A method and device for managing the function of an AI model

Abstract

This application discloses an AI model function management method and device. The method includes the following steps: in a mobile communication system, determining a function identifier set, wherein the elements in the function identifier set are identifiers used as AI functions; determining downlink information, the downlink information being used to query AI model functions, the downlink information containing instructions to query the AI ​​functions identified by at least a portion of the elements in the function identifier set; and determining uplink information, the uplink information being a response to the downlink information, containing content indication information for the AI ​​functions identified by the at least a portion of the elements. This application also includes apparatus for implementing the method. This application solves the problem of low efficiency in transmitting AI model function information in the prior art.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to an AI model function management method and device. Background Technology

[0002] Mobile communication networks contain a vast amount of data resources. Utilizing artificial intelligence (AI) technology to rationally utilize and explore these 5G data resources can effectively improve mobile communication systems. Mobile communication systems face a complex and diverse array of problems, and numerous studies have demonstrated that AI-based algorithms can effectively enhance the performance of both the mobile network and wireless sides. Improving mobile system performance using AI technology has become a major direction for future network design.

[0003] When wireless communication systems utilize AI technology to enhance system performance, the management of AI models becomes crucial. To ensure system efficiency, the AI ​​model on the terminal side needs to exchange relevant functional information with the network side before use. The network side then uses this information to confirm the terminal's understanding of the AI ​​model's functionality, thereby better leveraging AI technology to improve system performance. However, current 5G standards do not support explicit AI model information transmission. Summary of the Invention

[0004] This application proposes an AI model function management method and device, which solves the problem of low efficiency in transmitting AI model-related functional information in existing technologies, and is particularly suitable for wireless communication systems.

[0005] This invention focuses on the problem of transmitting AI model-related functional information in wireless communication systems, and provides a method and apparatus to support the efficient transmission of AI model-related functional information in communication systems.

[0006] In a first aspect, embodiments of this application propose an AI model function management method, comprising the following steps:

[0007] In a mobile communication system, a set of function identifiers is determined, wherein the elements in the set of function identifiers are identifiers used as AI functions;

[0008] Determine downlink information, which is used to query AI model functions. The downlink information contains instructions to query AI functions identified by at least a portion of the elements in the function identifier set.

[0009] Determine the uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

[0010] The AI ​​model function management method of the first aspect of this application, used in a network-side device, includes the following steps:

[0011] The network-side device determines a set of function identifiers, wherein the elements in the set of function identifiers are identifiers used for AI functions;

[0012] Send downlink information, the downlink information being used to query AI model functions, the downlink information containing instructions to query AI functions identified by at least a portion of the elements in the function identifier set;

[0013] Receive uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

[0014] The AI ​​model function management method of the first aspect of this application, used in a terminal device, includes the following steps:

[0015] The terminal device determines a set of function identifiers, where the elements in the set of function identifiers are identifiers used for AI functions.

[0016] Receive downlink information, the downlink information being used to query AI model functions, the downlink information containing instructions to select AI functions identified by at least a portion of the elements in the function identifier set;

[0017] Send uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some of the elements.

[0018] In any embodiment of the first aspect of this application, the method preferably includes the downlink information being a joint indication of DCI information carried by PDCCH and higher-layer information carried by PDSCH, or indicated by the higher-layer information; the uplink information is carried by PUCCH and / or PUSCH.

[0019] In the method described in any embodiment of the first aspect of this application, preferably, the downlink information includes a time point indication for determining the uplink information transmission time.

[0020] In the method described in any embodiment of the first aspect of this application, preferably, the uplink information includes one or more AI function set confirmation indication messages; each AI function set confirmation indication message includes information confirming the AI ​​functions identified by at least a portion of the elements.

[0021] In the method described in any embodiment of the first aspect of this application, preferably, the AI ​​functions identified by the at least some of the elements constitute a set of functions required based on the set AI characteristics.

[0022] More preferably, the downlink information includes identifiers of one or more of the defined AI features. And / or, more preferably, each defined AI feature corresponds to at least one AI function set. The downlink information includes query indication information for one or more AI function sets corresponding to the defined AI features, and each AI function set query indication information includes instructions for selecting AI functions identified by at least a subset of the elements.

[0023] Secondly, embodiments of this application propose a network-side device for implementing the method described in any embodiment of the first aspect of this application. At least one module in the network-side device is configured to perform at least one of the following functions: determining the function identifier set; determining the downlink information; sending the downlink information; receiving the uplink information; and determining the uplink information.

[0024] Thirdly, embodiments of this application provide a terminal-side device for implementing the method described in any embodiment of the second aspect of this application. At least one module in the terminal-side device is configured to perform at least one of the following functions: determining the function identifier set; receiving the downlink information; determining the downlink information; determining the uplink information; and sending the uplink information.

[0025] Thirdly, this application also proposes a communication device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any embodiment of the first aspect of this application.

[0026] Fourthly, this application also proposes a computer-readable medium on which a computer program is stored, which, when executed by a processor, implements the steps of the method described in any embodiment of the first aspect of this application.

[0027] Fifthly, this application also proposes a mobile communication system comprising at least one network-side device as described in any embodiment of this application and / or at least one terminal-side device as described in any embodiment of this application.

[0028] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects:

[0029] The method and apparatus provided by this invention enable the network and terminal to exchange key information using AI models. Especially when the terminal and network need to interact with the AI ​​model based on actual conditions, this invention provides a flexible information exchange method and apparatus. It offers an effective solution for the joint management of AI-based technologies by terminals and networks, reducing overhead through flexible configuration of comprehensive information and reported information. Attached Figure Description

[0030] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0031] Figure 1 This is a flowchart illustrating an embodiment of the method of this application;

[0032] Figure 2 This is a flowchart illustrating an embodiment of the method of this application used in a network-side device;

[0033] Figure 3 This is a flowchart illustrating an embodiment of the method of this application used in a terminal-side device;

[0034] Figure 4 This is an example of downlink information including function query instructions and time point indications;

[0035] Figure 5 An example of uplink information including functional description information;

[0036] Figure 6 An example of uplink information including function set confirmation instructions and function description information;

[0037] Figure 7 An example of uplink information containing a quantity indication of multiple function sets and a content indication of multiple function sets;

[0038] Figure 8 An example of downlink information containing multiple AI features and corresponding multiple function set query instructions;

[0039] Figure 9 An embodiment in which the uplink information includes multiple function set content indications corresponding to multiple set AI characteristics;

[0040] Figure 10 An embodiment in which the uplink information includes a function set confirmation instruction corresponding to multiple set AI features;

[0041] Figure 11 This is a schematic diagram of an embodiment of a network-side device;

[0042] Figure 12 This is a schematic diagram of an embodiment of the terminal-side device;

[0043] Figure 13 This is a schematic diagram of the structure of a network-side device according to another embodiment of the present invention;

[0044] Figure 14 This is a block diagram of a terminal-side device according to another embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0046] This invention primarily provides methods and apparatuses for transmitting AI model-related functional information in existing air interface designs. The technical solutions provided by various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0047] Figure 1 This is a flowchart illustrating an embodiment of the method of this application. Figure 1 The wireless communication system used in this application is provided, which can operate in both licensed and unlicensed frequency bands. Before using the AI ​​model, the network-side equipment and the terminal-side equipment need to perform a series of information exchanges to ensure the correct use of the AI ​​model. The specific information exchange process is as follows: Figure 1 As shown.

[0048] This application proposes an AI model function management method. The network-side device and the terminal-side device first agree on a set of AI model function-related information to be exchanged, forming the function identifier set. The network-side device sends an AI model function status query to the terminal-side device (the downlink information), and the terminal-side device reports the AI ​​model function support status based on the downlink information (the uplink information). Specifically, it includes the following steps 110-130:

[0049] Step 110: In the mobile communication system, determine the set of function identifiers, wherein the elements in the set of function identifiers are identifiers used as AI functions.

[0050] The network-side device and the terminal-side device determine the set of functions required to support one or more AI-based features through the set of function identifiers. The AI ​​functions represented by the elements in the set of function identifiers include, but are not limited to: the input and output of the AI ​​model, typical scenarios in which the AI ​​model is used, typical configurations of the AI ​​model, AI model size, AI model type, and AI model inference time. For example, the AI ​​function can be named using predefined characters or according to its position in the set.

[0051] The AI ​​features of this application include, but are not limited to, AI-based positioning, AI-based beamforming, and AI-based channel information compression feedback.

[0052] Step 120: Determine downlink information, which is used to query AI model functions. The downlink information contains instructions to query AI functions identified by at least a portion of the elements in the function identifier set.

[0053] After determining and generating the downlink information, the network-side device sends the downlink information. After receiving the downlink information, the terminal-side device determines the downlink information.

[0054] The network-side device notifies the terminal-side device via downlink information to support one or more sets of functions required based on AI characteristics, wherein the downlink information includes a subset of the set of function identifiers.

[0055] Preferably, the downlink information content can be jointly indicated by the DCI information carried by the PDCCH and the higher-layer information carried by the PDSCH, or indicated by the higher-layer information alone.

[0056] The joint indication refers to the indication provided by both DCI and higher-layer RRC signaling. For example, the DCI may indicate time indication information and / or AI feature indication information in the downlink information. Other information, such as query indications for corresponding elements in the function identifier set, is indicated in the higher-layer signaling.

[0057] Preferably, the downlink information includes an indication of the time point at which the terminal responds to the downlink information.

[0058] In one specific embodiment, the downlink information includes an indication to query one or more types of AI features supported by the terminal device, used to indicate the query of AI functions identified by at least a portion of the elements corresponding to the AI ​​feature. Alternatively, the downlink information may only include indications of one or more types of AI feature-based information supported by the terminal device, and may not include query indications for corresponding elements in the function identifier set.

[0059] It should be noted that for a given AI feature, a set of functions corresponding to that AI feature can be pre-defined as a subset of the set of function identifiers in step 110. Therefore, the indication information of the AI ​​feature in the downlink information can be used to query all function items in the set of functions corresponding to that AI feature.

[0060] When an AI feature corresponds to multiple function sets, and each function set is a subset of the function identifier set in step 110, when the downstream information contains an indication of the AI ​​feature information, it is also necessary to further query the corresponding element in the function set.

[0061] Step 130: Determine uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

[0062] The uplink information is a response to the downlink information. After determining and generating the uplink information, the terminal-side device sends the uplink information. After receiving the uplink information, the network-side device determines the downlink information.

[0063] In step 130, the terminal-side device prepares and reports the uplink information based on the downlink information. Preferably, the content of the uplink information corresponds one-to-one with the content of the downlink information.

[0064] Preferably, the uplink information is carried by PUCCH / PUSCH, and the transmission time is determined according to the downlink information indication.

[0065] More preferably, the uplink information may include a set of functions corresponding to multiple AI models.

[0066] The terminal-side device prepares and reports the uplink information based on the downlink information. The content of the uplink information is determined by the terminal and generally includes a subset of the function identifier set. More preferably, the uplink information may include function sets corresponding to multiple AI models.

[0067] It should be noted that the above steps are used for network entities in a wireless communication system, including terminal-side devices, network-side devices, or other intermediate devices; the above steps can also be used for service devices that provide information processing for the network entity devices; the above steps can also be used for any device, system, subsystem, circuit, chip, or software entity that provides information reception, transmission, identification, and processing for terminal-side devices or network-side devices.

[0068] Figure 2 This is a flowchart illustrating an embodiment of the method of this application used in a network-side device.

[0069] The method described in any embodiment of the first aspect of this application, used in a network-side device, includes the following steps 210-230:

[0070] Step 210: The network-side device determines a set of function identifiers, wherein the elements in the set of function identifiers are identifiers used for AI functions.

[0071] Step 220: Send downlink information, which is used to query AI model functions. The downlink information contains an instruction to query AI functions identified by at least a portion of the elements in the function identifier set.

[0072] Step 230: Receive uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

[0073] Figure 3 This is a flowchart illustrating an embodiment of the method of this application used in a terminal-side device.

[0074] The method described in any embodiment of the first aspect of this application, used in a terminal-side device, includes the following steps 310 to 330:

[0075] Step 310: The terminal device determines a set of function identifiers, wherein the elements in the set of function identifiers are identifiers used for AI functions.

[0076] Step 320: Receive downlink information, the downlink information being used to query AI model functions, the downlink information containing instructions to select AI functions identified by at least a portion of the elements in the function identifier set.

[0077] Step 330: Send uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

[0078] the following Figures 4-10 Examples 1 to 6 include the combination of uplink and downlink information.

[0079] Figure 4 This is an example of downlink information including function query instructions and time point indications. As Example 1, in this example, the function identifier set is based on AI characteristics, an example of which is AI channel information (CSI) compression feedback. The function set elements are {scenario, network configuration, pairing information of bilateral models, payload size}, and the meaning of the fields corresponding to each element is shown in Table 1.

[0080] Table 1. CSI Compression Feedback Functional Elements

[0081]

[0082] Network-side devices send the downlink information via higher-layer signaling, such as RRC signaling. The downlink information contains multiple fields, representing AI model characteristics, query instructions for AI functions corresponding to the elements in Table 1, and the uplink information feedback time.

[0083] A specific example of the downlink information is as follows: Figure 4 The downlink information content is 1101111, which means that 40ms after receiving the downlink information, the uplink information is used to report the CSI compression feedback characteristic scenario, the pairing information of the bilateral model, and the payload size.

[0084] The downlink information includes one or more identifiers for the set AI characteristics. For example, the first bit is an AI model characteristic indicator.

[0085] The downlink information includes query instructions for corresponding elements in the function set. For example, the second position is the scene information query instruction, the third position is the network configuration query instruction, the fourth position is the pairing information query instruction for the bilateral model, and the fifth position is the payload size query instruction. In the second to fifth positions, 1 indicates that the element needs to be reported, and 0 indicates that the element does not need to be reported.

[0086] The downlink information includes a time point indication to determine the uplink information transmission time. For example, the 6th and 7th bits indicate the uplink information feedback time. The two bits corresponding to the 6th and 7th bits represent the feedback time point, such as 00 representing 5ms, 01 representing 10ms, 10 representing 20ms, and 11 representing 40ms.

[0087] Figure 5 This is an embodiment where uplink information includes functional description information. In Embodiment 1, after the terminal device receives the downlink information, it feeds back the uplink information on the PUCCH / PUSCH. The packet contains content indication information for the AI ​​functions identified by a subset of elements in the functional identifier set. This subset of elements consists of elements in the downlink information where the query indication bit is 1.

[0088] The uplink information is fed back based on the content in Table 1 corresponding to the downlink information. For example, the downlink information indicates three functions: scenario, pairing information of the bilateral model, and payload size. The uplink information feedback includes content indication information for these three functions, where the downlink information indicating the scenario occupies 2 bits, the pairing information of the bilateral model occupies 2 bits, and the payload size indication information occupies 1 bit. Therefore, the content indication information consists of a total of 5 bits. The uplink information is fed back at the designated location in the downlink information.

[0089] Figure 6 This is an embodiment where uplink information includes function set confirmation indication and function description information. As embodiment 2, in this embodiment, the function identifier set is the same as in embodiment 1, and is AI-based channel information (CSI) compression feedback based on AI characteristics. The function set elements are {scenario, network configuration, pairing information of bilateral model, payload size}, and the meaning of the fields corresponding to each element is shown in Table 1.

[0090] Network-side devices send the downlink information via higher-layer signaling, such as RRC signaling. The downlink information only includes the triggering information for AI model feature reporting and the uplink information feedback time. For example, the first bit contains AI feature indication information (such as...). Figure 4The second and third bits represent the feedback time point, such as 00 for 5ms, 01 for 10ms, 10 for 20ms, and 11 for 40ms. The downlink information content is 111, which means that the uplink information is used to report the CSI compression feedback feature function 40ms after receiving the downlink information.

[0091] After receiving the downlink information, the terminal device feeds back the uplink information on the PUCCH / PUSCH. The content of the uplink information is fed back according to the content of Table 1 corresponding to the downlink information. The uplink information feeds back three functions: scenario, pairing information of the bilateral model, and payload size. The uplink information feedback content consists of 9 bits, as shown in the illustration. Figure 6 The uplink information includes confirmation indications for corresponding elements in the function set. For example, the first four bits are function set confirmation indication information, where each bit confirms one element in the function set, indicating whether the corresponding set element has a content indication. A 1 indicates that the element has a function reported, and a 0 indicates that the element has no corresponding function reported. 1011 indicates the indication of scene, bilateral model pairing information, and payload. The last five bits correspond to the content indication of the element, and the indication content corresponds to the content in Table 1. The uplink information is fed back at the specified position in the downlink information.

[0092] Figure 7 This is an embodiment where the uplink information includes an indication of the number of multiple function sets and an indication of multiple function sets. As Embodiment 3, in this embodiment, the function identification set and the downlink information are the same as in Embodiment 1. When the terminal device receives the downlink information, it feeds back the uplink information on the PUCCH / PUSCH. Unlike Embodiment 1, the uplink information can feed back multiple function sets. For example, the uplink information feeds back two function set information, and the content of each function set is fed back according to the content of Table 1 corresponding to the downlink information.

[0093] At this point, the uplink information design can be done in two ways: one is to directly indicate the number of function sets, such as using a 2-bit indicator; the other is not to directly indicate the number of function sets, but to directly feed back the reported function sets in sequence. Another method of directly indicating the number of function sets is as follows... Figure 7 As shown.

[0094] exist Figure 7In the above-link information, 2 bits are used to indicate the number of function sets, and 10 represents 2 function sets. The information includes content indication information for the AI ​​functions identified by elements of one or more function sets. The content indication information for each AI function set includes content indication information for feedback to the identified AI functions. For example, the 5 bits following the function set number indicate the content indication information for the first AI function set, and the other 5 bits represent the content indication information for the second AI function set.

[0095] When the third information does not contain the function set number, the function set number implicitly indicates the function set 1 and function set 2 with 10 bits, without including the function set number indication.

[0096] Figure 8 This is an example of downlink information containing multiple AI features and corresponding function set query indicators. As Example 4, in this example, the function identifier set is based on AI features, including two features: AI-based Channel Information (CSI) compression feedback and AI-based beam management. The AI-based CSI compression feedback function set elements are {scenario, network configuration, pairing information of the bilateral model, payload size}, and the meaning of the fields corresponding to each element is shown in Table 1. The AI-based beam management function set elements are {scenario, beam codebook indication, beam prediction time interval, model information}, and the meaning of the fields corresponding to the US and Russian elements is shown in Table 2.

[0097] Table 2 Beam Management Functional Elements

[0098]

[0099] Network-side devices send the downlink information via higher-layer signaling, such as RRC signaling. The downlink information contains multiple fields, representing AI model characteristics, indications corresponding to the set elements in Tables 1 and 2, and the uplink information feedback time. For example, bits 1 and 2 represent AI model characteristic indications, bits 3 to 7 represent AI function set query indications corresponding to characteristic 1, bits 8 to 11 represent AI function set query indications corresponding to characteristic 2, bits 12 and 13 represent the uplink information feedback time, where bits 3 to 11 contain 1 indicating that the element needs to be reported, and 0 indicating that the element does not need to be reported. Bits 6 and 7 represent the feedback time point, such as 00 representing 5ms, 01 representing 10ms, 10 representing 20ms, and 11 representing 40ms. A specific example of the downlink information is as follows: Figure 8 The downlink information content is 111011110111, which represents the scenario of using the uplink information to perform CSI compression feedback characteristics, bilateral model pairing information and payload size function reporting and beam management scenario, beam codebook, and model information function reporting 40ms after receiving the downlink information.

[0100] Figure 9 This embodiment describes an uplink information containing multiple function sets corresponding to multiple set AI characteristics. In embodiment 4, after the terminal device receives the downlink information, it feeds back the uplink information on the PUCCH / PUSCH. The content of the uplink information is fed back according to the content in Table 1 corresponding to the downlink information. For example, the downlink information indicates that feedback should be given for three functional elements: scenarios where the AI ​​characteristic is CSI compression feedback, bilateral model pairing information, and payload size; and that for scenarios where the AI ​​characteristic is beam management, beam codebook, and model information should be reported. The uplink information feedback content consists of 10 bits, as illustrated in the diagram. Figure 10 The first 5 bits represent the content indication information of the AI ​​function identified by the first AI feature element, corresponding to the functional feedback of the CSI compression feedback feature; the last 5 bits represent the content indication information of the AI ​​function identified by the second AI feature element, corresponding to the functional feedback of the beam management feature. The specific meaning of the feedback can be derived from Tables 1 and 2. The uplink information is fed back at the designated position of the downlink information.

[0101] Figure 10 This is an embodiment where uplink information includes function set confirmation indications corresponding to multiple set AI characteristics. As Embodiment 5, in this embodiment, the function identifier set is the same as in Embodiment 4, based on AI characteristics as AI-based Channel Information (CSI) compression feedback. The function set elements are {scenario, network configuration, bilateral model pairing information, payload size}, and the meaning of the fields corresponding to each element is shown in Table 1. The AI-based beam management function set elements are {scenario, beam codebook indication, beam prediction time interval, model information}, and the meaning of the fields corresponding to the US and Russian elements is shown in Table 2.

[0102] Network-side devices send the downlink information via higher-layer signaling, such as RRC signaling. The downlink information only includes the trigger for AI model feature reporting and the uplink information feedback time. For example, bits 1 and 2 indicate the AI ​​model feature, and bits 3 and 4 represent the feedback time point, such as 00 for 5ms, 01 for 10ms, 10 for 20ms, and 11 for 40ms. The downlink information content is 1111, indicating that 40ms after receiving the downlink information, the uplink information is used to report CSI compression feedback features and beam management functions.

[0103] After receiving the downlink information, the terminal device feeds back the uplink information on the PUCCH / PUSCH. The uplink information includes confirmation indications for multiple AI function sets and content indications for multiple AI function sets. The content of the uplink information is fed back according to the content in Table 1 corresponding to the downlink information.

[0104] The uplink information also includes one or more AI function set confirmation indication messages. Each AI function set confirmation indication message contains information confirming the AI ​​functions identified by a subset of elements. In each AI function set confirmation indication message, each bit confirms one element in the function set, indicating whether the corresponding set element has a content indication, where 1 represents that the element has a function reported, and 0 represents that the element has no corresponding function reported.

[0105] The first AI function set confirmation indication information of the uplink information includes information confirming the AI ​​functions identified by multiple functional elements, such as confirming three functions: scene with CSI compression feedback characteristics, pairing information of bilateral models, and payload size. According to Table 1, the confirmation indication information is 1011, totaling 4 bits. The content indication information of the first AI function set of the uplink information includes feedback on the three confirmed functions, namely, scene, pairing information of bilateral models, and payload size, reporting content indication information, totaling 5 bits.

[0106] The second AI function set confirmation indication of the uplink information includes information confirming the AI ​​functions identified by multiple functional elements, such as reporting the scene, beam codebook, and model information functions with AI characteristics of beam management. According to Table 2, the confirmation indication information is 1101, totaling 4 bits. The content indication information of the second AI function set of the uplink information includes feedback on the confirmed scene, beam codebook indication, and model information functions, totaling 5 bits.

[0107] like Figure 10 The uplink information feedback content consists of 18 bits. The first 4 bits are the CSI compressed feedback feature function content indicator, each bit used to confirm whether the elements in Table 1 have been indicated; the next 5 bits correspond to the content indication of the element, and the indicated content corresponds to the content in Table 1. The meaning of the 9 bits related to beam management is similar to that of the CSI compressed feedback part, with the first 4 bits being the element confirmation identifier and the last 5 bits indicating the content. The uplink information is fed back at the designated position of the downlink information.

[0108] Example 6: In this example, the function identifier set and the downlink information are the same as in Example 4. When the terminal device receives the downlink information, it feeds back the uplink information on the PUCCH / PUSCH. Unlike Example 3, the uplink information can feed back multiple function sets for multiple characteristics. For example, the uplink information feeds back two function sets for each of two characteristics, and the content of each function set is fed back according to the contents of Tables 1 and 2 corresponding to the downlink information. In this case, the uplink information feeds back different characteristics sequentially, first feeding back the function indication related to the first characteristic, then feeding back the function indication related to the second characteristic. The function indication for each characteristic can refer to the uplink information indication method in Example 3.

[0109] Figure 11 This is a schematic diagram of an embodiment of a network-side device.

[0110] This application also proposes a network-side device for implementing the method of any embodiment of this application. At least one module in the network-side device is used for at least one of the following functions: determining the function identifier set; determining the downlink information; sending the downlink information; receiving the uplink information; and determining the uplink information.

[0111] To implement the above technical solution, this application proposes a network-side device 400, which includes a network transmitting module 401, a network determining module 402, and a network receiving module 403 that are interconnected.

[0112] The network sending module is used to send the downlink information.

[0113] The network determination module is used to determine the set of function identifiers, downlink information, and uplink information.

[0114] The network receiving module is used to receive the uplink information.

[0115] The specific methods for implementing the functions of the network sending module, network determining module, and network receiving module are as described in the various method embodiments of this application, and will not be repeated here.

[0116] The network-side equipment described in this application may refer to base station facilities, network-side equipment or servers connected to base stations, systems that provide services for the aforementioned equipment, or any system, subsystem, module, circuit, chip or software operating device that provides information reception, transmission, identification and processing for the aforementioned equipment.

[0117] Figure 12 This is a schematic diagram of an embodiment of the terminal-side device.

[0118] This application also proposes a terminal-side device for implementing the method of any embodiment of this application, wherein at least one module in the terminal-side device is used for at least one of the following functions: determining the function identifier set; receiving the downlink information; determining the downlink information; determining the uplink information; and sending the uplink information.

[0119] To implement the above technical solution, this application proposes a terminal-side device 500, which includes a terminal transmitting module 501, a terminal determining module 502, and a terminal receiving module 503 that are interconnected.

[0120] The terminal receiving module is used to receive the downlink information.

[0121] The terminal determination module is used to determine the set of function identifiers, downlink information, and uplink information.

[0122] The terminal sending module is used to send the uplink information.

[0123] The specific methods for implementing the functions of the terminal sending module, the terminal determining module, and the terminal receiving module are as described in the various method embodiments of this application, and will not be repeated here.

[0124] The terminal-side equipment described in this application may refer to user equipment (UE), personal mobile terminal, smart terminal, mobile phone, computer with communication function, system providing services for the above-mentioned equipment, or any system, subsystem, module, circuit, chip or software running device that provides information reception, transmission, identification and processing for the above-mentioned equipment.

[0125] Figure 13 A schematic diagram of a network-side device according to another embodiment of the present invention is shown. As shown, the network-side device 600 includes a processor 601, a wireless interface 602, and a memory 603. The wireless interface may consist of multiple components, including a transmitter and a receiver, providing a unit for communication with various other devices over a transmission medium. The wireless interface implements communication functions with the terminal-side device, processes wireless signals through receiving and transmitting devices, and the data carried by the signals is communicated with the memory or processor via an internal bus structure. The memory 603 contains a computer program that executes any embodiment of this application, and the computer program runs or modifies the processor 601. When the memory, processor, and wireless interface circuit are connected through a bus system, the bus system includes a data bus, a power bus, a control bus, and a status signal bus, which will not be described in detail here.

[0126] Figure 14This is a block diagram of a terminal-side device according to another embodiment of the present invention. The terminal-side device 700 includes at least one processor 701, a memory 702, a user interface 703, and at least one network interface 704. The various components in the terminal-side device 700 are coupled together via a bus system. The bus system is used to implement communication between these components. The bus system includes a data bus, a power bus, a control bus, and a status signal bus.

[0127] User interface 703 may include a display, keyboard, or clicking device, such as a mouse, trackball, touchpad, or touchscreen.

[0128] The memory 702 stores executable modules or data structures. The memory may store an operating system and application programs. The operating system includes various system programs, such as a framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application functions.

[0129] In an embodiment of the present invention, the memory 702 contains a computer program that executes any embodiment of the present application, the computer program being run on or modified by the processor 701.

[0130] The memory 702 includes a computer-readable storage medium. The processor 701 reads the information in the memory 702 and, in conjunction with its hardware, completes the steps of the above-described method. Specifically, the computer-readable storage medium stores a computer program, which, when executed by the processor 701, implements the steps of the method embodiments described in any of the above embodiments.

[0131] The processor 701 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the method in this application can be completed by the integrated logic circuitry in the hardware of the processor 701 or by instructions in software form. The processor 701 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor.

[0132] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. In a typical configuration, the device of this application includes one or more processors (CPUs), an input / output user interface, a network interface, and memory.

[0133] Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] Therefore, this application also proposes a computer-readable medium storing a computer program that, when executed by a processor, implements the steps of the method described in any embodiment of this application. For example, the memory 603, 702 of the present invention may include non-permanent memory in the form of computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM.

[0135] Based on the embodiments of the above-described apparatus in this application, this application also proposes a mobile communication system, including at least one embodiment of any terminal-side device in this application and / or at least one embodiment of any network-side device in this application.

[0136] It should be noted that the specific mobile communication technology described in this invention is not limited, and can be WCDMA, CDMA2000, TD-SCDMA, WiMAX, LTE / LTE-A, LAA, MuLTEfire, and subsequent fifth-generation, sixth-generation, and Nth-generation mobile communication technologies.

[0137] The terminal described in this invention refers to a terminal-side product that can support the communication protocols of terrestrial mobile communication systems, and a specially designed wireless modem module that can be integrated into various types of terminal forms such as mobile phones, tablets, and data cards to complete communication functions.

[0138] For ease of description, we will use the fourth-generation mobile communication system LTE / LTE-A and its derivative MulteFire as an example, where the mobile communication terminal can be represented as UE (User Equipment), and the network-side access equipment can be represented as a base station or access point.

[0139] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0140] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for managing the function of an AI model, characterized in that, Includes the following steps: In a mobile communication system, a set of function identifiers is determined. The elements in the set of function identifiers are identifiers used as AI functions. The AI ​​functions include at least one of the following: input and output of AI model, typical scenarios in which AI model is used, typical configuration of AI model, size of AI model, type of AI model, and inference time of AI model. Determine downlink information, which is used to query AI model functions. The downlink information contains an instruction to query AI functions identified by at least a portion of the elements in the function identifier set. The function identifier set determines the set of functions required to support AI features. The AI ​​features include at least one of the following: AI-based positioning, AI-based beamforming, and AI-based channel information compression feedback. Determine the uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

2. An AI model function management method for network-side devices, characterized in that, Includes the following steps: The network-side device determines a set of function identifiers, the elements in the set of function identifiers being identifiers used for AI functions, the AI ​​functions including at least one of the following: AI model input and output, typical scenarios in which the AI ​​model is used, typical configurations in which the AI ​​model is used, AI model size, AI model type, and AI model inference time; Send downlink information, the downlink information being used to query AI model functions, the downlink information containing an instruction to query AI functions identified by at least a portion of the elements in the function identifier set, wherein the function identifier set is used to determine the set of functions required to support AI features, the AI ​​features including at least one of the following: AI-based positioning, AI-based beamforming, and AI-based channel information compression feedback. Receive uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some elements.

3. An AI model function management method for a terminal-side device, characterized in that, Includes the following steps: The terminal device determines a set of function identifiers, the elements in the set of function identifiers being identifiers used for AI functions, the AI ​​functions including at least one of the following: input and output of AI model, typical scenarios of AI model use, typical configuration of AI model use, AI model size, AI model type, and AI model inference time; Receive downlink information, the downlink information being used to query AI model functions, the downlink information containing instructions to select AI functions identified by at least a portion of the elements in the function identifier set, wherein the function identifier set is used to determine the set of functions required to support AI features, the AI ​​features including at least one of the following: AI-based positioning, AI-based beamforming, and AI-based channel information compression feedback. Send uplink information, which is a response to the downlink information and includes content indication information for the AI ​​functions identified by the at least some of the elements.

4. The AI ​​model function management method as described in any one of claims 1 to 3, characterized in that, The AI ​​functions identified by at least some of the elements constitute the set of functions required based on the defined AI characteristics.

5. The AI ​​model function management method as described in any one of claims 1 to 3, characterized in that, The downlink information is a joint indication of DCI information carried by PDCCH and higher-layer information carried by PDSCH, or is indicated by the higher-layer information. The uplink information is carried by PUCCH and / or PUSCH.

6. The AI ​​model function management method as described in any one of claims 1 to 3, characterized in that, The downlink information includes a time point indication, which is used to determine the time when the uplink information was sent.

7. The AI ​​model function management method as described in any one of claims 1 to 3, characterized in that, The uplink information includes one or more AI function set confirmation indication messages; each AI function set confirmation indication message includes information confirming the AI ​​functions identified by at least some of the elements.

8. The AI ​​model function management method as described in claim 4, characterized in that, The downlink information includes one or more identifiers of the set AI characteristics.

9. The AI ​​model function management method as described in claim 4, characterized in that, Each AI feature corresponds to at least one AI function set; The downlink information includes one or more AI function set query instructions corresponding to the set AI characteristics. Each AI function set query instruction includes an instruction to select the AI ​​function identified by at least some of the elements.

10. A network-side device for implementing the AI ​​model function management method according to any one of claims 1-2 and 4-9, characterized in that, At least one module in the network-side device is configured to perform at least one of the following functions: determine the function identifier set; determine the downlink information; send the downlink information; receive the uplink information; and determine the uplink information.

11. A terminal-side device for implementing the AI ​​model function management method according to any one of claims 1, 3 to 9, characterized in that, At least one module in the terminal-side device is used for at least one of the following functions: determining the function identifier set; receiving the downlink information; determining the downlink information; determining the uplink information; and sending the uplink information.

12. A communication device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any one of claims 1 to 9.

13. A computer-readable medium storing a computer program thereon, the computer program, when executed by a processor, implementing the steps of the method as claimed in any one of claims 1 to 9.

14. A mobile communication system comprising at least one network-side device as described in claim 10 and / or at least one terminal-side device as described in claim 11.

Images