Information transmission method, apparatus and system

Abstract

The present application provides an information transmission method, an apparatus and a system. Fox example, the method can be suitable for an artificial intelligence (AI) training scenario, for example, a scenario where training data is transmitted between a network device and a training apparatus through an air interface. The method comprises: a network device determines a first data set, data in the first data set being used for training a first AI model; and the network device sends the first data set and first indication information to the training apparatus, the first indication information indicating functions and / or features of the first AI model. The method can be suitable for an air interface transmission scenario of training data. When the network device issues the training data, indication information for indicating the data purpose is carried, such that different training data can be associated or distinguished, facilitating recognition of the association between different training data and the purpose of the training data by the training apparatus, thus meeting the training requirements of different AI models, and saving the overhead of the training apparatus.

Description

Information transmission method, device and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on April 2, 2024, with application number 202410397937.0 and invention name “Information Transmission Method, Device and System”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communications, and in particular to an information transmission method, device, and system. Background Art

[0003] Machine learning is a key technological approach to achieving artificial intelligence (AI). Currently, training of artificial intelligence (AI) models on user equipment (UE) is often triggered by the UE itself to collect relevant data. Currently, the network transmits training data to the UE over the air interface. The UE cannot determine the relationship between multiple received training data or training data received at different times, resulting in wasted overhead and UE power consumption, making it difficult to train AI models. Summary of the Invention

[0004] The present application provides an information transmission method, device and system, which can reduce the power consumption of a training device.

[0005] In a first aspect, an information transmission method is provided. The method can be performed by a data acquisition device. The data acquisition device can be a network-side device, or a module in the network-side device, such as a chip, circuit, or chip system. It can also be a terminal-side device or a chip, circuit, or chip system of a terminal-side device. This application does not limit this. Among them, the network-side device may include an access network device, a core network device, or a device that communicates with the access network device or the core network device, such as a server. The terminal-side device may include a terminal device, or a device that communicates with the terminal device, such as a server. For ease of description, the following is an example of the execution of the data acquisition device.

[0006] The method includes: determining a first data set, wherein data in the first data set is used for training a first artificial intelligence (AI) model; sending the first data set and first indication information, wherein the first indication information indicates functions and / or features of the first AI model.

[0007] This method is applicable to air-interface transmission scenarios for training data. When a data acquisition device sends training data, it carries information indicating the data's purpose. This can associate or distinguish different training data, making it easier for the training device to identify the associations between different training data and their purpose, thereby meeting the training needs of different AI models and saving training device overhead.

[0008] In some implementations, the first data set includes a first data subset and a second data subset, and the first indication information further indicates the function and / or feature of the AI ​​model corresponding to the first data subset and / or the second data subset.

[0009] In this way, by transmitting data sets over the air interface, it is possible to avoid leaking a large amount of private information on the network side related to AI model training to the training device side. Furthermore, for data subsets with different functions (or uses), the training device can determine the functions and / or characteristics of the AI ​​model corresponding to each data subset based on the first indication information, thereby avoiding the training device being unable to establish the relationship between the data subset and the functions and / or characteristics of the AI ​​model, thereby improving training efficiency.

[0010] In some implementations, the first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first data set and / or usage information of the first data set.

[0011] The first indication information indicates that the functions and / or features of the first AI model include:

[0012] The identifier of the first AI model and / or the identifier of the function indicates the function of the first AI model, and / or the identifier of the first AI model and / or the identifier of the function indicates a feature of the first AI model; or,

[0013] The identifier of the first data set and / or the usage information of the first data set indicates the function of the first AI model, and / or the identifier of the first data set and / or the usage information of the first data set indicates the characteristics of the first AI model.

[0014] It can be understood that one or more of the identification of the first AI model, the identification of the function of the first AI model, the function of the first AI model, the first AI model, the characteristics of the first AI model, the identification of the first data set, the characteristics of the first data set, the usage information of the first data set, etc. may have a corresponding relationship. Through this correspondence and corresponding indications, the application method of the first data set can be determined, such as which / which AI model operations it is used for, and the operation may include training and / or monitoring.

[0015] It can be understood that when there are multiple AI models determined by the above-mentioned correspondence, the training device can determine whether all or part of the multiple AI models are to be operated. The specific determination can be based on the system design and is not limited here.

[0016] In certain implementations, the first data set is also used for training a second AI model, and the first indication information further indicates functions and / or features of the second AI model.

[0017] In some implementations, the method further includes: determining a second data set; sending the second data set and second indication information, wherein the second indication information indicates a function and / or feature of the first AI model.

[0018] In some implementations, the second indication information and the first indication information have the same value.

[0019] In some implementations, the first data set includes a first data sample and a second data sample, and the method further includes: sending third indication information, wherein the third indication information indicates that the first data sample and the second data sample share first data, and the first data belongs to the first data set.

[0020] In some implementations, the first data is label information corresponding to input data and / or output data.

[0021] In some implementations, the method further includes: sending fourth indication information, wherein the fourth indication information indicates an identifier of the first data, or indicates resource information corresponding to the first data, wherein the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information.

[0022] In some implementations, the method further includes: receiving fifth indication information, wherein the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

[0023] In a second aspect, an information transmission method is provided. The method can be executed by a training device. For example, the training device can be an AI entity, such as an access network device, a core network device, a device communicating with an access network device or a core network device, a UE, or a device communicating with a UE, such as a server. The training device can also be a module in the AI ​​entity, such as a chip, a circuit, or a chip system. This application does not limit this. For ease of description, the following description uses the execution of a training device as an example.

[0024] The method includes: receiving a first data set and first indication information, wherein the data in the first data set is used for training a first AI model, and the first indication information indicates the function and / or characteristics of the first AI model; and determining, based on the first indication information, that the data in the first data set is used for training the first AI model.

[0025] In some implementations, the first data set includes a first data subset and a second data subset, and the first indication information also indicates the function and / or characteristics of the AI ​​model corresponding to the first data subset and / or the second data subset. The method also includes: determining the AI ​​model corresponding to the first data subset and / or the second data subset based on the first indication information.

[0026] In some implementations, the first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first data set and / or usage information of the first data set.

[0027] The method also includes: determining the purpose of the first data set and / or the first AI model corresponding to the first data set based on the first indication information.

[0028] In some implementations, the first data set is also used for training a second AI model, the first indication information further indicates functions and / or features of the second AI model, and the method further includes: determining the second AI model based on the first indication information.

[0029] In some implementations, the method further includes receiving a second data set and second indication information, where the second indication information indicates a function and / or feature of the first AI model.

[0030] In some implementations, the second indication information and the first indication information have the same value.

[0031] In some implementations, the first data set includes a first data sample and a second data sample, and the method further includes: receiving third indication information, the third indication information indicating that the first data sample and the second data sample share first data, and the first data belongs to the first data set; and determining, based on the third indication information, that the first data is used for the first data sample and the second data sample.

[0032] In some implementations, the first data is label information corresponding to input data and / or output data.

[0033] In some implementations, the method also includes: receiving fourth indication information, wherein the fourth indication information indicates an identifier of the first data, and / or indicates resource information corresponding to the first data, wherein the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information; and using the first data on resources determined based on the resource information.

[0034] In some implementations, the method further includes: sending fifth indication information, wherein the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

[0035] In a third aspect, a communication device is provided, comprising a processing unit and a transceiver unit, wherein the processing unit is used to determine a first data set, wherein the data in the first data set is used for training a first artificial intelligence (AI) model; and the transceiver unit is used to send the first data set and first indication information, wherein the first indication information indicates the function and / or characteristics of the first AI model.

[0036] In some implementations, the first data set includes a first data subset and a second data subset, and the first indication information further indicates the function and / or feature of the AI ​​model corresponding to the first data subset and / or the second data subset.

[0037] In certain implementations, the first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first dataset and / or usage information of the first dataset, and the first indication information indicates that the function and / or feature of the first AI model includes:

[0038] The first indication information indicates the function and / or feature of the first AI model through the identifier of the first AI model and / or the identifier of the function, or the identifier of the first data set and / or the usage information of the first data set.

[0039] In certain implementations, the first data set is also used for training a second AI model, and the first indication information further indicates functions and / or features of the second AI model.

[0040] In some implementations, the processing unit is further used to determine a second data set; the transceiver unit is further used to send the second data set and second indication information, wherein the second indication information indicates the function and / or characteristics of the first AI model.

[0041] In some implementations, the second indication information and the first indication information have the same value.

[0042] In some implementations, the first data set includes a first data sample and a second data sample, and the method further includes: sending third indication information, wherein the third indication information indicates that the first data sample and the second data sample share first data, and the first data belongs to the first data set.

[0043] In some implementations, the first data is label information corresponding to input data and / or output data.

[0044] In some implementations, the transceiver unit is further used to send fourth indication information, where the fourth indication information indicates an identifier of the first data, or indicates resource information corresponding to the first data, where the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information.

[0045] In some implementations, the transceiver unit is further used to receive fifth indication information, where the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

[0046] In a fourth aspect, a communication device is provided, comprising a processing unit and a transceiver unit, wherein the transceiver unit is used to receive a first data set and first indication information, wherein the data in the first data set is used for training a first AI model, and the first indication information indicates the function and / or characteristics of the first AI model; the processing unit is used to determine, based on the first indication information, that the data in the first data set is used for training the first AI model.

[0047] In some implementations, the first data set includes a first data subset and a second data subset, the first indication information also indicates the function and / or characteristics of the AI ​​model corresponding to the first data subset and / or the second data subset, and the processing unit is further used to determine the AI ​​model corresponding to the first data subset and / or the second data subset based on the first indication information.

[0048] In certain implementations, the first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first dataset and / or usage information of the first dataset, and the first indication information indicates that the function and / or feature of the first AI model includes:

[0049] The first indication information indicates the function and / or feature of the first AI model through the identifier of the first AI model and / or the identifier of the function, or the identifier of the first data set and / or the usage information of the first data set.

[0050] The processing unit is further used to determine the purpose of the first data set and / or the first AI model corresponding to the first data set based on the first indication information.

[0051] In some implementations, the first data set is also used for training a second AI model, the first indication information further indicates functions and / or features of the second AI model, and the processing unit is further used to determine the second AI model based on the first indication information.

[0052] In some implementations, the transceiver unit is further configured to receive a second data set and second indication information, where the second indication information indicates functions and / or features of the first AI model.

[0053] In some implementations, the second indication information and the first indication information have the same value.

[0054] In some implementations, the first data set includes a first data sample and a second data sample, and the transceiver unit is further used to receive third indication information, wherein the third indication information indicates that the first data sample and the second data sample share first data, and the first data belongs to the first data set; the processing unit is further used to determine, based on the third indication information, that the first data is used for the first data sample and the second data sample.

[0055] In some implementations, the first data is label information corresponding to input data and / or output data.

[0056] In some implementations, the transceiver unit is further used to receive fourth indication information, wherein the fourth indication information indicates an identifier of the first data and / or indicates resource information corresponding to the first data, wherein the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information; the processing unit is further used to use the first data on resources determined based on the resource information.

[0057] In some implementations, the transceiver unit is further used to send fifth indication information, where the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

[0058] It should be understood that the third aspect and the fourth aspect are implementation methods on the device side corresponding to the first aspect and the second aspect. The explanations, supplements and descriptions of the beneficial effects of the first aspect and the second aspect are also applicable to the third aspect and the fourth aspect and will not be repeated here.

[0059] In a fifth aspect, the present application provides a communication device, comprising an interface circuit and a processor, wherein the interface circuit is used to implement the function of the transceiver unit in the third aspect, and the processor is used to implement the function of the processing unit in the third aspect.

[0060] In a sixth aspect, the present application provides a communication device, comprising an interface circuit and a processor, wherein the interface circuit is used to implement the function of the transceiver unit in the fourth aspect, and the processor is used to implement the function of the processing unit in the fourth aspect.

[0061] In the seventh aspect, the present application provides a computer-readable medium storing a program code for execution on a terminal device, the program code comprising instructions for executing the method of the first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect.

[0062] In an eighth aspect, an embodiment of the present application provides a computer-readable medium storing a program code for execution by a data acquisition device, the program code including instructions for executing the method of the second aspect, or any possible manner of the second aspect, or all possible manners of the second aspect.

[0063] In the ninth aspect, a computer program product storing computer-readable instructions is provided, which, when the computer-readable instructions are executed on a computer, enables the computer to execute the method of the first aspect, or any possible method of the first aspect, or all possible methods of the first aspect.

[0064] In the tenth aspect, a computer program product storing computer-readable instructions is provided, which, when the computer-readable instructions are run on a computer, enables the computer to execute the method of the above-mentioned second aspect, or any possible method of the second aspect, or all possible methods of the second aspect.

[0065] In the eleventh aspect, a communication system is provided, which includes a device having functions of implementing the above-mentioned first aspect, or any possible manner in the first aspect, or all possible manners in the first aspect, the second aspect, or any possible manner in the second aspect, or all possible manners in the second aspect, and various possible designed functions.

[0066] In the twelfth aspect, a processor is provided, which is coupled to a memory and is used to execute the method of the above-mentioned first aspect, or any possible method of the first aspect, or all possible methods of the first aspect.

[0067] In a thirteenth aspect, a processor is provided, coupled to a memory, for executing the method of the second aspect, or any possible manner of the second aspect, or all possible manners of the second aspect.

[0068] In a fourteenth aspect, a chip system is provided, comprising a processor and a memory configured to execute computer programs or instructions stored in the memory, so that the chip system implements the method of any of the aforementioned first or second aspects, as well as any possible implementation of either aspect. The chip system may be composed of a chip alone, or may include a chip and other discrete components. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] FIG1 is a schematic diagram of a possible application framework in a communication system.

[0070] FIG2 is a schematic diagram of another possible application framework in a communication system.

[0071] FIG3 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0072] FIG4 is a schematic diagram of another communication system applicable to an embodiment of the present application.

[0073] FIG5 is a schematic block diagram of an autoencoder.

[0074] FIG6 is a schematic diagram of an AI application framework.

[0075] FIG7 is a schematic diagram of an information transmission method proposed in an embodiment of the present application.

[0076] FIG8 is a schematic diagram of data sharing.

[0077] FIG9 is a schematic block diagram of a communication device.

[0078] FIG10 is a schematic block diagram of yet another communication device.

[0079] FIG11 is a schematic block diagram of yet another communication device. DETAILED DESCRIPTION

[0080] The technical solution in this application will be described below with reference to the accompanying drawings.

[0081] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, wireless local area networks (WLAN) systems, satellite communication systems, future communication systems, or a fusion system of multiple systems. The technical solutions provided in this application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0082] A device in a communication system can send a signal to another device or receive a signal from another device. The signal may include information, signaling, or data. The device may also be replaced by an entity, a network entity, a network element, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the device as an example for description. For example, the communication system may include at least one terminal device and at least one network device. The network device may send a downlink signal to the terminal device, and / or the terminal device may send an uplink signal to the network device. It is understood that the terminal device in the present disclosure may be replaced by the first device, and the network device may be replaced by the second device, and both perform the corresponding information transmission method in the present disclosure.

[0083] In an embodiment of the present application, the terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0084] The terminal device may be a device that provides voice / data, such as a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals are: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or future evolved public land mobile communication networks (PLMNs). The terminal equipment in the network (PLMN), etc., is not limited to this in the embodiments of the present application.

[0085] 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.

[0086] In the embodiments of the present application, the device for realizing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to realize the function, such as a chip system, which can be installed in the terminal device or used in combination with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices. In the embodiments of the present application, only the terminal device is used as an example for description, and the embodiments of the present application are not limited to the solutions of the embodiments of the present application.

[0087] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and the network device may include an access network device or a radio access network device, such as a base station. The access network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects the terminal device to a wireless network. A base station may broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), master station, secondary station, multi-standard radio (motor slide retainer, MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. A base station may be a macro base station, a micro base station, a relay node, a donor node, or the like, or a combination thereof. The base station may also refer to a communication module, modem or chip used to be set in the aforementioned equipment or device. The base station may also be a mobile switching center and a device that performs the base station function in D2D, V2X, and M2M communications, a device that performs the base station function in future communication systems, etc. The base station can support networks with the same or different access technologies. Optionally, the RAN node may also be a server, a wearable device, a vehicle or an on-board device, etc. For example, the access network device in the vehicle to everything (V2X) technology may be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0088] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0089] In some deployments, the network devices mentioned in the embodiments of the present application may include a CU, a DU, or both a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)), a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network devices may include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0090] In some deployments, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing portions of the base station's functionality. For example, a RAN node can be a CU, DU, CU-CP, CU-UP, or RU. The CU and DU can be separate or included in the same network element, such as the BBU. The RU can be included in a radio frequency device or radio unit, such as an RRU, AAU, or RRH.

[0091] The RAN node may support one or more types of fronthaul interfaces, with different fronthaul interfaces corresponding to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0092] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0093] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0094] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (open RAN, ORAN / O-RAN) system, CU may also be referred to as O-CU (open CU), DU may also be referred to as O-DU, CU-CP may also be referred to as O-CU-CP, CU-UP may also be referred to as O-CU-UP, and RU may also be referred to as O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0095] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0096] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0097] In wireless communication networks, such as mobile communication networks, the services supported by the networks are becoming increasingly diverse, and therefore the demands that need to be met are becoming increasingly diverse. For example, the network needs to be able to support ultra-high speeds, ultra-low latency, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as network functionality becomes increasingly powerful, such as supporting higher spectrum, supporting high-order multiple input multiple output (MIMO) technology, supporting beamforming, and / or supporting new technologies such as beam management, network energy saving has become a hot research topic. These new demands, new scenarios, and new features have brought unprecedented challenges to network planning, operation and maintenance, and efficient operation. To meet this challenge, artificial intelligence technology can be introduced into wireless communication networks to achieve network intelligence.

[0098] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0099] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment, or the AI ​​node can be deployed separately, for example, in a location outside any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, and the other devices can be, for example, one or more of the following: access network equipment, terminal equipment, or network elements of the core network. Based on the object served by the AI ​​entity, the AI ​​entity can include an AI entity on the network device side, an AI entity on the terminal device side, or an AI entity on the core network side.

[0100] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0101] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0102] An AI node may be an AI network element or an AI module. An AI entity is used to implement corresponding AI functions. The AI ​​modules deployed in different network elements may be the same or different. The AI ​​model in the AI ​​entity may implement different functions according to different parameter configurations. The AI ​​model in the AI ​​entity may be configured based on one or more of the following parameters: structural parameters (e.g., the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the biases in the activation function), input parameters (e.g., the type of input parameters and / or the dimension of the input parameters), or output parameters (e.g., the type of output parameters and / or the dimension of the output parameters). The bias in the activation function may also be referred to as the bias of the neural network.

[0103] An AI entity can have one or more models. The learning, training, or inference processes of different models can be deployed in different entities or devices, or in the same entity or device.

[0104] Figure 1 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1, network elements in the communication system are connected through interfaces (such as next generation interfaces (NG), Xn interfaces) or air interfaces. One or more AI modules are provided in one or more devices of these network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals or OAM (for the sake of clarity, only one is shown in Figure 1). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0105] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0106] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0107] Figure 2 is a schematic diagram of a possible application framework in a communication system. As shown in Figure 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1, which are used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real time RIC, near-RT RIC) and a non-real-time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0108] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near real-time RIC delivers the reasoning result to the DU, and the DU sends it to the RU.

[0109] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0110] The near real-time RIC and non-real-time RIC may also be separately configured as a network element. Optionally, the near real-time RIC and non-real-time RIC may also be part of other devices. For example, the near real-time RIC is configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC is configured in an OAM, a cloud server, a core network device, or other network device.

[0111] FIG3 is a schematic diagram of a communication system applicable to the information transmission method of an embodiment of the present application. As shown in FIG3 , the communication system 100 may include at least one network device, such as the network device 110 shown in FIG3 ; the communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG3 . The network device 110 and the terminal device (such as the terminal device 120 and the terminal device 130) can communicate via a wireless link. The communication devices in the communication system, for example, the network device 110 and the terminal device 120, can communicate via a multi-antenna technology.

[0112] Figure 4 is a schematic diagram of another communication system applicable to the information transmission method of an embodiment of the present application. Compared to the communication system 100 shown in Figure 3, the communication system 200 shown in Figure 4 also includes an AI network element 140. AI network element 140 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0113] In one possible implementation, the network device 110 may send data related to the training of the AI ​​model to the AI ​​network element 140, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 140 may send the results of the operations related to the AI ​​model to the network device 110, and forward them to the terminal device through the network device 110. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 110, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 110. Alternatively, the trained AI model may be deployed on the terminal device.

[0114] It should be understood that Figure 4 illustrates only the example of a direct connection between AI network element 140 and network device 110. In other scenarios, AI network element 140 may also be connected to a terminal device. Alternatively, AI network element 140 may be connected to both network device 110 and a terminal device simultaneously. Alternatively, AI network element 140 may be connected to network device 110 through a third-party network element. This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0115] The AI ​​network element 140 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 110 or the terminal device shown in FIG3 .

[0116] It should be noted that Figures 3 and 4 are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 3 and 4. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0117] To facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0118] 1. Artificial Intelligence: This refers to the ability of machines to learn, accumulate experience, and solve problems that humans can solve through experience, such as natural language understanding, image recognition, and chess. Artificial Intelligence can be understood as the intelligence exhibited by machines created by humans. Generally, AI refers to the technology that represents human intelligence through computer programs. The goals of AI include understanding intelligence by constructing computer programs that can perform symbolic reasoning or deduction.

[0119] 2. Machine learning: This is an implementation of artificial intelligence. Machine learning is a method that empowers machines to learn, enabling them to perform functions that cannot be accomplished through direct programming. In practical terms, machine learning utilizes data to train models and then uses these models to make predictions. There are many machine learning methods, such as neural networks (NNs), decision trees, and support vector machines. Machine learning theory primarily involves the design and analysis of algorithms that enable computers to learn automatically. Machine learning algorithms automatically analyze data to identify patterns and use these patterns to make predictions about unknown data.

[0120] 3. Neural Network: A specific embodiment of machine learning. A neural network is a mathematical model that processes information by mimicking the behavioral characteristics of animal neural networks. The concept of a neural network is derived from the neuronal structure of the brain. Each neuron performs a weighted sum operation on its input values, and the result of this weighted summation is passed through an activation function to generate an output.

[0121] Neural networks generally comprise a multi-layer structure, with each layer comprising one or more logical decision units, referred to as neurons. Increasing the depth and / or width of a neural network can enhance its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can be understood as the number of layers it comprises, and the number of neurons in each layer can be referred to as the width of that layer. In one possible implementation, a neural network comprises an input layer and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to the output layer, which then obtains the output of the neural network. In another possible implementation, a neural network comprises an input layer, a hidden layer, and an output layer. The input layer of the neural network processes the input through neurons and then passes the result to an intermediate hidden layer. The hidden layer then passes the calculation result to the output layer or an adjacent hidden layer, which then obtains the output of the neural network. A neural network can comprise one or more sequentially connected hidden layers, without limitation.

[0122] During neural network training, a loss function can be defined. This function measures the difference between the model's predicted value and the actual value. During neural network training, the loss function describes the gap or discrepancy between the neural network's output and the ideal target value. Neural network training involves adjusting neural network parameters to ensure that the loss function's value is below a threshold or meets the target requirement. Neural network parameters can include at least one of the following: the number of neural network layers, their width, neuron weights, and parameters in the neuron activation function.

[0123] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this disclosure can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0124] 4. Deep neural network: A neural network with multiple hidden layers.

[0125] 5. Deep learning: Machine learning using deep neural networks.

[0126] 6. AI Model

[0127] An AI model is an algorithm or computer program that implements AI functionality. It represents the mapping between the model's inputs and outputs. AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0128] 7. Two-end model:

[0129] The two-end model can also be called a bilateral model, collaborative model, dual model, or two-side model. A two-end model is a model composed of multiple sub-models. The sub-models that make up the model must match each other. These sub-models can be deployed on different nodes.

[0130] The embodiments of the present application relate to an encoder for compressing channel state information (CSI) and a decoder for recovering compressed CSI. The encoder and decoder are used in matching manner, and it can be understood that the encoder and decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched with the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and corresponds one to one.

[0131] In one possible design, a matched set of encoders and decoders can be specifically two parts of the same auto-encoder (AE), as shown in Figure 5. An AE model, in which the encoder and decoder are deployed on different nodes, is a typical bilateral model. The encoder and decoder of an AE model are typically trained together and used in pairs. The encoder processes the input V to produce the processed output z, and the decoder decodes the encoder output z into the desired output V'.

[0132] An autoencoder is a type of neural network that performs unsupervised learning. Its characteristic is that it uses input data as labeled data. Therefore, an autoencoder can also be understood as a self-supervised learning neural network. Autoencoders can be used for both data compression and recovery. For example, the encoder in an autoencoder can compress (encode) data A to produce data B; the decoder in the autoencoder can decompress (decode) data B to recover data A. Alternatively, the decoder can be understood as the inverse operation of the encoder.

[0133] For example, the AI ​​model in the embodiments of the present application may include an encoder and a decoder. The encoder and decoder are used in combination, and it can be understood that the encoder and decoder are a matching AI model. The encoder and decoder can be deployed on terminal devices and network devices respectively.

[0134] Alternatively, the AI ​​model in the embodiment of the present application may be a single-end model, which may be deployed on a terminal device or a network device.

[0135] 8. Training data set and inference data:

[0136] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0137] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0138] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0139] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function, or objective function. These are important equations used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0140] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0141] 9. AI model design:

[0142] The design of an AI model primarily involves data collection (e.g., collecting training data and / or inference data), model training, and model inference. Furthermore, it can also include the application of inference results.

[0143] FIG6 shows an AI application framework.

[0144] In the aforementioned data collection phase, the data source is used to provide training datasets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training node is equivalent to learning the mapping relationship between the model's input and output using the training data. In the model inference phase, the AI ​​model trained in the model training phase is used to perform inference based on the inference data provided by the data source, obtaining an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by the execution (actor) entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., network devices or terminal devices) for execution. Alternatively, the execution entity can provide feedback on the model's performance to the data source to facilitate subsequent model update and training.

[0145] It is understandable that a communication system may include network elements with artificial intelligence capabilities. The above-mentioned AI model design-related steps can be performed by one or more network elements with artificial intelligence capabilities. In one possible design, AI functions (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as AI model training and / or inference. For example, the existing network element can be a network device or a terminal device. Alternatively, in another possible design, an independent network element can be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element can be referred to as an AI network element or an AI node, etc., and the embodiments of the present application are not limited to these names. For example, the AI ​​network element can be directly connected to the network equipment in the communication system, or it can be indirectly connected to the network equipment through a third-party network element. The third-party network element can be a core network element such as an authentication management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM), a cloud server, or other network element, without limitation. Exemplarily, the independent network element can be deployed on one or more of the following: a network device side, a terminal device side, or a core network side. Optionally, it can be deployed on a cloud server. Exemplarily, the communication system shown in FIG4 introduces an AI network element 140.

[0146] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The inference process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training phase of a terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training phase of a network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training phase of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, the model inference phase corresponding to the encoder is performed in the terminal device, and the model inference phase corresponding to the decoder is performed in the network device.

[0147] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0148] 10. Model training: The process of selecting a suitable loss function and using an optimization algorithm to train the model parameters so that the value of the loss function is less than the threshold, or the value of the loss function meets the target requirements.

[0149] 11. Model application: Use the trained model to solve practical problems.

[0150] 12. Channel information:

[0151] In a communication system (e.g., an LTE or NR communication system), network equipment determines one or more of the following configurations, including resources, modulation and coding scheme (MCS), and precoding, for scheduling the downlink data channel of a terminal device based on channel information. It is understood that channel information, also known as channel state information (CSI) or channel environment information, is information that can reflect channel characteristics and channel quality.

[0152] Channel information measurement refers to the receiving end solving the channel information based on the reference signal sent by the transmitting end, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of a channel state information reference signal (CSI-RS), a synchronization signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), or a demodulation reference signal (DMRS). CSI-RS, SSB, and DMRS can be used to measure downlink channel information. SRS and DMRS can be used to measure uplink channel information. Among them, channel information measurement can also be called CSI measurement or channel environment information measurement.

[0153] The channel information may be determined based on a channel measurement result of a reference signal. Alternatively, the channel information may be a channel measurement result of a reference signal. In an embodiment of the present application, the channel measurement result of a reference signal may also be replaced by the channel information.

[0154] Taking FDD communication scenarios as an example, in FDD communication scenarios, because uplink and downlink channels are not reciprocal or cannot be guaranteed, network equipment typically transmits a downlink reference signal to the terminal device. The terminal device performs channel and interference measurements based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report based on a protocol predefined method or a network device configuration method and feeds it back to the network device to obtain the downlink CSI.

[0155] In the present application, the meaning of CSI is broader than that of CSI in traditional solutions, and is not limited to channel quality indication (CQI), precoding matrix indicator (PMI), rank indicator (RI), or CSI-RS resource indicator (CRI). It can also be one or more of channel response information (such as channel response matrix, frequency domain channel response information, time domain channel response information), weight information corresponding to channel response, reference signal receiving power (RSRP) or signal to interference plus noise ratio (SINR). Among them, RI is used to indicate the number of layers of downlink transmission recommended by the terminal device, CQI is used to indicate the modulation and coding mode that can be supported by the current channel conditions determined by the terminal device, and PMI is used to indicate the precoding recommended by the terminal device. The number of precoding layers indicated by PMI corresponds to RI.

[0156] It should be understood that the RI, CQI, and PMI indicated in the above CSI report are only recommended values ​​for the terminal device, and the network device may perform downlink transmission according to part or all of the information indicated in the CSI report. Alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

[0157] As previously described, channel information can be obtained by measuring the reference signal. Feedback information can be obtained by compressing and / or quantizing the channel information. The feedback information can be reported via a channel information report (also known as a CSI report). The channel information can be recovered by decompressing and / or dequantizing the feedback information.

[0158] Feedback information may also be referred to as feedback information of channel information, feedback information of CSI, CSI feedback information, compressed information, compressed information of channel information, compressed information of CSI, compressed channel information, or compressed CSI, etc.

[0159] The recovered channel information may also be referred to as CSI recovery information.

[0160] The introduction of AI technology into wireless communication networks has resulted in a CSI feedback method based on AI models. Terminal devices use AI models to compress and feedback CSI, and network equipment uses AI models to recover the compressed CSI. AI-based CSI feedback transmits a sequence (such as a bit sequence), resulting in lower overhead than traditional CSI feedback.

[0161] Taking Figure 5 as an example, the encoder in Figure 5 can be a CSI generator, and the decoder can be a CSI reconstructor. The encoder can be deployed in a terminal device, and the decoder can be deployed in a network device. The terminal device can use the encoder to generate CSI feedback information z from channel information V. The terminal device reports a CSI report, which can include CSI feedback information z. The network device can reconstruct the CSI information using the decoder, thereby obtaining CSI recovery information V'.

[0162] The channel information V may be obtained by the terminal device through CSI measurement. For example, the channel information V may include the channel response of the downlink channel or the eigenvector matrix of the downlink channel (a matrix composed of eigenvectors). The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and / or quantization operations of the eigenmatrix according to the codebook in the related scheme are replaced by operations in which the encoder processes the eigenmatrix to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through a decoder to obtain CSI recovery information V'.

[0163] The following further illustrates the training process and reasoning process of the AI ​​model in the embodiments of the present application.

[0164] The training data used to train AI models includes training samples and sample labels. For example, the training samples are channel information determined by the terminal device, and the sample labels are the actual channel information, i.e., the true value CSI. If the encoder and decoder belong to the same autoencoder, the training data can only include the training samples, or the training samples are the sample labels.

[0165] In the field of wireless communications, the true CSI may be high-precision CSI.

[0166] The specific training process is as follows: the model training node uses the encoder to process the channel information, that is, the training sample, to obtain CSI feedback information, and uses the decoder to process the feedback information to obtain the recovered channel information, that is, the CSI recovery information. Then calculate the difference between the CSI recovery information and the corresponding sample label, that is, the value of the loss function, and update the parameters of the encoder and decoder according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, that is, minimize the loss function. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeat the above operations to obtain an encoder and decoder that meet the target requirements. The above model training node can be a terminal device, a network device, or other network elements with AI functions in a communication system.

[0167] It should be understood that the above description uses the AI ​​model for CSI compression as an example. The AI ​​model can also be used in other scenarios in CSI feedback. For example, the AI ​​model can be used for CSI prediction, that is, predicting channel information at one or more future moments based on channel information measured at one or more historical moments. The embodiments of this application do not limit the specific use of the AI ​​model in CSI feedback scenarios.

[0168] It should be understood that, in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication of information A refers to including information A; implicit indication of information A refers to indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0169] It should be understood that, in this application, information C is used to determine information D, which includes both information D being determined solely based on information C and information D being determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0170] In addition, in each embodiment of the present application, "network element A sends information A to network element B" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0171] Exemplarily, the network device may be a core network device, an access network node (RAN node) or one or more devices in OAM shown in Figure 1. For example, the AI ​​module may be the RIC shown in Figure 2, such as a near real-time RIC or a non-real-time RIC. For example, the near real-time RIC is set in the RAN node (e.g., CU, DU), while the non-real-time RIC is set in the OAM, in the cloud server, in the core network device, or in other network devices. The RIC can be obtained by obtaining a subset from multiple terminal devices from a RAN node (e.g., CU, CU-CP, CU-UP, DU and / or RU), reorganizing it into a training data set #2, and training based on the training data set #2.

[0172] For example, the near real-time RIC and the non-real-time RIC may also be separately configured as a network element, and the network device may be the near real-time RIC or the non-real-time RIC.

[0173] At present, the training of the AI ​​model on the UE side is often triggered by the UE itself to collect relevant data. At the same time, since it is a one-sided model, if there are different models on the UE side that meet different needs, it is necessary to determine the association between the data set and the AI ​​model through the input and output of the AI ​​model, or to determine the association between the data set and the AI ​​model through the correspondence between the input and output. For example, in AI-based sparse beam management, the input is often determined by scanning a subset of all beams to obtain the RSRP, and the output predicted by the model is the information of all beams, such as the predicted RSRP of all beams or the probability that each beam in all beams becomes the optimal beam. Alternatively, the correspondence between each input and output and the AI ​​model is identified by the quasi-colocation (QCL) relationship corresponding to the input and output. Alternatively, the correspondence between the input and output and the AI ​​model is determined by more direct information, such as the beam shape and beamwidth of the network-side beam in beam management.

[0174] In the process of transmitting the model training data set to the UE, if the data transmitted by the network side is a data set (i.e., multiple data samples), it is difficult for the UE to distinguish the two-to-two correspondences between multiple sets of data in a data set (i.e., identifying AI inputs, AI outputs, or multiple AI outputs or inputs). If each transmission is only a single piece of data, it is difficult for the UE to identify the association between the multiple transmissions of data. For example, if multiple sets of data correspond to the training of an AI model or a function, the UE needs to associate the multiple transmissions of data. This will waste the UE's power consumption.

[0175] In view of this, the present application proposes an information transmission method, which enables the training device to quickly determine the correspondence between the training data and the AI ​​model. The following uses the training device and the data acquisition device as examples of the sending and receiving ends to illustrate the method. It should be understood that the training device can be a network-side device or a terminal device. The type of training device is not limited in this application. The training device can be a network-side device, a terminal-side device, a part or component in a network-side device, or a part or component in a terminal-side device. For example, the method can be executed by a module in a data acquisition device and a training device, such as a chip or circuit or chip system, and this application does not limit this. For the sake of ease of description, the following is an example of the execution of a data acquisition device and a training device.

[0176] As shown in FIG7 , the method includes the following steps:

[0177] S710, the data acquisition device determines a first data set, and the data in the first data set is used for training a first artificial intelligence AI model.

[0178] The first data set may include at least one data sample. A data sample may also be referred to as data. Alternatively, the data may include one or more data samples, for example, the data may be composed of multiple data samples. Alternatively, the data may belong to a data sample, for example, the data sample may include one or more data. For example, the first data set includes data A, which is used to train the first AI model. In another example, the first data set includes data A, data B, data C, and so on, all of which are used to train the first AI model.

[0179] It should be understood that the first data set can be one data set or multiple data sets. This application does not limit the name of the first data set, for example, it can also be a first data group, a first data packet, etc., which can indicate the name of the data.

[0180] Optionally, the data included in the first data set can be used for AI model training until convergence. For example, the data in the first data set can be used for beam management of the first AI model training, and the first data set can include RSRP (Set B_1) for the input of the first AI model. The label used for the output of the first AI model, such as (Set A(1)), can be the RSRP of all beams or the identity document (ID) of the optimal beam, that is, the output of the first AI model is the RSRP of all beams, or the identification information of the optimal beam determined by the first AI model through training.

[0181] The function (or purpose) of the first AI model is not limited in this application. For example, in the above example, the function of the first AI model is training beam management. The first AI model can also be used for positioning training, channel prediction training, etc.

[0182] In one possible implementation, when the first data set is used to train the first AI model, the first data set may also include information related to the first AI model. For example, identification information of the first AI model, such as an ID. As another example, indexes corresponding to different AI models may be preconfigured, and the first data set may carry the index corresponding to the first AI model. It should be understood that the above-mentioned ID or index is merely an example of a method for identifying or distinguishing the first AI model. Other methods for identifying or distinguishing AI models may be applicable to this application and should be within the scope of protection of this application.

[0183] Furthermore, the first data set can also be used for training multiple AI models. For example, taking the example that the data included in the first data set can be used for training two AI models, the data included in the first data set can be used for training the first AI model, and can also be used for training the second AI model. Among them, the functions and / or features of the first AI model may be different from the functions and / or features of the second AI model. For example, the first AI model is used for positioning training, and the second AI model is used for beam management training. In this case, the first data set can correspond to information related to multiple AI models. For example, the first data set may include the ID of the first AI model, and the first data set may also include the ID of the second AI model. For example, the first data set includes (data1, data2, ID1, ID2), where data1 and data2 can be used for training the AI ​​model identified by ID1, and can also be used for training the AI ​​model identified by ID2.

[0184] In another possible scenario, the first data set includes the ID of the first AI function and the ID of the second AI function. When the AI ​​model corresponds to the function one-to-one, the training device can determine the corresponding AI model based on the function ID. When an AI function corresponds to multiple AI models, the data acquisition device can also issue an instruction message Q, which indicates which AI model the training device uses. For example, the instruction message Q indicates the ID of one or more AI models that support the function. Alternatively, the training device can autonomously determine which AI model or models to use for training among multiple AI models.

[0185] In one possible implementation, before the data acquisition device determines the first data set, the training device reports to the data acquisition device the relevant information of the AI ​​model supported by the training device. For example, the training device sends an indication message (i.e., the fifth indication message) to the data acquisition device, and the indication message indicates the functions and / or features of one or more AI models supported by the training device. That is, the training device reports to the data acquisition device which AI models need to be trained, and what types of data sets need to be issued by the data acquisition device to support the training of the AI ​​models. The indication message can also indicate the storage and / or computing power information of the training device, for example, how much data training the training device can support, or how much data can be stored. After completing the reporting of the training device, the data acquisition device can configure the corresponding data set according to the needs and / or capabilities of the training device. The needs of the training device are the functions and / or features corresponding to the AI ​​model that the training device needs to train. For example, the data acquisition device can configure a data set for AI beam management training, a data set for AI positioning training, or a data set for AI channel prediction training according to the needs and / or capabilities of the training device.

[0186] The function of the aforementioned AI model can also be the purpose of the AI ​​model. For example, the function of the first AI model is positioning training, that is, the first AI model is used for positioning training. The characteristics of the AI ​​model can include the input and / or output of the AI ​​model. For example, AI model #A and AI model #B are both used for beam management training, but AI model #A and AI model #B have at least one different input and output.

[0187] For example, Set B_1 can refer to a sparse beam, serving as the input for AI model #A, while Set B_2 can refer to another sparse beam, serving as the input for AI model #B. Assuming Set A has 64 beams, the possible beams selected by Set B_1 correspond to beam indices [1, 5, 9, …, 63], with every fourth beam being an odd number. Meanwhile, the possible beams selected by Set B_2 correspond to beam indices [0, 4, 8, …, 64], with every fourth beam being an even number. This means that AI model #A and AI model #B have different inputs, which can be considered different features. Alternatively, this means that the AI ​​models acquire input data differently. However, the outputs of AI model #A and AI model #B are the same. For example, AI model #A outputs the RSRP of all beams, and AI model #B also outputs the RSRP of all beams. Alternatively, the output of AI model #A and the output of AI model #B are both the IDs of the optimal beams obtained through training.

[0188] For example, let's assume that both AI Model #A and AI Model #B are used for beam management training. The inputs to AI Model #A and AI Model #B are Set B_1 and Set B_2, respectively. However, the output of AI Model #A is the RSRP of all beams, while the output of AI Model #B is the ID of the optimal beam obtained through training. This means that the outputs of AI Model #A and AI Model #B differ, which can be considered to indicate that the characteristics of AI Model #A and AI Model #B are different, or in other words, that AI Model #A and AI Model #B are different.

[0189] Optionally, in the same data set, there may be different data corresponding to different AI model functions and / or features. For example, the first data includes a first data subset and a second data subset, and the first data subset and the second data subset respectively correspond to different AI model features. The first data subset and / or the second data subset each contain the data in the first data set. For example, the first data includes {data 1, data 2, data 3, data 5, data 6, data 7}, and the first data subset includes {data 1, data 2, data 3}, which can be used for training model A; the second data subset includes {data 5, data 6, data 7}, which can be used for training model B. Model A and model B have different functions, or in other words, model A and model B have different features.

[0190] Optionally, in the same data set, different data subsets may correspond to different first features of the AI ​​model, but the same second features, and the AI ​​model functions are the same. For example, the first data includes a first data subset and a second data subset, and the first data subset and the second data subset respectively correspond to different features of the same AI model, such as different inputs of the same AI model, but the first data subset and the second data subset both correspond to the AI ​​model, and the corresponding outputs, i.e., the true value labels, are the same.

[0191] For example, Set B_1 can refer to a sparse beam, which is the input of AI Model #A, while Set B_2 can refer to another sparse beam, which is also the input of AI Model #A. Assuming that Set A has 64 beams, the beams that Set B_1 may select correspond to beam indices [1, 5, 9, … 63], i.e., every fourth beam is an odd number; while the beams that Set B_2 may select correspond to beam indices [0, 4, 8, …, 64], i.e., every fourth beam is an even number. In other words, Set B_1 and Set B_2 are both inputs to AI Model #A, and their corresponding outputs are the same. Thus, AI Model #A trained based on Set B_1 and Set B_2 has better generalization performance.

[0192] S720, the data acquisition device sends a first data set and first indication information to the training device. Correspondingly, the training device receives the first data set and first indication information, where the first indication information indicates the function and / or characteristics of the first AI model.

[0193] For the first data set, reference may be made to the description in S710 and details thereof will not be repeated.

[0194] The first indication information may indicate relevant information about the first AI model, such as the ID of the first AI model and / or information about the function of the first AI model. Specifically, the first indication information may include the identifier of the first AI model and / or the identifier of its function. The first indication information may also indicate information about the first dataset, such as the identifier of the first dataset and / or information about the usage of the first dataset.

[0195] When the first data set includes a first data subset and a second data subset, the first indication information may also indicate the function and / or feature of the AI ​​model corresponding to the first data subset and / or the second data subset. For example, the first indication information indicates the function identifier and / or feature identifier of the AI ​​model corresponding to the first data subset and / or the second data subset. It should be understood that the first indication information may indicate the function identifier and / or feature identifier of the AI ​​model corresponding to the first data subset and the second data subset respectively through different fields, or may indicate the function identifier and / or feature identifier of the AI ​​model corresponding to the first data subset and the second data subset through the same field. This application does not limit this.

[0196] When the first dataset is also used to train a second AI model, the first indication information also indicates the function and / or feature of the second AI model. For example, the first indication information indicates the function identifier and / or feature identifier of the second AI model. In other words, a dataset can be used to train multiple A models. In order to identify the purpose of the dataset, or to identify the different AI models corresponding to the dataset, the dataset can have multiple identification information, each corresponding to a different AI model.

[0197] It should be understood that when the AI ​​models corresponding to the data sets are the same, the identification information corresponding to the data sets is the same. For example, the data acquisition device determines the second data set, sends the second data set and second indication information to the training device, and the second indication information indicates the function and / or feature of the first AI model. The values ​​of the second indication information and the first indication information can be the same. For example, the first data set is used for positioning training of the first AI model, and the second data set is also used for positioning training of the first AI model, and the same identification (such as assigning the same number) can be used.

[0198] In a possible implementation, the first data set includes a first data sample and a second data sample. The first data sample and the second data sample share a portion of data (ie, first data), and the first data belongs to the first data set.

[0199] In one possible approach, the data acquisition device sends third indication information to the training device, and the training device receives the third indication information in response. The third indication information may indicate that the first data sample and the second data sample share the first data. For example, corresponding identification information may be configured for each data item, and the identification information is used to indicate whether the data item needs to be shared twice or more.

[0200] This implementation is applicable to AI time-domain prediction scenarios, such as AI-based channel prediction and AI-based time-domain beamforming. In these scenarios, historical information can be input into the AI ​​to predict future information. This type of prediction is performed based on a sliding window during training. For example, as shown in Figure 8, the AI ​​input is based on two time points, and the AI ​​output is information from two future time points. In this scenario, during the first training session, the AI ​​input is information from time points T1 and T2, and the output is information from time points T3 and T4. During the second training session, the AI ​​input is information from time points T2 and T3, and the output corresponds to information from time points T4 and T5. It can be seen that in this case, the information at time point T2 is reused as input, and the information at time point T4 is reused as output. The reused data needs to be transmitted twice, resulting in air interface transmission overhead and storage overhead for the training device. In this approach, the use of third indication information to indicate shared data can prevent the shared data from being transmitted multiple times, thereby reducing air interface transmission overhead and storage overhead for the training device.

[0201] Specifically, take the AI ​​model used for beam management training as an example:

[0202] Regarding AI model input: If the first data input is the dataset RSRP_1 and RSRP_2 (1 and 2 indicate the time sequence, respectively) scanned at two moments, and the second data input is RSRP_2 and RSRP_3, RSRP_2 is multiplexed. When transmitting data, RSRP_2 is marked as "shared" and activated, while RSRP_1 and RSRP_3 are marked as "shared" and deactivated, i.e., "not shared." For example, this can be done using a bitmap, where a single bit indicates whether the data is shared. The shared activation flag for this transmission of RSRP_1, RSRP_2, and RSRP_3 is 010. It should be understood that there are no limitations on bit values ​​and the meaning they represent. For example, a bit value of 0 can indicate that the corresponding data is shared or not shared. The same applies to a bit value of 1.

[0203] For the AI ​​model's output, the labels corresponding to the output are information for two future moments. The first output is label_1 and label_2, and the second output is label_2 and label_3. Similarly, the transmitted data is identified using a bitmap. For the output labels label_1, label_2, and label_3, their shared identification information is 010.

[0204] In another possible manner, the data acquisition device sends fourth indication information to the training device, and the training device receives the fourth indication information in response. The fourth indication information indicates an identifier of the first data, or indicates resource information corresponding to the first data, where the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information.

[0205] That is, each data in the first data set is assigned a corresponding identifier, and which data is shared (also called multiplexed) is indicated in the fourth indication information. Alternatively, the resource information corresponding to the shared data is directly indicated, and the training device can use the data on these resources.

[0206] Taking the sliding window training used by the training device as an example, the fourth indication information may indicate time domain information. Specifically:

[0207] For input: The input at each moment corresponds to a time window. For example, RSRP_1 corresponds to T_1, RSRP_2 corresponds to T_2, and RSRP_3 corresponds to T_3. The input of the first AI model is the RSRP at T_1 and T_2, and the input of the second AI model is the RSRP at T_2 and T_3. The reuse of RSRP_2 can be indicated by two dimensions: one is the indication time T_2, and the other is the shared activation indication (that is, the bit value 0 / 1 in the possible method mentioned above). The indication information corresponding to RSRP_2 is [T_2,1].

[0208] For output: the same as input, that is, label_1(T_3) and label_2(T_4) are the labels corresponding to the output of the first AI model, label_2(T_4) and label_3(T_5) are the labels corresponding to the output of the second AI model, then the indication information of label_2 is [T_3,1].

[0209] It should be understood that the above numerical values ​​and corresponding relationships are only examples and not limitations.

[0210] S730: The training device determines, based on the first indication information, that data in the first data set is used for training the first AI model.

[0211] The information transmission method of the present application can be applied to air interface transmission scenarios of training data. When the data acquisition device sends down the training data, it carries indication information indicating the purpose of the data, which can associate or distinguish different training data, making it convenient for the training device to identify the association between different training data and the purpose of the training data, so as to meet the training requirements of different AI models and save the cost of the training device. Furthermore, in scenarios where data reuse is required, the data acquisition device indicates these reused data through indication information, and the training device can identify the purpose of different data in the data set, reduce the repeated sending of data, reduce the transmission volume of air interface data, and achieve the purpose of reducing air interface overhead.

[0212] It should be understood that the design of the indication information is not limited in this application. For example, the first indication information may be carried in the first data set, or the first indication information and the first data set may be carried in different signaling. The first indication information and other indication information, such as the second indication information, may be carried in the same signaling or in different signaling.

[0213] It is understood that in some of the above embodiments, the training device and the data acquisition device are primarily used as examples for illustration, and this is not intended to be limiting. For example, the training device may be replaced by a component of the training device (e.g., a chip or circuit), and the data acquisition device may be replaced by a component of the data acquisition device (e.g., a chip or circuit).

[0214] Optionally, the training device in the present application may be a data acquisition device or a terminal device. The present application does not limit this. Any device that can complete the data training task can be applicable to the solution of the present application.

[0215] It can also be understood that the solutions in the various embodiments of the present application can be reasonably combined and used, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained with each other in the various embodiments, without limitation to this.

[0216] Figure 9 is a schematic block diagram of a communication device 900 provided in an embodiment of the present application. The device 900 includes a transceiver unit 910 and a processing unit 920. The transceiver unit 910 can be used to implement corresponding communication functions. The transceiver unit 910 can also be referred to as a communication interface or a communication unit. The processing unit 920 can be used to perform data processing.

[0217] Optionally, the device 900 may further include a storage unit, which may be used to store instructions and / or data. The processing unit 920 may read the instructions and / or data in the storage unit so that the device implements the aforementioned method embodiment.

[0218] As a design, the device 900 is used to execute the steps or processes executed by the data acquisition device in the above method embodiments, or a device equipped with the data acquisition device, or a chip used for the data acquisition device, such as the steps or processes executed by the data acquisition device in the embodiment shown in Figure 7. The transceiver unit 910 is used to perform the transceiver-related operations on the data acquisition device side (or the transmitting end) in the above method embodiments, and the processing unit 920 is used to perform the processing-related operations on the data acquisition device side (or the transmitting end) in the above method embodiments.

[0219] In one possible implementation, the processing unit 920 is used to determine a first data set, where data in the first data set is used to train a first artificial intelligence AI model.

[0220] In one example, the first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first data set and / or usage information of the first data set.

[0221] The transceiver unit 910 is used to send the first data set and first indication information, where the first indication information indicates the function and / or characteristics of the first AI model.

[0222] As another design, the device 900 is used to execute the steps or processes executed by the training device, or a device equipped with the training device, or a chip used for the training device in the above method embodiments, such as the steps or processes executed by the training device in the embodiment shown in Figure 7. The transceiver unit 910 is used to perform the transceiver-related operations on the training device side (or receiving end) in the above method embodiments, and the processing unit 920 is used to perform the processing-related operations on the training device side (or receiving end) in the above method embodiments.

[0223] In one possible implementation, the transceiver unit 910 is used to receive a first data set and first indication information, where the data in the first data set is used for training a first AI model, and the first indication information indicates the function and / or feature of the first AI model; the processing unit 920 is used to determine, based on the first indication information, that the data in the first data set is used for training the first AI model.

[0224] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0225] It should also be understood that the device 900 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merging logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 900 can be specifically the first terminal device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the first terminal device in the above-mentioned various method embodiments, or the device 900 can be specifically the second terminal device in the above-mentioned embodiment, and can be used to execute the various processes and / or steps corresponding to the second terminal device in the above-mentioned various method embodiments. To avoid repetition, it will not be described here.

[0226] The apparatus 900 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the first terminal device in the above-mentioned method, or the apparatus 900 of each of the above-mentioned solutions has the function of implementing the corresponding steps performed by the second terminal device in the above-mentioned method. The functions can be implemented by hardware, or can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as the processing unit, can be replaced by a processor to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

[0227] In addition, the transceiver unit 910 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

[0228] It should be noted that the apparatus in FIG9 may be a network element or device in the aforementioned embodiment, or may be a chip or chip system, such as a system on chip (SoC). The transceiver unit may be an input / output circuit or a communication interface; the processing unit may be a processor, microprocessor, or integrated circuit integrated on the chip. This is not limited here.

[0229] FIG10 is a schematic diagram of another communication device 1000 provided in an embodiment of the present application. The device 1000 includes a processing circuit 1010, which is coupled to a memory 1020. The memory 1020 is used to store computer programs or instructions and / or data. The processing circuit 1010 is used to execute the computer programs or instructions stored in the memory 1020, or read the data stored in the memory 1020, to perform the methods in the above method embodiments.

[0230] Optionally, the processing circuit 1010 is one or more processors or a circuit in one or more processors for processing or control.

[0231] Optionally, there are one or more memories 1020 .

[0232] Optionally, the memory 1020 is integrated with the processing circuit 1010 or provided separately.

[0233] Optionally, as shown in Figure 10, the device 1000 further includes a transceiver circuit 1030, which is used to receive and / or send signals. For example, the processing circuit 1010 is used to control the transceiver circuit 1030 to receive and / or send signals.

[0234] As an example, the processing circuit 1010 may have the function of the processing unit 820 shown in FIG. 8 , the memory 1020 may have the function of a storage unit, and the transceiver circuit 1030 may have the function of the transceiver unit 810 shown in FIG. 8 .

[0235] As a solution, the device 1000 is used to implement the operations performed by the data acquisition device in each of the above method embodiments.

[0236] For example, the processing circuit 1010 is configured to execute computer programs or instructions stored in the memory 1020 to implement the relevant operations of the data acquisition device in the above various method embodiments. For example, the method executed by the data acquisition device in the embodiment shown in FIG7 .

[0237] As another solution, the device 1000 is used to implement the operations performed by the training device in the above various method embodiments.

[0238] For example, the processing circuit 1010 is configured to execute computer programs or instructions stored in the memory 1020 to implement the relevant operations of the training device in the above various method embodiments. For example, the method executed by the training device in the embodiment shown in FIG7 .

[0239] It should be understood that the device 1000 can be the aforementioned data acquisition device, training device, a chip for a data acquisition device or a training device, or a device including a data acquisition device or a training device.

[0240] When the device 1000 is a data acquisition device or user equipment, the transceiver circuit 1030 may be a transceiver.

[0241] When the device 1000 is a chip used in a data acquisition device or a training device, the transceiver circuit 1030 may be an input / output interface.

[0242] When the device 1000 is a device that is physically independent of the data acquisition device or user equipment, such as an OTT device or a cloud server, the device 1000 communicates with the data acquisition device or user equipment, such as sending or receiving the first sequence through the air interface between the data acquisition device and the user equipment.

[0243] It should be understood that the processor mentioned in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0244] It should also be understood that the memory mentioned in the embodiments of the present application may be a volatile memory and / or a non-volatile memory. Among them, 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). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: 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 rambus RAM (DR RAM).

[0245] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, the memory (storage module) can be integrated into the processor.

[0246] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0247] 11 is a schematic diagram of a chip system 1100 provided in accordance with an embodiment of the present application. The chip system 1100 (or also referred to as a processing system) includes a processing circuit 1110 (also referred to as a logic circuit) and an input / output interface 1120 .

[0248] Logic circuit 1110 may be a processing circuit within chip system 1100. Logic circuit 1110 may be coupled to a storage unit and invoke instructions within the storage unit, enabling chip system 1100 to implement the methods and functions of various embodiments of the present application. Input / output interface 1120 may be an input / output circuit within chip system 1100, outputting information processed by chip system 1100 or inputting data or signaling information to be processed into chip system 1100 for processing.

[0249] Specifically, for example, if the network device is equipped with the chip system 1100, the logic circuit 1110 is coupled to the input / output interface 1120, and the logic circuit 1110 can send compressed information to the training device through the input / output interface 1120. The compressed information can be obtained by the logic circuit 1110 by compressing the channel information; or the input / output interface 1120 can input messages from the training device to the logic circuit 1110 for processing. For another example, if the training device is equipped with the chip system 1100, the logic circuit 1110 is coupled to the input / output interface 1120, and the input / output interface 1120 can input compressed information from the network device to the logic circuit 1110 for processing.

[0250] As a solution, the chip system 1100 is used to implement the operations performed by the data acquisition device in each of the above method embodiments.

[0251] For example, the logic circuit 1110 is used to implement the processing-related operations performed by the data acquisition device in the above method embodiments, such as the processing-related operations performed by the data acquisition device (or sending end) in the embodiment shown in Figure 7; the input / output interface 1120 is used to implement the sending and / or receiving-related operations performed by the data acquisition device in the above method embodiments, such as the sending and / or receiving-related operations performed by the data acquisition device (or sending end) in the embodiment shown in Figure 7.

[0252] As another solution, the chip system 1100 is used to implement the operations performed by the training device in the above various method embodiments.

[0253] For example, the logic circuit 1110 is used to implement the processing-related operations performed by the training device in the above method embodiments, such as the processing-related operations performed by the training device (or receiving end) in the embodiment shown in Figure 7, and the input / output interface 1120 is used to implement the sending and / or receiving-related operations performed by the training device (or receiving end) in the above method embodiments, such as the sending and / or receiving-related operations performed by the training device (or receiving end) in the embodiment shown in Figure 7.

[0254] An embodiment of the present application further provides a computer-readable storage medium on which computer instructions for implementing the methods executed by the data acquisition device or the training device in the above-mentioned method embodiments are stored.

[0255] For example, when the computer program is executed by a computer, the computer can implement the method performed by the data acquisition device or the training device in each embodiment of the above method.

[0256] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by the data acquisition device or the training device in the above-mentioned method embodiments.

[0257] The present application also provides a communication system comprising the data acquisition device and training device described in the above embodiments. For example, the system comprises the data acquisition device and training device shown in FIG7 . In another example, the system comprises a training device equipped with the data acquisition device and a data acquisition device equipped with the training device.

[0258] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0259] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0260] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, 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 described in 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 device. For example, the computer can be a personal computer, a server, or a network device, etc. 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 one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. 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 (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)). For example, the aforementioned available medium includes, but is not limited to, various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0261] 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 changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An information transmission method, characterized in that: include: Determining a first data set, where data in the first data set is used for training a first artificial intelligence (AI) model; Send the first data set and first indication information, where the first indication information indicates functions and / or features of the first AI model.

2. The method according to claim 1, characterized in that The first data set includes a first data subset and a second data subset, and the first indication information further indicates the function and / or feature of the AI ​​model corresponding to the first data subset and / or the second data subset.

3. The method according to claim 1 or 2, characterized in that The first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first data set and / or usage information of the first data set.

4. The method according to any one of claims 1 to 3, characterized in that The first data set is also used for training a second AI model, and the first indication information further indicates the functions and / or characteristics of the second AI model.

5. The method according to claim 1, wherein The method further comprises: determining a second data set; Send the second data set and second indication information, where the second indication information indicates the function and / or feature of the first AI model.

6. The method according to any one of claims 1 to 5, characterized in that The first indication information indicates the function and / or feature of the first AI model, including: The identifier of the first AI model and / or the identifier of the function indicates the function of the first AI model, and / or the identifier of the first AI model and / or the identifier of the function indicates a feature of the first AI model; or, The identifier of the first data set and / or the usage information of the first data set indicates the function of the first AI model, and / or the identifier of the first data set and / or the usage information of the first data set indicates the characteristics of the first AI model.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: determining a second data set; Send the second data set and second indication information, where the second indication information indicates the function and / or feature of the first AI model.

8. The method according to claim 7, characterized in that The method further comprises: The second indication information and the first indication information have the same value.

9. The method according to any one of claims 1 to 7, characterized in that The first data set includes a first data sample and a second data sample, and the method further includes: Third indication information is sent, where the third indication information indicates that the first data sample and the second data sample share first data, and the first data belongs to the first data set.

10. The method according to claim 9, characterized in that The method further comprises: The first data is label information corresponding to input data and / or output data.

11. The method according to claim 9 or 10, characterized in that The method further comprises: Send fourth indication information, where the fourth indication information indicates an identifier of the first data, or indicates resource information corresponding to the first data, where the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: Receive fifth indication information, where the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

13. An information transmission method, characterized in that: include: receiving a first data set and first indication information, where data in the first data set is used for training a first AI model, and the first indication information indicates a function and / or feature of the first AI model; Based on the first indication information, determine that data in the first data set is used for training the first AI model.

14. The method according to claim 13, characterized in that The first data set includes a first data subset and a second data subset, the first indication information further indicates a function and / or feature of an AI model corresponding to the first data subset and / or the second data subset, and the method further includes: Determine an AI model corresponding to the first data subset and / or the second data subset based on the first indication information.

15. The method according to claim 13 or 14, characterized in that The first indication information includes an identifier of the first AI model and / or an identifier of a function, or an identifier of the first data set and / or usage information of the first data set. The method further comprises: Determine the purpose of the first data set and / or the first AI model corresponding to the first data set based on the first indication information.

16. The method according to any one of claims 13 to 15, characterized in that The first data set is further used for training a second AI model, the first indication information further indicates functions and / or features of the second AI model, and the method further includes: Determine the second AI model based on the first indication information.

17. The method according to claim 16, characterized in that The method further comprises: A second data set and second indication information are received, where the second indication information indicates functions and / or features of the first AI model.

18. The method according to claim 17, characterized in that The second indication information and the first indication information have the same value.

19. The method according to any one of claims 13 to 18, characterized in that The first data set includes a first data sample and a second data sample, and the method further includes: receiving third indication information, where the third indication information indicates that the first data sample and the second data sample share first data, and the first data belongs to the first data set; Determine, based on the third indication information, that the first data is used for the first data sample and the second data sample.

20. The method according to claim 19, wherein The first data is label information corresponding to input data and / or output data.

21. The method according to claim 19 or 20, characterized in that The method further comprises: receiving fourth indication information, where the fourth indication information indicates an identifier of the first data and / or indicates resource information corresponding to the first data, where the resource information corresponding to the first data includes at least one of time domain resource information, frequency domain resource information, or spatial domain resource information; The first data is used on a resource determined based on the resource information.

22. The method according to any one of claims 13 to 18, characterized in that The method further comprises: Send fifth indication information, where the fifth indication information indicates at least one of the following: functions and / or features of one or more AI models supported by the training device, storage and / or computing power information of the training device, and the one or more AI models supported by the training device include the first AI model.

23. A communication device, characterized in that: The method comprises modules or units for executing the method according to any one of claims 1 to 22.

24. A communication device, characterized in that: include: Interface circuits and processors; The interface circuit is used to perform the sending and receiving steps in the method according to any one of claims 1 to 12, and the processor is used to perform the processing steps in the method according to any one of claims 1 to 12; or, The interface circuit is used to perform the sending and receiving steps in the method according to any one of claims 13 to 22, and the processor is used to perform the processing steps in the method according to any one of claims 13 to 22.

25. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program code for execution by a terminal device, wherein the program code includes instructions for executing the method according to any one of claims 1 to 22.

26. A computer program product, characterized in that The method comprises computer-readable instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 22.

27. A communication system, characterized in that: include: A device for implementing the method according to any one of claims 1 to 12, and / or a device for implementing the method according to any one of claims 13 to 22.

28. A chip system, characterized in that: The chip system includes a processor, which is used to execute computer programs or instructions, so that the chip system implements the method according to any one of claims 1 to 22.

Images