Communication method and device

Abstract

The invention provides a communication method and device, and the method comprises the steps: transmitting a first request message which is used for requesting data processing and comprises processing method information of each feature vector in a sample in a data set and / or file information for processing the sample in the data set; receiving a first response message, the first response message comprising a preprocessed data set, the preprocessed data set comprising sample data of one or more feature values, the sample data being determined based on processing method information of each feature in samples in the data set or the file information for sample processing in the data set, by the adoption of the method and device, mass data can be processed, and the processed data set can be obtained.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method and apparatus. Background Technology

[0002] As data becomes a key production factor in the digital society, 6G, as a crucial infrastructure, inevitably makes data from 6G systems an essential component of this production factor. With the continuous growth in the amount of data generated by mobile networks, the demand for data collection and processing is becoming increasingly prominent. Current 5G networks utilize a data collection framework based on the Data Collection Coordination Function (DCCF). In this framework, DCCF can collect data from different data sources based on user requests and perform some basic data processing. However, this processed data cannot be directly used for model training; currently, the data processing of feature data used for model training is based on the internal implementation of the model training function.

[0003] As data volume increases, the amount of data used for model training also increases accordingly. Relying entirely on model training functions for data processing will degrade the performance of model training network elements and increase training time. Furthermore, when multiple model training functions use the same features, different functions may need to apply the same data processing methods to the same dataset. Therefore, under current technology, data with the same characteristics cannot be shared among multiple model training functions, and data with different characteristics cannot be processed simultaneously by different data processing network elements. In short, current data processing methods cannot meet the demands of future massive data processing. How to achieve massive data processing in future networks is a technical problem that researchers in this field are currently addressing. Summary of the Invention

[0004] This application proposes a communication method and apparatus that can process massive amounts of data and obtain the processed dataset.

[0005] In a first aspect, embodiments of this application provide a communication method applicable to a first network element. This method can be executed by the first network element, by components within the first network element (e.g., processors, chips, or chip systems), or by a logic module or software capable of implementing all or part of the functions of the first network element. The method includes: sending a first request message to request data processing, the first request message including processing method information for each feature vector in samples of a dataset and / or file information for processing samples in the dataset; and receiving a first response message including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the processing method information for each feature in the samples of the dataset or the file information for processing samples in the dataset.

[0006] In the above method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The first network element can obtain sample data containing one or more feature values. This sample data is obtained by processing based on the data processing method provided by the first network element. Furthermore, through the above method, the first network element can send the same data processing request to multiple third network elements. Therefore, it is possible to process massive amounts of data and obtain the sample data required by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0007] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0008] In the above method, the processing method information of each feature in the sample data can be provided to the third network element in the above manner, so that the third network element can obtain the processing method information of each feature in the sample data, and perform data processing based on the processing method information of each feature to obtain the sample data required by the first network element.

[0009] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0010] In the above method, the third network element can be provided with file information for centralized sample processing of the data. The third network element does not need to understand the specific data processing logic. It only needs to use the data provided by the first network element, i.e. the second data information, as the input data of the file according to the first data processing file information provided by the first network element, and run the data processing file to obtain the sample data required by the first network element.

[0011] In another possible implementation, the method further includes: sending a second request message to a second network element, the second request message being used to request data processing method supported by at least one third network element and / or data processing file information supported by the at least one third network element; receiving a second response message from the second network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information of the receivable data processing file supported by the at least one third network element.

[0012] In the above method, the first network element can obtain the name and / or description of the data processing operation method supported by at least one third network element and / or information about the receivable data processing files supported by the at least one third network element. That is, the first network element can provide the corresponding data processing method to the third network element based on the obtained data processing operation supported by the third network element, ensuring that the third network element can recognize the data processing method and then process the data provided by the first network element according to the data processing method to obtain the dataset required by the first network element. This avoids the third network element being unable to process the data due to not recognizing the data processing method provided by the first network element.

[0013] In another possible implementation, the first data processing method is determined by customizing and arranging one or more operation methods based on the obtained operation method names and operation method descriptions supported by the third network element.

[0014] In the above method, the first network element can provide the third network element with a corresponding data processing method based on the data processing operations supported by the third network element. This ensures that the third network element can recognize the data processing method and then process the data provided by the first network element according to the data processing method to obtain the dataset required by the first network element. This avoids the situation where the third network element is unable to process the data due to not recognizing the data processing method provided by the first network element.

[0015] In another possible implementation, the information related to the receivable data processing file supported by the third network element includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0016] In another possible implementation, the first data processing file information is determined based on relevant information about the receivable data processing files supported by the third network element.

[0017] In the above method, the first network element can provide the third network element with a corresponding data processing method based on the information in the data processing file supported by the third network element. This method ensures that the third network element can recognize the data processing method and then process the data provided by the first network element according to that method to obtain the dataset required by the first network element. This avoids the third network element being unable to process the data due to not recognizing the data processing method provided by the first network element.

[0018] In another possible implementation, the first request message includes first indication information, which indicates a sample feature sorting rule, and the feature values ​​corresponding to the sample data in the dataset included in the first response message are sorted according to the sample feature sorting rule.

[0019] In the above method, the feature values ​​corresponding to the sample data in the dataset are sorted according to the sorting rules of the sample features, which facilitates quick searching and retrieval of sample data.

[0020] Secondly, embodiments of this application provide a communication method applicable to a second network element. This method can be executed by the second network element, by components within the second network element (e.g., processors, chips, or chip systems), or by a logic module or software capable of implementing all or part of the functions of the second network element. The method includes: receiving a third request message from a third network element, the third request message being used to request registration of data processing methods supported by the third network element and / or data processing file information supported by the third network element; receiving a second request message from a first network element; the second request message being used to request at least one data processing method supported by the third network element and / or data processing file information supported by the at least one third network element; and sending a second response message to the first network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information about the receivable data processing file supported by the at least one third network element.

[0021] In the above method, the second network element can provide the first network element with data processing methods and / or data processing file information supported by the third network element. Correspondingly, the first network element obtains the name and / or description information of the operation method supported by at least one third network element and / or the relevant information of the receivable data processing file supported by the at least one third network element. Furthermore, the first network element can provide basic or custom data processing methods.

[0022] In one possible implementation, the method further includes: receiving a first request message for requesting data processing, the first request message including processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset; determining one or more third network elements based on the first request message; sending a fourth request message to the one or more third network elements, the fourth request message including first information and / or second information; wherein the first information is a subset of the processing method information for each feature vector in the samples of the dataset included in the first request message, and / or the second information is a subset of the file information for processing the samples in the dataset included in the first request message; receiving one or more fourth response messages, each of the one or more fourth response messages including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the first information or the second information; determining a total sample dataset; wherein the total sample dataset is determined based on the preprocessed dataset carried in the one or more fourth response messages; and sending a first response message including the total sample dataset.

[0023] In the above method, the third network element can process data according to the data processing method provided by the first network element, avoiding the situation where the third network element cannot understand the data processing method provided by the first network element and cannot provide the required data to the first network element. Furthermore, different data processing operations are distributed across multiple third network elements, and the distributed processing of data can realize the processing of massive amounts of data, thus accelerating the speed of massive data processing.

[0024] In another possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0025] In the above method, the third network element can obtain the processing method information of each feature in the sample data, and perform data processing based on the processing method information of each feature to obtain the sample data required by the first network element.

[0026] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0027] In the above method, the third network element does not need to understand the specific data processing logic. It only needs to use the data provided by the first network element, i.e. the second data information, as the input data of the first data processing file provided by the first network element, and run the data processing file to obtain the sample data required by the first network element.

[0028] Thirdly, embodiments of this application provide a communication method applicable to a third network element. This method can be executed by the third network element, by components within the third network element (e.g., processors, chips, or chip systems), or by a logic module or software capable of implementing all or part of the functions of the third network element. The method includes: receiving a first request message, which requests data processing, the first request message including processing method information for each feature vector in samples of a dataset and / or file information for processing samples in the dataset; performing data processing based on the first request message to determine a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the processing method information for each feature in the samples of the dataset or the file information for processing samples in the dataset; and sending a first response message, the first response message including the preprocessed dataset.

[0029] In the above method, the third network element can process data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data to the file information for centralized sample processing, and run the data processing file to obtain the sample data needed by the first network element. This sample data can be directly used for model training.

[0030] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0031] In the above method, the third network element can obtain the processing method information of each feature in the sample data, and perform data processing based on the processing method information of each feature to obtain the sample data required by the first network element.

[0032] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0033] In the above method, the third network element does not need to understand the specific data processing logic. It only needs to use the data provided by the first network element, i.e. the second data information, as the input data of the first data processing file provided by the first network element, and run the data processing file to obtain the sample data required by the first network element.

[0034] In another possible implementation, the method further includes sending a third request message to the second network element, the third request message being used to request registration of supported data processing methods and / or supported data processing file information.

[0035] In another possible implementation, the supported data processing method refers to the name and / or description of the supported data operation method, and the supported data processing file information refers to the relevant information of the supported receivable data processing file.

[0036] In another possible implementation, the relevant information of the supported receivable data processing file includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0037] In another possible implementation, the first request message further includes first indication information, which indicates a sample feature sorting rule; the preprocessed dataset is obtained by sorting based on the sample feature sorting rule.

[0038] In the above method, the feature values ​​corresponding to the sample data in the dataset are sorted according to the sorting rules of the sample features, which facilitates quick searching and retrieval of sample data.

[0039] Fourthly, embodiments of this application provide a communication device, which may be a first network element, a component within the first network element (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the first network element.

[0040] In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the first aspect. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0041] In one possible implementation, the communication device includes a processing unit and a transceiver unit. The transceiver unit is configured to send a first request message requesting data processing. The first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. The transceiver unit is also configured to receive a first response message, which includes a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values, which are determined based on the processing method information for each feature in the samples of the dataset or the file information for processing the samples in the dataset.

[0042] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0043] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0044] In another possible implementation, the transceiver unit is further configured to send a second request message to the second network element, the second request message being used to request data processing method supported by at least one third network element and / or data processing file information supported by the at least one third network element; the transceiver unit is further configured to receive a second response message from the second network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information of the receivable data processing file supported by the at least one third network element.

[0045] In another possible implementation, the first data processing method is determined by customizing and arranging one or more operation methods based on the obtained operation method names and operation method descriptions supported by the third network element.

[0046] In another possible implementation, the information related to the receivable data processing file supported by the third network element includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0047] In another possible implementation, the first data processing file information is determined based on relevant information about the receivable data processing files supported by the third network element.

[0048] In another possible implementation, the first request message includes first indication information, which indicates a sample feature sorting rule, and the feature values ​​corresponding to the sample data in the dataset included in the first response message are sorted according to the sample feature sorting rule.

[0049] For the technical effects of the fourth aspect or possible implementation, please refer to the introduction of the technical effects of the first aspect or corresponding implementation.

[0050] Fifthly, embodiments of this application provide a communication device, which can be a second network element, a component within the second network element (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the second network element.

[0051] In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the second aspect one by one. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0052] In one possible implementation, the communication device includes: a processing unit and a transceiver unit. The transceiver unit is configured to receive a third request message from a third network element, the third request message being used to request registration of a data processing method supported by the third network element and / or data processing file information supported by the third network element. The transceiver unit is further configured to receive a second request message from a first network element, the second request message being used to request at least one data processing method supported by a third network element and / or data processing file information supported by the at least one third network element. The transceiver unit is further configured to send a second response message to the first network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information of the receivable data processing file supported by the at least one third network element.

[0053] In one possible implementation, the transceiver unit is further configured to receive a first request message, the first request message being used to request data processing, the first request message including processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset; the processing unit is further configured to determine one or more third network elements based on the first request message; and send a fourth request message to the one or more third network elements, the fourth request message including first information and / or second information; wherein, the first information is a subset of the processing method information for each feature vector in the samples of the dataset included in the first request message, and / or the second information is a subset of the first information. The first request message includes a subset of file information for sample processing in the dataset; the transceiver unit is further configured to receive one or more fourth response messages, each of the one or more fourth response messages including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the first information or the second information; the processing unit is further configured to determine the total sample dataset; wherein the total sample dataset is determined based on the preprocessed dataset carried in one or more fourth response messages; the transceiver unit is further configured to send a first response message, the first response message including the total sample dataset.

[0054] In another possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0055] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0056] For the technical effects of the fifth aspect or possible implementation, please refer to the introduction of the technical effects of the second aspect or corresponding implementation.

[0057] Sixthly, embodiments of this application provide a communication device, which can be a third network element, a component within a third network element (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of a third network element.

[0058] In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the third aspect one by one. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0059] In one possible implementation, the communication device includes: a processing unit and a transceiver unit. The transceiver unit is configured to receive a first request message, which requests data processing. The first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. The processing unit is further configured to perform data processing based on the first request message to determine a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values, which is determined based on the processing method information for each feature in the samples of the dataset or the file information for processing the samples in the dataset. The transceiver unit is further configured to send a first response message, which includes the preprocessed dataset.

[0060] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0061] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0062] In another possible implementation, the transceiver unit is also configured to send a third request message to the second network element, the third request message being used to request registration of supported data processing methods and / or supported data processing file information.

[0063] In another possible implementation, the supported data processing method refers to the name and / or description of the supported data operation method, and the supported data processing file information refers to the relevant information of the supported receivable data processing file.

[0064] In another possible implementation, the relevant information of the supported receivable data processing file includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0065] In another possible implementation, the first request message further includes first indication information, which indicates a sample feature sorting rule; the preprocessed dataset is obtained by sorting based on the sample feature sorting rule.

[0066] For the technical effects of the sixth aspect or possible implementation, please refer to the introduction of the technical effects of the third aspect or corresponding implementation.

[0067] In a seventh aspect, embodiments of this application provide a communication device, which includes at least one processor and a communication interface. The at least one processor invokes a computer program or instructions stored in a memory to execute the method described in the first aspect or a possible implementation thereof.

[0068] In one possible implementation, the communication device also includes the memory. Alternatively, the memory and processor are integrated together.

[0069] In one possible implementation, the memory is located outside the communication device.

[0070] Eighthly, embodiments of this application provide a communication device including at least one processor and a communication interface, wherein the at least one processor invokes a computer program or instructions stored in a memory to execute the method described in the second aspect or a possible implementation thereof.

[0071] In one possible implementation, the communication device also includes the memory. Alternatively, the memory and processor are integrated together.

[0072] In one possible implementation, the memory is located outside the communication device.

[0073] Ninthly, embodiments of this application provide a communication device including at least one processor and a communication interface, wherein the at least one processor invokes a computer program or instructions stored in a memory to execute the method described in the third aspect or a possible implementation thereof.

[0074] In one possible implementation, the communication device also includes the memory. Alternatively, the memory and processor are integrated together.

[0075] In one possible implementation, the memory is located outside the communication device.

[0076] In a tenth aspect, embodiments of this application provide a chip device including at least one processor for executing computer programs or instructions to implement any of the above aspects or possible implementations of any of the above aspects.

[0077] In one possible implementation, the input of the chip device corresponds to the receiving operation in any of the above-mentioned aspects or possible implementations, and the output of the chip device corresponds to the transmitting operation in any of the above-mentioned aspects or possible implementations.

[0078] Optionally, the processor is coupled to the memory via an interface.

[0079] Optionally, the chip device may also include a memory storing computer program instructions.

[0080] Eleventhly, embodiments of this application provide a computer-readable storage medium storing a computer program or instructions that, when executed on a processor, implement the method described above.

[0081] In a twelfth aspect, embodiments of this application provide a computer program product that includes a computer program or instructions that, when executed on a processor, implement the method described in any of the above aspects.

[0082] In a thirteenth aspect, embodiments of this application provide a communication system, which includes: the apparatus as described in the seventh aspect, the apparatus as described in the eighth aspect, and the apparatus as described in the ninth aspect. Attached Figure Description

[0083] Figure 1This is a schematic diagram of the structure of a communication system provided in an embodiment of this application;

[0084] Figure 2 This is a schematic diagram of the structure of another communication system provided in the embodiments of this application;

[0085] Figure 3 This is a schematic diagram of a data storage architecture based on DCCF;

[0086] Figures 4-8 This is a flowchart illustrating a communication method provided in an embodiment of this application;

[0087] Figure 9 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0088] Figure 10 This is a schematic diagram of the structure of another communication device provided in the embodiments of this application. Detailed Implementation

[0089] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0090] References to "one embodiment" or "some embodiments" as described in this application mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0091] In the description of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0092] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.

[0093] In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementations, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index; indirectly instructing the information to be instructed by instructing other information, where there is a relationship between the other information and the information to be instructed; or instructing only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent.

[0094] The information to be instructed can be sent as a whole or divided into multiple sub-information messages, and the sending period and / or timing of these sub-information messages can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

[0095] It is understood that "send" and "receive" in this application refer to the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which can include direct transmission via the air interface or indirect transmission via the air interface from other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which can include direct reception from YY via the air interface or indirect reception from YY via the air interface from other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0096] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0097] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0098] The communication method provided in this application can be applied to cellular communication systems related to the 3rd Generation Partnership Project (3GPP), such as 4th generation (4G) communication systems, including Long Term Evolution (LTE) systems. It can also be applied to 5th generation (5G) communication systems, such as 5G New Radio (NR) systems, or to various future communication systems, such as 6th generation (6G) systems. The method provided in this application can also be applied to Bluetooth systems, Wireless Fidelity (WiFi) systems, LoRa systems, or vehicle-to-everything (V2X) systems, as well as communication systems supporting the integration of multiple wireless technologies, and device-to-device (D2D) systems. The method provided in this application can also be applied to satellite communication systems, wherein the satellite communication system can be integrated with the aforementioned communication systems. The wireless communication systems involved in this application also include, but are not limited to: narrowband Internet of Things (NB-IoT), Global System for Mobile Communications (GSM), Enhanced Data Rate for GSM Evolution (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access 2000 (CDMA2000), or Time Division-Synchronization Code Division Multiple Access (TD-SCDMA).

[0099] Please see Figure 1 , Figure 1 This is a schematic diagram of the structure of a communication system provided in an embodiment of this application, to... Figure 1 The application scenario of this application is illustrated using the communication system structure shown. This communication system includes a first network element 101, a second network element 102, and a third network element 103. For example... Figure 2 As shown, Figure 2This is a schematic diagram of another communication system provided in this application embodiment. The first network element 101 can be a consumer, such as a terminal device, a network data analytics function (NWDAF) network element, or a user data application function (UDAF) network element. The second network element 102 can be a data management function (DMF) network element, and the third network element 103 can be a data handing function (DHF) network element. Optionally, the communication system may also include a data storage function (DSF) network element. The main functions of each network element are as follows:

[0100] DMF network elements: mainly used for centralized data management and authorized network elements, responsible for centralized network data management and control as well as the opening of data services.

[0101] DHF network elements are mainly used for real-time high-throughput data acquisition and transmission, as well as preprocessing and data quality assessment of artificial intelligence (AI) data.

[0102] NWDAF network elements are network elements that provide data analysis capabilities for network functions (NFs) and operations, administration, and management (OAM). NFs or OAMs can request network data analysis results from NWDAF network elements. Upon receiving a request, the NWDAF network element collects data from relevant network elements and trains an AI model. Finally, it uses the AI ​​model to perform data inference and feeds the inference results back to the corresponding NF or OAM. Depending on their functions, NWDAF network elements can be divided into model training logical function (MTLF), i.e., NWDAF(MTLF), and analytics logical function (AnLF), i.e., NWDAF(AnLF). NWDAF(MTLF) primarily supports model training, while NWDAF(AnLF) primarily supports model inference.

[0103] DSF network elements are mainly used for distributed data storage and data retrieval, reading and writing.

[0104] It should be noted that the division of functions of the above-mentioned network elements is not fixed, but is merely an example, and the embodiments in this application are not limited.

[0105] Understandable Figure 1 and Figure 2 This application only illustrates one possible communication system architecture that can be applied to an embodiment of this application. In other possible scenarios, the communication system architecture may also include other devices. It should be noted that the terminal device mentioned above can be any of the terminal devices described below.

[0106] 1) Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), etc., is a device that provides voice or data connectivity to a user. Specifically, it includes devices that provide voice connectivity, devices that provide data connectivity, or devices that provide both voice and data connectivity. For example, it may include handheld devices with wireless connectivity or processing devices connected to a wireless modem. This terminal equipment can communicate with the core network via a radio access network (RAN), exchanging voice or data with the RAN, or interacting with the RAN to exchange voice and data. Currently, terminal devices can include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices (such as smartwatches, smart bracelets, pedometers, etc.), in-vehicle devices (such as cars, bicycles, electric vehicles, airplanes, ships, trains, high-speed trains, etc.), virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, smart home devices (such as refrigerators, televisions, air conditioners, electricity meters, etc.), intelligent robots, workshop equipment, wireless terminals in autonomous driving, wireless terminals in remote surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, or wireless terminals in smart homes, and flying equipment (such as intelligent robots, hot air balloons, drones, airplanes), etc. Terminal devices can also be other devices with terminal functions; for example, a terminal device can also be a device that performs terminal functions in D2D communication.Terminal devices can also include vehicle-to-everything (V2X) terminal devices, machine-to-machine / machine-type communications (M2M / MTC) terminal devices, internet of things (IoT) terminal devices, light UEs, reduced capability UEs (REDCAP UEs), subscriber units, subscriber stations, mobile stations, remote stations, access points (APs), remote terminals, access terminals, user terminals, user agents, or user devices, and drone equipment. For example, this can include mobile phones (or "cellular" phones), computers with mobile terminal devices, portable, pocket-sized, handheld, and computer-embedded mobile devices, etc. Examples include personal communication service (PCS) telephones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, and personal digital assistants (PDAs). It also includes limited devices, such as those with low power consumption, limited storage capacity, or limited computing power. Examples include information sensing devices such as barcode scanners, radio frequency identification (RFID), sensors, global positioning systems (GPS), and laser scanners. In this application, terminal devices with wireless transceiver capabilities and chips that can be installed in the aforementioned terminal devices are collectively referred to as terminal devices.

[0107] It should be noted that the terminal device may be a device or apparatus with a chip, or a device or apparatus with integrated circuitry, or a chip, module or control unit in the device or apparatus shown above. This application does not limit the specific device.

[0108] Please see Figure 3 , Figure 3This is a schematic diagram of a data storage architecture based on DCCF (Data Collection Coordination Function). The data collection coordination function (DCCF) network element is mainly used to coordinate the collection and distribution of data requested by NF (Network Function) consumers. It also has the ability to preprocess the collected data according to the parameters specified by the consumers. The analytical data repository function (ADRF) network element is mainly used for data storage and model storage. When consumers collect data through the DCCF network element, a simple preprocessing method for the collected data is proposed. That is, the consumer specifies the data to be processed, the data processing interval, and the corresponding data processing method to the DCCF network element. Optionally, a data processing method corresponds to an event identifier. For example, the data processing method can refer to taking the maximum value, minimum value, average value, variance, or the time interval between two consecutive occurrences of the same event. Accordingly, the DCCF network element processes the data according to the data and data processing method known to the consumer, obtains the data processing result, and feeds it back to the consumer. DCCF network elements can also obtain data from different events from data source network function network elements, and aggregate the data of different events according to each terminal device, each region of interest, or time granularity (minutes or hours), and then send the aggregated data to consumers. Optionally, consumers can perform data analysis, feature extraction, and model training on the aggregated data. This data processing method only supports simple data processing of a single type of data, which can be understood as data generated for the same event identification information. It does not support the joint processing of two or more types of data, i.e., the combination of multiple data features, feature extraction of combined data, etc., nor does it support custom data processing methods. To solve the above problems, the embodiments of this application propose the following solutions.

[0109] Please see Figure 4 , Figure 4 This is a flowchart illustrating a communication method provided in an embodiment of this application. The method includes, but is not limited to, the following steps:

[0110] Step S401: The third network element sends a third request message to the second network element.

[0111] Correspondingly, the second network element receives a third request message from the third network element. Optionally, this third request message may also be called a registration request message.

[0112] The third request message is used to request the registration of data processing methods supported by the third network element and / or data processing file information supported by the third network element. The supported data processing method refers to the supported operation name and / or operation description. The supported data processing file information refers to information related to supported receivable data processing files. This information includes one or more of the following: the file format, language, deployment method, or executable file of the receivable data processing file.

[0113] In one possible implementation, the third request message is used to request the registration of data processing methods supported by the third network element. The supported data processing methods refer to the names and / or descriptions of the supported data operation methods.

[0114] This process can be understood as the third network element storing the names and / or descriptions of the supported data operation methods in the second network element.

[0115] The supported data operation method name refers to the name of the data processing operation method supported by the third network element, which may include the following four methods: as follows:

[0116] Method 1: The supported data manipulation method names can be the names of data manipulation methods, such as one or more of the following: add, subtract, multiply, divide, or average. For example, one or more of the above can have a one-to-one correspondence with index values. For example, index value 0 represents addition, index value 1 represents subtraction, index value 2 represents multiplication, and so on.

[0117] Method 2: Supported data manipulation method names can be symbols representing data manipulation methods, such as one or more of the following: "+", "-", "*", or " / ". For example, one or more of the above can have a one-to-one correspondence with index values; for instance, index value 0 represents "+", index value 1 represents "-", index value 2 represents "*", and so on.

[0118] Method 3: The supported data operation method names can be function identification information, such as one or more of the following: add(data1, data2), substract(data1, data2), multiple(data1, data2), divide(data1, data2), or average(data1, data2).

[0119] Method 4: The supported data operation method names can be function identifier information customized by the third network element, such as one or more of the following: map(data1, data2), combination(data1, data2, feature) or encoding(data1, method).

[0120] The operation method description information refers to the specific usage description of each supported operation. For example, `add`, `+`, or `add(data1, data2)` means `data1 add data2`, or `data1+data2`, which is adding data1 and data2. `substract`, `-`, or `substract(data1, data2)` means `data1 subtract data2`, or `data1-data2`, which is subtracting data1 and data2. `multiple`, `*`, or `multiple(data1, data2)` means `data1 multiple data2`, or `data1*data2`, which is multiplying data1 and data2. `divide`, ` / `, or `divide(data1, data2)` means `data1 divided at data2`, or `data1 / data2`, which is dividing data1 by data2. For example, `map(data1, data2)` means mapping data1 to data2, or replacing data1 with data2. The `combination(data1, data2, feature)` function combines the data from `data1` and `data2` to form the data corresponding to `feature`. The specific action of this function is specified by its corresponding operation method description. The above description is merely one example of the operation method description. `encoding(data1, method)` encodes the data from `data1` using the method specified by `method`.

[0121] It should be noted that the description of the operation method can be in different languages, and this application does not limit it in the embodiments.

[0122] It should be noted that the above description of the operation method is only one example, and there may be other description methods. This application does not limit the specific methods.

[0123] Optionally, the second network element may save the data processing methods supported by the third network element, i.e., the names and / or descriptions of the supported data operation methods, in the operation profile information of the third network element's attribute file. The operation profile information includes the following fields: the names and / or descriptions of the supported data operation methods.

[0124] In another possible implementation, the third request message is used to request data processing file information supported by the third network element. For example, the third request message may include: support for using a consumer-defined data processing method (support use consumer-defined data processing method) and support for a consumer-defined file format (supported consumer-defined file format). Here, "support use consumer-defined data processing method" means that the third network element supports the first network element providing a custom data processing method, which refers to a data processing file provided by the first network element, and the third network element supports running this file locally for data processing. "Supported consumer-defined file format" may refer to information related to supported and acceptable data processing files.

[0125] Step S402: The first network element sends a second request message to the second network element.

[0126] Correspondingly, the second network element receives a second request message from the first network element. Optionally, this second request message may also be referred to as an acquisition operation request message.

[0127] The second request message is used to request at least one data processing method supported by a third network element and / or at least one data processing file information supported by a third network element.

[0128] In one possible implementation, when the second request message is used to request a data processing method supported by at least one third network element, the second request message may include supported operation information and region of interest (AOI) information. The AOI information indicates the third network elements within the region corresponding to the AOI information, and the supported operation information is used to request the operation profile information of the third network elements. In this case, the second request message is used to request the supported operation profile information of the third network elements within the region corresponding to the AOI information stored in the second network element. Accordingly, after receiving the second request message from the first network element, the second network element determines the third network element supporting data processing within the region corresponding to the AOI information based on the AOI information, and sends the operation profile information of the third network element stored in the second network element to the first network element.

[0129] In one possible implementation, when the second request message is used to request data processing file information supported by at least one third network element, the second request message may include support for using a consumer-defined data processing method of the third network element. This indicates a request for the third network element to support a custom data processing method provided by the first network element, whereby the method refers to a file provided by the first network element for data processing, and the third network element supports running this file locally for data processing. Correspondingly, after receiving the first request message from the first network element, the second network element sends a second response message to the first network element. This second response message includes support for a consumer-defined file format of the third network element.

[0130] Step S403: The second network element sends a second response message to the first network element.

[0131] Correspondingly, the first network element receives a second response message from the second network element. Optionally, this second response message may also be referred to as a response message for obtaining an operation request.

[0132] The second response message includes the name and / or description of the operation method for data processing supported by at least one third network element and / or information related to the file of the receivable data processing supported by at least one third network element.

[0133] Wherein, when the second request message is used to request data processing method supported by at least one third network element, the second response message includes the name of the operation method and / or the description information of the operation method supported by at least one third network element; when the second request message is used to request data processing file information supported by at least one third network element, the second response message includes relevant information about the file of the receivable data processing supported by at least one third network element.

[0134] In the above method, the second network element can provide the first network element with data processing methods and / or data processing file information supported by the third network element. Correspondingly, the first network element obtains the name and / or description information of the operation method supported by at least one third network element and / or the relevant information of the receivable data processing file supported by the at least one third network element. Furthermore, the first network element can provide basic or custom data processing methods.

[0135] In one possible implementation, after the first network element receives the second response message from the second network element, it determines one or more third network elements based on the second response message, and accordingly, the first network element sends a first request message to the one or more third network elements.

[0136] For example, the first network element determining one or more third network elements based on the second response message can include two methods: Method 1: The first network element internally determines one or more third network elements. Method 2: When the first network element needs to perform data feature processing, different third network elements support different data processing operations. The first network element determines one or more third network elements based on the data processing operations supported by the third network elements. In one example, third network element DHF1 supports data processing operation 1, and third network element DHF2 supports data processing operation 2. If the first network element needs to use data processing operation 1 on data 1 and data processing operation 2 on data 2, then the first network element determines the third network elements as DHF1 and DHF2. In another example, based on the AOI area supported by the third network element, for example, if the first network element needs to process the data in AOI (AOI1+AOI2), and the third network element DHF1 can obtain the data in AOI1, and DHF2 can obtain the data in AOI2, then the first network element sends a data processing request 1 to DHF1, where the data processing method corresponds to the data in AOI1. The first network element sends a data processing request 2 to DHF2, where the data processing method corresponds to the data in AOI2. That is, the first network element determines that the third network element is DHF1 and DHF2.

[0137] In one example, the first network element receives a second response message from the second network element. The second response message includes the names and descriptions of data processing operation methods supported by three third network elements: network element 1, network element 2, and network element 3. The data processing operation method supported by network element 1 is named add(data1, data2), and the operation description is adding data1 and data2. The data processing operation method supported by network element 2 is named subtraction, and the operation description is subtracting data1 and data2. The data processing operation method supported by network element 3 is named "*", and the operation description is multiplying data1 and data2. The first network element determines network element 1 based on the second response message, and accordingly, the first network element sends a first request message to network element 1.

[0138] In another example, the first network element receives a second response message from the second network element. The second response message includes data processing file information supported by two third network elements. The data processing file information supported by network element 1 includes the format of file 1 and the executable file of file 1. The data processing file information supported by network element 2 includes the format of file 2 and the executable file of file 2.

[0139] Optionally, one or more third network elements can be determined based on the second response message. When the first request message is sent to multiple third network elements, it may mean that the data required by the first network element requires different data processing methods. Different data processing methods can be distributed on different third network elements. Through distributed data processing, the processing of massive amounts of data can be realized, and the speed of massive data processing can be accelerated.

[0140] Step S404: The first network element sends a first request message to the third network element.

[0141] Correspondingly, the third network element receives the first request message from the first network element.

[0142] The first request message is used to request data processing. This first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset.

[0143] The processing method information for each feature vector in the samples of this dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample. The feature name can also refer to the identifier of the feature vector of the sample determined after processing the first data information using the first data processing method specified by the first network element. The first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0144] The first data processing method is determined by customizing one or more operation methods based on the obtained operation method names and descriptions supported by the third network element. The obtained operation method names and descriptions supported by the third network element are carried in the second response message. For example, the obtained operation method names and descriptions supported by the third network element could be: For network element 1, the operation method name is add(data1, data2), and the operation description is adding data1 and data2; for network element 2, the operation method name is subtraction, and the operation description is subtracting data1 and data2. The first data processing method could be (add, subtraction), i.e., addition followed by subtraction.

[0145] In one example, the first request message carries (feature name:processing method(formula:data)), where feature name represents the feature name, formula represents the first data processing method, and data represents the first data information. The processing method indicates the raw data needed by the first network element to obtain the feature vector of the sample with feature name and the processing method used on the raw data. Formula can refer to the data processing operation supported by the third network element, such as formula = A operation1 B. Operation1 is the name of the data operation method supported in the operation profile information of the third network element. A and B refer to data. For example, if feature name is NM1, formula is add, and data includes data1 and data2, then the first request message carries (NM1:processing method(add:data1,data2)).

[0146] In the above method, the processing method information of each feature in the sample data can be provided to the third network element in the above manner, so that the third network element can obtain the processing method information of each feature in the sample data, and perform data processing based on the processing method information of each feature to obtain the sample data required by the first network element.

[0147] The file information used for centralized sample processing of the dataset includes: second data information and / or first data processing file information. The second data information is used to indicate the data required when performing data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file used for data processing.

[0148] The first data processing file information is determined based on the relevant information of the receivable data processing files supported by the third network element. This relevant information of the receivable data processing files supported by the third network element is carried in the second response message.

[0149] In one example, the first request message includes (data, processing method(consumer-defined, processing file)), where data represents the second data information, referring to the required raw data. This data may also include the correspondence between the second data information and the input parameters of the corresponding data in the processing file. consumer-defined and processing file are used to indicate the first data processing file information. consumer-defined refers to processing data using a method defined by the first network element, and processing file refers to the file provided by the first network element to the third network element for processing data. This can be a specific file, such as `file`, or the file's storage address (file URI / storage place), as well as the file name or file identifier information, etc.

[0150] In the above method, the third network element can be provided with file information for centralized sample processing of the data. The third network element does not need to understand the specific data processing logic. It only needs to use the data provided by the first network element, i.e. the second data information, as the input data of the file according to the first data processing file information provided by the first network element, and run the data processing file to obtain the sample data required by the first network element.

[0151] It should be noted that the processing method information for each feature vector in the samples of the dataset includes first data information and second data information including the file information used for processing the samples in the dataset. This second data information can be data from different data sources or data from different events from the same data source, that is, data with different event identification information, or it can be the same data.

[0152] Step S405: The third network element performs data processing based on the first request message to determine the preprocessed dataset.

[0153] The preprocessed dataset includes sample data of one or more feature values, which is determined based on the processing method information of each feature in the samples of the dataset or the file information used for processing the samples in the dataset.

[0154] In the above method, the third network element can process data according to the data processing method provided by the first network element, avoiding the situation where the third network element cannot understand the data processing method provided by the first network element and cannot provide the required data to the first network element. Furthermore, different data processing operations are distributed across multiple third network elements, and the distributed processing of data can realize the processing of massive amounts of data, thus accelerating the speed of massive data processing.

[0155] In one example, the sample data is determined based on the processing method information of each feature in the sample in the dataset. For example, the first request message carries (NM1:processing method(add:data1,data2)), that is, the feature name is NM1, the first data processing method is add, and the first data information includes data1 and data2. Based on the first request message, the third network element processes data1 and data2 in the first data information according to the first data processing method, that is, add data1 and data2 to obtain data3. This data3 is the sample data, and the feature name corresponding to this sample data data3 is NM1.

[0156] In the above method, the first network element can provide the third network element with a corresponding data processing method based on the data processing operations supported by the third network element. This ensures that the third network element can recognize the data processing method and then process the data provided by the first network element according to the data processing method to obtain the dataset required by the first network element. This avoids the situation where the third network element is unable to process the data due to not recognizing the data processing method provided by the first network element.

[0157] In one example, the sample data is determined based on file information used for centralized sample processing of the dataset. Specifically, the file information used for centralized sample processing of the dataset may include: second data information and / or first data processing file information. The third network element installs the data processing file corresponding to the first data processing file information and performs data processing on the second data information based on the data processing file to obtain the sample data.

[0158] In the above method, the first network element can provide the third network element with the corresponding data processing method based on the data processing operations supported by the third network element, that is, the data processing method corresponding to the first data processing file information, ensuring that the third network element can recognize the data processing method. Furthermore, the third network element does not need to understand the specific data processing logic. It only needs to use the data provided by the first network element, that is, the second data information, as the input data of the first data processing file information provided by the first network element, and run the data processing file to obtain the sample data required by the first network element.

[0159] Step S406: The third network element sends a first response message to the first network element.

[0160] Correspondingly, the first network element receives the first response message from the third network element.

[0161] The first response message includes the preprocessed dataset.

[0162] In one possible implementation, the first request message includes first indication information, which indicates a sample feature sorting rule. The feature values ​​corresponding to the sample data in the dataset included in the first response message are sorted according to the sample feature sorting rule. This sample sorting rule can be determined by the first network element or agreed upon by the protocol; this application embodiment does not limit it.

[0163] In the above method, the feature values ​​corresponding to the sample data in the dataset are sorted according to the sorting rules of the sample features, which facilitates quick searching and retrieval of sample data.

[0164] In one example, the preprocessed dataset includes sample data with three feature values, namely feature1, feature2, and feature3. The first indication information is used to indicate the sample feature sorting rule as feature1, feature2, and feature3. After data processing, the third network element obtains the sample data with the three feature values, aggregates the data according to feature1, feature2, and feature3, and feeds back the aggregated sample data to the first network element, as shown in Table 1.

[0165] Table 1

[0166] Feature 1 Feature 2 Feature 3 Sample 1 Value11 Value12 Value13 Sample 2 Value21 Value22 Value23 Sample 3 Value31 Value32 Value33

[0167] exist Figure 4In the described method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The third network element can then process the data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data for the file used for processing the samples in the dataset, and run the data processing file to obtain the sample data needed by the first network element. Furthermore, the first network element can obtain sample data containing one or more feature values, which is processed based on the data processing method provided by the first network element. Through this method, the first network element can send the same data processing request to multiple third network elements, thus enabling the processing of massive amounts of data and obtaining the sample data needed by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0168] Please see Figure 5 , Figure 5 This is a flowchart illustrating a communication method provided in an embodiment of this application. The method includes, but is not limited to, the following steps:

[0169] For steps S501-S503, please refer to the relevant descriptions in steps S401-S403, which will not be repeated here.

[0170] Step S504: The first network element sends a first request message to the second network element.

[0171] Correspondingly, the second network element receives the first request message from the first network element.

[0172] In one example, a first network element sends a first request message to a second network element. This first request message includes (data:processing method list[formula,data1][consumer-defined,data2,processingfile]), meaning it contains processing method information for each feature vector in the samples of the dataset and file information for processing the samples. Here, `data` represents all the raw data to be processed, and the processing method information for each feature vector in the samples includes a first data processing method and first data information. `formula` represents the first data processing method, and `data1` represents the first data information, i.e., the data required for data processing according to the first data processing method. The file information for processing the samples includes first data processing file information and second data information. `consumer-defined` and `processing file` represent the first data processing file information, and `data2` represents the second data information, i.e., the data required for data processing according to the data processing file corresponding to the first data processing file information. Optionally, `data1` and `data2` include the correspondence between input data and raw data.

[0173] Step S505: The second network element determines one or more third network elements based on the first request message.

[0174] The one or more third network elements support the processing method information for each feature vector in the samples of the dataset included in the first request message and / or the file information for processing the samples in the dataset.

[0175] Step S506: The second network element sends a fourth request message to one or more third network elements.

[0176] Correspondingly, one or more third network elements receive a fourth request message from the second network element. Each third network element corresponds to one fourth request message, wherein each of the one or more fourth request messages includes first information and / or second information; wherein the first information is a subset of the feature vector processing method information in the samples of the dataset included in the first request message, and / or the second information is a subset of the file information included in the first request message for processing samples in the dataset. Alternatively, the first information can be understood as a portion of the feature vector processing method information in the samples of the dataset included in the first request message, and the second information is a portion of the file information included in the first request message for processing samples in the dataset.

[0177] In one example, the first request message includes (data:processing method list([formula1,data1][formula2 data2][consumer-defined1,data3,processing file1][consumer-defined2,data4,processing file2]). The second network element determines four third network elements based on the first request message, namely network element 1, network element 2, network element 3, and network element 4. The second network element sends a fourth request message to network element 1, which includes first information, namely [formula1,data1]. The second network element sends a fourth request message to network element 2, which includes first information, namely [formula2 data2]. The second network element sends a fourth request message to network element 3, which includes second information, namely [consumer-defined1,data3,processing file1]. The second network element sends a fourth request message to network element 4, which includes second information, namely [consumer-defined2,data4,processing file2].

[0178] Furthermore, each third network element performs data processing based on the fourth request message to determine the preprocessed dataset.

[0179] In one possible implementation, after each third network element determines the preprocessed dataset based on the fourth request message, it can either feed back the preprocessed dataset to the second network element or to the first network element, as follows:

[0180] Method 1: Each third network element feeds back the preprocessed dataset to the second network element, which may include the following steps S507A-S509A.

[0181] Step S507A: One or more third network elements send one or more fourth response messages to the second network element.

[0182] Correspondingly, the second network element receives one or more fourth response messages from one or more third network elements. Each of the one or more third network elements corresponds to one fourth response message, and each fourth response message includes a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values, which are determined based on the first information or the second information.

[0183] Step S508A: The second network element determines the total sample dataset. This total sample dataset is determined based on the preprocessed dataset carried in one or more fourth response messages.

[0184] In one example, there are four third network elements, namely network element 1, network element 2, network element 3 and network element 4. Network element 1 determines the preprocessed dataset based on the fourth request message. The preprocessed dataset includes sample data with one feature value, namely feature1. Network element 2 determines the preprocessed dataset based on the fourth request message. The preprocessed dataset includes sample data with one feature value, namely feature2. Network element 3 determines the preprocessed dataset based on the fourth request message. The preprocessed dataset includes sample data with one feature value, namely feature3. Network element 4 determines the preprocessed dataset based on the fourth request message. The preprocessed dataset includes sample data with one feature value, namely feature4. The second network element determines the total sample dataset based on feature1, feature2, feature3 and feature4.

[0185] Step S509A: The second network element sends a first response message to the first network element. This first response message includes the total sample dataset.

[0186] Method 2: Each third network element feeds back the preprocessed dataset to the first network element. Specifically, this may include the following step S507B.

[0187] Step S507B: One or more third network elements send one or more fourth response messages to the first network element.

[0188] Accordingly, the first network element receives one or more fourth response messages from one or more third network elements. Each of the one or more third network elements corresponds to one fourth response message. Each fourth response message includes a preprocessed dataset, which includes sample data of one or more feature values, the sample data being determined based on the first information or the second information.

[0189] In the above method, the third network element can process data according to the data processing method provided by the first network element, avoiding the situation where the third network element cannot understand the data processing method provided by the first network element and cannot provide the required data to the first network element. Furthermore, different data processing operations are distributed across multiple third network elements, realizing distributed data processing and accelerating the data processing speed.

[0190] exist Figure 5In the described method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The third network element can then process the data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data for the file used for processing the samples in the dataset, and run the data processing file to obtain the sample data needed by the first network element. Furthermore, the first network element can obtain sample data containing one or more feature values, which is processed based on the data processing method provided by the first network element. Through this method, the first network element can send the same data processing request to multiple third network elements, thus enabling the processing of massive amounts of data and obtaining the sample data needed by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0191] Taking the first network element as the consumer, the second network element as the DMF network element, and the third network element as the DHF network element as an example, please refer to [link to example]. Figure 6 , Figure 6 This is a flowchart illustrating another communication method provided in an embodiment of this application. The method includes, but is not limited to, the following steps:

[0192] Step S601: The DHF network element sends a third request message to the DMF network element.

[0193] Correspondingly, the DMF network element receives the third request message from the DHF network element.

[0194] The third request message is used to request the registration of data processing methods supported by the third network element. These supported data processing methods refer to the supported operation name and / or operation description. For details, please refer to the relevant description in step S401, which will not be repeated here.

[0195] Step S602: The consumer sends a second request message to the DMF network element.

[0196] Correspondingly, the DMF network element receives the second request message from the consumer.

[0197] The second request message is used to request at least one data processing method supported by a third network element. For details, please refer to the relevant description in step S402.

[0198] Step S603: The DMF network element sends a second response message to the consumer.

[0199] Correspondingly, the consumer receives a second response message from the DMF network element.

[0200] The second response message includes the name and / or description of the operation method for data processing supported by at least one third network element. See the relevant description in step S403 for details.

[0201] Step S604: The consumer determines a DHF network element based on the second response message.

[0202] For details, please refer to the relevant description in step S403.

[0203] Step S605: The consumer sends a first request message to the DHF network element.

[0204] Correspondingly, the DHF network element receives the first request message from the consumer.

[0205] The first request message is used to request data processing. This first request message includes processing method information for each feature vector in the samples of the dataset. See step S404 for details.

[0206] Step S606: The DHF network element performs data processing based on the first request message to determine the preprocessed dataset.

[0207] The preprocessed dataset includes sample data of one or more feature values, which are determined based on the processing method information of each feature in the samples of the dataset. See step S405 for details.

[0208] Step S607: The DHF network element sends a first response message to the consumer.

[0209] The first response message includes the preprocessed dataset. See step S406 for details.

[0210] exist Figure 6In the described method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The third network element can then process the data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data for the file used for processing the samples in the dataset, and run the data processing file to obtain the sample data needed by the first network element. Furthermore, the first network element can obtain sample data containing one or more feature values, which is processed based on the data processing method provided by the first network element. Through this method, the first network element can send the same data processing request to multiple third network elements, thus enabling the processing of massive amounts of data and obtaining the sample data needed by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0211] Taking the first network element as the consumer, the second network element as the DMF network element, and the third network element as the DHF network element as an example, please refer to [link to example]. Figure 7 , Figure 7 This is a flowchart illustrating another communication method provided in an embodiment of this application. The method includes, but is not limited to, the following steps:

[0212] Step S701: The DHF network element sends a third request message to the DMF network element.

[0213] Correspondingly, the DMF network element receives the third request message from the DHF network element.

[0214] The third request message is used to request the registration of data processing file information supported by the third network element. This supported data processing file information refers to information related to supported and receivable data processing files. This information includes one or more of the following: the file format, language, deployment method, or executable file of the receivable data processing file. For details, please refer to the relevant description in step S401, which will not be repeated here.

[0215] Step S702: The consumer sends a second request message to the DMF network element.

[0216] Correspondingly, the DMF network element receives the second request message from the consumer.

[0217] The second request message is used to request data processing file information supported by at least one third network element. For details, please refer to the relevant description in step S402.

[0218] Step S703: The DMF network element sends a second response message to the consumer.

[0219] Correspondingly, the consumer receives a second response message from the DMF network element.

[0220] The second response message includes information about a file that can be received and processed by at least one third network element. See the relevant description in step S403 for details.

[0221] Step S704: The consumer determines a DHF network element based on the second response message.

[0222] For details, please refer to the relevant description in step S403.

[0223] Step S705: The consumer sends a first request message to the DHF network element.

[0224] Correspondingly, the DHF network element receives the first request message from the consumer.

[0225] The first request message is used to request data processing. This first request message includes file information for processing centralized samples within the data set. See step S404 for details.

[0226] Step S706: The DHF network element performs data processing based on the first request message to determine the preprocessed dataset.

[0227] The preprocessed dataset includes sample data of one or more feature values, which is determined by file information used for sample processing in the dataset. See step S405 for details.

[0228] Step S707: The DHF network element sends the first response message to the consumer.

[0229] The first response message includes the preprocessed dataset. See step S406 for details.

[0230] exist Figure 7In the described method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The third network element can then process the data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data for the file used for processing the samples in the dataset, and run the data processing file to obtain the sample data needed by the first network element. Furthermore, the first network element can obtain sample data containing one or more feature values, which is processed based on the data processing method provided by the first network element. Through this method, the first network element can send the same data processing request to multiple third network elements, thus enabling the processing of massive amounts of data and obtaining the sample data needed by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0231] Taking the first network element as the consumer, the second network element as the DMF network element, and the third network elements as DHF network element 1 and DHF network element 2 as an example, please refer to [link to example]. Figure 8 , Figure 8 This is a flowchart illustrating another communication method provided in an embodiment of this application. The method includes, but is not limited to, the following steps:

[0232] Step S801: DHF network element 1 sends a third request message to DMF network element.

[0233] Correspondingly, the DMF network element receives the third request message from DHF network element 1.

[0234] The third request message is used to request the registration of data processing methods and / or data processing file information supported by the third network element. For details, please refer to the relevant description in step S401.

[0235] Step S802: DHF network element 2 sends a third request message to DMF network element.

[0236] Correspondingly, the DMF network element receives the third request message from the DHF network element 2. See the relevant description in step S401 for details.

[0237] It should be noted that there is no obvious sequential relationship between steps S801 and S802.

[0238] Step S803: The consumer sends a second request message to the DMF network element.

[0239] Correspondingly, the DMF network element receives the second request message from the consumer.

[0240] The second request message is used to request at least one data processing method supported by a third network element and / or at least one data processing file information supported by a third network element. For details, please refer to the relevant description in step S402.

[0241] Step S804: The DMF network element sends a second response message to the consumer.

[0242] Correspondingly, the consumer receives a second response message from the DMF network element.

[0243] The second response message includes the name and / or description of the operation method supported by at least one third network element and / or information about the file of the data processing that can be received by at least one third network element. See the relevant description in step S403 for details.

[0244] Step S805: The consumer sends the first request message to the DMF network element.

[0245] Correspondingly, the DMF network element receives the first request message from the consumer.

[0246] The first request message is used to request data processing. This first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset.

[0247] Step S806: The DMF network element determines one or more DHF network elements based on the first request message.

[0248] For example, the one or more DHFs can be DHF network element 1 and DHF network element 2. DHF network element 1 and / or DHF network element 2 support processing method information for each feature vector in the samples of the dataset included in the first request message and / or file information for processing the samples in the dataset.

[0249] Step S807: The DMF network element sends a fourth request message to DHF network element 1 and DHF network element 2.

[0250] For details, please refer to the relevant description in step S506.

[0251] In one possible implementation, after DHF network element 1 and DHF network element 2 determine the preprocessed dataset based on the fourth request message, they can either feed the preprocessed dataset back to the DMF network element or back to the consumer, as detailed below:

[0252] Method 1: DHF network element 1 and DHF network element 2 feed back the preprocessed dataset to the DMF network element, which may include the following steps S808A-S810A.

[0253] Step S808A: DHF network element 1 and DHF network element 2 respectively send the fourth response message to the DMF network element.

[0254] Correspondingly, the DMF network element receives fourth response messages from DHF network element 1 and DHF network element 2. Each fourth response message includes a preprocessed dataset, which includes sample data of one or more feature values. The sample data is determined based on the first information or the second information. For details, please refer to the relevant description in step S507A.

[0255] Step S809A: The DMF network element determines the total sample dataset. This total sample dataset is determined based on the preprocessed dataset carried in one or more fourth response messages. See step S508A for details.

[0256] Step S810A: The DMF network element sends a first response message to the consumer. This first response message includes the total sample dataset.

[0257] Method 2: DHF network element 1 and DHF network element 2 feed back the preprocessed dataset to the consumer. Specifically, this may include the following steps S808B.

[0258] Step S808B: DHF network element 1 and DHF network element 2 respectively send the fourth response message to the consumer.

[0259] Correspondingly, the consumer receives fourth response messages from DHF network element 1 and DHF network element 2. Each fourth response message includes a preprocessed dataset, which includes sample data of one or more feature values, determined based on the first information or the second information. For details, please refer to the relevant description in step S507B.

[0260] exist Figure 8In the described method, the first network element can provide processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. That is, the first network element can provide basic or custom data processing methods. The third network element can then process the data based on the processing method information for each feature to obtain the sample data needed by the first network element. Alternatively, the third network element does not need to understand the specific data processing logic; it only needs to use the data provided by the first network element as input data for the file used for processing the samples in the dataset, and run the data processing file to obtain the sample data needed by the first network element. Furthermore, the first network element can obtain sample data containing one or more feature values, which is processed based on the data processing method provided by the first network element. Through this method, the first network element can send the same data processing request to multiple third network elements, thus enabling the processing of massive amounts of data and obtaining the sample data needed by the first network element through multiple third network elements. This sample data can be directly used for model training.

[0261] The methods of the embodiments of this application have been described in detail above, and the apparatus of the embodiments of this application is provided below.

[0262] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a communication device 900 provided in an embodiment of this application. The communication device 900 may include modules or units corresponding to the methods / operations / steps / actions performed by the first network element, the second network element, or the third network element in the above method embodiments. The unit may be a hardware circuit, software, or a combination of hardware circuit and software.

[0263] In one possible implementation, the communication device 900 may include a processing unit 901 and a transceiver unit 902, the specific details of which are as follows:

[0264] The processing unit 901 is used for data processing. The transceiver unit 902 can implement corresponding communication functions. The transceiver unit 902 can also be called a communication interface or a communication module.

[0265] Optionally, the communication device 900 may further include a storage unit, which can be used to store instructions and / or data. The processing unit 901 can read the instructions and / or data in the storage module to enable the implementation of the aforementioned method embodiments.

[0266] Optionally, the transceiver unit 902 may include a sending unit and a receiving unit. The sending unit is used to perform the sending operation in the above method embodiments. The receiving unit is used to perform the receiving operation in the above method embodiments.

[0267] It should be noted that the communication device 900 may include a transmitting unit but not a receiving unit. Alternatively, the communication device 900 may include a receiving unit but not a transmitting unit. Specifically, it depends on whether the above-described scheme executed by the communication device 900 includes both transmitting and receiving actions.

[0268] Optionally, the communication device 900 is used to perform the above. Figures 4-8 The actions performed by the first network element in the illustrated embodiment are shown above. For details, please refer to the above. Figures 4-8 The relevant descriptions in the illustrated embodiments will not be elaborated here. For example, the communication device 900 is used to execute the following scheme: the transceiver unit 902 is used to send a first request message, which requests data processing. The first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset; the transceiver unit 902 is also used to receive a first response message, which includes a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values, which are determined based on the processing method information for each feature in the samples of the dataset or the file information for processing the samples in the dataset.

[0269] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0270] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0271] In another possible implementation, the transceiver unit 902 is further configured to send a second request message to the second network element, the second request message being used to request data processing method supported by at least one third network element and / or data processing file information supported by the at least one third network element; the transceiver unit 902 is further configured to receive a second response message from the second network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information of the receivable data processing file supported by the at least one third network element.

[0272] In another possible implementation, the first data processing method is determined by customizing and arranging one or more operation methods based on the obtained operation method names and operation method descriptions supported by the third network element.

[0273] In another possible implementation, the information related to the receivable data processing file supported by the third network element includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0274] In another possible implementation, the first data processing file information is determined based on relevant information about the receivable data processing files supported by the third network element.

[0275] In another possible implementation, the first request message includes first indication information, which indicates a sample feature sorting rule, and the feature values ​​corresponding to the sample data in the dataset included in the first response message are sorted according to the sample feature sorting rule.

[0276] It should be noted that the implementation and beneficial effects of each module can be found by referring to [the relevant documentation / reference]. Figures 4-8 The corresponding description of the method embodiments shown.

[0277] Optionally, the communication device 900 is used to perform the above. Figures 4-8 The actions performed by the second network element in the illustrated embodiment are shown above. For details, please refer to the above. Figures 4-8 The relevant descriptions in the illustrated embodiments are not elaborated here. For example, the communication device 900 is used to execute the following scheme: the transceiver unit 902 is used to receive a third request message from a third network element, the third request message being used to request registration of data processing methods supported by the third network element and / or data processing file information supported by the third network element; the transceiver unit 902 is also used to receive a second request message from a first network element; the second request message being used to request at least one data processing method supported by a third network element and / or data processing file information supported by the at least one third network element; the transceiver unit 902 is also used to send a second response message to the first network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element and / or relevant information of the receivable data processing file supported by the at least one third network element.

[0278] In one possible implementation, the transceiver unit 902 is further configured to receive a first request message, which requests data processing. The first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset. The processing unit 901 is further configured to determine one or more third network elements based on the first request message; and send a fourth request message to the one or more third network elements, which includes first information and / or second information. The first information is a subset of the processing method information for each feature vector in the samples of the dataset included in the first request message, and / or the second information is a subset of the first information. The request message includes a subset of file information for sample processing in the dataset; the transceiver unit 902 is further configured to receive one or more fourth response messages, each of the one or more fourth response messages including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the first information or the second information; the processing unit 901 is further configured to determine the total sample dataset; wherein the total sample dataset is determined based on the preprocessed dataset carried in one or more fourth response messages; the transceiver unit 902 is further configured to send a first response message, the first response message including the total sample dataset.

[0279] In another possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0280] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0281] It should be noted that the implementation and beneficial effects of each module can be found by referring to [the relevant documentation / reference]. Figures 4-8 The corresponding description of the method embodiments shown.

[0282] Optionally, the communication device 900 is used to perform the above. Figures 4-8 The actions performed by the third network element in the illustrated embodiment. For details, please refer to the above. Figures 4-8The relevant descriptions in the illustrated embodiments are not elaborated here. For example, the communication device 900 is used to execute the following scheme: the transceiver unit 902 is used to receive a first request message, which requests data processing. The first request message includes processing method information for each feature vector in the samples of the dataset and / or file information for processing the samples in the dataset; the processing unit 901 is further used to perform data processing based on the first request message to determine a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values, which is determined based on the processing method information for each feature in the samples of the dataset or the file information for processing the samples in the dataset; the transceiver unit 902 is further used to send a first response message, which includes the preprocessed dataset.

[0283] In one possible implementation, the processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

[0284] In another possible implementation, the file information for processing centralized samples in the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required for data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file for data processing.

[0285] In another possible implementation, the transceiver unit 902 is further configured to send a third request message to the second network element, the third request message being used to request registration of supported data processing methods and / or supported data processing file information.

[0286] In another possible implementation, the supported data processing method refers to the name and / or description of the supported data operation method, and the supported data processing file information refers to the relevant information of the supported receivable data processing file.

[0287] In another possible implementation, the relevant information of the supported receivable data processing file includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

[0288] In another possible implementation, the first request message further includes first indication information, which indicates a sample feature sorting rule; the preprocessed dataset is obtained by sorting based on the sample feature sorting rule.

[0289] It should be noted that the implementation and beneficial effects of each module can be found by referring to [the relevant documentation / reference]. Figures 4-8 The corresponding description of the method embodiments shown is provided below. The module division in the embodiments of this application is illustrative and is merely a logical functional division; other division methods may be used in actual implementation.

[0290] The processing unit 901 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver unit 902 can be implemented by a transceiver or transceiver-related circuitry. The transceiver unit 902 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0291] Please see Figure 10 , Figure 10 This is a schematic diagram of another communication device 1000 provided in an embodiment of this application. The communication device 1000 includes at least one processor 1001 and a communication interface 1003. Optionally, it also includes a memory 1002. The processor 1001, memory 1002, and communication interface 1003 are interconnected via a bus 1004. Optionally, the processor 1001 and the memory 1002 can be integrated together.

[0292] The memory 1002 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), and is used for related computer programs and data. The communication interface 1003 is used for receiving and sending data.

[0293] The processor 1001 can be one or more central processing units (CPUs). If the processor 1001 is a CPU, the CPU can be a single-core CPU or a multi-core CPU.

[0294] The processor 1001 in the communication device 1000 is used to read computer programs or instructions stored in the memory 1002 to implement the functions of the aforementioned processing unit, and the communication interface 1003 in the communication device 1000 is used to implement the functions of the aforementioned transceiver unit.

[0295] This application also provides a chip device including at least one processor, which is used to call a computer program or instructions stored in a memory to cause the processor to execute the method provided in the above embodiments.

[0296] In one possible implementation, the input of the chip device corresponds to the receiving operation in any of the above embodiments, and the output of the chip device corresponds to the sending operation in any of the above embodiments.

[0297] Optionally, the processor is coupled to the memory via an interface.

[0298] Optionally, the chip device may also include a memory storing computer program instructions.

[0299] This application also provides a computer-readable storage medium storing a computer program or instructions that, when executed on a processor, implement the method performed by the first network element, the second network element, or the third network element in the above method embodiments.

[0300] This application also provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are run on a processor, they implement the method executed by the first network element, the second network element, or the third network element in the above method embodiments.

[0301] This application also provides a communication system, which includes a first network element, a second network element, and a third network element as described in the above embodiments. The first network element is used to perform some or all of the operations performed by the first network element in the above method embodiments, the second network element is used to perform some or all of the operations performed by the second network element in the above method embodiments, and the third network element is used to perform some or all of the operations performed by the third network element in the above method embodiments.

[0302] It is understood that the processor in the embodiments of this application may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor may be a microprocessor or any conventional processor.

[0303] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a base station or terminal. Of course, the processor and storage medium can also exist as discrete components in the base station or terminal.

[0304] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0305] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0306] In the description of this application, terms such as “first,” “second,” “S401,” or “S402” are used only for the purpose of distinguishing descriptions and for the convenience of context. The different sequence numbers themselves do not have specific technical meanings and should not be construed as indicating or implying relative importance, nor should they be construed as indicating or implying the order of execution of operations. The order of execution of each process should be determined by its function and internal logic.

Claims

1. A communication method, characterized in that, Applied to the first network element, including: Send a first request message, which is used to request data processing. The first request message includes processing method information for each feature vector in the samples in the dataset and / or file information for processing the samples in the dataset. Receive a first response message, the first response message including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the processing method information of each feature in the samples of the dataset or the file information for processing the samples in the dataset.

2. The method according to claim 1, characterized in that, The processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

3. The method according to claim 1, characterized in that, The file information used for centralized sample processing of the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required when performing data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file used for data processing.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Send a second request message to the second network element, the second request message being used to request at least one data processing method supported by a third network element and / or data processing file information supported by the at least one third network element; Receive a second response message from the second network element, the second response message including the name and / or description information of the operation method supported by the at least one third network element for data processing and / or relevant information of the receivable data processing file supported by the at least one third network element.

5. The method according to claim 4, characterized in that, The first data processing method is determined by customizing and arranging one or more operation methods based on the operation method name and operation method description information of the data processing supported by the third network element.

6. The method according to any one of claims 4, characterized in that, The information related to the receivable data processing files supported by the third network element includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

7. The method according to claim 6, characterized in that, The first data processing file information is determined based on the relevant information of the receivable data processing files supported by the third network element.

8. The method according to any one of claims 1-7, characterized in that, The first request message includes first indication information, which is used to indicate the sample feature sorting rule. The feature values ​​corresponding to the sample data in the dataset included in the first response message are sorted according to the sample feature sorting rule.

9. A communication method, characterized in that, Applied to the second network element, including: Receive a third request message from a third network element, the third request message being used to request the registration of data processing methods supported by the third network element and / or data processing file information supported by the third network element; Receive a second request message from a first network element; the second request message is used to request at least one data processing method supported by a third network element and / or data processing file information supported by the at least one third network element. Send a second response message to the first network element. The second response message includes the name and / or description of the operation method supported by the at least one third network element and / or information about the file of the data processing that the at least one third network element supports.

10. The method according to claim 9, characterized in that, The method further includes: Receive a first request message, the first request message being used to request data processing, the first request message including processing method information for each feature vector in the samples in the dataset and / or file information for processing the samples in the dataset; One or more third network elements are determined based on the first request message; Send a fourth request message to the one or more third network elements, the fourth request message including first information and / or second information; wherein, the first information is a subset of the processing method information for each feature vector in the samples of the dataset included in the first request message, and / or the second information is a subset of the file information for processing samples in the dataset included in the first request message; Receive one or more fourth response messages, each of the one or more fourth response messages including a preprocessed dataset, the preprocessed dataset including sample data of one or more feature values, the sample data being determined based on the first information or the second information; Determine the total sample dataset; wherein the total sample dataset is determined based on the preprocessed dataset carried in one or more fourth response messages; Send a first response message, which includes the total sample dataset.

11. The method according to claim 9 or 10, characterized in that, The processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

12. The method according to claim 9 or 10, characterized in that, The file information used for centralized sample processing of the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required when performing data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file used for data processing.

13. A communication method, characterized in that, Applied to third-party network elements, including: Receive a first request message, the first request message being used to request data processing, the first request message including processing method information for each feature vector in the samples in the dataset and / or file information for processing the samples in the dataset; Based on the first request message, data processing is performed to determine a preprocessed dataset. The preprocessed dataset includes sample data of one or more feature values. The sample data is determined based on the processing method information of each feature in the samples of the dataset or the file information used for processing the samples in the dataset. Send a first response message, which includes the preprocessed dataset.

14. The method according to claim 13, characterized in that, The processing method information for each feature vector in the samples of the dataset includes one or more of the following: feature name, first data processing method, or first data information; the feature name is used to indicate the characteristic identifier of the sample, the first data processing method is used to indicate the data processing operation corresponding to the feature name, and the first data information is used to indicate the data required when performing data processing using the first data processing method.

15. The method according to claim 13 or 14, characterized in that, The file information used for centralized sample processing of the dataset includes: second data information and / or first data processing file information, wherein the second data information is used to indicate the data required when performing data processing using the data processing file corresponding to the first data processing file information, and the first data processing file information is used to indicate the executable file used for data processing.

16. The method according to any one of claims 13-15, characterized in that, The method further includes: A third request message is sent to the second network element, the third request message being used to request the registration of supported data processing methods and / or supported data processing file information.

17. The method according to claim 16, characterized in that, The supported data processing methods refer to the names and / or descriptions of the supported data operation methods, and the supported data processing file information refers to the relevant information of the supported and receivable data processing files.

18. The method according to claim 16, characterized in that, The relevant information of the supported receivable data processing files includes one or more of the following: the file format, file language, file deployment method, or executable file of the receivable data processing file.

19. The method according to any one of claims 13-18, characterized in that, The first request message also includes first indication information, which is used to indicate the sample feature sorting rules; the preprocessed dataset is obtained by sorting based on the sample feature sorting rules.

20. A communication device, characterized in that, The apparatus includes a transceiver unit and a processing unit, wherein the processing unit is configured to perform the processing operation in the method as described in any one of claims 1-8, and the transceiver unit is configured to perform the transceiver operation in the method as described in any one of claims 1-8.

21. A communication device, characterized in that, The apparatus includes a transceiver unit and a processing unit, wherein the processing unit is configured to perform the processing operation in the method as described in any one of claims 9-12, and the transceiver unit is configured to perform the transceiver operation in the method as described in any one of claims 9-12.

22. A communication device, characterized in that, The apparatus includes a transceiver unit and a processing unit, the processing unit being configured to perform processing operations in the method as described in any one of claims 13-19, and the transceiver unit being configured to perform transceiver operations in the method as described in any one of claims 13-19.

23. A communication device, characterized in that, The device includes at least one processor and a communication interface, wherein the at least one processor invokes a computer program or instructions stored in a memory to perform the method as described in claims 1-8.

24. A communication device, characterized in that, The device includes at least one processor and a communication interface, wherein the at least one processor invokes a computer program or instructions stored in a memory to perform the method as described in claims 9-12.

25. A communication device, characterized in that, The device includes at least one processor and a communication interface, wherein the at least one processor invokes a computer program or instructions stored in a memory to perform the method as described in claims 13-19.

26. A communication system, characterized in that, The communication system includes: the apparatus as described in claim 23, the apparatus as described in claim 24, and the apparatus as described in claim 25.

27. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or instructions that, when executed on a processor, implement the method as described in any one of claims 1-19.

28. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when run on a computer, implement the method as described in any one of claims 1-19.

Images