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, apparatus and system

[0001] The present application claims priority to the Chinese patent application No. 202410397937.0, filed on April 2, 2024, and entitled "Information transmission method, apparatus and system", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication. In particular, the present application relates to an information transmission method, apparatus and system. BACKGROUND

[0003] Machine learning is an important technical approach to realize artificial intelligence. Currently, the training of an artificial intelligence (AI) model on the user equipment (UE) side is often triggered by the UE itself to collect relevant data. The current network side transmits training data to the UE through the air interface, and the UE cannot determine the relationship between multiple received training data or different times of received training data, resulting in waste of overhead and power consumption of the UE, which is not conducive to the training of the AI model. SUMMARY

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

[0005] In a first aspect, an information transmission method is provided. The method can be performed by a data acquisition apparatus. The data acquisition apparatus can be a network side device, a module in the network side device, such as a chip or a circuit or a chip system, a terminal side device or a chip or a circuit or a chip system in the terminal side device. The present application does not limit the data acquisition apparatus. The network side device can include an access network device, a core network device, or a device in communication with the access network device or the core network device, such as a server. The terminal side device can include a terminal device or a device in communication with the terminal device, such as a server. For ease of description, the following describes the data acquisition apparatus performing the method.

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

[0007] The method can be applied to the air interface transmission scene of the training data. When the data acquisition device issues the training data, the indication information indicating the use of the data is carried, different training data can be associated or distinguished, and the training device can identify the association between different training data and the use of the training data, so as to meet the training needs of different AI models and save the overhead of the training device.

[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, the data set is transmitted through the air interface, which can avoid leaking a large amount of network side private information about AI model training to the training device side. Further, for data subsets with different functions (or uses), the training device can determine the function and / or feature of the AI model corresponding to each data subset according to the first indication information, so as to avoid the training device from being unable to establish the relationship between the data subset and the function and / or feature of the AI model, and improve the training efficiency.

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

[0011] The first indication information indicating the function and / or feature of the first AI model includes:

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

[0013] The identifier of the first data set and / or the use 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 use information of the first data set indicates the feature of the first AI model.

[0014] It can be understood that one or more of the identifier of the first AI model, the identifier of the function of the first AI model, the function of the first AI model, the first AI model, the feature of the first AI model, the identifier of the first data set, the feature of the first data set, and the use information of the first data set can have a corresponding relationship, and through the corresponding relationship and the corresponding indication, the application mode of the first data set can be determined, such as which AI model operation, which operation can include training and / or monitoring.

[0015] It can be understood that, in the case that the AI model corresponding to the above-mentioned correspondence is multiple, all or part of the multiple AI models can be determined by the training apparatus to operate, and how to determine can be based on system design, which is not limited herein.

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

[0017] In some implementations, the method further includes determining a second data set, and transmitting the second data set and second indication information, the second indication information indicating a function and / or a 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 transmitting third indication information, the third indication information indicating that the first data sample and the second data sample share first data, the first data belonging 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 transmitting fourth indication information, the fourth indication information indicating an identity of the first data, or indicating resource information corresponding to the first data, the resource information corresponding to the first data including at least one of time domain resource information, frequency domain resource information, or space domain resource information.

[0022] In some implementations, the method further includes receiving fifth indication information, the fifth indication information indicating at least one of a function and / or a feature of one or more AI models supported by the training apparatus, or storage and / or computing power information of the training apparatus, the one or more AI models supported by the training apparatus including the first AI model.

[0023] In a second aspect, an information transmission method is provided, which can be performed by a training apparatus, such as an AI entity, for example, an access network device, a core network device, a device in communication with the access network device or the core network device, a UE, or a device in communication with the UE, such as a server, etc. The training apparatus can also be a module in the AI entity, such as a chip or a circuit or a chip system, which is not limited in the present application. For ease of description, the following will be described by taking the training apparatus as an example.

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

[0025] In some implementations, the first data set comprises a first data subset and a second data subset, the first indication information further indicating a function and / or a feature of an AI model corresponding to the first data subset and / or the second data subset, and the method further comprises: determining, based on the first indication information, the AI model corresponding to the first data subset and / or the second data subset.

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

[0027] The method further comprises: determining, based on the first indication information, a use of the first data set and / or the first AI model corresponding to the first data set.

[0028] In some implementations, the first data set is further used for training of a second AI model, the first indication information further indicating a function and / or a feature of the second AI model, and the method further comprises: determining, based on the first indication information, the second AI model.

[0029] In some implementations, the method further comprises: receiving a second data set and second indication information, the second indication information indicating a function and / or a 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 comprises a first data sample and a second data sample, and the method further comprises: receiving third indication information, the third indication information indicating that the first data sample and the second data sample share first data, the first data belonging 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 embodiments, the method further includes: receiving fourth indication information, the fourth indication information indicating an identity of the first data, and / or indicating resource information corresponding to the first data, the resource information corresponding to the first data including at least one of time domain resource information, frequency domain resource information, or space domain resource information; and using the first data on a resource determined based on the resource information.

[0034] In some embodiments, the method further includes: sending fifth indication information, the fifth indication information indicating at least one of a function and / or a feature of one or more AI models supported by a training device, and / or storage and / or computing power information of the training device, the one or more AI models supported by the training device including the first AI model.

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

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

[0037] In some embodiments, the first indication information includes an identity of the first AI model and / or an identity of a function of the first AI model, or an identity of the first data set and / or usage information of the first data set, and the first indication information indicating the function and / or the feature of the first AI model includes:

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

[0039] In some embodiments, the first data set is further used for training of a second AI model, and the first indication information further indicates a function and / or a feature of the second AI model.

[0040] In some embodiments, the processing unit is further configured to determine a second data set, and the transceiver unit is further configured to send the second data set and second indication information, the second indication information indicating the function and / or the feature of the first AI model.

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

[0042] In some embodiments, the first data set includes a first data sample and a second data sample, and the method further includes: sending third indication information, the third indication information indicating that the first data sample and the second data sample share first data, the first data belonging to the first data set.

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

[0044] In some embodiments, the transceiver is further configured to send fourth indication information, the fourth indication information indicating an identity of the first data or indicating resource information corresponding to the first data, the resource information corresponding to the first data including at least one of time domain resource information, frequency domain resource information, or space domain resource information.

[0045] In some embodiments, the transceiver is further configured to receive fifth indication information, the fifth indication information indicating at least one of the following: a function and / or a feature of one or more AI models supported by a training device, storage and / or computing power information of the training device, the one or more AI models supported by the training device including the first AI model.

[0046] In some embodiments, the transceiver is further configured to receive fifth indication information, the fifth indication information indicating at least one of the following: a function and / or a feature of one or more AI models supported by a training device, storage and / or computing power information of the training device, the one or more AI models supported by the training device including the first AI model.

[0047] In some embodiments, the first data set includes a first data subset and a second data subset, and the first indication information further indicates a function and / or a feature of an AI model corresponding to the first data subset and / or the second data subset, and the processing unit is further configured 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 some embodiments, the first indication information includes an identity of the first AI model and / or an identity of a function of the first AI model, or an identity of the first data set and / or use information of the first data set, and the first indication information indicating the function and / or the feature of the first AI model includes:

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

[0050] The processing unit is further configured to determine the usage 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 further used for training of a second AI model, the first indication information further indicates the function and / or feature of the second AI model, and the processing unit is further configured to determine the second AI model based on the first indication information.

[0052] In some implementations, the transceiver is further configured to receive a second data set and second indication information, and the second indication information indicates the function and / or feature 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, the transceiver is further configured to receive third indication information, and 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; and the processing unit is further configured to determine that the first data is used for the first data sample and the second data sample based on the third indication information.

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

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

[0057] In some implementations, the transceiver is further configured to send fifth indication information, and the fifth indication information indicates at least one of the following: function and / or feature of one or more AI models supported by a training device, and 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 the implementation manners of the device corresponding to the first aspect and the second aspect, and the description, supplement and 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.

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

[0061] In a seventh aspect, the present application provides a computer readable medium, which stores program codes for terminal device execution, the program codes comprising instructions for executing the method of the first aspect, or any possible implementation manner of the first aspect, or all possible implementation manners of the first aspect.

[0062] In an eighth aspect, the present application provides a computer readable medium, which stores program codes for data acquisition device execution, the program codes comprising instructions for executing the method of the second aspect, or any possible implementation manner of the second aspect, or all possible implementation manners of the second aspect.

[0063] In a ninth aspect, a computer program product storing computer readable instructions is provided, when the computer readable instructions run on a computer, the computer executes the method of the first aspect, or any possible implementation manner of the first aspect, or all possible implementation manners of the first aspect.

[0064] In a tenth aspect, a computer program product storing computer readable instructions is provided, when the computer readable instructions run on a computer, the computer executes the method of the second aspect, or any possible implementation manner of the second aspect, or all possible implementation manners of the second aspect.

[0065] In an eleventh aspect, a communication system is provided, which comprises devices with the functions of the method of the first aspect, or any possible implementation manner of the first aspect, or all possible implementation manners of the first aspect, the second aspect, or any possible implementation manner of the second aspect, or all possible implementation manners of the second aspect.

[0066] In a twelfth aspect, a processor is provided for coupling with a memory for performing the method of the first aspect, or any possible implementation of the first aspect, or all possible implementations of the first aspect.

[0067] In a thirteenth aspect, a processor is provided for coupling with a memory for performing the method of the second aspect, or any possible implementation of the second aspect, or all possible implementations of the second aspect.

[0068] In a fourteenth aspect, a chip system is provided, which includes a processor, and can further include a memory, for executing a computer program or instructions stored in the memory, so that the chip system implements the method in the first aspect or the second aspect, or any possible implementation of any aspect, and any possible implementation of any aspect. The chip system can be composed of a chip, or can include a chip and other discrete devices. BRIEF DESCRIPTION OF DRAWINGS

[0069] FIG. 1 is a schematic diagram of a possible application framework in a communication system.

[0070] FIG. 2 is a schematic diagram of another possible application framework in a communication system.

[0071] FIG. 3 is a schematic diagram of a communication system suitable for use with embodiments of the application.

[0072] FIG. 4 is a schematic diagram of another communication system suitable for use with embodiments of the application.

[0073] FIG. 5 is a schematic block diagram of an autoencoder.

[0074] FIG. 6 is a schematic diagram of an AI application framework.

[0075] FIG. 7 is a schematic diagram of a method of information transmission according to embodiments of the application.

[0076] FIG. 8 is a schematic diagram of data sharing.

[0077] FIG. 9 is a schematic block diagram of a communication device.

[0078] FIG. 10 is a schematic block diagram of another communication device.

[0079] FIG. 11 is a schematic block diagram of yet another communication device. DETAILED DESCRIPTION

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

[0081] The technical solutions provided in the present application can be applied to various communication systems, for example, a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system, or a fusion system of multiple systems, and the like. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and an internet of things (IoT) communication system 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 can include information, signaling, or data, and the like. The device can also be replaced by an entity, a network entity, a network element, a communication device, a communication module, a node, a communication node, and the like. The device is taken as an example for description in the present disclosure. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device. It can be understood that the terminal device in the present disclosure can be replaced by a first device, and the network device can be replaced by a second device, both of which perform the corresponding information transmission method in the present disclosure.

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

[0084] The terminal device can be a device providing voice / data, for example, a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of terminals are: mobile phone, tablet computer, notebook computer, palm computer, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, wearable device, terminal device in a 5G network, or terminal device in a future evolved public land mobile network (PLMN), etc. The embodiments of the present application are not limited thereto.

[0085] By way of example and not limitation, in the embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories. The wearable device is not only a hardware device, but also a device that realizes powerful functions through software support and data interaction and cloud interaction. The general wearable smart device includes devices with full functions, large size, and the ability to realize complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, and devices that focus on a certain application function and need to be used in cooperation with other devices, such as smart phones, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0086] In the embodiments of the present application, the apparatus for implementing the function of the terminal device can be a terminal device, or can be an apparatus capable of supporting the terminal device to implement the function, for example, a chip system, which can be installed in the terminal device or used in matching with the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or can include the chip and other discrete devices. In the embodiments of the present application, only the apparatus for implementing the function of the terminal device is taken as an example for description, and the scheme of the embodiments of the present application is not limited in this way.

[0087] The network device in the embodiments of the present application can be a device for communicating with a terminal device, which can 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 can refer to a radio access network (RAN) node (or device) that accesses a terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip used in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs the function of a base station in D2D, V2X, M2M communication, a device that performs the function of a base station in a future communication system, etc. The base station can support networks of the same or different access technologies. Alternatively, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in the vehicle to everything (V2X) technology can 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 device.

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

[0089] In some deployments, the network device mentioned by embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)), and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP, and a gNB-DU.

[0090] In some deployments, wireless access is assisted by multiple RAN nodes cooperating to assist a terminal, and different RAN nodes respectively implement part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can also be included in the same network element, such as a BBU. The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an AAU, or an RRH.

[0091] The RAN node can support one or more types of fronthaul interfaces, different fronthaul interfaces respectively corresponding to DUs and RUs having 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 of baseband functions, and the RU is configured to implement one or more of radio frequency functions. If the fronthaul interface between the DU and the RU is another interface, which, relative to the CPRI, moves one or more of partial baseband functions of the downlink and / or uplink, such as, for the downlink, one or more of precoding, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / add cyclic prefix (CP), from the DU to the RU for implementation, and for the uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / remove cyclic prefix (CP), from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (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, with layer mapping as the cut, the DU is configured to implement layer mapping and one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, while other functions (e.g., one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, with de-RE mapping as the cut, the DU is configured to implement de-mapping and one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, de-modulation, inverse discrete Fourier transform (IDFT), channel equalization, de-RE mapping) before de-mapping, while other functions (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) after de-mapping are implemented in the RU. It can be understood that the function description of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described here.

[0093] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0094] In different systems, the CU (or CU-CP and CU-UP), DU or RU can 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, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application can 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 apparatus for implementing the function of the network device can be a network device; or can be an apparatus capable of supporting the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus can be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the apparatus for implementing the function of the network device is taken as an example for description, and the scheme of the embodiments of the present application is not limited in this way.

[0096] The network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water surface; and can also be deployed on airplanes, balloons and satellites in the air. The scenarios in which the network device and the terminal device are located are not limited in the embodiments of the present application. In addition, the terminal device and the network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The specific forms of the terminal device and the network device are not limited in the present application.

[0097] In a wireless communication network, for example, in a mobile communication network, the services supported by the network are increasingly diverse, and therefore the needs to be met are increasingly diverse. For example, the network needs to be able to support ultra-high rates, ultra-low latencies, and / or ultra-large connections. This feature makes network planning, network configuration, and / or resource scheduling increasingly complex. In addition, as the functions of the network become increasingly powerful, for example, supporting increasingly high frequency spectrums, 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 needs, new scenarios and new features bring unprecedented challenges to network planning, operation and efficient operation. In order to meet this challenge, artificial intelligence technology can be introduced into the wireless communication network, thereby realizing network intelligentization.

[0098] In order to support AI technology in the wireless network, an AI node can also be introduced into the network.

[0099] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc., or the AI node can also be deployed separately, for example, in a position other than any of the above devices, such as a host or a cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: an access network device, a terminal device, or a network element of a core network, etc. 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 can be understood that the present 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 functions, such as different AI nodes being responsible for different functions.

[0101] It can also be understood that the AI node can be a device independent of each other, can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform), and the present application does not limit the specific form of the AI node.

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

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

[0104] FIG. 1 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 1, network elements in the communication system are connected through interfaces (e.g., next generation (NG) interface, Xn interface), or air interfaces. One or more AI modules (only one is shown in FIG. 1 for clarity) are deployed in one or more of the network element nodes, such as a core network device, an access network node (RAN node), a terminal, or an OAM device. The access network node can be a single RAN node or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or the DU can also be provided with one or more AI modules. Optionally, the CU can be further split into a CU-CP and a CU-UP. One or more AI models are deployed in the CU-CP and / or the CU-UP.

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

[0106] One AI module can have one or more models. One model can infer an output including one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0107] FIG. 2 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 2, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI module 117, 118 shown in FIG. 1, which is configured to implement an AI-related function. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The Non-RT RIC mainly processes non-real time information, such as data that is not sensitive to latency, which can be in the order of seconds. The near-RT RIC mainly processes near-real time information, such as data that is relatively sensitive to latency, which can be in the order of tens of milliseconds.

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

[0109] The non-real-time RIC is also used for model training and inference. For example, the non-real-time RIC is used for training an AI model, and inference is performed using the AI model. The non-real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data, and inference results can be delivered to the RAN node and / or the terminal. Optionally, the inference results can be exchanged between a CU and a DU, and / or between a DU and a RU. For example, the non-real-time RIC delivers the inference results to a DU, and the DU delivers the inference results to a RU.

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

[0111] FIG. 3 is a schematic diagram of a communication system applicable to the information transmission method according to an embodiment of the present application. As shown in FIG. 3, the communication system 100 can include at least one network device, such as the network device 110 shown in FIG. 3, and can include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in FIG. 3. The network device 110 and the terminal devices (e.g., the terminal device 120 and the terminal device 130) can communicate with each other through wireless links. The communication devices in the communication system can communicate with each other through multi-antenna technology, for example, the network device 110 and the terminal device 120.

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

[0113] In a possible implementation, the network device 110 can send data related to the training of the AI model to the AI network element 140, the AI network element 140 constructs a training data set and trains the AI model. For example, the data related to the training of the AI model can include data reported by the terminal device. The AI network element 140 can send the result of the AI model related operation to the network device 110 and forward it to the terminal device through the network device 110. For example, the result of the AI model related operation can include at least one of the following: a trained AI model, an evaluation result or a test result of the model, and the like. For example, part of the trained AI model can be deployed on the network device 110, and the other part can be deployed on the terminal device. Alternatively, the trained AI model can be deployed on the network device 110. Alternatively, the trained AI model can be deployed on the terminal device.

[0114] It should be understood that FIG. 4 is only used as an example to illustrate that the AI network element 140 is directly connected to the network device 110, and in other scenarios, the AI network element 140 can also be connected to the terminal device. Alternatively, the AI network element 140 can be connected to both the network device 110 and the terminal device. Alternatively, the AI network element 140 can also be connected to the network device 110 through a third-party network element. The connection relationship between the AI network element and other network elements is not limited in the embodiments of the present application.

[0115] The AI network element 140 can also be set as a module in the network device and / or the terminal device, for example, in the network device 110 or the terminal device shown in FIG. 3.

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

[0117] In order to facilitate understanding of the scheme of the embodiments of the present application, the terms that can be involved in the embodiments of the present application are explained as follows.

[0118] 1. Artificial intelligence: It is to make the machine have learning ability and can accumulate experience to solve the problems that can be solved by human experience, such as natural language understanding, image recognition and chess playing. Artificial intelligence can be understood as the intelligence shown by the machine made by human. Artificial intelligence usually refers to the technology of presenting human intelligence through computer program. The goal of artificial intelligence includes understanding intelligence by constructing symbolic reasoning or reasoning computer program.

[0119] 2、Machine learning: is a way of implementing artificial intelligence. Machine learning is a method that can give a machine the ability to learn and complete functions that cannot be completed by direct programming. In a practical sense, machine learning is a method of training a model by using data and then using the model for prediction. There are many methods of machine learning, such as neural network (NN), decision tree, support vector machine, etc. The theory of machine learning is mainly to design and analyze some algorithms that can be automatically learned by a computer. Machine learning algorithm is a kind of algorithm that can automatically analyze the rules from data and use the rules to predict unknown data.

[0120] 3、Neural network: is a specific embodiment of machine learning method. Neural network is a mathematical model that simulates the behavior characteristics of animal neural network for information processing. The idea of neural network comes from the neuron structure of brain tissue. Each neuron can perform weighted sum operation on its input value, and the result of weighted sum operation is output through an activation function.

[0121] The neural network generally includes a multi-layer structure, and each layer can include one or more logical judgment units, which can be referred to as neurons. By increasing the depth and / or width of the neural network, the expression ability of the neural network can be improved, and the neural network can provide stronger information extraction and abstract modeling ability for complex systems. The depth of the neural network can be understood as the number of layers included in the neural network, and the number of neurons included in each layer can be referred to as the width of the layer. In one possible implementation, the neural network includes an input layer and an output layer. The input layer of the neural network transmits the results obtained by processing the received input through neurons to the output layer, and the output layer obtains the output result of the neural network. In another possible implementation, the neural network includes an input layer, a hidden layer and an output layer. The input layer of the neural network transmits the results obtained by processing the received input through neurons to the hidden layer, and the hidden layer transmits the calculation results to the output layer or the adjacent hidden layer, and finally the output layer obtains the output result of the neural network. A neural network can include one or more hidden layers connected in sequence, without limitation.

[0122] In the training process of the neural network, a loss function can be defined. The loss function is used to measure the difference between the predicted value of the model and the true value. In the training process of the neural network, the loss function describes the gap or difference between the output value of the neural network and the ideal target value. The training process of the neural network is a process of adjusting the neural network parameters so that the value of the loss function is less than a threshold value or meets the target demand. The neural network parameters can include at least one of the following: the number of layers of the neural network, the width, the weight of the neuron, and the parameters in the activation function of the neuron.

[0123] Taking the type of the AI model as a neural network as an example, the AI model involved in the present disclosure can be a deep neural network (DNN). According to the construction manner of the network, the DNN can include a feedforward neural network (FNN), a convolutional neural network (CNN), a recurrent neural network (RNN), and the like.

[0124] 4. Deep neural network (DNN): a neural network with multiple hidden layers.

[0125] 5. Deep learning: machine learning using a deep neural network.

[0126] 6. AI model:

[0127] The AI model is an algorithm or computer program capable of realizing an AI function, and the AI model represents the mapping relationship between the input and the output of the model. The type of the AI model can be a neural network, a linear regression model, a decision tree model, a support vector machine (SVM), a Bayesian network, a Q learning model, or other machine learning (ML) models.

[0128] 7. Two-side model:

[0129] The two-side model can also be referred to as a bilateral model, a collaborative model, a dual model, or a two-side model, etc. The two-side model refers to a model composed of multiple sub-models. The multiple sub-models constituting the model need to be matched with each other. The multiple sub-models can be deployed in different nodes.

[0130] The embodiments of the present disclosure involve an encoder for compressing channel state information (CSI) and a decoder for restoring the compressed CSI. The encoder and the decoder are matched for use, and it can be understood that the encoder and the decoder are matched AI models. One encoder can 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 matched encoder and decoder is the same and one-to-one correspondence.

[0131] In one possible design, a set of matching encoder and decoder can be embodied as two parts in the same auto-encoder (AE), for example, as shown in FIG. 5. The AE model with the encoder and the decoder deployed in different nodes is a typical bilateral model. The encoder and the decoder of the AE model are usually jointly trained and used in matching. The encoder processes the input V to obtain the processed result z, and the decoder can decode the output z of the encoder to the expected output V'.

[0132] The auto-encoder is a neural network for unsupervised learning, which is characterized by taking the input data as the label data. Therefore, the auto-encoder can also be understood as a neural network for self-supervised learning. The auto-encoder can be used for data compression and recovery. For example, the encoder in the auto-encoder can compress (encode) the data A to obtain the data B; the decoder in the auto-encoder can decompress (decode) the data B to recover the data A. Alternatively, it can be understood that the decoder is the inverse operation of the encoder.

[0133] For example, the AI model in the embodiment of the present application can include an encoder and a decoder. The encoder and the decoder are used in matching, and can be understood as a matched AI model. The encoder and the decoder can be respectively deployed in a terminal device and a network device.

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

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

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

[0137] The training data set is used for training the AI model, and the training data set can include the input of the AI model or the input and target output of the AI model. The training data set includes one or more training data, and the training data can include a training sample input to the AI model or a target output of the AI model. The target output can also be referred to as a label, a sample label or a label sample. The label is the ground truth.

[0138] In the field of communication, the training data set can include simulation data collected through a simulation platform, can include experimental data collected in an experimental scenario, or can include measured data collected in an actual communication network. Due to differences in geographical environment and channel conditions where the data is generated, such as differences in indoor, outdoor, mobile speed, frequency band, or antenna configuration, the collected data can be classified when the data is obtained. For example, data with the same channel propagation environment and antenna configuration are classified into one category.

[0139] Model training is essentially learning some features from the training data. In the process of training an AI model (such as a neural network model), because the output of the AI model is expected to be as close as possible to the value that is truly intended to be predicted, the weight vector of each layer of the AI model can be updated according to the difference between the predicted value of the current network and the truly intended target value by comparing the predicted value of the current network with the truly intended target value (of course, there is usually an initialization process before the first update, that is, the parameters of each layer of the AI model are pre-configured), for example, if the predicted value of the network is too high, the weight vector is adjusted to make it predict lower, and the adjustment is continuously made until the AI model can predict the truly intended target value or a value very close to the truly intended target value. Therefore, it is necessary to define "how to compare the difference between the predicted value and the target value", which is the loss function or the objective function, which is an important equation for measuring the difference between the predicted value and the target value. Taking the loss function as an example, the higher the output value (loss) of the loss function, the greater the difference, and the training of the AI model becomes a process of minimizing the loss, so that the value of the loss function is less than a threshold, or the value of 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 of the neural network, the width, the weight of the neuron, or the parameters of the activation function of the neuron.

[0140] Inference data can be input into the AI model that has completed training, for inference of the AI model. In the model inference process, the inference data is input into the AI model, and the corresponding output obtained is the inference result.

[0141] 9. AI model design:

[0142] The design of the AI model mainly includes the data collection link (such as collecting training data and / or inference data), the model training link, and the model inference link. Further, it can also include the inference result application link.

[0143] FIG. 6 shows an AI application framework.

[0144] In the foregoing data collection link, a data source is configured to provide training data and inference data. In the model training link, 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 input and output of the model. The AI model is learned by the model training node, which is equivalent to learning the mapping relationship between the input and output of the model by using the training data. In the model inference link, the AI model trained in the model training link is used to perform inference based on the inference data provided by the data source, and an inference result is obtained. This link can also be understood as follows: the inference data is input into the AI model, and the output of the AI model is obtained, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operation executed by the execution object. In the inference result application link, the inference result is published, for example, the inference result can be uniformly planned by an execution entity, for example, the execution entity can send the inference result to one or more execution objects (for example, network devices or terminal devices, etc.) to execute. For example, the execution entity can also feed back the performance of the model to the data source to facilitate subsequent implementation of model update training.

[0145] It can be understood that the communication system can include network elements with artificial intelligence functions. The above-mentioned AI model design related links can be executed by one or more network elements with artificial intelligence functions. 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 training and / or inference of AI models. For example, the existing network element can be a network device or a terminal device, etc. Or in another possible design, a separate network element can also be introduced in the communication system to perform AI related operations, such as training an AI model. The separate network element can be referred to as an AI network element or an AI node, etc., and the name is not limited by the embodiments of the present application. For example, the AI network element can be directly connected with the network device in the communication system, or can be indirectly connected with the network device through a third party network element. The third party network element can be an authentication management function (AMF) network element, a user plane function (UPF) network element, etc. core network element, operation administration and maintenance (OAM), cloud server or other network element, which is not limited. For example, the separate network element can be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a cloud server. For example, as shown in FIG. 4, an AI network element 140 is introduced in the communication system.

[0146] The training processes of different models can be deployed in different devices or nodes, or in the same device or node. The inference processes of different models can be deployed in different devices or nodes, or in the same device or node. Taking the terminal device to complete the model training link as an example, the terminal device can train the corresponding encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the network device to complete the model training link as an example, the network device can train the corresponding encoder and decoder, and then indicate the model parameters of the encoder to the terminal device. Taking the independent AI network element to complete the model training link as an example, the AI network element can train the corresponding 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 link corresponding to the encoder is performed in the terminal device, and the model inference link corresponding to the decoder is performed in the network device.

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

[0148] 10. Model training: a process of training model parameters by selecting a suitable loss function and using an optimization algorithm to make the value of the loss function less than a threshold, or to make the value of the loss function meet the target requirements.

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

[0150] 12. Channel information:

[0151] In a communication system (for example, an LTE communication system or an NR communication system, etc.), the network device determines one or more of the following configurations based on the channel information: the resource of the downlink data channel of the terminal device, the modulation coding scheme (MCS), and the precoding, etc. It can be understood that the channel information can also be referred to as channel state information (CSI) or channel environment information, which is an information that can reflect the characteristics and quality of the channel.

[0152] The channel information measurement refers to that a receiving end solves channel information according to a reference signal sent by a sending end, that is, estimates the channel information by using a channel estimation method. Exemplarily, the reference signal can include one or more of a channel state information reference signal (CSI-RS), a synchronizing signal / physical broadcast channel block (SSB), a sounding reference signal (SRS), a demodulation reference signal (DMRS), or the like. The CSI-RS, the SSB, and the DMRS, or the like can be used to measure downlink channel information. The SRS and the DMRS, or the like can be used to measure uplink channel information. The channel information measurement can also be referred to as CSI measurement or channel environment information measurement.

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

[0154] Taking an FDD communication scenario as an example, in the FDD communication scenario, because the uplink and downlink channels do not have reciprocity or the reciprocity of the uplink and downlink channels cannot be guaranteed, the network device usually sends a downlink reference signal to the terminal device, and the terminal device performs channel measurement and interference measurement according to the received downlink reference signal to estimate downlink CSI. The terminal device generates a CSI report according to a protocol pre-defined manner or a network device configured manner, and feeds back to the network device, so that the network device obtains the downlink CSI.

[0155] In this application, the meaning of CSI is broader than that in the traditional scheme, 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 the channel response, reference signal receiving power (RSRP) or signal to interference plus noise ratio (SINR) and the like. 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 scheme that can be supported by the terminal device under the current channel condition, and PMI is used to indicate the precoding recommended by the terminal device. The number of layers of precoding indicated by PMI corresponds to RI.

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

[0157] As mentioned earlier, measuring the reference signal can obtain channel information. The compression and / or quantization operation on the channel information can obtain feedback information. The feedback information can be reported through the channel information report (also known as CSI report). The decompression and / or dequantization operation on the feedback information can recover the channel information.

[0158] The feedback information can 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 can also be referred to as CSI recovery information.

[0160] The introduction of AI technology into wireless communication networks has produced a CSI feedback method based on AI models. The terminal device uses AI models to compress and feedback CSI, and the network device uses AI models to recover compressed CSI. In AI-based CSI feedback, a sequence (such as a bit sequence) is transmitted, and the overhead is lower than that of traditional CSI feedback CSI.

[0161] Taking FIG. 5 as an example, the encoder in FIG. 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 generate CSI feedback information z by processing channel information V through the encoder. The terminal device reports a CSI report, which can include the CSI feedback information z. The network device can reconstruct the CSI information by processing the CSI feedback information z through the decoder, and obtain CSI recovery information V'.

[0162] The channel information V can be obtained by the terminal device through CSI measurement. For example, the channel information V can include a channel response of a downlink channel or a feature vector matrix (a matrix composed of feature vectors) of the downlink channel. The encoder processes the feature vector matrix of the downlink channel to obtain the CSI feedback information z. In other words, the operation of compressing and / or quantizing the feature matrix according to the codebook in the related scheme is replaced by the operation of processing the feature matrix by the encoder to obtain the CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through the decoder to obtain the CSI recovery information V'.

[0163] The training process and the inference process of the AI model in the embodiments of the present application are further exemplarily described below.

[0164] The training data for training the AI model includes training samples and sample labels. Exemplarily, the training samples are channel information determined by a terminal device, and the sample labels are real channel information, i.e., true value CSI. For the case that the encoder and the decoder belong to the same autoencoder, the training data can only include the training samples, or in other words, the training samples are the sample labels.

[0165] In the field of wireless communication, the true value CSI can be high-precision CSI.

[0166] The specific training process is as follows: a model training node processes channel information, i.e., training samples, using the encoder to obtain CSI feedback information, and processes the feedback information using the decoder to obtain recovered channel information, i.e., CSI recovery information. Then, the difference between the CSI recovery information and the corresponding sample label, i.e., the value of the loss function, is calculated, and the parameters of the encoder and the decoder are updated according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, i.e., the loss function is minimized. Exemplarily, the loss function can be mean square error (MSE) or cosine similarity. By repeating the above operation, the encoder and the decoder that meet the target requirements can be obtained. 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 only takes the AI model for CSI compression as an example. In CSI feedback, the AI model can also be used in other scenarios. For example, the AI model can be used for CSI prediction, that is, predicting channel information at one or more future time instants based on channel information measured at one or more historical time instants. The specific use of the AI model in the CSI feedback scenario is not limited in the embodiments of the present application.

[0168] It should be understood that in the present application, indication includes direct indication (also known as explicit indication) and implicit indication. Among them, direct indication of information A means including information A; implicit indication of information A means indicating information A through the correspondence between information A and information B and directly indicating information B. The correspondence between information A and information B can be pre-defined, pre-stored, pre-burned, or pre-configured.

[0169] It should be understood that in the present application, information C is used for the determination of information D, which includes that information D is determined based on information C only, and also includes that information D is determined based on information C and other information. In addition, information C for determining information D can also be determined indirectly, such as the case where information D is determined based on information E, and information E is determined based on information C.

[0170] In addition, in the embodiments of the present application, "network element A sends information A to network element B" can be understood as the destination of the information A or the intermediate network element in the transmission path between the destination is network element B, which can include direct or indirect sending of information to network element B. "Network element B receives information A from network element A" can be understood as the source of the information A or the intermediate network element in the transmission path between the source is network element A, which can include direct or indirect receiving of information from network element A. The information between the source and the destination of the information transmission can be processed as necessary, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, and will not be described here.

[0171] Exemplarily, the network device can be one or more of the core network device, the access network node (RAN node), or the OAM shown in FIG. 1. For example, the AI module can be the RIC shown in FIG. 2, such as near-real-time RIC or non-real-time RIC. For example, the near-real-time RIC is arranged in the RAN node (for example, in the CU, DU), and the non-real-time RIC is arranged in the OAM, in the cloud server, in the core network device, or in other network devices. The RIC can obtain a subset of information from multiple terminal devices from the RAN node (for example, CU, CU-CP, CU-UP, DU and / or RU), reorganize it into a training data set #2, and train based on the training data set #2.

[0172] Exemplarily, the near-real-time RIC and the non-real-time RIC can be separately set as a network element, and the network device can be the near-real-time RIC or the non-real-time RIC.

[0173] Currently, the training of the UE-side AI model is often triggered by the UE to collect relevant data. Meanwhile, since it is a single-sided model, if different models meeting different requirements exist on the UE side, the association between the data set and the AI model needs to be determined through the input and output of the AI model, or the association between the data set and the AI model is determined through the corresponding relationship between the input and the output. For example, in AI-based sparse beam management, the input is often determined by the RSRP of a subset of all beams obtained by scanning all beams, and the output predicted by the model is the information of all beams, such as the RSRP of all beams or the probability that each beam in all beams becomes the optimal beam. Alternatively, the corresponding relationship between each input and output and the AI model is identified through the quasi-colocation (QCL) relationship corresponding to the input and the output. Alternatively, the corresponding relationship between the input and the output and the AI model is determined through more direct information, such as the beam shape and beam width of the network-side beam in beam management.

[0174] In the process of transferring the model training data set to the UE, if the network side transfers a data set (i.e., multiple data samples), the UE cannot distinguish the pairwise corresponding relationship between multiple groups of data in the data set (i.e., identify the AI input, AI output, or multiple AI outputs or inputs). If only one data is transmitted each time, the UE cannot identify the association between the data transmitted multiple times, for example, if multiple groups of data correspond to the training of one AI model or one function, the UE needs to associate the data transmitted multiple times. This will waste the power consumption of the UE.

[0175] Therefore, the present application provides an information transmission method, which can enable the training device to quickly determine the corresponding relationship between the training data and the AI model. The following describes the method by taking the training device and the data acquisition device as an example of the transceiving ends. It should be understood that the training device can be a network-side device or a terminal device. The type of the training device is not limited in the present application. The training device can be a network-side device, a terminal-side device, a part or component of the network-side device, or a part or component of the terminal-side device. Exemplarily, the method can be executed by a module such as a chip or a circuit or a chip system in the data acquisition device and the training device, which is not limited in the present application. For ease of description, the following describes the method by taking the data acquisition device and the training device as an example.

[0176] As shown in FIG. 7, the method includes the following steps:

[0177] At S710, the data acquisition device determines a first data set, data in the first data set being used for training of a first artificial intelligence (AI) model.

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

[0179] It should be understood that the first data set can be one data or multiple data. The name of the first data set is not limited in the present application, for example, it can also be a first data group, a first data package, and the like, which can indicate a name containing data.

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

[0181] The function (or use) of the first AI model is not limited in the present application. For example, the function of the first AI model in the above example is to train beam management, and the first AI model can also be used for positioning training, channel prediction training, and the like.

[0182] In one possible implementation, when the first data set is used for training of the first AI model, the first data set can also include information related to the first AI model. For example, identification information such as ID of the first AI model. For another example, different indexes corresponding to different AI models can be pre-configured, and the first data set carries an index corresponding to the first AI model. It should be understood that the above ID or index is only an example of a way to identify or distinguish the first AI model, and other ways to identify or distinguish the AI model can also be applicable to the present application and should be within the protection scope of the present application.

[0183] Further, the first data set can also be used for training of multiple AI models. For example, the data included in the first data set can be used for training of two AI models as an example, the data included in the first data set can be used for training of a first AI model, and can also be used for training of a second AI model. Wherein the function and / or feature of the first AI model can be different from the function and / or feature 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 can include an ID of the first AI model, and the first data set can also include an ID of the second AI model. For example, the first data set includes (data1, data2, ID1, ID2), wherein data1 and data2 can be used for training of the AI model identified by ID1, and can also be used for training of the AI model identified by ID2.

[0184] In another possible case, the first data set includes an ID of a first AI function and an ID of a second AI function. When an AI model corresponds to a function one by one, the training device can determine the corresponding AI model according to the function ID. When one AI function corresponds to multiple AI models, the data acquisition device can also issue instruction information Q, which indicates which AI model the training device uses, such as instruction information Q indicating the ID of one or more AI models supporting the function. Alternatively, the training device can autonomously determine which one or more AI models to use for training among multiple AI models.

[0185] In a possible implementation, before the data acquisition device determines the first data set, the training device reports relevant information of the AI model supported by the training device to the data acquisition device. For example, the training device sends instruction information (i.e., fifth instruction information) to the data acquisition device, which indicates the function and / or feature 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 how many types of data sets need to be issued by the data acquisition device to support training of the AI model. The instruction information can also indicate the storage and / or computing power information of the training device, for example, how much data the training device can support for training, or how much data the training device can store. After the training device completes the reporting, the data acquisition device can configure the corresponding data set according to the demand and / or capability of the training device. Wherein the demand of the training device is the function and / or feature 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 demand and / or capability of the training device.

[0186] The function of the AI model can also be the use of the AI model. For example, the function of the first AI model is positioning training, i.e., the first AI model is used for positioning training. The features of the AI model can include the input and / or output of the AI model, such as AI model #A and AI model #B are also used for beam management training, but at least one of the input and output of AI model #A and AI model #B is different.

[0187] For example, Set B_1 can refer to a kind of sparse beam, and Set B_1 is the input of AI model #A, and Set B_2 can refer to another kind of sparse beam, and Set B_2 is the input of AI model #B. Assuming that there are 64 beams in Set A, the beam indices corresponding to the beams that Set B_1 can select are [1, 5, 9, … 63], i.e., every four takes an odd number; and the beam indices corresponding to the beams that Set B_2 can select are [0, 4, 8, …, 64], i.e., every four takes an even number. That is, the inputs of AI model #A and AI model #B are different, and it can be considered that the features of AI model #A and AI model #B are different. It can also be called that the way the AI model obtains the input data is different. The outputs of the AI model #A and the AI model #B are the same, for example, the output of the AI model #A is the RSRP of all beams, and the output of the AI model #B is also the RSRP of all beams. Or, the output of the AI model #A and the output of the AI model #B are both the ID of the optimal beam obtained by training.

[0188] For another example, AI model #A and AI model #B are both used for beam management training, and the inputs of 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, and the output of AI model #B is the ID of the optimal beam obtained by training. That is, the outputs of AI model #A and AI model #B are different, and it can be considered that the features of AI model #A and AI model #B are different, or that AI model #A and AI model #B are different.

[0189] Optionally, in the same data set, different data can correspond 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 correspond to different AI model features respectively. The first data subset and / or the second data subset each contain data in the first data set. For example, the first data includes {data1, data2, data3, data5, data6, data7}, the first data subset includes {data1, data2, data3}, which can be used for training of model A; the second data subset includes {data5, data6, data7}, which can be used for training of model B, and the functions of model A and model B are different, or the features of model A and model B are different.

[0190] Optionally, in the same data set, the first features of the AI models corresponding to different data subsets are different, the second features are the same, and the functions of the AI models are the same. For example, the first data includes a first data subset and a second data subset, the first data subset and the second data subset 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 correspond to the same AI model, and the corresponding output, i.e., the true label, is the same.

[0191] For example, Set B_1 can refer to a kind of sparse beam, Set B_1 is the input of AI model #A, and Set B_2 can refer to another kind of sparse beam, Set B_2 is also the input of AI model #A. Assuming that there are 64 beams in Set A, the beam indexes corresponding to the beams that Set B_1 can select are [1, 5, 9, … 63], that is, every four takes an odd number; and the beam indexes corresponding to the beams that Set B_2 can select are [0, 4, 8, …, 64], that is, every four takes an even number. That is, Set B_1 and Set B_2 are both inputs of AI model #A, and the outputs corresponding to them are the same. In this way, the AI model #A trained based on Set B_1 and Set B_2 has good generalization.

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

[0193] The first data set can refer to the description in S710, which will not be repeated here.

[0194] The first indication information can indicate the related information of the first AI model, such as the ID of the first AI model and / or the function information of the first AI model, and the like. Specifically, the first indication information can include the identification of the first AI model and / or the identification of the function. The first indication information can also indicate the information of the first data set, such as the identification of the first data set and / or the purpose information of the first data set.

[0195] When the first data set includes the first data subset and the second data subset, the first indication information can further 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 can indicate the function identifier and / or feature identifier of the AI model corresponding to the first data subset and the second data subset through different fields, or can 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. The present application does not limit this.

[0196] When the first data set is also used for training of the second AI model, the first indication information further 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. That is, a data set can be used for training of multiple AI models, in order to identify the use of the data set, or in order to identify the different AI models corresponding to the data set, the data set can have multiple identification information, and each identification information corresponds to an AI model.

[0197] It should be understood that when the AI model corresponding to the data set is the same, the identification information corresponding to the data set is the same. For example, the data acquisition device determines the second data set, and sends the second data set and the 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 the same number) can be used.

[0198] In a possible implementation, the first data set includes the first data sample and the second data sample, and the first data sample and the second data sample share a part of data (i.e., the first data), and the first data belongs to the first data set.

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

[0200] The implementation manner can be applicable to a time domain prediction scene of AI, such as an AI-based channel prediction, an AI-based time domain beam prediction, and the like. In these scenes, future information can be predicted by inputting historical information into AI. Such prediction is performed based on a sliding window during training, for example, as shown in FIG. 8, the input of AI is based on two time points, and the output of AI is information of two future time points. In this case, the input of AI in the first training is information of two time points T1 and T2, and the output is information of two time points T3 and T4. In the second training, the input of AI is information of two time points T2 and T3, and the output is information of two time points T4 and T5. It can be seen that, in this case, the information of the time point T2 as the input is reused, and the information of the time point T4 as the output is reused. The data of the reused part needs to be transmitted twice, causing the overhead of air interface transmission and the overhead of storage of a training device. In the above manner, the reused data is indicated by the third indication information, so that the reused data is not transmitted multiple times, thereby reducing the overhead of air interface transmission and the overhead of storage of the training device.

[0201] Specifically, taking that the AI model is used for beam management training as an example:

[0202] For the input of the AI model: if the first input of data is a data set RSRP_1 and RSRP_2 scanned at two time points (1 and 2 respectively indicate the time sequence), and the second input is RSRP_2 and RSRP_3, then RSRP_2 is reused, and when the data is transmitted, the activation identifier of “reuse” is added to RSRP_2, and the deactivation identifier of “reuse” is added to RSRP_1 and RSRP_3, that is, the identifier of “non-reuse”. For example, the identifier is indicated in the form of a bitmap, for example, the value of a bit is used to indicate whether the data is reused. The reuse activation identifier of RSRP_1, RSRP_2, and RSRP_3 in this transmission is 010. It should be understood that the value of the bit and the meaning represented by the value are not limited. For example, the value of the bit is 0, which can represent that the data corresponding to the bit is reused or not reused. The value of the bit is 1, and the same is true.

[0203] For the output of the AI model: the corresponding label of the output is information of two future time points, the first output is label_1 and label_2, and the second output is label_2 and label_3. As above, the data transmitted is indicated in the form of a bitmap, and the reuse identifier information of the output labels label_1, label_2, and label_3 is 010.

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

[0205] That is, for each data in the first data set, a corresponding identifier is configured, and for data that is shared (also referred to as multiplexed), the identifier corresponding to the data 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 the resources.

[0206] Taking that the training device uses a sliding window training as an example, the fourth indication information can indicate time domain information. Specifically,

[0207] For input: Each time input 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 multiplexing of RSRP_2 can be indicated by two dimensions, one is to indicate the time T_2, and the other is the shared activation indication (that is, the bit value 0 / 1 in the above possible implementation). The indication information corresponding to RSRP_2 is [T_2, 1].

[0208] For output: As for the input, the label_1(T_3) and the label_2(T_4) are the labels corresponding to the output of the first AI model, and the label_2(T_4) and the label_3(T_5) are the labels corresponding to the output of the second AI model. 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 are not limiting.

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

[0211] The information transmission method of the present application can be applied to the air interface transmission scene of training data. When the data acquisition device issues training data, it carries indication information indicating the use of the data, which can associate or distinguish different training data, facilitating the training device to identify the association between different training data and the use of the training data to meet the training needs of different AI models, saving the overhead of the training device. Further, in the scene where data multiplexing is required, the data acquisition device indicates these multiplexed data through the indication information, and the training device can identify the use of different data in the data set, reducing the repeated sending of data and reducing the transmission amount of air interface data, achieving the purpose of reducing air interface overhead.

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

[0213] It can be understood that in some embodiments described above, the training device and the data acquisition device are mainly exemplarily illustrated, and this is not limited. For example, the training device can be replaced by a component (such as a chip or a circuit) of the training device, and the data acquisition device can be replaced by a component (such as a chip or a circuit) of the data acquisition device.

[0214] Optionally, the training device in the present application can be a data acquisition device or a terminal device, and the present application does not limit this. The device capable of completing the data training task can be applied to the scheme of the present application.

[0215] It can also be understood that the schemes in the embodiments of the present application can be reasonably combined, and the explanation or description of each term appearing in the embodiments can be mutually referenced or explained in each embodiment, and this is not limited.

[0216] FIG. 9 is a schematic block diagram of a communication device 900 provided by 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 the corresponding communication function. The transceiver unit 910 can also be referred to as a communication interface or a communication unit. The processing unit 920 can be used for data processing.

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

[0218] As a design, the apparatus 900 is configured to perform the steps or procedures performed by the data acquisition device in the above method embodiments, or the steps or procedures performed by the device provided with the data acquisition device or the chip for the data acquisition device, such as the steps or procedures performed by the data acquisition device in the embodiment shown in FIG. 7. The transceiver unit 910 is configured to perform the operations related to transceiving at the side (or the sending end) of the data acquisition device in the above method embodiments, and the processing unit 920 is configured to perform the operations related to processing at the side (or the sending end) of the data acquisition device in the above method embodiments.

[0219] In a possible implementation, the processing unit 920 is configured to determine a first data set, and data in the first data set is used for training of a first artificial intelligence (AI) model.

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

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

[0222] As another design, the apparatus 900 is configured to perform the steps or procedures performed by the training device in the above method embodiments, or the steps or procedures performed by the device provided with the training device or the chip for the training device, such as the steps or procedures performed by the training device in the embodiment shown in FIG. 7. The transceiver unit 910 is configured to perform the operations related to transceiving at the side (or the receiving end) of the training device in the above method embodiments, and the processing unit 920 is configured to perform the operations related to processing at the side (or the receiving end) of the training device in the above method embodiments.

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

[0224] It should be understood that the specific processes in which the units perform the above corresponding steps have been described in detail in the above method embodiments, and thus are not described herein again for the sake of brevity.

[0225] It should also be understood that the apparatus 900 herein is embodied in the form of a functional unit. The term "unit" herein can refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (for example, a shared processor, a dedicated processor or a group processor and the like) and a memory for executing one or more software or firmware programs, a combination of logical circuit and / or other suitable components supporting the described functions. In an optional example, those skilled in the art can understand that the apparatus 900 can be embodied as the first terminal device in the above embodiments, and can be used to execute the processes and / or steps corresponding to the first terminal device in the above method embodiments, or the apparatus 900 can be embodied as the second terminal device in the above embodiments, and can be used to execute the processes and / or steps corresponding to the second terminal device in the above method embodiments, and details are not repeated here to avoid repetition.

[0226] The apparatus 900 of each of the above schemes has a function of implementing the corresponding steps performed by the first terminal device in the above method, or the apparatus 900 of each of the above schemes has a function of implementing the corresponding steps performed by the second terminal device in the above method. The function can be implemented by hardware or by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (for example, the transmitting 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, which respectively performs the transceiving operations and related processing operations in each method embodiment.

[0227] In addition, the transceiver unit 910 described above can also be a transceiver circuit (for example, can include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit.

[0228] It should be noted that the apparatus in FIG. 9 can be a network element or device in the above embodiments, or can be a chip or chip system, for example, a system on chip (SoC). The transceiver unit can be an input / output circuit, a communication interface; and the processing unit is a processor or microprocessor integrated on the chip or an integrated circuit. This is not limited here.

[0229] FIG. 10 is a schematic diagram of another communication apparatus 1000 provided by the embodiments of the present application. The apparatus 1000 includes a processing circuit 1010, and the processing circuit 1010 is coupled with a memory 1020, the memory 1020 is used to store computer programs or instructions and / or data, and 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 one or more processing circuits for processing or control.

[0231] Optionally, the memory 1020 is one or more.

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

[0233] Optionally, the apparatus 1000 further includes a transceiver circuit 1030 for receiving and / or transmitting signals, as shown in FIG. 10. For example, the processing circuit 1010 is configured to control the transceiver circuit 1030 to receive and / or transmit signals.

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

[0235] As an example, the apparatus 1000 is configured to implement operations performed by the data acquisition apparatus in the various 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 related operations of the data acquisition apparatus in the various method embodiments. For example, the method performed by the data acquisition apparatus in the embodiment shown in FIG. 7.

[0237] As another example, the apparatus 1000 is configured to implement operations performed by the training apparatus in the 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 related operations of the training apparatus in the various method embodiments. For example, the method performed by the training apparatus in the embodiment shown in FIG. 7.

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

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

[0241] When the apparatus 1000 is a chip for the data acquisition apparatus or the training apparatus, the transceiver circuit 1030 can be an input / output interface.

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

[0243] It should be understood that the processor mentioned in the embodiments of the present application can be a central processing unit (CPU), and can also 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 gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0244] It should also be understood that the memory mentioned in the embodiments of the present application can be a volatile memory and / or a non-volatile memory. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM). For example, the RAM can be used as an external cache. As an example but not limitation, the RAM includes the following various forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (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, or 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] Figure 11 is a schematic diagram of a chip system 1100 provided in an embodiment of this application. The chip system 1100 (or may also be called a processing system) includes a processing circuit 1110 (or logic circuit) and an input / output interface 1120.

[0248] The logic circuit 1110 can be a processing circuit in the chip system 1100. The logic circuit 1110 can be coupled to a memory unit, calling instructions from the memory unit, enabling the chip system 1100 to implement the methods and functions of the embodiments of this application. The input / output interface 1120 can be an input / output circuit in the chip system 1100, outputting processed information from the chip system 1100, or inputting data or signaling information to be processed into the chip system 1100 for processing.

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

[0250] As one approach, the chip system 1100 is used to implement the operations performed by the data acquisition device in the various method embodiments described above.

[0251] For example, logic circuit 1110 is used to implement 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 FIG7; input / output interface 1120 is used to implement 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 FIG7.

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

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

[0254] The embodiments of the present application further provide a computer readable storage medium, having stored thereon computer instructions for implementing the method performed by the data acquisition device or the training device in the various method embodiments above.

[0255] For example, the computer program, when executed by a computer, enables the computer to implement the method performed by the data acquisition device or the training device in the various method embodiments above.

[0256] The embodiments of the present application further provide a computer program product, containing instructions, which, when executed by a computer, implement the method performed by the data acquisition device or the training device in the various method embodiments above.

[0257] The embodiments of the present application further provide a communication system, which includes the data acquisition device and the training device in the various embodiments above. For example, the system includes the data acquisition device and the training device shown in FIG. 7. For another example, the system includes the training device with the data acquisition device arranged therein and the data acquisition device with the training device arranged therein.

[0258] The explanations and beneficial effects of the related contents in any of the above-provided devices can refer to the corresponding method embodiments provided above, which will not be repeated here.

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

[0260] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially 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, all or part of the processes or functions described in the embodiments of this application are generated. 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. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. 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 integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks, SSDs). For example, the aforementioned available media include, but are not limited to, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, and other media capable of storing program code.

[0261] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of information transmission, characterized in that, The method comprises: determining a first data set, data in the first data set being used for training of a first artificial intelligence (AI) model; sending the first data set and first indication information, the first indication information indicating a function and / or a feature of the first AI model.

2. The method of claim 1, wherein, The first data set comprises a first data subset and a second data subset, and the first indication information further indicates a function and / or a feature of an 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 comprises an identifier of the first AI model and / or an identifier of a function of the first AI model, or an identifier of the first data set and / or use 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 further used for training of a second AI model, and the first indication information further indicates a function and / or a feature of the second AI model.

5. The method of claim 1, wherein, The method further comprises: determining a second data set; sending the second data set and second indication information, the second indication information indicating a function and / or a 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 indicating the function and / or the feature of the first AI model comprises: the identifier of the first AI model and / or the identifier of the function of the first AI model indicating the function of the first AI model, and / or the identifier of the first AI model and / or the identifier of the function of the first AI model indicating the feature of the first AI model; or the identifier of the first data set and / or the use information of the first data set indicating the function of the first AI model, and / or the identifier of the first data set and / or the use information of the first data set indicating the feature 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; sending the second data set and second indication information, the second indication information indicating a function and / or a feature of the first AI model.

8. The method of claim 7, wherein, The method further comprises: the second indication information and the first indication information having the same value.

9. The method according to any one of claims 1 to 7, characterized in that, The first data set comprises a first data sample and a second data sample, and the method further comprises: sending third indication information, the third indication information indicating that the first data sample and the second data sample share first data, the first data belonging to the first data set.

10. The method of claim 9, wherein, The method further comprises: the first data being 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: sending fourth indication information, the fourth indication information indicating an identifier of the first data, or indicating resource information corresponding to the first data, the resource information corresponding to the first data comprising at least one of time domain resource information, frequency domain resource information, or space domain resource information.

12. The method according to any one of claims 1 to 11, characterized in that, The method further comprises: receiving fifth indication information, the fifth indication information indicating at least one of a function and / or a feature of one or more AI models supported by a training device, or storage and / or computing power information of the training device, the one or more AI models supported by the training device comprising the first AI model.

13. An information transmission method characterized by comprising: The method comprises: receiving a first data set and first indication information, data in the first data set being used for training of a first AI model, the first indication information indicating a function and / or a feature of the first AI model; determine, based on the first indication information, that data in the first data set is used for training of the first AI model.

14. The method of claim 13, wherein, The first data set includes a first data subset and a second data subset, and the first indication information further indicates functions and / or features of AI models corresponding to the first data subset and / or the second data subset, and the method further includes: determining, based on the first indication information, AI models corresponding to the first data subset and / or the second data subset.

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 of the first AI model, or an identifier of the first data set and / or use information of the first data set, The method further includes: determining, based on the first indication information, a use of the first data set and / or the first AI model corresponding to the first data set.

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

17. The method of claim 16, wherein, The method further includes: receiving a second data set and second indication information, the second indication information indicating functions and / or features of the first AI model.

18. The method of claim 17, wherein, 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, the third indication information indicating that the first data sample and the second data sample share first data, the first data belonging to the first data set; determining, 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 of claim 19, wherein, The first data is label information corresponding to input data and / or output data.

21. The method of claim 19 or 20, wherein, The method further includes: receiving fourth indication information, the fourth indication information indicating an identifier of the first data and / or indicating resource information corresponding to the first data, the resource information corresponding to the first data including at least one of time domain resource information, frequency domain resource information, or space domain resource information; using the first data on resources determined based on the resource information.

22. The method of any one of claims 13-18, wherein, The method further includes: sending fifth indication information, the fifth indication information indicating at least one of the following: functions and / or features of one or more AI models supported by a training device, storage and / or computing power information of the training device, the one or more AI models supported by the training device including the first AI model.

23. A communications device, characterized by including a module or unit for performing the method of any one of claims 1 to 22.

24. A communications device, characterized by including: an interface circuit and a processor; the interface circuit is configured to perform the transceiving steps in the method of any one of claims 1 to 12, and the processor is configured to perform the processing steps in the method of any one of claims 1 to 12; or, the interface circuit is configured to perform the transceiving steps in the method of any one of claims 13 to 22, and the processor is configured to perform the processing steps in the method of any one of claims 13 to 22.

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

26. A computer program product, characterised in that, comprising computer readable instructions which, when run on a computer, cause the computer to perform the method of any one of claims 1 to 22.

27. A communication system, characterized by comprising: having means to implement the method of any one of claims 1 to 12, and / or, having means to implement the method of any one of claims 13 to 22.

28. A chip system, characterized by The chip system comprises a processor for executing a computer program or instructions, such that the chip system implements the method of any one of claims 1 to 22.

Images