Model management method and device and communication equipment
By defining a reference model in a wireless communication network, including some or all the parameters and structures of the target model, the problem of difficulty in managing AI models is solved, the model management efficiency is improved and communication performance is ensured.
Patent Information
- Application Number
- CN202310535672.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-11
- Publication Date
- 2024-11-12
AI Technical Summary
In wireless communication networks, the performance, complexity and size differences of AI models make it difficult to manage the model and affect communication performance.
By defining a reference model, which contains some or all parameters and structures of the target model, used to perform predetermined communication processes, thereby achieving efficient management of the AI model.
Improve the efficiency of AI model management and ensure the stability and optimization of communication performance.
Smart Images

Figure CN118945701A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of communication technology, and specifically relates to a model management method, device and communication equipment. Background Art
[0002] Artificial Intelligence (AI) has been widely used in various fields. For example, integrating AI into wireless communication networks can significantly improve technical indicators such as throughput, latency, and user capacity, which is an important task for future wireless communication networks.
[0003] However, for the same communication process, the AI models used by the terminals may have various designs, and their performance, complexity, and size may vary greatly, making AI model management difficult and affecting communication performance. Summary of the invention
[0004] The embodiments of the present application provide a model management method, apparatus, and communication equipment, which can solve the problem of difficulty in AI model management and ensure communication performance.
[0005] In a first aspect, a model management method is provided, comprising: a first communication device performs model management on a reference model; wherein the reference model defines at least part of the model parameters or at least part of the model structure of a target model, and the target model is used by the first communication device to perform a predetermined communication process.
[0006] According to a second aspect, a communication method is provided, the method comprising: a second communication device performs model management on a reference model; wherein the reference model is configured on a first communication device, and the reference model defines at least part of the model parameters or at least part of the model structure of a target model, and the target model is used to execute a predetermined communication process.
[0007] According to a third aspect, a model management device is provided, comprising: a model management module for performing model management on a reference model; wherein the reference model defines at least part of the model parameters or at least part of the model structure of a target model, and the target model is used by a first communication device to perform a predetermined communication process.
[0008] In a fourth aspect, a model management device is provided, comprising: a model management module for performing model management on a reference model; wherein the reference model is configured in a first communication device, and the reference model defines at least part of the model parameters or at least part of the model structure of a target model, and the target model is used to execute a predetermined communication process.
[0009] In a fifth aspect, a communication device is provided, which terminal includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect or the second aspect are implemented.
[0010] In a sixth aspect, a communication device is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.
[0011] In the seventh aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.
[0012] In an eighth aspect, a wireless communication system is provided, comprising: a first communication device and a second communication device, wherein the first communication device can be used to execute the steps of the method described in the first aspect, and the second communication device can be used to execute the steps of the method described in the second aspect.
[0013] In the ninth aspect, a chip is provided, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.
[0014] In the tenth aspect, a computer program / program product is provided, wherein the computer program / program product is stored in a storage medium, and the program / program product is executed by at least one processor to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.
[0015] In an embodiment of the present application, the first communication device performs model management on a reference model, and the reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used by the first communication device to execute a predetermined communication process. Thus, the management of the target model for executing the predetermined communication process is achieved through the management of the reference model, which can solve the problem of difficult AI model management, improve model management efficiency, and ensure communication performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is a structural diagram of a wireless communication system provided by an exemplary embodiment of the present application.
[0017] Figure 2 It is one of the flowcharts of the model management method provided by an exemplary embodiment of the present application.
[0018] Figure 3 This is the second flowchart of the model management method provided by an exemplary embodiment of the present application.
[0019] Figure 4 This is the third flow chart of the model management method provided by an exemplary embodiment of the present application.
[0020] Figure 5 It is one of the structural schematic diagrams of the model management device provided by an exemplary embodiment of the present application.
[0021] Figure 6 This is the second structural diagram of the model management device provided by an exemplary embodiment of the present application.
[0022] Figure 7 It is a structural diagram of a communication device provided by an exemplary embodiment of the present application.
[0023] Figure 8 It is a schematic diagram of the structure of a terminal provided by an exemplary embodiment of the present application.
[0024] Fig. 9 It is a schematic diagram of the structure of a network side device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION
[0025] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of this application.
[0026] The terms "first", "second", etc. of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of one type, and the number of objects is not limited, for example, the first object can be one or more. In addition, "or" in the present application represents at least one of the connected objects. For example, "A or B" covers three schemes, namely, Scheme 1: including A but not including B; Scheme 2: including B but not including A; Scheme 3: including both A and B. The character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0027] The term "indication" in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication; an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.
[0028] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used for the systems and radio technologies mentioned above as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following descriptions, but these technologies can also be applied to systems other than NR systems, such as the 6th generation (6 th Generation, 6G) communication system.
[0029] Figure 1A block diagram of a wireless communication system applicable to an embodiment of the present application is shown. The wireless communication system includes a terminal 11 and a network side device 12. Among them, the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, an ultra-mobile personal computer (Ultra-mobile Personal Computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR), a virtual reality (Virtual Reality, VR) device, a robot, a wearable device (Wearable Device), an aircraft (flight vehicle), a vehicle-mounted device (Vehicle User Equipment, VUE), a ship-mounted device, a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (Personal Computer, PC), a teller machine or a self-service machine and other terminal side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (Wireless Local Area Network, WLAN) access point (Access Point, AS) or a wireless fidelity (Wireless Fidelity, WiFi) node, etc.Among them, the base station may be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a Relay Base Station (RBS), a Serving Base Station (SBS), a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a Home Node B (HNB), a Home Evolved Node B, a Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiments of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.
[0030] The technical solution provided by the embodiments of the present application is described in detail below through some embodiments and their application scenarios in combination with the accompanying drawings.
[0031] It should be noted that, depending on the communication scenario, there may be multiple types of the first communication device and the second communication device mentioned in this application. For example, when the communication scenario is a sidelink (SL) communication scenario, the first communication device and the second communication device may both be terminals. When the communication scenario is an uplink / downlink, the first communication device may be a terminal and the second communication device may be a network side device, etc., and no restrictions are made here.
[0032] In addition, the reference model mentioned below may also be referred to as an AI unit, an AI model, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a neural network, a neural network function, a neural network function, etc., or the reference model may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the reference model may be a processing method, algorithm, function, module or unit for a specific data set, or the reference model may be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as a graphics processing unit (GPU), a neural network processor (NPU), a tensor processor (TPU), an application specific integrated circuit (ASIC), etc., and this application does not specifically limit this. Among them, the specific data set includes the input or output of the reference model, etc.
[0033] Correspondingly, the model identifier of the reference model mentioned subsequently may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the reference model, or an identifier of a specific scenario, environment, channel feature, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. This application does not make any specific limitations on this.
[0034] Based on this, Figure 2 As shown, it is a flowchart of a model management method 200 provided by an exemplary embodiment of the present application. The method 200 can be, but is not limited to, executed by a first communication device, and can be specifically executed by hardware and / or software installed in the first communication device. In this embodiment, the method 200 can at least include the following steps.
[0035] S210: The first communication device performs model management on the reference model.
[0036] Among them, considering that in the related art, for different communication processes, various AI models may be deployed or configured in the first communication device, and even for the same communication process, multiple AI models with widely varying performance, complexity, size, etc. may be configured, which makes the management of AI models difficult. In this regard, a reference model is provided in the present application, and at least part of the model parameters (model parameter) or at least part of the model structure (model structure) of the target model is defined in the reference model, so that when the target model needs to be used or applied to perform a predetermined communication process, the target model corresponding to the predetermined communication process is directly determined based on the reference model, without the need to deploy or configure different AI models in the first communication device.
[0037] That is to say, the present application defines a reference model for use in a predetermined communication process, thereby solving the problem of difficulty in AI model management existing in related technologies through model management of the reference model, thereby improving model management efficiency.
[0038] In this case, if the reference model only defines some model parameters or some model structures of the target model, the target model can be generated based on the reference model and relevant characteristics of the predetermined communication process; if the reference model defines all model parameters or all model structures of the target model, the reference model can be directly determined as the target model and applied to the predetermined communication process, which is not limited in this embodiment.
[0039] It is worth noting that in order to ensure the model performance of the target model, the reference model provided in this embodiment can be a model with a classic structure, simple structure, stable performance, and good robustness, or the reference model can be measured by RF / baseband (such as RAN4) so that the target model determined based on the reference model can achieve better performance in the predetermined communication process.
[0040] Optionally, the reference model may have multiple model types, such as a neural network, a decision tree, a support vector machine, a Bayesian classifier, etc.; the neural network may be a fully connected neural network, a convolutional neural network, a recursive neural network, an attention neural network, a transformer neural network, etc., or any combination thereof, without limitation herein.
[0041] In addition, in this embodiment, the model parameters or model structure of the reference model configured or deployed in the first communication device can be implemented by protocol agreement, high-level configuration, negotiation among manufacturers, etc., and no limitation is made here.
[0042] Furthermore, according to different communication scenarios, there may be multiple predetermined communication processes. For example, in this embodiment, the predetermined communication process may include but is not limited to the following.
[0043] (a) Signal processing, including signal detection, filtering, equalization, etc. The signal may include but is not limited to a demodulation reference signal (DMRS), a sounding reference signal (SRS), a synchronization signal block (SSB), a tracking reference signal (TRS), a phase tracking reference signal (PTRS), a channel state information reference signal (CSI-RS), etc.
[0044] (b) Signal transmission / reception / demodulation / transmission. Including channels PDCCH, PDSCH, PUCCH, PUSCH, PRACH, PBCH, etc.
[0045] (c) Channel state information acquisition.
[0046] For example, channel state information feedback. The channel state information includes channel related information, channel matrix related information, channel characteristic information, channel matrix characteristic information, precoding matrix indicator (PMI), rank indicator (RI), CSI-RS resource indicator (CRI), channel quality indicator (CQI), layer indicator (LI), etc.
[0047] Another example is the partial reciprocity of uplink and downlink in frequency division duplex (FDD). For FDD systems, based on partial reciprocity, the base station obtains angle and delay information based on the uplink channel, and can notify the terminal of the angle and delay information through CSI-RS precoding or direct indication. The terminal then reports according to the indication of the base station or selects and reports within the indication range of the base station, thereby reducing the terminal's calculation workload and the CSI reporting overhead.
[0048] (d) Beam management, such as beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, and new beam indication in beam failure recovery.
[0049] (e) Channel prediction, such as prediction of channel state information, beam prediction, etc.
[0050] (f) Interference suppression, such as intra-cell interference suppression, inter-cell interference suppression, out-of-band interference suppression, and intermodulation interference suppression.
[0051] (g) Positioning: Positioning is performed by estimating the specific position (including horizontal position or vertical position) or possible future trajectory of the terminal through a reference signal (such as SRS), or by using information to assist in position estimation or trajectory estimation.
[0052] (h) Prediction and management of high-level services and parameters, such as throughput, required packet size, service demand, mobile speed, noise information, etc.
[0053] (i) Analysis of control signaling: The control signaling may be, but is not limited to, signaling related to power control, signaling related to beam management, etc.
[0054] In this embodiment, the first communication device performs model management on a reference model, and the reference model defines at least part of the model parameters or at least part of the model structure of the target model. The target model is used by the first communication device to execute a predetermined communication process. Thus, the management of the target model for executing the predetermined communication process is achieved through the management of the reference model, which can solve the problem of difficult AI model management, improve model management efficiency, and ensure communication performance.
[0055] like Figure 3 As shown, it is a flowchart of a model management method 300 provided by an exemplary embodiment of the present application. The method 300 can be, but is not limited to, executed by a first communication device, and can be specifically executed by hardware and / or software installed in the first communication device. In this embodiment, the method 300 can at least include the following steps.
[0056] S310: The first communication device performs model management on a reference model.
[0057] The reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used for the first communication device to perform a predetermined communication process.
[0058] It can be understood that in addition to referring to the relevant description in the aforementioned method embodiment 200, the implementation process of method embodiment 300 can, as a possible implementation method, when the first communication device performs model management on the reference model, it can be implemented based on its own capability information, such as at least one of the following methods 1 and 2.
[0059] Mode 1: Assuming that the reference model is divided into multiple levels, that is, the first communication device supports multiple reference models of different levels, then the first communication device can send device capability information to the second communication device to indicate the level (Level) of the reference model supported by the first communication device.
[0060] Optionally, in this embodiment, the device capability information may include at least one of the following (11)-(13).
[0061] (11) The highest level in the reference model supported by the first communication device.
[0062] (12) The lowest level in the reference model supported by the first communication device.
[0063] (13) All levels in the reference model supported by the first communication device.
[0064] It is worth noting that when the first communication device reports the device capability information, by reporting the highest level, the lowest level, and all levels of the reference model it supports, the first communication device and the second communication device can have the same understanding of the reference model supported by the first communication device, so as to achieve effective management of the reference model while saving signaling overhead.
[0065] For example, assuming that the reference model supported by the first communication device is divided into Level 0, Level 1, Level 2, and Level 3, then if the first communication device reports that it supports level 2, it means that the first communication device supports Level 0, Level 1, and Level 2, that is, the first communication device only needs to report the highest level it supports instead of reporting all levels, thereby saving signaling overhead.
[0066] Or, it means that the first communication device only supports Level 2, that is, the first communication device needs to report all the levels it supports.
[0067] Or, it indicates that the first communication device supports Level 2 and Level 3, that is, the first communication device needs to report the lowest level it supports instead of reporting all levels, thereby saving signaling overhead.
[0068] For another example, if the first communication device reports support for Level 0 and Level 2, it means that the first communication device supports Level 0, Level 1, and Level 2, that is, the first communication device needs to report the highest level and the lowest level it supports instead of reporting all levels, thereby saving signaling overhead.
[0069] Mode 2: When the first communication device supports the AI-enable function, the second communication device is not reported to support the reference model. Accordingly, when the second communication device determines that the first communication device supports the AI-enable function, it may assume that the first communication device supports the reference model. Thus, while achieving the management of the reference model, it is possible to avoid additional signaling interaction for capabilities related to the reference model, effectively saving signaling overhead.
[0070] Furthermore, when performing model management of the reference model, in order to ensure that the reference model matches the predetermined communication process, in this embodiment, the first communication device can support updating of the model parameters of the reference model (i.e., without updating the model structure of the reference model), as well as monitoring of the model performance of the reference model.
[0071] For example, in a possible implementation, the first communication device may send first indication information to the second communication device to indicate that the first communication device supports model-related operations based on model parameters. Accordingly, after receiving the first indication information, the second communication device may perform model-related operations based on the model parameters to implement model management of the reference model, thereby effectively saving signaling overhead. At this time, the model structure of the reference model remains unchanged, and only the model parameters change.
[0072] The model-related operations may include but are not limited to at least one of model update, model delivery, and model transfer. It can be understood that the model transfer generally refers to the model being transferred over the air interface, or the model being transferred based on 3GPP signaling or 3GPP visible signaling. The model transfer is a relatively broad concept, which refers to the transfer of the model from one side to the other side.
[0073] It is worth noting that when performing model management based on model parameters, if the first communication device does not report the model structure supporting the reference model, the first communication device and the second communication device both assume that the first communication device supports the model structure of the reference model.
[0074] For example, in another possible implementation, the first communication device may also perform performance monitoring on the model performance of the reference model based on the target monitoring resources, or send the monitoring results of the model performance to the second communication device. Thus, while realizing model management of the reference model, it can also save signaling overhead and ensure the stability of communication performance.
[0075] Wherein, when performing model performance monitoring, the target monitoring resource can be configured by protocol agreement, high-level configuration or network side configuration, and is not limited here. Wherein, assuming that the target monitoring resource is configured by the network side device, then regardless of whether the reference model is in an active state or an inactive state, the network side needs to configure the target monitoring resource for the first communication device for performance monitoring or reporting of the reference model.
[0076] In addition, if a non-reference model exists on the first communication device, the network-side device may configure additional or more monitoring resources for performance monitoring or reporting of the non-reference model.
[0077] Of course, in one implementation, when monitoring the model performance of the reference model, the performance monitoring indicator (performance monitoring KPI) or performance monitoring method (or mode or configuration) corresponding to the model performance may be a default value. And the default value may be agreed upon by the protocol, or the default value may be determined by the first communication device and reported to the second communication device, which is not limited here.
[0078] Furthermore, when the first communication device performs model management on the reference model, in addition to the aforementioned management method, as a possible implementation method, the first communication device can also implement further effective management of the reference model from the two aspects of model registration and model activation, so as to improve the stability of the communication system while saving signaling overhead.
[0079] For example, when the first communication device performs model registration of the reference model, its implementation method may include at least one of the following methods 1 to 3.
[0080] Method 1: When the model identifier (model ID) of the reference model is agreed upon by the protocol, the first communication device does not perform the model registration process of the reference model, that is, the model identifier of the reference model is agreed upon by the protocol and no additional model registration process is required, thereby effectively saving signaling overhead.
[0081] It should be noted that the aforementioned model identifier can be a logical model identifier (logical model ID), and when a non-reference model is also configured in the first communication device, the model identifier of the reference model is different from the model identifier of the non-reference model to avoid the non-reference model occupying the model identifier of the reference model.
[0082] Of course, an additional registration process is required for non-reference models.
[0083] Mode 2: The model identifier of the reference model is different from the model identifier of the non-reference model to avoid the non-reference model occupying the model identifier of the reference model.
[0084] Mode 3: When there is one (or only one) reference model, the first communication device initiates a model registration process for the reference model. The model registration process does not carry or indicate a model identifier. That is, when the first communication device supports only one reference model, although a model registration process is required, the reference model does not require a model identifier (such as a logical model identifier). In this way, when performing related signaling interactions for the reference model, the model identifier of the reference model may not be carried, thereby saving signaling overhead.
[0085] In this case, when the first communication device or the second communication device does not carry or indicate a model identifier in the received model-related information (or related signaling of a reference model), it can be determined that the model indicated by the model-related information is the reference model, thereby being able to indicate the reference model while saving the signaling overhead caused by the model identifier.
[0086] For another example, when the first communication device activates or uses a reference model, its implementation method may include: when at least one of the following (21)-(22) is met, the first communication device may activate or use the reference model by default, thereby avoiding the transmission of activation signaling to save signaling overhead.
[0087] (21) The first communication device accesses a target cell, where the target cell is a cell to which the first communication device accesses after cell switching, or the target cell is an initial access cell of the first communication device.
[0088] (22) The first communication device falls back to a non-AI mode. Here, “the first communication device falls back to” can be understood as the function / feature / module corresponding to the reference model falling back to a non-AI mode, or in other words, using a non-AI algorithm or process to run the function / feature / module corresponding to the reference model.
[0089] Furthermore, the first communication device may also perform model management on the reference model from the perspective of model usage to ensure the stability of the communication system. For example, when the reference model is used for model reasoning, the model reasoning must meet predetermined requirements. It should be noted that the model reasoning must meet predetermined requirements may mean that in a typical scenario, the model reasoning must meet predetermined requirements. For atypical scenarios, the model reasoning may not meet predetermined requirements.
[0090] Optionally, the aforementioned "typical scenario" may be, but is not limited to, a scenario in a test case defined by RAN4, and may include a data set generated under given parameters of a 3GPP channel model, a given field data set, etc. Correspondingly, the model reasoning meeting the predetermined requirements may also be that the performance indicators defined by RAN4 meet the predetermined requirements.
[0091] Correspondingly, the aforementioned “atypical scenarios” may be, but are not limited to, scenarios other than the typical scenarios, and are not limited here.
[0092] Exemplarily, in the present application, the model reasoning satisfying the predetermined requirements may include at least one of the following (31)-(35).
[0093] (31) The relevant indicators of the model inference results meet the first requirement. The model inference results can be the cosine similarity, normalized mean square error (NMSE), etc. between the recovered channel and the channel to be compressed (or the input and output of the model) in the CSI compression use case, the cosine similarity, NMSE, etc. between the predicted channel and the actual channel in the CSI prediction use case, the beam prediction error, beam prediction accuracy, etc. in the beam management use case, and the position error, positioning error, intermediate positioning information (time of arrival (TOA), time difference of arrival (TDOA), line of sight (LOS) delay, arrival angle (AOA), departure angle (AOD) error, etc.) in the positioning use case.
[0094] (32) The system performance related to the model reasoning meets the second requirement. The system performance may be, but is not limited to, system BLER, system throughput, etc.
[0095] (33) The inference delay of the model inference meets the third requirement.
[0096] (34) The inference power consumption of the model inference meets the fourth requirement.
[0097] (35) The hardware indicators of the model reasoning meet the fifth requirement. The hardware indicators may include but are not limited to the memory size, computing power, complexity, etc. of the communication device (such as the first communication device) that uses the reference model to perform model reasoning.
[0098] It is worth noting that the aforementioned first requirement, second requirement, third requirement, fourth requirement, and fifth requirement can be implemented by protocol agreement, high-level configuration, or network-side configuration, and are not limited here.
[0099] In this embodiment, by performing life cycle management on the reference model from aspects such as device capability reporting, model transmission, model registration, model activation, and model performance monitoring, it is possible to reduce the difficulty of model management, achieve efficient model management, save signaling overhead, and ensure the stability of the communication system.
[0100] like Figure 4 As shown, it is a flowchart of a model management method 400 provided by an exemplary embodiment of the present application. The method 400 can be, but is not limited to, executed by a first communication device, and can be specifically executed by hardware and / or software installed in the first communication device. In this embodiment, the method 400 can at least include the following steps.
[0101] S410: The second communication device performs model management on the reference model.
[0102] The reference model is configured in the first communication device, and at least part of the model parameters or at least part of the model structure of the target model are defined in the reference model, and the target model is used to execute a predetermined communication process.
[0103] Optionally, the second communication device performs model management on the reference model, including any of the following: receiving device capability information sent by the first communication device, the communication device capability information being used to indicate the level of the reference model supported by the first communication device; when it is determined that the first communication device supports the AI enabling function, assuming that the first communication device supports the reference model.
[0104] Optionally, the second communication device performs model management on the reference model, including at least one of the following: receiving first indication information sent by the first communication device, the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters of the reference model, and the model-related operations include at least one of model update, model transfer, and model transmission; upon receiving a model registration request corresponding to the reference model sent by the first communication device, registering the reference model, wherein the model registration process does not carry or indicate a model identifier.
[0105] It can be understood that the various implementation methods of the model management method mentioned in the present method embodiment 400 have the same or corresponding technical features as the model management method mentioned in the aforementioned method embodiments 200-300. Therefore, the implementation process of the various implementation methods of the model management method mentioned in the present method embodiment 400 can refer to the relevant description in the aforementioned method embodiments 200-300, and achieve the same or corresponding technical effects. In order to avoid repetition, it will not be repeated here.
[0106] The model management method 200-400 provided in the embodiment of the present application can be executed by a model management device. In the embodiment of the present application, the model management device provided in the embodiment of the present application is described by taking the execution of the model management method by the model management device as an example.
[0107] like Figure 5 As shown, it is a structural diagram of a model management device 500 provided in an embodiment of the present application, and the device 500 includes a model management module 510, which is used to perform model management on a reference model; wherein, the reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used for the first communication device to execute a predetermined communication process.
[0108] Optionally, the device 500 may further include a model acquisition module for acquiring the reference model. The reference model may be determined by network side device indication, protocol agreement, high-level configuration, negotiation among various manufacturers, etc., which is not limited here.
[0109] Optionally, the model management module 510 performs model management on the reference model, including at least one of the following: when the first communication device supports multiple reference models of different levels, sending device capability information to the second communication device, wherein the device capability information is used to indicate the level of the reference model supported by the first communication device; when the first communication device supports the AI-enable feature, not reporting to the second communication device that the first communication device supports the reference model.
[0110] Optionally, the device capability information includes at least one of the following: the highest level in the reference model supported by the first communication device; the lowest level in the reference model supported by the first communication device; all levels in the reference model supported by the first communication device.
[0111] Optionally, the model management module 510 performs model management on the reference model, including: sending a first indication information to the second communication device, the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters, and the model-related operations include at least one of model update, model transfer, and model transmission.
[0112] Optionally, the model management module 510 performs model management on the reference model, including at least one of the following: when the model identifier of the reference model is a protocol agreement, the model registration process of the reference model is not executed; the model identifier of the reference model is different from the model identifier of the non-reference model; when there is only one reference model, the model registration process of the reference model is initiated, wherein the model registration process does not carry or indicate the model identifier.
[0113] Optionally, after the first communication device initiates the model registration process of the reference model, the device also includes: a determination module, used to determine that the model indicated by the model-related information is the reference model when the received model-related information does not carry or indicate a model identifier.
[0114] Optionally, the model management module 510 performs model management on the reference model, including: the first communication device activates or uses the reference model when at least one of the following is met: the first communication device accesses a target cell, the target cell is a cell after the first communication device performs cell switching, or the target cell is an initial access cell of the first communication device; the first communication device falls back to non-AI mode.
[0115] Optionally, when the reference model is used for model reasoning, the model reasoning meets predetermined requirements.
[0116] Optionally, the model reasoning meets predetermined requirements, including at least one of the following: relevant indicators of the model reasoning results meet the first requirement; the system performance related to the model reasoning meets the second requirement; the reasoning delay of the model reasoning meets the third requirement; the reasoning power consumption of the model reasoning meets the fourth requirement; and the hardware indicators of the model reasoning meet the fifth requirement.
[0117] Optionally, the model management module 510 performs model management on the reference model, including at least one of the following: monitoring the model performance of the reference model based on target monitoring resources; and sending the monitoring result to the second communication device.
[0118] Optionally, the performance monitoring indicator or performance monitoring device corresponding to the model performance is a default value: the default value satisfies at least one of the following: agreed upon by a protocol; determined by the first communication device and reported to the second communication device.
[0119] like Figure 6As shown, it is a structural diagram of a model management device 600 provided in an embodiment of the present application, and the device 600 includes: a model management module 610, which is used to perform model management on a reference model; wherein the reference model is configured in a first communication device, and at least part of the model parameters or at least part of the model structure of the target model are defined in the reference model, and the target model is used to execute a predetermined communication process.
[0120] Optionally, the apparatus 600 further includes a sending module, configured to send relevant information of a reference model to a first communication device, wherein the relevant information of the reference model is used by the first communication device to configure or deploy the reference model.
[0121] Optionally, the model management module 610 performs model management on the reference model, including any of the following: receiving device capability information sent by a first communication device, the device capability information being used to indicate a level of the reference model supported by the first communication device; and when it is determined that the first communication device supports the AI enabling function, assuming that the first communication device supports the reference model.
[0122] Optionally, the model management module 610 performs model management on the reference model, including at least one of the following: receiving first indication information sent by the first communication device, the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters of the reference model, and the model-related operations include at least one of model update, model transfer, and model transmission; upon receiving a model registration request corresponding to the reference model sent by the first communication device, registering the reference model, wherein the model registration process does not carry or indicate a model identifier.
[0123] The model management device 500-600 in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than a terminal. Exemplarily, the terminal can include but is not limited to the types of the terminal 11 listed above, and other devices can be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiment of the present application.
[0124] The model management device 500-600 provided in the embodiment of the present application can realize Figures 2 to 4 The various processes implemented by the method embodiment and achieving the same technical effect are not described here to avoid repetition.
[0125] like Figure 7As shown, the embodiment of the present application further provides a communication device 700, including a processor 701 and a memory 702, and the memory 702 stores a program or instruction that can be run on the processor 701. For example, when the communication device 700 is a terminal, the program or instruction is executed by the processor 701 to implement the various steps of the above-mentioned model management method embodiment, and can achieve the same technical effect. When the communication device 700 is a network side device, the program or instruction is executed by the processor 701 to implement the various steps of the above-mentioned model management method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0126] The embodiment of the present application also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the following Figure 2-Figure 4 The steps in the method embodiment shown. This terminal embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this terminal embodiment and can achieve the same technical effect. Specifically, Figure 8 A schematic diagram of the hardware structure of a terminal for implementing an embodiment of the present application.
[0127] The terminal 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809 and at least some of the components of a processor 810.
[0128] Those skilled in the art will appreciate that the terminal 800 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 810 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 8 The terminal structure shown in the figure does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
[0129] It should be understood that in the embodiment of the present application, the input unit 804 may include a GPU 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.
[0130] In the embodiment of the present application, after receiving downlink data from the network side device, the radio frequency unit 801 can transmit the data to the processor 810 for processing; in addition, the radio frequency unit 801 can send uplink data to the network side device. Generally, the radio frequency unit 801 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
[0131] The memory 809 can be used to store software programs or instructions and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 809 may include a volatile memory or a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
[0132] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 810.
[0133] The processor 810 is used to perform model management on the reference model; wherein the reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used by the first communication device to perform a predetermined communication process.
[0134] Optionally, the processor 810 performs model management on the reference model, including at least one of the following: when the first communication device supports multiple reference models of different levels, sending device capability information to the second communication device, wherein the device capability information is used to indicate the level of the reference model supported by the first communication device; when the first communication device supports the AI-enable feature, not reporting to the second communication device that the first communication device supports the reference model.
[0135] Optionally, the device capability information includes at least one of the following: the highest level in the reference model supported by the first communication device; the lowest level in the reference model supported by the first communication device; all levels in the reference model supported by the first communication device.
[0136] Optionally, the processor 810 performs model management on the reference model, including: sending first indication information to the second communication device, the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters, and the model-related operations include at least one of model update, model transfer, and model transmission.
[0137] Optionally, the processor 810 performs model management on the reference model, including at least one of the following: when the model identifier of the reference model is a protocol agreement, the model registration process of the reference model is not executed; the model identifier of the reference model is different from the model identifier of the non-reference model; when there is only one reference model, the model registration process of the reference model is initiated, wherein the model registration process does not carry or indicate the model identifier.
[0138] Optionally, the processor 810 is further configured to determine that the model indicated by the model-related information is the reference model when the received model-related information does not carry or indicate a model identifier.
[0139] Optionally, the processor 810 performs model management on the reference model, including: the first communication device activates or uses the reference model when at least one of the following is met: the first communication device accesses a target cell, the target cell is a cell after the first communication device performs cell switching, or the target cell is an initial access cell of the first communication device; the first communication device falls back to non-AI mode.
[0140] Optionally, when the reference model is used for model reasoning, the model reasoning meets predetermined requirements.
[0141] Optionally, the model reasoning meets predetermined requirements, including at least one of the following: relevant indicators of the model reasoning results meet the first requirement; the system performance related to the model reasoning meets the second requirement; the reasoning delay of the model reasoning meets the third requirement; the reasoning power consumption of the model reasoning meets the fourth requirement; and the hardware indicators of the model reasoning meet the fifth requirement.
[0142] Optionally, the processor 810 performs model management on the reference model, including at least one of the following: monitoring the model performance of the reference model based on the target monitoring resource; and sending the monitoring result to the second communication device.
[0143] Optionally, the performance monitoring indicator or performance monitoring device corresponding to the model performance is a default value: the default value satisfies at least one of the following: agreed upon by a protocol; determined by the first communication device and reported to the second communication device.
[0144] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of method embodiments 200-400, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.
[0145] The embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method embodiment shown in Figures 200-400. The network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the network side device embodiment, and can achieve the same technical effect.
[0146] Specifically, the embodiment of the present application also provides a network side device. Fig. 9 As shown, the network side device 900 includes: an antenna 901, a radio frequency device 902, a baseband device 903, a processor 904 and a memory 905. The antenna 901 is connected to the radio frequency device 902. In the uplink direction, the radio frequency device 902 receives information through the antenna 901 and sends the received information to the baseband device 903 for processing. In the downlink direction, the baseband device 903 processes the information to be sent and sends it to the radio frequency device 902. The radio frequency device 902 processes the received information and sends it out through the antenna 901.
[0147] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 903 , which includes a baseband processor.
[0148] The baseband device 903 may include, for example, at least one baseband board on which a plurality of chips are arranged. Fig. 9As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 905 through a bus interface to call the program in the memory 905 to execute the network device operations shown in the above method embodiment.
[0149] The network side device may further include a network interface 906, which is, for example, a Common Public Radio Interface (CPRI).
[0150] Specifically, the network side device 900 of the embodiment of the present application further includes: an instruction or program stored in the memory 905 and executable on the processor 904, and the processor 904 calls the instruction or program in the memory 905 to execute Figure 5 or Figure 6 The methods executed by the modules shown achieve the same technical effects, and therefore will not be described here in detail to avoid repetition.
[0151] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned model management method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0152] The processor is the processor in the terminal described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.
[0153] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned model management method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0154] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
[0155] The embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned model management method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0156] An embodiment of the present application also provides a wireless communication system, including: a first communication device and a second communication device, wherein the first communication device can be used to execute the various processes of the above method embodiments 200-300, and the second communication device can be used to execute the various processes of the above method embodiment 400, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0157] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0158] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general hardware platform, and of course, can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, disk, CD, etc.), including several instructions to enable a terminal or a network-side device to execute the methods described in each embodiment of the present application.
[0159] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of the present application and the scope of protection of the claims, and these implementation methods are all within the protection of the present application.
Claims
1. A model management method, characterized in that: include: The first communication device performs model management on the reference model; The reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used for the first communication device to perform a predetermined communication process.
2. The method according to claim 1, characterized in that The first communication device performs model management on the reference model, including at least one of the following: In a case where the first communication device supports multiple reference models of different levels, sending device capability information to the second communication device, wherein the device capability information is used to indicate the level of the reference model supported by the first communication device; In a case where the first communication device supports the AI-enable feature, the fact that the first communication device supports the reference model is not reported to the second communication device.
3. The method according to claim 2, characterized in that The device capability information includes at least one of the following: the highest level in the reference model supported by the first communication device; the lowest level of the reference model supported by the first communication device; All levels in the reference model supported by the first communication device.
4. The method according to any one of claims 1 to 3, characterized in that The first communication device performs model management on the reference model, including: Sending first indication information to the second communication device, where the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters, and the model-related operations include at least one of model updating, model passing, and model transmission.
5. The method according to claim 1, characterized in that The first communication device performs model management on the reference model, including at least one of the following: In a case where the model identifier of the reference model is a protocol agreement, the first communication device does not perform a model registration process of the reference model; The model identification of the reference model is different from the model identification of the non-reference model; In the case that there is only one reference model, the first communication device initiates a model registration procedure for the reference model, wherein the model registration procedure does not carry or indicate a model identifier.
6. The method according to claim 5, characterized in that After the first communication device initiates the model registration process of the reference model, the method further includes: In a case where the received model-related information does not carry or indicate a model identifier, it is determined that the model indicated by the model-related information is the reference model.
7. The method according to any one of claims 1 to 6, characterized in that The first communication device performs model management on the reference model, including: The first communication device activates or uses the reference model when at least one of the following conditions is met: The first communication device accesses a target cell, where the target cell is a cell after the first communication device performs cell switching, or the target cell is an initial access cell of the first communication device; The first communications device falls back to a non-AI mode.
8. The method according to any one of claims 1 to 7, characterized in that When the reference model is used for model reasoning, the model reasoning meets predetermined requirements.
9. The method according to claim 8, characterized in that The model reasoning meets predetermined requirements, including at least one of the following: The relevant indicators of the model reasoning results meet the first requirement; The system performance related to the model reasoning meets the second requirement; The inference delay of the model inference meets the third requirement; The inference power consumption of the model inference meets the fourth requirement; The hardware indicators of the model reasoning meet the fifth requirement.
10. The method according to any one of claims 1 to 9, characterized in that The first communication device performs model management on the reference model, including at least one of the following: monitoring the model performance of the reference model based on the target monitoring resource; The monitoring result is sent to the second communication device.
11. The method according to claim 10, characterized in that The performance monitoring indicators or performance monitoring methods corresponding to the model performance are default values: The default value satisfies at least one of the following: As agreed upon by agreement; The first communication device determines and reports to the second communication device.
12. A communication method, characterized in that: The method comprises: The second communication device performs model management on the reference model; The reference model is configured in the first communication device, and at least part of the model parameters or at least part of the model structure of the target model are defined in the reference model, and the target model is used to execute a predetermined communication process.
13. The method according to claim 12, characterized in that The second communication device performs model management on the reference model, including any of the following: Receiving device capability information sent by a first communication device, where the communication device capability information is used to indicate a level of a reference model supported by the first communication device; In a case where it is determined that the first communication device supports the AI enabling function, it is assumed that the first communication device supports the reference model.
14. The method according to claim 12, characterized in that The second communication device performs model management on the reference model, including at least one of the following: receiving first indication information sent by the first communication device, where the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters of the reference model, where the model-related operations include at least one of model update, model transfer, and model transmission; Upon receiving a model registration request corresponding to the reference model sent by the first communication device, registering the reference model, wherein the model registration process does not carry or indicate a model identifier.
15. A model management device, characterized in that: include: A model management module is used to manage the reference model; The reference model defines at least part of the model parameters or at least part of the model structure of the target model, and the target model is used for the first communication device to perform a predetermined communication process.
16. The device according to claim 15, characterized in that The model management module performs model management on the reference model, including at least one of the following: In a case where the first communication device supports multiple reference models of different levels, sending device capability information to the second communication device, wherein the device capability information is used to indicate the level of the reference model supported by the first communication device; In a case where the first communication device supports the AI-enable feature, the fact that the first communication device supports the reference model is not reported to the second communication device.
17. The device according to claim 16, characterized in that The device capability information includes at least one of the following: the highest level in the reference model supported by the first communication device; the lowest level of the reference model supported by the first communication device; All levels in the reference model supported by the first communication device.
18. The device according to any one of claims 15 to 17, characterized in that The model management module performs model management on the reference model, including: Sending first indication information to the second communication device, where the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters, and the model-related operations include at least one of model updating, model passing, and model transmission.
19. The device according to claim 15, characterized in that The model management module performs model management on the reference model, including at least one of the following: In the case where the model identifier of the reference model is a protocol agreement, the model registration process of the reference model is not performed; The model identification of the reference model is different from the model identification of the non-reference model; In the case that there is only one reference model, a model registration process of the reference model is initiated, wherein the model registration process does not carry or indicate a model identifier.
20. The device according to claim 19, characterized in that After the first communication device initiates the model registration process of the reference model, the apparatus further includes: The determination module is used to determine that the model indicated by the model-related information is the reference model when the received model-related information does not carry or indicate a model identifier.
21. The device according to any one of claims 15 to 20, characterized in that The model management module performs model management on the reference model, including: The first communication device activates or uses the reference model when at least one of the following conditions is met: The first communication device accesses a target cell, where the target cell is a cell after the first communication device performs cell switching, or the target cell is an initial access cell of the first communication device; The first communications device falls back to a non-AI mode.
22. The device according to any one of claims 15 to 21, characterized in that When the reference model is used for model reasoning, the model reasoning meets predetermined requirements.
23. The device according to claim 22, characterized in that The model reasoning meets predetermined requirements, including at least one of the following: The relevant indicators of the model reasoning results meet the first requirement; The system performance related to the model reasoning meets the second requirement; The inference delay of the model inference meets the third requirement; The inference power consumption of the model inference meets the fourth requirement; The hardware indicators of the model reasoning meet the fifth requirement.
24. The device according to any one of claims 15 to 23, characterized in that The model management module performs model management on the reference model, including at least one of the following: monitoring the model performance of the reference model based on the target monitoring resource; The monitoring result is sent to the second communication device.
25. The device according to claim 24, characterized in that The performance monitoring indicators or performance monitoring devices corresponding to the model performance are default values: The default value satisfies at least one of the following: As agreed upon by agreement; The first communication device determines and reports to the second communication device.
26. A model management device, characterized in that: The device comprises: A model management module is used to manage the reference model; The reference model is configured in the first communication device, and at least part of the model parameters or at least part of the model structure of the target model are defined in the reference model, and the target model is used to execute a predetermined communication process.
27. The device according to claim 26, characterized in that The model management module performs model management on the reference model, including any of the following: Receiving device capability information sent by a first communication device, where the device capability information is used to indicate a level of a reference model supported by the first communication device; In a case where it is determined that the first communication device supports the AI enabling function, it is assumed that the first communication device supports the reference model.
28. The device according to claim 26, characterized in that The model management module performs model management on the reference model, including at least one of the following: receiving first indication information sent by the first communication device, where the first indication information is used to indicate that the first communication device supports model-related operations based on model parameters of the reference model, where the model-related operations include at least one of model update, model transfer, and model transmission; Upon receiving a model registration request corresponding to the reference model sent by the first communication device, registering the reference model, wherein the model registration process does not carry or indicate a model identifier.
29. A communication device, characterized in that: It includes a processor and a memory, the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, it implements the steps of the model management method as described in any one of claims 1 to 11, or implements the steps of the model management method as described in any one of claims 12 to 14.
30. A readable storage medium, characterized in that: The readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the steps of the model management method as described in any one of claims 1 to 11 are implemented, or the steps of the model management method as described in any one of claims 12 to 14 are implemented.
Citation Information
Cited By
Model management method and apparatus, and communication device
EP4712426A1
