CN117643134A - Operation configuration method and device - Google Patents
Operation configuration method and device Download PDFInfo
- Publication number
- CN117643134A CN117643134A CN202280002108.7A CN202280002108A CN117643134A CN 117643134 A CN117643134 A CN 117643134A CN 202280002108 A CN202280002108 A CN 202280002108A CN 117643134 A CN117643134 A CN 117643134A
- Authority
- CN
- China
- Prior art keywords
- model
- capability information
- configuration
- terminal device
- network side
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 194
- 238000004891 communication Methods 0.000 claims abstract description 46
- 230000004044 response Effects 0.000 claims description 122
- 238000012549 training Methods 0.000 claims description 112
- 238000013480 data collection Methods 0.000 claims description 99
- 230000005540 biological transmission Effects 0.000 claims description 82
- 238000012544 monitoring process Methods 0.000 claims description 72
- 230000015654 memory Effects 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000003672 processing method Methods 0.000 abstract description 20
- 230000006870 function Effects 0.000 description 22
- 238000005516 engineering process Methods 0.000 description 17
- 238000007726 management method Methods 0.000 description 11
- 230000008859 change Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 7
- 239000004065 semiconductor Substances 0.000 description 6
- 238000009966 trimming Methods 0.000 description 6
- 230000005291 magnetic effect Effects 0.000 description 5
- 229910044991 metal oxide Inorganic materials 0.000 description 5
- 150000004706 metal oxides Chemical class 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 229910000577 Silicon-germanium Inorganic materials 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- JBRZTFJDHDCESZ-UHFFFAOYSA-N AsGa Chemical compound [As]#[Ga] JBRZTFJDHDCESZ-UHFFFAOYSA-N 0.000 description 1
- 101150069124 RAN1 gene Proteins 0.000 description 1
- LEVVHYCKPQWKOP-UHFFFAOYSA-N [Si].[Ge] Chemical compound [Si].[Ge] LEVVHYCKPQWKOP-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W72/00—Local resource management
- H04W72/04—Wireless resource allocation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The disclosure provides an operation configuration method, an operation configuration device, operation configuration equipment and a storage medium, and belongs to the technical field of communication. The method comprises the steps of receiving a capability information set sent by a terminal device aiming at an artificial intelligent AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model; and according to the capability information set, sending the operation configuration aiming at the AI model to the terminal equipment. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Description
The present disclosure relates to the field of communications technologies, and in particular, to an operation configuration method, an apparatus, a device, and a storage medium.
In the communication system, the wide application of the fifth generation mobile communication technology (5th Generation Mobile Communication Technology,5G) brings about a great change in aspects of people's lives. The sustainable development of the AI technology not only brings various colorful applications for intelligent terminal equipment, but also promotes industry upgrading in various industries. In operation for the artificial intelligence (Artificial Intelligence, AI) model, the operations involved by the terminal device may include a variety. However, different operations have different requirements on software and hardware of the terminal device, and different AI models have different requirements on capabilities of the terminal device, and a matching scheme of the capabilities of the terminal device and the AI models is not provided yet, so that the accuracy of operation determination performed on the AI models is low.
Disclosure of Invention
The operation configuration method, the device, the equipment and the storage medium provided by the disclosure are used for determining the operation of the terminal equipment on the basis of the capacity of the terminal equipment on the basis of the AI model, so that the accuracy of the operation determination on the AI model is improved, and the matching between the operation on the AI model and the capacity of the terminal equipment is improved.
An embodiment of an aspect of the present disclosure provides an operation configuration method, where the method is performed by a network side device, and the method includes:
receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
and according to the capability information set, sending operation configuration aiming at the AI model to the terminal equipment.
Optionally, in one embodiment of the disclosure, the sending, according to the capability information set, an operation configuration for the AI model to the terminal device includes:
and in response to the capability information set comprising training capability information for the AI model, transmitting training configuration for the AI model to the terminal device according to the training capability information.
Optionally, in one embodiment of the disclosure, the training configuration for the AI model includes at least one of:
configuration of training the AI model solely by the terminal device;
and jointly training the AI model by the network side equipment and the terminal equipment.
Optionally, in one embodiment of the disclosure, the method further comprises:
and training the AI model to obtain a trained AI model in response to the capability information set not including the training capability information for the AI model.
Optionally, in one embodiment of the disclosure, the sending, according to the capability information set, an operation configuration for the AI model to the terminal device includes:
and in response to the capability information set comprising inference capability information for the AI model, transmitting an inference configuration for the AI model to the terminal device in accordance with the inference capability information.
Optionally, in one embodiment of the disclosure, the inference configuration for the AI model includes at least one of:
configuration of reasoning the AI model by the terminal device alone;
And the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
Optionally, in one embodiment of the disclosure, the method further comprises:
and in response to the capability information set not including the reasoning capability information for the AI model, reasoning the AI model to obtain a reasoning AI model.
Optionally, in one embodiment of the disclosure, the sending, according to the capability information set, an operation configuration for the AI model to the terminal device includes:
and in response to the capability information set comprising transmission capability information for the AI model, transmitting a transmission configuration for the AI model to the terminal device according to the transmission capability information.
Optionally, in one embodiment of the disclosure, the sending the transmission configuration for the AI model to the terminal device includes at least one of:
transmitting deployment configuration for the AI model to the terminal device, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
and sending the uploading configuration for the AI model to the terminal equipment.
Optionally, in one embodiment of the disclosure, after the sending the upload configuration for the AI model to the terminal apparatus, the method further includes:
and receiving an AI model corresponding to the uploading configuration sent by the terminal equipment.
Optionally, in one embodiment of the disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
Optionally, in one embodiment of the disclosure, the sending, according to the capability information set, an operation configuration for the AI model to the terminal device includes:
and in response to the capability information set comprising update capability information for the AI model, sending an update configuration for the AI model to the terminal device according to the update capability information.
Optionally, in one embodiment of the disclosure, the method further comprises:
and updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model.
Optionally, in one embodiment of the disclosure, the sending, according to the capability information set, an operation configuration for AI to the terminal device includes:
and in response to the capability information set comprising fine-tuning capability information for the AI model, sending fine-tuning configuration for the AI model to the terminal device according to the fine-tuning capability information.
Optionally, in one embodiment of the disclosure, the method further comprises:
and in response to the capability information set not including the fine-tuning capability information for the AI model, fine-tuning the AI model to obtain a fine-tuned AI model.
Optionally, in one embodiment of the disclosure, the sending, according to the set of capability information, an operation configuration for the AI model to the terminal device according to the set of capability information includes:
and in response to the capability information set comprising data collection capability information for the AI model, transmitting a data collection configuration for the AI model to the terminal device according to the data collection capability information.
Optionally, in one embodiment of the disclosure, the method further comprises:
And in response to the capability information set not including the data collection capability information for the AI model, performing data collection on the AI model to obtain data corresponding to the AI model.
Optionally, in one embodiment of the disclosure, the sending, according to the set of capability information, an operation configuration for the AI model to the terminal device according to the set of capability information includes:
and in response to the capability information set comprising performance monitoring capability information for the AI model, sending a performance monitoring configuration for the AI model to the terminal device according to the performance monitoring capability information.
Optionally, in one embodiment of the disclosure, the method further comprises:
performance monitoring of the AI model is performed in response to the set of capability information not including the performance monitoring capability information for the AI model.
Optionally, in one embodiment of the disclosure, the set of capability information includes at least one of:
generic capability information for the AI model;
and specific capability information of the use case aiming at the AI model.
Optionally, in one embodiment of the disclosure, the generic capability information includes at least one of:
The terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
the terminal equipment supports the capability information of model reasoning.
Optionally, in one embodiment of the disclosure, the use case specific capability information includes at least one of:
data collection capability information;
model performance monitoring capability information.
Optionally, in one embodiment of the disclosure, the data collection capability information includes at least one of:
enhanced data collection capability information for channel state information (Channel State Information, CSI);
data collection capability information for beam management;
capability information is collected for data of the positioning information.
Another aspect of the present disclosure provides an operation configuration method, which is performed by a terminal device, and includes:
transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of the terminal device for operating an AI model;
And receiving the operation configuration for the AI model sent by the network side equipment according to the capability information set.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving training configuration sent by the network side equipment for the AI model in response to the capability information set comprising training capability information for the AI model.
Optionally, in one embodiment of the disclosure, the training configuration for the AI model includes at least one of:
configuration of training the AI model solely by the terminal device;
and jointly training the AI model by the network side equipment and the terminal equipment.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving the reasoning configuration sent by the network side equipment for the AI model in response to the capability information set comprising the reasoning capability information for the AI model.
Optionally, in one embodiment of the disclosure, the inference configuration for the AI model includes at least one of:
configuration of reasoning the AI model by the terminal device alone;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving a transmission configuration for the AI model sent by the network side equipment in response to the capability information set comprising the transmission capability information for the AI model.
Optionally, in one embodiment of the disclosure, the receiving the transmission configuration for the AI model sent by the network side device includes at least one of:
receiving deployment configuration sent by the network side equipment and aiming at the AI model, wherein the deployment configuration comprises configuration for updating model parameters aiming at the AI model;
and receiving the uploading configuration for the AI model sent by the network side equipment.
Optionally, in one embodiment of the disclosure, after the receiving the upload configuration for the AI model sent by the network side device, the method further includes:
And sending the AI model corresponding to the uploading configuration to the network side equipment.
Optionally, in one embodiment of the disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving updating configuration sent by the network side equipment for the AI model in response to the capability information set comprising updating capability information for the AI model.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving fine tuning configuration sent by the network side equipment for the AI model in response to the capability information set comprising fine tuning capability information for the AI model.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
And receiving the data collection configuration sent by the network side equipment for the AI model in response to the capability information set comprising the data collection capability information for the AI model.
Optionally, in one embodiment of the disclosure, the receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving performance monitoring configuration sent by the network side equipment for the AI model in response to the capability information set comprising the performance monitoring capability information for the AI model.
Optionally, in one embodiment of the disclosure, the set of capability information includes at least one of:
generic capability information for the AI model;
and specific capability information of the use case aiming at the AI model.
Optionally, in one embodiment of the disclosure, the generic capability information includes at least one of:
the terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
The terminal equipment supports the capability information of model reasoning.
Optionally, in one embodiment of the disclosure, the use case specific capability information includes at least one of:
data collection capability information;
model performance monitoring capability information.
Optionally, in one embodiment of the disclosure, the data collection capability information includes at least one of:
data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
An operation configuration device according to an embodiment of another aspect of the present disclosure includes:
the terminal equipment comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving a capability information set sent by the terminal equipment aiming at an AI model, and the capability information set is used for indicating capability information of the terminal equipment aiming at the AI model;
and the sending module is used for sending the operation configuration aiming at the AI model to the terminal equipment according to the capability information set.
An operation configuration device according to an embodiment of another aspect of the present disclosure includes:
a sending module, configured to send a capability information set to a network side device, where the capability information set is used to indicate capability information that the terminal device operates with respect to an AI model;
And the receiving module is used for receiving the operation configuration for the AI model sent by the network side equipment according to the capability information set.
In a further aspect of the disclosure, the apparatus includes a processor and a memory, where the memory stores a computer program, and the processor executes the computer program stored in the memory, so that the apparatus performs the method set forth in the embodiment of the foregoing aspect.
In a further aspect, the embodiment of the present disclosure proposes a network side device, where the apparatus includes a processor and a memory, where the memory stores a computer program, and the processor executes the computer program stored in the memory, so that the apparatus performs the method as set forth in the embodiment of the other aspect above.
In another aspect of the present disclosure, a communication apparatus includes: a processor and interface circuit;
the interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;
the processor is configured to execute the code instructions to perform a method as set forth in an embodiment of an aspect.
In another aspect of the present disclosure, a communication apparatus includes: a processor and interface circuit;
The interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;
the processor is configured to execute the code instructions to perform a method as set forth in another embodiment.
A further aspect of the present disclosure provides a computer-readable storage medium storing instructions that, when executed, cause a method as set forth in the embodiment of the aspect to be implemented.
A further aspect of the present disclosure provides a computer-readable storage medium storing instructions that, when executed, cause a method as set forth in the embodiment of the further aspect to be implemented.
In summary, in the embodiments of the present disclosure, a capability information set sent by a terminal device for an AI model is received, where the capability information set is used to indicate capability information of the terminal device for operating for the AI model, and according to the capability information set, operation configuration for the AI model is sent to the terminal device. In the embodiment of the disclosure, the operation configuration for the AI model is determined through the capability information set sent by the terminal equipment, so that the matching performance of the operation performed by the terminal equipment for the AI model and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal equipment cannot perform operation for the AI model is reduced. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is an exemplary schematic diagram of an artificial intelligence framework in a wireless air interface provided by an embodiment of the present disclosure;
FIG. 2 is a flow chart of a method of operation configuration according to another embodiment of the present disclosure;
FIG. 3 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 4 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 5 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 6 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 7 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 8 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 9 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 10 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 11 is a flow chart of a method of operation configuration according to another embodiment of the present disclosure;
FIG. 12 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 13 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 14 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 15 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 16 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 17 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 18 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 19 is a flow chart of a method of operation configuration according to yet another embodiment of the present disclosure;
FIG. 20 is a schematic diagram of an operation configuration device according to an embodiment of the present disclosure;
FIG. 21 is a schematic view of an operation configuration device according to another embodiment of the present disclosure;
fig. 22 is a block diagram of a terminal device provided by an embodiment of the present disclosure;
Fig. 23 is a block diagram of a network side device according to an embodiment of the present disclosure.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Rather, they are merely examples of apparatus and methods consistent with aspects of embodiments of the present disclosure as detailed in the accompanying claims.
The terminology used in the embodiments of the disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the disclosure. As used in this disclosure of embodiments and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in embodiments of the present disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of embodiments of the present disclosure. The words "if" and "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination", depending on the context.
In communication systems, the wide application of 5G technology brings about a great change in aspects of people's lives. According to the prospect of the international telecommunications union (International Telecommunication Union, ITU), 5G will penetrate into various areas of future society, building an omnidirectional information ecosystem with users as the center. For example, the 5G user experience rate can reach 100Mbit/s to 1Gbit/s, and can support extreme business experiences such as mobile Virtual Reality (VR). For example, the peak rate of 5G can reach 10 Gbit/s-20 Gbit/s, and the flow density can reach 10Mbit/s/m 2 The method can support the increase of the mobile service flow by thousands of times in the future. For example, the density of 5G connection number can reach 100 ten thousand/m 2 Massive Internet of things equipment can be effectively supported. For example, the 5G transmission delay can reach millisecond order, and can meet the severe requirements of the Internet of vehicles and industrial control. For example, 5G can support a moving speed of 500km/h, and can meet a good user experience in a high-speed railway environment. It follows that 5G as a new infrastructure representative will reconstruct future information-based society.
In recent years, AI technology has been breaking through in a number of fields. The continuous development in the fields of intelligent voice, computer vision and the like not only brings various colorful applications for the intelligent terminal, but also has wide application in a plurality of fields of education, traffic, home, medical treatment, retail, security and the like, brings convenience to life of people, and simultaneously promotes industry upgrading of various industries. AI technology is also accelerating cross-penetration with other discipline fields, and its development incorporates knowledge of different disciplines while also providing new directions and methods for development of different disciplines.
In the third generation partnership project 3GPP (3 rd Generation Partnership Project,) 3GPP Release 18 phase, a research project on artificial intelligence technology in the radio air interface was set up in the radio access network RAN 1. The project aims at researching how to introduce artificial intelligence technology into a wireless air interface and discussing how the artificial intelligence technology assists in improving the transmission technology of the wireless air interface. Fig. 1 is an exemplary schematic diagram of an artificial intelligence framework in a wireless air interface according to an embodiment of the present disclosure. As shown in fig. 1, the flow may include, for example, data collection (Data collection); training data (training data); model training (model training); model deployment or update (Model discover/Updata); inferential data (information data); model inference (Model reference); an Output (Output); model performance feedback (Model performance feedback); an (Actor) actuator and Feedback (Feedback).
And, in one embodiment of the present disclosure, in AI operation, a procedure involved in the terminal device side includes at least one of the following:
collecting training data;
training a model;
model transmission;
monitoring the model reasoning performance;
Fine tuning of AI model (fine tuning);
reasoning of the AI model;
and updating the model.
An operation configuration method, apparatus, device and storage medium provided by embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a method for configuring an operation, which is provided in an embodiment of the present disclosure, and the method is executed by a network side device, as shown in fig. 2, and the method may include the following steps:
step 201, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
and 202, according to the capability information set, sending operation configuration aiming at the AI model to the terminal equipment.
It is noted that in one embodiment of the present disclosure, a terminal device may be a device that provides voice and/or data connectivity to a user. The terminal device may communicate with one or more core networks via a RAN (Radio Access Network ), and may be an internet of things terminal, such as a sensor device, a mobile phone (or "cellular" phone), and a computer with an internet of things terminal, for example, a fixed, portable, pocket, hand-held, computer-built-in, or vehicle-mounted device. Such as a Station (STA), subscriber unit (subscriber unit), subscriber Station (subscriber Station), mobile Station (mobile), remote Station (remote Station), access point, remote terminal (remote), access terminal (access terminal), user device (user terminal), or user agent (user agent). Alternatively, the terminal device may be a device of an unmanned aerial vehicle. Or, the terminal device may be a vehicle-mounted device, for example, a vehicle-mounted computer with a wireless communication function, or a wireless terminal externally connected with the vehicle-mounted computer. Alternatively, the terminal device may be a roadside device, for example, a street lamp, a signal lamp, or other roadside devices having a wireless communication function.
It should be noted that, in one embodiment of the present disclosure, the terminal device refers to a terminal device that communicates with the location management function entity LMF, and the first terminal device is merely used to indicate a terminal device that communicates with the LMF, and the terminal device is not specifically referred to as a certain fixed terminal device.
Wherein, in one embodiment of the disclosure, according to the capability information set, sending an operation configuration for the AI model to the terminal device includes:
and transmitting training configuration for the AI model to the terminal device according to the training capability information in response to the capability information set including training capability information for the AI model.
Illustratively, in one embodiment of the present disclosure, wherein the training configuration for the AI model comprises at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment.
Wherein, in one embodiment of the disclosure, the method further comprises:
and training the AI model to obtain a trained AI model in response to the capability information set not including training capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the training capability information is used to determine a capability parameter of the terminal device to train the AI model.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
in response to the capability information set including inference capability information for the AI model, an inference configuration for the AI model is sent to the terminal device in accordance with the inference capability information.
Illustratively, in one embodiment of the present disclosure, wherein the inference configuration for the AI model comprises at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
And, in one embodiment of the present disclosure, the method further comprises:
and in response to the capability information set not including the reasoning capability information for the AI model, reasoning the AI model to obtain the AI model after reasoning.
Wherein in one embodiment of the present disclosure, the inference capability information is used to determine capability parameters for the terminal device to infer the AI model.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
in response to the set of capability information including transmission capability information for the AI model, a transmission configuration for the AI model is sent to the terminal device in accordance with the transmission capability information.
Wherein, in one embodiment of the disclosure, the transmission capability information is used to determine a capability parameter of the terminal device for transmitting the AI model.
And in one embodiment of the disclosure, sending a transmission configuration for the AI model to a terminal device includes at least one of:
transmitting deployment configuration for the AI model to the terminal device, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
and sending the uploading configuration for the AI model to the terminal equipment.
And in one embodiment of the present disclosure, after transmitting the upload configuration for the AI model to the terminal apparatus, further comprising:
and receiving an AI model corresponding to the uploading configuration sent by the terminal equipment.
Illustratively, in one embodiment of the present disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
In response to the capability information set including updated capability information for the AI model, an updated configuration for the AI model is sent to the terminal device in accordance with the updated capability information.
And, in one embodiment of the present disclosure, the method further comprises:
and updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the update capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
in response to the capability information set including fine-tuning capability information for the AI model, a fine-tuning configuration for the AI model is sent to the terminal device in accordance with the fine-tuning capability information.
And, in one embodiment of the present disclosure, the method further comprises:
and in response to the capability information set not including the fine-tuning capability information for the AI model, fine-tuning the AI model to obtain a fine-tuned AI model.
Wherein, in one embodiment of the present disclosure, the fine-tuning capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
in response to the capability information set including data collection capability information for the AI model, a data collection configuration for the AI model is sent to the terminal device in accordance with the data collection capability information.
In one implementation, the set of capability information is used to indicate capability information of the terminal device to operate with respect to the AI model.
And, in one embodiment of the present disclosure, the method further comprises:
and in response to the capability information set not including the data collection capability information for the AI model, performing data collection on the AI model to obtain data corresponding to the AI model.
Wherein, in one embodiment of the present disclosure, the data collection capability information is used to indicate capability parameters of the terminal device for data collection of the AI model.
And in one embodiment of the disclosure, transmitting an operational configuration for the AI model to the terminal device in accordance with the set of capability information, comprising:
and sending the performance monitoring configuration for the AI model to the terminal device according to the performance monitoring capability information in response to the capability information set including the performance monitoring capability information for the AI model.
Wherein, in one embodiment of the disclosure, the performance monitoring capability information is used to indicate a capability parameter of the terminal device for performance monitoring of the AI model.
And, in one embodiment of the present disclosure, the method further comprises:
and in response to the capability information set not including performance monitoring capability information for the AI model, performing performance monitoring on the AI model.
And, in one embodiment of the present disclosure, a set of capability information includes at least one of:
generic capability information for AI models;
use case specific capability information for AI model.
And, in one embodiment of the present disclosure, the generic capability information includes at least one of:
the terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
the terminal device supports the capability information of model reasoning.
Illustratively, in one embodiment of the present disclosure, the generic capability information is used to indicate capability information that is generic for all usage scenario cases.
And, in one embodiment of the present disclosure, use case specific capability information, including at least one of:
Data collection capability information;
model performance monitoring capability information.
Illustratively, in one embodiment of the present disclosure, the case-specific capability information is used to indicate capability information specific to only a certain AI case.
And, in one embodiment of the present disclosure, data collection capability information, including at least one of:
data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
In summary, in the embodiments of the present disclosure, by receiving the capability information set sent by the terminal device for the AI model, the operation configuration for the AI model is sent to the terminal device according to the capability information set. In the embodiment of the disclosure, the operation configuration for the AI model is determined through the capability information set sent by the terminal equipment, so that the matching performance of the operation performed by the terminal equipment for the AI model and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal equipment cannot perform operation for the AI model is reduced. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 3 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 3, the method may include the following steps:
step 301, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
the following steps are alternatively executed:
step 302, responding to the capability information set to comprise training capability information aiming at an AI model, and sending training configuration aiming at the AI model to the terminal equipment according to the training capability information;
and 303, training the AI model to obtain a trained AI model in response to the capability information set not including the training capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the training capability information is used to determine a capability parameter of the terminal device to train the AI model.
And, in one embodiment of the present disclosure, training configuration for AI models, comprising at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment.
Wherein, in one embodiment of the present disclosure, the capability information set refers to a collective body formed by gathering capability information. The capability information set does not refer specifically to a certain fixed information set. For example, when the capability information included in the capability information set changes, the capability information set may also change accordingly. For example, when the amount of capability information included in the capability information set changes, the capability information set may also change accordingly.
For example, in one embodiment of the present disclosure, when the network side device acquires a capability information set that is received from the terminal device and sent for the AI model, the network side device may determine whether training capability information for the AI model is included in the capability information set. In response to the set of capability information including training capability information for the AI model, the network side device may send training configuration for the AI model to the terminal device in accordance with the training capability information. In response to the capability information set not including training capability information for the AI model, the network side device may train the AI model to obtain a trained AI model.
And, in one embodiment of the present disclosure, the training configuration refers to a configuration for instructing the terminal device to participate in training of the AI model. When the training configuration includes a configuration in which the AI model is trained by the terminal device alone, only the terminal device model-trains the AI model. When the training configuration includes a configuration in which the network side device and the terminal device jointly train the AI model, it may be that the terminal device and the network side device jointly train the AI model.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the training capability information for the AI model, the training configuration for the AI model is sent to the terminal device according to the training capability information; and training the AI model to obtain a trained AI model in response to the capability information set not including training capability information for the AI model. In the embodiment of the disclosure, the training configuration for the AI model is determined through the training capability information sent by the terminal equipment, so that the matching performance of the training operation performed by the terminal equipment and the training capability information can be improved, the accuracy of the training operation determination for the AI model can be improved, and the situation that the terminal equipment cannot perform the training operation is reduced. In embodiments of the present disclosure, a scheme for determining a training configuration based on training capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 4 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 4, the method may include the following steps:
step 401, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
the following steps are alternatively executed:
step 402, responding to the capability information set to comprise the reasoning capability information aiming at the AI model, and sending reasoning configuration aiming at the AI model to the terminal equipment according to the reasoning capability information;
and step 403, in response to the capability information set not including the reasoning capability information for the AI model, reasoning the AI model to obtain the AI model after reasoning.
Wherein in one embodiment of the present disclosure, the inference capability information is used to determine capability parameters for the terminal device to infer the AI model.
And, in one embodiment of the present disclosure, the inference configuration for the AI model includes at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
And, in one embodiment of the present disclosure, the inferential configuration is not specific to a fixed configuration, e.g., when the configuration information included in the inferential configuration changes, the inferential configuration may also change accordingly.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, if the capability information set includes the inference capability information for the AI model, the terminal device sends the inference configuration for the AI model according to the inference capability information, and if the capability information set does not include the inference capability information for the AI model, the AI model is inferred, so as to obtain the inferred AI model. In the embodiment of the disclosure, the inference configuration is determined through the inference capability information sent by the terminal equipment, so that the matching performance of the inference operation performed by the terminal equipment and the inference capability information can be improved, the accuracy of the inference operation determination can be improved, and the situation that the terminal equipment cannot perform the inference operation is reduced. In embodiments of the present disclosure, a scheme for determining AI reasoning configuration based on reasoning capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 5 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 5, the method may include the following steps:
step 501, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
step 502, in response to the capability information set including transmission capability information for the AI model, transmitting a transmission configuration for the AI model to the terminal device according to the transmission capability information.
Wherein, in one embodiment of the disclosure, the transmission capability information is used to determine a capability parameter of the terminal device for transmitting the AI model.
And, in one embodiment of the present disclosure, the transmission configuration may include at least one of a deployment configuration and an upload configuration, for example. That is, the transmission configuration does not refer to a fixed configuration. The transmission configuration may include, for example, only a deployment configuration, only an upload configuration, and both a transmission configuration and an upload configuration.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the transmission capability information for the AI model, the transmission configuration for the AI model is sent to the terminal device according to the transmission capability information. In the embodiment of the disclosure, the AI transmission configuration is determined through the transmission capability information sent by the terminal equipment, so that the matching performance of AI transmission operation and reasoning capability information performed by the terminal equipment can be improved, the accuracy of AI transmission operation determination can be improved, and the situation that the terminal equipment cannot perform transmission operation is reduced. In the embodiments of the present disclosure, a scheme of determining an AI transmission configuration based on AI transmission capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 6 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 6, the method may include the following steps:
step 601, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
wherein, in response to the capability information set including the transmission capability information for the AI model, the transmitting configuration for the AI model to the terminal device according to the transmission capability information includes at least one of the following steps, that is, the following steps may be alternatively performed, or may be simultaneously performed:
step 602, responding to the capability information set to comprise transmission capability information aiming at an AI model, and sending deployment configuration aiming at the AI model to a terminal device according to the transmission capability information, wherein the deployment configuration comprises configuration aiming at updating model parameters of the AI model;
step 603, in response to the capability information set including the transmission capability information for the AI model, sending an upload configuration for the AI model to the terminal device according to the transmission capability information.
Among other things, in one embodiment of the present disclosure, a deployment configuration for an AI model includes at least one of:
Deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
Illustratively, in one embodiment of the present disclosure, according to the deployment configuration, the terminal device may deploy an AI model corresponding to the deployment configuration in the terminal device, and the terminal device may only support model parameter updating for the AI model.
And in one embodiment of the disclosure, the network side device sends an upload configuration for the AI model to the terminal device according to the transmission capability information, where the upload configuration is used to instruct the terminal device to upload the AI model corresponding to the upload configuration. The upload configuration is not particularly limited to a fixed configuration. For example, when the AI model configured by the upload configuration changes, the upload configuration may also change accordingly.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the transmission capability information for the AI model, a deployment configuration for the AI model is sent to the terminal device according to the transmission capability information, where the deployment configuration includes a configuration for updating the model parameters for the AI model; and transmitting an uploading configuration for the AI model to the terminal device according to the transmission capability information in response to the capability information set comprising the transmission capability information for the AI model. In the embodiment of the disclosure, the transmission configuration is determined through the transmission capability information sent by the terminal equipment, so that the matching performance of the transmission operation performed by the terminal equipment and the transmission capability information can be improved, the accuracy of the determination of the transmission operation can be improved, and the situation that the terminal equipment cannot perform the transmission operation is reduced. In the embodiments of the present disclosure, a scheme in which a transmission configuration includes a deployment configuration and an upload configuration is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 7 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 7, the method may include the following steps:
step 701, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
step 702, in response to the capability information set including transmission capability information for the AI model, sending an upload configuration for the AI model to the terminal device according to the transmission capability information;
step 703, receiving an AI model corresponding to the uploading configuration sent by the terminal device.
In one embodiment of the present disclosure, the AI model refers to a model corresponding to an upload configuration, and the AI model is not particularly limited to a fixed model. For example, when the upload configuration changes, the AI model may also change accordingly.
In summary, in the embodiments of the present disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the transmission capability information for the AI model, according to the transmission capability information, the upload configuration for the AI model is sent to the terminal device, and the AI model corresponding to the upload configuration sent by the terminal device is received. In the embodiment of the disclosure, the uploading configuration is determined through the transmission capability information sent by the terminal equipment, so that the matching performance of the uploading operation performed by the terminal equipment and the uploading capability information can be improved, the accuracy of the uploading operation determination can be improved, and the situation that the terminal equipment cannot perform the uploading operation is reduced. In the embodiment of the disclosure, a scheme of uploading the AI model corresponding to the uploading configuration to the network side device is specifically described, so that the accuracy of the AI model uploading can be improved. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 8 is a flowchart of a method for configuring an operation, which is provided in an embodiment of the present disclosure, and the method is executed by a network side device, as shown in fig. 8, and the method may include the following steps:
step 801, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
the following steps are alternatively executed:
step 802, in response to the capability information set including update capability information for the AI model, sending update configuration for the AI model to the terminal device according to the update capability information;
and 803, updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the update capability information is used to indicate capability parameters of the terminal device for updating the AI model.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the updated capability information for the AI model, according to the updated capability information, an update configuration for the AI model is sent to the terminal device; and updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model. In the embodiment of the disclosure, the update configuration is determined through the update capability information sent by the terminal equipment, so that the matching performance of the update operation performed by the terminal equipment and the update capability information can be improved, the accuracy of the update operation determination can be improved, and the situation that the terminal equipment cannot perform the update operation is reduced. In embodiments of the present disclosure, a scheme of determining an update configuration based on update capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 9 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 9, the method may include the following steps:
step 901, receiving a capability information set sent by a terminal device aiming at an AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;
the following steps are alternatively executed:
step 902, in response to the capability information set including fine-tuning capability information for the AI model, sending fine-tuning configuration for the AI model to the terminal device according to the fine-tuning capability information;
and step 903, performing fine tuning on the AI model to obtain a fine-tuned AI model in response to the capability information set not including fine-tuning capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the fine-tuning capability information is used to indicate capability parameters of the terminal device for updating the AI model.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the fine tuning capability information for the AI model, the fine tuning configuration for the AI model is sent to the terminal device according to the fine tuning capability information; and in response to the capability information set not including the fine-tuning capability information for the AI model, fine-tuning the AI model to obtain a fine-tuned AI model. In the embodiment of the disclosure, the trimming configuration is determined through the trimming capability information sent by the terminal equipment, so that the matching performance of the trimming operation performed by the terminal equipment and the trimming capability information can be improved, the accuracy of determining the trimming operation can be improved, and the situation that the terminal equipment cannot perform the trimming operation is reduced. In embodiments of the present disclosure, a scheme for determining a trim configuration based on trim capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 10 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 10, the method may include the following steps:
step 1001, receiving a capability information set sent by a terminal device for an AI model, where the capability information set is used to indicate capability information of the terminal device for operating for the AI model;
the following steps are alternatively executed:
step 1002, responding to the capability information set to comprise data collection capability information aiming at an AI model, and sending data collection configuration aiming at the AI model to a terminal device according to the data collection capability information;
and step 1003, in response to the capability information set not including the data collection capability information for the AI model, collecting the data of the AI model to obtain the data corresponding to the AI model.
And, in one embodiment of the present disclosure, data collection capability information, including at least one of:
data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
Wherein, in one embodiment of the present disclosure, the data collection capability information is used to indicate capability parameters of the terminal device for data collection of the AI model.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the data collection capability information for the AI model, according to the data collection capability information, sending the data collection configuration for the AI model to the terminal device; and responding to the capability information set not including the data collection capability information aiming at the AI model, carrying out data collection on the AI model to obtain the AI model after data collection. In the embodiment of the disclosure, the AI data collection configuration is determined through the data collection capability information sent by the terminal equipment, so that the matching performance of the data collection operation performed by the terminal equipment and the data collection capability information can be improved, the accuracy of determining the data collection operation can be improved, and the situation that the terminal equipment cannot perform the data collection operation is reduced. Among the embodiments of the present disclosure, a scheme for determining a data collection configuration based on data collection capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 11 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a network side device, and as shown in fig. 11, the method may include the following steps:
step 1101, receiving a capability information set sent by the terminal device for the AI model, wherein the capability information set is used for indicating capability information of the terminal device for operating for the AI model;
the following steps are alternatively executed:
step 1102, responding to the capability information set to comprise performance monitoring capability information aiming at an AI model, and sending performance monitoring configuration aiming at the AI model to terminal equipment according to the performance monitoring capability information;
and step 1103, performing performance monitoring on the AI model in response to the capability information set not including the performance monitoring capability information for the AI model.
Wherein, in one embodiment of the disclosure, the performance monitoring capability information is used to indicate a capability parameter of the terminal device for performance monitoring of the AI model.
In summary, in the embodiment of the disclosure, by receiving the capability information set sent by the terminal device for the AI model, in response to the capability information set including the capability information for monitoring the performance of the AI model, according to the capability information for monitoring the performance, sending the configuration for monitoring the performance of the AI model to the terminal device; and in response to the capability information set not including the capability information for the performance monitoring of the AI model, performing performance monitoring on the AI model to obtain the AI model after performance monitoring. In the embodiment of the disclosure, the performance monitoring configuration is determined through the performance monitoring capability information sent by the terminal equipment, so that the matching performance of the performance monitoring operation performed by the terminal equipment and the performance monitoring capability information can be improved, the accuracy of the performance monitoring operation determination can be improved, and the situation that the performance monitoring operation cannot be performed by the terminal equipment is reduced. In embodiments of the present disclosure, a scheme for determining a performance monitoring configuration based on performance monitoring capability information is specifically described. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 12 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 12, the method may include the following steps:
step 1201, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device operating against an AI model;
step 1202, receiving an operation configuration for an AI model sent by the network side device according to the capability information set.
Wherein, in one embodiment of the disclosure, receiving the operation configuration for the AI model sent by the network side device according to the capability information set includes:
and receiving training configuration for the AI model sent by the network side equipment in response to the capability information set comprising training capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the training capability information is used to determine a capability parameter of the terminal device to train the AI model.
And, in one embodiment of the present disclosure, wherein the training configuration for the AI model comprises at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
and receiving the reasoning configuration for the AI model sent by the network side equipment in response to the capability information set comprising the reasoning capability information for the AI model.
Wherein in one embodiment of the present disclosure, the inference capability information is used to determine capability parameters for the terminal device to infer the AI model.
Illustratively, in one embodiment of the present disclosure, wherein the inference configuration for the AI model comprises at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
and receiving the transmission configuration for the AI model sent by the network side equipment in response to the capability information set comprising the transmission capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the transmission capability information is used to determine a capability parameter of the terminal device for transmitting the AI model.
And in one embodiment of the disclosure, receiving a transmission configuration for an AI model sent by a network side device, including at least one of:
receiving deployment configuration for an AI model sent by network side equipment, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
and receiving the uploading configuration for the AI model sent by the network side equipment.
And in one embodiment of the disclosure, after receiving the upload configuration for the AI model sent by the network side device, further includes:
and sending the AI model corresponding to the uploading configuration to the network side equipment.
Illustratively, in one embodiment of the present disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
and receiving the updating configuration for the AI model sent by the network side equipment in response to the capability information set comprising the updating capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the update capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
and receiving fine tuning configuration for the AI model sent by the network side equipment in response to the capability information set comprising fine tuning capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the fine-tuning capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
and receiving the data collection configuration for the AI model sent by the network side equipment in response to the capability information set comprising the data collection capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the data collection capability information is used to indicate capability parameters of the terminal device for data collection of the AI model.
And in one embodiment of the disclosure, receiving an operation configuration for an AI model sent by a network side device according to a capability information set includes:
And receiving the performance monitoring configuration for the AI model sent by the network side equipment in response to the capability information set comprising the performance monitoring capability information for the AI model.
Wherein, in one embodiment of the disclosure, the performance monitoring capability information is used to indicate a capability parameter of the terminal device for performance monitoring of the AI model.
Illustratively, in one embodiment of the present disclosure, the set of capability information includes at least one of:
generic capability information for AI models;
use case specific capability information for AI model.
Illustratively, in one embodiment of the present disclosure, the generic capability information includes at least one of:
the terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
the terminal device supports the capability information of model reasoning.
Illustratively, in one embodiment of the present disclosure, the use case specific capability information includes at least one of:
data collection capability information;
model performance monitoring capability information.
Illustratively, in one embodiment of the present disclosure, the data collection capability information includes at least one of:
Data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, where the capability information set is used to indicate capability information of a terminal device operating on an AI model, and an operation configuration for the AI model sent by the network side device according to the capability information set is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 13 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 13, the method may include the following steps:
step 1301, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device for operating an AI model;
step 1302, receiving training configuration sent by the network side device for the AI model in response to the capability information set including training capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the training capability information is used to determine a capability parameter of the terminal device to train the AI model.
And, in one embodiment of the present disclosure, training configuration for AI models, comprising at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment. A step of
And in one embodiment of the disclosure, after the terminal device receives the training configuration for the AI model sent by the network side device, the terminal device may perform a training operation on the AI model based on the training configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including training capability information for an AI model, a training configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. Among the embodiments of the present disclosure, a scheme for receiving training configuration based on training capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 14 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 14, the method may include the following steps:
Step 1401, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device operating aiming at an AI model;
step 1402, in response to the capability information set including the inference capability information for the AI model, receiving an inference configuration for the AI model sent by the network side device.
Wherein in one embodiment of the present disclosure, the inference capability information is used to determine capability parameters for the terminal device to infer the AI model.
And, in one embodiment of the present disclosure, the inference configuration for the AI model includes at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
For example, in one embodiment of the present disclosure, the inference configuration received by the terminal device may be, for example, a configuration in which the terminal device alone infers the AI model, and the terminal device may perform an inference operation on the AI model alone.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including inference capability information for an AI model, an inference configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. Among the embodiments of the present disclosure, a scheme for receiving inference configuration based on inference capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 15 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 15, the method may include the following steps:
step 1501, transmitting a capability information set to a network side device, where the capability information set is used to indicate capability information of a terminal device operating on an AI model;
in step 1502, in response to the capability information set including the transmission capability information for the AI model, a transmission configuration sent by the network side device for the AI model is received.
Wherein, in one embodiment of the disclosure, the transmission capability information is used to determine a capability parameter of the terminal device for transmitting the AI model.
And in one embodiment of the disclosure, receiving a transmission configuration for an AI model sent by a network side device, including at least one of:
receiving deployment configuration for an AI model sent by network side equipment, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
and receiving the uploading configuration for the AI model sent by the network side equipment.
And in one embodiment of the disclosure, after receiving the upload configuration for the AI model sent by the network side device, further includes:
And sending the AI model corresponding to the uploading configuration to the network side equipment.
Illustratively, in one embodiment of the present disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
And in one embodiment of the disclosure, after the terminal device receives the deployment configuration for the AI model sent by the network side device, the terminal device may deploy the AI model corresponding to the deployment configuration in the terminal device based on the deployment configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including transmission capability information for an AI model, a transmission configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. In an embodiment of the present disclosure, a scheme for receiving a transmission configuration based on transmission capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 16 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 16, the method may include the following steps:
1601, transmitting a capability information set to a network side device, where the capability information set is used to indicate capability information of a terminal device operating on an AI model;
step 1602, in response to the capability information set including updated capability information for the AI model, receives an updated configuration for the AI model sent by the network side device.
Wherein, in one embodiment of the present disclosure, the update capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, after the terminal device receives the update configuration for the AI model sent by the network side device, the terminal device may perform an update operation on the AI model based on the update configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including update capability information for an AI model, an update configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. In embodiments of the present disclosure, a scheme for receiving an AI update configuration based on AI update capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 17 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 17, the method may include the following steps:
step 1701, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device for operating an AI model;
step 1702, in response to the capability information set including fine-tuning capability information for the AI model, receiving fine-tuning configuration for the AI model sent by the network side device.
Wherein, in one embodiment of the present disclosure, the fine-tuning capability information is used to indicate capability parameters of the terminal device for updating the AI model.
And in one embodiment of the disclosure, after the terminal device receives the fine tuning configuration for the AI model sent by the network side device, the terminal device may perform a fine tuning operation on the AI model based on the fine tuning configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including AI fine-tuning capability information for an AI model, fine-tuning configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. Among the embodiments of the present disclosure, a scheme for receiving a fine tuning configuration based on fine tuning capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 18 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 18, the method may include the following steps:
step 1801, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device for operating an AI model;
step 1802, receiving a data collection configuration for the AI model sent by the network side device in response to the capability information set including data collection capability information for the AI model.
Wherein, in one embodiment of the present disclosure, the data collection capability information is used to indicate capability parameters of the terminal device for data collection of the AI model.
And in one embodiment of the disclosure, after the terminal device receives the data collection configuration for the AI model sent by the network side device, the terminal device may collect data corresponding to the AI model based on the data collection configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, and in response to the capability information set including AI data collection capability information for an AI model, a data collection configuration for the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. Among the embodiments of the present disclosure, a scheme for receiving a data collection configuration based on data collection capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 19 is a flowchart of an operation configuration method provided by an embodiment of the present disclosure, where the method is performed by a terminal device, and as shown in fig. 19, the method may include the following steps:
step 1901, transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of a terminal device operating aiming at an AI model;
and step 1902, receiving performance monitoring configuration sent by the network side equipment aiming at the AI model in response to the capability information set comprising the performance monitoring capability information aiming at the AI model.
Wherein, in one embodiment of the disclosure, the performance monitoring capability information is used to indicate a capability parameter of the terminal device for performance monitoring of the AI model.
And in one embodiment of the disclosure, after the terminal device receives the performance monitoring configuration for the AI model sent by the network side device, the terminal device may perform a performance monitoring operation on the AI model based on the fine tuning configuration.
In summary, in the embodiments of the present disclosure, a capability information set is sent to a network side device, where the capability information set is used to indicate capability information of a terminal device operating on an AI model, and in response to the capability information set including AI performance monitoring capability information on the AI model, a performance monitoring configuration on the AI model sent by the network side device is received. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. Among the embodiments of the present disclosure, a scheme for receiving performance monitoring configuration based on performance monitoring capability information is specifically disclosed. The disclosure provides a processing method for the situation of 'operation configuration', so as to determine the operation of the terminal equipment on the basis of the capability of the terminal equipment on the basis of the AI model, improve the accuracy of the operation determination on the AI model, and improve the matching between the operation on the AI model and the capability of the terminal equipment.
Fig. 20 is a schematic structural diagram of an operation configuration device according to an embodiment of the disclosure, as shown in fig. 20, the device 2000 may include:
a receiving module 2001, configured to receive a capability information set sent by a terminal device for an AI model, where the capability information set is used to indicate capability information of the terminal device for operating for the AI model;
and the sending module 2002 is used for sending the operation configuration for the AI model to the terminal equipment according to the capability information set.
In summary, in the operation configuration apparatus according to the embodiments of the present disclosure, the receiving module may receive a capability information set sent by the terminal device for the AI model, where the capability information set is used to indicate capability information of the terminal device for operating the AI model, and the sending module may send, according to the capability information set, operation configuration for the AI model to the terminal device. In the embodiment of the disclosure, the operation configuration for the AI model is determined through the capability information set sent by the terminal equipment, so that the matching performance of the operation performed by the terminal equipment and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal equipment cannot perform the operation is reduced. The present disclosure provides a processing apparatus for the case of "operation configuration" to determine an operation performed by a terminal device with respect to an AI model based on capabilities supported by the terminal device with respect to the AI model, improve accuracy of operation determination performed with respect to the AI model, and improve matching between the operation performed with respect to the AI model and capabilities of the terminal device.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
and transmitting training configuration for the AI model to the terminal device according to the training capability information in response to the capability information set including training capability information for the AI model.
Optionally, in one embodiment of the disclosure, the training configuration for the AI model includes at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and training the AI model to obtain a trained AI model in response to the capability information set not including training capability information for the AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
in response to the capability information set including inference capability information for the AI model, an inference configuration for the AI model is sent to the terminal device in accordance with the inference capability information.
Optionally, in one embodiment of the disclosure, the inference configuration for the AI model includes at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and in response to the capability information set not including the reasoning capability information for the AI model, reasoning the AI model to obtain the AI model after reasoning.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
in response to the set of capability information including transmission capability information for the AI model, a transmission configuration for the AI model is sent to the terminal device in accordance with the transmission capability information.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to send the transmission configuration for the AI model to the terminal device, including at least one of:
transmitting deployment configuration for the AI model to the terminal device, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
And sending the uploading configuration for the AI model to the terminal equipment.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, after sending the upload configuration for the AI model to the terminal device, further specifically configured to:
and receiving an AI model corresponding to the uploading configuration sent by the terminal equipment.
Optionally, in one embodiment of the disclosure, the deployment configuration for the AI model includes at least one of:
deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
in response to the capability information set including updated capability information for the AI model, an updated configuration for the AI model is sent to the terminal device in accordance with the updated capability information.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
in response to the capability information set including fine-tuning capability information for the AI model, a fine-tuning configuration for the AI model is sent to the terminal device in accordance with the fine-tuning capability information.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and in response to the capability information set not including the fine-tuning capability information for the AI model, fine-tuning the AI model to obtain a fine-tuned AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
in response to the capability information set including data collection capability information for the AI model, a data collection configuration for the AI model is sent to the terminal device in accordance with the data collection capability information.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and in response to the capability information set not including the data collection capability information for the AI model, performing data collection on the AI model to obtain data corresponding to the AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is configured to, when sending the operation configuration for the AI model to the terminal device according to the capability information set, specifically configured to:
and sending the performance monitoring configuration for the AI model to the terminal device according to the performance monitoring capability information in response to the capability information set including the performance monitoring capability information for the AI model.
Optionally, in one embodiment of the disclosure, the sending module 2002 is further configured to:
and in response to the capability information set not including performance monitoring capability information for the AI model, performing performance monitoring on the AI model.
Optionally, in one embodiment of the disclosure, the set of capability information includes at least one of:
generic capability information for AI models;
use case specific capability information for AI model.
Optionally, in one embodiment of the present disclosure, the generic capability information includes at least one of:
the terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
The terminal device supports the capability information of model reasoning.
Optionally, in one embodiment of the disclosure, the use case specific capability information includes at least one of:
data collection capability information;
model performance monitoring capability information.
Optionally, in one embodiment of the present disclosure, the data collection capability information includes at least one of:
data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
Fig. 21 is a schematic structural diagram of an operation configuration device according to an embodiment of the disclosure, as shown in fig. 21, the device 2100 may include:
a transmitting module 2101, configured to transmit a capability information set to a network side device, where the capability information set is used to indicate capability information that a terminal device operates with respect to an AI model;
and a receiving module 2102, configured to receive an operation configuration for the AI model sent by the network side device according to the capability information set.
In summary, in the operation configuration apparatus according to the embodiments of the present disclosure, the sending module may send a capability information set to the network side device, where the capability information set is used to indicate capability information of the terminal device for operating the AI model, and the receiving module may receive an operation configuration for the AI model sent by the network side device according to the capability information set. In the embodiment of the disclosure, the operation configuration for the AI model can be received by sending the capability information set to the network side device, so that the matching performance of the operation performed by the terminal device and the capability information set can be improved, the accuracy of the operation determination performed for the AI model can be improved, and the situation that the terminal device cannot perform the operation is reduced. The present disclosure provides a processing apparatus for the case of "operation configuration" to determine an operation performed by a terminal device with respect to an AI model based on capabilities supported by the terminal device with respect to the AI model, improve accuracy of operation determination performed with respect to the AI model, and improve matching between the operation performed with respect to the AI model and capabilities of the terminal device.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving training configuration for the AI model sent by the network side equipment in response to the capability information set comprising training capability information for the AI model.
Optionally, in one embodiment of the disclosure, the training configuration for the AI model includes at least one of:
the terminal equipment is used for independently configuring the AI model for training;
and jointly training the AI model by the network side equipment and the terminal equipment.
Optionally, in one embodiment of the disclosure, the receiving module 2102 is configured to receive an operation configuration for an AI model sent by a network side device according to a capability information set, and is specifically configured to:
and receiving the reasoning configuration for the AI model sent by the network side equipment in response to the capability information set comprising the reasoning capability information for the AI model.
Optionally, in one embodiment of the disclosure, the inference configuration for the AI model includes at least one of:
the terminal equipment independently carries out the reasoning configuration on the AI model;
And the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving the transmission configuration for the AI model sent by the network side equipment in response to the capability information set comprising the transmission capability information for the AI model.
Optionally, in one embodiment of the disclosure, the receiving module 2102 is configured to receive a transmission configuration for an AI model sent by a network side device, including at least one of:
receiving deployment configuration for an AI model sent by network side equipment, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;
and receiving the uploading configuration for the AI model sent by the network side equipment.
Optionally, in one embodiment of the disclosure, the sending module 2101 is configured to, after receiving the upload configuration for the AI model sent by the network side device, further be configured to:
and sending the AI model corresponding to the uploading configuration to the network side equipment.
Optionally, in one embodiment of the disclosure, the deployment configuration for the AI model includes at least one of:
Deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;
deployment configuration of AI models for a model structure.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving the updating configuration for the AI model sent by the network side equipment in response to the capability information set comprising the updating capability information for the AI model.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving fine tuning configuration for the AI model sent by the network side equipment in response to the capability information set comprising fine tuning capability information for the AI model.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving the data collection configuration for the AI model sent by the network side equipment in response to the capability information set comprising the data collection capability information for the AI model.
Optionally, in one embodiment of the present disclosure, the receiving module 2102 is configured to receive, when the network side device sends an operation configuration for the AI model according to the capability information set, specifically configured to:
and receiving the performance monitoring configuration for the AI model sent by the network side equipment in response to the capability information set comprising the performance monitoring capability information for the AI model.
Optionally, in one embodiment of the disclosure, the set of capability information includes at least one of:
generic capability information for AI models;
use case specific capability information for AI model.
Optionally, in one embodiment of the present disclosure, the generic capability information includes at least one of:
the terminal equipment supports the capability information of AI model training;
the terminal equipment supports the capability information of the fine adjustment of the model;
the terminal equipment supports the downloading or uploading capability information of the model;
the terminal equipment supports the capability information of model updating;
the terminal device supports the capability information of model reasoning.
Optionally, in one embodiment of the disclosure, the use case specific capability information includes at least one of:
data collection capability information;
model performance monitoring capability information.
Optionally, in one embodiment of the present disclosure, the data collection capability information includes at least one of:
data collection capability information enhanced for channel state information CSI;
data collection capability information for beam management;
capability information is collected for data of the positioning information.
Fig. 22 is a block diagram of a terminal device UE2200 provided in one embodiment of the present disclosure. For example, the UE2200 may be a mobile phone, a computer, a digital broadcast terminal device, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, or the like.
Referring to fig. 22, the ue2200 may include at least one of the following components: a processing component 2202, a memory 2204, a power component 2206, a multimedia component 2208, an audio component 2210, an input/output (I/O) interface 2212, a sensor component 2214, and a communication component 2216.
The processing component 2202 generally controls overall operation of the UE2200, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 2202 may include at least one processor 2220 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 2202 may include at least one module to facilitate interaction between the processing component 2202 and other components. For example, the processing component 2202 may include a multimedia module to facilitate interaction between the multimedia component 2208 and the processing component 2202.
The memory 2204 is configured to store various types of data to support operations at the UE 2200. Examples of such data include instructions for any application or method operating on the UE2200, contact data, phonebook data, messages, pictures, videos, and the like. The memory 2204 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 2206 provides power to the various components of the UE 2200. The power supply components 2206 may include a power management system, at least one power supply, and other components associated with generating, managing, and distributing power for the UE 2200.
The multimedia component 2208 includes a screen between the UE2200 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes at least one touch sensor to sense touch, swipe, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also a wake-up time and pressure associated with the touch or slide operation. In some embodiments, the multimedia assembly 2208 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the UE2200 is in an operation mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 2210 is configured to output and/or input audio signals. For example, the audio component 2210 includes a Microphone (MIC) configured to receive external audio signals when the UE2200 is in an operation mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in memory 2204 or transmitted via communication component 2216. In some embodiments, the audio component 2210 also includes a speaker for outputting audio signals.
The I/O interface 2212 provides an interface between the processing component 2202 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor component 2214 includes at least one sensor for providing status assessment of various aspects to the UE 2200. For example, the sensor component 2214 may detect an on/off state of the device 2200, a relative positioning of components such as a display and keypad of the UE2200, the sensor component 2214 may also detect a change in position of the UE2200 or one of the components of the UE2200, the presence or absence of user contact with the UE2200, an azimuth or acceleration/deceleration of the UE2200, and a change in temperature of the UE 2200. The sensor assembly 2214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 2214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 2214 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 2216 is configured to facilitate wired or wireless communication between the UE2200 and other devices. The UE2200 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication component 2216 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 2216 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the UE2200 may be implemented by at least one Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic components for performing the above-described methods.
Fig. 23 is a block diagram of a network side device 2300 provided by an embodiment of the disclosure. For example, the network-side device 2300 may be provided as a network-side device. Referring to fig. 23, network-side device 2300 includes a processing component 2322 that further includes at least one processor, and memory resources represented by memory 2332 for storing instructions, such as applications, executable by processing component 2322. The applications stored in memory 2332 may include one or more modules each corresponding to a set of instructions. Furthermore, the processing component 2322 is configured to execute instructions to perform any of the methods described above as applied to the network-side device, for example, as shown in fig. 1.
The network-side device 2300 may also include a power component 2326 configured to perform power management of the network-side device 2300, a wired or wireless network interface 2350 configured to connect the network-side device 2300 to a network, and an input/output (I/O) interface 2358. Network side device 2300 may operate based on an operating system stored in memory 2332, such as Windows Server TM, mac OS XTM, unix (TM), linux (TM), free BSDTM, or the like.
In the embodiments provided in the present disclosure, the method provided in the embodiments of the present disclosure is described from the perspective of the network side device and the UE, respectively. In order to implement the functions in the method provided by the embodiments of the present disclosure, the network side device and the UE may include a hardware structure, a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Some of the functions described above may be implemented in a hardware structure, a software module, or a combination of a hardware structure and a software module.
In the embodiments provided in the present disclosure, the method provided in the embodiments of the present disclosure is described from the perspective of the network side device and the UE, respectively. In order to implement the functions in the method provided by the embodiments of the present disclosure, the network side device and the UE may include a hardware structure, a software module, and implement the functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. Some of the functions described above may be implemented in a hardware structure, a software module, or a combination of a hardware structure and a software module.
The embodiment of the disclosure provides a communication device. The communication device may include a transceiver module and a processing module. The transceiver module may include a transmitting module and/or a receiving module, where the transmitting module is configured to implement a transmitting function, the receiving module is configured to implement a receiving function, and the transceiver module may implement the transmitting function and/or the receiving function.
The communication device may be a terminal device (such as the terminal device in the foregoing method embodiment), or may be a device in the terminal device, or may be a device that can be used in a matching manner with the terminal device. Alternatively, the communication device may be a network device, a device in the network device, or a device that can be used in cooperation with the network device.
Another communication apparatus provided by an embodiment of the present disclosure. The communication device may be a network device, or may be a terminal device (such as the terminal device in the foregoing method embodiment), or may be a chip, a chip system, or a processor that supports the network device to implement the foregoing method, or may be a chip, a chip system, or a processor that supports the terminal device to implement the foregoing method. The device can be used for realizing the method described in the method embodiment, and can be particularly referred to the description in the method embodiment.
The communication device may include one or more processors. The processor may be a general purpose processor or a special purpose processor, etc. For example, a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processor may be used to control communication apparatuses (e.g., network side devices, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute computer programs, and process data of the computer programs.
Optionally, the communication device may further include one or more memories, on which a computer program may be stored, and the processor executes the computer program, so that the communication device performs the method described in the above method embodiments. Optionally, the memory may also store data therein. The communication device and the memory may be provided separately or may be integrated.
Optionally, the communication device may further comprise a transceiver, an antenna. The transceiver may be referred to as a transceiver unit, transceiver circuitry, or the like, for implementing the transceiver function. The transceiver may include a receiver, which may be referred to as a receiver or a receiving circuit, etc., for implementing a receiving function, and a transmitter; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., for implementing a transmitting function.
Optionally, one or more interface circuits may also be included in the communication device. The interface circuit is used for receiving the code instruction and transmitting the code instruction to the processor. The processor executes the code instructions to cause the communication device to perform the method described in the method embodiments above.
The communication device is a network side device: the processor is configured to perform the method shown in any of figures 2-11.
The communication device is a terminal device (such as the terminal device in the foregoing method embodiment): the processor is configured to perform the method shown in any one of fig. 12-19.
In one implementation, a transceiver for implementing the receive and transmit functions may be included in the processor. For example, the transceiver may be a transceiver circuit, or an interface circuit. The transceiver circuitry, interface or interface circuitry for implementing the receive and transmit functions may be separate or may be integrated. The transceiver circuit, interface or interface circuit may be used for reading and writing codes/data, or the transceiver circuit, interface or interface circuit may be used for transmitting or transferring signals.
In one implementation, a processor may have a computer program stored thereon, which, when executed on the processor, may cause a communication device to perform the method described in the method embodiments above. The computer program may be solidified in the processor, in which case the processor may be implemented in hardware.
In one implementation, a communication device may include circuitry that may implement the functions of transmitting or receiving or communicating in the foregoing method embodiments. The processors and transceivers described in this disclosure may be implemented on integrated circuits (integrated circuit, ICs), analog ICs, radio frequency integrated circuits RFICs, mixed signal ICs, application specific integrated circuits (application specific integrated circuit, ASIC), printed circuit boards (printed circuit board, PCB), electronic devices, and the like. The processor and transceiver may also be fabricated using a variety of IC process technologies such as complementary metal oxide semiconductor (complementary metal oxide semiconductor, CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (bipolar junction transistor, BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.
The communication apparatus described in the above embodiment may be a network device or a terminal device (such as the terminal device in the foregoing method embodiment), but the scope of the communication apparatus described in the present disclosure is not limited thereto, and the structure of the communication apparatus may not be limited. The communication means may be a stand-alone device or may be part of a larger device. For example, the communication device may be:
(1) A stand-alone integrated circuit IC, or chip, or a system-on-a-chip or subsystem;
(2) A set of one or more ICs, optionally also comprising storage means for storing data, a computer program;
(3) An ASIC, such as a Modem (Modem);
(4) Modules that may be embedded within other devices;
(5) A receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handset, a mobile unit, a vehicle-mounted device, a network device, a cloud device, an artificial intelligent device, and the like;
(6) Others, and so on.
In the case where the communication device may be a chip or a system of chips, the chip includes a processor and an interface. The number of the processors may be one or more, and the number of the interfaces may be a plurality.
Optionally, the chip further comprises a memory for storing the necessary computer programs and data.
Those of skill in the art will further appreciate that the various illustrative logical blocks (illustrative logical block) and steps (step) described in connection with the embodiments of the disclosure may be implemented by electronic hardware, computer software, or combinations of both. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation is not to be understood as beyond the scope of the embodiments of the present disclosure.
The present disclosure also provides a readable storage medium having instructions stored thereon which, when executed by a computer, perform the functions of any of the method embodiments described above.
The present disclosure also provides a computer program product which, when executed by a computer, performs the functions of any of the method embodiments described above.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, the flow or functions described in accordance with the embodiments of the present disclosure are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer program may be stored in or transmitted from one computer readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means from one website, computer, server, or data center. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
Those of ordinary skill in the art will appreciate that: the various numbers of first, second, etc. referred to in this disclosure are merely for ease of description and are not intended to limit the scope of embodiments of this disclosure, nor to indicate sequencing.
At least one of the present disclosure may also be described as one or more, a plurality may be two, three, four or more, and the present disclosure is not limited. In the embodiment of the disclosure, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "a", "B", "C", and "D", and the technical features described by "first", "second", "third", "a", "B", "C", and "D" are not in sequence or in order of magnitude.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (48)
- A method of operational configuration, the method being performed by a network-side device, the method comprising:receiving a capability information set sent by a terminal device aiming at an artificial intelligent AI model, wherein the capability information set is used for indicating capability information of the terminal device aiming at the AI model;and according to the capability information set, sending operation configuration aiming at the AI model to the terminal equipment.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:and in response to the capability information set comprising training capability information for the AI model, transmitting training configuration for the AI model to the terminal device according to the training capability information.
- The method of claim 2, wherein the training configuration for the AI model comprises at least one of:Configuration of training the AI model solely by the terminal device;and jointly training the AI model by the network side equipment and the terminal equipment.
- The method according to claim 1, wherein the method further comprises:and training the AI model to obtain a trained AI model in response to the capability information set not including the training capability information for the AI model.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:and in response to the capability information set comprising inference capability information for the AI model, transmitting an inference configuration for the AI model to the terminal device in accordance with the inference capability information.
- The method of claim 5, wherein the inference configuration for the AI model comprises at least one of:configuration of reasoning the AI model by the terminal device alone;and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
- The method according to claim 1, wherein the method further comprises:and in response to the capability information set not including the reasoning capability information for the AI model, reasoning the AI model to obtain a reasoning AI model.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:and in response to the capability information set comprising transmission capability information for the AI model, transmitting a transmission configuration for the AI model to the terminal device according to the transmission capability information.
- The method of claim 8, wherein the sending a transmission configuration for the AI model to the terminal device comprises at least one of:transmitting deployment configuration for the AI model to the terminal device, wherein the deployment configuration comprises configuration for updating model parameters for the AI model;and sending the uploading configuration for the AI model to the terminal equipment.
- The method of claim 9, further comprising, after the sending the upload configuration for the AI model to the terminal device:And receiving an AI model corresponding to the uploading configuration sent by the terminal equipment.
- The method of claim 9, wherein the deployment configuration for the AI model comprises at least one of:deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;deployment configuration of AI models for a model structure.
- The method of claim 1, wherein the sending an operating configuration for the AI mode to the terminal device according to the set of capability information comprises:and in response to the capability information set comprising update capability information for the AI model, sending an update configuration for the AI model to the terminal device according to the update capability information.
- The method according to claim 12, wherein the method further comprises:and updating the AI model to obtain an updated AI model in response to the capability information set not including the updated capability information for the AI model.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:And in response to the capability information set comprising fine-tuning capability information for the AI model, sending fine-tuning configuration for the AI model to the terminal device according to the fine-tuning capability information.
- The method of claim 14, wherein the method further comprises:and in response to the capability information set not including the fine-tuning capability information for the AI model, fine-tuning the AI model to obtain a fine-tuned AI model.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:and in response to the capability information set comprising data collection capability information for the AI model, transmitting a data collection configuration for the AI model to the terminal device according to the data collection capability information.
- The method of claim 16, wherein the method further comprises:and in response to the capability information set not including the data collection capability information for the AI model, performing data collection on the AI model to obtain data corresponding to the AI model.
- The method of claim 1, wherein the sending an operating configuration for the AI model to the terminal device in accordance with the set of capability information comprises:and in response to the capability information set comprising performance monitoring capability information for the AI model, sending a performance monitoring configuration for the AI model to the terminal device according to the performance monitoring capability information.
- The method of claim 18, wherein the method further comprises:performance monitoring of the AI model is performed in response to the set of capability information not including the performance monitoring capability information for the AI model.
- The method of claim 1, wherein the set of capability information comprises at least one of:generic capability information for the AI model;and specific capability information of the use case aiming at the AI model.
- The method of claim 20, wherein the generic capability information comprises at least one of:the terminal equipment supports the capability information of AI model training;the terminal equipment supports the capability information of the fine adjustment of the model;the terminal equipment supports the downloading or uploading capability information of the model;The terminal equipment supports the capability information of model updating;the terminal equipment supports the capability information of model reasoning.
- The method of claim 20, wherein the use case specific capability information comprises at least one of:data collection capability information;model performance monitoring capability information.
- The method of claim 22, wherein the data collection capability information comprises at least one of:data collection capability information enhanced for channel state information CSI;data collection capability information for beam management;capability information is collected for data of the positioning information.
- A method of operation configuration, the method being performed by a terminal device, the method comprising:transmitting a capability information set to a network side device, wherein the capability information set is used for indicating capability information of the terminal device for operating an AI model;and receiving the operation configuration for the AI model sent by the network side equipment according to the capability information set.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:And receiving training configuration sent by the network side equipment for the AI model in response to the capability information set comprising training capability information for the AI model.
- The method of claim 25, wherein the training configuration for the AI model comprises at least one of:configuration of training the AI model solely by the terminal device;and jointly training the AI model by the network side equipment and the terminal equipment.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving the reasoning configuration sent by the network side equipment for the AI model in response to the capability information set comprising the reasoning capability information for the AI model.
- The method of claim 27, wherein the inference configuration for the AI model comprises at least one of:configuration of reasoning the AI model by the terminal device alone;and the network side equipment and the terminal equipment jointly perform the inferred configuration on the AI model.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving a transmission configuration for the AI model sent by the network side equipment in response to the capability information set comprising the transmission capability information for the AI model.
- The method of claim 29, wherein the receiving the transmission configuration for the AI model sent by the network side device comprises at least one of:receiving deployment configuration sent by the network side equipment and aiming at the AI model, wherein the deployment configuration comprises configuration for updating model parameters aiming at the AI model;and receiving the uploading configuration for the AI model sent by the network side equipment.
- The method of claim 30, further comprising, after the receiving the upload configuration for the AI model sent by the network-side device:and sending the AI model corresponding to the uploading configuration to the network side equipment.
- The method of claim 30, wherein the deployment configuration for the AI model comprises at least one of:Deployment configuration for at least two AI models, wherein the model structures of the at least two AI models are different;deployment configuration of AI models for a model structure.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving updating configuration sent by the network side equipment for the AI model in response to the capability information set comprising updating capability information for the AI model.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving fine tuning configuration sent by the network side equipment for the AI model in response to the capability information set comprising fine tuning capability information for the AI model.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving the data collection configuration sent by the network side equipment for the AI model in response to the capability information set comprising the data collection capability information for the AI model.
- The method of claim 24, wherein the receiving the operational configuration for the AI model sent by the network side device according to the set of capability information comprises:and receiving performance monitoring configuration sent by the network side equipment for the AI model in response to the capability information set comprising the performance monitoring capability information for the AI model.
- The method of claim 24, wherein the set of capability information comprises at least one of:generic capability information for the AI model;and specific capability information of the use case aiming at the AI model.
- The method of claim 37, wherein the generic capability information comprises at least one of:the terminal equipment supports the capability information of AI model training;the terminal equipment supports the capability information of the fine adjustment of the model;the terminal equipment supports the downloading or uploading capability information of the model;the terminal equipment supports the capability information of model updating;the terminal equipment supports the capability information of model reasoning.
- The method of claim 37, wherein the use case specific capability information comprises at least one of:Data collection capability information;model performance monitoring capability information.
- The method of claim 39, wherein the data collection capability information comprises at least one of:data collection capability information enhanced for channel state information CSI;data collection capability information for beam management;capability information is collected for data of the positioning information.
- An operation configuration device, characterized by comprising:the terminal equipment comprises a receiving module, a processing module and a processing module, wherein the receiving module is used for receiving a capability information set sent by the terminal equipment aiming at an AI model, and the capability information set is used for indicating capability information of the terminal equipment aiming at the AI model;and the sending module is used for sending the operation configuration aiming at the AI model to the terminal equipment according to the capability information set.
- An operation configuration device, characterized by comprising:a sending module, configured to send a capability information set to a network side device, where the capability information set is used to indicate capability information that the terminal device operates with respect to an AI model;and the receiving module is used for receiving the operation configuration for the AI model sent by the network side equipment according to the capability information set.
- A network side device, characterized in that the apparatus comprises a processor and a memory, wherein the memory has stored therein a computer program, and the processor executes the computer program stored in the memory to cause the apparatus to perform the method according to any one of claims 1 to 23.
- A terminal device, characterized in that the apparatus comprises a processor and a memory, wherein the memory has stored therein a computer program, which processor executes the computer program stored in the memory to cause the apparatus to perform the method according to any of claims 24 to 40.
- A communication device, comprising: processor and interface circuit, whereinThe interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;the processor for executing the code instructions to perform the method of any one of claims 1 to 23.
- A communication device, comprising: processor and interface circuit, whereinThe interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;the processor is configured to execute the code instructions to perform the method of any one of claims 24 to 40.
- A computer readable storage medium storing instructions which, when executed, cause a method as claimed in any one of claims 1 to 23 to be implemented.
- A computer readable storage medium storing instructions which, when executed, cause a method as claimed in any one of claims 24 to 40 to be implemented.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2022/100930 WO2023245586A1 (en) | 2022-06-23 | 2022-06-23 | Operation configuration method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117643134A true CN117643134A (en) | 2024-03-01 |
Family
ID=89378923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202280002108.7A Pending CN117643134A (en) | 2022-06-23 | 2022-06-23 | Operation configuration method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117643134A (en) |
| WO (1) | WO2023245586A1 (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021142609A1 (en) * | 2020-01-14 | 2021-07-22 | Oppo广东移动通信有限公司 | Information reporting method, apparatus and device, and storage medium |
| CN113747462A (en) * | 2020-05-30 | 2021-12-03 | 华为技术有限公司 | Information processing method and related equipment |
| WO2021243619A1 (en) * | 2020-06-03 | 2021-12-09 | 北京小米移动软件有限公司 | Information transmission method and apparatus, and communication device and storage medium |
| EP4175338A4 (en) * | 2020-06-24 | 2023-07-19 | Beijing Xiaomi Mobile Software Co., Ltd. | Communication processing method, communication processing apparatus and storage medium |
| CN114745712A (en) * | 2021-01-07 | 2022-07-12 | 中国移动通信有限公司研究院 | Terminal capability-based processing method and device, terminal and network equipment |
-
2022
- 2022-06-23 CN CN202280002108.7A patent/CN117643134A/en active Pending
- 2022-06-23 WO PCT/CN2022/100930 patent/WO2023245586A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023245586A1 (en) | 2023-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113544996A (en) | Time domain window determining method, device, user equipment, base station and storage medium | |
| CN113692756A (en) | Relay determination method and device | |
| CN115004776B (en) | Position information recording method and device for successful PScell addition or replacement report | |
| CN115004775B (en) | Method and device for recording related information of successful PScell addition or replacement report | |
| CN115004764A (en) | Method and device for recording success report of PScell addition or change | |
| CN114080844B (en) | Paging grouping method, paging grouping device, terminal equipment, base station and storage medium | |
| CN115997470A (en) | Session distinguishing method and device | |
| CN115088297A (en) | Reporting method and device | |
| CN117643134A (en) | Operation configuration method and device | |
| CN115004765A (en) | Method and device for reporting successful PScell addition or replacement report | |
| CN114503688A (en) | Measurement relaxation method, equipment, storage medium and device | |
| CN114731566A (en) | Path switching method and device | |
| CN116076101A (en) | Reference signal measurement method, device, user equipment, network side equipment and storage medium | |
| CN113424485B (en) | Indication information configuration and receiving method and device, user equipment, base station and medium | |
| CN114586401B (en) | Measurement relaxation method, device, storage medium and apparatus | |
| CN117322047A (en) | Configuration management method, device, equipment and storage medium | |
| WO2023201498A1 (en) | Information storage method and apparatus, device and storage medium | |
| WO2023173254A1 (en) | Timing adjustment method/apparatus/device and storage medium | |
| EP4354786A1 (en) | Information configuration method and apparatus, user equipment, base station, and storage medium | |
| CN117322039A (en) | Measurement report sending method, measurement report receiving method and device | |
| CN117322045A (en) | Cell management method, device, equipment and storage medium | |
| CN117546595A (en) | Cell activation method, device, equipment and storage medium | |
| CN116349322A (en) | On-demand positioning reference signal PRS request method, device, user equipment, network side equipment and storage medium | |
| CN117796045A (en) | DRX period determining method and device | |
| CN116584133A (en) | Method and equipment for determining threshold value in non-contention random access CFRA (computational fluid dynamics), storage medium and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |