Information transmission method, device and communication equipment

Abstract

The present application discloses an information transmission method, an apparatus, and a communication device in the field of communication technology. In an embodiment of the information transmission method of the present application, a first communication device transmits first information to a second communication device, where the first information includes information for indicating data used to obtain accuracy of a first model.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority from Chinese Patent Application No. 202310057714.5 filed in China on January 16, 2023, and from Chinese Patent Application No. 202310091135.2 filed in China on February 9, 2023, the entire contents of which are incorporated herein by reference.

[0002] The present application relates to the field of communications technology, and more particularly to information transmission methods, devices and communication equipment. [Background technology]

[0003] With the development of science and technology, research has begun on applying artificial intelligence (AI) models to communication systems. For example, communication data can be transmitted between network devices and terminals via an AI model. In actual use, an AI model is a file containing elements such as network structure and parameter information. A trained AI model can be directly used by other devices without the need for repeated construction or learning. Currently, when an AI model is transmitted, it generally only transmits relevant information about the model, such as the model file address and optional validity period, and the model receiver cannot know the accuracy information of the model. Summary of the Invention [Problem to be solved by the invention]

[0004] The embodiments of the present application provide an information transmission method, apparatus, and communication device that can solve the problem in the related art that a model receiving end cannot know the accuracy information of the model. [Means for solving the problem]

[0005] According to a first aspect, there is provided an information transmission method, the information transmission method comprising: transmitting first information from a first communication device to a second communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0006] According to a second aspect, there is provided an information transmission method, the information transmission method comprising: receiving, by a second communication device, the first information transmitted from the first communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0007] According to a third aspect, there is provided an information transmission device, the information transmission device comprising: a transmitting module for transmitting the first information to the second communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0008] According to a fourth aspect, there is provided an information transmission device, the information transmission device comprising: a receiving module for receiving first information transmitted from a first communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0009] According to a fifth aspect, there is provided a communications device, the communications device including a processor and a memory, the memory storing a program or instructions operable to run on the processor, the program or instructions being executed by the processor to perform the steps of the method of the first aspect or to perform the steps of the method of the second aspect.

[0010] According to a sixth aspect, there is provided a communications device, the communications device including a processor and a communications interface, wherein the communications interface is used to transmit first information to a second communications device or to receive first information transmitted from a first communications device, the first information including information for indicating data used to obtain accuracy of a first model.

[0011] According to a seventh aspect, there is provided a communication system, the communication system including a first communication device and a second communication device, the first communication device may be used to perform steps of the information transmission method described in the first aspect, and the second communication device may be used to perform steps of the information transmission method described in the second aspect.

[0012] According to an eighth aspect, there is provided a readable storage medium having a program or instructions stored thereon, which, when executed by a processor, performs the steps of the information transmission method described in the first aspect or the steps of the information transmission method described in the second aspect.

[0013] According to a ninth aspect, there is provided a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor running a program or instruction to realize the information transmission according to the first aspect or to realize the information transmission according to the second aspect.

[0014] According to a tenth aspect, there is provided a computer program / program product, the computer program / program product being stored on a storage medium, the computer program / program product being executed by at least one processor to implement the steps of the information transmission method according to the first or second aspect. [Effects of the Invention]

[0015] In an embodiment of the present application, a first communication device sends first information to a second communication device, and the first information includes information for indicating data used to obtain the accuracy of a first model, so that the second communication device can obtain the accuracy of the first model through these data information, thereby allowing the second communication device to better use the first model and improve the reliability and use experience of the first model. [Brief explanation of the drawings]

[0016] [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] 1 is a flowchart of an information transmission method according to an embodiment of the present application; [Figure 3] 4 is a flowchart of another information transmission method according to an embodiment of the present application. [Figure 4] 1 is a structural diagram of an information transmission device according to an embodiment of the present application; [Figure 5] FIG. 10 is a structural diagram of another information transmission device according to an embodiment of the present application; [Figure 6] 1 is a structural diagram of a communication device according to an embodiment of the present application; [Figure 7] FIG. 2 is a structural diagram of a terminal according to an embodiment of the present application; [Figure 8] FIG. 2 is a structural diagram of a network-side device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0017] The following clearly describes the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present application fall within the scope of protection of the present application.

[0018] The terms "first," "second," etc. in the specification and claims of this application are intended to distinguish between similar objects and are not intended to describe a particular order or sequence. It should be understood that terms used in this manner are interchangeable where appropriate, so that embodiments of this application may be performed in orders other than those illustrated or described herein, and that objects distinguished by "first" and "second" are generally of the same type and do not limit the number of objects; for example, a first object may be one or more. Furthermore, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / " generally indicates an "or" relationship between the related objects.

[0019] It should be noted that the techniques described in the embodiments of the present application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be applied to 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 the present application are always used interchangeably, and the described techniques may be used in the above-mentioned systems and radio technologies, as well as other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description. However, these techniques may also be used in applications other than NR system applications, such as sixth generation (6G) networks.th This may be applied to 6G (6th Generation) communication systems.

[0020] 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 palmtop computer, 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 with wireless communication capabilities, such as a refrigerator, a television, a washing machine, or furniture), a game console, a personal computer, a The network side device 12 may be a terminal side device such as a mobile phone (mobile phone, mobile computer, PC), a teller machine or a self-service machine, and the wearable device includes a smart watch, a smart bracelet, a smart earphone, a smart glasses, a smart accessory (a smart bracelet, a smart hand chain, a smart ring, a smart necklace, a smart ankle bracelet, a smart anklet, etc.), a smart band, a smart clothing, etc. It should be noted that the specific type of the terminal 11 in the embodiments of the present application is not limited. The network side device 12 may include an access network device or a core network device, where the access network device may be referred to as a radio access network device, 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, or a Wireless Fidelity (WiFi) node, and the base station may be referred to as 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 Transmission and Reception Point (TRP), or any other appropriate term in the art. As long as the same technical effect is achieved, the base station is not limited to a specific technical term. For illustrative purposes, the embodiments of this application only take a base station in an NR system as an example, and do not limit the specific type of base station.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). It should be noted that the embodiments of the present application only take core network equipment in an NR system as an example, and do not limit the specific type of core network equipment.

[0021] The following describes in detail the transmission method according to the embodiments of the present application through several embodiments and its application scenarios in conjunction with the drawings.

[0022] Referring to FIG. 2, FIG. 2 is a flowchart of a transmission method according to an embodiment of the present application. As shown in FIG. 2, the method includes the following steps:

[0023] Step 201: A first communication device transmits first information to a second communication device, wherein the first information includes information for indicating data used to obtain accuracy of a first model.

[0024] It should be noted that in the embodiments of the present application, the first communication device may be a network side device, such as a network element, a terminal, a base station, a gateway, etc. The second communication device may be a network side device, a terminal, a base station, a gateway, etc. For example, the first communication device is a network side device and the second communication device is a terminal. Optionally, the first communication device may be a model sending end, having model sending capability and model training capability, such as a Model Training Logical Function (MTLF), and the second communication device may be a model receiving end, having model receiving capability and model reasoning capability, such as an Analytics Logical Function (AnLF).

[0025] In an embodiment of the present application, a first communication device transmits first information to a second communication device, the first information including information for indicating data used to obtain the accuracy of a first model, so that the second communication device can know the information of the data used to calculate the accuracy of the first model through the first information, so that the second communication device can know the accuracy of the inference result output by the first model based on the accuracy of the first model in the process of using the first model, so that the second communication device can better use the first model and improve the reliability and use experience of the first model. Optionally, the second communication device can obtain the accuracy of the first model through these data information.

[0026] Alternatively, obtaining the accuracy of the first model may be performed by the first communication device in a computational manner, or by another communication device or the like.

[0027] It should be noted that the first model may be an existing model of the second communication device, for example, the second communication device has already obtained the first model from the first communication device or another third party, or the first model may be a model that the second communication device requests the first communication device to newly obtain. Optionally, when the first communication device transmits the first information to the second communication device, the first communication device transmits the first model to the second communication device, and the second communication device can further obtain the first model and information on data used to obtain the accuracy of the first model.

[0028] Optionally, the accuracy may be model accuracy, analytics accuracy, training accuracy, accuracy provided by a third device (e.g., MTLF), performance information of the first model, etc. It may be accuracy at the time of model training, or accuracy at the time of model use.

[0029] Optionally, the information indicating data used to obtain the accuracy of the first model comprises: (1), a first number indicating the number of data used to obtain the accuracy of the first model; (2) A first collection time (e.g., a time node or a time range, e.g., data from 12:00 to 18:00 on a certain day is used to calculate the accuracy of the first model) for indicating the collection time of the data used to obtain the accuracy of the first model; (3) First distribution information for indicating a statistical method such as the distribution of data used to obtain the accuracy of the first model, for example, the mean, median, or variance among samples; (4) First source information for indicating the source of data used to obtain the accuracy of the first model, such as source location information, source network element information, and source target information (e.g., one or more user equipments (UEs)); (5) a first representative ratio for characterizing the percentage of targets to which the first model training process is applied (for example, when the target information corresponding to the first model is a set of UEs or any UE, the first representative ratio indicates the percentage of relevant UEs for training the first model; for example, when the target information includes 100 UEs and data from 70 of the UEs is used in the first model training process, the first representative ratio is 70%); (6), a third number to indicate the number of times to perform the inference; (7), and a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; It should be noted that in some scenarios, the data used to obtain the accuracy of the first model may be referred to as sample data, training data, inference data, etc. In the embodiments of the present application, the data may be data used during the inference of the first model (i.e., the process of obtaining the output result of the first model), or may be data used for training the first model. Here, the data used for training the first model includes data used for training the first model and / or data used for calculating the accuracy of the first model in the process of training the first model.

[0030] Alternatively, the method for calculating the number of data may include directly calculating each piece of data, and counting all the pieces of data obtained. It can be understood that the number of data refers to the number of pieces of data. In another method, the number of sets of data is calculated, and data corresponding to one model run is counted as one set of data, and this set of data includes label data corresponding to predicted data, true values, etc. It can be understood that the number of data refers to the number of data sets, or the predicted data and / or the time corresponding to the predicted data is used as a key for the set of data to generate input data corresponding to the predicted data at this time, label data corresponding to the predicted data at this time, etc., and the number of data refers to the total number of data sets. It should be noted that the set of data may include at least one of input data, output data, predicted values ​​(predicted data), label data, ground truth, etc.

[0031] It should be mentioned that in this application, the meaning of label data is similar to that of true value and may be substituted for each other, and thereafter will not be further explained.

[0032] It should be mentioned that the meaning of output data in this application is similar to that of predicted value and may be substituted for each other, and will not be further explained thereafter.

[0033] It should be noted that the meanings of inference and analytics in this application are the same and may be substituted for each other, for example, the meanings of performing inference and performing analysis are the same, the meanings of the number of times inference is performed and the number of times analysis is performed are the same, the meanings of inference output and analysis output are the same, or the meanings of the number of times inference output and the number of times analysis output are the same, and thereafter, no further explanation is given.

[0034] It should be noted that since each data item can be used to perform one inference by the model, the number of data items used to obtain the accuracy information of the first model may be understood as the number of inferences performed to obtain the accuracy information of the first model, or the number of inferences performed when obtaining the first accuracy information.

[0035] It should be clarified that in this application the number of times an inference is performed may be understood as the number of inference outputs or the number of analytics outputs.

[0036] Alternatively, the first number (the number of data sets used to obtain the accuracy of the first model) may be the number of training iterations, the number of inferences, etc. Here, the number of inferences may be numerically equal to the number of data sets, or may be the number of times the model performs inferences on the first communication device or the second communication device. When the first number is used to indicate the number of times the model performs inferences on the first communication device, it may be the number of inferences used to calculate the accuracy of the model in the training phase (during training), or the number of inferences used to calculate the accuracy of the model in the use phase (after the model has already transmitted to another communication device).

[0037] Optionally, in an embodiment of the present application, the accuracy of the first model is a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and and an F1 score (an index for measuring model accuracy) of the first model.

[0038] It should be noted that accuracy (also known as the precision rate) is the percentage of the number of correct model predictions to the total number of predictions. During the training phase, the validation dataset includes input data and labels (label data), which are in correspondence with each other, with one set of input data corresponding to one (set of) labels. The accuracy of the current training is determined by comparing the predicted values ​​generated by the comparison model with the labels corresponding to the current training. In one implementation, the first communication device determines the accuracy of the first model by dividing the number of times the model produces a correct inference result by the total number of inferences, specifically, the accuracy of the model = number of times it predicts a correct result ÷ total number of predictions.

[0039] Accuracy (also called precision) is the ratio of the number of times a model correctly predicts a certain type to the number of types for which the model prediction results are certain, i.e., the ratio of samples correctly predicted as "A" to samples inferred (predicted) as "A," and may be used to represent the accuracy of model inference. For example, it refers to how many of the samples predicted by the model as "A" are actually "A" samples, where "A" may be any one type, such as the cell in which the UE is located or the level of network load. Accuracy = number of samples predicted as "A" and that are actually "A" ÷ number of samples predicted as "A."

[0040] The recall rate refers to the ratio of the number of times a model correctly predicts a certain type (or may be called inference, i.e., the model's output data) to the number of data that actually fall into that type; that is, the ratio of data correctly predicted as "A" among sample data that actually fall into "A." It may be used to indicate whether the results of a model's inference or prediction are complete or comprehensive. Here, "A" may refer to any one type, such as the cell in which the UE is located or the level of network load. Recall rate = number of items predicted as "A" and actually falling into "A" / number of items that actually fall into "A."

[0041] The F1 score is a comprehensive evaluation of precision and recall. If both precision and recall are high, the F1 score will also be high. The specific formula is as follows:

number

[0042] The formula for Mean Absolute Error (MAE) is as follows:

number

number

number

[0043] In an embodiment of the present application, the first information comprises: (1) Model identifier information, where each model includes corresponding identifier (identity, ID) information for uniquely identifying the model; (2) A first calculation method for indicating the accuracy of the first model, such as the ratio of the correct prediction number to the total prediction number, for example, the mean absolute error (MAE), the root mean square error (RMSE), the recall rate (Recall), the precision, the F1 score, etc.; (3) first model accuracy information for indicating the accuracy of the first model or for indicating the degree of discrimination or prediction accuracy that the first model can achieve after training is completed; (4) First accuracy result distribution information for indicating the distribution of the accuracy result of the first model, for example, a dimension of the accuracy result, for example, a mean accuracy of the first model, a median accuracy of the first model, a variance of the accuracy of the first model, etc., which may be obtained based on accuracy results of multiple model evaluations performed during the first model training or inference, or may be obtained by aggregating the accuracy of models obtained from other communication devices.

[0044] It should be noted that the accuracy information of the first model may be obtained from the prediction results of the first model. In one alternative approach, the accuracy of the first model may be calculated by dividing the number of times the first model prediction results (i.e., output results) are correct by the total number of predictions, e.g., accuracy = number of times the prediction results are correct / total number of predictions. Specifically, the second communication device may provide a validation data set for evaluating the accuracy of the first model, the validation set including input data and true label data for inputting the first model. The input data is input to the trained first model to obtain output data, and the output data is compared to determine whether it matches the true label data to determine whether the current prediction result is correct. The accuracy value of the first model is then obtained using the above formula. Furthermore, for regression problems, i.e., when the output value of the first model is a specific value rather than a single type, the performance and accuracy of the first model can be calculated and expressed using MAE.

[0045] It should be noted that the calculation method may have a certain relationship with the accuracy, for example, the value represented by the accuracy information is the calculation method corresponding to the calculation method information.

[0046] It should be noted that the contents of the first information may be transmitted by the first communication device to the second communication device all at once or separately, for example, first transmitting information indicating the data used to obtain the accuracy of the first model, then transmitting model identifier information and the first calculation method, and then transmitting the first accuracy information, etc.

[0047] Optionally, the first information further comprises: (1) Model address information for indicating an address for storing the first model, such as an Internet Protocol (IP) address or a Fully Qualified Domain Name (FQDN), and further, model address information for allowing a second communication device to obtain a file of the first model at this address; (2) data analysis task identifier information for indicating a task type targeted by the first model, wherein the second communication device can determine to which service the first model is applied; and (3) First model filtering information (model filter information) for indicating conditions that the first model needs to satisfy, such as an Area of ​​Interest (AOI), Single Network Slice Selection Assistance Information (S-NSSAI), and Data Network Name (DNN) information; (4) target information for indicating a target of the first model, such as a specific UE(s), a set or a plurality of sets of UEs, etc.; (5) Model size information for indicating the size of the first model or the storage space required to store or run the first model, thereby enabling the second communication device to reserve sufficient storage space for storing and running the first model; and (6) reasoning time information of the first model for indicating a possible length of time required to reason using the first model; (7) Time information of the first model training data, for example, a time of the training data, for example, from three months ago to two months ago, where the time of the training data may be the time the training data was generated or the time the training data was collected.

[0048] In an embodiment of the present application, the method further comprises: The method may include the first communication device transmitting the first model to the second communication device.

[0049] In an embodiment of the present application, when a first communication device transmits first information to a second communication device, the first communication device may transmit a first model corresponding to the first information to the second communication device. For example, in one possible scenario, when the second communication device trains a new model, the second communication device may spontaneously transmit the new model (i.e., the first model) to the second communication device, and the second communication device may timely obtain the model. The second communication device may communicate with the first communication device using the model, thereby realizing service exchange between the second communication device and the first communication device using the AI ​​model.

[0050] Optionally, if the first communication device decides to transmit the first model to the second communication device, the first communication device may calculate the accuracy of the first model during training. Regarding the accuracy information of the first model, the first communication device may divide all training data into two sets: one set is used to train the first model, and the other set is used to calculate the accuracy of the first model. For example, after training using the first set of training data to obtain the first model, accuracy calculation is performed using the second set of training data to further obtain the accuracy information of the first model. For example, the accuracy of the first model may be characterized by the similarity between the data output by the first model based on the input data inputting the second set of training data and the label data or ground truth corresponding to the second set of training data, or by the root mean square error, recall rate, etc. It should be noted that the specific accuracy calculation method varies depending on the accuracy dimension (or meaning of accuracy), but this embodiment is not specifically limited thereto.

[0051] In an embodiment of the present application, the method further comprises: The method may include receiving, by the first communication device, a first request transmitted from the second communication device to request acquisition of the first model.

[0052] Optionally, the second communication device may send a first request to the first communication device to request acquisition of a first model. For example, the second communication device may request acquisition of a specific model, a certain type model, a model that meets a preset accuracy level, or a model that meets the needs of the first communication device. When the first communication device receives the first request, it may determine the first model based on the first request and send the first model to the second communication device to respond to the first request sent from the second communication device.

[0053] In some alternative embodiments, when the first communication device receives the first request, after determining the first model, it further determines information on data used to obtain the accuracy of the first model to obtain the first information, and transmits the first model and the first information to the second communication device together, either simultaneously or separately. Furthermore, when the second communication device obtains the first model, it can also obtain information describing data used to obtain the accuracy of the first model, and the second communication device can obtain the accuracy of the first model based on the information on this data, thereby helping the second communication device to better use the first model.

[0054] Optionally, receiving a first request transmitted from the second communication device by the first communication device includes: receiving, by the first communication device, a first request sent directly from the second communication device; and receiving, by the first communication device, a first request sent by the second communication device via a third communication device.

[0055] For example, the first communication device may directly receive the first request through a connection, signaling, service, etc. (e.g., Nnwdaf_AnalyticsSubscription_Subscribe / notify, Nnwdaf_MLModelProvision_Subscribe / notify, Nnwdaf_MLModelInfo_Request, etc.) between the second communication device and the first communication device, or may forward the first request through a third communication device, i.e., the second communication device sends the first request to a third communication device, and the third communication device sends the first request to the first communication device. Here, the third communication device is a communication device having forwarding capability. Optionally, the third communication device may be one or more. For example, the second communication device sends the first request to a third communication device, and the third communication device forwards the first request to the first communication device through another third communication device.

[0056] Optionally, the first request is: second information for indicating information necessary to calculate the accuracy of the model; A second calculation method for indicating the method needed to calculate the accuracy of the model, such as the ratio of correct predictions to total predictions, e.g., mean absolute error (MAE), RMSE, recall, F1 score, etc.; Second accuracy information indicating the required accuracy information of the model or indicating the accuracy of discrimination or prediction that the model needs to achieve after training is completed, where this accuracy may be the accuracy of the prediction being correct or the error value of the prediction, such as MAE, and this requirement information may be in the form of a specific numerical value, for example, a percentage such as accuracy requirement information 70%, that is, the accuracy of the first model is required to be 70% or more, and this accuracy information may be a threshold, and when the accuracy of the model exceeds this threshold (greater than or less than), the first communication device will send the first information, etc.; second accuracy result distribution information to indicate the distribution of the required model accuracy results, e.g., mean model accuracy, median model accuracy, variance of model accuracy, etc.; and first instruction information for instructing the first communication device to feed back the first information.

[0057] For example, the first request includes second information, i.e., information for indicating information necessary for calculating the accuracy of the model, i.e., when the second communication device requests the first communication device to obtain the first model, it may send the information necessary for calculating the accuracy of the model to the first communication device, i.e., notify the first communication device that it can calculate the accuracy of the first model based on the necessary information.

[0058] Alternatively, the first request may further include a second calculation method, that is, the second communication device may send a method required to calculate the accuracy of the model to the first communication device, and the first communication device may calculate the accuracy of the first model based on the second calculation method. Of course, the first communication device may not use the second calculation method sent by the second communication device in the process of actually calculating the accuracy of the first model, for example, it may use another calculation method to calculate the accuracy of the first model, and the first calculation method of the accuracy of the first model in the first information sent from the first communication device may be different from the second calculation method.

[0059] Alternatively, the first request may include second accuracy result distribution information, which indicates the distribution of the accuracy result of the model required for the first communication device, for example, what average value the accuracy of the first model needs to satisfy, etc. It should be noted that in the process of actually calculating the accuracy of the first model, the accuracy result distribution information actually obtained by the first communication device may be different from the accuracy result distribution information required for the second communication device, i.e., the first accuracy result distribution information may be different from the second accuracy result distribution information.

[0060] Furthermore, the first request may further include first instruction information, which may be used to instruct the first communication device to feed back the first information, specifically, to instruct the first communication device to feed back at least one of information on data used to obtain the accuracy of the first model, model identifier information, the first calculation method, the first accuracy information, the first accuracy result distribution information, etc. For example, the first instruction information may be used to instruct the first communication device to feed back information on data used to obtain the accuracy of the first model, or to instruct the first communication device to feed back a calculation method for the accuracy of the first model, or to instruct the first communication device to feed back the accuracy of the first model, etc., which are not listed here. In this way, when the first communication device transmits the first model to the second communication device based on the first request, it may feed back information related to the accuracy of the first model to the second communication device based on the first instruction information.

[0061] Optionally, the first requirement further includes: (1),data analysis task identifier information to indicate the task type for,which the required model is intended; (2) Model filtering information for indicating conditions that a required model must satisfy, such as AOI, S-NSSAI, DNN, etc., which may be used to assist the first communication device in model selection and model training, e.g., training that the data of the first model must be within these location ranges or slices; and (3) target information for indicating the target to which the required model is directed, e.g., specific UE(s), a set or sets of UEs, etc.; (4) model size information for indicating a required model size or storage space required to store the first model or run the first model; (5) ,the required model reasoning time information and , (6) Time information of the required model training data.

[0062] As can be understood, the first request sent by the second communication device to the first communication device may include at least one of the above information, and the second communication device may further send the necessary information related to the first model to the first communication device, which may help the first communication device select or train a first model that meets the needs of the second communication device based on the information content included in the first request.

[0063] Optionally, the second information is: a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of subjects to be applied required in the first model training process.

[0064] It should be noted that the second information is used to indicate information required to calculate the accuracy of the model, i.e., the second communication device can send relevant information of data required to calculate the accuracy of the model to the first communication device, and the first communication device may calculate the accuracy of the first model based on the number of data, data distribution, data source, etc. corresponding to this information, or may not be based on this information.

[0065] It should be noted that the information related to calculating the accuracy of the model indicated in the second information may be understood as information related to model monitoring, where "calculating the accuracy of the model" or "performing model monitoring" may refer to a network device collecting data (e.g., actual data in the network) and performing accuracy calculation, etc. In other words, the terms "calculating the accuracy of the model" and the like in this application have the same meaning as "performing model monitoring" and may be interchangeable, and will not be further described thereafter.

[0066] It should be noted that the meanings of inference and analytics in this application are the same and may be substituted for each other, for example, the meanings of performing inference and performing analysis are the same, the meanings of the number of times inference is performed and the number of times analysis is performed are the same, the meanings of inference output and analysis output are the same, or the meanings of the number of times inference output and the number of times analysis output are the same, and thereafter, no further explanation is given.

[0067] It should be noted that the second number (the number of data required to calculate the accuracy of the model) or the fourth number (the number of times required to perform inference) may be a threshold. If the number of data used in obtaining the accuracy information of the first model and / or the number of times to perform inference is equal to or greater than this threshold, the first device transmits the first information. For example, if the threshold is 1000, the first device transmits the first information only if the number of data used in obtaining the first accuracy information of the first model and / or the number of times to perform inference is equal to or greater than 1000.

[0068] For example, the number of data (second number) required to calculate the accuracy of the first model is different from the number of data used to actually calculate the accuracy of the first model. Or, the data collection time required to calculate the accuracy of a model is different from the data collection time used to actually calculate the accuracy of the first model. Of course, the second distribution information may be different from the first distribution information, the second source information may be different from the first source information, and the second representative ratio may be different from the first representative ratio, which will not be further described here.

[0069] In an embodiment of the present application, the method further comprises: The method may further include receiving, by the first communication device, a second request transmitted from the second communication device to request acquisition of model accuracy corresponding to the first model. In some alternative embodiments, when the first communication device receives the second request, the first communication device acquires the accuracy of the first model by performing an operation such as calculating model accuracy or model monitoring.

[0070] Optionally, receiving a second request transmitted from the second communication device by the first communication device includes: receiving, by the first communication device, a second request sent directly from the second communication device; receiving, by the first communication device, a second request sent by the second communication device via a third communication device.

[0071] For example, the first communication device may directly receive the second request through a connection, signaling, service, or other method (e.g., Nnwdaf_MLModelProvision_Subscribe / notify, Nnwdaf_MLModelMonitor_Request, etc.) between the second communication device and the first communication device, or may forward the second request through a third communication device, i.e., the second communication device sends the second request to the third communication device, and the third communication device sends the second request to the first communication device. Here, the third communication device is a communication device having forwarding capability. Optionally, there may be one or more third communication devices. For example, the second communication device sends the first request to the third communication device, and the third communication device forwards the first request to the first communication device through another third communication device.

[0072] Optionally, the second request is: Information to indicate the information needed to calculate the accuracy of the model; Information to indicate how to calculate the accuracy of the model, such as the ratio of correct predictions to total predictions, such as mean absolute error (MAE), RMSE, recall, F1 score, etc. Information for indicating the required accuracy of the model, or the degree of accuracy of discrimination or prediction that the model needs to achieve after training is completed, where this accuracy may be the accuracy of the prediction being correct or the error value of the prediction, such as MAE, and this requirement information may be in the form of a specific numerical value, for example, a percentage such as accuracy requirement information 70%, i.e., the accuracy of the first model is required to be 70% or more, and this accuracy information may be a threshold, and if the accuracy of the model exceeds this threshold (greater than or less than), etc., the first communication device will transmit the first information, etc.; Information to indicate the distribution of required model accuracy results, e.g., mean model accuracy, median model accuracy, variance of model accuracy, etc.; The first information includes at least one of information for instructing the first communication device to feed back the first information.

[0073] Optionally, the second request is: data analysis task identifier information to indicate the task type for which the required model is intended; model filtering information to indicate conditions that a required model must meet, such as AOI, S-NSSAI, DNN, etc., which may be used to assist model selection and model training by the first communications device, e.g., to train that the data of the first model must be within these location ranges or slices; and Target information to indicate the target for which the required model is intended, e.g., specific UE(s), a set or sets of UEs, etc.; Model identifier information, etc. Information indicating the number of data points required to calculate the accuracy of the model; Information to indicate the data collection time required to calculate the accuracy of the model; Information to indicate the data distribution needed to calculate the accuracy of the model; Information indicating the data sources needed to calculate the accuracy of the model; and information for characterizing the percentage of subjects to be applied required in the first model training process.

[0074] In an embodiment of the present application, after the first communication device receives a first request sent from the second communication device, the method further comprises: the first communication device selecting an existing model as the first model based on the first request; and the first communication device training a target model based on the first request to obtain the first model.

[0075] For example, after a first communication device receives the first request, the first communication device may retain a trained model to satisfy the first request, and if the first communication device receives a similar request and generates a trained model, the first communication device may take the existing model that satisfies this first request as the first model and transmit the first model to a second communication device.

[0076] Alternatively, after the first communication device receives the first request, the first communication device may newly train a model as the first model. For example, the first communication device may determine the data type to be collected based on task information (e.g., data analysis task identifier information) in the first request, further determine a certain device type, and send a data acquisition request to a device of this device type to request acquisition of related data. If the first communication device determines to collect network element load data information based on the task information, it sends a data acquisition request to a UPF network element to acquire the related data. After acquiring the related data, the first communication device uses the data to perform model training to obtain a first model that meets the demand, and then transmits the first model obtained by training to the second communication device.

[0077] It should be noted that satisfying the demand means that the relevant information of the model selected or trained by the first communication device matches the information in the first request, for example, the target task of the first model is the target task type required in the first request, and the accuracy of the first model is equal to or greater than the accuracy corresponding to the model accuracy demand information in the first request.

[0078] In an embodiment of the present application, a first communication device selects or trains a first model that meets a first request sent from a second communication device based on the first request, sends the first model to the second communication device, and sends data information to the second communication device to instruct the second communication device to obtain the accuracy of the first model. In addition, in the process of the second communication device using the first model, the second communication device can know the accuracy of the output result of the first model based on the accuracy of the first model, so that the second communication device can better use the first model and improve the reliability and user experience of the first model.

[0079] The term "instructions" in the specification and claims of this application may be explicit instructions or implicit instructions, where an explicit instruction may be understood as an instruction sent by a sender that clearly notifies a receiver of an operation that needs to be performed or a desired result, and an implicit instruction may be understood as an instruction sent by a sender that the receiver makes a judgment based on the instruction sent from the sender and determines an operation that needs to be performed or a desired result based on the judgment result.

[0080] Referring to FIG. 3, FIG. 3 is a flowchart of another information transmission method according to an embodiment of the present application, as shown in FIG. 3, the method includes the following steps:

[0081] Step 301: A second communication device receives first information transmitted from a first communication device, wherein the first information includes information for indicating data used to obtain accuracy of a first model.

[0082] Optionally, the first information is: Model identifier information; a first calculation method for instructing how to calculate the accuracy of the first model; first accuracy information for indicating the accuracy of the first model; and first accuracy result distribution information for indicating a distribution of accuracy results of the first model.

[0083] Optionally, the information indicating data used to obtain the accuracy of the first model comprises: a first number indicating the number of data points used to obtain the accuracy of the first model; a third number to indicate the number of times the reasoning is to be performed; a first collection time for indicating a collection time of data used to obtain the accuracy of the first model; a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; first distribution information for indicating a distribution of data used to obtain the accuracy of the first model; first source information for indicating a source of data used to obtain the accuracy of the first model; a first representative ratio for characterizing a percentage of subjects to which the first model training process is applied.

[0084] Optionally, the method further comprises: The method further includes receiving, by the second communication device, the first model transmitted from the first communication device.

[0085] Optionally, the method further comprises: The method further includes the second communication device sending a first request to the first communication device to request acquisition of the first model.

[0086] Optionally, the second communication device sending a first request to the first communication device comprises: The second communication device receives a first request transmitted from a third communication device and transmits the first request to the first communication device.

[0087] Optionally, the first request is: second information for indicating information necessary to calculate the accuracy of the model; a second calculation method for indicating the method required to calculate the accuracy of the model; second accuracy information for indicating the required model accuracy information; second accuracy result distribution information for indicating a distribution of accuracy results for the required model; and first instruction information for instructing the first communication device to feed back the first information.

[0088] Optionally, the second information is: a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of subjects to be applied required in the model training process.

[0089] Optionally, the accuracy of the first model is determined by: a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and and the F1 score of the first model.

[0090] It should be noted that the information transmission method according to the embodiment of the present application is applied to a second communication device and corresponds to the method applied to the first communication device side described in FIG. 2 above. For the relevant concepts and specific implementation flow related to the embodiment of the present application, please refer to the description in the embodiment of the method described in FIG. 2 above. In order to avoid repetition, this embodiment will not be further described.

[0091] In an embodiment of the present application, a second communication device receives first information sent from a first communication device, the first information including information for indicating data used to obtain the accuracy of a first model, and the second communication device can obtain the accuracy of the first model through the information of these data, thereby enabling the second communication device to better use the first model and improve the reliability and usage experience of the first model.

[0092] In the information transmission method according to the embodiment of the present application, the execution body may be an information transmission device. In the embodiment of the present application, the information transmission device according to the embodiment of the present application will be described by taking the execution of the information transmission method by the information transmission device as an example.

[0093] Referring to FIG. 4, FIG. 4 is a structural diagram of an information transmission device according to an embodiment of the present application. As shown in FIG. 4, the information transmission device 400 includes: a transmitting module 401 for transmitting first information to a second communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0094] Optionally, the first information is: Model identifier information; a first calculation method for instructing how to calculate the accuracy of the first model; first accuracy information for indicating the accuracy of the first model; and first accuracy result distribution information for indicating a distribution of accuracy results of the first model.

[0095] Optionally, the information indicating data used to obtain the accuracy of the first model comprises: a first number indicating the number of data points used to obtain the accuracy of the first model; a third number to indicate the number of times the reasoning is to be performed; a first collection time for indicating a collection time of data used to obtain the accuracy of the first model; a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; first distribution information for indicating a distribution of data used to obtain the accuracy of the first model; first source information for indicating a source of data used to obtain the accuracy of the first model; a first representative ratio for characterizing a percentage of subjects to which the first model training process is applied.

[0096] Optionally, the transmitting module 401 further comprises: It is used to transmit the first model to the second communication device.

[0097] Optionally, the device comprises: The communication device further includes a receiving module for receiving a first request, transmitted from the second communication device, for requesting acquisition of the first model.

[0098] Optionally, the receiving module: It is used to receive a first request sent by the second communication device via a third communication device.

[0099] Optionally, the first request is: second information for indicating information necessary to calculate the accuracy of the model; a second calculation method for indicating the method required to calculate the accuracy of the model; second accuracy information for indicating the required model accuracy information; second accuracy result distribution information for indicating a distribution of accuracy results for the required model; and first instruction information for instructing the first communication device to feed back the first information.

[0100] Optionally, the second information is: a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of subjects to be applied required in the model training process.

[0101] Optionally, the accuracy of the first model is determined by: a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and and the F1 score of the first model.

[0102] Optionally, the device comprises: selecting an existing model as the first model based on the first request; and training a target model based on the first requirement to obtain the first model.

[0103] In an embodiment of the present application, the device sends first information to a second communication device, the first information including information for indicating data used to obtain the accuracy of the first model, so that the second communication device can obtain the accuracy of the first model through the information of these data, thereby enabling the second communication device to better use the first model and improve the reliability and use experience of the first model.

[0104] The information transmission device 400 in the embodiment of the present application may be an electronic device, such as an electronic device having an operating system, or a component of an electronic device, such as an integrated circuit or chip. The electronic device may be a terminal or other device other than a terminal. Exemplarily, the terminal may include, but is not limited to, the types of terminals 11 listed above. The other device may be a server, a network-attached storage (NAS), etc., and the embodiment of the present application is not specifically limited thereto.

[0105] The information transmission device 400 according to the embodiment of the present application can implement each process implemented by the first communication device in the method embodiment of Figure 2 and achieve the same technical effects, and will not be further described here to avoid repetition.

[0106] Referring to FIG. 5, FIG. 5 is a structural diagram of another information transmission device according to an embodiment of the present application. As shown in FIG. 5, the information transmission device 500 includes: a receiving module 501 for receiving first information transmitted from a first communication device; Here, the first information includes information for indicating data used to obtain the accuracy of the first model.

[0107] Optionally, the first information is: Model identifier information; a first calculation method for instructing how to calculate the accuracy of the first model; first accuracy information for indicating the accuracy of the first model; and first accuracy result distribution information for indicating a distribution of accuracy results of the first model.

[0108] Optionally, the information indicating data used to obtain the accuracy of the first model comprises: a first number indicating the number of data points used to obtain the accuracy of the first model; a third number to indicate the number of times the reasoning is to be performed; a first collection time for indicating a collection time of data used to obtain the accuracy of the first model; a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; first distribution information for indicating a distribution of data used to obtain the accuracy of the first model; first source information for indicating a source of data used to obtain the accuracy of the first model; a first representative ratio for characterizing a percentage of subjects to which the first model training process is applied.

[0109] Optionally, the receiving module 501 further comprises: It is used to receive the first model transmitted from the first communication device.

[0110] Optionally, the device comprises: The device further includes a transmitting module for transmitting a first request to the first communication device to request acquisition of the first model.

[0111] Optionally, the transmitting module: receiving a first request sent from a third communication device; and transmitting the first request to the first communication device.

[0112] Optionally, the first request is: second information for indicating information necessary to calculate the accuracy of the model; a second calculation method for indicating the method required to calculate the accuracy of the model; second accuracy information for indicating the required model accuracy information; second accuracy result distribution information for indicating a distribution of accuracy results for the required model; and first instruction information for instructing the first communication device to feed back the first information.

[0113] Optionally, the second information is: a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of subjects to be applied required in the model training process.

[0114] Optionally, the accuracy of the first model is determined by: a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and and the F1 score of the first model.

[0115] In an embodiment of the present application, the device receives first information transmitted from a first communication device, the first information including information for indicating data used to obtain the accuracy of a first model, and the device can obtain the accuracy of the first model through these data information, thereby enabling the device to better use the first model and improve the reliability and usage experience of the first model.

[0116] The information transmission device 500 according to the embodiment of the present application can implement each process implemented by the second communication device in the method embodiment of Figure 3 and achieve the same technical effects, and will not be further described here to avoid repetition.

[0117] Optionally, as shown in Fig. 6, an embodiment of the present application further provides a communication device 600, which includes a processor 601 and a memory 602, and stores a program or instruction that can be run on the processor 601 in the memory 602. For example, if the communication device 600 is a first communication device, when the program or instruction is executed by the processor 601, it can realize each step of the embodiment of the information transmission method and achieve the same technical effect. If the communication device 600 is a second communication device, when the program or instruction is executed by the processor 601, it can realize each step of the embodiment of the information transmission method and achieve the same technical effect. In order to avoid repetition, no further description will be given here.

[0118] An embodiment of the present application further provides a terminal, the terminal including a processor and a communication interface, the communication interface being used to send first information to a second communication device or receive first information sent from a first communication device, where the first information includes information for indicating data used to obtain the accuracy of the first model. This embodiment of the terminal corresponds to the embodiment of the method on the first communication device or the second communication device, and the implementation processes and realization manners of the embodiment of the method can all be applied to this embodiment of the terminal, and the same technical effects can be achieved. Specifically, Figure 7 is a schematic diagram of a hardware structure for realizing the terminal of the embodiment of the present application.

[0119] The terminal 700 includes at least some components such as, but not limited to, a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709 and a processor 710.

[0120] As will be understood by those skilled in the art, the terminal 700 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 710 by a power management system, thereby enabling the power management system to realize functions such as charge / discharge management and power consumption management. The terminal structure shown in Figure 7 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than those shown, or a combination of some components, or a different arrangement of components, which will not be further described here.

[0121] It should be understood that in the embodiment of the present application, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 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. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. The other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control buttons, switch buttons, etc.), a trackball, a mouse, and a control lever, which will not be further described herein.

[0122] In the embodiment of the present application, the radio frequency unit 701 can receive downlink data from the network side device and then transmit the data to the processor 710 for processing, and can also transmit uplink data to the network side device. Generally, the radio frequency unit 701 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, etc.

[0123] The memory 709 may be used to store software programs or instructions and various data. The memory 709 may include a first storage area that mainly stores programs or instructions and a second storage area that stores data. Here, the first storage area may store an operating system, an application program or instructions necessary for at least one function (e.g., an audio playback function, an image playback function, etc.), etc. The memory 709 may include volatile memory or nonvolatile memory, or may include both volatile 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. 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), synchronous link dynamic random access memory (SLDRAM), and direct Rambus random access memory (DRRAM). Memory 709 in embodiments of the present application includes, but is not limited to, these and any other suitable types of memory.

[0124] The processor 710 may include one or more processing units. Optionally, the processor 710 may integrate an application processor and a modem processor, where the application processor mainly processes operations related to the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication signals, e.g., a baseband processor. As can be appreciated, the modem processor may not be integrated into the processor 710.

[0125] In one embodiment, the terminal 700 in the embodiment of the present application can realize each process of the above information transmission method as a first communication device, where the radio frequency unit 701 is used to transmit first information to a second communication device, and the first information includes information for indicating data used to obtain the accuracy of the first model.

[0126] In another embodiment, the terminal 700 in the embodiment of the present application can realize each process of the above information transmission method as a second communication device, where the radio frequency unit 701 is used to receive first information transmitted from a first communication device, and the first information includes information for indicating data used to obtain the accuracy of the first model.

[0127] In an embodiment of the present application, a terminal sends or receives first information, and the first information includes information for indicating data used to obtain the accuracy of a first model, so that the accuracy of the first model can be obtained through these data information, thereby allowing the terminal or the other party to better use the first model and improve the reliability and use experience of the first model.

[0128] An embodiment of the present application further provides a network-side device, which includes a processor and a communication interface. This embodiment of the network-side device corresponds to the embodiment of the method on the first communication device side or the second communication device side, and the implementation processes and realization manners of the embodiment of the method can be applied to this embodiment of the network-side device, and the same technical effects can be achieved.

[0129] Specifically, an embodiment of the present application further provides a network side device. As shown in Fig. 8, the network side device 800 includes an antenna 81, a radio frequency device 82, a baseband device 83, a processor 84, and a memory 85. The antenna 81 and the radio frequency device 82 are connected. In the uplink direction, the radio frequency device 82 receives information through the antenna 81 and transmits the received information to the baseband device 83 for processing. In the downlink direction, the baseband device 83 processes the information to be transmitted and transmits it to the radio frequency device 82, and the radio frequency device 82 processes the received information and then transmits it through the antenna 81.

[0130] The methods performed by the network side equipment in the above embodiments may be implemented in a baseband device 83, which includes a baseband processor.

[0131] The baseband device 83 may include, for example, at least one baseband board, on which multiple chips are installed, and as shown in FIG. 8, one of the chips is, for example, a baseband processor, which is connected to a memory 85 via a bus interface and calls the program in the memory 85 to perform the network equipment operations shown in the above method embodiments.

[0132] The network side equipment may further include a network interface 86, which may be, for example, a common public radio interface (CPRI).

[0133] Specifically, the network side device 800 of the embodiment of the present application further includes instructions or programs stored in the memory 85 and capable of running on the processor 84, and the processor 84 can call the instructions or programs in the memory 85 to execute the methods performed by each module shown in FIG. 4 or FIG. 5, and achieve the same technical effects, which will not be further described here to avoid repetition.

[0134] An embodiment of the present application further provides a readable storage medium, which stores a program or instruction, and when the program or instruction is executed by a processor, it can realize each process of the embodiment of the method shown in FIG. 2 above, or realize each process of the embodiment of the method shown in FIG. 3 above, and achieve the same technical effect, which will not be further described here to avoid repetition.

[0135] Wherein, the processor is the processor in the terminal described in the above embodiment. The readable storage medium includes 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.

[0136] An embodiment of the present application further provides a chip, the chip including a processor and a communication interface, the communication interface coupled to the processor, the processor running a program or instruction to realize each process of the embodiment of the method shown in FIG. 2 above, or to realize each process of the embodiment of the method shown in FIG. 3 above, and can achieve the same technical effect, which will not be further described here to avoid repetition.

[0137] It should be understood that the chips referred to in the embodiments of this application may be referred to as system level chips, system chips, chip systems, or system-on-chips.

[0138] An embodiment of the present application further provides a computer program product, which is stored in a storage medium, and which can be executed by at least one processor to realize each process of the method embodiment shown in FIG. 2 above, or each process of the method embodiment shown in FIG. 3 above, and achieve the same technical effects, and will not be further described here to avoid repetition.

[0139] An embodiment of the present application further provides a communication system, which includes a first communication device and a second communication device, wherein the first communication device is used to perform steps of the method described in FIG. 2, and the second communication device is used to perform steps of the method described in FIG. 3 above.

[0140] It should be noted that, in this specification, the terms "comprise," "include," "includes," or any other variations thereof are intended to cover the non-exclusive "comprise," whereby a process, method, article, or apparatus comprising a set of elements not only includes those elements, but also other elements not expressly listed or inherent in such process, method, article, or apparatus. Absent further limitations, an element defined by the phrase "comprises one of" does not preclude the presence of other identical elements in the process, method, article, or apparatus comprising that element. It should 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 in an essentially simultaneous manner or in the reverse order based on the functions involved. 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.

[0141] As will be apparent to those skilled in the art from the above description of the embodiments, the methods of the above embodiments can be realized in the form of software and a necessary general-purpose hardware platform. Of course, they can also be realized in hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical proposal of the present application, in substance or in part contributing to the prior art, may be embodied in the form of a computer software product, which is stored in a storage medium (e.g., ROM / RAM, magnetic disk, optical disk) and includes a number of instructions for causing a terminal (which may be a mobile phone, computer, server, air conditioner, network device, etc.) to execute the methods described in each embodiment of the present application.

[0142] Although the embodiments of the present application have been described above in conjunction with the drawings, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not limiting. Those skilled in the art can take the teachings of the present application into account and implement many forms without departing from the spirit and scope of the claims, all of which fall within the scope of protection of the present application.

Claims

1. 1. A method for transmitting information, comprising: transmitting first information from a first communication device to a second communication device; An information transmission method, wherein the first information includes information for indicating data used to obtain the accuracy of the first model.

2. The first information is Model identifier information; a first calculation method for instructing how to calculate the accuracy of the first model; first accuracy information for indicating the accuracy of the first model; and first accuracy result distribution information for indicating a distribution of accuracy results of the first model.

3. the information for indicating data used to obtain the accuracy of the first model comprises: a first number indicating the number of data points used to obtain the accuracy of the first model; a third number to indicate the number of times the reasoning is to be performed; a first collection time for indicating a collection time of data used to obtain the accuracy of the first model; a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; first distribution information for indicating a distribution of data used to obtain the accuracy of the first model; first source information for indicating a source of data used to obtain the accuracy of the first model; and a first representative ratio for characterizing a percentage of subjects to which the first model training process is applied.

4. The method comprises: The method of claim 1 or 2, further comprising the first communication device transmitting the first model to the second communication device.

5. The method comprises: The method of claim 4 , further comprising receiving, by the first communication device, a first request sent from the second communication device to request acquisition of the first model.

6. The first communication device receiving a first request transmitted from the second communication device includes: The method of claim 5 , comprising receiving, by the first communication device, a first request transmitted by the second communication device via a third communication device.

7. The first requirement is: second information for indicating information necessary to calculate the accuracy of the model; a second calculation method for indicating the method required to calculate the accuracy of the model; second accuracy information for indicating the required model accuracy information; second accuracy result distribution information for indicating a distribution of accuracy results for the required model; and first instruction information for instructing the first communication device to feed back the first information.

8. The second information is a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of applied subjects required in the model training process.

9. The accuracy of the first model is a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and the accuracy of the first model; and and an F1 score of the first model.

10. The method comprises: the first communication device selecting an existing model as the first model based on the first request; and the first communication device training a target model based on the first request to obtain the first model.

11. The method comprises:

3. The method of claim 1, further comprising receiving, by the first communication device, a second request sent from the second communication device to request obtaining the accuracy of a model corresponding to the first model.

12. receiving, by the first communication device, a second request transmitted from the second communication device; The method of claim 11 , comprising receiving, by the first communication device, a second request sent by the second communication device via a third communication device.

13. 1. A method for transmitting information, comprising: receiving, by a second communication device, the first information transmitted from the first communication device; An information transmission method, wherein the first information includes information for indicating data used to obtain the accuracy of the first model.

14. The first information is Model identifier information; a first calculation method for instructing how to calculate the accuracy of the first model; first accuracy information for indicating the accuracy of the first model; and first accuracy result distribution information for indicating a distribution of accuracy results of the first model.

15. the information for indicating data used to obtain the accuracy of the first model comprises: a first number indicating the number of data points used to obtain the accuracy of the first model; a third number to indicate the number of times the reasoning is to be performed; a first collection time for indicating a collection time of data used to obtain the accuracy of the first model; a first collection area for indicating a collection area of ​​data used to obtain the accuracy of the first model; first distribution information for indicating a distribution of data used to obtain the accuracy of the first model; first source information for indicating a source of data used to obtain the accuracy of the first model; and a first representative ratio for characterizing a percentage of subjects to which the first model training process is applied.

16. The method comprises: The method of claim 13 or 14, further comprising the second communication device receiving the first model transmitted from the first communication device.

17. The method comprises: The method of claim 16 , further comprising the second communication device sending a first request to the first communication device to request acquisition of the first model.

18. transmitting a first request from the second communication device to the first communication device; 20. The method of claim 17, comprising: the second communication device receiving a first request sent from a third communication device; and transmitting the first request to the first communication device.

19. The first requirement is: second information for indicating information necessary to calculate the accuracy of the model; a second calculation method for indicating the method required to calculate the accuracy of the model; second accuracy information for indicating the required model accuracy information; second accuracy result distribution information for indicating a distribution of accuracy results for the required model; and first instruction information for instructing the first communication device to feed back the first information.

20. The second information is a second number indicating the number of data points required to calculate the accuracy of the model; a fourth number to indicate the number of times required to perform the inference; a second collection time to indicate the data collection time required to calculate the accuracy of the model; a second collection area for indicating the data collection area required to calculate the accuracy of the model; second distribution information for indicating the data distribution required to calculate the accuracy of the model; Secondary source information for indicating the data sources required to calculate the accuracy of the model; and a second representative ratio for characterizing the percentage of applied subjects required in the model training process.

21. The accuracy of the first model is a ratio of the first model correct prediction number to the first model total prediction number; the mean absolute error of the first model; and the recall rate of the first model; and and an F1 score of the first model.

22. An information transmission device, a transmitting module for transmitting the first information to the second communication device; An information transmission device, wherein the first information includes information for indicating data used to obtain the accuracy of the first model.

23. An information transmission device, a receiving module for receiving first information transmitted from a first communication device; An information transmission device, wherein the first information includes information for indicating data used to obtain the accuracy of the first model.

24. A communications device including a processor and a memory, wherein the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, the communications device implements the steps of the information transmission method described in any one of claims 1 to 12, or the steps of the information transmission method described in any one of claims 13 to 21.

25. A readable storage medium having a program or instructions stored therein, the program or instructions being executed by a processor to implement the steps of the information transmission method of any one of claims 1 to 12, or the steps of the information transmission method of any one of claims 13 to 21.

Images