Model request method, device, communication device and readable storage medium

Abstract

The present application discloses a model request method, an apparatus, a communication device, and a readable storage medium, which belong to the technical field of wireless communication. The model request method of an embodiment of the present application includes: a first communication device sending a first request to request multiple models for one or more data analysis tasks; and a first communication device receiving a first response including related information of the multiple models that satisfy the first request.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to Chinese Patent Application No. 202211250071.8, filed in China on October 12, 2022, the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the technical field of wireless communication, and in particular to a model request method, apparatus, communication device and readable storage medium. [Background technology]

[0003] In a communication network in the related art, a model receiving end can request a trained model from a model sending end as needed to analyze data. Currently, a model receiving end can only request one model from a model sending end at a time. If multiple models are required simultaneously, multiple signalings need to be sent multiple times, which results in problems such as an increase in network load. Summary of the Invention

[0004] The embodiments of the present invention provide a model request method, device, communication device and readable storage medium, which can solve the problem that a model receiving end can only request one model from a model sending end at a time.

[0005] In the first aspect, a first communication device transmitting a first request to request a plurality of models for one or more data analysis tasks; and receiving, by the first communication device, a first response including relevant information of a plurality of models that satisfy the first request.

[0006] In a second aspect, a second communication device receiving a first request to request a plurality of models for one or more data analysis tasks; the second communication device obtaining a plurality of models that satisfy the first requirement; the second communication device sending a first response including information related to the plurality of models.

[0007] In a third aspect, a first sending module for sending a first request to request a plurality of models for one or more data analysis tasks; a first receiving module for receiving a first response including relevant information of a plurality of models that satisfy the first request.

[0008] In a fourth aspect, a first receiving module for receiving a first request to request a plurality of models for one or more data analysis tasks; an acquisition module for acquiring a plurality of models that satisfy the first requirement; a first sending module for sending a first response including relevant information of the plurality of models.

[0009] In a fifth aspect, there is provided a communications device comprising a processor and a memory, wherein the memory stores programs or commands executable on the processor, and wherein, when the programs or commands are executed by the processor, the steps of the method according to the first or second aspect are realized.

[0010] In a sixth aspect, there is provided a communications device comprising a processor and a communications interface, the communications interface being used to send a first request to request a plurality of models for one or more data analysis tasks, and to receive a first response including associated information of the plurality of models that satisfy the first request.

[0011] In a seventh aspect, there is provided a communications device comprising a processor and a communications interface, wherein the communications interface is adapted to receive a first request for requesting a plurality of models for one or more data analysis tasks, the processor is adapted to obtain a plurality of models that satisfy the first request, and the communications interface is further adapted to send a first response including relevant information for the plurality of models.

[0012] In an eighth aspect, there is provided a communication system including a first communication device usable to perform steps of the model request method described in the first aspect, and a second communication device usable to perform steps of the model request method described in the second aspect.

[0013] In a ninth aspect, there is provided a readable storage medium having stored thereon a program or command, the program or command causing the steps of the method according to the first aspect to be realized or the steps of the method according to the second aspect to be realized when the program or command is executed by a processor.

[0014] In a tenth aspect, there is provided a chip comprising a processor and a communication interface, the communication interface being coupled to the processor, the processor executing a program or command to implement the method of the first aspect or used to implement the method of the second aspect.

[0015] In an eleventh aspect, there is provided a computer program / program product stored on a storage medium and configured to, when executed by at least one processor, implement the steps of the model request method according to the first or second aspect.

[0016] In an embodiment of the present application, the first communication device can request multiple models at once, reducing signaling consumption within the network. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a block diagram of a wireless communication system to which an embodiment of the present application can be applied. [Figure 2] Schematic diagram of the signaling interactions between AnLF-containing NWDAFs and MTLF-containing NWDAFs. [Figure 3] 1 is a flowchart (part 1) of a model request method according to an embodiment of the present application. [Figure 4] 1 is a flowchart (part 2) of a model request method according to an embodiment of the present application. [Figure 5] 1 is a flowchart (part 3) of a model request method according to an embodiment of the present application. [Figure 6] 10 is a flowchart (part 4) of a model request method according to an embodiment of the present application. [Figure 7] 1 is a structural schematic diagram (part 1) of a model request device according to an embodiment of the present application. [Figure 8] FIG. 2 is a structural schematic diagram (part 2) of a model request device according to an embodiment of the present application. [Figure 9] 1 is a structural schematic diagram of a communication device according to an embodiment of the present application; [Figure 10] FIG. 2 is a hardware structure schematic diagram of a terminal according to an embodiment of the present application; [Figure 11] 1 is a hardware structure schematic diagram (part 1) of a network side device according to an embodiment of the present application; [Figure 12] FIG. 2 is a second schematic diagram of the hardware structure of a network-side device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0018] The technical solutions in the embodiments of the present application will be clearly explained below with reference to the drawings in the embodiments of the present application, and it should be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments, and all other embodiments obtained by those skilled in the art based on the embodiments of the present application shall fall within the scope of protection of the present application.

[0019] The terms "first," "second," and the like in the specification and claims of this application are not intended to describe a particular order or chronological order, but rather to distinguish between similar objects. These terms may be interchanged where appropriate so that the embodiments of this application can be implemented in an order other than that illustrated or described herein. It should also be understood that the objects distinguished by "first" and "second" generally belong to one category, and the number of objects is not limited; for example, the first object may be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the " / " symbol generally indicates that the related objects before and after are in an "or" relationship.

[0020] It should be noted that the techniques described in the embodiments of this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but may also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-Carrier Frequency Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in the embodiments of this application are often used interchangeably, and the described techniques may be used in other systems and wireless technologies in addition to those mentioned above. In the following description, New Radio (NR) systems are described as examples, and NR terminology is used in much of the following description; however, these technologies may be used in conjunction with 6th Generation (6G) networks. thIt may also be applied to applications other than NR system applications, such as 6G (Generation 6G) communication systems.

[0021] 1 shows a block diagram of a wireless communication system to which an embodiment of the present application can be applied. The wireless communication system includes a terminal 11 and a network side device 12. Here, the terminal 11 may be a mobile phone, a tablet personal computer, a laptop computer (also called a notebook computer), a personal digital assistant (PDA), a personal digital assistant, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, a vehicle user equipment (VUE), a pedestrian user equipment (PUE), a smart home (home devices equipped with wireless communication functions such as a refrigerator, a television, a washing machine, furniture, etc.), a game console, a personal computer (PC), an automated teller machine, a kiosk, or other terminal side device. The wearable device includes a smart watch, a smart bracelet, a smart headphone, a smart glass, smart jewelry (such as a smart bracelet, a smart bangle, a smart ring, a smart necklace, a smart anklet bangle, or a smart bracelet), a smart wristband, and smart wear. Note that, in the embodiments of the present application, the specific type of the terminal 11 is not limited. The network side equipment 12 may include an access network equipment or a core network equipment, where the access network equipment may also be referred to as a radio access network equipment, a radio access network (RAN), a radio access network function, or a radio access network unit.The access network equipment may include a base station, a Wireless Local Area Network (WLAN) access point, a WiFi node, etc., and the base station may be called a Node B, an evolved Node B (eNB), an access point, a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a Home B node, a Home evolved B node, a Transmitting Receiving Point (TRP), or any other appropriate term in the field. As long as the same technical effect can be achieved, the base station is not limited to a specific technical term. It should be noted that although the embodiments of this application only describe base stations in an NR system as examples, the specific type of the base station is not limited.Core network devices include core network nodes, core network functions, mobility management entities (MMEs), access and mobility management functions (AMFs), session management functions (SMFs), user plane functions (UPFs), policy control functions (PCFs), policy and charging rules functions (PCRFs), edge application server discovery functions (EASDFs), unified data management (UDMs), unified data repository (UDRs), home subscriber servers (HSSs), centralized network configuration (CNCs), network repository functions (NRFs), network exposure functions (NEFs), local NEFs (or L-NEFs), binding support functions (BSFs), and application functions (Application Node Functions). The core network device may include, but is not limited to, at least one of the following: a QoS function (e.g., QoS function ...

[0022] First, the technical points of the present application will be briefly explained below.

[0023] 1. The Network Data Analytics Function (NWDAF) can be divided into two network elements as follows:

[0024] An NWDAF containing a Model Training Logical Function (MTLF) used to generate and train models.

[0025] An NWDAF containing an Analytics Logical Function (AnLF) that is used to reason based on the acquired models and generate predictive information or summaries of historical data.

[0026] See step 1 below in Figure 2.

[0027] By invoking the Nnwdaf_MLModelProvision_Subscribe / Nnwdaf_MLModel Provision_Unsubscribe service operations, an NWDAF service consumer (i.e., an NWDAF including an AnLF) subscribes to, modifies, or unsubscribes from a set of trained Machine Learning (ML) models (also called Artificial Intelligence (AI) models) associated with a set of Analytic Identifiers (IDs).

[0028] Upon receiving a subscription for an ML model associated with an analysis ID, the NWDAF, including the MTLF, Determine whether an existing trained ML model is available for subscription; or It can be determined whether further training of an existing trained ML model needs to be triggered.

[0029] If the NWDAF, including the MTLF, determines that further training is necessary, it can initiate data collection from the Network Function (NF) (e.g., AMF / Data Collection Coordination Function (DCCF) / Analytics Data Repository Function (ADRF)) and the User Equipment (UE)'s (also known as terminal) applications (Application Function (AF) or OAM (Operation, Administration, Maintenance)) to generate an ML model.

[0030] When calling the service to change subscription or unsubscribe, the NWDAF service consumer includes an identifier (subscribe related ID) to perform the change when calling Nnwdaf_MLModelProvision_Subscribe.

[0031] See step 2 below in Figure 2.

[0032] When an NWDAF service consumer subscribes to a set of trained ML models associated with a set of analysis IDs, the NWDAF including the MTLF notifies the NWDAF service consumer of the trained "ML model information" (file address containing the set of trained ML models) by calling the Nnwdaf_MLModelProvision_Notify service operation.

[0033] If the NWDAF, including the MTLF, determines that the previously provided trained ML model needs to be retrained in step 1, it further invokes the NWDAF_MLModelProvision_Notify service operation to notify the availability of the retrained ML model.

[0034] When step 1 is used for a subscribe change (i.e., includes a subscribe related ID), the NWDAF including the MTLF can provide a new training ML model that is different from the one previously provided or retrain the ML model by calling the Nnwdaf_MLModelProvision_Notify service operation.

[0035] 2. Contents provided by ML models 2.1. Consumers of the ML model provisioning service (i.e., NWDAFs including AnLFs) can provide input parameters, such as analytical information for the requested ML model.

[0036] The requested analysis information of the ML model is 1) A list of analysis IDs that identify analyses using ML models; 2) (Selective) Single Network Slice Selection Assistance Information (S-NSSAI), ML model filter information that allows the selection of an ML model requiring analysis, such as an area of ​​interest, and 3) (Optional) A target for the ML model report, indicating for which the ML model is requested, such as a specific UE, a set of UEs, or any UE (i.e., all UEs); and 4) ML model report information, wherein the ML model report information includes: (Applicable only to Nnwdaf_MLModelProvision_Subscribe) ML model report information parameters determined based on the event report information parameters defined in Table 4.15.1-1, TS 23.502 [3]; and a target period of the ML model representing a time interval of the ML model that requires (selective) analysis, the time interval being expressed in terms of an actual start time and an actual end time (e.g., in Coordinated Universal Time (UTC)); It has the following parameters: a notification address (and notification association ID) defined in 4.15.1 of TS 23.502 [3], which allows notifications received from the NWDAF containing the MTLF to be associated with this subscription.

[0037] 2.2, the output information provided by the NWDAF, including the MTLF, to consumers of the ML model provisioning service operation is (Applicable only to Nnwdaf_MLModelProvision_Notify) Notification related information and ML model information including the address (e.g., Uniform Resource Locator (URL) or Fully Qualified Domain Name (FQDN)) of the ML model file for the analysis ID; (Optional) a validity period, which indicates the period during which the provided ML model information applies; and (Optional) Spatial validity, which represents the area to which the provided ML model information applies.

[0038] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the model request method, apparatus, communication device and readable storage medium provided in the embodiments of the present application will be described in detail with reference to the drawings according to several embodiments and application scenarios.

[0039] Referring to FIG. 3, the embodiment of the present application is a first communication device transmitting 31 a first request to request a plurality of models for one or more data analysis tasks; The first communication device receives 32 a first response including relevant information of a plurality of models that satisfy the first request.

[0040] In the embodiment of the present application, multiple models can be requested from the model sender at one time, reducing signaling consumption within the network.

[0041] In an embodiment of the present application, optionally, the task identifiers of the plurality of data analysis tasks are the same.Optionally, the task identifiers of the plurality of data analysis tasks are the same, i.e., the plurality of data analysis tasks are data analysis tasks of the same type.

[0042] In an embodiment of the present application, optionally, the first communication device may be referred to as a model receiving end, and may include at least one of a terminal (e.g., a modem within the terminal (responsible for networking activities such as making calls, connecting to the Internet, sending short messages, etc.)), an access network element, a core network element, an NWDAF, and an NWDAF including an AnLF.

[0043] In an embodiment of the present application, optionally, the first communication device sends a first request to a second communication device, and receives a first response sent from the second communication device.

[0044] In an embodiment of the present application, optionally, the second communication device may be referred to as a model transmitting end, which is responsible for training and distributing the model, and may include at least one of an access network element (e.g., a base station, a base station gateway, etc.), a core network element, an NWDAF, an NWDAF including an MTLF, and a third-party server.

[0045] In an embodiment of the present application, optionally, the first requirement includes at least one of 1) to 6).

[0046] 1) Task identifier information The task identifier information is used to identify the type of the data analysis task. Optionally, task identifiers belonging to the same type of data analysis task are the same.

[0047] The task identifier may be, for example, an Analytic ID.

[0048] 2) Task condition restriction information The task condition limiting information may also be referred to as analytical filter information, and is used to indicate filter information for data analysis results, including, for example, areas of interest (AOI), single network slice selection assistance information (S-NSSAI), and data network name (DNN).

[0049] 3) Task analysis information The task analytic target information can be understood as the target of analytic reporting, and is used to indicate whether the target of task analysis is a specific device, multiple devices, or all devices.

[0050] 4) First instruction information for instructing that multiple models are requested at once In an embodiment of the present application, optionally, the first indication information may appear explicitly, such as a specific information source, or may appear implicitly, such as being understood based on the name of the signaling in which the first request is located.

[0051] 5) Information distinguishing the plurality of models Optionally, the distinguishing information is: a plurality of levels of accuracy information corresponding to the plurality of models, such as high accuracy, medium accuracy, and low accuracy; A plurality of time period information corresponding to the plurality of models, which may appear in the form of a list of time periods of interest, such as morning, afternoon, and evening time periods; Location information corresponding to the plurality of models, which may be referred to as area information, and may be a city or cell range, etc., and may appear, for example, in the form of an area of ​​interest list or in other forms; and slice information corresponding to the plurality of models.

[0052] Here, the accuracy information may be accuracy, maximum absolute error (MAE), precision, or the like.

[0053] In an embodiment of the present application, optionally, all information of the multiple models other than the distinguishing information is the same, for example, the multiple models are multiple models for analyzing the load situation of the target network element with different precision.

[0054] 6) Model-specific information to limit the scope of use of the model Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0055] The model limitation information is used to assist the model sender in selecting or training a model, for example, the data for training the model must be within a specific location range or slice.

[0056] In an embodiment of the present application, optionally, the model-limited information can be obtained based on task condition-limited information, and the first request may include only task condition-limited information or only model-limited information.

[0057] In an embodiment of the present application, optionally, before the step of the first communication device sending the first request: the first communication device receiving a task request and then generating the first request in response to the task request; and the first communication device, after receiving a plurality of task requests within a preset time range, generating the first request in response to the plurality of task requests.

[0058] The task request is used to request the execution of a data analysis task, and the data analysis task for the first request is obtained based on the data analysis task in the task request or is the same as the data analysis task in the task request.

[0059] Optionally, the task identifiers of the data analysis tasks corresponding to the task requests are the same, i.e., the task types of the data analysis tasks are the same.

[0060] Optionally, the task request comprises: task identifier information; Task condition limiting information, and analysis target information of the task.

[0061] Here, the task condition limitation information may also be called analytical filter information, and is used to indicate filter information of data analysis results, including, for example, areas of interest (AOI), single network slice selection assistance information (S-NSSAI), and data network name (DNN), etc.

[0062] The task analytic target information can be understood as the target of analytic reporting, and is used to indicate whether the target of task analysis is a specific device, multiple devices, or all devices.

[0063] In an embodiment of the present application, optionally, the first communication device receives a task request sent from a third communication device, which may be called a data service consumer, and may include at least one of an application processor (AP, responsible for an operating system, a user interface, an application program, etc.) and a core network element (e.g., AMF, SMF, etc.).

[0064] In an embodiment of the present application, optionally, the multiple task requests received by the first communication device may be multiple task requests sent by the same third communication device, or multiple task requests sent by multiple third communication devices.

[0065] Alternatively, the task request can be sent via Nnwdaf_AnalyticsSubscription_Subscribe.

[0066] In an embodiment of the present application, optionally, the relevant information of the model is: 1) Model information, which is the model itself or address information for storing the model; 2) model identifier information; and 3) Model description information, which may be called model-specific information, etc. Selectively, Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; slice information corresponding to the model; and 4) task identifier information; 5) Task condition limiting information, 6) Task analysis target information.

[0067] Referring to FIG. 4, in an embodiment of the present application, optionally, the method includes: a step 41 in which the first communication device requests desired associated data based on the received task request; The method further includes step 42, in which the first communication device analyzes the relevant data using the plurality of models to obtain a data analysis result.

[0068] In an embodiment of the present application, optionally, the first communication device requests desired relevant data from the fourth communication device, which may be referred to as a data source and may include at least one of a core network element (e.g., AMF, SMF), an access network element (e.g., base station), etc.

[0069] In an embodiment of the present application, optionally, the step of the first communication device analyzing the relevant data using the plurality of models includes the first communication device analyzing the relevant data using different models for different received task requests.

[0070] In an embodiment of the present application, optionally, after the step of obtaining a data analysis result, the method further includes the step of the first communication device sending the data analysis result to a third communication device.

[0071] For example, in one embodiment, when a UE requests a specific model or a specific intelligentization-related task from the network, for example, the consumer AP in the UE sends a task request to the model receiving end (e.g., the modem in the UE) to request the execution of a specific intelligentization task such as predicting signal strength at a specific time, decoding / encoding, etc., the model receiving end (e.g., the modem in the UE) sends a first request to the model sending end (e.g., the base station) to request the acquisition of multiple models that can complete the task, the model sending end selects an internal trained model that meets the first request, or sends a data request to a data source to request the acquisition of training data to train the model, and obtains / generates a model that meets the first request, the model sending end returns multiple models that meet the first request to the model receiving end, and the model receiving end can then use the models to complete the task requested by the consumer and feed back the results to the consumer.

[0072] In another embodiment, when a network element in a core network requests a specific intelligentization-related task, for example, a consumer network element SMF or AMF etc. sends a task request to a model receiving end (e.g., an NWDAF including an AnLF) to request the performance of a specific intelligentization task, such as predicting the network load situation at a specific time; the model receiving end sends a first request to a model sending end (e.g., an NWDAF including an MTLF) to request the acquisition of multiple models that can complete the task; the model sending end selects an internal trained model that meets the first request, or sends a data request to a data source to request the acquisition of training data to train the model, and obtains / generates a model that meets the first request; the model sending end returns multiple models that meet the first request to the model receiving end; and the model receiving end can use the models to complete the task requested by the consumer and feed back the results to the consumer.

[0073] Referring to FIG. 5, the embodiment of the present application is a second communication device receiving 51 a first request to request a plurality of models for one or more data analysis tasks; the second communication device obtaining 52 a plurality of models satisfying the first requirement; The second communication device transmits a first response including relevant information of the plurality of models (53).

[0074] In an embodiment of the present application, multiple models can be returned to the model receiving end at once to reduce signaling consumption within the network.

[0075] In an embodiment of the present application, optionally, the task identifiers of the multiple data analysis tasks are the same.

[0076] In an embodiment of the present application, optionally, the second communication device may be referred to as a model transmitting end, which is responsible for training and distributing the model, and may include at least one of an access network element (e.g., a base station, a base station gateway, etc.), a core network element, an NWDAF, an NWDAF including an MTLF, and a third-party server.

[0077] In an embodiment of the present invention, optionally, the second communication device receives the first request sent from the first communication device, and sends a first response to the first communication device.

[0078] In an embodiment of the present application, optionally, the first communication device may be referred to as a model receiving end, and may include at least one of a terminal (e.g., a modem within the terminal (responsible for networking activities such as making calls, connecting to the Internet, sending short messages, etc.)), an access network element, a core network element, an NWDAF, and an NWDAF including an AnLF.

[0079] In an embodiment of the present application, optionally, the first request is: 1) task identifier information; 2) Task condition limiting information, 3) Task analysis information, 4) first instruction information for instructing that multiple models are requested at once; 5) Distinguishing information of the plurality of models, Selectively, multiple levels of accuracy information corresponding to the multiple models; a plurality of time zone information corresponding to the plurality of models; location information, which may be referred to as area information, corresponding to the plurality of models; time zone information corresponding to the plurality of models; and distinction information including at least one of the above. 6) Model limitation information for limiting the range of use of the model; Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0080] In an embodiment of the present application, optionally, the step of the second communication device obtaining a plurality of models that satisfy the first requirement comprises: said second communication device obtaining a stored model that satisfies said first request; The second communication device includes at least one of: collecting training data based on the first request; and performing model training using the training data to obtain a trained model.

[0081] In an embodiment of the present application, optionally, the second communication device may obtain a model that satisfies the first requirement from a locally stored model, or may obtain a model that satisfies the first requirement from a model stored in another communication device (e.g., an ADRF).

[0082] In an embodiment of the present application, optionally, the second communication device collects training data from a fifth communication device, which may be referred to as a data source and may include at least one of a core network element (e.g., AMF, SMF), an access network element (e.g., base station), etc.

[0083] In an embodiment of the present application, optionally, the step of the second communication device obtaining a stored model that satisfies the first requirement comprises: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, and, based on at least one of the first request, the second communication device obtains a stored model that satisfies the first request.

[0084] For example, the second communication device can determine a model that satisfies the first requirement based on a combination of the multiple model distinction information, model limitation information, and / or task condition limitation information. For example, if the used distinction information includes accuracy information and time period information and the model limitation information includes area information, one of the determined multiple models may have high accuracy, be in the cell 1 area, and be used from 7:00 to 11:00 every day, another model may have medium accuracy, be in the cell 1 area, and be used from 7:00 to 11:00 every day, and yet another model may have low accuracy, be in the cell 1 area, and be used from 7:00 to 11:00 every day.

[0085] In an embodiment of the present application, optionally, the step of the second communication device collecting training data based on the first request includes: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, and the second communication device collects training data based on at least one of the first request and the task analysis target information.

[0086] For example, the second communication device trains a model that matches the accuracy information based on the accuracy information among the distinction information of the multiple models in the first request.

[0087] The second communication device obtains training data that matches the location information and / or slice information based on the model limiting information in the first request or the location information and / or slice information in the condition limiting information of the task, and trains a model.

[0088] In an embodiment of the present application, optionally, the relevant information of the model is: 1) Model information, which is the model itself or address information for storing the model; 2) model identifier information; and 3) Model description information, It is used to explain the characteristics of the model, for example, it may be used to explain the range in which the model can be used, such as time of day, location, slice information, etc., or it may be used to explain the characteristics of the model, such as accuracy information corresponding to the model, That is, Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; slice information corresponding to the model; and 4) task identifier information; 5) Task condition limiting information, 6) Task analysis target information.

[0089] The following describes the model request method of the embodiment of the present application by way of example according to a specific application scenario.

[0090] Example 1 of the present application Referring to FIG. 6, the model request method of the embodiment of the present application includes the following steps 1a to 6.

[0091] In step 1a, optionally, a consumer initiates a task request to the model receiving end to request acquisition of analysis results for a target task. The task request is used to request specific data analysis results and may include task information (task identifier information, task condition limiting information, task analysis target information, etc.). The task identifier information is used to indicate the desired data analysis results, and the data analysis results may be multiple data analysis results for a specific type of task. The task condition limiting information and filter information indicating the data analysis results are used to further limit the scope of the task and vary depending on the task. The filter information may include at least one of, for example, a region range, slice information, accuracy level, time, etc.

[0092] In step 1b, optionally, the model receiving end receives a plurality of task requests, which may be, for example, a plurality of task requests sent from a particular consumer or a plurality of task requests sent from a plurality of consumers.

[0093] In step 2a, the model receiving end determines whether to initiate a first request to request multiple models. In one implementation, after receiving a task request, the model receiving end determines to initiate a first request for the task request to request multiple models, and can request multiple related models in advance to avoid subsequent multiple requests for the model, thereby reducing signaling consumption. The model receiving end may receive multiple task requests with the same task identifiers for corresponding multiple data analysis tasks at the same time or within a predetermined time range, and the model receiving end can initiate a first request for the multiple task requests to request multiple models.

[0094] In step 2b, the model receiving end sends a first request to the model sending end to request a plurality of models so that the models can be used later to complete data analysis.

[0095] In an embodiment of the present application, optionally, the first request is: 1) task identifier information; 2) Task condition limiting information, 3) Task analysis information, 4) first instruction information for instructing that multiple models are requested at once; 5) Distinguishing information of the plurality of models, Selectively, multiple levels of accuracy information corresponding to the multiple models, such as high accuracy, medium accuracy, and low accuracy; a plurality of time zone information corresponding to the plurality of models, such as morning, afternoon, and night time zones; location information corresponding to the plurality of models; slice information corresponding to the plurality of models; and distinction information including at least one of the above. 6) Model limitation information for limiting the range of use of the model; Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0096] In an embodiment of the present application, when the model receiving end is an NWDAF including an AnLF and the model transmitting end is an NWDAF including an MTLF, when the NWDAF including an AnLF sends a first request to the NWDAF including an MTLF, it can be sent via signaling such as Nnwdaf_MLModelInfo_Request or Nnwdaf_MLModelProvision_subscribe.

[0097] In step 3, the model sending end selects a model or a target data source that meets the first requirement based on the first requirement, sends a data request to the target data source to request training data, and uses the training data to train the model.

[0098] Specifically, the model sending end can determine the category of training data to be collected based on the task information in the first request, and further determine the category of a specific device, and send a data request to the device to request acquisition of related training data. If it determines that network element load data information needs to be collected based on the task information, it determines to send a data request to the UPF network element to acquire training data (e.g., based on internal logic or pre-configuration). After obtaining the related training data, the model sending end uses the training data to perform model training to obtain a model that meets the first request. Or, if a trained model that meets the first request is stored in the model sending end (e.g., the model sending end receives a similar first request and a trained model has already been generated), it selects the model that meets the first request.

[0099] In step 4, the model sending end sends a first response to the model receiving end, including a plurality of models that satisfy the first request, and may send the models themselves, such as files, or may send address information for storing the models, etc. In addition, the first response may include model identifier information, model description information, etc.

[0100] In step 5, after receiving the multiple models sent from the model sending end, the model receiving end can perform model inference using different models for different task requests (e.g., the task requests received in step 1b). When performing model inference, the model receiving end first requests related data required for the model (e.g., input data of the model) from the data source device based on the information in the task request.

[0101] In step 6, the model receiving end feeds back the data analysis result to the consumer. The data analysis result is used to indicate the analysis result for the task, and the content of the data analysis result varies depending on the task. For example, for a network element load task, the data analysis result may be the load situation of the target network element at a specific time in the future, such as the UPF network element load being high in the morning of the next day.

[0102] The model request method provided in the embodiments of the present application may be executed by a model request device. In the embodiments of the present application, the model request device provided in the embodiments of the present application will be described by taking the execution of the model request method by the model request device as an example.

[0103] Referring to FIG. 7, the embodiment of the present application is a first sending module 71 for sending a first request to request a plurality of models for one or more data analysis tasks; There is further provided a model requesting device 70 including a first receiving module 72 for receiving a first response including relevant information of a plurality of models that satisfy said first request.

[0104] In the embodiment of the present application, multiple models can be requested from the model sender at one time, reducing signaling consumption within the network.

[0105] Optionally, the task identifiers of the plurality of data analysis tasks are the same.

[0106] Optionally, the first request is: task identifier information; Task condition limiting information, Task analysis target information, First instruction information for instructing that multiple models are requested at once; Distinguishing information of the plurality of models; and model limitation information for limiting the range of use of the model.

[0107] Optionally, the distinguishing information is: multiple levels of accuracy information corresponding to the multiple models; and a plurality of time period information corresponding to the plurality of models.

[0108] Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0109] Optionally, the model requesting device 70: a first generating module for receiving a task request and then generating the first request for the task request; a second generating module for generating the first request for a plurality of task requests after receiving the plurality of task requests within a predetermined time range.

[0110] Optionally, the task identifiers of the multiple data analysis tasks corresponding to the multiple task requests are the same.

[0111] Optionally, the task request comprises: task identifier information; Task condition limiting information, and analysis target information of the task.

[0112] Optionally, the relevant information of the model is: Model information and model identifier information; Model description information; task identifier information; Task condition limiting information, and analysis target information of the task.

[0113] Optionally, the model description information comprises: Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; and slice information corresponding to the model.

[0114] Optionally, the model requesting device 70: a request module for requesting desired associated data based on the received task request; and an analysis module for analyzing the relevant data using the plurality of models to obtain a data analysis result.

[0115] Optionally, the analysis module is adapted to analyze the associated data using different models for different received task requests.

[0116] Optionally, the model requesting device 70: The data analysis device further includes a second transmitting module for transmitting the data analysis result to a third communication device.

[0117] The model request device provided in the embodiments of the present application can implement each process implemented in the method embodiments of Figures 3 and 4, and achieve the same technical effects, so detailed descriptions will be omitted here to avoid repetition.

[0118] Referring to FIG. 8, the embodiment of the present application is a first receiving module 81 for receiving a first request to request a plurality of models for one or more data analysis tasks; an acquisition module 82 for acquiring a plurality of models that satisfy the first requirement; There is further provided a model requesting device 80 including: a first sending module 83 for sending a first response including relevant information of the plurality of models.

[0119] In an embodiment of the present application, multiple models can be returned to the model receiving end at once to reduce signaling consumption within the network.

[0120] Optionally, the task identifiers of the plurality of data analysis tasks are the same.

[0121] Optionally, the first request is: task identifier information; Task condition limiting information, Task analysis target information, First instruction information for instructing that multiple models are requested at once; Distinguishing information of the plurality of models; and model limitation information for limiting the range of use of the model.

[0122] Optionally, the distinguishing information is: multiple levels of accuracy information corresponding to the multiple models; and a plurality of time period information corresponding to the plurality of models.

[0123] Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0124] Optionally, the acquisition module 82: Obtaining a stored model that satisfies the first requirement; and collecting training data based on the first request; performing model training using the training data; and obtaining a trained model.

[0125] Optionally, the acquisition module 82: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, and the analysis target information of the task, based on at least one of the first requirements, to obtain a stored model that satisfies the first requirement.

[0126] Optionally, the acquisition module 82: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, and the task analysis target information in the first request, and is used to collect training data based on at least one of the first request and the task analysis target information.

[0127] Optionally, the relevant information of the model is: the model itself or address information for storing the model; model identifier information; Model description information; and task information corresponding to the model.

[0128] Optionally, the model description information comprises: Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; and slice information corresponding to the model.

[0129] The model request device provided in the embodiment of the present application can implement each process implemented in the method embodiment of Figure 5 and achieve the same technical effect, so as not to be repeated, detailed description will be omitted here.

[0130] 9, an embodiment of the present application further provides a communication device 90 including a processor 91 and a memory 92, wherein the memory 92 stores a program or command executable on the processor 91. For example, when the communication device 90 is a first communication device, the program or command is executed by the processor 91 to realize the steps of the embodiment of the model request method executed by the first communication device described above, and the same technical effect can be achieved. When the communication device 90 is a second communication device, the program or command is executed by the processor 91 to realize the steps of the embodiment of the model request method executed by the second communication device described above, and the same technical effect can be achieved. To avoid repetition, detailed descriptions will be omitted here.

[0131] An embodiment of the present application further provides a terminal including a processor and a communication interface, the communication interface being used for sending a first request to request a plurality of models for one or more data analysis tasks and receiving a first response including relevant information of the plurality of models that satisfy the first request. The terminal embodiment corresponds to the method embodiment on the first communication device side, and the implementation processes and realization methods in the method embodiment are all applicable to the terminal embodiment, and the same technical effects can be achieved. Specifically, Figure 10 is a schematic diagram of the hardware structure of a terminal implementing the embodiment of the present application.

[0132] The terminal 100 includes at least some of the following components, but is not limited to: a radio frequency unit 101, a network module 102, an audio output unit 103, an input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, and a processor 1010.

[0133] As will be understood by those skilled in the art, the terminal 100 may further include a power source (e.g., a battery) for powering each component, and the power source may be logically connected to the processor 1010 through a power management system, which may further realize functions such as charge / discharge management and power consumption management. The structure of the terminal shown in Figure 10 is not intended to limit the terminal, and the terminal may include more or fewer components than those shown, or a combination of some components, or a different component arrangement, and detailed description thereof will be omitted here.

[0134] It should be understood that in the embodiment of the present application, the input unit 104 may include a graphics processing unit (GPU) 1041 that processes image data of still or video images captured by an image capture device (e.g., a camera) in a video capture mode or an image capture mode, and a microphone 1042. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 107 includes at least one of a touch panel 1071 and other input devices 1072. The touch panel 1071 is also called a touch screen. The touch panel 1071 may include two parts: a touch detection device and a touch controller. The other input devices 1072 may include, but are not limited to, a physical keyboard, function buttons (e.g., volume control buttons, switch buttons, etc.), a trackball, a mouse, and a control lever, and detailed descriptions thereof will be omitted here.

[0135] In the embodiment of the present application, the radio frequency unit 101 can receive downlink data from the network side device, then transmit the data to the processor 1010 for processing, and can also transmit uplink data to the network side device. Typically, the radio frequency unit 101 includes, but is not limited to, an antenna, an amplifier, a receiver / transmitter, a coupler, a low-noise amplifier, a duplexer, etc.

[0136] The memory 109 can be used to store software programs or commands and various data. The memory 109 may mainly include a first storage area for storing programs or commands and a second storage area for storing data. Here, the first storage area can store an operating system, an application or command required for at least one function (e.g., an audio playback function, an image playback function, etc.), etc. The memory 109 may include volatile memory or nonvolatile memory, or may include both volatile memory and nonvolatile memory. Here, the nonvolatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synch link dynamic random access memory (SLDRAM), and direct Rambus random access memory (DRRAM). Memory 109 in embodiments of the present application includes, but is not limited to, these memories and any other suitable type.

[0137] The processor 1010 may include one or more processing units, and optionally, an application processor that mainly processes operations related to an operating system, a user interface, applications, etc., and a modem processor that mainly processes wireless communication signals, such as a baseband processor, are integrated into the processor 1010. It is understood that the modem processor need not be integrated into the processor 1010.

[0138] Here, the high frequency unit 101 is used to send a first request to request multiple models for one or more data analysis tasks, and to receive a first response including relevant information of the multiple models that satisfy the first request.

[0139] In the embodiment of the present application, multiple models can be requested from the model sender at one time, reducing signaling consumption within the network.

[0140] Optionally, the task identifiers of the plurality of data analysis tasks are the same.

[0141] Optionally, the first request is: task identifier information; Task condition limiting information, Task analysis target information, First instruction information for instructing that multiple models are requested at once; Distinguishing information of the plurality of models; and model limitation information for limiting the range of use of the model.

[0142] Optionally, the distinguishing information is: multiple levels of accuracy information corresponding to the multiple models; and a plurality of time period information corresponding to the plurality of models.

[0143] Optionally, the model-specific information is: Location information corresponding to the model; and slice information corresponding to the model.

[0144] Optionally, the processor 1010 is used to generate the first request for a task request after receiving the task request, and / or to generate the first request for the multiple task requests after receiving multiple task requests within a predetermined time range.

[0145] Optionally, the task identifiers of the multiple data analysis tasks corresponding to the multiple task requests are the same.

[0146] Optionally, the task request comprises: task identifier information; Task condition limiting information, and analysis target information of the task.

[0147] Optionally, the relevant information of the model is: Model information and model identifier information; Model description information; task identifier information; Task condition limiting information, and analysis target information of the task.

[0148] Optionally, the model description information comprises: Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; and slice information corresponding to the model.

[0149] Optionally, the processor 1010 is adapted to request desired relevant data based on the received task request, and analyze the relevant data using the plurality of models to obtain a data analysis result.

[0150] Optionally, the processor 1010 is adapted to analyze the associated data using different models for different received task requests.

[0151] Optionally, the high frequency unit 101 is further used for transmitting the data analysis result to a third communication device.

[0152] An embodiment of the present application further provides a network-side device, including a processor and a communication interface, wherein the communication interface is used for sending a first request to request a plurality of models for one or more data analysis tasks, and receiving a first response including relevant information of the plurality of models that satisfy the first request. The embodiment of the network-side device corresponds to the method embodiment of the second communication device, and the implementation processes and realization methods in the method embodiments are all applicable to the embodiment of the network-side device, and can achieve the same technical effects.

[0153] An embodiment of the present application further provides a network-side device including a processor and a communication interface, wherein the communication interface is used for receiving a first request for requesting multiple models for one or more data analysis tasks, the processor is used for obtaining multiple models that satisfy the first request, and the communication interface is further used for sending a first response including relevant information of the multiple models. The embodiment of the network-side device corresponds to the method embodiment of the second communication device, and the implementation processes and realization methods in the method embodiments are all applicable to the embodiment of the network-side device, and can achieve the same technical effects.

[0154] Specifically, an embodiment of the present application further provides a network side device. As shown in Fig. 11, the network side device 110 includes an antenna 111, a high frequency device 112, a baseband device 113, a processor 114, and a memory 115. The antenna 111 is connected to the high frequency device 112. In the uplink direction, the high frequency device 112 receives information through the antenna 111 and sends the received information to the baseband device 113 for processing. In the downlink direction, the baseband device 113 processes the information to be transmitted and sends it to the high frequency device 112, and the high frequency device 112 processes the received information before transmitting it through the antenna 111.

[0155] The methods performed by the network side equipment in the above embodiments may be implemented in a baseband device 113 including a baseband processor.

[0156] The baseband device 113 may, for example, include at least one baseband board provided with multiple chips, and as shown in FIG. 11, one of the chips is, for example, a baseband processor that is connected to the memory 115 via a bus interface, thereby calling a program in the memory 115 and performing the operations of the network equipment shown in the above method embodiments.

[0157] The network side equipment may further include a network interface 116, which may be, for example, a common public radio interface (CPRI).

[0158] Specifically, the network side device 110 in the embodiment of the present application further includes a command or program stored in the memory 115 and executable on the processor 114, and the processor 114 invokes the command or program in the memory 115 to execute the method performed by each module shown in Fig. 7 or Fig. 8, thereby achieving the same technical effect. In order to avoid repetition, detailed description will be omitted here.

[0159] Specifically, an embodiment of the present application further provides a network side device. As shown in Fig. 12, the network side device 120 includes a processor 121, a network interface 122, and a memory 123. Here, the network interface 122 is, for example, a common public radio interface (CPRI).

[0160] Specifically, the network side device 120 in the embodiment of the present application further includes a command or program stored in the memory 123 and executable on the processor 121, and the processor 121 invokes the command or program in the memory 123 to execute the method performed by each module shown in Fig. 7 or Fig. 8, thereby achieving the same technical effect. In order to avoid repetition, detailed description will be omitted here.

[0161] The embodiments of the present application further provide a readable storage medium, which stores a program or command, and when the program or command is executed by a processor, the processes in the above-mentioned embodiment of the model request method are realized and the same technical effects can be achieved. In order to avoid repetition, detailed descriptions are omitted here.

[0162] Wherein, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes, for example, a computer readable storage medium such as a computer read only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0163] The embodiments of the present application further provide a chip including a processor and a communication interface, the communication interface being coupled to the processor, and the processor being used to implement each process in the embodiments of the model request method by executing a program or command, and the same technical effect can be achieved. In order to avoid repetition, detailed descriptions are omitted here.

[0164] It should be understood that the chips referred to in the embodiments of this application may also be referred to as system level chips, system chips, chip systems, or system-on-chips, etc.

[0165] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium and can be executed by at least one processor to realize the processes in the above-mentioned model request method embodiments and achieve the same technical effects. Detailed descriptions are omitted here to avoid repetition.

[0166] An embodiment of the present application further provides a communication system including a first communication device and a second communication device, wherein the first communication device can be used to perform steps of the model request method performed by the first communication device side as described above, and the second communication device can be used to perform steps of the model request method performed by the second communication device side as described above.

[0167] It should be noted that, as used herein, the terms "comprises," "has," and any other variations thereof are intended to include a non-exclusive inclusion, such that a process, method, article, or apparatus comprising a set of elements includes not only those elements but also other elements not expressly listed or inherent in such process, method, article, or apparatus. Unless otherwise specified, an element limited by a phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element. It should also be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may include performing functions substantially simultaneously or in the reverse order, depending on such functionality. For example, the described method may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with reference to some examples may be combined in other examples.

[0168] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be realized in the form of a combination of software and a necessary common hardware platform, and of course, they can also be realized by hardware, but in many cases the former is a more preferred embodiment. Based on this view, the technical solutions of the present application can be substantially embodied in the form of a software product, and the computer software product is stored in a storage medium (e.g., ROM / RAM, magnetic disk, optical disk) and includes a plurality of commands that cause a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0169] Although the examples of the present application have been described above with reference to the drawings, the present application is not limited to the above-mentioned specific embodiments, which are merely illustrative and not limiting. Based on the suggestions of the present application, many forms that a person skilled in the art can make without departing from the spirit of the present application and the scope of protection of the claims are all within the scope of protection of the present application.

Claims

1. a first communication device transmitting a first request to request a plurality of models for one or more data analysis tasks; and receiving, by the first communication device, a first response including associated information of a plurality of models that satisfy the first request.

2. The method of claim 1 , wherein the task identifiers of the multiple data analysis tasks are the same.

3. The first request is: task identifier information; Task condition limiting information, Task analysis target information, First instruction information for instructing that multiple models are requested at once; Distinguishing information of the plurality of models; and model limiting information for limiting the range of use of the model.

4. The distinguishing information is multiple levels of accuracy information corresponding to the multiple models; and a plurality of time zone information corresponding to the plurality of models.

5. The model-specific information is Location information corresponding to the model; and slice information corresponding to the model.

6. before the step of the first communication device transmitting the first request; the first communication device receiving a task request and then generating the first request in response to the task request; the first communication device receiving a plurality of task requests within a predetermined time range and then generating the first request in response to the plurality of task requests.

7. The method of claim 6 , wherein task identifiers of the multiple data analysis tasks corresponding to the multiple task requests are the same.

8. The task request: task identifier information; Task condition limiting information, and analysis target information of the task.

9. The relevant information for the model is: Model information and Model identifier information; Model description information; task identifier information; Task condition limiting information, and analysis target information of the task.

10. The model description information Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; and slice information corresponding to the model.

11. the first communication device requesting desired associated data based on the received task request; The method of claim 1 , further comprising: the first communication device analyzing the relevant data using the plurality of models to obtain a data analysis result.

12. After the step of obtaining data analysis results, The method of claim 11 , further comprising the first communication device transmitting the data analysis results to a third communication device.

13. a second communication device receiving a first request to request a plurality of models for one or more data analysis tasks; the second communication device obtaining a plurality of models that satisfy the first requirement; the second communication device transmitting a first response including information related to the plurality of models.

14. The method of claim 13 , wherein the task identifiers of the multiple data analysis tasks are the same.

15. The first request is: task identifier information; Task condition limiting information, Task analysis target information, First instruction information for instructing that multiple models are requested at once; Distinguishing information of the plurality of models; and model limiting information for limiting the range of use of the model.

16. The distinguishing information is multiple levels of accuracy information corresponding to the multiple models; and a plurality of time zone information corresponding to the plurality of models.

17. The model-specific information is Location information corresponding to the model; and slice information corresponding to the model.

18. The step of the second communication device obtaining a plurality of models satisfying the first requirement comprises: the second communication device obtaining a stored model that satisfies the first request; 14. The method of claim 13, further comprising at least one of: the second communication device collecting training data based on the first request; and performing model training using the training data to obtain a trained model.

19. The step of the second communication device obtaining a stored model that satisfies the first requirement comprises: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, 20. The method of claim 18, further comprising: based on at least one of the first request, task analysis target information, and the second communication device retrieving a stored model that satisfies the first request.

20. The step of collecting training data by the second communication device based on the first request comprises: Distinguishing information of the plurality of models; Model-specific information to limit the scope of use of the model, and task identifier information; Task condition limiting information, 20. The method of claim 18, further comprising the second communication device collecting training data based on at least one of the following in the first request: and task analysis information.

21. The relevant information for the model is: Model information and Model identifier information; Model description information; task identifier information; Task condition limiting information, and analysis target information of the task.

22. The model description information Accuracy information corresponding to the model, Time zone information corresponding to the model, Location information corresponding to the model; and slice information corresponding to the model.

23. a first sending module for sending a first request to request a plurality of models for one or more data analysis tasks; a first receiving module for receiving a first response including associated information of a plurality of models that satisfy the first request.

24. a first receiving module for receiving a first request to request a plurality of models for one or more data analysis tasks; an acquisition module for acquiring a plurality of models that satisfy the first requirement; a first sending module for sending a first response including relevant information of the plurality of models.

25. A communications device comprising a processor and a memory, wherein the memory stores a program or command executable on the processor, and when the program or command is executed by the processor, the steps of the model request method according to any one of claims 1 to 12 are realized, or the steps of the model request method according to any one of claims 13 to 22 are realized.

26. A readable storage medium having stored thereon a program or commands which, when executed by a processor, cause the steps of the model request method of any one of claims 1 to 12 to be realized, or the steps of the method of any one of claims 13 to 22 to be realized.

Images