A method and device for jointly deploying mobile communication network data and models

Abstract

The present application discloses a method for jointly deploying mobile communication network data and models, comprising the following steps: the first information in the downlink includes the characteristic parameters of the AI model and / or the data set; in response to the first information, the second information in the uplink includes the feedback corresponding to the characteristic parameters for confirming the value of at least one of the characteristic parameters; in response to the second information, the third information in the downlink includes the input data set of the AI model that meets the confirmed characteristic parameters; in response to the third information, the fourth information in the uplink includes the confirmation information on the availability of the data set. The present application also includes a device applying the method. The present application solves the problem that a wireless communication system uses an air interface to complete efficient data set transmission between the network and the terminal, and is particularly applicable to 5G and further evolved mobile communication systems.

Description

Technical Field

[0001] This application relates to the field of wireless communication technologies, and in particular, to a method and device for jointly deploying an AI model and a dataset in a mobile communication network. Background Art

[0002] Mobile communication networks contain a large amount of data resources. The rational utilization and exploration of 5G data resources using artificial intelligence (AI) technology can effectively improve the performance of mobile communication systems. The problems faced in mobile communication systems are complex and diverse. A large number of studies have shown that the performance of the network side and the wireless side of mobile communication networks can be effectively improved through AI-based algorithms. Using AI technology to improve the performance of mobile systems has become the main direction of future network design.

[0003] When a wireless communication system uses AI technology to enhance system performance, it involves the training and deployment of AI models. Since the training of AI models often requires a large amount of computing resources and also a large amount of data for training. The transfer of models between the network and the terminal is restricted in various ways, making it difficult for the terminal to directly apply the models sent by the network side. For some use cases where models need to be deployed on both the terminal and the network side, such as data compression and decompression, the network and the terminal need to deploy the models separately to complete the data compression and decompression functions. There are various ways for the terminal side to obtain models, for example, obtaining from the network side or training by itself through a dataset. Direct model transmission through the air interface is restricted by various limitations and is not supported by the standard. Sending the required dataset from the network side to the terminal side through the air interface to complete the model training on the terminal side has become another important option. The solution of the present invention provides a method and device for the terminal side to obtain a dataset from the network side to complete the model training on the terminal side. Summary of the Invention

[0004] This application proposes a method and device for jointly deploying data and models in a mobile communication network, which solves the problem of efficiently transmitting a dataset between the network and the terminal using the air interface in a wireless communication system.

[0005] In a first aspect, this application proposes a method for jointly deploying data and models in a mobile communication network, including the following steps:

[0006] The first information in the downlink contains the characteristic parameters of the AI model and / or the dataset;

[0007] In response to the first information, the second information in the uplink contains feedback corresponding to the characteristic parameters for confirming the value of at least one of the characteristic parameters;

[0008] In response to the second information, the third information in the downlink contains the input dataset of the AI model that meets the confirmed characteristic parameters;

[0009] In response to the third information, the uplink fourth information includes confirmation information on the availability of the dataset.

[0010] The method according to any one of the embodiments of the first aspect of this application, for a network device, includes the following steps:

[0011] Send downlink first information, including characteristic parameters of the AI model and / or the dataset;

[0012] Receive uplink second information, obtain feedback on the first information, and confirm the value of at least one of the characteristic parameters;

[0013] In response to the second information, send downlink third information, including the input dataset of the AI model that meets the confirmed characteristic parameters;

[0014] Receive uplink fourth information, obtain confirmation information on the availability of the dataset.

[0015] The method according to any one of the embodiments of the first aspect of this application, for a terminal device, includes the following steps:

[0016] Receive downlink first information, obtain characteristic parameters of the AI model and / or the dataset;

[0017] In response to the first information, send uplink second information, including feedback corresponding to the characteristic parameters, for confirming the value of at least one of the characteristic parameters;

[0018] Receive downlink third information, obtain the input dataset of the AI model that meets the confirmed characteristic parameters;

[0019] In response to the third information, send uplink fourth information, including confirmation information on the availability of the dataset.

[0020] In any one of the embodiments of the first aspect of this application, preferably, the characteristic parameters include at least one of the following: AI model usage AImodel_case, AI model algorithm type AImodel_type, dataset size DATA_size, dataset type DATA_type, number of data segments DATA_segment.

[0021] In any one of the embodiments of the first aspect of this application, preferably, the first information includes an indication of the feedback time of the second information.

[0022] In any one of the embodiments of the first aspect of this application, preferably, the first information is indicated by DCI information carried by PDCCH, or the first information is jointly indicated by DCI information carried by PDCCH and high-layer information carried by PDSCH.

[0023] In any embodiment of the first aspect of the present application, preferably, the second information is carried by PUCCH or PUSCH; and / or, the fourth information is carried by PUCCH or PUSCH.

[0024] In any embodiment of the first aspect of the present application, preferably, the third information is indicated by DCI information carried by PDCCH, or the third information is jointly indicated by DCI information carried by PDCCH and high-layer information carried by PDSCH.

[0025] In any embodiment of the first aspect of the present application, preferably, each indication information in the second information is used to confirm whether the value of at least one characteristic parameter is available or unavailable.

[0026] In any embodiment of the first aspect of the present application, preferably, the third information includes relevant information of the data set, and the relevant information includes at least one of the following information: data format, data quantity, training set and validation set division.

[0027] In any embodiment of the first aspect of the present application, preferably, the fourth information includes the available time of the AI model trained by the data set.

[0028] In a second aspect, the present application further provides a network device for implementing the method according to any one of the first aspects of the present application. At least one module in the network device is used for at least one of the following functions: sending the first information and the third information; receiving the second information and the fourth information; determining the input data set of the AI model in response to the second information; determining the availability of the data set in response to the fourth information.

[0029] In a third aspect, the present application further provides a terminal device for implementing the method according to any one of the first aspects of the present application. At least one module in the terminal device is used for at least one of the following functions: receiving the first information and the third information; sending the second information and the fourth information; determining the value of at least one of the characteristic parameters in response to the first information; determining the availability of the data set in response to the third information.

[0030] In a fourth aspect, the present application further provides a communication device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the method according to any embodiment of the first aspect of the present application are implemented.

[0031] Fifth aspect, the present application further provides a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any embodiment of the first aspect of the present application are implemented.

[0032] Sixth aspect, the present application further provides a mobile communication system, including at least one network device described in any embodiment of the present application and / or at least one terminal device described in any embodiment of the present application.

[0033] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects:

[0034] The present invention provides a method and device for supporting independent model training between a terminal and a network. The method and device provided by the present invention can enable the terminal to use the model provided by the network to enhance the corresponding air interface transmission ability. Especially when the network device is not clear about the AI support ability of the terminal device, the present invention provides key processes and design methods for exchanging information related to AI model interaction and deployment. It provides an effective solution for the terminal device to use the AI model provided by the network device. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0036] Figure 1 is a flowchart of an embodiment of the method of the present application;

[0037] Figure 2 is a flowchart of an embodiment of the method of the present application for a network device;

[0038] Figure 3 is a flowchart of an embodiment of the method of the present application for a terminal device;

[0039] Figure 4 is a schematic diagram of the composition of the first information;

[0040] Figure 5 is a schematic diagram of the composition of the second information;

[0041] Figure 6 is a schematic diagram of the composition of the third information;

[0042] Figure 7 is another schematic diagram of the composition of the first to fourth information;

[0043] Figure 8 is a schematic diagram of an embodiment of a network device;

[0044] Figure 9 It is a schematic diagram of an embodiment of a terminal device;

[0045] Figure 10 It is a schematic structural diagram of a network device according to another embodiment of the present invention;

[0046] Figure 11 It is a block diagram of a terminal device according to another embodiment of the present invention. Detailed implementation manners

[0047] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part rather than all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0048] Consider a communication system composed of a network device and terminal devices. A network device can simultaneously send and receive data with multiple terminal devices. The network data unit and the terminal data unit send data through the downlink data shared channel (PDSCH) and the uplink data shared channel (PUSCH). The PDCCH sends downlink control information (DCI) to indicate the specific transmission format related content of the PDSCH, PUSCH, and PUCCH. The PUCCH then sends uplink control information (UCI), which includes feedback or confirmation information from the terminal device to the network device.

[0049] The following will describe in detail the technical solutions provided by each embodiment of the present application in conjunction with the drawings.

[0050] Figure 1 It is a flowchart of an embodiment of the method of the present application. The present application proposes a method for jointly deploying mobile communication network data and models, including the following steps 101-104:

[0051] Step 101, the first information in the downlink includes the feature parameters of the AI model and / or the feature parameters of the data set;

[0052] The purpose of the first information is to notify the terminal device to prepare for running the AI model for training. The feature parameters can be the feature parameters of the AI model, the feature parameters of the data set, or a combination of the two, including at least one of the following: the purpose of the AI model AImodel_case, the type of AI model algorithm AImodel_type, the size of the data set DATA_size, the type of data set DATA_type, the number of data segments DATA_segment.

[0053] It should be noted that the characteristic parameters of the AI model here are only symbols or bytes used for indexing, and are not the entire compressed package of the AI model. According to the solution of the present application, the network does not send the compressed model to the terminal, but sends a training dataset to the terminal, and then the terminal trains the compressed model by itself.

[0054] Similarly, the characteristic parameters of the dataset here are only symbols or bytes used for indexing, and are not the dataset itself. The terminal device determines whether it has the ability to run the AI model or dataset specified by the characteristic parameters according to the characteristic parameters included in the first indication information.

[0055] Preferably, the first information includes an indication of the feedback time of the second information, such as timing Feedback_timing or time slot Feedback_slot.

[0056] Preferably, the first information is indicated by the DCI information carried by the PDCCH, or the first information is jointly indicated by the DCI information carried by the PDCCH and the high-layer information carried by the PDSCH. When jointly indicated, the DCI first includes the signaling information of the first information, indicating the position of the query symbol in the PDSCH.

[0057] Table 1 Examples of the name, indication information, and parameter values of the characteristic parameters in the first information

[0058] (The first row is the indication information of the characteristic parameter value, and the first column is the type of the characteristic parameter)

[0059]

[0060] Step 102: In response to the first information, the uplink second information includes feedback corresponding to the characteristic parameters, for confirming the value of at least one of the characteristic parameters;

[0061] The second information is carried by the PUCCH or the PUSCH.

[0062] For the second information, the terminal device feeds back to confirm the ability of the terminal device to support AI model training. For example, each indication information in the second information is used to confirm the value of at least one characteristic parameter (as shown in Table 1).

[0063] It should be noted that the confirmation in this application includes available or unavailable. For example, an indication information in the second information confirms the value of at least one characteristic parameter can be used for the terminal device by a preset combination, that is, the terminal device can support the corresponding AI model to be trained according to the indicated data set. For another example, an indication information in the second information confirms the value of at least one characteristic parameter is not available for the terminal device by a preset combination, that is, the terminal device cannot run the training of the corresponding AI model.

[0064] Step 103, in response to the second information, the downlink third information includes the input data set of the AI model that meets the confirmation for the characteristic parameter;

[0065] The purpose of the third information is to implement the data set download of the AI model.

[0066] The third information includes but is not limited to the data set and related information of the data set. The data set can be sent once or divided into multiple times, and the data set size and number do not exceed the relevant limits fed back in the second information.

[0067] The third information is indicated by the DCI information carried by the PDCCH, or the third information is jointly indicated by the DCI information carried by the PDCCH and the high-layer information carried by the PDSCH. When jointly indicating, first include the signaling information of the third information in the DCI information, indicating the position where the data of the AI model of the third information is transmitted in the PDSCH.

[0068] Preferably, the third information includes the related information of the data set, and the related information includes at least one of the following information: data format, data quantity, training set and validation set division.

[0069] Step 104, in response to the third information, the uplink fourth information includes the confirmation information of the availability of the data set.

[0070] The fourth information is used to confirm the AI model deployment result.

[0071] The fourth information is carried by the PUCCH or PUSCH.

[0072] Preferably, the fourth information further includes the available time of the AI model trained by the data set.

[0073] It should be noted that in this application, the availability of the data set means that the data set can be used for the training of the AI model and run with the support of the capabilities of the terminal device. For example, the software and hardware of the AI model that loads the data set can work and output results according to the set functions.

[0074] Figure 2Flowchart of an embodiment of the method of the present application for a network device. The method described in any embodiment of the first aspect of the present application, when used for a network device, includes the following steps 201 to 204:

[0075] Step 201: The network device sends the first information in the downlink direction, including the characteristic parameters of the AI model and / or the data set; the network device notifies the terminal device to prepare for AI model training through the first information.

[0076] Step 202: The network device receives the second information in the uplink direction, obtains the feedback on the first information, and confirms the value of at least one of the characteristic parameters;

[0077] Step 203: In response to the second information, the network device sends the third information in the downlink direction, including the input data set of the AI model that meets the confirmed characteristic parameters;

[0078] Step 204: The network device receives the fourth information in the uplink direction and obtains the confirmation information on the availability of the data set.

[0079] Figure 3 Flowchart of an embodiment of the method of the present application for a terminal device. The method described in any embodiment of the first aspect of the present application, when used for a terminal device, includes the following steps:

[0080] Step 301: The terminal device receives the first information in the downlink direction and obtains the characteristic parameters of the AI model and / or the data set;

[0081] Step 302: In response to the first information, the terminal device sends the second information in the uplink direction, including the feedback corresponding to the characteristic parameters, for confirming the value of at least one of the characteristic parameters;

[0082] Step 303: The terminal device receives the third information in the downlink direction and obtains the input data set of the AI model that meets the confirmed characteristic parameters;

[0083] Step 304: In response to the third information, the terminal device sends the fourth information in the uplink direction, including the confirmation information on the availability of the data set.

[0084] In step 304, the terminal device first parses the third information, interprets the third information, completes model training according to the data set, and feeds back the fourth information to the network device. The fourth information includes whether the data set sent by the third information can be used, the time point when the AI model trained according to the data set sent by the third information can be used, and other information.

[0085] According to the embodiments of steps 101-104, 201-204, and 301-304 above, before the terminal device uses the data set provided by the network device for AI model training, a series of information interactions are carried out with the network device to ensure that the terminal obtains the required data set. The specific process of the information interaction is as Figures 4 - 5 shown. The network device first needs to initiate the preparation for AI model training. After receiving the feedback from the terminal device, the network device transmits the data set and related information required for AI model training, as Figure 6 shown. After the terminal device obtains the data set and related information, it conducts the training of the AI model, then deploys it, and notifies the network device that the AI model can be used. The solution provided by the present invention will be further described through multiple embodiments below.

[0086] Figure 4 It is a schematic diagram of the composition of the first information. In this embodiment, the network device sends the first information through PDCCH. The first information (AI_training_prepare) contains multiple fields, which respectively represent the supported AI model usage (AImodel_case), the type of the AI model (AImodel_type), the data set size (Data_size), the data format of the data set (Data_type), and the data set segmentation (Data_segement). Each field is represented by a certain number of bits, notifying the terminal of the data set and the model usage information. AI_training_prepare also contains the feedback time point (Feedback_timing) for the relevant information of the first information, which can be composed of multiple bits. Figure 4 A schematic diagram of the first information is given, where 12 bits, with 2 bits for each field, represent the corresponding information.

[0087] Figure 5 It is a schematic diagram of the composition of the second information. When the terminal device receives the first information, it feeds back the second information (AI_training_feedback) on the PUCCH. The content of the second information is fed back according to the corresponding content of the first information. The second information can feed back part of the first information. As Figure 5 shown, if the terminal device confirms that it will use the data set provided by the network device for model training, then set AI_training_confirm to 1, and at the same time accept the data set format and segmentation method adopted by the network device for training, and both Data_type_f and Data_segment_f repeat the indication information sent by the network device.

[0088] Figure 6It is a schematic diagram of the composition of the third information. After receiving the second information, the network device feeds back the data set and related information, that is, the third information. The specific information (Data_inf) of the data set includes data set format, data set size, training set, data set identifier, etc. The data set (Data_inf) of the third information is sent by the high-layer signaling or data-plane information carried by PDSCH. The data set related information (Data_rel_inf) is carried by PDCCH, and the DCI information carrying the data set related information also indicates the sending location of the data set and indicates the feedback point of the fourth information. The figure exemplarily shows the signaling information part in the third information carried by DCI, including the data set related information (Data_rel_inf), carried by PDCCH. The DCI information carrying the AI model related information also indicates the location of the data set (at "1" in the figure, for example, the training data set and the validation data set can be further distinguished), and indicates the feedback point of the fourth information (at "2" in the figure).

[0089] After receiving the third information, the terminal device completes the interpretation of the third information and the training of the AI model, and sends the fourth information to the network device at the location indicated by the third information. The fourth information completes the confirmation of the AI model training. Further, it confirms the available time of the AI model.

[0090] Figure 7 It is a schematic diagram of another embodiment of the composition of the first to fourth information. The network device sends the first information through PDCCH. The first information (AI_capacity_report) is the same as that in the above embodiment, triggering the terminal device to inquire whether to use the data set provided by the network device for AI model training. After receiving the first information, the terminal device completes the reporting of 1 bit of the second information according to the first information, respectively representing whether to use the data set used in the first information for training. When the terminal cannot perform AI model training, it will report using a specific combination of the second information, such as all 0. A combination of multiple characteristic parameter values is indicated by an indication information. After receiving the second information, the network device sends the data set and related information, that is, the third information. The third information is the same as that in the above embodiment. After receiving the third information, the terminal device completes the interpretation of the third information and the training of the AI model, and sends the fourth information to the network device at the location indicated by the third information.

[0091] Figure 8Schematic diagram of an embodiment of a network device. An embodiment of the present application also proposes a network device that uses the method of any one of the embodiments of the present application. At least one module in the network device is used for at least one of the following functions: sending the first information and the third information; receiving the second information and the fourth information; determining the AI model input data set in response to the second information; determining the availability of the data set in response to the fourth information.

[0092] To implement the above technical solution, a network device 400 proposed by the present application includes a network sending module 401, a network determining module 402, and a network receiving module 403 that are interconnected.

[0093] The network sending module is used to send the first information and the second information.

[0094] The network determining module is used to determine the AI model and / or the data set according to the value of the characteristic parameter confirmed in the second information; and is also used to determine the availability and running time of the data set according to the fourth information, and further determine that the AI deployment is successful.

[0095] The network receiving module is used to receive the third information and the fourth information.

[0096] The specific methods for implementing the functions of the network sending module, the network determining module, and the network receiving module are as described in the method embodiments of the present application and will not be elaborated here.

[0097] Figure 9 Schematic diagram of an embodiment of a terminal device. The present application also proposes a terminal device that uses the method of any one of the embodiments of the present application. At least one module in the terminal device is used for at least one of the following functions: receiving the first information and the third information; sending the second information and the fourth information; determining the value of at least one of the characteristic parameters in response to the first information; determining the availability of the data set in response to the third information.

[0098] To implement the above technical solution, a terminal device 500 proposed by the present application includes a terminal sending module 501, a terminal determining module 502, and a terminal receiving module 503 that are interconnected.

[0099] The terminal sending module is used to send the second information and the fourth information.

[0100] The terminal determining module is used to determine the value of at least one of the characteristic parameters according to the indication information of the characteristic parameters in the first information and the operating ability of the terminal device; and to trial-run the data set according to the indication of the third information to determine the availability and running time of the data set.

[0101] The terminal receiving module is configured to receive the first information and the third information.

[0102] 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 method embodiments of the present application, and will not be elaborated here.

[0103] The terminal device described in the present application may refer to a mobile terminal device.

[0104] Figure 10 FIG. shows a schematic structural diagram of a network device according to another embodiment of the present invention. As shown in the figure, the network device 600 includes a processor 601, a wireless interface 602, and a memory 603. Among them, the wireless interface may be multiple components, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on a transmission medium. The wireless interface implements the communication function with the terminal device, processes wireless signals through the receiving and transmitting devices, and the data carried by the signals communicates with the memory or the processor through the internal bus structure. The memory 603 contains a computer program for executing any embodiment of the present application, and the computer program runs or changes on the processor 601. When the memory, the processor, and the 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 elaborated here.

[0105] Figure 11 is a block diagram of a terminal device according to another embodiment of the present invention. The terminal device 700 includes at least one processor 701, a memory 702, a user interface 703, and at least one network interface 704. Each component in the terminal device 700 is coupled together through a bus system. The bus system is used to realize the connection and communication between these components. The bus system includes a data bus, a power bus, a control bus, and a status signal bus.

[0106] The user interface 703 may include a display, a keyboard, or a pointing device, for example, a mouse, a trackball, a touchpad, or a touch screen, etc.

[0107] The memory 702 stores executable modules or data structures. The memory may store an operating system and application programs. Among them, the operating system contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs contain various application programs, such as a media player, a browser, etc., for implementing various application services.

[0108] In the embodiment of the present invention, the memory 702 contains a computer program for executing any embodiment of the present application, and the computer program runs or changes on the processor 701.

[0109] The memory 702 contains a computer-readable storage medium. The processor 701 reads the information in the memory 702 and combines its hardware to complete the steps of the above method. Specifically, a computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor 701, it implements the steps of the method embodiments described in any one of the above embodiments.

[0110] The processor 701 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the method of the present application can be completed by the integrated logic circuit in the hardware of the processor 701 or the instructions in the form of software. The processor 701 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.

[0111] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. In a typical configuration, the device of the present application includes one or more processors (CPUs), an input / output user interface, a network interface, and a memory.

[0112] In addition, the present invention can 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.

[0113] Therefore, the present application also proposes a computer-readable medium. A computer program is stored on the computer-readable medium. When the computer program is executed by the processor, it implements the steps of the method described in any one of the embodiments of the present application. For example, the memories 603 and 702 of the present invention may include non-permanent memories in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM).

[0114] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0115] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0116] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for jointly deploying mobile communication network data and models, characterized in that It includes the following steps: The first downlink information includes the characteristic parameters of the AI model and / or the dataset; In response to the first information, the second uplink information includes the feedback corresponding to the characteristic parameters, which is used to confirm the value of at least one of the characteristic parameters and confirm the ability of the terminal device to support AI model training; In response to the second information, the third downlink information includes the input dataset of the AI model that meets the confirmed characteristic parameters, and the dataset is used for AI model training; In response to the third information, the fourth uplink information includes the confirmation information on the availability of the dataset and the available time of the AI model trained by the dataset; the availability of the dataset means that the dataset can be used for AI model training, run with the support of the capabilities of the terminal device, and the AI model loaded with the dataset can work and output results according to the set functions.

2. A method for jointly deploying mobile communication network data and models, which is used for network devices, and is characterized in that It includes the following steps: Send the first downlink information, which includes the characteristic parameters of the AI model and / or the dataset; Receive the second uplink information to obtain the feedback on the first information, confirm the value of at least one of the characteristic parameters, and confirm the ability of the terminal device to support AI model training; In response to the second information, send the third downlink information, which includes the input dataset of the AI model that meets the confirmed characteristic parameters, and the dataset is used for AI model training; Receive the fourth uplink information to obtain the confirmation information on the availability of the dataset and the available time of the AI model trained by the dataset; The availability of the dataset means that the dataset can be used for AI model training, run with the support of the capabilities of the terminal device, and the AI model loaded with the dataset can work and output results according to the set functions.

3. A method for jointly deploying mobile communication network data and models, which is used for terminal devices, and is characterized in that, It includes the following steps: Receive the first downlink information to obtain the characteristic parameters of the AI model and / or the dataset; In response to the first information, send the second uplink information, which includes the feedback corresponding to the characteristic parameters, which is used to confirm the value of at least one of the characteristic parameters and confirm the ability of the terminal device to support AI model training; Receive the third downlink information to obtain the input dataset of the AI model that meets the confirmed characteristic parameters, and the dataset is used for AI model training; In response to the third information, send the fourth uplink information, which includes the confirmation information on the availability of the dataset and the available time of the AI model trained by the dataset; the availability of the dataset means that the dataset can be used for AI model training, run with the support of the capabilities of the terminal device, and the AI model loaded with the dataset can work and output results according to the set functions.

4. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, characterized in that The characteristic parameters include at least one of the following: AI model usage AImodel_case, AI model algorithm type AImodel_type, dataset size DATA_size, dataset type DATA_type, number of data segments DATA_segment.

5. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the first information includes an indication of the feedback time of the second information.

6. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the first information is indicated by DCI information carried by PDCCH, or the first information is jointly indicated by DCI information carried by PDCCH and high-layer information carried by PDSCH.

7. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the second information is carried by PUCCH or PUSCH; the fourth information is carried by PUCCH or PUSCH.

8. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the third information is indicated by DCI information carried by PDCCH, or the third information is jointly indicated by DCI information carried by PDCCH and high-layer information carried by PDSCH.

9. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein each indication information in the second information is used to confirm whether the value of at least one characteristic parameter is available or unavailable.

10. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the third information includes relevant information of the data set, and the relevant information includes at least one of the following information: data format, data quantity, division of training set and validation set.

11. The method for jointly deploying mobile communication network data and model according to any one of claims 1 to 3, wherein the fourth information includes the available time of the AI model trained by the data set.

12. A network device for implementing the method for jointly deploying mobile communication network data and model according to any one of claims 1 to 2, 4 to 11, wherein at least one module in the network device is used for at least one of the following functions: sending the first information and the third information; receiving the second information and the fourth information; determining the input data set of the AI model in response to the second information; determining the availability of the data set in response to the fourth information.

13. A terminal device for implementing the method for jointly deploying mobile communication network data and model according to any one of claims 1, 3 to 11, wherein at least one module in the terminal device is used for at least one of the following functions: receiving the first information and the third information; sending the second information and the fourth information; determining the value of at least one of the characteristic parameters in response to the first information; determining the availability of the data set in response to the third information.

14. A communication device, characterized in that, Comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the computer program is executed by the processor, the steps of the method for jointly deploying mobile communication network data and model according to any one of claims 1 to 11 are implemented.

15. A computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for jointly deploying mobile communication network data and a model according to any one of claims 1 to 11.

16. A mobile communication system, comprising at least one network device according to claim 12 and / or at least one terminal device according to claim 13.

Images