as indicated by the third information and the group identifier allocated as indicated by the fourth information.

[0169] Optionally, the third information indicates that the allocated configuration information does not contain the group identifier of the multicast group corresponding to the first information, and the fourth information can be used to allocate the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast. After obtaining the fourth information, the terminal device can monitor the first information within the effective time range of the group identifier based on the configuration information allocated as indicated by the third information, the group identifier allocated as indicated by the fourth information, and the index corresponding to the bearer resource information for multicast as indicated by the fourth information.

[0170] Optionally, the network device indicates the fourth information through a MAC control element (CE) and / or through downlink control information (DCI) of a PDCCH. The terminal device may obtain the fourth information through a MAC CE and / or PDCCH DCI. Thus, the fourth information is transmitted through a MAC CE and / or PDCCH DCI, thereby improving the accuracy and efficiency of the transmission of the fourth information.

[0171] Exemplarily, the network device may use the cell-radio network temporary identifier (C-RNTI) corresponding to the terminal device to schedule MAC CE and / or PDCCH DCI. In other words, MAC CE and / or PDCCH DCI may be scheduled for transmission using the C-RNTI corresponding to the terminal device in the connected state. The MAC CE and / or PDCCH DCI may include the C-RNTI, the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast; the terminal device may use the C-RNTI and the group identifier to monitor and obtain the MAC CE and / or PDCCH DCI. Among them, C-RNTI is a cell-level identifier. Different terminal devices in a cell may correspond to different C-RNTIs, that is, an ID that uniquely identifies the user within the cell range in a cell. The network device schedules MAC CE through C-RNTI, and can accurately configure the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, and the index corresponding to the bearer resource information for multicast to the corresponding terminal device.

[0172] S504, the network device multicasts the first information according to the group identifier of the multicast group corresponding to the first information, the effective time range of the group identifier, one or more indexes corresponding to the bearer resource information used for multicast, and configuration information related to the multicast of the AI ​​algorithm model.

[0173] S505: The terminal device monitors the first information, and obtains model data of the AI ​​algorithm model from the first information obtained through monitoring.

[0174] In one embodiment, the network device can multicast the first information based on the group identifier of the multicast group corresponding to the first information and the configuration information related to the multicast of the AI ​​algorithm. The first information is used to indicate the group identifier and the model data of the AI ​​algorithm model. The terminal device can monitor the first information based on the group identifier and the configuration information and obtain the model data of the AI ​​algorithm model from the first information.

[0175] In another approach, the network device may multicast the first information within the effective time range of the group identifier based on the group identifier of the multicast group corresponding to the first information and the configuration information related to the multicast of the AI ​​algorithm. The terminal device may monitor the first information within the effective time range of the group identifier based on the group identifier and the configuration information, and obtain the model data of the AI ​​algorithm model from the first information. Because this approach provides an effective time range, the terminal device only needs to monitor the first information within the effective time range, reducing the complexity of monitoring the first information on the terminal device side and improving efficiency.

[0176] In another embodiment, the network device can multicast the first information based on the group identifier of the multicast group corresponding to the first information, the index corresponding to the bearer resource information used for multicast, and the configuration information related to the multicast of the AI ​​algorithm model. The terminal device can monitor the first information based on the group identifier, the index and the configuration information, and obtain the model data of the AI ​​algorithm model from the first information.

[0177] In another embodiment, the network device can multicast the first information within the effective time range of the group identifier based on the group identifier of the multicast group corresponding to the first information, the index corresponding to the bearer resource information used for multicast, and the configuration information related to the multicast of the AI ​​algorithm model. The terminal device can monitor the first information within the effective time range of the group identifier based on the group identifier, the index, and the configuration information, and obtain the model data of the AI ​​algorithm model from the first information. Since this method provides an effective time range, the terminal device only needs to monitor the first information within the effective time range, which reduces the complexity of monitoring the first information on the terminal device side and improves efficiency.

[0178] The above method can be combined with the optional solutions below step S503, which will not be described in detail.

[0179] In an embodiment of the present application, the terminal device reports its own algorithm capabilities related to the AI ​​algorithm model to the network device. Based on the algorithm capabilities of the terminal device, the network device allocates appropriate configuration information related to the multicast of the AI ​​algorithm model to the terminal device through the third information; the network device may also indicate the fourth information to the terminal device, indicating one or more of the group identifier, the effective time range of the group identifier, the index corresponding to the bearer resource information for multicast, the activation monitoring group identifier, and the deactivation monitoring group identifier through the fourth information. If the fourth information is not indicated, the terminal device can monitor the first information after the third information; if the fourth information is indicated and the fourth information does not indicate the effective time range, the terminal device can activate or deactivate the monitoring of the first information after the fourth information; if the fourth information is indicated and the fourth information indicates the effective time range, the terminal device can monitor the first information within the effective time range. In this way, multiple solutions for transmitting AI algorithm models through multicast are provided, and the terminal device can also avoid constantly monitoring the first information by indicating the effective time range, thereby improving the transmission efficiency of the AI ​​algorithm model.

[0180] Optionally, the multicast group corresponding to the first information includes terminal devices in a connected state and / or terminal devices in an inactive state. It is understandable that any of the above embodiments can be applied to terminal devices in a connected state or in an inactive state, thereby multicasting the AI ​​algorithm model to terminal devices in a connected state and / or in an inactive state, reducing or avoiding repeated transmission of the AI ​​algorithm model and saving air interface resources.

[0181] Optionally, for terminal devices in an inactive state, the network device may indicate fifth information at a paging time within a RAN-based notification area before multicasting the first information. The fifth information is used to wake up the terminal device in an inactive state and / or instruct to multicast the AI ​​algorithm model. When the fifth information is used to instruct to multicast the model data of the AI ​​algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information. The terminal device in an inactive state obtains the fifth information at a paging time. Thus, for a terminal device in an inactive state, the network device indicates the fifth information at a paging time to wake up the terminal device and / or inform the terminal device that the network device is preparing to multicast the model data of the AI ​​algorithm model, so that the terminal device in an inactive state can receive the first information in a timely manner, thereby improving the success rate of multicasting the AI ​​algorithm model to the terminal device in an inactive state.

[0182] Optionally, after obtaining the fifth information during the paging period, the terminal device in the inactive state may send an RRC recovery establishment request message to request migration from the inactive state to the connected state, so as to obtain the first information in the connected state, that is, obtain the AI ​​algorithm model transmitted by the network device through multicast in the connected state, thereby improving the success rate of the AI ​​algorithm model transmission.

[0183] Optionally, the RRC recovery establishment request message sent by the terminal device in the inactive state carries indication information, and the indication information is used to indicate that the terminal device supports receiving model data of the AI ​​algorithm model, so that the network device knows in time that the terminal device in the inactive state is ready to receive model data of the AI ​​algorithm model. After obtaining the RRC recovery establishment request message, the network device can multicast the first information to improve the success rate of AI algorithm model transmission.

[0184] Optionally, for a terminal device in an inactive state, the network device may indicate third information before the terminal device migrates from a connected state to an inactive state. The third information may be described with reference to the description of the aforementioned embodiment and will not be repeated here. The network device indicates the third information before the terminal device migrates from a connected state to an inactive state, so as to configure the configuration information related to the multicast of the AI ​​algorithm model to the terminal device in advance; after the terminal device obtains the third information, it may save the configuration information related to the multicast of the AI ​​algorithm model, and after migrating from a connected state to an inactive state, it may also obtain the first information based on the configuration information.

[0185] Optionally, in the case where the network device indicates third information before the terminal device migrates from the connected state to the inactive state, the third information may be an RRC connection release message used to instruct the terminal device to migrate from the connected state to the inactive state, so as to complete the state migration instruction of the terminal device and the allocation of configuration information related to the multicast of the AI ​​algorithm model through the RRC release message; or, the third information may be an RRC message other than the RRC connection release message obtained by the terminal device in the connected state. Thus, after migrating to the inactive state, the terminal device can also obtain the first information broadcast by the network device based on the configuration information.

[0186] FIG6 is a schematic diagram of a model transmission method provided by another embodiment of the present application. As shown in FIG6 , the model transmission method provided by this embodiment includes:

[0187] S601, the terminal device sends second information in a connected state, where the second information is used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device.

[0188] S602, the network device indicates third information, where the third information is used to distribute configuration information related to multicast of the AI ​​algorithm model.

[0189] Optionally, the third information is an RRC release message instructing the terminal device to migrate from a connected state to an inactive state, or an RRC message other than the RRC connection release message obtained by the terminal device in the connected state.

[0190] Optionally, the network device may further indicate fourth information.

[0191] Among them, the relevant contents of the second information, the third information, and the fourth information can refer to the aforementioned embodiments and will not be repeated here.

[0192] S603: The terminal device saves configuration information related to the multicast of the AI ​​algorithm model.

[0193] S604: The terminal device migrates from the connected state to the inactive state.

[0194] The execution order between S603 and S604 is not limited.

[0195] S605: The network device indicates fifth information during paging within the RAN-based notification area. The fifth information is used to wake up an inactive terminal device and / or instruct multicast of an AI algorithm model.

[0196] Wherein, when the fifth information is used to instruct multicasting of the AI ​​algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information. The relevant content of the fifth information can be referred to the above embodiment and will not be repeated here.

[0197] S606: The terminal device sends an RRC recovery establishment request message to request migration from the inactive state to the connected state.

[0198] Optionally, the RRC recovery establishment request message carries indication information, which is used to indicate that the terminal device supports receiving model data of the AI ​​algorithm model. For details, please refer to the above embodiment and will not be repeated here.

[0199] S607, the network device multicasts first information, where the first information is used to indicate model data of the AI ​​algorithm model and / or a model identifier of the AI ​​algorithm model.

[0200] S608, the terminal device obtains the first multicast information, and obtains the model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model from the first information.

[0201] Among them, S601 to S606 are optional steps. The terminal device can monitor the first information in an inactive state.

[0202] The implementation principles and technical effects of S601 to S608 may refer to the aforementioned embodiments and will not be described in detail.

[0203] In an embodiment of the present application, a process for implementing the propagation of an AI algorithm model by multicasting between a network device and an inactive terminal device is provided. The network device can configure corresponding parameters for the terminal device before the terminal device switches to the inactive state. After the terminal device switches to the inactive state, the network device can wake up the terminal device and / or remind the terminal device to prepare for multicasting of the model data of the AI ​​algorithm model during a paging period. The model data of the AI ​​algorithm model is then transmitted to the terminal device by multicasting the first information. In this way, repeated transmission of the AI ​​algorithm model is reduced or avoided, saving air interface resources.

[0204] FIG7 is a schematic diagram of a model transmission method provided by another embodiment of the present application. As shown in FIG7 , the model transmission method provided by this embodiment includes:

[0205] S701, the network device multicasts first information, where the first information is used to indicate model data of the AI ​​algorithm model.

[0206] S702, the terminal device obtains the first multicast information, and obtains model data of the AI ​​algorithm model from the first information.

[0207] The implementation principles and technical effects of S701 and S702 can be referred to the aforementioned embodiments and will not be described in detail.

[0208] S703, when the data packet transmission corresponding to the model data of the AI ​​algorithm model fails, the terminal device sends sixth information, and the sixth information is used to indicate that the data packet transmission corresponding to the model data of the AI ​​algorithm model fails.

[0209] Among them, the model data of the AI ​​algorithm model is transmitted in the form of one or more data packets.

[0210] Exemplarily, the transmission of the data packet corresponding to the model data of the AI ​​algorithm model fails, for example, the terminal device fails to obtain the first information, or the terminal device successfully obtains part of the data packet from the first information, or errors occur in part of the data packet corresponding to the model data of the AI ​​algorithm model during transmission.

[0211] Among them, the sixth information can be used to indicate the identification information of the data packet that failed to be transmitted (such as the model identification of the AI ​​algorithm model and the position identification of the data packet that failed to be transmitted in the model data of the AI ​​algorithm model).

[0212] Optionally, the sixth information is also used to indicate a device identifier (such as C-RNTI) of the terminal device, so that the network device can determine the terminal device where data transmission failure occurs in a multicast scenario.

[0213] In this embodiment, if the terminal device fails to transmit the data packet corresponding to the model data of the AI ​​algorithm model, the terminal device may send sixth information to the network device to inform the network device of the data packet transmission failure.

[0214] S704: The network device retransmits the data packet on the unicast channel corresponding to the terminal device.

[0215] In this embodiment, after the network device obtains the sixth information, it can retransmit the data packet that failed to be transmitted on the unicast channel corresponding to the terminal device where the data packet transmission failed, without having to re-multicast the model data of the AI ​​algorithm model, thereby avoiding re-multicasting the model data of the AI ​​algorithm model to occupy more air interface resources.

[0216] In an embodiment of the present application, in the event of a data packet failure in the model data of the AI ​​algorithm model, the failed data packet can be retransmitted on the unicast channel corresponding to the terminal device to save air interface resources.

[0217] The model transmission method of the embodiment of the present application has been described above. The device for executing the above method provided by the embodiment of the present application is described below. Those skilled in the art will understand that the method and device can be combined and referenced with each other, and the relevant device provided by the embodiment of the present application can perform the steps in the above-mentioned list sorting method.

[0218] FIG8 is a schematic diagram of a network device provided in an embodiment of the present application. As shown in FIG8 , the network device 80 includes: a multicast module 81 .

[0219] Among them, the multicast module 81 is used to multicast the first information, and the first information is used to indicate the model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model.

[0220] In an optional embodiment, the network device also includes: an algorithm capability acquisition module (not shown) for acquiring second information, the second information being used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; a configuration module (not shown) for indicating third information, the third information being used to allocate configuration information related to multicast of the AI ​​algorithm model.

[0221] In an optional embodiment, the configuration information related to the multicast of the AI ​​algorithm model includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is scheduled for transmission through the group identifier.

[0222] In an optional embodiment, the configuration module is also used to: indicate fourth information, and the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating the effective time range of the group identifier, indicating the index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, and deactivating monitoring of the group identifier.

[0223] In an optional embodiment, the configuration module, in the process of indicating the fourth information, is specifically configured to: indicate the fourth information through MAC CE and / or PDCCH DCI.

[0224] In an optional embodiment, the multicast group corresponding to the first information includes terminal devices in a connected state and / or terminal devices in an inactive state.

[0225] In an optional embodiment, for a terminal device in an inactive state, the network device further includes: a first indication module (not shown), which is used to indicate fifth information at a paging time within a RAN-based notification area, and the fifth information is used to wake up the terminal device in an inactive state and / or indicate the multicast of the AI ​​algorithm model. When the fifth information is used to indicate the multicast of the AI ​​algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information.

[0226] In an optional embodiment, for a terminal device in an inactive state, the network device further includes: a second indication module (not shown), configured to indicate third information before the terminal device migrates from a connected state to an inactive state.

[0227] In an optional embodiment, the third information is an RRC release message used to instruct the terminal device to migrate from a connected state to an inactive state, or the third information is other RRC messages other than the RRC connection release message obtained by the terminal device in the connected state.

[0228] In an optional embodiment, the network device also includes a retransmission module (not shown), which is used to: obtain sixth information, where the sixth information is used to indicate that the data packet corresponding to the model data of the AI ​​algorithm model has failed to be transmitted; and retransmit the data packet on the unicast channel corresponding to the terminal device where the data packet transmission failed.

[0229] In an optional embodiment, the multicast module 81 is configured to multicast the first information in a manner of multicasting user plane data or multicasting signaling. In this embodiment, two multicasting methods of the first information are provided.

[0230] In an optional embodiment, the multicast range of the first information includes one or more of the following: the cell where the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device.

[0231] The network device provided in this embodiment is used to implement the technical solution of the network device in the aforementioned method embodiment. Its implementation principle and technical effects are similar and will not be described in detail here.

[0232] FIG9 is a schematic diagram of a terminal device provided in an embodiment of the present application. As shown in FIG9 , the terminal device 90 includes an information acquisition module 91 and a model data acquisition module 92 .

[0233] Among them, the information acquisition module 91 is used to obtain the first multicast information, and the first information is used to indicate the model data of the AI ​​algorithm model and / or the model identifier of the AI ​​algorithm model; the model data acquisition module 92 is used to obtain the model data and / or the model identifier from the first information.

[0234] In an optional embodiment, the terminal device also includes: a first sending module (not shown) for sending second information, the second information is used to indicate the algorithm capabilities related to the AI ​​algorithm model supported by the terminal device; the information acquisition module 91 is also used to: obtain third information, the third information is used to allocate configuration information related to the multicast of the AI ​​algorithm model.

[0235] In an optional embodiment, the configuration information related to the multicast of the AI ​​algorithm model also includes one or more of the following: RRC parameters, channel resources for multicast, bearer resources for multicast, air interface resources for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is scheduled for transmission through the group identifier.

[0236] In an optional embodiment, the information acquisition module 91 is specifically used to: monitor and obtain the first information according to the configuration information related to the multicast of the AI ​​algorithm model.

[0237] In an optional embodiment, the information acquisition module 91 is also used to: obtain fourth information, the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating the effective time range of the group identifier, indicating the index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, deactivating monitoring of the group identifier, and the first information is scheduled for transmission through the group identifier.

[0238] In an optional embodiment, the information acquisition module 91 is specifically configured to acquire the fourth information through MAC CE and / or PDCCH DCI during the process of acquiring the fourth information.

[0239] In an optional embodiment, the terminal device is in a connected state or an inactive state.

[0240] In an optional embodiment, when the terminal device is in an inactive state, the information acquisition module 91 is also used to: obtain fifth information at the paging time, the fifth information is used to wake up the terminal device in the inactive state and / or instruct to perform multicast of the AI ​​algorithm model, and when the fifth information is used to instruct to perform multicast of the AI ​​algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information.

[0241] In an optional embodiment, the terminal device further includes: a second sending module (not shown), configured to send an RRC recovery establishment request message to request migration from an inactive state to a connected state.

[0242] In an optional embodiment, the RRC recovery establishment request message carries indication information, which is used to indicate that the terminal device supports receiving model data of the AI ​​algorithm model.

[0243] In an optional embodiment, the information acquisition module 91 is specifically configured to acquire the third information before the terminal device transitions from a connected state to an inactive state during the process of acquiring the third information.

[0244] In an optional embodiment, the third information is an RRC release message used to instruct the terminal device to migrate from a connected state to an inactive state, or the third information is other RRC messages other than the RRC connection release message obtained by the terminal device in the connected state.

[0245] In an optional embodiment, the terminal device further includes a retransmission module (not shown), which is used to: send sixth information, where the sixth information is used to indicate that the data packet corresponding to the model data has failed to be transmitted; and obtain the retransmitted data packet on the unicast channel corresponding to the terminal device.

[0246] In an optional embodiment, the first information is multicast in the form of multicast user plane data or multicast signaling.

[0247] In an optional embodiment, the multicast range of the first information includes one or more of the following: the cell where the network device is located, a configured cell list, a RAN-based notification area, and a TA corresponding to the terminal device.

[0248] The terminal device provided in this embodiment is used to implement the technical solution of the terminal device in the aforementioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0249] It should be noted that the module names involved in the embodiments of the present application can be defined as other names as long as the functions of each module can be achieved, and there is no specific restriction on the names of the modules.

[0250] Figure 10 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in Figure 10, the electronic device 1000 includes: at least one processor 1001, a memory 1002, a communication interface 1003, and a system bus 1004. Among them, the memory 1002 and the communication interface 1003 are connected to the processor 1001 via the system bus 1004 and complete communication with each other. The memory 1002 is used to store instructions, the communication interface 1003 is used to communicate with other devices, and the processor 1001 is used to call instructions in the memory to execute the method steps provided in the above method embodiment. The specific implementation method and technical effects are similar and will not be repeated here.

[0251] The system bus 1004 mentioned in FIG10 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The system bus 1004 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the figure shows only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0252] The communication interface 1003 is used to implement communication between the database access apparatus and other devices (such as a client, a read-write library, and a read-only library).

[0253] The memory 1002 may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0254] Processor 1001 can be a general-purpose processor, including a central processing unit, a network processor (NP), etc.; a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0255] The embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, it is used to implement the method steps in the above method embodiment. The method described in the above embodiment can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. If implemented in software, the function can be stored as one or more instructions or codes on a computer-readable medium or transmitted on a computer-readable medium. Computer-readable media can include computer storage media and communication media, and can also include any medium that can transfer a computer program from one place to another. The storage medium can be any target medium that can be accessed by a computer.

[0256] In one possible implementation, computer-readable media may include RAM, ROM, compact disc read-only memory (CD-ROM) or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium designed to carry or store the desired program code in the form of instructions or data structures and accessible by a computer. Furthermore, any connection is appropriately referred to as a computer-readable medium. For example, if software is transmitted from a website, server or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technologies such as infrared, radio and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of medium. Disk and disc as used herein include optical disc, laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while optical discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0257] The present application also provides a computer program product, which includes a computer program. When the computer program is executed, the computer executes the method steps in the above method embodiment.

[0258] An embodiment of the present application also provides a chip system, including at least one processor and a communication interface, the communication interface and the at least one processor are interconnected through lines, and the at least one processor is used to run computer programs or instructions to execute the method steps in the above method embodiment.

[0259] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0260] The present application embodiment is described with reference to the flow chart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present application.It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processing unit of general-purpose computer, special-purpose computer, embedded processing machine or other programmable device to produce a machine, so that the instruction executed by the processing unit of computer or other programmable data processing device produces the device for realizing the function specified in one flow chart flow or multiple flows and / or one block or multiple blocks of block diagram.

[0261] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the present invention should be included in the scope of protection of the present invention.

Claims

1. A model transmission method, characterized in that: include: Multicast first information, where the first information is used to indicate model data of an artificial intelligence (AI) algorithm model and / or a model identifier of the AI algorithm model.

2. The method according to claim 1, characterized in that Before the multicast first information, the method further includes: Obtaining second information, where the second information is used to indicate algorithm capabilities related to the AI algorithm model supported by the terminal device; Indicates third information, where the third information is used to allocate configuration information related to the multicast of the AI algorithm model.

3. The method according to claim 2, characterized in that The configuration information includes one or more of the following: wireless resource control RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is scheduled for transmission via the group identifier.

4. The method according to claim 2 or 3, characterized in that After indicating the third information, the method further includes: Indicates fourth information, where the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating an effective time range of the group identifier, indicating an index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, and deactivating monitoring of the group identifier, and the first information is scheduled for transmission via the group identifier.

5. The method according to claim 4, characterized in that The fourth indication information includes: The fourth information is indicated by a control element CE of a medium access control MAC and / or by downlink control information DCI of a physical downlink control channel PDCCH.

6. The method according to any one of claims 2 to 5, characterized in that The multicast group corresponding to the first information includes terminal devices in a connected state and / or terminal devices in an inactive state.

7. The method according to claim 6, characterized in that For a terminal device in an inactive state, before multicasting the first information, the method further includes: Within the notification area based on the radio access network RAN, the fifth information is indicated at the paging occasion, and the fifth information is used to wake up the terminal device in the inactive state and / or instruct the multicast of the AI algorithm model. When the fifth information is used to instruct the multicast of the AI algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information.

8. The method according to claim 6 or 7, characterized in that For inactive terminal devices, it also includes: Before the terminal device migrates from the connected state to the inactive state, the third information is indicated.

9. The method according to claim 8, characterized in that The third information is an RRC connection release message used to instruct the terminal device to migrate from a connected state to an inactive state, or the third information is other RRC messages other than the RRC connection release message obtained by the terminal device in the connected state.

10. The method according to any one of claims 1 to 9, characterized in that After the multicast first information, the method further includes: Acquire sixth information, where the sixth information is used to indicate that transmission of a data packet corresponding to the model data fails; The data packet is retransmitted on the unicast channel corresponding to the terminal device where the data packet transmission fails.

11. The method according to any one of claims 1 to 10, characterized in that The multicast range of the first information includes one or more of the following: the cell where the network device is located, a configured cell list, a notification area based on RAN, and a tracking area TA corresponding to the terminal device.

12. A model transmission method, characterized in that: include: Acquire first multicast information, where the first information is used to indicate model data of an AI algorithm model and / or a model identifier of the AI algorithm model; The model data and / or the model identifier are obtained from the first information.

13. The method according to claim 12, characterized in that Before acquiring the first multicast information, the method further includes: Sending second information, where the second information is used to indicate algorithm capabilities related to the AI algorithm model supported by the terminal device; Obtain third information, where the third information is used to allocate configuration information related to the multicast of the AI algorithm model.

14. The method according to claim 13, characterized in that The configuration information includes one or more of the following: RRC parameters, channel resource information for multicast, bearer resource information for multicast, air interface resource information for multicast, security parameters for data security, and the group identifier of the multicast group corresponding to the first information, and the first information is scheduled for transmission via the group identifier.

15. The method according to claim 13 or 14, characterized in that The obtaining of the first multicast information includes: The first information is obtained by monitoring according to the configuration information.

16. The method according to any one of claims 13 to 15, characterized in that After obtaining the third information, the method further includes: Obtain fourth information, where the fourth information is used for one or more of the following: allocating a group identifier of the multicast group corresponding to the first information, indicating an effective time range of the group identifier, indicating an index corresponding to the bearer resource information used for multicast, activating monitoring of the group identifier, and deactivating monitoring of the group identifier. The first information is scheduled for transmission via the group identifier.

17. The method according to claim 16, characterized in that The obtaining of the fourth information includes: The fourth information is acquired through MAC CE and / or PDCCH DCI.

18. The method according to any one of claims 13 to 17, characterized in that The terminal device is in a connected state or an inactive state. When the terminal device is in an inactive state, before obtaining the first information, the method further includes: The fifth information is obtained at the paging occasion, and the fifth information is used to wake up the terminal device in the inactive state and / or instruct the multicast of the AI algorithm model. When the fifth information is used to instruct the multicast of the AI algorithm model, the fifth information includes the group identifier of the multicast group corresponding to the first information.

19. The method according to claim 18, characterized in that After acquiring the fifth information at the paging occasion, the method further includes: Send an RRC recovery establishment request message to request migration from the inactive state to the connected state.

20. The method according to claim 19, characterized in that The RRC recovery establishment request message carries indication information, and the indication information is used to indicate that the terminal device supports receiving the model data.

21. The method according to any one of claims 13 to 20, characterized in that The obtaining of the third information includes: Before the terminal device migrates from the connected state to the inactive state, the third information is obtained, where the third information is an RRC connection release message used to instruct the terminal device to migrate from the connected state to the inactive state, or the third information is other RRC messages other than the RRC connection release message obtained by the terminal device in the connected state.

22. The method according to any one of claims 12 to 21, characterized in that Also includes: Sending sixth information, where the sixth information is used to indicate that the data packet corresponding to the model data has failed to be transmitted; The retransmitted data packet is obtained on the unicast channel corresponding to the terminal device.

23. The method according to any one of claims 12 to 22, characterized in that The multicast range of the first information includes one or more of the following: the cell where the network device is located, the configured cell list, the RAN-based notification area, and the TA corresponding to the terminal device.

24. An electronic device, characterized in that: include: processor and memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 11, or the electronic device performs the method according to any one of claims 12 to 23.

25. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 11 is implemented; or when the computer program is executed by a processor, the method according to any one of claims 12 to 23 is implemented.

26. A chip system, characterized in that: The method comprises at least one processor and a communication interface, wherein the communication interface and the at least one processor are interconnected via a line, and the at least one processor is used to run a computer program or instruction to execute the method according to any one of claims 1 to 11, or to execute the method according to any one of claims 12 to 23.

27. A computer program product, characterized in that The invention comprises a computer program, which, when being executed, causes a computer to execute the method according to any one of claims 1 to 11, or causes a computer to execute the method according to any one of claims 12 to 23.

Images