Communication method and communication device

Abstract

The present application relates to a communication method. The method comprises: a first communication device sending indication information, which is used for indicating auxiliary information corresponding to a target model. In the embodiments of the present application, a first communication device sends auxiliary information of a target model, which is conducive to ensuring the consistency of understanding, with respect to a model, of a transmitting end and a receiving end for the model, thereby ensuring normal use of the model.

Description

Communication method and communication device Technical Field

[0001] The present application relates to the field of communications, and more specifically, to a communication method and a communication device. Background Art

[0002] Artificial Intelligence (AI)-based solutions are increasingly being used in wireless communication systems. For example, AI can be used to implement Channel State Information (CSI) feedback and CSI prediction. When considering model transmission issues, if the transmitter and receiver have inconsistent understandings of the transmission model, the model transmitted by the transmitter may be unusable at the receiver.

[0003] Summary of the Invention

[0004] The embodiments of the present application provide a communication method and a communication device that can complete the conversion, update, and use of model versions.

[0005] An embodiment of the present application provides a communication method, including:

[0006] The first communication device sends indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0007] An embodiment of the present application provides a communication method, including:

[0008] The second communication device receives indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0009] An embodiment of the present application provides a first communication device, including:

[0010] The sending unit is used to send indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0011] An embodiment of the present application provides a second communication device, including:

[0012] The receiving unit is used to receive indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0013] An embodiment of the present application provides a communication device, comprising: a transceiver, a processor, and a memory. The memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and execute the computer program stored in the memory so that the communication device performs the above-mentioned communication method.

[0014] An embodiment of the present application provides a chip for implementing the above-mentioned communication method.

[0015] Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the chip executes the above-mentioned communication method.

[0016] An embodiment of the present application provides a computer-readable storage medium for storing a computer program, which, when executed by a device, enables the device to execute the above-mentioned communication method.

[0017] An embodiment of the present application provides a computer program product, including computer program instructions, which enable a computer to execute the above-mentioned communication method.

[0018] An embodiment of the present application provides a computer program, which, when executed on a computer, enables the computer to execute the above-mentioned communication method.

[0019] In the embodiment of the present application, the first communication device sends auxiliary information of the target model, which is conducive to ensuring that the sending and receiving ends of the model have a consistent understanding of the model and ensures the normal use of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] FIG1 is a schematic diagram of an application scenario according to an embodiment of the present application.

[0021] 2a to 2d are schematic diagrams of applications based on AI in wireless communication systems.

[0022] FIG3 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0023] FIG4 a is a schematic flowchart of a communication method according to an embodiment of the present application.

[0024] FIG4b and FIG4c are schematic flow charts of the interaction between the UE and the base station in the communication method according to FIG4a.

[0025] FIG5 a is a schematic flowchart of a communication method according to an embodiment of the present application.

[0026] FIG5b and FIG5c are schematic flow charts of the interaction between the UE and the base station in the communication method according to FIG5a.

[0027] FIG6 a is a schematic flowchart of a communication method according to an embodiment of the present application.

[0028] FIG6b , FIG6c , FIG6d and FIG6e are schematic flow charts of the interaction between the UE and the base station in the communication method according to FIG6a .

[0029] FIG7 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0030] FIG8 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0031] FIG9 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0032] FIG10 is a schematic flowchart of a communication method according to an embodiment of the present application.

[0033] 11 and 12 are flowcharts according to Example 1 of the present application.

[0034] 13 and 14 are flowcharts according to Example 2 of the present application.

[0035] FIG15 is a schematic block diagram of a first communication device according to an embodiment of the present application.

[0036] FIG16 is a schematic block diagram of a second communication device according to an embodiment of the present application.

[0037] FIG17 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0038] FIG18 is a schematic block diagram of a chip according to an embodiment of the present application.

[0039] FIG19 is a schematic block diagram of a communication system according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0041] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, Advanced Long Term Evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-based access to unlicensed spectrum, NR-U) system, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), Fifth Generation (5G) system or other communication systems.

[0042] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0043] In one embodiment, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.

[0044] In one embodiment, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.

[0045] The embodiments of the present application describe various embodiments in conjunction with network devices and terminal devices, wherein the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0046] The terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a next-generation communication system such as an NR network, or a terminal device in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0047] In an embodiment of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.).

[0048] In an embodiment of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0049] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0050] In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in a WLAN, an evolved base station (eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or a network device in an NTN network, etc.

[0051] As an example and not a limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Alternatively, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.

[0052] In an embodiment of the present application, the network device can provide services for a cell, and the terminal device communicates with the network device through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to the network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0053] FIG1 exemplarily illustrates a communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and each network device 110 may include a different number of terminal devices 120 within its coverage area, which is not limited in this embodiment of the present application.

[0054] In one embodiment, the communication system 100 may further include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which is not limited in this embodiment of the present application.

[0055] Among them, the network equipment may include access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks for communicating with the access network equipment. The access network equipment can be an evolutionary base station (evolutional node B, abbreviated as eNB or e-NodeB) macro base station, micro base station (also called "small base station"), pico base station, access point (AP), transmission point (TP) or new generation base station (new generation Node B, gNodeB), etc. in a long-term evolution (LTE) system, a next-generation (mobile communication system) (next radio, NR) system or an authorized auxiliary access long-term evolution (LAA-LTE) system.

[0056] It should be understood that in the embodiments of the present application, a device having a communication function in a network / system may be referred to as a communication device. Taking the communication system shown in Figure 1 as an example, the communication device may include a network device and a terminal device having a communication function. The network device and the terminal device may be specific devices in the embodiments of the present application and will not be described in detail here. The communication device may also include other devices in the communication system, such as a network controller, a mobility management entity, and other network entities, which are not limited in the embodiments of the present application.

[0057] It should be understood that the terms "system" and "network" are often used interchangeably herein. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " generally indicates that the related objects are in an "or" relationship.

[0058] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0059] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0060] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following relevant technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all fall within the protection scope of the embodiments of the present application.

[0061] 1. AI-based wireless communication solutions

[0062] Regarding CSI feedback, as shown in Figure 2a, AI-based compression and feedback of CSI information are achieved through the introduction of an AI encoder and AI decoder. Regarding channel estimation, as shown in Figure 2b, an AI channel estimator is used to achieve high-performance estimation of a given channel. Regarding positioning, as shown in Figure 2c, an AI-based positioning algorithm relies on positioning channel information to obtain high-precision positioning results. Regarding beam management, as shown in Figure 2d, an AI-based beam management algorithm is used to obtain preferred or more refined beam information based on known beam information, or to obtain predictions of beam information for future moments.

[0063] 2. Purpose of AI / Machine Learning (ML) Model Transfer

[0064] For AI / ML solutions in wireless communication systems, there are generally three scenarios for training, acquiring, and optimizing models: (1) the model is trained, acquired, and optimized on the UE side; (2) the model is trained, acquired, and optimized on the network side; and (3) the model is trained, acquired, and optimized on both the UE and network sides. Similarly, for AI / ML solutions in wireless communication systems, there are generally three scenarios for deployment models: (1) the model is deployed on the UE side; (2) the model is deployed on the network side; and (3) the model is distributed on the UE and network sides. However, this does not mean that the nodes used for training, acquiring, and optimizing the model are the same nodes used for model deployment.

[0065] If the model acquisition node and the model deployment location are consistent, for example, both on the UE side, both on the network side, or on the UE side and the network side respectively, then in most cases no additional model transmission is required. However, if the model acquisition node and the model deployment location are inconsistent, there is a need to transmit the model between nodes in different communication systems, so as to ensure that AI / ML-related solutions in wireless communication systems can be effectively generated, transmitted, and used. Examples of inconsistencies between the model acquisition node and the model deployment location include: the model needs to be trained on the network side, but needs to be used on the UE side; or the model needs to be trained on the UE side, but needs to be used on the network side; or the model needs to be trained on a specific UE manufacturer or network manufacturer, but needs to be deployed and used by other UE manufacturers or network manufacturers.

[0066] When considering model transmission, the most fundamental requirement is to ensure that both the sender and receiver have a consistent understanding of the transmission model, preventing the model transmitted by the sender from being inoperable on the receiver. When both the sender and receiver are from the same manufacturer or supplier, or when different manufacturers have sufficient communication, inconsistent understanding of the transmission model, leading to problems with normal operation, is generally not an issue.

[0067] However, it's important to note that wireless communication systems involve a large number of different vendors, suppliers, and solution providers, such as chip manufacturers, terminal manufacturers, base station manufacturers, and operators. Expecting all model transfers to be completed through negotiation and communication between any combination of vendors is inefficient. Therefore, standardized processes are needed to support model transfer, including post-transmission model recognition, compilation, deployment, and usage, even when there isn't sufficient communication between vendors and devices.

[0068] For the models to be transmitted, there are differences in model implementation, such as different model frameworks, different model development environments, and different deployment environments. It is precisely these differences that may cause different recipients to have difficulties in model identification, compilation, deployment, and use. Therefore, when designing a model transmission solution, the solution provided by the embodiment of the present application can pay extra attention to the indication and interaction of model-related, especially model development framework, environment, version, function library, and other related auxiliary information on the basis of the transmission of the model itself. This information is helpful for the cross-node and cross-vendor use of the model, or cross-node and cross-vendor conversion.

[0069] In summary, the communication method provided in the embodiments of the present application may include a method for indicating auxiliary information related to the AI / ML model to ensure that different manufacturers and nodes can align their understanding of the transmitted AI / ML model, and complete the transformation (or conversion), update or use of the model version.

[0070] FIG3 is a schematic flow chart of a communication method 300 according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.

[0071] S310. The first communication device sends indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0072] In an embodiment of the present application, the first communication device can be a terminal device or a network device. The indication information sent by the first communication device can indicate auxiliary information corresponding to a single target model or multiple target models. The indication information can include the specific content of the auxiliary information or an identifier of the auxiliary information. The auxiliary information can be used to identify one or more of the following: the target model itself, partial content of the target model, the target model identifier, a portion of the target model identifier, the target model function identifier, or a portion of the target model function identifier. The second communication device that receives the indication information can perform operations such as parsing, identifying, compiling, deploying, using, and converting the target model based on the auxiliary information indicated in the indication information. The auxiliary information of the model can include information such as the development framework, environment, version, and library functions. The auxiliary information corresponding to different target models may be different or the same. For example, the development frameworks of Models A and B are the same, while the development frameworks of Models B and C are different. In an embodiment of the present application, the first communication device sending the auxiliary information helps ensure that both the sending and receiving ends of the model have a consistent understanding of the model, ensuring the normal use of the model. For example, on-demand model transmission and conversion can ensure the normal use of the model after transmission.

[0073] Figure 4a is a schematic flow chart of a communication method 400 according to an embodiment of the present application. The method may include one or more features of the above-mentioned method 300 embodiment. In one embodiment, the method further includes: S410, the first communication device sends the target model information corresponding to the auxiliary information. S410 and S310 may not limit the timing relationship, for example, S310 may be executed first and then S410, or S410 may be executed first and then S310. For example, as shown in Figure 4b, the UE sends auxiliary information of the target model, and the UE sends target model information. As shown in Figure 4c, the base station sends auxiliary information of the target model, and the base station sends target model information.

[0074] In one embodiment, the target model information includes: at least one of a target model, a target model identifier, and a function identifier of the target model. In an embodiment of the present application, the target model sent by the first communication device may include the structure, parameters, data, and other contents of the target model. The first communication device may also send a target model identifier, and the second communication device that receives the target model identifier may find the structure, parameters, data, and other contents of the target model based on the target model identifier. The first communication device may also send a function identifier of the target model, and the second communication device that receives the function identifier may find the structure, parameters, data, and other contents of the target model based on the function identifier.

[0075] Figure 5a is a schematic flow chart of a communication method 500 according to an embodiment of the present application. The method may include one or more features of the above-mentioned method 300 embodiment. In one embodiment, the method further includes: S510, the first communication device receives the target model information corresponding to the auxiliary information. S510 and S310 may not limit the timing relationship, for example, S310 may be executed first and then S510, or S510 may be executed first and then S310. For example, as shown in Figure 5b, the UE sends auxiliary information of the target model, and the base station sends target model information, and the UE can receive the target model information from the base station. As shown in Figure 5c, the base station sends auxiliary information of the target model, and the UE sends target model information, and the base station can receive the target model information from the UE.

[0076] In one embodiment, the target model information includes: at least one of a target model, a target model identifier, and a target model function identifier. For details, please refer to the relevant explanations in the above method embodiment.

[0077] FIG6a is a schematic flow chart of a communication method 600 according to an embodiment of the present application. The method may include one or more features of the above-mentioned method embodiments. In one embodiment, the method further includes:

[0078] S610, the first communication device receives an auxiliary information set, which includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device. For example, execute S610 first, then execute S310, and then execute S410. For another example, execute S610 first, then execute S310, and then execute S510. For example, as shown in Figure 6b, the base station sends a supported auxiliary information set, and the UE can receive the auxiliary information set from the base station; the UE sends indication information to indicate the auxiliary information of the target model, and the UE sends the target model information. As shown in Figure 6c, the UE sends a supported auxiliary information set, and the base station can receive the auxiliary information set from the UE; the base station sends indication information to indicate the auxiliary information of the target model, and the base station sends the target model information. For another example, as shown in Figure 6d, the base station sends a supported auxiliary information set, and the UE can receive the auxiliary information set from the base station; the UE sends indication information to indicate the auxiliary information of the target model, and the base station sends the target model information. As shown in FIG6e , the UE sends a supported auxiliary information set, and the base station may receive the auxiliary information set from the UE; the base station sends indication information indicating the auxiliary information of the target model, and the UE sends the target model information.

[0079] In one embodiment, the auxiliary information is used to indicate at least one of the following: development framework information, development environment version information, and function library information used for development. The development environment version information may also be referred to as development environment information or development version information. The auxiliary information may independently indicate the development framework information, the development environment version information, and the function library information used for development, or may jointly indicate two or more of the development framework information, the development environment version information, and the function library information used for development.

[0080] In one embodiment, the development framework information includes at least one of the following: TensorFlow, PyTorch, Open Neural Network Exchange (ONNX), Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and Computational Network Toolkit (CNTK).

[0081] In one embodiment, the version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

[0082] In one embodiment, the function library information used in the development includes at least one of the following:

[0083] The function library information used includes: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0084] In the embodiment of the present application, the auxiliary information set may include multiple types of auxiliary information supported by the second communication device, and may also include auxiliary information corresponding to multiple models. The first communication device that receives the auxiliary information set may select the required auxiliary information from the auxiliary information set.

[0085] For example, the auxiliary information set includes auxiliary information 1, auxiliary information 2, and auxiliary information 3. Among them, auxiliary information 1 includes development framework information as TensorFlow, version information of the development environment as TensorFlow version 2.0, and function library information used for development as TensorFlow function library information. Auxiliary information 2 includes development framework information as TensorFlow, and version information of the development environment as version 2.4. Auxiliary information 3 includes development framework information as PyTorch, and version information of the development environment as PyTorch version 1.5. After receiving the auxiliary information set, the first communication device can select auxiliary information 1 to indicate to the second communication device. The second communication device can parse or convert the model corresponding to the auxiliary information 1 based on the development framework information in the auxiliary information 1 as TensorFlow, the version information of the development environment as TensorFlow version 2.0, and the function library information used for development as TensorFlow function library information.

[0086] In an embodiment of the present application, the auxiliary information may include some bits for indicating one or any combination of development framework information, development environment version information, and function library information used for development. For example, multiple bits may be used to indicate multiple types of development framework information, multiple bits may be used to indicate multiple types of development environment version information, and multiple bits may be used to indicate multiple types of function library information used for development. Multiple bits indicating the same type of information may be considered a group of bits.

[0087] In one embodiment, the indication information includes a first group of bits, which are used to indicate a plurality of different development framework information. For example, if the first group of bits includes 5 bits, it can be configured to distinguish up to 32 different initial development framework information. If the first group of bits includes 6 bits, it can be configured to distinguish up to 64 different development framework information.

[0088] In one embodiment, the indication information includes a plurality of first numerical values, and the plurality of first numerical values ​​are used to indicate a plurality of different development framework information. For example, using two decimal numbers can constitute a maximum of 100 different initial development framework information.

[0089] In one embodiment, the indication information includes a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments. For example, the second group of bits includes 5 bits, which can constitute version information for distinguishing up to 32 different development environments.

[0090] In one embodiment, the indication information includes multiple second values, which are used to indicate version information of multiple different development environments. For example, using one decimal number can constitute version information for distinguishing up to 10 different development environments, and using two decimal numbers can constitute version information for distinguishing up to 100 different development environments.

[0091] In one embodiment, the indication information includes a third group of bits, which is used to indicate information about a plurality of different function libraries used for development. For example, the third group of bits includes 7 bits, which can constitute information for distinguishing a maximum of 128 different initial function libraries.

[0092] In one embodiment, the indication information includes multiple third values, which are used to indicate function library information used for multiple different developments. For example, using two decimal numbers can constitute function library information used to distinguish at most 100 different developments, and using three decimal numbers can constitute function library information used to distinguish at most 1,000 different developments.

[0093] In one embodiment, the indication information includes a fourth group of bits, which is used to indicate a combination of at least two of the development framework information, the development environment version information, and the function library information used for development. For example, the fourth group of bits includes 7 bits, wherein the first 2 bits are used to indicate the development framework information, the 3rd and 4th bits indicate the development environment version information, and the 5th and 6th bits indicate the development environment version information and the function library information used for development.

[0094] In one embodiment, the indication information includes multiple fourth numerical values, which are used to indicate a combination of at least two of the development framework information, the version information of the development environment, and the function library information used for development. For example, 2 decimal numbers can be used to distinguish up to 100 different types of development framework information, development environment version information, and function library information used for development. For example, the value "1" corresponds to "the development framework information is TensorFlow, the version information of the development environment is version 2.0 of TensorFlow, and the function library information used for development is the function library information of TensorFlow." The value "2" corresponds to "the development framework information is TensorFlow, and the version information of the development environment is version 2.4." For another example, the value "3" corresponds to "the development framework information is PyTorch, and the version information of the development environment is version 1.5 of PyTorch."

[0095] The above binary and decimal systems are merely examples and not limitations. Other systems, such as hexadecimal, may also be used to distinguish various auxiliary information or combinations thereof in the auxiliary information set.

[0096] In one embodiment, the bits and / or values ​​in the indication information may also be used to indicate the identifier of the auxiliary information. For example, the auxiliary information set received by the first communication device includes auxiliary information 1, auxiliary information 2, and auxiliary information 3. The values ​​of two specific bits in the indication information sent by the first communication device are 01, indicating auxiliary information 1, 10, indicating auxiliary information 2, and 11, indicating auxiliary information 3. Alternatively, the decimal value of one bit in the indication information sent by the first communication device is 1, indicating auxiliary information 1, 2, indicating auxiliary information 2, and 3, indicating auxiliary information 3.

[0097] In one embodiment, the target model includes one of the multiple models, or the auxiliary information corresponding to the target model is one of multiple types of auxiliary information supported by the second communication device. For example, the auxiliary information set sent by the UE to the base station includes auxiliary information corresponding to model A, auxiliary information corresponding to model B, and auxiliary information corresponding to model C. The base station receives the auxiliary information set, selects the auxiliary information corresponding to model C, and sends it to the UE. The UE then sends information about model C, such as model C itself, a model identifier of model C, or a function identifier of model C, to the base station.

[0098] In one embodiment, the auxiliary information is used to assist a second communication device in parsing the target model or converting the target model, and the second communication device is a device that receives the auxiliary information.

[0099] In one implementation, the first communication device is a network device, and the second communication device that receives the indication information is a terminal device.

[0100] In one embodiment, the carrying manner of the indication information includes at least one of the following: a broadcast message, a radio resource control (RRC) message, a medium access control (MAC) control element (CE), downlink control information (DCI), a downlink message in a random access process, a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a downlink channel dedicated to artificial intelligence AI / machine learning ML, and a capability indication on the network side.

[0101] In one implementation, the first communication device is a terminal device, and the second communication device that receives the indication information is a network device.

[0102] In one embodiment, the carrying mode of the indication information includes at least one of the following: RRC message, uplink control information (UCI), uplink message in random access process, physical uplink control channel (PUCCH), physical uplink shared channel (PUSCH), AI / ML dedicated uplink channel, and terminal device capability report.

[0103] In one implementation, the first communication device is a first terminal device, and the second communication device that receives the indication information is a second terminal device.

[0104] In one embodiment, the indication information is carried in at least one of the following ways: sidelink control information (SCI), physical sidelink control channel (PSCCH), and physical sidelink shared channel (PSSCH).

[0105] In one implementation, the first communication device is a first network device, and the second communication device that receives the indication information is a second network device.

[0106] FIG7 is a schematic flow chart of a communication method 700 according to an embodiment of the present application. The method can optionally be applied to the system shown in FIG1 , but is not limited thereto. The method includes at least part of the following contents.

[0107] S710. The second communication device receives indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0108] Figure 8 is a schematic flow chart of a communication method 800 according to an embodiment of the present application. The method may include one or more features of the embodiment of the method 700 described above. In one embodiment, the method further includes: S810, the second communication device receives target model information corresponding to the auxiliary information.

[0109] Figure 9 is a schematic flow chart of a communication method 900 according to an embodiment of the present application. The method may include one or more features of the above-mentioned method 700 embodiment. In one embodiment, the method further includes: S910, the second communication device sends target model information corresponding to the auxiliary information.

[0110] In one embodiment, the target model information includes: at least one of a target model, a target model identifier, and a function identifier of the target model.

[0111] Figure 10 is a schematic flow chart of a communication method 1000 according to an embodiment of the present application. The method may include one or more features of the aforementioned methods 700, 800, and 900. In one embodiment, the method further includes: S1010, the second communication device sends an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

[0112] In one embodiment, the target model includes one of the multiple models, or the auxiliary information corresponding to the target model is one of multiple types of auxiliary information supported by the second communication device.

[0113] In one embodiment, the auxiliary information is used to assist a second communication device in parsing the target model or converting the target model, and the second communication device is a device that receives the auxiliary information.

[0114] In one implementation, the second communication device is a terminal device, and the first communication device that sends the auxiliary information is a network device.

[0115] In one embodiment, the carrying mode of the indication information includes at least one of the following: a broadcast message, an RRC message, a MAC CE, a DCI, a downlink message in a random access process, a PDCCH, a PDSCH, an AI / ML dedicated downlink channel, and a capability indication on the network side.

[0116] In one implementation, the second communication device is a network device, and the first communication device that sends the auxiliary information is a terminal device.

[0117] In one embodiment, the carrying manner of the indication information includes at least one of the following: RRC message, UCI, uplink message in the random access process, PUCCH, PUSCH, AI / ML dedicated uplink channel, and UE capability reporting.

[0118] In one implementation, the second communication device is a second terminal device, and the first communication device that sends the auxiliary information is a first terminal device.

[0119] In one embodiment, the carrying mode of the indication information includes at least one of the following: SCI, PSCCH, and PSSCH.

[0120] In one embodiment, the auxiliary information is used to indicate at least one of the following:

[0121] Development framework information, development environment version information, and function library information used for development.

[0122] In one embodiment, the indication information includes a first group of bits, and the first group of bits is used to indicate a variety of different development framework information.

[0123] In one embodiment, the indication information includes multiple first values, and the multiple first values ​​are used to indicate multiple different development framework information.

[0124] In one embodiment, the indication information includes a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments.

[0125] In one embodiment, the indication information includes multiple second values, and the multiple second values ​​are used to indicate version information of multiple different development environments.

[0126] In one embodiment, the indication information includes a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

[0127] In one embodiment, the indication information includes a plurality of third values, and the plurality of third values ​​are used to indicate function library information used in a plurality of different developments.

[0128] In one embodiment, the indication information includes a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0129] In one embodiment, the indication information includes a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0130] In one embodiment, the development framework information includes at least one of the following: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0131] In one embodiment, the version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

[0132] In one embodiment, the function library information used in the development includes at least one of the following:

[0133] The function library information used includes: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0134] For specific examples of the second communication device executing methods 700, 800, 900, and 1000 of this embodiment, reference can be made to the relevant descriptions about the second communication device in the above methods 300, 400, 500, and 600, which will not be repeated here for the sake of brevity.

[0135] The communication method of the embodiment of the present application may include a method for transmitting auxiliary information of an AI / ML model. For example, in addition to transmitting and / or indicating the model, the first node may also indicate the auxiliary information of the model so that the second node can use the model normally. For another example, the second node indicates and / or requests a model constructed under specific conditions so that the first node can provide the corresponding model on demand. The above-mentioned model auxiliary information may include information such as development framework, environment, version, library function, etc. The purpose of indicating these auxiliary information is to ensure that the sending and receiving ends have a consistent understanding of the model during model transmission, and the normal use of the model after transmission can be achieved through on-demand transmission and on-demand conversion of the model. In the embodiment of the present application, according to the difference between the model on the network side and the UE side, a method for the model provider to indicate the model development framework, environment, version, and library function conditions, as well as a method for the model user network to indicate the expected development framework, environment, version, and library function conditions are given. The following are several specific examples.

[0136] Example 1: The first node indicates the initial model auxiliary information, and the first node transmits the model

[0137] In this example, the first node can be a UE or a network.

[0138] 1. The instruction process of the first node may include at least one of the following situations:

[0139] For example, the network (or UE) may transmit a specific model A to the UE (or network). The manner of transmitting the model between the network and the UE may include at least one of the following: (1) directly transmitting the model itself, (2) indicating the corresponding model ID and / or function ID. The model A given by the network (or UE) may be developed under specific conditions (for example, development framework, development environment, version, function library used for development, etc.). When the network (or UE) transmits the specific model A to the UE (or network), auxiliary information such as the initial development framework, initial development environment, version, library functions supported by the initial model, etc. may be notified to the UE (or network) so that the UE (or network) can effectively and efficiently complete the identification, compilation, deployment, and use of the model.

[0140] For another example, the network (or UE) can transmit a specific model A to the UE (or network). The method of transmitting the model between the network and the UE may include at least one of the following: (1) directly transmitting the model itself, (2) indicating the corresponding model ID and / or function ID. The model A given by the network (or UE) may be developed under specific conditions (for example: development framework, development environment, version, function library used for development, etc.). However, the UE (or network) may only be able to complete the identification, compilation, deployment, and use of the model under other specific conditions (for example: development framework, development environment, version, function library used for development, etc.). In this case, the UE (or network) needs to perform some model conversion to ensure the normal identification, compilation, deployment, and use of the model. When the network (or UE) transmits the specific model A to the UE (or network), performing the above-mentioned conversion operation also requires confirming more information about the specific initial model, such as the above-mentioned initial development conditions, such as: initial development framework, initial development environment, version, library functions supported by the initial model, and other auxiliary information. Therefore, the network (or UE) needs to transmit the auxiliary information of the specific model A to the UE (or network).

[0141] Taking the above two situations as an example, as shown in Figures 11 and 12, in addition to transmitting the model (directly transmitting the model, or indicating the corresponding model ID, function ID) to the UE, the network needs to notify the second node (UE or network) of the relevant auxiliary information of the model to ensure that different manufacturers and nodes can align their understanding of the transmitted AI / ML model, and complete the conversion, update, and use of the model version. The first node indicates the model auxiliary information to the second node. When the first node is a network device, the second node is the UE. When the first node is a UE, the second node is a network device. The first node and the second node can both be UEs. The first node and the second node can both be network devices.

[0142] The first node transmits the model (directly transmits the model, or indicates the corresponding model ID, function ID) to the second node. The timing relationship between the first node transmitting the model and the first node transmitting the model auxiliary information can be that the first node indicates and transmits the model first, or the first node transmits the model auxiliary information first, or the first node indicates and transmits the model and model auxiliary information to the second node at the same time.

[0143] 2. The content of model auxiliary information can be one or more of the following information:

[0144] 1. Initial development framework information

[0145] For example: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, CNTK and other development frameworks.

[0146] The indication of the initial development framework information has one or more of the following effects: (1) indicating the initial development framework can facilitate the second node to adopt the corresponding development framework to parse the transmitted model, or (2) facilitate the second node to transform the model based on the initial development framework information.

[0147] Examples of indication methods: using N1bit, for example, 6bit to distinguish up to 64 different development framework information; or using N1 numbers, for example, 2 decimal numbers to distinguish up to 100 different development framework information

[0148] 2. Initial development environment and version information

[0149] The functions of the initial development environment information here may include indicating the characteristics of the model's initial development environment, such as the specific version of the initial development framework, different versions caused by software updates and development, different versions corresponding to different operating systems, and different versions corresponding to different devices.

[0150] For example: TensorFlow version information (e.g., 2.0, 2.4, 2.7), PyTorch version information (e.g., 1.5, 1.8), ONNX version information, Keras version information, Caffe2 version information, MXNet version information, ML.NET version information, Scikit-learn version information, Tensor version information, Theano version information, CNTK version information, and other model development environment version information. Another example is Android version, iOS version, etc.

[0151] If the UE and network use different development frameworks, the model may not be recognized, compiled, deployed, or used after transmission. Similarly, if the UE and network have different understandings of the development environment and version for the same development framework, this can also cause problems with the model being recognized, compiled, deployed, or used after transmission. Therefore, the model development environment and version information are required.

[0152] Examples of indication methods: using N2 bits, such as 5 bits to distinguish up to 32 different initial development environments and version information; or using N2 numbers, such as 2 decimal numbers to distinguish up to 100 different initial development environments and version information

[0153] It should be noted that the development framework indication and the development environment and version indication can be independent or combined. When combined, if the information (bits) indicating the development framework are different, then even if the values ​​of the bits indicating the development environment and version are the same, the development environment and version information indicated by these bits may be different. For example, the first six bits of 000001001 indicate the first development framework, and the last three bits 001 indicate the first development version of the first development framework. The first six bits of 000002001 indicate the second development framework, and the last three bits 001 indicate the first development version of the second development framework.

[0154] 3. Information about the initial function libraries supported and used

[0155] If the function libraries supported by the UE and the network differ, this can lead to problems with model recognition, compilation, deployment, and use after transmission. For example, when a base station transmits a model to a UE, the model was developed using a first function library. If the UE does not have the first function library when using the model, or if the conversion tool used to convert the model on the UE does not have the first function library or does not have the conversion capabilities for the first function library, this can also cause model use and conversion to fail.

[0156] Indications of supported and used library information may include, for example: TensorFlow library information, PyTorch library information, ONNX library information, Keras library information, Caffe2 library information, MXNet library information, ML.NET library information, Scikit-learn library information, Tensor library information, Theano library information, CNTK library information, and other library information involved in model development.

[0157] Examples of indication methods include: using N3 bits, for example, 7 bits, to construct information for distinguishing a maximum of 128 different initial function libraries; or using N3 numbers, for example, 2 decimal numbers, to construct information for distinguishing a maximum of 100 different initial function libraries.

[0158] Similarly, the indication of supported and used function library information, the indication of development framework, and the indication of development environment and version can be independent or combined.

[0159] 3. The indication method of model auxiliary information can be one or more of the following methods:

[0160] When the network indicates model assistance information to the UE, one or more of the following methods may be used:

[0161] (1) Broadcast messages, such as MIB, SIB1, SIBx, (2) RRC messages, (3) MAC CE, (4) DCI messages, (5) Downlink messages during random access, such as MsgB, Msg2, Msg4, (4) PDCCH, (5) PDSCH, (6) AI / ML dedicated downlink channels, (7) Capability indication on the network side.

[0162] When the UE indicates model assistance information to the network, one or more of the following may be used:

[0163] (1) RRC message, (2) UCI ​​message, (3) Uplink message during random access, such as MsgA, Msg3. (4) PUCCH, (5) PUSCH, (6) AI / ML dedicated uplink channel, (7) UE capability reporting.

[0164] Example 2: The second node indicates the target model auxiliary information, and the first node transmits the model

[0165] In addition to the scenario described in Example 1, there is another scenario in which the second node indicates auxiliary information of the target model, or the second node requests the first node to transmit the target model according to specific conditions. If the first node is a UE, the second node can be a network device. If the first node is a network device, the second node can be a UE. The first node and the second node can both be UEs, for example, when the first node is UE1, the second node is UE2. The first node and the second node can both be network devices, for example, when the first node is network device 1, the second node is network device 2.

[0166] 1. The interaction process between the first node and the second node may include at least one of the following situations:

[0167] For example, the network (or UE) can transmit a specific model A to the UE (or network). The way of transmitting the model between the network and the UE may include at least one of the following: (1) directly transmitting the model itself, (2) indicating the corresponding model ID and / or function ID. The model A given by the network (or UE) may be developed under specific conditions (for example: development framework, development environment, version, function library used for development, etc.). However, the UE (or network) may only be able to complete the identification, compilation, deployment, and use of the model under other specific conditions (for example: development framework, development environment, version, function library used for development, etc.). In this case, the network (or UE) can perform some model conversions in advance to ensure that the UE (or network) side can achieve normal identification, compilation, deployment, and use of the model. When the network (or UE) transmits the specific model A to the UE (or network), performing the above-mentioned conversion operation also requires confirming more information about the specific target model, such as the above-mentioned target development conditions, such as: target development framework, target development environment, version, library functions supported by the target model, etc. Therefore, the network (or UE) needs to transmit auxiliary information of the specific model A to the UE (or network).

[0168] For another example, the network (or UE) can transmit a specific model A to the UE (or network). The manner of transmitting the model between the network and the UE may include at least one of the following: (1) directly transmitting the model itself, (2) indicating the corresponding model ID and / or function ID. The network (or UE) may provide the model A constructed under different specific conditions (for example, development framework, development environment, version, function library used for development, etc.). When the network (or UE) can transmit the specific model A to the UE (or network), the UE (or network) may indicate and / or request the network (or UE) the model A constructed under specific conditions (for example, auxiliary information such as target development framework, target development environment, version, function library used by the target model, etc.).

[0169] Taking the above scenario as an example, as shown in Figures 13 and 14, for different reasons, the second node (UE or network) instructs or requests model auxiliary information from the first node (network or UE), and then the first node instructs or provides the required target model to the second node. When the first node is a network device, the second node is a UE. When the first node is a UE, the second node is a network device. When the first node is UE1, the second node is UE2. When the first node is network device 1, the second node is network device 2.

[0170] 2. The content of model auxiliary information can be one or more of the following information:

[0171] (1) Target development framework information

[0172] For example: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, CNTK, and other development frameworks

[0173] The indication of the target development framework information has one or more of the following effects: (1) indicating the target development framework can help the first node adopt the corresponding development framework to parse the transmitted model, or (2) help the first node transform the model based on the target development framework information.

[0174] Examples of indication methods: using N1bit, for example, 6bit to distinguish up to 64 different development framework information; or using N1 numbers, for example, 2 decimal numbers to distinguish up to 100 different development framework information

[0175] (2) Target development environment and version information

[0176] The functions of the target development environment information here may include indicating the characteristics of the model target development environment, such as the specific version of the target development framework, such as different versions caused by software updates and development, different versions corresponding to different operating systems, and different versions corresponding to different devices.

[0177] For example: TensorFlow version information (e.g., 2.0, 2.4, 2.7), PyTorch version information (e.g., 1.5, 1.8), ONNX version information, Keras version information, Caffe2 version information, MXNet version information, ML.NET version information, Scikit-learn version information, Tensor version information, Theano version information, CNTK version information, and other model development environment version information. Another example is Android version, iOS version, etc.

[0178] If the UE and network use different development frameworks, the model may not be recognized, compiled, deployed, or used after transmission. Similarly, if the UE and network have different understandings of the development environment and version for the same development framework, this can also cause problems with the model being recognized, compiled, deployed, or used after transmission. Therefore, the model development environment and version information are required.

[0179] Examples of indication methods include: using N2 bits, such as 5 bits, to distinguish up to 32 different target development environments and version information; or using N2 numbers, such as 2 decimal numbers, to distinguish up to 100 different target development environments and version information.

[0180] It should be noted here that the indication of the development framework and the indication of the development environment and version can be independent or combined. When combined, if the information (bits) indicating the development framework are different, then even if the values ​​of the bits used to indicate the development environment and version are the same, the development environment and version information indicated by the bits representing these bits may be different. For example, the first 6 bits of 000001001 indicate the first development framework, and the last 3 bits 001 indicate the first development version under the first development framework; the first 6 bits of 000002001 indicate the second development framework, and the last 3 bits 001 indicate the first development version under the second development framework.

[0181] (3) Information on supported and used target function libraries

[0182] If the function libraries supported by the UE and the network differ, this can lead to problems with model recognition, compilation, deployment, and use after transmission. For example, when a base station transmits a model to a UE, the model was developed using a first function library. If the UE does not have the first function library when using the model, or if the conversion tool used to convert the model on the UE does not have the first function library or does not have the conversion capabilities for the first function library, this can also cause model use and conversion to fail.

[0183] Indications of supported and used library information may include, for example: TensorFlow library information, PyTorch library information, ONNX library information, Keras library information, Caffe2 library information, MXNet library information, ML.NET library information, Scikit-learn library information, Tensor library information, Theano library information, CNTK library information, and other library information involved in model development.

[0184] Examples of indication methods include: using N3 bits, for example, 7 bits, to construct information for distinguishing a maximum of 128 different target function libraries; or using N3 numbers, for example, 2 decimal numbers, to construct information for distinguishing a maximum of 100 different target function libraries.

[0185] Similarly, the indication of supported and used function library information, the indication of development framework, and the indication of development environment and version can be independent or combined.

[0186] 3. The method for indicating model auxiliary information and the method for requesting the target model may include one or more of the following methods:

[0187] When the UE indicates model assistance information to the network, or when the UE requests a specific target model, one or more of the following may be used:

[0188] (1)RRC message (2)UCI message (3)Uplink message during random access, such as MsgA and Msg3. (4)PUCCH (5)PUSCH (6)AI / ML dedicated uplink channel (7)UE capability reporting.

[0189] When the network indicates model assistance information to the UE, or when the network requests a specific target model, one or more of the following methods may be used:

[0190] (1) Broadcast messages, such as MIB, SIB1, SIBx (2) RRC messages (3) MAC CE (4) DCI messages (5) Downlink messages during random access, such as MsgB, Msg2, Msg4 (4) PDCCH (5) PDSCH (6) AI / ML dedicated downlink channel (7) Capability indication on the network side.

[0191] Furthermore, for Examples 1 and 2, the model auxiliary information can be used to indicate a portion of a model ID or a functionality ID. For example, it can indicate a portion of a field in a model ID or a portion of a field in a functionality ID. Alternatively, the model auxiliary information can be used to determine information about either the model ID or the functionality ID.

[0192] For example, a model identifier (or function identifier) ​​is an identifier of X bits in length, where Y bits indicate model auxiliary information (such as development framework, development environment, version, function library used for development, etc.).

[0193] For example: the model identifier (or function identifier) ​​is an identifier of the Z bit length, and the model auxiliary information (such as the development framework, development environment, version, function library used for development, etc.) is used to confirm the above Z bit information, or is one of the information used to confirm the above Z bit information.

[0194] In the above example, before the first node indicates the auxiliary information, it may also receive an auxiliary information set. The auxiliary information indicated by the first node may be part or all of the auxiliary information set.

[0195] In wireless communication systems, there is a need for model transmission. However, for the same model, due to differences in influencing factors such as development framework, environment, version, library function, etc., it may lead to situations where different manufacturers and nodes cannot complete model recognition, compilation, deployment, and use even after the model itself is transmitted. In an embodiment of the present application, two situations can be considered: the first situation is that the party providing the model can provide models under multiple conditions, such as development framework, environment, version, and library function conditions; the second situation is that the party providing the model can only provide models under specific conditions, such as specific development framework, environment, version, and library function conditions, and model conversion is required on the provider or the recipient. In these two cases, the embodiment of the present application provides a solution for model auxiliary information indication. In addition to the transmission of the model itself, the transmission of model auxiliary information is introduced to assist the model provider or recipient in realizing model selection, transmission, conversion, and use under specific conditions.

[0196] FIG15 is a schematic block diagram of a first communication device 1500 according to an embodiment of the present application. The first communication device 1500 may include:

[0197] The first sending unit 1501 is configured to send indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0198] In one implementation, the first communication device 1500 further includes: a second sending unit 1502 further configured to send target model information corresponding to the auxiliary information.

[0199] In one embodiment, the first communication device 1500 further includes:

[0200] The first receiving unit 1503 is configured to receive target model information corresponding to the auxiliary information.

[0201] In one embodiment, the target model information includes: at least one of a target model, a target model identifier, and a function identifier of the target model.

[0202] In one embodiment, the first communication device 1500 further includes: a second receiving unit 1504 further configured to receive an auxiliary information set, the auxiliary information set including auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

[0203] In one embodiment, the target model includes one of the multiple models, or the auxiliary information corresponding to the target model is one of multiple types of auxiliary information supported by the second communication device.

[0204] In one embodiment, the auxiliary information is used to assist a second communication device in parsing the target model or converting the target model, and the second communication device is a device that receives the auxiliary information.

[0205] In one implementation, the first communication device is a network device, and the second communication device that receives the indication information is a terminal device.

[0206] In one embodiment, the carrying method of the indication information includes at least one of the following: a broadcast message, a radio resource control RRC message, a media access control MAC control unit CE, downlink control information DCI, a downlink message in a random access process, a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, a downlink channel dedicated to artificial intelligence AI / machine learning ML, and a capability indication on the network side.

[0207] In one implementation, the first communication device is a terminal device, and the second communication device that receives the indication information is a network device.

[0208] In one embodiment, the carrying method of the indication information includes at least one of the following: RRC message, uplink control information UCI, uplink message in the random access process, physical uplink control channel PUCCH, physical uplink shared channel PUSCH, AI / ML dedicated uplink channel, and terminal device capability report.

[0209] In one implementation, the first communication device is a first terminal device, and the second communication device that receives the indication information is a second terminal device.

[0210] In one embodiment, the indication information is carried in at least one of the following ways: sidelink control information SCI, a physical sidelink control channel PSCCH, and a physical sidelink shared channel PSSCH.

[0211] In one embodiment, the auxiliary information is used to indicate at least one of the following:

[0212] Development framework information, development environment version information, and function library information used for development.

[0213] In one embodiment, the indication information includes a first group of bits, and the first group of bits is used to indicate a variety of different development framework information.

[0214] In one embodiment, the indication information includes multiple first values, and the multiple first values ​​are used to indicate multiple different development framework information.

[0215] In one embodiment, the indication information includes a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments.

[0216] In one embodiment, the indication information includes multiple second values, and the multiple second values ​​are used to indicate version information of multiple different development environments.

[0217] In one embodiment, the indication information includes a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

[0218] In one embodiment, the indication information includes a plurality of third values, and the plurality of third values ​​are used to indicate function library information used in a plurality of different developments.

[0219] In one embodiment, the indication information includes a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0220] In one embodiment, the indication information includes a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0221] In one embodiment, the development framework information includes at least one of the following: TensorFlow, PyTorch, Open Neural Network Exchange ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and Cognitive Computing Network Toolkit CNTK.

[0222] In one embodiment, the version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

[0223] In one embodiment, the function library information used in the development includes at least one of the following:

[0224] The function library information used includes: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0225] The first communication device 1500 of the embodiment of the present application can implement the corresponding functions of the first communication device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the first communication device 1500 can be found in the corresponding descriptions in the above-mentioned method embodiments, and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units or components, etc.) in the first communication device 1500 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).

[0226] FIG16 is a schematic block diagram of a second communication device 1600 according to an embodiment of the present application. The second communication device 1600 may include:

[0227] The first receiving unit 1601 is configured to receive indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0228] In one implementation, the second communication device 1600 further includes: a second receiving unit 1602 further configured to receive target model information corresponding to the auxiliary information.

[0229] In one implementation, the second communication device 1600 further includes: a first sending unit 1603, configured to send target model information corresponding to the auxiliary information.

[0230] In one embodiment, the target model information includes: at least one of a target model, a target model identifier, and a function identifier of the target model.

[0231] In one embodiment, the second communication device 1600 further includes: the second sending unit 1604 is further configured to send an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

[0232] In one embodiment, the target model includes one of the multiple models, or the auxiliary information corresponding to the target model is one of multiple types of auxiliary information supported by the second communication device.

[0233] In one embodiment, the auxiliary information is used to assist a second communication device in parsing the target model or converting the target model, and the second communication device is a device that receives the auxiliary information.

[0234] In one implementation, the second communication device is a terminal device, and the first communication device that sends the auxiliary information is a network device.

[0235] In one embodiment, the carrying mode of the indication information includes at least one of the following: a broadcast message, an RRC message, a MAC CE, a DCI, a downlink message in a random access process, a PDCCH, a PDSCH, an AI / ML dedicated downlink channel, and a capability indication on the network side.

[0236] In one implementation, the second communication device is a network device, and the first communication device that sends the auxiliary information is a terminal device.

[0237] In one embodiment, the carrying manner of the indication information includes at least one of the following: RRC message, UCI, uplink message in the random access process, PUCCH, PUSCH, AI / ML dedicated uplink channel, and UE capability reporting.

[0238] In one implementation, the second communication device is a second terminal device, and the first communication device that sends the auxiliary information is a first terminal device.

[0239] In one embodiment, the carrying mode of the indication information includes at least one of the following: SCI, PSCCH, and PSSCH.

[0240] In one embodiment, the auxiliary information is used to indicate at least one of the following:

[0241] Development framework information, development environment version information, and function library information used for development.

[0242] In one embodiment, the indication information includes a first group of bits, and the first group of bits is used to indicate a variety of different development framework information.

[0243] In one embodiment, the indication information includes multiple first values, and the multiple first values ​​are used to indicate multiple different development framework information.

[0244] In one embodiment, the indication information includes a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments.

[0245] In one embodiment, the indication information includes multiple second values, and the multiple second values ​​are used to indicate version information of multiple different development environments.

[0246] In one embodiment, the indication information includes a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

[0247] In one embodiment, the indication information includes a plurality of third values, and the plurality of third values ​​are used to indicate function library information used in a plurality of different developments.

[0248] In one embodiment, the indication information includes a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0249] In one embodiment, the indication information includes a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, development environment version information, and function library information used for development.

[0250] In one embodiment, the development framework information includes at least one of the following: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0251] In one embodiment, the version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

[0252] In one embodiment, the function library information used in the development includes at least one of the following:

[0253] The function library information used includes: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

[0254] The second communication device 1600 of the embodiment of the present application can implement the corresponding functions of the second communication device in the aforementioned method embodiment. The processes, functions, implementation methods and beneficial effects corresponding to the various modules (sub-modules, units or components, etc.) in the second communication device 1600 can be found in the corresponding descriptions in the above-mentioned method embodiments, and will not be repeated here. It should be noted that the functions described in the various modules (sub-modules, units or components, etc.) in the second communication device 1600 of the embodiment of the application can be implemented by different modules (sub-modules, units or components, etc.) or by the same module (sub-module, unit or component, etc.).

[0255] Figure 17 is a schematic structural diagram of a communication device 1700 according to an embodiment of the present application. The communication device 1700 includes a processor 1710, which can call and execute a computer program from a memory to enable the communication device 1700 to implement the method in the embodiment of the present application.

[0256] In one embodiment, the communication device 1700 may further include a memory 1720. The processor 1710 may call and execute a computer program from the memory 1720 to enable the communication device 1700 to implement the method in the embodiment of the present application.

[0257] The memory 1720 may be a separate device independent of the processor 1710 , or may be integrated into the processor 1710 .

[0258] In one embodiment, the communication device 1700 may further include a transceiver 1730 , and the processor 1710 may control the transceiver 1730 to communicate with other devices. Specifically, the transceiver 1730 may send information or data to other devices, or receive information or data sent by other devices.

[0259] The transceiver 1730 may include a transmitter and a receiver. The transceiver 1730 may further include an antenna, and the number of antennas may be one or more.

[0260] In one embodiment, the communication device 1700 may be the first communication device of the embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0261] In one embodiment, the communication device 1700 may be the second communication device of the embodiment of the present application, and the communication device 1700 may implement the corresponding processes implemented by the second communication device in each method of the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0262] 18 is a schematic structural diagram of a chip 1800 according to an embodiment of the present application. The chip 1800 includes a processor 1810, which can call and execute a computer program from a memory to implement the method according to the embodiment of the present application.

[0263] In one embodiment, the chip 1800 may further include a memory 1820. The processor 1810 may call and execute a computer program from the memory 1820 to implement the method executed by the first communication device or the second communication device in the embodiment of the present application.

[0264] The memory 1820 may be a separate device independent of the processor 1810 , or may be integrated into the processor 1810 .

[0265] In one embodiment, the chip 1800 may further include an input interface 1830. The processor 1810 may control the input interface 1830 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0266] In one embodiment, the chip 1800 may further include an output interface 1840. The processor 1810 may control the output interface 1840 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0267] In one embodiment, the chip can be applied to the first communication device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the first communication device in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0268] In one embodiment, the chip can be applied to the second communication device in the embodiment of the present application, and the chip can implement the corresponding processes implemented by the second communication device in each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0269] The chips used in the first communication device and the second communication device may be the same chip or different chips.

[0270] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0271] The processor mentioned above may be a general-purpose processor, a digital signal processor (DSP), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. The general-purpose processor mentioned above may be a microprocessor or any conventional processor, etc.

[0272] The memory mentioned above may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM).

[0273] It should be understood that the above-mentioned memories are exemplary but not restrictive. For example, the memories in the embodiments of the present application may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM RAM (DR RAM), etc. In other words, the memories in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0274] FIG19 is a schematic block diagram of a communication system 1900 according to an embodiment of the present application. The communication system 1900 includes a first communication device 1910 and a second communication device 1920 .

[0275] The first communication device 1910 is used to send indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

[0276] The second communication device 1920 is configured to receive the indication information.

[0277] The first communication device 1910 can be used to implement the corresponding functions implemented by the first communication device in the above method, and the second communication device 1920 can be used to implement the corresponding functions implemented by the first communication device in the above method. For the sake of brevity, they are not described here in detail.

[0278] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function in accordance with the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)).

[0279] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0280] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0281] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A communication method, comprising: The first communication device sends indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

2. The method according to claim 1, wherein: The method further comprises: The first communication device sends target model information corresponding to the auxiliary information.

3. The method according to claim 1, wherein: The method further comprises: The first communication device receives target model information corresponding to the auxiliary information.

4. The method according to claim 2 or 3, wherein: The target model information includes: at least one of a target model, a target model identifier and a function identifier of the target model.

5. The method according to any one of claims 1 to 4, wherein: The method further comprises: The first communication device receives an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

6. The method according to claim 5, wherein: The target model includes one model among the multiple models, or the auxiliary information corresponding to the target model is one of multiple categories of auxiliary information supported by the second communication device.

7. The method according to any one of claims 1 to 6, wherein: The auxiliary information is used to assist a second communication device in parsing the target model or transforming the target model, and the second communication device is a device that receives the auxiliary information.

8. The method according to any one of claims 1 to 7, wherein: The first communication device is a network device, and the second communication device that receives the indication information is a terminal device.

9. The method according to claim 8, wherein: The carrying method of the indication information includes at least one of the following: a broadcast message, a radio resource control RRC message, a media access control MAC control unit CE, downlink control information DCI, a downlink message in a random access process, a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, a downlink channel dedicated to artificial intelligence AI / machine learning ML, and a capability indication on the network side.

10. The method according to any one of claims 1 to 6, wherein: The first communication device is a terminal device, and the second communication device that receives the indication information is a network device.

11. The method according to claim 10, wherein: The carrying mode of the indication information includes at least one of the following: RRC message, uplink control information UCI, uplink message in random access process, physical uplink control channel PUCCH, physical uplink shared channel PUSCH, AI / ML dedicated uplink channel, terminal device capability report.

12. The method according to any one of claims 1 to 6, wherein: The first communication device is a first terminal device, and the second communication device that receives the indication information is a second terminal device.

13. The method according to claim 12, wherein: The carrying mode of the indication information includes at least one of the following: sidelink control information SCI, physical sidelink control channel PSCCH, and physical sidelink shared channel PSSCH.

14. The method according to any one of claims 1 to 13, wherein: The auxiliary information is used to indicate at least one of the following: Development framework information, development environment version information, and function library information used for development.

15. The method according to claim 14, wherein: The indication information includes a first group of bits, where the first group of bits is used to indicate a variety of different development framework information.

16. The method according to claim 14 or 15, wherein: The indication information includes a plurality of first numerical values, and the plurality of first numerical values ​​are used to indicate a plurality of different development framework information.

17. The method according to any one of claims 14 to 16, wherein: The indication information includes a second group of bits, where the second group of bits is used to indicate version information of a plurality of different development environments.

18. The method according to any one of claims 14 to 17, wherein: The indication information includes a plurality of second values, and the plurality of second values ​​are used to indicate version information of a plurality of different development environments.

19. The method according to any one of claims 14 to 18, wherein: The indication information includes a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

20. The method according to any one of claims 14 to 19, wherein: The indication information includes a plurality of third values, and the plurality of third values ​​are used to indicate function library information used in a plurality of different developments.

21. The method according to any one of claims 14 to 20, wherein: The indication information includes a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

22. The method according to any one of claims 14 to 21, wherein: The indication information includes a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

23. The method according to any one of claims 14 to 22, wherein: The development framework information includes at least one of the following: TensorFlow, PyTorch, Open Neural Network Exchange ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and Computational Network Toolkit CNTK.

24. The method according to any one of claims 14 to 23, wherein: The version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

25. The method according to any one of claims 14 to 24, wherein: The function library information used in the development includes at least one of the following: The function library information of TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK used.

26. A communication method, comprising: The second communication device receives indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

27. The method according to claim 26, wherein: The method further comprises: The second communication device receives target model information corresponding to the auxiliary information.

28. The method according to claim 26, wherein: The method further comprises: The second communication device sends target model information corresponding to the auxiliary information.

29. The method according to claim 27 or 28, wherein: The target model information includes: at least one of a target model, a target model identifier and a function identifier of the target model.

30. The method according to any one of claims 26 to 29, wherein: The method further comprises: The second communication device sends an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

31. The method according to claim 30, wherein: The target model includes one model among the multiple models, or the auxiliary information corresponding to the target model is one of multiple categories of auxiliary information supported by the second communication device.

32. The method according to any one of claims 26 to 31, wherein: The auxiliary information is used to assist a second communication device in parsing the target model or transforming the target model, and the second communication device is a device that receives the auxiliary information.

33. The method according to any one of claims 26 to 32, wherein: The second communication device is a terminal device, and the first communication device that sends the auxiliary information is a network device.

34. The method of claim 33, wherein: The carrying mode of the indication information includes at least one of the following: a broadcast message, an RRC message, a MAC CE, a DCI, a downlink message in a random access process, a PDCCH, a PDSCH, a downlink channel dedicated to AI / ML, and a capability indication on the network side.

35. The method according to any one of claims 26 to 34, wherein: The second communication device is a network device, and the first communication device that sends the auxiliary information is a terminal device.

36. The method of claim 35, wherein: The carrying mode of the indication information includes at least one of the following: RRC message, UCI, uplink message in random access process, PUCCH, PUSCH, AI / ML dedicated uplink channel, UE capability reporting.

37. The method according to any one of claims 26 to 36, wherein: The second communication device is a second terminal device, and the first communication device that sends the auxiliary information is a first terminal device.

38. The method of claim 37, wherein: The carrying mode of the indication information includes at least one of the following: SCI, PSCCH, and PSSCH.

39. The method according to any one of claims 29 to 38, wherein: The auxiliary information is used to indicate at least one of the following: Development framework information, development environment version information, and function library information used for development.

40. The method of claim 39, wherein: The indication information includes a first group of bits, where the first group of bits is used to indicate a variety of different development framework information.

41. The method according to claim 39 or 40, wherein: The indication information includes a plurality of first numerical values, and the plurality of first numerical values ​​are used to indicate a plurality of different development framework information.

42. The method according to any one of claims 39 to 41, wherein: The indication information includes a second group of bits, where the second group of bits is used to indicate version information of a plurality of different development environments.

43. A method according to any one of claims 39 to 42, wherein: The indication information includes a plurality of second values, and the plurality of second values ​​are used to indicate version information of a plurality of different development environments.

44. A method according to any one of claims 39 to 43, wherein: The indication information includes a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

45. A method according to any one of claims 39 to 44, wherein: The indication information includes a plurality of third values, and the plurality of third values ​​are used to indicate function library information used in a plurality of different developments.

46. ​​A method according to any one of claims 39 to 45, wherein: The indication information includes a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

47. A method according to any one of claims 39 to 46, wherein: The indication information includes a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

48. A method according to any one of claims 39 to 47, wherein: The development framework information includes at least one of the following: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

49. The method according to any one of claims 39 to 48, wherein: The version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

50. The method according to any one of claims 39 to 49, wherein: The function library information used in the development includes at least one of the following: The function library information of TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK used.

51. A first communication device, comprising: The first sending unit is used to send indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

52. The first communication device according to claim 51, wherein: The first communication device further includes: The second sending unit is used to send the target model information corresponding to the auxiliary information.

53. The first communication device according to claim 51, wherein: The first communication device further includes: The first receiving unit is used to receive target model information corresponding to the auxiliary information.

54. The first communication device according to claim 52 or 53, wherein: The target model information includes: at least one of a target model, a target model identifier and a function identifier of the target model.

55. The first communication device according to any one of claims 51 to 54, wherein: The first communication device further includes: The second receiving unit is used to receive an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

56. The method of claim 55, wherein: The target model includes one model among the multiple models, or the auxiliary information corresponding to the target model is one of multiple categories of auxiliary information supported by the second communication device.

57. The first communication device according to any one of claims 51 to 56, wherein: The auxiliary information is used to assist a second communication device in parsing the target model or transforming the target model, and the second communication device is a device that receives the auxiliary information.

58. The first communication device according to any one of claims 51 to 57, wherein: The first communication device is a network device, and the second communication device that receives the second indication information of the auxiliary information is a terminal device.

59. The first communication device according to claim 58, wherein: The indication method of the auxiliary information includes at least one of the following: a broadcast message, a radio resource control RRC message, a media access control MAC control unit CE, downlink control information DCI, a downlink message in a random access process, a physical downlink control channel PDCCH, a physical downlink shared channel PDSCH, a downlink channel dedicated to artificial intelligence AI / machine learning ML, and a capability indication on the network side.

60. The first communication device according to any one of claims 51 to 56, wherein: The first communication device is a terminal device, and the second communication device that receives the second indication information of the auxiliary information is a network device.

61. The first communication device according to claim 60, wherein: The indication method of the auxiliary information includes at least one of the following: RRC message, uplink control information UCI, uplink message in the random access process, physical uplink control channel PUCCH, physical uplink shared channel PUSCH, AI / ML dedicated uplink channel, terminal device capability reporting.

62. The first communication device according to any one of claims 61 to 66, wherein: The first communication device is a first terminal device, and the second communication device that receives the second indication information of the auxiliary information is a second terminal device.

63. The first communication device according to claim 62, wherein: The indication mode of the auxiliary information indicates that the carrying mode of the information includes at least one of the following: sidelink control information SCI, physical sidelink control channel PSCCH, and physical sidelink shared channel PSSCH.

64. The first communication device according to any one of claims 51 to 63, wherein: The auxiliary information is used to indicate at least one of the following: Development framework information, development environment version information, and function library information used for development.

65. The first communication device according to claim 64, wherein: The auxiliary information includes indication information including a first group of bits, where the first group of bits is used to indicate a variety of different development framework information.

66. The first communication device according to claim 64 or 65, wherein: The auxiliary information includes indication information including a plurality of first values, and the plurality of first values ​​are used to indicate a plurality of different development framework information.

67. The first communication device according to any one of claims 64 to 66, wherein: The auxiliary information includes indication information including a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments.

68. The first communication device according to any one of claims 64 to 67, wherein: The auxiliary information includes indication information including a plurality of second values, and the plurality of second values ​​are used to indicate version information of a plurality of different development environments.

69. The first communication device according to any one of claims 64 to 68, wherein: The auxiliary information includes indication information including a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

70. The first communication device according to any one of claims 64 to 69, wherein: The auxiliary information includes indication information including a plurality of third values, and the plurality of third values ​​are used to indicate function library information used for a variety of different developments.

71. The first communication device according to any one of claims 64 to 70, wherein: The auxiliary information includes indication information including a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

72. The first communication device according to any one of claims 64 to 71, wherein: The auxiliary information includes indication information including a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

73. The first communication device according to any one of claims 64 to 72, wherein: The development framework information includes at least one of the following: TensorFlow, PyTorch, Open Neural Network Exchange ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and Computational Network Toolkit CNTK.

74. The first communication device according to any one of claims 64 to 73, wherein: The version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

75. The first communication device according to any one of claims 64 to 74, wherein: The function library information used in the development includes at least one of the following: The function library information of TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK used.

76. A second communication device, comprising: The first receiving unit is used to receive indication information, where the indication information is used to indicate auxiliary information corresponding to the target model.

77. The second communication device according to claim 76, wherein: The second communication device further includes: The second receiving unit is used to receive the target model information corresponding to the auxiliary information.

78. The second communication device according to claim 76, wherein: The second communication device further includes: The first sending unit is used to send the target model information corresponding to the auxiliary information.

79. The second communication device according to claim 77 or 78, wherein: The target model information includes: at least one of a target model, a target model identifier and a function identifier of the target model.

80. The second communication device according to any one of claims 76 to 79, wherein: The second communication device further includes: The second sending unit is used to send an auxiliary information set, where the auxiliary information set includes auxiliary information corresponding to multiple models, or multiple categories of auxiliary information supported by the second communication device.

81. The second communication device according to claim 80, wherein: The target model includes one model among the multiple models, or the auxiliary information corresponding to the target model is one of multiple categories of auxiliary information supported by the second communication device.

82. The second communication device according to any one of claims 76 to 81, wherein: The auxiliary information is used to assist a second communication device in parsing the target model or transforming the target model, and the second communication device is a device that receives the auxiliary information.

83. The second communication device according to any one of claims 76 to 82, wherein: The second communication device is a terminal device, and the first communication device that sends the auxiliary information is a network device.

84. The second communication device according to claim 83, wherein: The indication method of the auxiliary information includes at least one of the following: a broadcast message, an RRC message, a MAC CE, a DCI, a downlink message in a random access process, a PDCCH, a PDSCH, an AI / ML dedicated downlink channel, and a capability indication on the network side.

85. The second communication device according to any one of claims 76 to 84, wherein: The second communication device is a network device, and the first communication device that sends the auxiliary information is a terminal device.

86. The second communication device according to claim 85, wherein: The indication method of the auxiliary information includes at least one of the following: RRC message, UCI, uplink message in the random access process, PUCCH, PUSCH, AI / ML dedicated uplink channel, UE capability reporting.

87. The second communication device according to any one of claims 76 to 86, wherein: The second communication device is a second terminal device, and the first communication device that sends the auxiliary information is a first terminal device.

88. The second communication device according to claim 87, wherein: The indication method of the auxiliary information includes at least one of the following bearing methods: SCI, PSCCH, and PSSCH.

89. The second communication device according to any one of claims 79 to 88, wherein: The auxiliary information is used to indicate at least one of the following: Development framework information, development environment version information, and function library information used for development.

90. The second communication device according to claim 89, wherein: The auxiliary information includes indication information including a first group of bits, where the first group of bits is used to indicate a variety of different development framework information.

91. The second communication device according to claim 89 or 90, wherein: The auxiliary information includes indication information including a plurality of first values, and the plurality of first values ​​are used to indicate a plurality of different development framework information.

92. The second communication device according to any one of claims 89 to 91, wherein: The auxiliary information includes indication information including a second group of bits, and the second group of bits is used to indicate version information of multiple different development environments.

93. The second communication device according to any one of claims 89 to 92, wherein: The auxiliary information includes indication information including a plurality of second values, and the plurality of second values ​​are used to indicate version information of a plurality of different development environments.

94. The second communication device according to any one of claims 89 to 93, wherein: The auxiliary information includes indication information including a third group of bits, and the third group of bits is used to indicate function library information used for various developments.

95. The second communication device according to any one of claims 89 to 94, wherein: The auxiliary information includes indication information including a plurality of third values, and the plurality of third values ​​are used to indicate function library information used for a variety of different developments.

96. The second communication device according to any one of claims 89 to 95, wherein: The auxiliary information includes indication information including a fourth group of bits, and the fourth group of bits is used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

97. The second communication device according to any one of claims 89 to 96, wherein: The auxiliary information includes indication information including a plurality of fourth values, and the plurality of fourth values ​​are used to indicate a combination of at least two of development framework information, version information of a development environment, and function library information used for development.

98. The second communication device according to any one of claims 89 to 97, wherein: The development framework information includes at least one of the following: TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK.

99. The second communication device according to any one of claims 89 to 98, wherein: The version information of the development environment includes at least one of the following: version information of TensorFlow, version information of PyTorch, version information of ONNX, version information of Keras, version information of Caffe2, version information of MXNet, version information of ML.NET, version information of Scikit-learn, version information of Tensor, version information of Theano, version information of CNTK, Android version information, and IOS version information.

100. The second communication device according to any one of claims 89 to 99, wherein: The function library information used in the development includes at least one of the following: The function library information of TensorFlow, PyTorch, ONNX, Keras, Caffe2, MXNet, ML.NET, Scikit-learn, Tensor, Theano, and CNTK used.

101. A communication device comprising: A transceiver, a processor and a memory, wherein the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to call and run the computer program stored in the memory so that the communication device executes the method as described in any one of claims 1 to 25 or any one of 26 to 50.

102. A chip, comprising: A processor, configured to call and run a computer program from a memory, so that a device equipped with the chip executes a method as claimed in any one of claims 1 to 25 or any one of claims 26 to 50.

103. A computer-readable storage medium for storing a computer program, which, when executed by a device, causes the device to perform a method as claimed in any one of claims 1 to 25 or any one of claims 26 to 50.

104. A computer program product comprising computer program instructions for causing a computer to perform the method of any one of claims 1 to 25 or any one of claims 26 to 50.

105. A computer program causing a computer to perform the method of any one of claims 1 to 25 or any one of claims 26 to 50.

Images