Communication method and related device

Abstract

A communication method and a related device. In the method, a first communication apparatus can deploy a first model, and, on the basis of indication by first information, perform measurement and / or provide feedback on task performance achieved by an output of the first model. Hence, the computing power of a communication node can process a model and a downstream task (and / or a downstream model) of the model, and can also perform measurement on performance and / or provide feedback on performance. In some embodiments, the first communication apparatus can, on the basis of the indication by the first information, provide feedback on the performance of M tasks corresponding to the first model, thus improving flexibility in solution implementation, and also indicating, in a scenario in which the first model is provided with a downstream task (and / or a downstream model), measurement and / or feedback on the performance of the downstream task (and / or the downstream model).

Description

A communication method and related equipment

[0001] This application claims priority to Chinese Patent Application No. 202410175499.3, filed on February 7, 2024, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a communication method and related equipment. Background Technology

[0003] Wireless communication can be a transmission communication between two or more communication nodes that does not propagate through conductors or cables. These communication nodes generally include network devices and terminal devices.

[0004] Currently, in wireless communication systems, communication nodes generally possess signal transmission and reception capabilities as well as computing capabilities. Taking network devices with computing capabilities as an example, the computing capabilities of network devices mainly provide computational support for signal transmission and reception capabilities (e.g., processing signals for transmission and reception) to enable communication between network devices and other communication nodes.

[0005] However, in communication networks, communication nodes may possess surplus computing power beyond simply providing computational support for the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical problem that needs to be solved. Summary of the Invention

[0006] This application provides a communication method and related equipment, which enables communication nodes to process models and their downstream tasks (and / or downstream models) while also enabling performance measurement and / or performance feedback of the downstream tasks (and / or downstream models).

[0007] This application provides a communication method executed by a first communication device. The first communication device can be a communication equipment (such as a terminal device or network device), or it can be a component of a communication equipment (e.g., a processor, chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, or chip system, etc.). Alternatively, the first communication device can also be a logic module or software capable of implementing all or part of the functions of the communication equipment. In this method, the first communication device receives first information indicating M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the first communication device sends second information indicating the performance of one or more of the M tasks.

[0008] Based on the above technical solution, after receiving first information indicating M tasks, the first communication device can send second information and indicate the performance of one or more of the M tasks through the second information. In other words, the first communication device can deploy a first model and, based on the indication of the first information, measure and / or provide feedback on the task performance achieved by the output of the first model. This enables the computing power of the communication node to process the model and its downstream tasks (and / or downstream models) while also achieving performance measurement and / or performance feedback.

[0009] Furthermore, among the M tasks indicated by the first information, the input of any task is determined based on the output of the first model, meaning that the output of the first model can be used to execute one or more tasks. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M tasks corresponding to the first model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the indication of performance measurement and / or feedback for downstream tasks in scenarios where the first model has downstream tasks.

[0010] In this application, the terms "model" and "other terms" may be used interchangeably, such as neural network model, neural network, artificial intelligence (AI) model, machine learning model, etc.

[0011] Optionally, the first information may be used to instruct the performance of the M tasks to perform one or more of the following operations: measurement, testing, monitoring, evaluation, measurement, feedback, or reporting.

[0012] It should be understood that the input of any of the M tasks is determined based on the output of the first model. This can be understood as the input of any task including at least the result obtained by passing the output of the first model through 0, 1, or more tasks.

[0013] Optionally, any of the M tasks can be implemented in various ways, including signal processing, model processing, processing in other applications (APP), or other methods.

[0014] As an example, the output of the first model can be multipath component (MPC) information. Any of the M tasks can be model processing for channel-state information (CSI) acquisition, resource management or user scheduling application, model processing for path loss prediction, network optimization application, model processing for beam prediction, or beam management application.

[0015] As another example, the output of the first model can be the channel frequency response (CFR), and any of the M tasks can be model processing for CSI acquisition, resource management or user scheduling application, model processing for interference prediction, interference management application, model processing for modulation and coding scheme (MCS) prediction, or adaptive modulation and coding application.

[0016] Optionally, the performance of a task may include one or more of the following: accuracy, precision, and processing speed of the task (or its output).

[0017] It should be noted that the second piece of information can indicate the performance of one or more tasks in a variety of ways.

[0018] For example, after the first communication device locally executes the one or more tasks and obtains the output of the one or more tasks, it determines the performance of the one or more tasks based on the output of the one or more tasks, and the second information sent by the first communication device may include information for indicating or characterizing the performance of the one or more tasks.

[0019] For example, after the first communication device can execute the one or more tasks locally and obtain the output of the one or more tasks, the second information sent by the first communication device may include the output of the one or more tasks; subsequently, the recipient of the second information can determine the performance of the one or more tasks based on the output of the one or more tasks.

[0020] In one possible implementation of the first aspect, the first communication device sends second information, including: when the performance of one or more of the M tasks is lower than or equal to a threshold, the first communication device sends the second information.

[0021] Based on the above technical solution, after receiving the first information indicating M tasks, the first communication device can obtain the performance corresponding to the M tasks, and if the performance of one or more of the M tasks is lower than or equal to a threshold, it sends second information to indicate the performance of the one or more tasks, so that the recipient of the second information can determine the task with degraded performance through the second information.

[0022] A second aspect of this application provides a communication method executed by a second communication device. The second communication device can be a communication device (such as a terminal device or network device), or it can be a component of a communication device (e.g., a processor, chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, or chip system, etc.). Alternatively, the second communication device can also be a logic module or software capable of implementing all or part of the functions of the communication device. In this method, the second communication device sends first information indicating M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the second communication device receives second information indicating the performance of one or more of the M tasks.

[0023] Based on the above technical solution, after sending first information indicating M tasks, the second communication device can receive second information and determine the performance of one or more of the M tasks through the second information. In other words, the first communication device can deploy a first model and, based on the indication of the first information, measure and / or provide feedback on the task performance achieved by the output of the first model. This enables the computing power of the communication node to process the model and its downstream tasks (and / or downstream models) while also achieving performance measurement and / or performance feedback.

[0024] Furthermore, among the M tasks indicated by the first information, the input of any task is determined based on the output of the first model, meaning that the output of the first model can be used to execute one or more tasks. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M tasks corresponding to the first model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the indication of performance measurement and / or feedback for downstream tasks in scenarios where the first model has downstream tasks.

[0025] It should be understood that the input of any of the M tasks is determined based on the output of the first model. This can be understood as the input of any task including at least the result obtained by passing the output of the first model through 0, 1, or more tasks.

[0026] In one possible implementation of the first or second aspect, the M tasks are contained within N tasks, where N is an integer greater than or equal to M; the N tasks correspond to P task sets, each of the P task sets includes one or more tasks from the N tasks, and different task sets in the P task sets contain different tasks; wherein, the input of any task in the (i+1)th task set in the P task sets includes the output of one or more tasks in the ith task set in the P task sets, where P is a positive integer and i is from 1 to P-1.

[0027] For example, taking P greater than 2 as an example, in P task sets, the input of one or more tasks in the first task set includes at least the output of the first model; the input of one or more tasks in the second task set includes at least the result obtained by processing the output of the first model through one or more tasks in the first task set, and so on. Similarly, the input of one or more tasks in the Pth task set includes at least the result obtained by processing the output of the first model through one or more tasks in the (P-1)th task set. In other words, P task sets can also be described as P-level task sets. For example, in a P-level task set, the input of one or more tasks in the first-level task set includes at least the output of the first model; the input of one or more tasks in the second-level task set includes at least the result obtained by processing the output of the first model through one or more tasks in the first-level task set, and so on. The input of one or more tasks in the Pth-level task set includes at least the result obtained by processing the output of the first model through one or more tasks in the (P-1)th-level task set.

[0028] Alternatively, different task sets can be understood as task sets of different levels. For example, P task sets can be described as P-level task sets, the i-th task set can be described as the i-th level task set, the (i+1)-th task set can be described as the (i+1)-th level task set, and so on.

[0029] Based on the above technical solution, in N tasks comprising M tasks, the input of any task is determined based on the output of the first model. The input of any task includes at least the result obtained by processing the output of the first model through 0, 1, or more tasks; that is, the N tasks can include a set of one or more downstream tasks of the first model. This enables the first information to provide performance measurement and / or feedback indications for the downstream tasks of the first model in scenarios where the first model has a set of one or more downstream tasks.

[0030] Optionally, the input of any task in the (i+1)th task set of the P task sets includes the output of one or more tasks in the ith task set of the P task sets; this can be understood as the input of any task in the jth task set of the P task sets including the result obtained after the output of the first model has undergone j-1 processing steps, where each j-1 processing step includes the processing of one or more tasks in each of the j-1 task sets preceding the jth task set, and the value of j ranges from 1 to P.

[0031] In one possible implementation of the first or second aspect, the first information includes M identifiers, each of which is used to indicate one or more tasks; any one of the M identifiers includes K indices, wherein the k-th index of the K indices is used to indicate one or more tasks in the k-th task set among the first K task sets in the P task sets, where k is a positive integer less than or equal to P.

[0032] It should be understood that the M identifiers are used to indicate the M tasks respectively. This can be understood as a one-to-one correspondence between the M identifiers and the M tasks, and / or, the m-th identifier among the M identifiers is used to indicate the m-th task among the M tasks, where m takes the value from 1 to M.

[0033] Based on the above technical solution, the first information received by the first communication device may include M identifiers, each used to indicate one of the M tasks. In the P task sets, the task indicated by any identifier can be represented as a task in the Kth task set (K is an integer less than or equal to P) of the P task sets. Furthermore, any of the M identifiers may include K indices, which can be used to indicate one or more tasks contained in each of the K task sets.

[0034] Alternatively, different task sets can be understood as task sets at different levels. For example, K task sets can be described as K-level task sets, and the k-th task set can be described as the k-th level task set.

[0035] Optionally, in the K task sets, the indices between different task sets (i.e., the K indices) can be consecutive (e.g., consecutively increasing or consecutively decreasing).

[0036] In one possible implementation of the first or second aspect, the identifier may also include the identifier of the first model.

[0037] Based on the above technical solution, the first communication device can deploy one or more first models, and correspondingly, each first model may have downstream tasks. Therefore, among the M identifiers used to indicate the M tasks, any identifier may also include an identifier of the first model. In this way, the first information can instruct the downstream tasks corresponding to one or more first models.

[0038] In one possible implementation of the first or second aspect, the first information includes T indices, the T indices indicating the tasks of the M tasks, the T indices respectively indicating T task sets in P task sets, where T is a positive integer less than or equal to P; the t-th index of the T indices is used to indicate 0 or more tasks contained in the t-th task set in the T task sets, where t is a positive integer less than T.

[0039] Based on the above technical solution, the N downstream tasks of the first model can be contained in P task sets, and correspondingly, the M tasks among the N tasks can be contained in T task sets among the P task sets. The first information used to indicate the M tasks can include T indices, which are used to indicate zero or one or more tasks in each of the T task sets. In this way, the first information can indicate the M tasks through the tasks contained in each of the T task sets.

[0040] Alternatively, different task sets can be understood as task sets at different levels. For example, a set of T tasks can be described as a set of tasks at level T, and the t-th task set can be described as a set of tasks at level t.

[0041] Optionally, T is less than or equal to P, meaning that the T task sets are part or all of the P task sets. Correspondingly, within the T task sets, the indices between different task sets (i.e., the T indices) can be consecutive (e.g., consecutively increasing or consecutively decreasing) or non-consecutive, which is not limited here.

[0042] In one possible implementation of the first or second aspect, the first information also includes the identifier of the first model.

[0043] Based on the above technical solution, in addition to including T indices, the first information may also include the identifier of the first model. The first communication device can deploy one or more first models, and each first model may have downstream tasks. Therefore, the first information used to indicate M tasks may also include the identifier of the first model. In this way, the first information can indicate the downstream tasks corresponding to one or more first models.

[0044] In one possible implementation of the first or second aspect, the T indices satisfy at least one of the following: in the t-th index of the T indices, the value of the first bit is used to indicate whether the first information includes the (t+x)-th index, where x is 1 to Tt; or, in the t-th index of the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the tasks (or all tasks) contained in the t-th task set.

[0045] For example, the value of the t-th index is a preset value, which can be understood as the values ​​of the bits other than the first bit in the multiple bits contained in the t-th index being preset values ​​(e.g., all 0s or all 1s); or, the values ​​of the multiple bits in the multiple bits contained in the t-th index being preset values.

[0046] Based on the above technical solution, in the case where the value of the first bit in the t-th index of the T indices is used to indicate whether the first information includes the (t+x)-th index, the first communication device can determine whether the (t+x)-th index needs to be parsed based on the value of the first bit in the t-th index, thereby reducing the implementation complexity and avoiding unnecessary overhead.

[0047] Furthermore, in the t-th index among the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the tasks contained in the t-th task set. In this way, it is possible to indicate one or more tasks corresponding to an identifier through a specific value of the identifier, thereby reducing overhead.

[0048] In one possible implementation of the first or second aspect, the first information includes M identifiers, each of which is used to indicate one of the M tasks; and the length of each of the M identifiers is the same.

[0049] Based on the above technical solution, the first information can indicate M tasks respectively through M identifiers of equal length. That is, different tasks can be indicated by sequences of equal length. In this way, the implementation complexity can be reduced.

[0050] In one possible implementation of the first or second aspect, the second information is also used to indicate one or more of the M tasks.

[0051] It should be understood that the way the second information indicates one or more of the M tasks can be similar to the way the first information indicates one or more of the M tasks. For example, the second information may include M identifiers, T indexes, etc.

[0052] Based on the above technical solution, the second information can be used to indicate the performance of one or more tasks among the M tasks. Correspondingly, the second information can also be used to indicate the performance of those one or more tasks. In this way, the recipient of the second information can determine one or more tasks among the M tasks based on the second information, and clearly define the performance indicated by the second information as the performance of one or more tasks among the M tasks.

[0053] A third aspect of this application provides a communication method executed by a first communication device. The first communication device can be a communication equipment (such as a terminal device or network device), or it can be a component of a communication equipment (e.g., a processor, chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, or chip system, etc.). Alternatively, the first communication device can also be a logic module or software capable of implementing all or part of the functions of the communication equipment. In this method, the first communication device receives third information indicating M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the first communication device sends fourth information indicating the performance of one or more of the M models.

[0054] Based on the above technical solution, after receiving first information indicating M models, the first communication device can send fourth information, and use the fourth information to indicate the performance of one or more of the M models. In other words, the first communication device can deploy a second model and M models derived from the second model, and measure and / or provide feedback on the performance of the M models based on the indication of the first information. Thus, the computing power of the communication node can process the model and its downstream tasks (and / or downstream models), while also achieving performance measurement and / or performance feedback.

[0055] Furthermore, among the M models indicated by the first information, each model is determined based on the second model; that is, the second model can be processed once or multiple times to generate any of the M models. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M models corresponding to the second model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the measurement and / or feedback of the performance of downstream models in scenarios where the second model has downstream models.

[0056] It should be understood that any one of the M models is determined based on the second model. This can be understood as any one of the M models being obtained by processing the second model one or more times. Any of these one or more processing steps can be model fine-tuning, model distillation, model pruning, model compression, model fusion, or other model processing.

[0057] Optionally, the performance of the model may include one or more of the model's (or the model's output) accuracy, precision, and processing speed.

[0058] It should be noted that the fourth information can indicate the performance of one or more models in a variety of ways.

[0059] For example, after the first communication device executes the one or more models locally and obtains the output of the one or more models, it determines the performance of the one or more models based on the output of the one or more models, and the fourth information sent by the first communication device may include information for indicating or characterizing the performance of the one or more models.

[0060] For example, after the first communication device can execute the one or more models locally and obtain the output of the one or more models, the fourth information sent by the first communication device may include the output of the one or more models; subsequently, the recipient of the second information can determine the performance of the one or more models based on the output of the one or more models.

[0061] In one possible implementation of the third aspect, the first communication device sends fourth information, including: when the performance of one or more of the M models is lower than or equal to a threshold, the first communication device sends the fourth information.

[0062] Based on the above technical solution, after receiving the third information indicating M models, the first communication device can obtain the performance corresponding to the M models, and if the performance of one or more of the M models is lower than or equal to a threshold, it sends fourth information to indicate the performance of the one or more models, so that the recipient of the fourth information can determine the model with degraded performance through the fourth information.

[0063] A fourth aspect of this application provides a communication method executed by a second communication device. The second communication device can be a communication device (such as a terminal device or network device), or it can be a component of a communication device (e.g., a processor, chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, or chip system, etc.). Alternatively, the second communication device can also be a logic module or software capable of implementing all or part of the functions of the communication device. In this method, the second communication device sends third information indicating M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the second communication device receives fourth information indicating the performance of one or more of the M models.

[0064] Based on the above technical solution, after sending first information indicating M models, the second communication device can receive fourth information and determine the performance of one or more of the M models through the fourth information. In other words, the first communication device can deploy the second model and the M models derived from it, and measure and / or provide feedback on the performance of the M models based on the indication of the first information. Thus, the computing power of the communication node is able to process the model and its downstream tasks (and / or downstream models), while also achieving performance measurement and / or performance feedback.

[0065] Furthermore, among the M models indicated by the first information, each model is determined based on the second model; that is, the second model can be processed once or multiple times to generate any of the M models. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M models corresponding to the second model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the measurement and / or feedback of the performance of downstream models in scenarios where the second model has downstream models.

[0066] In one possible implementation of the third or fourth aspect, the M models are contained in N models, where N is an integer greater than or equal to M; the N models correspond to P model sets, each of the P model sets includes one or more models from the N models, and different model sets in the P model sets contain different models; wherein any model in the (i+1)th model set in the P model sets is determined based on one or more models in the ith model set in the P model sets, where P is a positive integer and i is from 1 to P-1.

[0067] For example, taking P greater than 2 as an example, in P model sets, any model in one or more models contained in the first model set is obtained by processing the second model; any model in one or more models contained in the second model set is obtained by processing the first model set; and so on. Similarly, any model in one or more models contained in the Pth model set is obtained by processing the (P-1)th model set. In other words, P model sets can also be described as P-level model sets. For example, in a P-level model set, any model in one or more models contained in the first-level model set is obtained by processing the second model once; any model in one or more models contained in the second-level model set is obtained by processing the first model set; and so on. Similarly, any model in one or more models contained in the Pth-level model set is obtained by processing the (P-1)th-level model set.

[0068] Alternatively, different model sets can be understood as model sets of different levels. For example, P model sets can be described as a P-level model set, the i-th model set can be described as an i-level model set, the (i+1)-th model set can be described as an (i+1)-level model set, and so on.

[0069] Based on the above technical solution, in N models containing M models, any model is determined based on the second model. This "any model" can be obtained by processing the second model zero, one, or more times; that is, the N models can include a set of one or more downstream models of the second model. This enables the first information to provide performance measurement and / or feedback indications for the downstream models of the second model in scenarios where the second model has a set of one or more downstream models.

[0070] Optionally, any model in the (i+1)th model set of the P model sets is determined based on one or more models in the ith model set of the P model sets; this can be understood as any model in the pth model set of the P model sets being obtained based on the second model after p-1 processing steps, where p-1 processing steps include model processing corresponding to one or more models in each of the p-1 model sets preceding the pth model set, and p takes values ​​from 1 to P.

[0071] In one possible implementation of the third or fourth aspect, the third information includes M identifiers, each of which is used to indicate one of the M models; any one of the M identifiers includes K indices; wherein the k-th index of the K indices is used to indicate the model processing corresponding to one or more models in the k-th model set among the first K model sets in the P model sets, where k takes the value from 1 to K, and K is a positive integer less than or equal to P.

[0072] It should be understood that the M identifiers are used to indicate the M models respectively. This can be understood as a one-to-one correspondence between the M identifiers and the M models, and / or, the m-th identifier among the M identifiers is used to indicate the m-th model among the M models, where m takes the value from 1 to M.

[0073] Based on the above technical solution, the first information received by the first communication device may include M identifiers, each used to indicate one of the M models. Specifically, in the P model sets, the model indicated by any identifier can be represented as the model in the Kth model set (K is an integer less than or equal to P) of the P model sets. Furthermore, any of the M identifiers may include K indices, which can be used to indicate the model processing corresponding to that model.

[0074] Alternatively, different model sets can be understood as model sets of different levels. For example, K model sets can be described as K-level model sets, and the k-th model set can be described as the k-th level model set.

[0075] Optionally, in the K model sets, the indices between different model sets (i.e., the K indices) can be consecutive (e.g., consecutively increasing or consecutively decreasing).

[0076] In one possible implementation of the third or fourth aspect, the identifier may also include an identifier for the processing of the second model.

[0077] Based on the above technical solution, the first communication device can deploy one or more second models, and correspondingly, each second model may have a downstream model. Therefore, among the M identifiers used to indicate the M models, any identifier may also include an identifier of the second model. In this way, the first information can indicate the downstream model corresponding to one or more second models.

[0078] In one possible implementation of the third or fourth aspect, the third information includes T indices, the T indices indicating the models of the M models, the T indices respectively indicating the T model sets in the P model sets, where T is a positive integer less than or equal to P; the t-th index of the T indices is used to indicate 0 or more models contained in the t-th model set in the T model sets, where t is a positive integer less than T.

[0079] Based on the above technical solution, the N downstream models of the second model can be contained in P model sets, and correspondingly, the M models among the N models can be contained in T model sets among the P model sets. The first information used to indicate the M models can include T indices, which are used to indicate zero or one or more models in each of the T model sets. In this way, the first information can indicate the M models through the models contained in each of the T model sets.

[0080] Alternatively, different model sets can be understood as model sets of different levels. For example, T model sets can be described as T-level model sets, and the t-th model set can be described as the t-th level model set.

[0081] Optionally, T is less than or equal to P, meaning that the T model sets are part or all of the P model sets. Correspondingly, within the T model sets, the indices between different model sets (i.e., the T indices) can be consecutive (e.g., continuously increasing or continuously decreasing) or non-consecutive, which is not limited here.

[0082] In one possible implementation of the third or fourth aspect, the third information also includes an identifier of the processing of the second model.

[0083] Based on the above technical solution, in addition to including T indices, the third information may also include the identifier of the second model. The first communication device can deploy one or more second models, and each second model may have downstream models. Therefore, the third information used to indicate M models may also include the identifier of the second model. In this way, the first information can indicate the downstream models corresponding to one or more second models.

[0084] In one possible implementation of the third or fourth aspect, the T indices satisfy at least one of the following: in the t-th index of the T indices, the value of the first bit is used to indicate whether the third information includes the (t+x)-th index, where x is 1 to Tt; or, in the t-th index of the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the models (or all models) contained in the t-th model set.

[0085] For example, the value of the t-th index is a preset value, which can be understood as the values ​​of the bits other than the first bit in the multiple bits contained in the t-th index being preset values ​​(e.g., all 0s or all 1s); or, the values ​​of the multiple bits in the multiple bits contained in the t-th index being preset values.

[0086] Based on the above technical solution, in the case where the value of the first bit in the t-th index of the T indices is used to indicate whether the first information includes the (t+x)-th index, the first communication device can determine whether the (t+x)-th index needs to be parsed based on the value of the first bit in the t-th index, thereby reducing the implementation complexity and avoiding unnecessary overhead.

[0087] Furthermore, in the t-th index among the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the models contained in the t-th model set. In this way, one or more models corresponding to an identifier can be indicated by a specific value of the identifier, thereby reducing overhead.

[0088] In one possible implementation of the third or fourth aspect, the third information includes M identifiers, each of which is used to indicate one of the M models; among the M identifiers, the lengths of the different identifiers are the same.

[0089] Based on the above technical solution, the third information can indicate M models respectively through M identifiers of equal length. That is, different models can be indicated by sequences of equal length. In this way, the implementation complexity can be reduced.

[0090] In one possible implementation of the third or fourth aspect, the fourth information is also used to indicate the identification of one or more of the M models.

[0091] Based on the above technical solution, the fourth information can be used to indicate the performance of one or more models among the M models. Correspondingly, the fourth information can also be used to indicate the performance of those one or more models. In this way, the recipient of the fourth information can determine one or more models among the M models based on the fourth information, and clearly define the performance indicated by the fourth information as the performance of one or more models among the M models.

[0092] It should be understood that the way the fourth information indicates one or more models among the M models can be similar to the way the third information indicates one or more models among the M models. For example, the fourth information may include M identifiers, T indices, etc.

[0093] A fifth aspect of this application provides a communication device, which is a first communication device, comprising a transceiver unit and a processing unit; the transceiver unit is configured to receive first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the processing unit is configured to determine second information; the transceiver unit is further configured to transmit the second information, which indicates the performance of one or more of the M tasks.

[0094] In the fifth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the first aspect and achieve the corresponding technical effects. For details, please refer to the first aspect, which will not be repeated here.

[0095] A sixth aspect of this application provides a communication device, which is a second communication device, comprising a transceiver unit and a processing unit; the processing unit is configured to determine first information; the transceiver unit is configured to transmit the first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the transceiver unit is further configured to receive second information, which indicates the performance of one or more of the M tasks.

[0096] In the sixth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the second aspect and achieve the corresponding technical effects. For details, please refer to the second aspect, which will not be repeated here.

[0097] A seventh aspect of this application provides a communication device, which is a first communication device, comprising a transceiver unit and a processing unit; the transceiver unit is configured to receive third information, which indicates M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the processing unit is configured to determine fourth information; the transceiver unit is further configured to transmit the fourth information, which indicates the performance of one or more of the M models.

[0098] In the seventh aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the third aspect and achieve the corresponding technical effects. For details, please refer to the third aspect, which will not be repeated here.

[0099] The eighth aspect of this application provides a communication device, which is a second communication device, comprising a transceiver unit and a processing unit; the processing unit is used to determine third information, and the transceiver unit is used to transmit the third information, which is used to indicate M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the transceiver unit is also used to receive fourth information, which is used to indicate the performance of one or more of the M models.

[0100] In the eighth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the fourth aspect and achieve the corresponding technical effects. For details, please refer to the fourth aspect, which will not be repeated here.

[0101] The ninth aspect of this application provides a communication device including at least one processor coupled to a memory; the memory is used to store a program or instructions; the at least one processor is used to execute the program or instructions to enable the device to implement the method described in any possible implementation of any of the first to fourth aspects.

[0102] The tenth aspect of this application provides a communication device including at least one logic circuit and an input / output interface; the logic circuit is used to perform the method described in any of the possible implementations of the first to fourth aspects described above.

[0103] The eleventh aspect of this application provides a communication system, which includes the first communication device and the second communication device described above.

[0104] The twelfth aspect of this application provides a computer-readable storage medium for storing one or more computer-executable instructions, which, when executed by a processor, perform the method as described in any possible implementation of any of the first to fourth aspects described above.

[0105] The thirteenth aspect of this application provides a computer program product (or computer program) that, when executed by a processor, performs the method described in any possible implementation of any of the first to fourth aspects described above.

[0106] The fourteenth aspect of this application provides a chip or chip system including at least one processor for supporting a communication device in implementing the method described in any possible implementation of any of the first to fourth aspects.

[0107] In one possible design, the chip or chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0108] The technical effects of any of the design methods in aspects five through fourteen can be found in the technical effects of the different design methods in aspects one through four above, and will not be repeated here. Attached Figure Description

[0109] Figures 1a to 1c are schematic diagrams of the communication system provided in this application;

[0110] Figures 2a to 2e are schematic diagrams of the AI ​​processing involved in this application;

[0111] Figure 3 is an interactive schematic diagram of the communication method provided in this application;

[0112] Figures 4a and 4b are schematic diagrams illustrating the relationship between the model and the task provided in this application;

[0113] Figure 5 is an interactive schematic diagram of the communication method provided in this application;

[0114] Figures 6a and 6b are schematic diagrams illustrating the relationship between the different models provided in this application;

[0115] Figures 7 to 11 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0116] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0117] (1) Terminal device: can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0118] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0119] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices or smart wearable devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0120] Terminals can also be drones, robots, devices for device-to-device (D2D) communication, vehicles for everything (V2X), virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes, etc.

[0121] Furthermore, terminal devices can also be terminal devices in future communication systems beyond the fifth generation (5G) (such as sixth generation (6G) communication systems) or in future public land mobile networks (PLMNs). For example, 6G networks can further expand the form and function of 5G communication terminals; 6G terminals include, but are not limited to, vehicles, cellular network terminals (integrating satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0122] In this embodiment, the terminal device can also obtain AI services provided by the network device. Optionally, the terminal device can also have AI processing capabilities.

[0123] (2) Network equipment: This can be equipment in a wireless network. For example, network equipment can be a RAN node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in 5G communication systems, transmit / receive point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in a network structure, network equipment can include centralized unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including CU nodes and DU nodes.

[0124] Optionally, RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor nodes, or radio controllers in cloud radio access network (CRAN) scenarios. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0125] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions. For example, RAN nodes can be centralized units (CU), distributed units (DU), CU-control plane (CP), CU-user plane (UP), or radio units (RU), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0126] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open access network (open RAN, O-RAN, or ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0127] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0128] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0129] Table 1

[0130] Network devices can be other devices that provide wireless communication functions for terminal devices. The embodiments of this application do not limit the specific technology or form of the network device. For ease of description, the embodiments of this application are not limited.

[0131] Network equipment may also include core network equipment, such as the Mobility Management Entity (MME), Home Subscriber Server (HSS), Serving Gateway (S-GW), Policy and Charging Rules Function (PCRF), and Public Data Network Gateway (PDN Gateway, P-GW) in 4th generation (4G) networks; and access and mobility management function (AMF), user plane function (UPF), or session management function (SMF) in 5G networks. Furthermore, this core network equipment may also include other core network equipment in 5G networks and next-generation networks of 5G networks.

[0132] In this embodiment of the application, the network device may also have network nodes with AI capabilities, which can provide AI services to terminals or other network devices. For example, it may be an AI node, computing node, RAN node with AI capabilities, or core network element with AI capabilities on the network side (access network or core network).

[0133] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing that function, such as a chip system, which can be installed in the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0134] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device / server sending configuration information or parameter values ​​to the terminal via messages or signaling, so that the terminal can determine communication parameters or resources for transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, parameter information or parameter values ​​specified by standard protocols for use by the base station / network device or terminal device, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0135] Furthermore, these values ​​and parameters can be changed or updated.

[0136] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0137] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0138] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0139] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0140] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0141] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and the various methods / designs / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various methods / designs / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various methods / designs / implementations within each embodiment can be combined to form new embodiments, methods, or implementations based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0142] This application can be applied to long-term evolution (LTE) systems, new radio (NR) systems, or future communication systems beyond 5G (such as 6G). These communication systems include at least one network device and / or at least one terminal device.

[0143] Please refer to Figure 1a, which is a schematic diagram of a communication system according to this application. Figure 1a exemplarily shows one network device and six terminal devices, namely terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in Figure 1a, terminal device 1 is a smart teacup, terminal device 2 is a smart air conditioner, terminal device 3 is a smart gas pump, terminal device 4 is a vehicle, terminal device 5 is a mobile phone, and terminal device 6 is a printer.

[0144] As shown in Figure 1a, the entity sending AI configuration information can be a network device. The entity receiving AI configuration information can be terminal devices 1-6. In this case, the network device and terminal devices 1-6 form a communication system. In this communication system, terminal devices 1-6 can send data to the network device, and the network device needs to receive the data sent by terminal devices 1-6. At the same time, the network device can send configuration information to terminal devices 1-6.

[0145] For example, in Figure 1a, terminal devices 4 to 6 can also form a communication system. Terminal device 5 acts as a network device, i.e., the entity sending AI configuration information; terminal devices 4 and 6 act as terminal devices, i.e., the entities receiving AI configuration information. For instance, in a vehicle-to-everything (V2X) system, terminal device 5 sends AI configuration information to terminal devices 4 and 6 respectively, and receives data sent by terminal devices 4 and 6; correspondingly, terminal devices 4 and 6 receive the AI ​​configuration information sent by terminal device 5 and send data back to terminal device 5.

[0146] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including network devices and network devices, network devices and terminal devices, and / or terminal devices and terminal devices) may also perform AI-related services.

[0147] As shown in Figure 1b, taking a network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0148] As shown in Figure 1c, taking terminal devices including televisions and mobile phones as an example, communication-related services and AI-related services can also be performed between televisions and mobile phones.

[0149] The technical solutions provided in this application can be applied to wireless communication systems (such as the systems shown in Figures 1a, 1b, or 1c). For example, AI network elements can be introduced into the communication system provided in this application to realize some or all AI-related operations. AI network elements can also be called AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network element can be built into a network element within the communication system. For example, the AI ​​network element can be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration, and maintenance (OAM) management system, to implement AI-related functions. The OAM can be the management system for core network equipment and / or the management system for access network equipment. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to implement AI-related functions.

[0150] The following is a brief introduction to the artificial intelligence (AI) that may be involved in this application.

[0151] Artificial intelligence (AI) enables machines to possess human-like intelligence, such as allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve AI, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. These models represent the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0152] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0153] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and then expresses this learned mapping relationship using an AI model. The process of training the machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values, and the model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). After the mapping relationship is learned, it can be used to predict new sample labels. The mapping relationship learned in supervised learning can include linear or non-linear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0154] Unsupervised learning relies on collected sample values ​​to discover inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationship from sample to sample; this is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0155] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and a better (e.g., optimal) decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0156] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0157] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0158] Figure 2a shows a schematic diagram of a neuron structure. Assume the input to the neuron is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w0, w1, ..., w] n ], where n is a positive integer, w i and x i It can be any possible type, such as real numbers, integers (e.g., 0, positive integers, or negative integers), or complex numbers. i As x i The weights are used to assign weights to x. iWeighting is applied. The bias for the weighted sum of the input values ​​is, for example, b. Activation functions can take many forms. Suppose the activation function of a neuron is: y = f(z) = max(0, z), then the output of that neuron is: For example, if the activation function of a neuron is y = f(z) = z, then the output of that neuron is: Here, b can be any possible type, such as a real number, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network can be the same or different.

[0159] Furthermore, neural networks generally consist of multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it includes, and the number of neurons in each layer can be called the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the received input information through neurons and passes the processing result to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, hidden layers, and an output layer. The input layer processes the received input information through neurons and passes the processing result to the hidden layer. The hidden layer calculates the received processing result and passes the calculation result to the output layer or the next adjacent hidden layer, ultimately obtaining the output of the neural network. A neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0160] Neural networks, for example, are deep neural networks (DNNs). Depending on how the network is constructed, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

[0161] Figure 2b is a schematic diagram of an FNN network. A characteristic of FNN networks is that neurons in adjacent layers are completely connected pairwise. This characteristic makes FNNs typically require a large amount of storage space, leading to high computational complexity.

[0162] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0163] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0164] In the model training process described above for machine learning, a loss function can be defined. The loss function describes the difference or discrepancy between the model's output value and the ideal target value. The loss function can be expressed in various forms, and there are no restrictions on its specific form. The model training process can be viewed as follows: by adjusting some or all of the model's parameters, the value of the loss function is made to be less than a threshold value or to meet the target requirement.

[0165] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0166] The implementation process of a fully connected neural network will be described below with reference to the accompanying drawings. A fully connected neural network is also called a multilayer perceptron (MLP).

[0167] As shown in Figure 2c, an MLP consists of an input layer (left side), an output layer (right side), and multiple hidden layers (middle). Each layer of an MLP contains several nodes, called neurons. Neurons in adjacent layers are connected pairwise.

[0168] Optionally, considering neurons in two adjacent layers, the output h of the next layer's neurons is the weighted sum of all neurons x in the previous layer connected to it and passed through an activation function, which can be expressed as: h = f(wx + b).

[0169] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0170] Alternatively, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…)+b n ).

[0171] Where n is the index of the neural network layer, 1 <= n <= N, and N is the total number of layers in the neural network.

[0172] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of obtaining this mapping from random values ​​w and b using existing data is called training the neural network.

[0173] Optionally, the training process can be carried out by using a loss function to evaluate the output of the neural network.

[0174] As shown in Figure 2d, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the loss function reaches its minimum, which is the "better point (e.g., the optimal point)" in Figure 2d. It can be understood that the neural network parameters corresponding to the "better point (e.g., the optimal point)" in Figure 2d can be used as the neural network parameters in the trained AI model information.

[0175] Alternatively, the gradient descent process can be represented as:

[0176] Where θ represents the parameters to be optimized (including w and b), L is the loss function, and η is the learning rate, controlling the step size of gradient descent. This represents the differentiation operation. This indicates taking the derivative of θ with respect to L.

[0177] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0178] As shown in Figure 2e, the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer, and can be expressed as:

[0179] Among them, w ij Let s be the weight of the connection between node j and node i.i The weighted sum of the inputs at node i.

[0180] The technical solution provided in this application can be applied to wireless communication systems (such as the systems shown in Figure 1a, 1b, or 1c). In wireless communication systems, communication nodes generally possess signal transmission and reception capabilities as well as computing capabilities. Taking a network device with computing capabilities as an example, the computing capabilities of the network device mainly provide computational support for the signal transmission and reception capabilities (e.g., processing the transmission and reception of signals) to realize the communication tasks between the network device and other communication nodes.

[0181] However, in communication networks, communication nodes may possess surplus computing power beyond simply providing computational support for the aforementioned communication tasks. Therefore, how to utilize this computing power is a pressing technical problem that needs to be solved.

[0182] To address the aforementioned problems, this application provides a communication method and related equipment, which will be described in detail below with reference to the accompanying drawings.

[0183] Please refer to Figure 3, which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0184] It should be noted that in the following text, Figures 3 and 5 illustrate the method using the first and second communication devices as examples of the execution subjects in this interactive illustration, but this application does not limit the execution subjects of this interactive illustration. For example, the first communication device can be a communication device (e.g., a terminal device or a network device), or a chip, baseband chip, modem chip, system-on-chip (SoC) chip containing a modem core, system-in-package (SIP) chip, communication module, chip system, processor, logic module, or software, etc., within the communication device. Similarly, the second communication device can be a communication device (e.g., a terminal device or a network device), or a chip, chip system, processor, logic module, or software, etc., within the communication device.

[0185] S301. The second communication device sends first information, and correspondingly, the first communication device receives the first information. The first information indicates M tasks, where M is a positive integer. Furthermore, the input to any of the M tasks is determined based on the output of the first model.

[0186] S302. The first communication device sends second information, and correspondingly, the second communication device receives the second information. The second information is used to indicate the performance of one or more of the M tasks.

[0187] In this application, the terms "model" and "other terms" may be used interchangeably, such as neural network model, neural network, artificial intelligence (AI) model, machine learning model, etc.

[0188] Optionally, the first information received by the first communication device in step S301 can be used to instruct one or more of the following operations to be performed on the performance of the M tasks: measurement, testing, monitoring, evaluation, measurement, feedback, or reporting.

[0189] It should be understood that the input of any of the M tasks is determined based on the output of the first model. This can be understood as the input of any task including at least the result obtained by processing the output of the first model through zero, one, or more tasks. Since the input of any of the M tasks can be obtained based on the output of the first model, these M tasks can be referred to as downstream tasks of the first model.

[0190] Optionally, the output of the first model can be used to determine the input of one or more downstream tasks.

[0191] To facilitate understanding, the following example, with M set to 8, will be used to illustrate the relationship between the first model and the M tasks.

[0192] In the example shown in Figure 4a, the input of any one of the tasks 1, 2, 3 and 4 can include the output of the first model, that is, the input of any one of these four tasks can include the result obtained by passing the output of the first model through 0 tasks.

[0193] In the example shown in Figure 4a, the input to Task 5 may include the output of Task 1, that is, the input to Task 5 may include the result obtained by passing the output of the first model through a task in a task set (i.e., Task 1).

[0194] In the example shown in Figure 4a, the input to task 6 or task 7 may include the output of task 2. That is, the input to task 6 or task 7 may include the result obtained by passing the output of the first model through a task in a task set (i.e., task 2).

[0195] In the example shown in Figure 4a, the input to task 8 may include the output of task 5. That is, the input to task 8 may include the result obtained by passing the output of the first model through the tasks in the two task sets (i.e., task 1 and task 5).

[0196] It should be noted that M can be a positive integer. When M takes other values, the relationship between the M tasks and the first model can be seen in the example shown in Figure 4a. That is, in the M tasks, the input of any task includes at least the output of the first model obtained by passing it through 0, 1 or more tasks.

[0197] For example, the first model can be a wireless pre-trained model, a pre-trained model, or a wireless large model, etc.

[0198] Optionally, the input to the first model can be implemented in a variety of ways, such as environmental parameters collected by the first communication device, communication signals received by the first communication device from other communication devices (e.g., the second communication device), and one or more of the information pre-configured locally by the first communication device.

[0199] Optionally, any of the M tasks can be implemented in various ways, including signal processing, model processing, processing in other applications (APP), or other methods.

[0200] As an example, the output of the first model can be multipath component (MPC) information. Any of the M tasks can be model processing for channel state information (CSI) acquisition, resource management or user scheduling application, model processing for path loss prediction, network optimization application, model processing for beam prediction, or beam management application.

[0201] As another example, the output of the first model can be the channel frequency response (CFR), and any of the M tasks can be model processing for CSI acquisition, resource management or user scheduling application, model processing for interference prediction, interference management application, model processing for modulation and coding scheme (MCS) prediction, or adaptive modulation and coding application.

[0202] Optionally, the performance of a task may include one or more of the following: accuracy, precision, and processing speed of the task (or its output).

[0203] It should be noted that the second piece of information can indicate the performance of one or more tasks in a variety of ways.

[0204] For example, after the first communication device locally executes the one or more tasks and obtains the output of the one or more tasks, it determines the performance of the one or more tasks based on the output of the one or more tasks, and the second information sent by the first communication device may include information for indicating or characterizing the performance of the one or more tasks.

[0205] For example, after the first communication device can execute the one or more tasks locally and obtain the output of the one or more tasks, the second information sent by the first communication device may include the output of the one or more tasks; subsequently, the recipient of the second information can determine the performance of the one or more tasks based on the output of the one or more tasks.

[0206] In one possible implementation, the M tasks indicated by the first information sent by the second communication device in step S301 are contained in N tasks, where N is an integer greater than or equal to M; the N tasks correspond to P task sets, each of the P task sets includes one or more tasks from the N tasks, and different task sets in the P task sets contain different tasks; wherein, the input of any task in the (i+1)th task set in the P task sets includes the output of one or more tasks in the ith task set in the P task sets, where P is a positive integer and i is from 1 to P-1.

[0207] Specifically, in the N tasks comprising M tasks, the input of any task is determined based on the output of the first model. The input of any task includes at least the result obtained by processing the output of the first model through zero, one, or more tasks; that is, the N tasks can include a set of one or more downstream tasks of the first model. This enables the first information to provide performance measurement and / or feedback indications for the downstream tasks of the first model in scenarios where the first model has a set of one or more downstream tasks.

[0208] For example, taking P greater than 2 as an example, in P task sets, the input of one or more tasks in the first task set includes at least the output of the first model; the input of one or more tasks in the second task set includes at least the result obtained by processing the output of the first model through one or more tasks in the first task set... and so on, the input of one or more tasks in the Pth task set includes at least the result obtained by processing the output of the first model through one or more tasks in the (P-1)th task set. In other words, P task sets can also be described as P-level task sets. For example, in a P-level task set, the input of one or more tasks in the first-level task set includes at least the output of the first model; the input of one or more tasks in the second-level task set includes at least the result obtained by processing the output of the first model through one or more tasks in the first-level task set... and so on, the input of one or more tasks in the Pth-level task set includes at least the result obtained by processing the output of the first model through one or more tasks in the (P-1)th-level task set.

[0209] To facilitate understanding, the following example, shown in Figure 4b, with N being 11 and M being 8, will be used to illustrate the relationship between the first model and the M tasks.

[0210] In the example shown in Figure 4b, the implementation of tasks 1 to 8 can be referred to Figure 4a and related descriptions above.

[0211] In the example shown in Figure 4b, the input to task 9 or task 10 may include the output of task 8. That is, the input to task 9 or task 10 may include the output of the first model obtained by passing through one or more of the tasks contained in each of the first three task sets (i.e., task 1, task 5, and task 8).

[0212] In the example shown in Figure 4b, the input to Task 11 may include the outputs of Task 9 and Task 10. That is, the input to Task 11 may include the result obtained by passing the output of the first model through 5 tasks (i.e., Task 1, Task 5, Task 8, Task 9 and Task 10).

[0213] Furthermore, in the example shown in Figure 4b, 10 (N=11) tasks can correspond to 5 (P=5) task sets.

[0214] In the first task set, the input of any task includes the output of the first model (i.e., the result of the first model's output passing through 0 tasks). For example, in this first task set, the input of any of the tasks 1, 2, 3, and 4 includes the output of the first model.

[0215] When i = 1 and i + 1 = 2, in the second task set, the input of any task includes the result of processing the output of the first model through one or more tasks in the first task set (i.e., the output of one or more tasks in the first task set). For example, in this second task set, the input of task 5 includes the result of processing the output of the first model through task 1, that is, the input of task 5 can include the result of processing the output of the first model through a task in one task set (i.e., task 1); the input of task 6 or task 7 can include the output of task 2, that is, the input of task 6 or task 7 can include the result of processing the output of the first model through a task (i.e., task 2).

[0216] When i = 2 and i + 1 = 3, in the third task set, the input of any task includes the result of processing the output of the first model through one or more tasks in the first two task sets (i.e., the output of one or more tasks in the second task set). For example, in this third task set, the input of task 8 includes the result of processing the output of the first model through tasks 1 and 5, that is, the input of task 8 can include the result of processing the output of the first model through tasks in the two task sets (i.e., tasks 1 and 5).

[0217] When i = 3 and i + 1 = 4, in the fourth task set, the input of any task includes the result of the first model's output processed by the first three tasks (i.e., the output of one or more tasks in the third task set). For example, in this fourth task set, the input of task 9 or task 10 includes the result of the first model's output processed by tasks 1, 5, and 8. That is, the input of task 9 or task 10 can include the result of the first model's output processed by the tasks in the three task sets (i.e., tasks 1, 5, and 8).

[0218] When i = 4 and i + 1 = 5, in the fifth task set, the input of any task includes the result of the first model's output being processed by the first four tasks (i.e., the output of one or more tasks in the fourth task set). For example, in this fifth task set, the input of task 11 includes the result of the first model's output being processed by tasks 1, 5, 8, 9, and 10. That is, the input of task 11 can include the result of the first model's output being processed by tasks in the four task sets (i.e., tasks 1, 5, 8, 9, and 10).

[0219] Optionally, the input of any task in the (i+1)th task set of the P task sets includes the output of one or more tasks in the ith task set of the P task sets; this can be understood as the input of any task in the jth task set of the P task sets including the result obtained after the output of the first model has undergone j-1 processing steps, where each j-1 processing step includes the processing of one or more tasks in each of the j-1 task sets preceding the jth task set, and the value of j ranges from 1 to P.

[0220] For example, in the example shown in Figure 4b, for task 8 in the 3rd (j=3) task set, the output of the first model is the result obtained after 2 (j-1=2) processing steps. These two processing steps respectively include the processing of one or more tasks in each of the 2 (j-1=2) task sets preceding the 3rd (j=3) task set. That is, these two processing steps are the processing of task 1 in the 1st (j-2=1) task set and the processing of task 1 in the 2nd (j-1=2) task set, respectively.

[0221] For example, in the example shown in Figure 4b, for task 9 in the 4th (j=4) task set, the output of the first model is the result obtained after 3 (j-1=3) processing steps. These 3 processing steps respectively include the processing of one or more tasks in each of the 3 (j-1=3) task sets preceding the 4th (j=4) task set. That is, these 3 processing steps are the processing of task 1 in the 1st (j-3=1) task set, the processing of task 1 in the 2nd (j-2=2) task set, and the processing of task 8 in the 3rd (j-1=3) task set.

[0222] In one possible implementation, the process of the first communication device sending the second information in step S302 includes: when the performance of one or more of the M tasks is lower than or equal to a threshold, the first communication device sends the second information. Specifically, after receiving the first information indicating the M tasks, the first communication device can obtain the performance corresponding to the M tasks, and when the performance of one or more of the M tasks is lower than or equal to the threshold, it sends second information indicating the performance of the one or more tasks, so that the recipient of the second information can determine the task with degraded performance through the second information.

[0223] In one possible implementation, the second information sent by the first communication device in step S302 is also used to identify one or more of the M tasks. Specifically, the second information can be used to indicate the performance of one or more of the M tasks, and correspondingly, the second information can also be used to indicate the performance of the one or more tasks. In this way, the recipient of the second information can determine one or more of the M tasks based on the second information, and clearly identify the performance indicated by the second information as the performance of one or more of the M tasks.

[0224] It should be understood that the way the second information indicates one or more of the M tasks can be similar to the way the first information indicates one or more of the M tasks. For example, the second information may include M identifiers, T indexes, etc.

[0225] Based on the technical solution shown in Figure 3, after receiving first information indicating M tasks in step S301, the first communication device can send second information in step S302, and use the second information to indicate the performance of one or more of the M tasks. In other words, the first communication device can deploy a first model and, based on the indication of the first information, measure and / or provide feedback on the task performance achieved by the output of the first model. Thus, the computing power of the communication node can process the model and its downstream tasks (and / or downstream models), while also achieving performance measurement and / or performance feedback.

[0226] Furthermore, among the M tasks indicated by the first information, the input of any task is determined based on the output of the first model, meaning that the output of the first model can be used to execute one or more tasks. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M tasks corresponding to the first model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the indication of performance measurement and / or feedback for downstream tasks in scenarios where the first model has downstream tasks.

[0227] In the method shown in Figure 3, the first information sent by the second communication device in step S301 to indicate the M tasks can be implemented in a variety of ways, which will be explained below through some implementation examples.

[0228] In Example 1, the first information includes M identifiers, which are used to indicate the M tasks respectively. Each of the M identifiers includes K indices, where the k-th index of the K indices is used to indicate one or more tasks in the k-th task set of the first K task sets in the P task sets. The value of k is from 1 to K, and K is a positive integer less than or equal to P.

[0229] It should be understood that the M identifiers are used to indicate the M tasks respectively. This can be understood as a one-to-one correspondence between the M identifiers and the M tasks, and / or, the m-th identifier among the M identifiers is used to indicate the m-th task among the M tasks, where m takes the value from 1 to M.

[0230] In Implementation Example 1, the first information received by the first communication device may include M identifiers, each used to indicate one of the M tasks. In the P task sets, the task indicated by any identifier may be represented as a task in the Kth task set (K is an integer less than or equal to P) of the P task sets. Furthermore, any of the M identifiers may include K indices to indicate one or more tasks contained in each of the K task sets.

[0231] Optionally, in Implementation Example 1, any identifier may also include an identifier of the first model. Specifically, the first communication device may deploy one or more first models, and correspondingly, each first model may have downstream tasks. Therefore, among the M identifiers used to indicate the M tasks, any identifier may also include an identifier of the first model. In this way, the first information can indicate the downstream tasks corresponding to one or more first models.

[0232] As an application example of implementing Example 1, taking the output of the first model as MPC, the value of M as 7, and the M tasks as Task 1 to Task 7 shown in Figure 4a as an example, the above first information can be implemented in the manner shown in Table 2 below.

[0233] Table 2

[0234] In Table 1, tasks 1 through 7 are identified by the identifiers “100”, “101”, “110”, “111”, “1000”, “1010”, and “1011”, respectively. The first bit of each identifier indicates the “first model”. For example, if the first bit of an identifier is 0, the identifier can be interpreted as indicating the first model; if the first bit of an identifier is 1, the identifier can be interpreted as indicating the downstream task of the first model.

[0235] Regarding the identifier "0" of the first model, if the first information received by the first communication device in step S301 contains the identifier "0", then the first communication device can determine that the first information indicates the first model. The second information subsequently sent by the first communication device in step S302 can contain the performance of the first model. For example, the second information can contain multipath error, that is, the performance of task 1 is characterized by the value of the multipath error.

[0236] For the identifier "100" of Task 1, the K indices are all "00" after the first bit, i.e., K=1, and each index occupies 2 bits. Accordingly, if the first information received by the first communication device in step S301 contains the identifier "100", then the first communication device can determine that the M tasks indicated by the first information include Task 1 (i.e., channel prediction). If the second information sent by the first communication device in step S302 contains the performance of Task 1, then the second information may include the CSI normalized mean square error (NMSE), that is, the performance of Task 1 is characterized by the value of CSI NMSE.

[0237] For the identifier "101" of Task 2, the K indices are all "01" after the first bit, i.e., K=1, and these K (K=1) indices occupy 2 bits. Accordingly, if the first information received by the first communication device in step S301 contains the identifier "101", then the first communication device can determine that the M tasks indicated by the first information include Task 2 (i.e., PMI prediction). If the second information sent by the first communication device in step S302 contains the performance of Task 2, the second information can include the squared generalized cosine similarity (SGCS) of PMI, that is, the performance of Task 2 is characterized by the value of PMI SGCS.

[0238] For the identifier "110" of task 3, the K indices are all "10" after the first bit, i.e., K=1, and these K (K=1) indices occupy 2 bits. Accordingly, if the first information received by the first communication device in step S301 includes the identifier "110", then the first communication device can determine that the M tasks indicated by the first information include task 3 (i.e., loss prediction). If the second information sent by the first communication device in step S302 includes the performance of task 3, then the second information can include the path loss error, i.e., the performance of task 3 is characterized by the value of the path loss error.

[0239] For the identifier "111" of task 4, the K indices are all "11" after the first bit, i.e., K=1, and these K (K=1) indices occupy 2 bits. Accordingly, if the first information received by the first communication device in step S301 contains the identifier "111", then the first communication device can determine that the M tasks indicated by the first information include task 4 (i.e., line-of-sight path Loss prediction). If the second information sent by the first communication device in step S302 contains the performance of task 4, then the second information can contain the LOS detection accuracy, i.e., the performance of task 4 is characterized by the value of the LOS detection accuracy.

[0240] For the identifier "1000" of task 5, the K indices are all "1000" after the first bit, i.e., K=2. The first index of these K (K=2) K indices occupies 2 bits, and the second index occupies 1 bit. Accordingly, if the first information received by the first communication device in step S301 contains the identifier "1000", then the first communication device can determine that the M tasks indicated by the first information include task 5 (i.e., MCS prediction). If the second information subsequently sent by the first communication device in step S302 contains information about the performance of task 5, then the second information can include the MCS accuracy, i.e., the performance of task 5 is characterized by the value of the MCS accuracy.

[0241] For the identifier "1010" of task 6, the K indices are all "1010" after the first bit, i.e., K=2. The first index of these K (K=2) indices occupies 2 bits, and the second index occupies 1 bit. Accordingly, if the first information received by the first communication device in step S301 includes the identifier "1010", then the first communication device can determine that the M tasks indicated by the first information include task 6 (i.e., beam prediction). If the second information subsequently sent by the first communication device in step S302 includes the performance of task 6, then the second information can include beam accuracy, i.e., the performance of task 6 is characterized by the value of beam accuracy.

[0242] For the identifier "1011" of task 7, the K indices are all "1011" after the first bit, i.e., K=2. The first index of these K (K=2) K indices occupies 2 bits, and the second index occupies 1 bit. Accordingly, if the first information received by the first communication device in step S301 contains the identifier "1011", then the first communication device can determine that the M tasks indicated by the first information include task 7 (i.e., beam prediction). If the second information sent by the first communication device in step S302 contains the performance of task 7, then the second information may include the beam reference signal received power (RSRP) error, i.e., the performance of task 7 is characterized by the value of the beam RSRP error.

[0243] In Example 2, the first information includes T indices, which indicate the tasks of the M tasks. The T indices respectively indicate the T task sets in the P task sets, where T is a positive integer less than or equal to P. The t-th index in the T indices is used to indicate 0 or more tasks contained in the t-th task set in the T task sets, where t is a positive integer less than T.

[0244] In Example 2, the N downstream tasks of the first model can be contained in P task sets, and correspondingly, the M tasks among the N tasks can be contained in T task sets among the P task sets. The first information used to indicate the M tasks can include T indices, which are used to indicate zero or more tasks in each of the T task sets. In this way, the first information can indicate the M tasks through the tasks contained in each of the T task sets.

[0245] Optionally, in implementation example two, the first information further includes the identifier of the first model. Specifically, in addition to including T indices, the first information may also include the identifier of the first model. The first communication device may deploy one or more first models, and each first model may have downstream tasks. Therefore, the first information used to indicate M tasks may also include the identifier of the first model. In this way, the first information can indicate the downstream tasks corresponding to one or more first models.

[0246] Optionally, in Implementation Example 2, the T indices satisfy at least one of the following: in the t-th index of the T indices, the value of the first bit is used to indicate whether the first information includes the (t+x)-th index, where x ranges from 1 to Tt; or, when the value of the t-th index is a preset value, the t-th index is used to indicate the tasks (or all tasks) contained in the t-th task set. Therefore, when the value of the first bit in the t-th index of the T indices is used to indicate whether the first information includes the (t+x)-th index, the first communication device can determine whether the (t+x)-th index needs to be parsed based on the value of the first bit in the t-th index, reducing implementation complexity and avoiding unnecessary overhead.

[0247] Furthermore, in the t-th index among the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the tasks contained in the p-th task set. In this way, it is possible to indicate one or more tasks corresponding to an identifier through a specific value of the identifier, thereby reducing overhead.

[0248] For example, the value of the t-th index is a preset value, which can be understood as the values ​​of the bits other than the first bit in the multiple bits contained in the t-th index being preset values ​​(e.g., all 0s or all 1s); or, the values ​​of the multiple bits in the multiple bits contained in the t-th index being preset values.

[0249] The following will take the scenario shown in Figure 4b as an example, and describe the various implementation methods of T indexes when the M tasks indicated by the first information are 4 tasks (task 1, task 2, task 5 and task 9 respectively).

[0250] As an application example of implementing Example 2, the value of T is equal to the value of P. That is, the first information can include 4 (T = P = 4) indices, which can be implemented as shown in Table 3 below.

[0251] Table 3

[0252] As shown in Table 3, the first information may include T indices, as follows:

[0253] The first index corresponds to the first task set in Figure 4b, and the value of the first index is used to indicate task 1 and task 2.

[0254] The second index corresponds to the second task set in Figure 4b, and the value of the second index is used to indicate task 5.

[0255] The third index corresponds to the third task set in Figure 4b, and the value of the third index is used to indicate that the M tasks do not include any of the tasks in the third task set.

[0256] The fourth index corresponds to the fourth task set in Figure 4b, and the value of the fourth index is used to indicate task 9.

[0257] The following example uses the first index as an illustration.

[0258] In the first implementation, the first index needs to indicate one or more tasks from task 1 to task 4. Accordingly, the first index can include 4 bits, represented by a bitmap. For example, if the value of the i-th bit is 1, it indicates that M tasks include the i-th task corresponding to that i-th bit; conversely, if the value of the i-th bit is 0, it indicates that M tasks do not include the i-th task corresponding to that i-th bit. In the example above, the value of the 4 bits in the first index can be "1100".

[0259] Optionally, in the first index, the value of the first bit can also be used to indicate whether the first information includes the 1+x (x is 1 to 3)th index. Accordingly, the first index can include 5 bits with a value of "11100". The first bit being "1" indicates that the first information includes at least one of the second, third, and fourth indices. The last four bits are "1100", with the meaning described above.

[0260] In the second implementation method, the first index needs to indicate one or more tasks from task 1 to task 4, resulting in 15 possible cases. Correspondingly, at least four bits can be used to indicate each of these 15 cases, as follows:

[0261] Case 1: Indicates that M tasks include task 1, for example, the value of these four bits is 0001;

[0262] Case 2: Indicates that M tasks include task 2, for example, the value of these four bits is 0010;

[0263] Case 3: Indicates that M tasks include task 3, for example, the value of these four bits is 0011;

[0264] Case 4: Indicates that M tasks include task 4, for example, the value of these four bits is 0100;

[0265] Case 5: Indicates that M tasks include Task 1 and Task 2, for example, the value of these four bits is 0101;

[0266] Case 6: Indicates that M tasks include Task 1 and Task 3, for example, the value of these four bits is 0110;

[0267] Case 7: Indicates that M tasks include Task 1 and Task 4, for example, the value of these four bits is 0111;

[0268] Case 8: Indicates that M tasks include Task 2 and Task 3, for example, the value of these four bits is 1000;

[0269] Case 9: Indicates that M tasks include Task 2 and Task 4, for example, the value of these four bits is 1001;

[0270] Case 10: Indicates M tasks including task 3 and task 4, for example, the value of the four bits is 1010;

[0271] Case 11: Indicates M tasks including Task 1, Task 2 and Task 3, for example, the value of these four bits is 1011;

[0272] Case 12: Indicates M tasks including Task 1, Task 3 and Task 4, for example, the value of these four bits is 1100;

[0273] Case 13: Indicates M tasks including Task 1, Task 2 and Task 4, for example, the value of these four bits is 1101;

[0274] Case 14: Indicates M tasks including Task 2, Task 3 and Task 4, for example, the value of these four bits is 1110;

[0275] Case 15: Indicates M tasks including Task 1, Task 2, Task 3 and Task 4, for example, the value of these four bits is 1111.

[0276] In the example above, the value of the 4 bits in the first index can be "0101".

[0277] Optionally, in the first index, the value of the first bit can also be used to indicate whether the first information includes the 1+x (x is 1 to 3)th index. Accordingly, the first index can include 5 bits with a value of "10101". The first bit being "1" indicates that the first information includes at least one of the second, third, and fourth indices. The last four bits are "0101", with the meanings described above.

[0278] In implementation method three, the first index indicates one of the four cases from task 1 to task 4, the case where none of the tasks from task 1 to task 4 are selected, and the case where all of the tasks from task 1 to task 4 are selected. There are a total of six cases, and each of these six cases can be indicated by at least three bits, as follows:

[0279] Case 1: Indicates that M tasks include task 1, for example, the value of these four bits is 001;

[0280] Case 2: Indicates that M tasks include task 2, for example, the value of these four bits is 010;

[0281] Case 3: Indicates that M tasks include task 3, for example, the value of these four bits is 011;

[0282] Case 4: Indicates that M tasks include task 4, for example, the value of these four bits is 100;

[0283] Case 5: Indicate that tasks 1 through 4 are not selected, for example, the value of these four bits is 101;

[0284] Case 6: Instruct all tasks 1 to 4 to be selected, for example, the value of these four bits is 111.

[0285] Optionally, 101 and 110 are reserved values ​​that can be used to indicate other information.

[0286] In implementation method four, the first index indicates one of the four cases from task 1 to task 4. Correspondingly, at least two bits can be used to indicate each of the four cases, as follows:

[0287] Case 1: Indicates that M tasks include task 1, for example, the value of these four bits is 00;

[0288] Case 2: Indicates that M tasks include task 2, for example, the value of these four bits is 01;

[0289] Case 3: Indicates that M tasks include task 3, for example, the value of these four bits is 10;

[0290] Case 4: Indicates that M tasks include task 4, for example, the value of the four bits is 11.

[0291] In addition to containing several bits to indicate tasks 1 to 4, the first index may also contain a bit (e.g., the first bit) to indicate whether the first information includes the second index. For example, if the first bit in the first index is 0, the first communication device may determine that the first information does not include the second index or any other identifiers following the second index; if the first bit in the first index is 1, the first communication device may determine that the first information includes the second index and at least one of the other indices following the second index.

[0292] As an application example of implementing Example 2, the value of T is less than or equal to the value of P. Since the M tasks (i.e., task 1, task 2, task 5, and task 9) are located in the first task set, the second task set, and the fourth task set, respectively, the first information can include 3 (T=3) indices, which can be implemented as shown in Table 4 below.

[0293] Table 4

[0294] As shown in Table 4, the first information may include T indices, as follows:

[0295] The first index corresponds to the first task set in Figure 4b, and the value of the first index is used to indicate task 1 and task 2.

[0296] The second index corresponds to the second task set in Figure 4b, and the value of the second index is used to indicate task 5.

[0297] The third index corresponds to the fourth task set in Figure 4b, and the value of the fourth index is used to indicate task 9.

[0298] It should be noted that the values ​​of each index in Table 4 can be referenced from the implementation methods described in Method 1 and Method 2 above.

[0299] Example 3: The first information includes M identifiers, which are used to indicate the M tasks respectively; among the M identifiers, the lengths of the different identifiers are the same.

[0300] In Example 3, the first information can be indicated by M identifiers of equal length to indicate M tasks respectively. That is, different tasks can be indicated by sequences of equal length. In this way, the implementation complexity can be reduced.

[0301] As an example of implementing Example 3, taking the scenario shown in Figure 4b as an example, the first information may include 10 (N=10) identifiers, which can be implemented in the manner shown in Table 5 below.

[0302] Table 5

[0303] In Table 5, different tasks can be indicated by taking different values ​​for Q bits (Q is a positive integer).

[0304] As an example, if none of the values ​​from 1 to 10 are the same, Q is greater than or equal to 4, meaning that at least 4 bits are used to indicate the ten different values.

[0305] As another example, when values ​​1 to 5 are the same, and values ​​6 to 10 are the same, Q is greater than or equal to 1, meaning that at least one bit is used to indicate two different values ​​respectively. In other words, in this case, the first information can be used to indicate whether the M tasks include tasks 1 to 5, and whether the M tasks include tasks 6 to 10.

[0306] Please refer to Figure 5, which is a schematic diagram of another implementation of the communication method provided in this application. The method includes the following steps.

[0307] S501. The second communication device sends third information, and correspondingly, the first communication device receives the third information. The third information indicates M models, where M is a positive integer. Furthermore, any one of the M models is derived based on the second model.

[0308] Optionally, the third information received by the first communication device in step S501 can be used to instruct the performance of the M models to perform one or more of the following operations: measurement, testing, monitoring, evaluation, measurement, feedback, reporting, uploading, or submission.

[0309] S502. The first communication device sends a fourth message, and correspondingly, the second communication device receives the fourth message. The fourth message is used to indicate the performance of one or more of the M models.

[0310] It should be understood that any one of the M models is determined based on the second model. This can be understood as any one of the M models being obtained by processing the second model one or more times. Any of these one or more processing steps can be model fine-tuning, model distillation, model pruning, model compression, model fusion, or other model processing.

[0311] Optionally, the performance of the model may include one or more of the model's (or the model's output) accuracy, precision, and processing speed.

[0312] It should be noted that the fourth information can indicate the performance of one or more models in a variety of ways.

[0313] For example, after the first communication device executes the one or more models locally and obtains the output of the one or more models, it determines the performance of the one or more models based on the output of the one or more models, and the fourth information sent by the first communication device may include information for indicating or characterizing the performance of the one or more models.

[0314] For example, after the first communication device can execute the one or more models locally and obtain the output of the one or more models, the fourth information sent by the first communication device may include the output of the one or more models; subsequently, the recipient of the second information can determine the performance of the one or more models based on the output of the one or more models.

[0315] Optionally, the input to the second model can be implemented in a variety of ways, such as environmental parameters collected by the first communication device, communication signals received by the first communication device from other communication devices (e.g., the second communication device), and one or more of the information pre-configured locally by the first communication device.

[0316] To facilitate understanding, the following example, with M set to 8, will be used to illustrate the relationship between the second model and the M models.

[0317] In the example shown in Figure 6a, any one of Model 1, Model 2, Model 3 and Model 4 can be obtained based on the second model, that is, any one of these four models can be obtained by processing the second model once.

[0318] In the example shown in Figure 6a, model 5 can be obtained based on model 1, that is, model 5 can be obtained by processing the second model twice.

[0319] In the example shown in Figure 6a, model 6 or model 7 can be obtained based on model 2, that is, model 6 or model 7 can be obtained by processing the second model twice.

[0320] In the example shown in Figure 6a, model 8 can be obtained based on model 5, that is, model 8 can be obtained by processing the second model three times.

[0321] It should be noted that M can be a positive integer. When M takes other values, the relationship between the M models and the first model can be seen in the example shown in Figure 6a. That is, any of the M models can be obtained by processing the second model through one or more models.

[0322] For example, the first model can be a wireless pre-trained model, a pre-trained model, or a wireless large model, etc.

[0323] In one possible implementation, the M models indicated by the third information sent by the second communication device in step S501 are contained in N models, where N is an integer greater than or equal to M; the N models correspond to P model sets, each of the P model sets includes one or more models from the N models, and different model sets in the P model sets contain different models; wherein any model in the (i+1)th model set in the P model sets is determined based on one or more models in the ith model set in the P model sets, where P is a positive integer and i is from 1 to P-1.

[0324] For example, taking P greater than 2 as an example, in P model sets, any model in one or more models contained in the first model set is obtained by processing the second model; any model in one or more models contained in the second model set is obtained by processing the first model set; and so on. Similarly, any model in one or more models contained in the Pth model set is obtained by processing the (P-1)th model set. In other words, P model sets can also be described as P-level model sets. For example, in a P-level model set, any model in one or more models contained in the first-level model set is obtained by processing the second model once; any model in one or more models contained in the second-level model set is obtained by processing the first model set; and so on. Similarly, any model in one or more models contained in the Pth-level model set is obtained by processing the (P-1)th-level model set.

[0325] Specifically, among the N models containing M models, any one model is determined based on the second model. This any one model can be obtained by processing the second model zero, one, or more times; that is, the N models can include a set of one or more downstream models of the second model. This enables the first information to provide performance measurement and / or feedback indications for the downstream models of the second model, even when the second model has a set of one or more downstream models.

[0326] Optionally, any model in the (i+1)th model set of the P model sets is determined based on one or more models in the ith model set of the P model sets; this can be understood as any model in the pth model set of the P model sets being obtained based on the second model after p-1 processing steps, where p-1 processing steps include model processing corresponding to one or more models in each of the p-1 model sets preceding the pth model set, and p takes values ​​from 1 to P.

[0327] To facilitate understanding, the following example, shown in Figure 6b, with N being 11 and M being 8, will be used to illustrate the relationship between the second model and the M models.

[0328] In the example shown in Figure 6b, the implementation of Models 1 to 8 can be referred to Figure 6a and related descriptions above.

[0329] In the example shown in Figure 6b, model 9 or model 10 can be obtained based on model 8, that is, model 9 or model 10 can be obtained by model 8 through model processing.

[0330] In the example shown in Figure 6b, model 11 can be obtained based on model 9 and model 10, that is, model 11 can be obtained by model processing through model 9 and model 10.

[0331] Furthermore, in the example shown in Figure 6b, 10 (N=11) models can correspond to 4 (P=5) model sets.

[0332] In the first model set, any model can be derived from the second model. For example, in this first model set, any of the models 1, 2, 3, and 4 is derived from the second model through a certain model processing step.

[0333] When i = 1 and i + 1 = 2, in the second model set, any model can be obtained by processing one or more models from the previous model set based on the second model (i.e., by processing one or more models from the first model set). For example, in the second model set, model 5 is obtained by processing the model corresponding to model 1 based on the second model; model 6 or model 7 is obtained by processing the model corresponding to model 2 based on the second model.

[0334] When i = 2 and i + 1 = 3, in the third model set, any model can be obtained by processing the second model with the model corresponding to one or more models in the first two model sets (i.e., by processing the model with the model corresponding to one or more models in the second model set). For example, in this third model set, model 8 is obtained by processing the second model with the model corresponding to model 1 and model 5.

[0335] When i = 3 and i + 1 = 4, in the fourth model set, any model can be obtained by processing the second model with the model corresponding to one or more models in the first three model sets (i.e., by processing the model with the model corresponding to one or more models in the third model set). For example, in this fourth model set, model 9 or model 10 is obtained by processing the second model with the model corresponding to model 1, model 5, and model 8.

[0336] When i = 4 and i + 1 = 5, in the fifth model set, any model can be obtained by processing the second model with the model corresponding to one or more models in the first four model sets (i.e., by processing the model with the model corresponding to one or more models in the fourth model set). For example, in this fifth model set, model 11 is obtained by processing the second model with the model corresponding to model 1, model 5, model 8, model 9 and model 10.

[0337] In one possible implementation, the process of the first communication device sending the fourth information in step S502 includes: when the performance of one or more of the M models is lower than or equal to a threshold, the first communication device sends the fourth information. Specifically, after receiving the third information indicating the M models, the first communication device can obtain the performance corresponding to the M models, and when the performance of one or more of the M models is lower than or equal to the threshold, it sends fourth information to indicate the performance of the one or more models, so that the recipient of the fourth information can determine the model with degraded performance through the fourth information.

[0338] In one possible implementation, the fourth information transmitted by the first communication device in step S502 can also be used to indicate one or more models among the M models. Specifically, the fourth information can be used to indicate the performance of one or more models among the M models, and correspondingly, the fourth information can also be used to indicate the one or more models. In this way, the recipient of the fourth information can determine one or more models among the M models based on the fourth information, and clearly define the performance indicated by the fourth information as the performance of one or more models among the M models.

[0339] It should be understood that the way the fourth information indicates one or more models among the M models can be similar to the way the third information indicates one or more models among the M models. For example, the fourth information may include M identifiers, T indices, etc.

[0340] Based on the technical solution shown in Figure 5, after receiving the first information indicating the M models in step S501, the first communication device can send the fourth information in step S502, and use the fourth information to indicate the performance of one or more of the M models. In other words, the first communication device can deploy the second model and the M models obtained based on the second model, and measure and / or provide feedback on the performance of the M models based on the indication of the first information. Thus, the computing power of the communication node can process the model and its downstream tasks (and / or downstream models), while also achieving performance measurement and / or performance feedback.

[0341] Furthermore, among the M models indicated by the first information, each model is determined based on the second model; that is, the second model can be processed once or multiple times to generate any of the M models. In the above technical solution, the first communication device can measure and / or provide feedback on the performance of the M models corresponding to the second model based on the indication of the first information. This improves the flexibility of the solution implementation and also enables the measurement and / or feedback of the performance of downstream models in scenarios where the second model has downstream models.

[0342] In the method shown in Figure 5, the third information sent by the second communication device in step S501 to indicate the M models can be implemented in a variety of ways, which will be explained below through some implementation examples.

[0343] Example A is implemented where the third information includes M identifiers, each of which is used to indicate one of the M models. Each of the M identifiers includes K indices. The k-th index of the K indices is used to indicate the model processing corresponding to one or more models in the k-th model set among the first K model sets in the P model sets. The value of k is from 1 to K, where K is a positive integer less than or equal to P.

[0344] It should be understood that the M identifiers are used to indicate the M models respectively. This can be understood as a one-to-one correspondence between the M identifiers and the M models, and / or, the m-th identifier among the M identifiers is used to indicate the m-th model among the M models, where m takes the value from 1 to M.

[0345] In implementation example A, the third information received by the first communication device may include M identifiers, each used to indicate one of the M models. In the P model sets, the model indicated by any identifier may be represented as the model in the Kth model set (K is an integer less than or equal to P) of the P model sets. Furthermore, any of the M identifiers may include K indices to indicate the model processing corresponding to that model.

[0346] Optionally, in implementation example A, any identifier may also include an identifier for processing the second model. Specifically, the first communication device may deploy one or more second models, and correspondingly, each second model may have a downstream model. Therefore, among the M identifiers used to indicate the M models, any identifier may also include an identifier for the second model. In this way, the third information can indicate the downstream model corresponding to one or more second models.

[0347] It should be noted that the implementation process of the third information in Example A can be referred to the implementation process of the first information in Example 1 above.

[0348] Implementation example B, the third information includes T indices, the T indices indicate the M models, the T indices are used to indicate the T model sets in the P model sets respectively, T is a positive integer less than or equal to P; the t-th index in the T indices is used to indicate 0 or more models contained in the t-th model set in the T model sets, t is a positive integer less than T.

[0349] In implementation example B, the N downstream models of the second model can be contained in P model sets. Correspondingly, the M models among the N models can be contained in T model sets among the P model sets. The third information used to indicate the M models can include T indices, which respectively indicate zero or one or more models in each of the T model sets. In this way, the third information can indicate the M models through the models contained in each of the T model sets.

[0350] Optionally, in implementation example B, the third information also includes an identifier for the processing of the second model. Specifically, in addition to including T indices, the third information may also include an identifier for the second model. The first communication device may deploy one or more second models, and each second model may have a downstream model. Therefore, the third information used to indicate M models may also include the identifier for the second model. In this way, the third information can indicate the downstream model corresponding to one or more second models.

[0351] Optionally, in implementation example B, the T indices satisfy at least one of the following: in the t-th index of the T indices, the value of the first bit is used to indicate whether the third information includes the (t+x)-th index, where x is 1 to Tt; or, in the t-th index of the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the models (or all models) contained in the t-th model set.

[0352] For example, the value of the t-th index is a preset value, which can be understood as the values ​​of all bits except the first bit in the t-th index being preset values ​​(e.g., all 0s or all 1s); or, the values ​​of all bits in the t-th index being preset values. Specifically, in the case where the value of the first bit in the t-th index of the T indices is used to indicate whether the third information includes the (t+x)-th index, the first communication device can determine whether the (t+x)-th index needs to be parsed based on the value of the first bit in the t-th index, thereby reducing implementation complexity and avoiding unnecessary overhead.

[0353] Furthermore, in the t-th index among the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the models contained in the t-th model set. In this way, one or more models corresponding to an identifier can be indicated by a specific value of the identifier, thereby reducing overhead.

[0354] It should be noted that the implementation process of the third information in Example B can be referred to the implementation process of the first information in Example 2 above.

[0355] Implementation example C, the third information includes M identifiers, which are used to indicate the M models respectively; among the M identifiers, the lengths of the different identifiers are the same.

[0356] Optionally, in implementation example C, the third information can indicate M models respectively through M identifiers of equal length. That is, different models can be indicated by sequences of equal length. In this way, the implementation complexity can be reduced.

[0357] It should be noted that the implementation process of the third information in Example C can refer to the implementation process of the first information in Example 3 above.

[0358] Please refer to Figure 7. This application embodiment provides a communication device 700, which can realize the functions of the second communication device or the first communication device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments. In this application embodiment, the communication device 700 can be the first communication device (or the second communication device), or it can be an integrated circuit or component inside the first communication device (or the second communication device), such as a chip.

[0359] It should be noted that the transceiver unit 702 may include a transmitting unit and a receiving unit, which are used to perform transmitting and receiving respectively.

[0360] In one possible implementation, when the device 700 is used to execute the method performed by the first communication device in FIG3 and related embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the processing unit 701 is used to determine second information; the transceiver unit 702 is also used to send the second information, which indicates the performance of one or more of the M tasks.

[0361] In one possible implementation, when the device 700 is used to execute the method performed by the second communication device in FIG3 and related embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine first information; the transceiver unit 702 is used to send the first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of a first model; the transceiver unit 702 is also used to receive second information, which indicates the performance of one or more of the M tasks.

[0362] In one possible implementation, when the device 700 is used to execute the method performed by the first communication device in FIG5 and related embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the transceiver unit 702 is used to receive third information, which is used to indicate M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the processing unit 701 is used to determine fourth information; the transceiver unit 702 is also used to send the fourth information, which is used to indicate the performance of one or more of the M models.

[0363] In one possible implementation, when the device 700 is used to execute the method performed by the second communication device in FIG5 and related embodiments, the device 700 includes a processing unit 701 and a transceiver unit 702; the processing unit 701 is used to determine third information, and the transceiver unit 702 is used to send the third information, which is used to indicate M models, where M is a positive integer; wherein any of the M models is determined based on the second model; the transceiver unit 702 is also used to receive fourth information, which is used to indicate the performance of one or more of the M models.

[0364] In one possible design, when the communication device 700 is a terminal device, a terminal, or a communication module within a terminal, the function of the processing unit 701 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the transceiver unit 702 can be implemented by transceiver circuitry.

[0365] In one possible design, when the communication device 700 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 701 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the transceiver unit 702 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0366] It should be noted that the information execution process of the unit of the above-mentioned communication device 700 can be specifically described in the method embodiment shown above in this application, and will not be repeated here.

[0367] Please refer to Figure 8, which is another schematic structural diagram of the communication device 800 provided in this application. The communication device 800 includes a logic circuit 801 and an input / output interface 802. The communication device 800 can be a chip or an integrated circuit.

[0368] In this context, the transceiver unit 702 shown in Figure 7 can be a communication interface, which can be the input / output interface 802 in Figure 8, and the input / output interface 802 can include an input interface and an output interface. Alternatively, the communication interface can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0369] In one possible implementation, when the device 800 is used to execute the method performed by the first communication device in FIG3 and related embodiments, the input / output interface 802 is used to receive first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of the first model; the logic circuit 801 is used to determine second information; the input / output interface 802 is also used to send second information, which indicates the performance of one or more of the M tasks.

[0370] In one possible implementation, when the device 800 is used to execute the method performed by the second communication device in FIG3 and related embodiments, the logic circuit 801 is used to determine first information; the input / output interface 802 is used to send the first information, which is used to indicate M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of the first model; the input / output interface 802 is also used to receive second information, which is used to indicate the performance of one or more of the M tasks.

[0371] In one possible implementation, when the device 800 is used to execute the method performed by the first communication device in FIG5 and related embodiments, the input / output interface 802 is used to receive third information, which is used to indicate M models, where M is a positive integer; wherein any of the M models is determined based on a second model; the logic circuit 801 is used to determine fourth information; the input / output interface 802 is also used to send fourth information, which is used to indicate the performance of one or more of the M models.

[0372] In one possible implementation, when the device 800 is used to execute the method performed by the second communication device in FIG5 and related embodiments, the logic circuit 801 is used to determine third information, the input / output interface 802 is used to send the third information, the third information being used to indicate M models, where M is a positive integer; wherein any of the M models is determined based on the second model; the input / output interface 802 is also used to receive fourth information, the fourth information being used to indicate the performance of one or more of the M models.

[0373] The logic circuit 801 and the input / output interface 802 can also perform other steps performed by the first or second communication device in any embodiment and achieve corresponding beneficial effects, which will not be elaborated here.

[0374] In one possible implementation, the processing unit 701 shown in FIG7 can be the logic circuit 801 in FIG8.

[0375] Optionally, the logic circuit 801 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0376] Optionally, the processing apparatus may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform the corresponding processing and / or steps in any of the method embodiments.

[0377] Optionally, the processing device may consist of only a processor. A memory for storing computer programs is located outside the processing device, and the processor is connected to the memory via circuitry / wires to read and execute the computer programs stored in the memory. The memory and processor may be integrated together or physically independent of each other.

[0378] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0379] Please refer to Figure 9, which shows the communication device 900 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 900 can be the communication device as a terminal device in the above embodiments. The example shown in Figure 9 is that the terminal device is implemented through the terminal device (or the components in the terminal device).

[0380] The present invention provides a possible logical structure diagram of the communication device 900, which may include, but is not limited to, at least one processor 901 and a communication port 902.

[0381] In Figure 7, the transceiver unit 702 can be a communication interface, which can be the communication port 902 in Figure 9. The communication port 902 can include an input interface and an output interface. Alternatively, the communication port 902 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0382] Further optionally, the device may also include at least one of a memory 903 and a bus 904. In the embodiments of this application, the at least one processor 901 is used to control the operation of the communication device 900.

[0383] Furthermore, the processor 901 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0384] It should be noted that the communication device 900 shown in Figure 9 can be used to implement the steps implemented by the terminal device in the aforementioned method embodiments and to achieve the corresponding technical effects of the terminal device. The specific implementation of the communication device shown in Figure 9 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0385] Please refer to Figure 10, which is a schematic diagram of the structure of the communication device 1000 involved in the above embodiments provided in the embodiments of this application. The communication device 1000 can specifically be a communication device as a network device in the above embodiments. The example shown in Figure 10 is that the network device is implemented through a network device (or a component in the network device). The structure of the communication device can refer to the structure shown in Figure 10.

[0386] The communication device 1000 includes at least one processor 1011 and at least one network interface 1014. Optionally, the communication device further includes at least one memory 1012, at least one transceiver 1013, and one or more antennas 1015. The processor 1011, memory 1012, transceiver 1013, and network interface 1014 are connected, for example, via a bus. In this embodiment, the connection may include various interfaces, transmission lines, or buses, etc., and this embodiment is not limited thereto. The antenna 1015 is connected to the transceiver 1013. The network interface 1014 enables the communication device to communicate with other communication devices through a communication link. For example, the network interface 1014 may include a network interface between the communication device and core network equipment, such as an S1 interface; the network interface may also include a network interface between the communication device and other communication devices (e.g., other network devices or core network equipment), such as an X2 or Xn interface.

[0387] In this context, the transceiver unit 702 shown in Figure 7 can be a communication interface, which can be the network interface 1014 in Figure 10. The network interface 1014 can include an input interface and an output interface. Alternatively, the network interface 1014 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0388] The processor 1011 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data from these programs, for example, to support the actions described in the embodiments of the communication device. The communication device may include a baseband processor and a central processing unit (CPU). The baseband processor is primarily used to process communication protocols and communication data, while the CPU is primarily used to control the entire terminal device, execute software programs, and process data from these programs. The processor 1011 in Figure 10 can integrate the functions of both a baseband processor and a CPU. Those skilled in the art will understand that the baseband processor and CPU can also be independent processors interconnected via technologies such as buses. Those skilled in the art will understand that a terminal device can include multiple baseband processors to adapt to different network standards, and multiple CPUs to enhance its processing capabilities. Various components of the terminal device can be connected via various buses. The baseband processor can also be described as a baseband processing circuit or a baseband processing chip. The CPU can also be described as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built into the processor or stored in memory as a software program, which is then executed by the processor to implement the baseband processing function.

[0389] The memory is primarily used to store software programs and data. The memory 1012 can exist independently or be connected to the processor 1011. Optionally, the memory 1012 can be integrated with the processor 1011, for example, integrated within a single chip. The memory 1012 can store program code that executes the technical solutions of the embodiments of this application, and its execution is controlled by the processor 1011. The various types of computer program code being executed can also be considered as drivers for the processor 1011.

[0390] Figure 10 shows only one memory and one processor. In actual terminal devices, there may be multiple processors and multiple memories. Memory can also be called storage medium or storage device, etc. Memory can be a storage element on the same chip as the processor, i.e., an on-chip storage element, or it can be a separate storage element; this application does not limit this.

[0391] Transceiver 1013 can be used to support the reception or transmission of radio frequency (RF) signals between a communication device and a terminal. Transceiver 1013 can be connected to antenna 1015. Transceiver 1013 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1015 can receive RF signals. The receiver Rx of transceiver 1013 is used to receive the RF signals from the antennas, convert the RF signals into digital baseband signals or digital intermediate frequency (IF) signals, and provide the digital baseband signals or IF signals to processor 1011 so that processor 1011 can perform further processing on the digital baseband signals or IF signals, such as demodulation and decoding. In addition, the transmitter Tx in transceiver 1013 is also used to receive modulated digital baseband signals or IF signals from processor 1011, convert the modulated digital baseband signals or IF signals into RF signals, and transmit the RF signals through one or more antennas 1015. Specifically, the receiver Rx can selectively perform one or more stages of downmixing and analog-to-digital conversion on the radio frequency signal to obtain a digital baseband signal or a digital intermediate frequency (IF) signal. The order of these downmixing and IF conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of upmixing and digital-to-analog conversion on the modulated digital baseband signal or digital IF signal to obtain a radio frequency signal. The order of these upmixing and IF conversion processes is also adjustable. The digital baseband signal and the digital IF signal can be collectively referred to as digital signals.

[0392] The transceiver 1013 can also be called a transceiver unit, transceiver, transceiver device, etc. Optionally, the device in the transceiver unit that performs the receiving function can be regarded as the receiving unit, and the device in the transceiver unit that performs the transmitting function can be regarded as the transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit can also be called a receiver, input port, receiving circuit, etc., and the transmitting unit can be called a transmitter, transmitter, or transmitting circuit, etc.

[0393] It should be noted that the communication device 1000 shown in Figure 10 can be used to implement the steps implemented by the network device in the aforementioned method embodiments and to achieve the corresponding technical effects of the network device. The specific implementation of the communication device 1000 shown in Figure 10 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0394] Please refer to Figure 11, which is a schematic diagram of the structure of the communication device involved in the above embodiments provided in the embodiments of this application.

[0395] It is understood that the communication device 110 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to execute the technical solutions provided in this application. The communication device 110 may be the terminal device or network device described above, or a component (e.g., a chip) within these devices, used to implement the methods described in the following method embodiments. The communication device 110 includes one or more processors 111. The processor 111 may be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (e.g., a RAN node, terminal, or chip), execute software programs, and process data from the software programs.

[0396] Optionally, in one design, the processor 111 may include a program 113 (sometimes also referred to as code or instructions) that can be executed on the processor 111 to cause the communication device 110 to perform the methods described in the embodiments below. In yet another possible design, the communication device 110 includes circuitry (not shown in FIG11).

[0397] Optionally, the communication device 110 may include one or more memories 112 storing a program 114 (sometimes referred to as code or instructions), which can be run on the processor 111 to cause the communication device 110 to perform the methods described in the above method embodiments.

[0398] Optionally, the processor 111 and / or memory 112 may include AI modules 117 and 118, which are used to implement AI-related functions. The AI ​​modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a radio intelligence control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0399] Optionally, the processor 111 and / or memory 112 may also store data. The processor and memory may be configured separately or integrated together.

[0400] Optionally, the communication device 110 may further include a transceiver 115 and / or an antenna 116. The processor 111, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 115, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device through the antenna 116.

[0401] In this context, the processing unit 701 shown in Figure 7 can be a processor 111. The transceiver unit 702 shown in Figure 7 can be a communication interface, which can be the transceiver 115 in Figure 11. The transceiver 115 can include an input interface and an output interface. Alternatively, the transceiver 115 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0402] This application also provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor performs the method described in the possible implementations of the first or second communication device in the foregoing embodiments.

[0403] This application also provides a computer program product (or computer program) that, when executed by a processor, executes the method described above for the possible implementation of the first or second communication device.

[0404] This application also provides a chip system including at least one processor for supporting a communication device in implementing the functions involved in the possible implementations of the communication device described above. Optionally, the chip system further includes an interface circuit that provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing the program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices, wherein the communication device may specifically be the first communication device or the second communication device in the aforementioned method embodiments.

[0405] This application also provides a communication system, the network system architecture of which includes a first communication device and a second communication device in any of the above embodiments.

[0406] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. Whether a function is implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0407] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0408] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A communication method, characterized in that, include: Receive first information, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of the first model; Send a second message, which is used to indicate the performance of one or more of the M tasks.

2. A communication method, characterized in that, include: Send a first message, which indicates M tasks, where M is a positive integer; wherein the input of any of the M tasks is determined based on the output of the first model; Receive second information, which is used to indicate the performance of one or more of the M tasks.

3. The method according to claim 1 or 2, characterized in that, The M tasks are contained within N tasks, where N is an integer greater than or equal to M; the N tasks correspond to P task sets, and each task set in the P task sets includes one or more tasks from the N tasks, and different task sets in the P task sets contain different tasks; Wherein, the input of any task in the (i+1)th task set of the P task sets includes the output of one or more tasks in the ith task set of the P task sets, where P is a positive integer and i is from 1 to P-1.

4. The method according to claim 3, characterized in that, The first information includes M identifiers, each of which is used to indicate one of the M tasks. Each of the M identifiers includes K indices; wherein the k-th index of the K indices is used to indicate one or more tasks in the k-th task set of the first K task sets in the P task sets, and the value of k is from 1 to K, where K is a positive integer less than or equal to P.

5. The method according to claim 4, characterized in that, The identifier also includes the identifier of the first model.

6. The method according to claim 4, characterized in that, The first information includes T indices, the T indices indicating the tasks of the M tasks, the T indices respectively indicating T task sets in the P task sets, where T is a positive integer less than or equal to P; the t-th index in the T indices is used to indicate 0 or more tasks contained in the t-th task set in the T task sets, where t is a positive integer less than T.

7. The method according to claim 6, characterized in that, The first information also includes the identifier of the first model.

8. The method according to claim 6 or 7, characterized in that, The T indexes satisfy at least one of the following: In the t-th index of the T indices, the value of the first bit is used to indicate whether the first information includes the (t+x)-th index, where x ranges from 1 to Tt; or, In the t-th index among the T indices, when the value of the t-th index is a preset value, the t-th index is used to indicate the tasks contained in the t-th task set.

9. The method according to any one of claims 1 to 3, characterized in that, The first information includes M identifiers, each of which is used to indicate one of the M tasks. Among the M identifiers, the lengths of the different identifiers are the same.

10. The method according to any one of claims 1 to 9, characterized in that, The second information is also used to indicate one or more of the M tasks.

11. The method according to any one of claims 1 to 10, characterized in that, The performance of one or more of the M tasks is lower than or equal to the threshold.

12. A communication device, characterized in that, Includes a module for performing the method as described in any one of claims 1 to 11.

13. A communication device, characterized in that, It includes at least one processor coupled to a memory; the at least one processor is used to perform the method as described in any one of claims 1 to 11.

14. The communication device according to claim 13, characterized in that, The communication device is a chip or chip system.

15. A readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a communication device, implement the method as described in any one of claims 1 to 11.

Images