Communication function based on bilateral model

Abstract

The embodiment of the invention relates to a device, a method, equipment and a computer readable storage medium for a communication function based on a bilateral model. In one method, a first device obtains a reference data set for a communication function. The reference data set comprises reference data associated with a plurality of terminal devices, a plurality of network devices and at least one test device. The first device updates a reference encoder of the communication function based at least on the reference data. The first device updates a reference decoder of the communication function based at least on the reference data. At least one of the updated reference encoder or the updated reference decoder is used by another device to optimize communication functionality.

Description

Technical Field

[0001] Various exemplary embodiments of the present disclosure relate generally to the field of telecommunications, and more particularly, to devices, methods, apparatuses, and computer-readable storage media for communication functions based on a two-sided model. Background Art

[0002] Several techniques have been proposed to improve communication performance. For example, communication devices may use artificial intelligence (AI) / ML models to improve communication quality. AI / ML models can be applied to different communication functions in different scenarios. In some cases, communication functions based on two-sided AI / ML models are proposed. For example, a user equipment (UE) side encoder and a network (NW) side decoder can be used for communication functions. The performance of two-sided model-based communication functions is an important issue. Summary of the invention

[0003] In a first aspect of the present disclosure, a first device is provided. The first device includes at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the first device: obtains a reference data set of a communication function, wherein the reference data set includes reference data associated with multiple terminal devices, multiple network devices, and at least one test device; updates a reference encoder of the communication function based on at least the reference data; and updates a reference decoder of the communication function based on at least the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0004] In a second aspect of the present disclosure, a second device is provided. The second device includes at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the second device: receives information for updating a target encoder of a communication function from a first device, wherein the information includes at least one of the following: reference data of the communication function, a result of a reference encoder of the communication function of the first device using the reference data, and a parameter set of the reference encoder; and updates the target encoder based on the information.

[0005] In a third aspect of the present disclosure, a third device is provided. The third device includes at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the third device: receives information for updating a target decoder of a communication function from a first device, wherein the information includes at least one of the following: reference data of the communication function, a second result of a reference decoder of the communication function of the first device using a first result of an encoder of the communication function, and a parameter set of the reference decoder; and updates the target decoder based on the information.

[0006] In a fourth aspect of the present disclosure, a method is provided. The method comprises: obtaining a reference data set of a communication function at a first device, the reference data set comprising reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; updating a reference encoder of the communication function based at least on the reference data; and updating a reference decoder of the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0007] In a fifth aspect of the present disclosure, a method is provided. The method comprises: receiving, at a second device, information for updating a target encoder of a communication function from a first device, the information comprising at least one of the following: reference data of the communication function, a result of a reference encoder of the communication function of the first device using the reference data, and a parameter set of the reference encoder; and updating the target encoder based on the information.

[0008] In a sixth aspect of the present disclosure, a method is provided. The method comprises: receiving, at a third device, information for updating a target decoder of a communication function from a first device, the information comprising at least one of the following: reference data of the communication function, a first result of an encoder using the communication function, a second result of a reference decoder of the communication function of the first device, and a parameter set of the reference decoder; and updating the target decoder based on the information.

[0009] In a seventh aspect of the present disclosure, a first device is provided. The first device comprises: a component for obtaining a reference data set of a communication function, the reference data set comprising reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; a component for updating a reference encoder of the communication function based at least on the reference data; and a component for updating a reference decoder of the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0010] In an eighth aspect of the present disclosure, a second device is provided. The second device includes: a component for receiving information for updating a target encoder of a communication function from a first device, the information including at least one of the following: reference data of the communication function, a result of a reference encoder of the communication function of the first device using the reference data, and a parameter set of the reference encoder; and a component for updating the target encoder based on the information.

[0011] In a ninth aspect of the present disclosure, a third device is provided. The third device includes: a component for receiving information for updating a target decoder of a communication function from a first device, the information including at least one of the following: reference data of the communication function, a second result of a reference decoder of the communication function of the first device using a first result of an encoder of the communication function, and a parameter set of the reference decoder; and a component for updating the target decoder based on the information.

[0012] In a tenth aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, and the instructions are used to cause a device to at least execute the method according to the fourth, fifth or sixth aspect.

[0013] It should be understood that the invention summary is not intended to identify the key features or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0015] Figure 1 An example communication environment is shown in which example embodiments of the present disclosure may be implemented;

[0016] Figure 2 An example framework for training a two-sided model for communication functions is shown;

[0017] Figure 3 shows an example signaling diagram for a communication function based on a two-sided model according to some example embodiments of the present disclosure;

[0018] Figure 4 An example framework for training and testing a two-sided model of communication functions according to some example embodiments of the present disclosure is shown;

[0019] Figure 5 A flowchart showing a method implemented at a first device according to some example embodiments of the present disclosure is shown;

[0020] Figure 6 A flowchart showing a method implemented at a second device according to some example embodiments of the present disclosure is shown;

[0021] Figure 7 A flowchart showing a method implemented at a third device according to some example embodiments of the present disclosure is shown;

[0022] Figure 8 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0023] Fig. 9 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.

[0024] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION

[0025] The principle of the present invention will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described only for the purpose of illustration, and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation to the scope of the present disclosure. In addition to the embodiments described below, the embodiments described herein can be implemented in various ways.

[0026] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0027] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," etc., indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. Further, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is considered to be within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0028] It should be understood that, although the terms "first", "second", "second", etc., preceding nouns, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element, and they do not limit the order of the nouns. For example, without departing from the scope of the exemplary embodiment, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0029] As used herein, “at least one of: «a list of two or more elements» and “a list of two or more elements» and similar expressions, wherein a list of two or more elements is connected by “and” or “or”, refer to at least any one of the elements, or at least any two or more of the elements, or at least all of the elements.

[0030] As used herein, unless explicitly stated, performing a step “in response to A” does not mean performing the step immediately after “A” occurs, and may include one or more intermediate steps.

[0031] The terms used herein are only used for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that when used herein, the terms "comprises", "comprising", "has", "having", "includes", and / or "including" specify the presence of the features, elements, and / or parts, etc., but do not exclude the presence or addition of one or more other features, elements, parts, and / or combinations thereof.

[0032] As used in this application, the term "circuitry" may refer to one or more or all of the following:

[0033] (a) hardware circuit implementation only (e.g., implementation only in analog and / or digital circuits), and

[0034] (b) a combination of hardware circuitry and software such as (where applicable):

[0035] A combination of analog and / or digital hardware circuits and software / firmware, and

[0036] (ii) any portion of a hardware processor with software (including a digital signal processor), software, and memory that work together to enable a device such as a mobile phone or server to perform various functions; and

[0037] (c) A hardware circuit and / or processor, such as a microprocessor or portion of a microprocessor, that requires software (e.g., firmware) for operation, but the software may not be present when not needed for operation.

[0038] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of only a hardware circuit or processor (or multiple processors) or a portion of a hardware circuit or processor and its (or its) accompanying software and / or firmware. For example and if applicable to the particular claim element, the term circuitry also covers a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in a server, cellular network device, or other computing or network device.

[0039] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), Advanced LTE (LTE-A), Wideband Code Division Multiple Access (WCDMA), High Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. In addition, the communication between the terminal device and the network device in the communication network can be performed according to any suitable generation communication protocol, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), sixth generation (6G) communication protocol and / or any other protocol currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communication, there are of course future types of communication technologies and systems that can implement the present disclosure. It should not be considered that the scope of the present disclosure is limited to the above-mentioned system.

[0040] As used herein, the term "network device" refers to a node in a communication network via which a terminal device accesses a network and receives services from it. A network device may refer to a base station (BS) or an access point (AP), such as a NodeB (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NRNB (also known as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a repeater, an integrated access and backhaul (IAB) node, a low power node (such as a femto), a micro-net, a non-terrestrial network (NTN) or non-terrestrial network equipment, such as satellite network equipment, a low earth orbit (LEO) satellite and a geosynchronous orbit (GEO) satellite, an aircraft network equipment, etc., depending on the terminology and technology applied. In some example embodiments, a radio access network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at an IAB donor node. An IAB node includes a mobile terminal (IAB-MT) portion that behaves like a UE toward a parent node, and a DU portion of an IAB node behaves like a base station toward a next-hop IAB node.

[0041] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not limitation, the terminal device may also be referred to as a communication device, a user equipment (UE), a subscriber station (SS), a portable subscriber station, a mobile station (MS) or an access terminal (AT). The terminal device may include, but is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local loop phone, a tablet computer, a wearable terminal device, a personal digital assistant (PDA), a portable computer, a desktop computer, an image capture terminal device such as a digital camera, a game terminal device, a music storage and playback device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded device (LEE), a laptop mounted device (LME), a USB dongle, a smart device, a wireless customer premises equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable, a head mounted display (HMD), a vehicle, a drone, a medical device and an application (e.g., remote surgery), an industrial device and an application (e.g., a robot and / or other wireless devices operating in an industrial and / or automatic processing chain environment), a consumer electronic device, a device operating on a commercial and / or industrial wireless network, etc. The terminal device may also correspond to the mobile terminal (MT) part of an IAB node (eg, a relay node).In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.

[0042] As used herein, the terms "resource", "transmission resource", "resource block", "physical resource block" (PRB), "uplink resource" or "downlink resource" may refer to any resource used to perform communication (e.g., communication between a terminal device and a network device), such as a resource in the time domain, a resource in the frequency domain, a resource in the spatial domain, a resource in the code domain, or any other combination of time, frequency, space and / or code domain resources to achieve communication. In the following, unless explicitly stated, resources in the frequency domain and the time domain will be used as examples of transmission resources for describing some example embodiments of the present disclosure. It should be noted that the example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0043] As used herein, the term "AI / ML model" may refer to a data-driven algorithm that applies AI / ML techniques to produce a set of outputs based on a set of inputs. In the context of the present disclosure, the term "AI / ML model" may be used interchangeably with the terms "model," "AI model," and "ML model." The term "AI / ML" may be used interchangeably with the terms "AI" and "ML."

[0044] As mentioned above, AI / ML for the New Radio (NR) air interface is now being studied in the 3rd Generation Partnership Project (3GPP). One of the objectives of the study is to cover the interoperability and testability aspects of the newly defined AI / ML-enabled features.

[0045] In some mechanisms, work on interoperability and testability is started after there is sufficient progress on use case studies in Radio Access Network (RAN) 1 and RAN2. Requirements and test frameworks are intended to validate AI / ML based performance enhancements and ensure that UEs and gNBs with AI / ML meet or exceed existing minimum requirements (if applicable). The need and implications for AI / ML processing capability definition can be considered.

[0046] The AI / ML based communication function can be used for different use cases. For example, the AI / ML based communication function can be an AI / ML enabled channel state information (CSI) feedback enhancement, which can also be referred to as an AI / ML based CSI feedback use case. This use case is a potential use case that will be selected for the Release 19 work item on AI / ML.

[0047] In some mechanisms, CSI feedback enhancement based on a bilateral model is proposed. As an example, CSI compression is one of the sub-use cases of CSI feedback enhancement based on a bilateral model. CSI compression includes AI / ML-based encoding of CSI feedback (e.g., channel matrix, channel matrix eigenvalues, or Rel-17 type 11W2 coefficients) on the UE side and decoding it with a matching AI / ML model on the NW side. Because there are two components: a UE-side encoder and a NW-side decoder, such a model can be called a "bilateral model" or "two-sided model".

[0048] There are several methods for training such bilateral models. The training of bilateral models can be referred to as training collaboration for bilateral models. In one method (also known as type 1 training or type 1 joint training), the encoder and decoder can be jointly trained by a single entity or a single side (e.g., UE side or network side). In another method (also known as type 2 training or type 21 joint training), the encoder and decoder can be jointly trained at the UE and the network, respectively. In another method (also known as type 3 training or separate training), the encoder and decoder can be trained separately on the network side and the UE side. For example, the UE-side CSI generation part and the network-side CSI reconstruction part are trained by the UE side and the network side, respectively. It should be understood that any other suitable collaborative training types are not excluded.

[0049] As used herein, joint training means that the generation model and the reconstruction model should be trained in the same cycle for forward propagation and backward propagation. Joint training can be performed in a single node or across multiple nodes (e.g., by gradient exchange between nodes).

[0050] As used herein, separate training includes sequential training starting with UE-side training, or sequential training starting with NW-side training, or parallel training at UE and NW.

[0051] For type 3 training, independent or sequential training becomes an acceptable candidate for most companies. In type 3, there is a possibility to train the UE side first or the NW side first. In the case of UE-first independent training, the NW vendor needs to handle multiple UE-side (encoder) models, while the UE vendor can focus on a single (or only a few) encoder models. In the case of NW-first independent training, the UE vendor needs to handle multiple NW-side (decoder) models, while the NW vendor may focus on a single (or only a few) decoder models.

[0052] Since bilateral CSI compression is one of the selected sub-use cases, the testing mechanism for bilateral models and encoder / decoder design in RAN4 is a topic of great interest in 3GPP.

[0053] In some mechanisms (referred to as option 1), the reference decoder is provided by the supplier of the encoder to be tested, so that the encoder and decoder are jointly designed and trained. Alternatively, in some mechanisms (referred to as option 2), the reference decoder is provided by the supplier of the decoder (hereinafter supplier), so that the encoder and decoder are jointly designed and trained.

[0054] In some mechanisms (called option 3), the reference decoder is fully specified and captured in the RAN4 specification to ensure identical implementations across equipment vendors without the need for an additional training process. Alternatively, in some mechanisms (called option 4), the reference decoder is partially specified and captured in the RAN4 specification.

[0055] In some mechanisms (called option 6), the test decoder is specified and captured in RAN4 and provided by the test environment vendor.The encoder and decoder can be trained jointly.

[0056] It should be understood that other mechanisms or other options are not excluded.

[0057] In some mechanisms, the principles / conditions for the decoder / encoder (options 3 and 4, 6) specified by RAN4 can be designed. If a two-sided model is used at the WI stage, RAN4 should consider complexity constraints based on, for example, the feasibility of the test equipment (TE) implementation and the complexity level that the network vendor / UE vendor considers feasible for the decoder / encoder deployment.

[0058] Among some mechanisms, RAN4's choice of test decoder / encoder should be targeted as much as possible to avoid limiting the implementation choices of UE / gNB encoders / decoders operating in the field, including for example complexity, post-skeleton model, etc.

[0059] According to the ongoing discussions in RAN1 and RAN4, for the test framework, it is desirable to have a reference encoder or decoder suitable for both UE and network vendors, which can guarantee reasonable performance when used in a test setup. At the same time, the inherent details of the design of the encoder and decoder are not revealed.

[0060] According to some example embodiments of the present disclosure, a solution for a communication function based on a bilateral model is provided. In this solution, a first device (such as a test device (TE)) obtains a reference data set of a communication function. The reference data set includes reference data associated with multiple terminal devices, multiple network devices, and at least one test device. The first device updates a reference encoder and a reference decoder of the communication function based on at least the reference data. For example, the first device may create a reference encoder or a reference decoder. The created reference encoder or reference decoder may be further updated. At least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function. For example, the other device may be a terminal device, a network device, or a TE.

[0061] In this way, the communication function can be optimized. For example, an encoder or decoder for the communication function of another device can be updated. For another example, a reference decoder or reference encoder can also be used to test an encoder or decoder of another device.

[0062] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0063] Figure 1 1 shows an example communication environment 100 in which example embodiments of the present disclosure may be implemented. Figure 1 As shown, the communication network 100 may include a first device 110, a second device 120, and a third device 130. The first device 110 may communicate with the second device 120 and the third device 130. The second device 120 and the third device 130 may also communicate with each other.

[0064] A two-sided AI / ML model (also referred to as a “two-sided model”) may be deployed at the second device 120 and the third device 130. The two-sided AI / ML model may be used for any suitable use case or to implement any suitable communication function, such as, but not limited to, channel state information (CSI) feedback enhancement, etc. For example, an encoder for a communication function (e.g., an AI / ML encoder) may be deployed at or included in the second device 120. A decoder for a communication function (e.g., an AI / ML decoder) may be deployed at or included in the third device 130. The encoder of the second device 120 and the decoder of the third device 130 may be collectively referred to as a two-sided model or a two-sided AI / ML model.

[0065] It should be understood that Figure 1 The numbers of the first devices, the second devices, and the third devices shown in FIG. 1 are given for illustrative purposes and do not imply any limitation. The communication network 100 may include any suitable number of second devices and first devices.

[0066] In some example embodiments, the first device 110 may include a test device (TE). The second device 120 may include a device under test (DUT), such as a terminal device. The third device 130 may include a DUT such as a network device. For example, an AI / ML model may be implemented at the second device 120.

[0067] As used herein, the term "communication functionality" may refer to a function or service provided by an AI / ML model (such as a two-sided model). The term "communication functionality" may also be referred to as an "AI / ML-based functionality" or "AI / ML-enabled functionality" or "AI / ML-based use cases". In some example embodiments, the AI / ML models at the second device 120 and the third device 130 may need to be updated or tested. In other words, the communication functionality may need to be updated or tested.

[0068] In the following, for the purpose of illustration, some example embodiments are described as the first device 110 operating as a TE, the second device 120 operating as a terminal device, and the third device 130 operating as a network device. However, in some example embodiments, the operations described in conjunction with the TE may be implemented in a terminal device or a network device or other device, the operations described in conjunction with the terminal device may be implemented in a network device or other device, and the operations described in conjunction with the network device may be implemented in a terminal device or other device.

[0069] In some example embodiments, if the third device 130 is a network device and the second device 120 is a terminal device, the link from the second device 120 to the third device 130 is referred to as an uplink (UL), and the link from the third device 130 to the second device 120 is referred to as a downlink (DL). In the UL, the second device 120 is a transmitting (TX) device (or transmitter), and the third device 130 is a receiving (RX) device (or receiver). In the DL, the third device 130 is a TX device (or transmitter), and the second device 120 is an RX device (or receiver).

[0070] The communication in the communication environment 100 may be implemented according to any suitable communication protocol, including but not limited to cellular communication protocols of the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), fifth generation (5G), sixth generation (6G), etc., wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, etc., and / or any other protocol currently known or developed in the future. In addition, the communication may use any suitable wireless communication technology, including but not limited to: code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), frequency division duplex (FDD), time division duplex (TDD), multiple input multiple output (MIMO), orthogonal frequency division multiple access (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM) and / or any other technology currently known or developed in the future.

[0071] Figure 2 An example framework 200 for training a two-sided model for communication functions is shown. Assume Figure 2 The training in is NW first split training. For illustration purposes, relative to Figure 2 The communication function shown is CSI feedback or CSI compression.

[0072] As shown in the figure, separate training includes a NW side model training phase 210 and a UE side model training phase 250. Here, the AI ​​decoder on the NW side is first trained. When the AI ​​decoder on the NW side is trained together with the corresponding hypothetical AI encoder (training phase 210), the NW vendor needs to assume the AI ​​encoder model on the UE side. In this NW side model training phase 210, the input at the hypothetical AI encoder on the UE side (assuming the NW side) is called "INPUT-CSI-NW" in 3GPP. In some sense, this can be viewed as a “hypothesized target CSI”, i.e., the “hypothesis” is based on the NW-assumed pre-AIML chain operations at the UE (i.e., channel estimation, pre-processing like singular value decomposition (SVD), etc.), and a “target CSI”, since this is the target CSI that the AI ​​decoder at the NW side should aim to reconstruct from the hypothesized CSI feedback (dequantized hypothesized latent vector). Note that the hypothesized target CSI may deviate to some extent from the actual target CSI at the actual UE, as it depends on UE implementation specific properties, such as antenna imbalance, radio frequency integrated circuit (RFIC) characteristics, radio frequency (RF) non-linearities, baseband (BB) DL channel measurement algorithm, specific implementation practices of SVD, etc.

[0073] However, for the framework 200, it is desirable to have a reference encoder or decoder suitable for both UEs and network providers, which can guarantee reasonable performance when used in a test setting. At the same time, the inherent details of the design of the encoder and decoder are not revealed.

[0074] According to some example embodiments of the present disclosure, a first device 110 (such as a test device (TE)) obtains a reference data set of a communication function. The reference data set includes reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device. The first device 110 updates a reference encoder and a reference decoder of the communication function based on at least the reference data. At least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function. For example, the other device may be a terminal device, a network device, or a TE.

[0075] In this way, the communication function can be optimized. For example, an encoder or decoder for the communication function of another device can be updated. For another example, a reference decoder or reference encoder can also be used to test an encoder or decoder of another device.

[0076] Reference now Figure 3 , which shows a signaling diagram 300 for a communication function based on a two-sided model according to some example embodiments of the present disclosure. Figure 3 As shown, the signaling diagram 300 includes Figure 1The first device 110, the second device 120, the third device 130 and the optional fourth device 301 in the embodiment. The fourth device 301 can be a TE or any other suitable device.

[0077] The signaling diagram 300 may be applicable to any suitable AI / ML use case or any suitable communication function. For example, different communication functions may include, but are not limited to, CSI feedback enhancement, beam management, positioning, etc. Some example embodiments are described below using CSI feedback as an example. However, it should be understood that this is only an example without any limitation, and the concepts described with respect to CSI feedback may be applied to another AI / ML-based communication function or use case.

[0078] It should be understood that although Figure 3 A single first device 110, a single second device 120, a single third device 130, and a single optional fourth device 301 are shown, but it should be understood that there may be multiple devices that perform similar operations as described below with respect to the first device 110, the second device 120, the third device 130, or the fourth device 301.

[0079] like Figure 3 As shown, the signaling diagram 300 includes a data collection process 310. In the data collection process 310, the first device 110 obtains (324) a reference data set of the communication function. As used herein, the term "reference data set" may also be referred to as a "training data set". The term "reference data" may also be referred to as "training data". The reference data set includes reference data associated with multiple terminal devices, multiple network devices, and at least one test device. In some example embodiments, different devices (such as UE vendors or NW vendors) share data that can be used for training at the first device 110. TE vendors may also share data.

[0080] For example, the second device 120 may transmit (312) reference data to the first device 110. The third device 130 may send (316) reference data to the first device 110. The fourth device 301 may send reference data to the first device 110 (320). The first device 301 may receive (314 / 318 / 322) reference data from the second device 120, the third device 130, or the fourth device 301.

[0081] The first device 110 may store the received ( 314 / 318 / 322 ) reference data in a reference data set. For example, reference data from different sources may be stored in a data repository communicatively connected to the first device 110 or included in the first device 110 .

[0082] The first device 110 may perform an update or training process 330 based on the reference data set. The first device 110 may create (333) or generate a reference encoder for the communication function based at least on the reference data. For example, the reference encoder may cater to different decoders of the third device 130. The reference encoder may be created (333) or designed in concert with all state holders. The design and characteristics of the reference encoder may be fully or partially specified by 3GPP or any other standardization body.

[0083] Alternatively, in some example embodiments, the first device 110 may not create a reference encoder, but the first device 110 may receive a parameter set of the reference encoder from the fourth device 301 or from any other suitable device. The first device 110 may alternatively receive the parameter set of the reference encoder from a data repository.

[0084] In some example embodiments, the first device 110 may generate (332) synthetic data based on the reference data. The first device 110 may create (333) a reference encoder based on the synthetic data.

[0085] In some example embodiments, various aspects of the data that can be used to train the model (encoder and / or decoder) (e.g., the minimum set of parameters that can be used across datasets from different sources) are specified (in whole or in part) by 3GPP or any other standardization organization. Based on those aspects and other mutual agreements between stakeholders, synthetic data can be generated from the latest datasets available in the data repository.

[0086] First device 110 updates (334) a reference encoder of the communication function based on at least the reference data. For example, first device 110 may partially or completely train the reference encoder, or fine-tune, refine, or retrain the reference encoder. In some example embodiments, the reference encoder may be a hypothetical encoder.

[0087] It should be understood that in some example embodiments, if the reference encoder created (333) is well created (or well trained), then the updating (334) of the reference encoder may be optional. As used herein, the term "updating an encoder" may refer to "determining parameters of a created encoder" or "updating parameters of an existing or trained encoder." As used herein, the term "updated reference encoder" may also refer to a well created reference encoder that is not updated, or to a "partially or fully trained encoder," a "refined or retrained encoder," or a "fine-tuned encoder."

[0088] Likewise, the first device 110 may create (337) or generate a reference decoder for the communication function based at least on the reference data. For example, the reference decoder may be created from scratch. In some example embodiments, the first device 110 may create (337) a reference decoder based on the synthesized data. For example, the reference decoder may cater to different encoders designed by various UE vendors. The reference decoder may be created (337) or designed to be consistent with all state holders. The design and characteristics of the reference decoder may be specified in whole or in part by 3GPP or any other standardization body.

[0089] Alternatively, in some example embodiments, the first device 110 may not create a reference decoder, but the first device 110 may receive a parameter set of the reference decoder from the fourth device 301 or from any other suitable device. The first device 110 may alternatively receive a parameter set of the reference decoder from a data repository.

[0090] First device 110 updates (338) a reference decoder of the communication function based at least on the reference data. For example, first device 110 may partially or completely train the reference decoder, or fine-tune, refine, or retrain the reference decoder. In some example embodiments, the reference encoder may be a hypothetical decoder. This updated reference decoder may cater to different encoders.

[0091] It should be understood that in some example embodiments, if the reference decoder created (337) is well created (or well trained), then the updating (338) of the reference decoder may be optional. As used herein, the term "updating a decoder" may refer to "determining parameters of a created decoder" or "updating parameters of an existing or trained decoder". As used herein, the term "updated reference decoder" may also refer to a well created reference decoder that is not updated, or to a "partially or fully trained decoder", "a refined or retrained decoder", or a "fine tuned decoder".

[0092] At least one of the updated (334) reference encoder or the updated (338) reference decoder is used by another device (such as the second device 120, the third device 130, or the fourth device 301) to optimize communication functions.

[0093] In some example embodiments, first device 110 may obtain (336) a first result of an updated reference encoder of a communication function using the reference data. First device 110 may update (338) a reference decoder of the communication function based on the first result and the reference data. Taking CSI feedback as an example of a communication function, the first result may be CSI feedback, such as hypothetical CSI feedback.

[0094] In some example embodiments, signaling diagram 300 may include feedback process 340. In feedback process 340, first device 110 may send (342) first information for updating a target encoder of a communication function to second device 120. Second device 120 may receive (344) the first information. The first information may include at least one of reference data, a first result, or a first parameter set of an updated reference encoder. In this manner, a training set for training the reference encoder and assumed CSI feedback are shared with the UE vendor.

[0095] In response to receiving (344) the first information, the second device 120 can update (346) the target encoder of the communication function. For example, the second device 120 can train, retrain or refine the target encoder. As used herein, the target encoder can also be referred to as a real encoder.

[0096] In feedback process 340, first device 110 may send (348) second information for updating a target decoder of a communication function to third device 130. Third device 130 may receive (350) the second information. The second information may include at least one of the following: reference data, a second result of an updated reference decoder of a communication function using the first result, or a second parameter set of the updated reference decoder. In an example embodiment where the first result includes hypothetical CSI feedback, the second result may include reconstructed CSI feedback.

[0097] In this way, the training set for training the reference decoder and the reconstructed CSI feedback are shared with the NW vendor. The third device 130 can update the target decoder or the real decoder of the communication function based on the second information. For example, the second device 120 such as the UE vendor can use the received information such as the training data to train their real encoder. The actual encoder will be deployed in the DUT.

[0098] In some example embodiments, the first device 110 may add the first result of the updated reference encoder and the second result of the updated reference decoder to the reference data set. In this way, the reference data set may be updated.

[0099] Reference data sets can be shared with stakeholders to help them improve over time using the feedback process 340. These stakeholders can also help improve the reference decoder or reference encoder by collaborating and sharing these data sets.

[0100] In some example embodiments, the first device 110 may send (352) at least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder to the fourth device 301. The fourth device 301 may receive (354) at least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder.

[0101] It should be understood that the feedback process 340 or feedback phase need not occur immediately after the update or training process 330. For illustrative purposes only, it is shown after the update or training process 330. The feedback process 340 may also occur in the background. The data set exchange between the first device 110 and other devices and different state holders may occur at any suitable time interval.

[0102] In some example embodiments, signaling diagram 300 may also include a testing process 360. In testing process 360, first device 110 may test (378) a target encoder of a communication function of second device 120 based on an updated reference decoder. In some example embodiments, a target encoder or an actual encoder designed based on a pre-agreed or specified principle of a reference decoder may be available at second device 120. The updated reference decoder may cater to different encoders.

[0103] The second device 120 may deploy 362 a target encoder. For example, the second device 120 may deploy 364 a target encoder in the DUT. The first device 110 may deploy 364 an updated reference decoder. The first device 110 may deploy 364 an updated reference decoder as part of the testing process 360.

[0104] For example, the first device 110 can transmit (366) input data to the second device 120. The second device 120 can receive (368) the input data. The second device 120 can generate (370) a third result of the communication function using the input data by the target encoder.

[0105] The second device 120 may send (372) the third result to the first device 110. The first device 110 may receive (374) the third result. The first device 110 may generate (376) a fourth result together with the third result by using the updated reference decoder of the communication function. The first device 110 may test (378) the target encoder, for example, to determine a test result of the target encoder based on the fourth result. The first device 110 may report (380) the test result.

[0106] Taking CSI feedback as an example of a communication function, the first device 110 may send a channel state information reference signal (CSIRS) as input data to the second device 120 for channel estimation at the DUT. The second device 120 may encode the CSI feedback using a target encoder. The first device 110 may receive the encoded CSI feedback (ie, the third result). The first device 110 may use an updated reference decoder to reconstruct the CSI feedback from the encoded CSI feedback. Based on the reconstructed CSI feedback (ie, the fourth result), the first device 110 may continue to test. Once the test is completed, the first device 110 may report the test results.

[0107] An example embodiment has been described regarding testing the target encoder of the second device 120 based on the updated reference decoder. It should be understood that in some example embodiments, the reference encoder may also be used to test the target decoder of the communication function of the third device 130. The process of testing the target decoder of the third device 130 as a DUT is similar to the test process 360 and will not be described in detail herein.

[0108] It should be understood that the example training mechanism used to illustrate the signaling diagram is a type 3 training, where NW first training is applied. However, the signaling diagram can be easily adapted to other different training methods mutually agreed with stakeholders. The scope of the present disclosure is not limited in this regard.

[0109] By using signaling diagram 300, the target encoder and / or target decoder of the communication function can be well trained or tested. Thus, the performance of the communication function can be improved. In addition, a reference decoder is designed, trained and deployed, which can cater to different encoders designed by various UE suppliers. Similarly, a reference encoder can be designed, trained and deployed, and the reference encoder can cater to different decoders designed by individual NW suppliers. In this way, UE and NW suppliers do not need to share the details of their encoder or decoder design.

[0110] Already referred to Figure 3 Several example embodiments of communication functions based on the two-sided model are described. In order to better understand the solution of the present disclosure, now use Figure 4 Describing further example embodiments, Figure 4 An example framework 400 for training and testing a two-sided model of communication functions according to some example embodiments of the present disclosure is shown.

[0111] The framework 400 may be applicable to any suitable AI / ML use case or any suitable communication function. Some example embodiments are described below using CSI feedback as an example. However, it should be understood that this is only an example without any limitation, and the concepts described with respect to CSI feedback may be applied to another AI / ML-based communication function or use case.

[0112] As shown, data repository 410 is deployed in framework 400. Data repository 410 may store reference data (or training data) from different sources, including but not limited to one or more terminal devices 412, one or more network devices 414, and one or more TEs 416.

[0113] The reference data can be both real-field data and data synthesized using a simulated environment. The content of the data set can be agreed upon between the sources listed above. In addition, the content of the data set can also be fully or partially specified by 3GPP or any other standardization body.

[0114] In some example embodiments, the training framework 420 and the testing framework 430 may be implemented at the first device 110. In the training framework 420, models may be created and / or updated, such as encoders and decoders used in the testing framework 430. For example, in block 422, a hypothetical encoder is created and / or updated. It should be noted that the hypothetical encoder is not the actual encoder used by the vendor, hence the name hypothetical encoder. This is used in the framework to mitigate the requirement of the actual encoder used at the DUT that the UE vendor may not want to share.

[0115] At block 424, the hypothesized encoder is used to generate inferences of communication functions, such as generating hypothesized CSI feedback 426 to serve as a training data set along with a synthetic target CSI that may be very close to the true encoded CSI feedback.

[0116] At block 428, a reference decoder is created or updated. For example, a reference decoder may be created or updated based on hypothetical CSI feedback 426 from a hypothetical encoder and a synthetic target CSI (which is synthetic in that the data is not directly based on real-world data but is derived from different data sets from different sources). It should be understood that the design and characteristics of the reference decoder may also be specified in whole or in part by 3GPP or any other standardization body.

[0117] In some example embodiments, the training set and hypothetical CSI feedback used to train and generate hypothetical encoders can be shared with UE vendors to improve their encoders. The training set and reconstructed CSI feedback used to train and generate reference decoders can be shared with NW and TE vendors to improve their decoders and reference decoders.

[0118] In the test framework 430, the first device 110 can use a reference decoder (e.g., a created or updated reference decoder) to test against different encoders tested in the DUT. The source of the encoder is the UE vendor. For example, once the reference decoder is trained or generated, the reference decoder will be deployed in the first device 110 for testing against the encoder in the DUT. For example, in block 432, the reference decoder is deployed.

[0119] In the test framework, at block 440, the second device 120 (e.g., UE vendor) can use the synthetic target CSI data set and the output of the hypothetical encoder to train the real encoder on its terminal. Alternatively, or additionally, the second device 120 can use the real world CSI feedback data and the synthetic CSI data to train the real encoder. The real encoder 450 can be deployed in the DUT (e.g., the second device 120) to test against the reference decoder.

[0120] In order to test the functionality using the double-sided model, the first device 110 may be deployed with a created or updated reference decoder. The second device 120 is deployed by the UE vendor together with the actual encoder. The CSI feedback encoded by the real encoder 450 may be decoded with the reference decoder, and the performance may be compared and reported. For example, the encoded CSI feedback 444 may be generated by the real encoder 450 based on the target CSI 442. The reference decoder may generate a reconstructed CSI feedback 436 based on the encoded CSI feedback 444. Thus, the performance of the real encoder 450 may be compared and reported. For example, in block 438, the first device 110 may perform a test report, such as reporting the test results.

[0121] In some example embodiments, the initially assumed encoder may not be closer to reality, but periodically when the UE vendor updates the data repository with real data the assumed encoder may be moved closer to the real encoder, thereby helping both the UE and the network vendor.

[0122] Alternatively, in some exemplary embodiments, this potential problem may be mitigated by introducing a reference target CSI data set that UE vendors may need to align to. The reference target CSI data set may be specific enough to reflect UE device specific variants, but should be generic enough to represent the common input CSI across multiple involved UE vendors and their multiple chipsets / models. Thus, there is a tradeoff.

[0123] Example embodiments have been described with respect to testing a real encoder of a UE vendor based on a reference decoder. It should be understood that in some example embodiments, the reference encoder may also be used to test a real decoder of a communication function of a network device as a DUT.

[0124] It should be understood that the example training mechanism used to illustrate the signaling diagram is a type 3 training, where NW first training is applied. However, the signaling diagram can be easily adapted to other different training methods mutually agreed with stakeholders. The scope of the present disclosure is not limited in this regard.

[0125] Utilizing the framework 400, actual encoders of UE vendors can be better trained and tested. In this way, communication functionality can be improved.

[0126] Already referred to Figure 3 to Figure 4 Several example embodiments are described. It should be understood that these example embodiments may be used in any suitable combination, or alone. It should be noted that Figure 3 to Figure 4 The communication function of CSI feedback or CSI compression is shown as an example. The above concepts can be applied to other communication functions or use cases.

[0127] Figure 5 A flowchart of an example method 500 implemented at a first device according to some example embodiments of the present disclosure is shown. For the purpose of discussion, Figure 1 The perspective description method 500 of the first device 110 in FIG.

[0128] In block 510 , the first device 110 obtains a reference data set of a communication function, the reference data set including reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device.

[0129] At block 520, the first device 110 updates a reference encoder of the communication function based on at least the reference data. At block 530, the first device 110 updates a reference decoder of the communication function based on at least the reference data. At least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0130] In some example embodiments, the method 500 further comprises creating at least one of a reference encoder or a reference decoder based at least on the reference data.

[0131] In some example embodiments, the method 500 further includes: obtaining a first result of an updated reference encoder of the communication function using the reference data; and updating a reference decoder of the communication function based on the first result and the reference data.

[0132] In some example embodiments, the method 500 further includes: sending first information for updating the target encoder of the communication function to the second device, the first information including at least one of the following: reference data, a first result, or a first parameter set of an updated reference encoder.

[0133] In some example embodiments, method 500 further includes sending second information for updating a target decoder of a communication function to a third device, the second information comprising at least one of: reference data, a second result of an updated reference decoder of a communication function utilizing the first result, or a second parameter set of an updated reference decoder.

[0134] In some example embodiments, method 500 further comprises: adding the first result and the second result to a reference data set.

[0135] In some example embodiments, the method 500 further includes: testing a target encoder of a communication function of the second device based on the updated reference decoder.

[0136] In some example embodiments, method 500 also includes: sending input data to a second device; receiving from the second device a third result generated by a target encoder of a communication function of the second device using the input data; generating a fourth result using the third result by using an updated reference decoder of the communication function; and determining a test result of the target encoder based on the fourth result.

[0137] In some example embodiments, the method 500 further comprises: sending at least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder to a fourth device.

[0138] In some example embodiments, the method 500 further comprises: receiving at least one of the first parameter set of the reference encoder or the second parameter set of the reference decoder from a fourth device.

[0139] Figure 6 FIG. 6 is a flowchart showing an example method 600 implemented at a second device according to some example embodiments of the present disclosure. Figure 1 The perspective description method 600 of the second device 120 in FIG.

[0140] At block 610, the second device 120 receives information for updating a target encoder for a communication function from the first device. The information includes at least one of the following: reference data for the communication function, a result of a reference encoder for the communication function of the first device using the reference data, or a parameter set of the reference encoder. At block 620, the second device 120 updates the target encoder based on the information.

[0141] Figure 7 FIG. 7 is a flowchart showing an example method 700 implemented at a third device according to some example embodiments of the present disclosure. Figure 1 Method 700 is described from the perspective of the third device 130.

[0142] At block 710, the third device 130 receives information for updating a target decoder of a communication function from the first device. The information includes at least one of the following: reference data of the communication function, a first result of an encoder using the communication function, a second result of a reference decoder of the communication function of the first device, or a parameter set of a reference decoder. At block 720, the third device 130 updates the target decoder based on the information.

[0143] In some example embodiments, a first device (eg, Figure 1 The first device 110 in the method 500 may include a device for performing the corresponding operation of the method 500. The device may be implemented in any suitable form. For example, the device may be implemented in a circuit or a software module. The first device may be implemented as or included in Figure 1 In the first device 110.

[0144] In some example embodiments, the first device includes: a component for obtaining a reference data set for a communication function, the reference data set including reference data associated with multiple terminal devices, multiple network devices, and at least one test device; a component for updating a reference encoder for the communication function based at least on the reference data; and a component for updating a reference decoder for the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0145] In some example embodiments, the first apparatus further comprises means for creating at least one of a reference encoder or a reference decoder based at least on the reference data.

[0146] In some example embodiments, the first device further comprises: means for obtaining a first result of an updated reference encoder of the communication function using the reference data; and means for updating the reference decoder of the communication function based on the first result and the reference data.

[0147] In some example embodiments, the first device further comprises: means for sending first information for updating a target encoder for a communication function to the second device, the first information comprising at least one of: reference data, a first result, or a first parameter set of an updated reference encoder.

[0148] In some example embodiments, the first device further comprises: a component for sending second information for updating a target decoder of a communication function to a third device, the second information comprising at least one of: reference data, a second result of an updated reference decoder of a communication function utilizing the first result, or a second parameter set of the updated reference decoder.

[0149] In some example embodiments, the first apparatus further comprises: means for adding the first result and the second result to a reference dataset.

[0150] In some example embodiments, the first device further includes means for testing a target encoder of a communication function of the second device based on the updated reference decoder.

[0151] In some example embodiments, the first device further includes: a component for transmitting input data to the second device; a component for receiving from the second device a third result generated by a target encoder of a communication function of the second device using the input data; a component for generating a fourth result by using an updated reference decoder of the communication function with the third result; and a component for determining a test result of the target encoder based on the fourth result.

[0152] In some example embodiments, the first apparatus further comprises means for sending at least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder to the fourth apparatus.

[0153] In some example embodiments, the first apparatus further comprises means for receiving at least one of the first parameter set of the reference encoder or the second parameter set of the reference decoder from a fourth apparatus.

[0154] In some example embodiments, the first apparatus further comprises means for performing the method 500 or other operations in some example embodiments of the first apparatus 110. In some example embodiments, the apparatus comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the first apparatus.

[0155] In some example embodiments, a second device (eg, Figure 1 The second device 120 in the method 600 may include a component for performing the corresponding operation of the method 600. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The second device may be implemented as or included in Figure 1 In the second device 120.

[0156] In some example embodiments, the second device includes a component for receiving information for updating a target encoder for a communication function from the first device, the information including at least one of: reference data for the communication function, a result of a reference encoder for the communication function of the first device using the reference data, or a parameter set of the reference encoder; and a component for updating the target encoder based on the information.

[0157] In some demonstrative embodiments, the second apparatus further comprises means for performing method 600 or other operations in some demonstrative embodiments of second apparatus 120. In some example embodiments, the apparatus comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause performance of the second apparatus.

[0158] In some example embodiments, a third device (eg, Figure 1 The third device 130 in the method 700 may include a component for performing the corresponding operation of the method 700. The device may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The third device may be implemented as or included in Figure 1 In the third device 130.

[0159] In some example embodiments, the third device includes a component for receiving information for updating a target decoder of a communication function from the first device, the information including at least one of: reference data of the communication function, a first result of an encoder utilizing the communication function, a second result of a reference decoder of the communication function of the first device, or a parameter set of a reference decoder; and a component for updating the target decoder based on the information.

[0160] In some demonstrative embodiments, the third apparatus further comprises means for performing method 700 or other operations in some demonstrative embodiments of third apparatus 130. In some example embodiments, the apparatus comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the performance of the third apparatus.

[0161] Figure 8 8 is a simplified block diagram of an apparatus 800 suitable for implementing an example embodiment of the present disclosure. The apparatus 800 may be configured to implement a communication device, such as Figure 1 The first device 110 or the second device 120 or the third device 130 shown in FIG. As shown in the figure, the device 800 includes one or more processors 810, one or more memories 820 coupled to the processor 810, and one or more communication modules 840 coupled to the processor 810.

[0162] The communication module 840 is used for two-way communication. The communication module 840 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface necessary for communication with other network elements. In some example embodiments, the communication module 840 may include at least one antenna.

[0163] Processor 810 may be of any type suitable for the local technology network and may include one or more of the following: a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture, as non-limiting examples. Device 800 may have multiple processors, such as application specific integrated circuit chips, which are time-slaved to a clock that synchronizes a master processor.

[0164] The memory 820 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 824, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic and / or optical memories. Examples of volatile memories include, but are not limited to, random access memory (RAM) 822 and other volatile memories that will not last for the duration of a power outage.

[0165] The computer program 830 includes computer executable instructions executed by the associated processor 810. The instructions of the program 830 may include instructions for performing the operations / actions of some exemplary embodiments of the present disclosure. The program 830 may be stored in a memory (e.g., ROM 824). The processor 810 may perform any suitable actions and processes by loading the program 830 into the RAM 822.

[0166] The exemplary embodiments of the present disclosure may be implemented by a program 830 so that the device 800 may execute the Figures 3 to 7 Any process of the present disclosure discussed. Example embodiments of the present disclosure may also be implemented by hardware or a combination of software and hardware.

[0167] In some example embodiments, the program 830 may be tangibly embodied in a computer-readable medium that may be included in the device 800 (such as in the memory 820) or in other storage devices accessible by the device 800. The device 800 may load the program 830 from the computer-readable medium to the RAM 822 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein is a limitation of the medium itself (i.e., tangible, not a signal), versus a limitation on data storage persistence (e.g., RAM vs. .ROM).

[0168] Fig. 9 An example of a computer readable medium 900 is shown, which may be in the form of a CD, DVD or other optical storage disk. The computer readable medium 900 has a program 830 stored thereon.

[0169] Generally, various embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software, which may be executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of the present disclosure are illustrated and described as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0170] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as a non-volatile computer-readable medium). The computer program product includes computer executable instructions, such as those included in a program module, that are executed in a device on a target physical or virtual processor to perform any method as described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The functionality of a program module can be combined or split between program modules as needed in different embodiments. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media.

[0171] The program code for performing the method of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that the program code, when executed by the processor or controller, causes the implementation of the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine, partially on a remote machine, or entirely on a remote machine or server.

[0172] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform the various processes and operations described above. Examples of carriers include signals, computer readable media, etc.

[0173] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of computer readable storage media will include an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0174] Further, although the operations are depicted in a particular order, this should not be construed as requiring the execution of such operations in the particular order shown or in a sequential order, or the execution of all described operations, to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to a particular embodiment. Unless explicitly stated, certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, unless explicitly stated, the different features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination.

[0175] Although the disclosure has been described in language specific to structural features and / or methodological actions, it is to be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or actions described above. Instead, the specific features and actions described above are disclosed as example forms of implementing the claims.

[0176] This disclosure provides the following examples:

[0177] Example 1. A first device comprises: at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the first device: obtains a reference data set of a communication function, wherein the reference data set comprises reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; updates a reference encoder of the communication function based at least on the reference data; and updates a reference decoder of the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0178] Example 2. The first apparatus of Example 1, wherein the first apparatus is caused to: create at least one of the reference encoder or the reference decoder based at least on the reference data.

[0179] Example 3. The first apparatus according to example 1 or 2, wherein the first apparatus is caused to: obtain a first result of the updated reference encoder of the communication function using the reference data; and update the reference decoder of the communication function based on the first result and the reference data.

[0180] Example 4. The first device according to Example 3, wherein the first device is further configured to: send first information for updating a target encoder of the communication function to a second device, the first information comprising at least one of the following: the reference data, the first result, and an updated first parameter set of the reference encoder.

[0181] Example 5. The first device according to Example 3 or 4, wherein the first device is further configured to: send second information for updating a target decoder of the communication function to a third device, wherein the second information includes at least one of the following: the reference data, a second result of the updated reference decoder of the communication function using the first result, and a second parameter set of the updated reference decoder.

[0182] Example 6. The first apparatus according to example 5, wherein the first apparatus is further caused to: add the first result and the second result to the reference data set.

[0183] Example 7. The first apparatus of any one of Examples 1 to 6, wherein the first apparatus is further caused to: test a target encoder of the communication function of the second apparatus based on the updated reference decoder.

[0184] Example 8. The first device according to Example 7, wherein the first device is further caused to: send input data to the second device; receive from the second device a third result generated by a target encoder of the communication function of the second device using the input data; generate a fourth result using the third result by using the updated reference decoder of the communication function; and determine a test result of the target encoder based on the fourth result.

[0185] Example 9. The first apparatus of any one of Examples 1 to 8, wherein the first apparatus is caused to: send at least one of an updated first parameter set of the reference encoder or an updated second parameter set of the reference decoder to a fourth apparatus.

[0186] Example 10. The first apparatus of any one of Examples 1 to 8, wherein the first apparatus is caused to: receive at least one of the first parameter set of the reference encoder or the second parameter set of the reference decoder from a fourth apparatus.

[0187] Example 11. A second device comprises: at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the second device: receives information for updating a target encoder for a communication function from a first device, wherein the information comprises at least one of the following: reference data for the communication function, a result of a reference encoder of the communication function of the first device using the reference data, and a parameter set of the reference encoder; and updates the target encoder based on the information.

[0188] Example 12. A third device comprises: at least one processor; and at least one memory, wherein the at least one memory stores instructions, and when the instructions are executed by the at least one processor, the third device: receives information for updating a target decoder of a communication function from a first device, wherein the information comprises at least one of the following: reference data of the communication function, a second result of a reference decoder of the communication function of the first device using a first result of an encoder of the communication function, and a parameter set of the reference decoder; and updates the target decoder based on the information.

[0189] Example 13. A method, comprising: obtaining a reference data set for a communication function at a first device, the reference data set comprising reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; updating a reference encoder for the communication function based at least on the reference data; and updating a reference decoder for the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

[0190] Example 14. The method of Example 13, further comprising: creating at least one of the reference encoder or the reference decoder based at least on the reference data.

[0191] Example 15. The method of example 13 or 14, further comprising: obtaining a first result of the updated reference encoder of the communication function using the reference data; and updating the reference decoder of the communication function based on the first result and the reference data.

[0192] Example 16. The method according to Example 15 further comprises: sending first information for updating a target encoder of the communication function to a second device, the first information comprising at least one of the following: the reference data, the first result, and an updated first parameter set of the reference encoder.

[0193] Example 17. The method according to Example 15 or 16 further comprises: sending second information for updating the target decoder of the communication function to a third device, the second information comprising at least one of the following: the reference data, a second result of the updated reference decoder of the communication function using the first result, and a second parameter set of the updated reference decoder.

[0194] Example 18. The method according to Example 17, further comprising: adding the first result and the second result to the reference data set.

[0195] Example 19. The method of any one of Examples 13 to 18, further comprising: testing a target encoder of the communication function of the second device based on the updated reference decoder.

[0196] Example 20. The method according to Example 19 further includes: sending input data to the second device; receiving from the second device a third result generated by a target encoder of the communication function of the second device using the input data; generating a fourth result using the third result by using the updated reference decoder of the communication function; and determining a test result of the target encoder based on the fourth result.

[0197] Example 21. The method of any one of Examples 13 to 20, further comprising: sending at least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder to a fourth device.

[0198] Example 22. The method of any one of Examples 13 to 20, further comprising: receiving at least one of the first parameter set of the reference encoder or the second parameter set of the reference decoder from a fourth device.

[0199] Example 23. A method, comprising: receiving, at a second device, information for updating a target encoder for a communication function from a first device, the information comprising at least one of the following: reference data for the communication function, a result of a reference encoder of the communication function of the first device using the reference data, a parameter set of the reference encoder; and updating the target encoder based on the information.

[0200] Example 24. A method, comprising: receiving, at a third device, information for updating a target decoder for a communication function from a first device, the information comprising at least one of the following: reference data for the communication function, a first result of an encoder utilizing the communication function, a second result of a reference decoder of the communication function of the first device, a parameter set of the reference decoder; and updating the target decoder based on the information.

[0201] Example 25. A first apparatus comprises: a component for obtaining a reference data set for a communication function, the reference data set comprising reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; a component for updating a reference encoder for the communication function based at least on the reference data; and a component for updating a reference decoder for the communication function based at least on the reference data, wherein at least one of the updated reference encoder or the updated reference decoder is used by another apparatus to optimize the communication function.

[0202] Example 26. A second device, comprising: a component for receiving information for updating a target encoder for a communication function from a first device, the information comprising at least one of the following: reference data for the communication function, a result of a reference encoder for the communication function of the first device using the reference data, a parameter set of the reference encoder; and a component for updating the target encoder based on the information.

[0203] Example 27. A third device, comprising: a component for receiving information for updating a target decoder of a communication function from a first device, the information comprising at least one of the following: reference data of the communication function, a second result of a reference decoder of the communication function of the first device using a first result of an encoder of the communication function, a parameter set of the reference decoder; and a component for updating the target decoder based on the information.

[0204] Example 28. A computer-readable medium comprising instructions stored thereon, the instructions being used to cause an apparatus to at least perform the method according to any one of Examples 13 to 22, the method according to Example 23, or the method according to Example 24.

Claims

1. A first device, comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the first device to: obtaining a reference data set for a communication function, the reference data set comprising reference data associated with a plurality of terminal devices, a plurality of network devices, and at least one test device; updating a reference encoder of the communication function based at least on the reference data; as well as updating a reference decoder of the communication function based at least on the reference data, At least one of the updated reference encoder or the updated reference decoder is used by another device to optimize the communication function.

2. The first device according to claim 1, wherein the first device: At least one of the reference encoder or the reference decoder is created based at least on the reference data.

3. The first device according to claim 1, wherein the first device: obtaining a first result of the updated reference encoder for the communication function using the reference data; and The reference decoder of the communication function is updated based on the first result and the reference data.

4. The first device according to claim 3, wherein the first device is further configured to: Sending first information for updating a target encoder of the communication function to the second device, wherein the first information includes at least one of the following: The reference data, The first result, An updated first parameter set of the reference encoder.

5. The first device according to claim 3, wherein the first device is further configured to: Sending second information for updating a target decoder of the communication function to a third device, wherein the second information includes at least one of the following: The reference data, a second result of the reference decoder updated using the communication function of the first result, An updated second parameter set for the reference decoder.

6. The first device according to claim 5, wherein the first device is further configured to: The first result and the second result are added to the reference data set.

7. The first device according to claim 1, wherein the first device is further configured to: A target encoder of the communication function of the second device is tested based on the updated reference decoder.

8. The first device according to claim 7, wherein the first device is further configured to: sending input data to the second device; receiving from the second device a third result generated by a target encoder of the communication function of the second device using the input data; generating a fourth result using the third result by using the updated reference decoder of the communication function; as well as A test result of the target encoder is determined based on the fourth result.

9. The first device according to any one of claims 1 to 8, wherein the first device: At least one of the updated first parameter set of the reference encoder or the updated second parameter set of the reference decoder is sent to a fourth device.

10. The first device according to any one of claims 1 to 8, wherein the first device: At least one of the first parameter set of the reference encoder or the second parameter set of the reference decoder is received from a fourth device.

Images