Data acquisition method and related device

Abstract

Disclosed in the embodiments of the present application is a data acquisition method. In the method, a user of data used for a machine learning model may acquire, on the basis of query assistance information sent by a collection node and from a first storage node, first data collected by the collection node, such that the user can acquire the first data in a convenient and standardized manner on the basis of the instruction of the collection node, so as to implement the operations, such as training, inference and / or monitoring, of the machine learning model in a wireless task.

Description

Data acquisition method and related device

[0001] The present application claims priority to the Chinese patent application No. 202410898121.6, filed on July 4, 2024, and entitled "A data acquisition method and related device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of artificial intelligence, in particular to a data acquisition method and related device. BACKGROUND

[0003] With the continuous development of artificial intelligence technology, artificial intelligence technology is also applied to wireless communication systems, and is integrated with wireless networks, thereby realizing network native intelligence and the intelligence of wireless devices such as terminals and base stations in the network.

[0004] When artificial intelligence technology is applied in a wireless communication system, the data collected for the training or inference process of a machine learning model has a great influence on the application of artificial intelligence technology in the wireless communication system. However, there is no clear data collection and use scheme in the current wireless communication system, which makes it difficult for the user of data such as base stations or terminals to conveniently obtain data for a machine learning model. SUMMARY

[0005] The embodiments of the present application provide a data acquisition method, which can enable the user of data to conveniently and regularly acquire data for a machine learning model. The present application also provides corresponding devices, equipment, computer readable storage media and computer program products, etc.

[0006] The first aspect of the present application provides a data acquisition method, wherein the communication system includes a data using node for a machine learning model, a data collecting node and a data storing node. The method includes: the using node receiving query assistance information about first data from the collecting node, the first data being contained in the data, and the query assistance information being used to query the first data; the using node sending a first acquisition request about the first data to a first storing node storing the first data according to the query assistance information, the first storing node being contained in the storing node; and the using node receiving the first data from the first storing node.

[0007] In the first aspect, the user of data for a machine learning model can acquire the first data collected by the collecting node from the first storing node based on the query assistance information sent by the collecting node, so that the user can conveniently and regularly acquire the first data based on the indication of the collecting node to realize the training, inference and / or monitoring of the machine learning model in the wireless task.

[0008] In a possible implementation manner of the first aspect, the query assistance information comprises index information used for indicating the storage location of the first data.

[0009] In the possible implementation manner, according to the index information, the storage location of the first data can be determined efficiently by the using node, and thus the first data can be queried efficiently from the first storage node.

[0010] In a possible implementation manner of the first aspect, the index information comprises one or more of the following information: location information of the first storage node, storage location information of the first data on the first storage node.

[0011] In the possible implementation manner, the location information of the first storage node can comprise an address of the first storage node, and the storage location information of the first data on the first storage node can be used to index the first data on the first storage node. The specific content of the storage location information can be in various forms. For example, the storage location information can comprise an identifier of a data set in which the first data is stored.

[0012] In a possible implementation manner of the first aspect, the query assistance information comprises a feature of the first data.

[0013] In the possible implementation manner, when the first storage node stores data according to the features of the data, the storage location information can further comprise the feature of the first data, so as to indicate that the first data can be indexed in the first storage node according to the feature of the first data. For example, the feature of the first data contained in the storage location information can comprise one or more of the following features: data amount of the first data, use of the first data, collection condition of the first data, function of the first data, manufacturer to which the first data belongs, type of the first data, format of the first data, precision of the first data, distribution of the first data, and source of the first data.

[0014] In a possible implementation manner of the first aspect, before the using node receives the query assistance information about the first data from the collecting node, the method further comprises: sending, by the using node, a second acquisition request about the first data to the collecting node.

[0015] The second aspect of the present application provides a data acquisition method. In the method, a communication system comprises a using node of data used for a machine learning model, a collecting node of the data, and a storage node of the data. The method comprises: sending, by the collecting node, query assistance information about first data to the using node, the first data being contained in the data, and the query assistance information being used for instructing the using node to query the first data from a first storage node in which the first data is stored.

[0016] In a possible implementation manner of the second aspect, before the collection node sends the query assistance information about the first data to the usage node, the method further includes: the collection node sending the first data to the first storage node; the collection node receiving storage indication information about the first data from the first storage node, the storage indication information being used for indicating storage of the first data in the first storage node; and the collection node obtaining the query assistance information according to the storage indication information.

[0017] In a possible implementation manner of the second aspect, the storage indication information is used for indicating a storage location of the first data.

[0018] In a possible implementation manner of the second aspect, the storage indication information includes a feature of the first data, and the first data in the first storage node is stored based on the feature of the first data.

[0019] In a possible implementation manner of the second aspect, the collection node sending the first data to the first storage node includes: the collection node sending the first data to the first storage node through over-the-top (OTT) data transmission.

[0020] In a possible implementation manner of the second aspect, the query assistance information includes index information used for indicating the storage location of the first data.

[0021] In a possible implementation manner of the second aspect, the index information includes one or more of the following information: location information of the first storage node, storage location information of the first data on the first storage node.

[0022] In a possible implementation manner of the second aspect, the query assistance information includes a feature of the first data.

[0023] The third aspect of the present application provides a communication device, which has a function of implementing the method of the first aspect or any possible implementation manner of the first aspect, or has a function of implementing the method of the second aspect or any possible implementation manner of the second aspect. The function can be implemented by hardware, or can be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions, for example, a sending module, a processing module or a receiving module.

[0024] The fourth aspect of the present application provides a communication device, which includes a processor and an interface circuit, the interface circuit being used for receiving a signal from another communication device and transmitting the signal to the processor or sending a signal from the processor to the other communication device, and the processor being used for implementing a function of the method of the first aspect or any possible implementation manner of the first aspect, or implementing a function of the method of the second aspect or any possible implementation manner of the second aspect, through a logic circuit or executing code instructions.

[0025] The fifth aspect of the present application provides a computer readable storage medium storing one or more computer-executable instructions that, when executed by a processor, cause the processor to perform the method of the first aspect or any possible implementation of the first aspect, or the method of the second aspect or any possible implementation of the second aspect.

[0026] The sixth aspect of the present application provides a computer program product storing one or more computer-executable instructions that, when executed by a processor, cause the processor to perform the method of the first aspect or any possible implementation of the first aspect, or the method of the second aspect or any possible implementation of the second aspect.

[0027] The seventh aspect of the present application provides a chip system including a processor configured to support a communication apparatus to implement the functions involved in the first aspect or any possible implementation of the first aspect, or implement the functions involved in the second aspect or any possible implementation of the second aspect. In a possible design, the chip system can further include a memory configured to store necessary program instructions and data. The chip system can be composed of a chip, or include a chip and other discrete devices.

[0028] The technical effects brought by the second aspect to the seventh aspect or any possible implementation thereof can be referred to the technical effects brought by the first aspect or any possible implementation of the first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0029] FIG. 1 is an exemplary schematic diagram of a communication system according to an embodiment of the present application;

[0030] FIG. 2 is an exemplary schematic diagram of a data acquisition method according to an embodiment of the present application;

[0031] FIG. 3 is an exemplary flow diagram according to an embodiment of the present application;

[0032] FIG. 4 is an exemplary schematic diagram of a communication apparatus according to an embodiment of the present application;

[0033] FIG. 5 is another exemplary schematic diagram of a communication apparatus according to an embodiment of the present application;

[0034] FIG. 6 is a structural schematic diagram of a communication apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] The embodiments of the present application will be described below in conjunction with the accompanying drawings. The terms used in the embodiment part of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0036] Those skilled in the art can know that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0037] In the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the front and rear associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, which is only a way of distinguishing the objects with the same properties used in the description of the embodiments of the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, so that the process, method, system, product or equipment including a series of units does not have to be limited to those units, but can include other units not clearly listed or inherent to these processes, methods, products or equipment.

[0038] The embodiments of the present application provide a data acquisition method, which can enable the user of the data to conveniently and regularly acquire data for a machine learning model.

[0039] The method can be applied to a communication system.

[0040] The specific architecture of the communication system can have multiple cases.

[0041] FIG. 1 is a schematic diagram of an exemplary architecture of a communication system to which the embodiments of the present application are applied. As shown in FIG. 1, the communication system includes at least one radio access network device and at least one terminal, and further includes a storage node. The terminal is connected to the radio access network device in a wireless manner, and the radio access network device is connected to the core network in a wireless or wired manner. The core network device and the radio access network device can be independent and different physical devices, or the functions of the core network device and the logical functions of the radio access network device can be integrated on the same physical device, or a physical device can integrate part of the functions of the core network device and part of the functions of the radio access network device. The terminals and the terminals, and the radio access network devices and the radio access network devices can be connected to each other in a wired or wireless manner. FIG. 1 is only a schematic diagram, and the communication system can further include other network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in FIG. 1.

[0042] The radio access network device is an access device through which a terminal accesses a communication system in a wireless manner. The radio access network device can be a base station, an evolved NodeB (eNodeB), a transmission reception point (TRP), a next generation NodeB (gNB) in a 5th generation (5G) mobile communication system, a next generation NodeB in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. The radio access network device can also be a module or unit that completes part of the functions of a base station, for example, it can be a central unit (CU) or a distributed unit (DU). The CU here completes the functions of the radio resource control protocol and the packet data convergence protocol (PDCP) of the base station, and can also complete the function of the service data adaptation protocol (SDAP); the DU completes the functions of the radio link control layer and the medium access control (MAC) layer of the base station, and can also complete part of the physical layer or the entire physical layer. For specific descriptions of the above-mentioned protocol layers, reference can be made to the relevant technical specifications of the 3rd generation partnership project (3GPP). The radio access network device can be a macro base station, a micro base station or an indoor station, or a relay node or a donor node, etc. The embodiments of the present application do not limit the specific technologies and specific device forms adopted by the radio access network device. For ease of description, the following describes the base station as an example of the radio access network device.

[0043] A terminal is a device with wireless transceiving function, which can send signals to a base station or receive signals from a base station. A terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. A terminal can be widely applied to various scenarios, such as device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, automatic driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. A terminal can be a mobile phone, tablet computer, computer with wireless transceiving function, wearable device, vehicle, airplane, ship, robot, mechanical arm, smart home device, etc. Embodiments of the present application do not limit the specific technology and specific device form of the terminal.

[0044] In embodiments of the present application, the functions of the base station can also be performed by a module (such as a chip) in the base station, or by a control subsystem containing the functions of the base station. The control subsystem containing the functions of the base station herein can be a control center in the above-mentioned application scenarios such as smart power grid, industrial control, smart transportation, smart city, etc. The functions of the terminal can also be performed by a module (such as a chip or modem) in the terminal, or by a device containing the functions of the terminal.

[0045] In addition, in embodiments of the present application, the communication system can further include a first storage node, which can be connected with the terminal and the base station respectively and can provide storage function.

[0046] The specific type of the first storage node is not limited herein. Exemplarily, the first storage node can include one or more storage devices, and the types of different storage devices can be the same or different. Any storage device can be a storage server or a storage chip, and can be a read only memory (ROM), static storage device, dynamic storage device, random access memory (RAM), etc. The connection between the first storage node and the collection node can have various cases. In one example, the first storage node and the collection node can use over the top (OTT) mode for data transmission. OTT refers to providing various application services to users through the network connection provided by the operator, such as the Internet. In other examples, the first storage node and the collection node can also use other wireless communication modes.

[0047] The specific type of the communication system can be various. Illustratively, the communication system includes, but is not limited to, a narrow band-Internet of things (NB-IoT) system, a global system for mobile communications (GSM) system, an enhanced data rate for GSM evolution (EDGE) system, a wideband code division multiple access (WCDMA) system, a code division multiple access 2000 (CDMA2000) system, a time division-synchronization code division multiple access (TD-SCDMA) system, a long term evolution (LTE) system, a 5G mobile communication system or a 6G mobile communication system, etc.

[0048] The communication system of the embodiments of the present application can apply a machine learning model to implement a wireless communication related task.

[0049] The type and function of the machine learning model are not limited herein.

[0050] Illustratively, the type of the machine learning model can be a neural network such as a convolutional neural network (CNN), a long short-term memory (LSTM), or a recurrent neural network (RNN), a decision tree, or a linear regression model, or other machine learning models developed later. The use of the machine learning model can be various, for example, the machine learning model can be used for one or more wireless tasks such as wireless channel related time-frequency domain channel estimation, prediction, beam prediction, etc.

[0051] The communication system can involve one or more of the operations of training or inference of the machine learning model, etc. It can be seen that in the embodiments of the present application, the data in the communication system can be used for the training or inference of the machine learning model, etc. The specific use of the data is not limited herein.

[0052] In actual application process, the communication system can involve collection and use of data for inference and / or training process of a machine learning model, and therefore, the communication system can specifically include a collection node and a use node of the data.

[0053] The collection node is configured to collect the data. The data can be collected in various manners. For example, the data can be generated by the collection node, collected by the collection node through a webpage or other application, collected by the collection node through a sensor or other device, transmitted to the collection node by other devices (such as an external sensor or other electronic device for information interaction), or obtained by processing image data, voice data, text data, etc. by the collection node.

[0054] The collection node can be a device or a group of devices in the communication system, or a chip of a device in the communication system. The use node can be a device or a group of devices in the communication system, or a chip of a device in the communication system.

[0055] For example, in some examples, the collection node can be a terminal in the communication system, and the use node can be a base station in the communication system; and in other examples, the collection node can be a base station in the communication system, and the use node can be a terminal in the communication system. It can be seen that in actual use scenarios, the specific types of the collection node and the use node can be various based on the needs of the scenarios, which are not limited herein.

[0056] In addition, in the embodiments of the present application, a first storage node in the communication system can provide a storage function for storing the data.

[0057] The first storage node can be connected to the collection node and the use node respectively. The connection between the first storage node and the collection node can be in various manners.

[0058] In an example, the storage node and the collection node can perform data transmission in an OTT manner. In this example, the collection node as a third party outside the operator can build a transmission channel between the third-party collection node and the third-party storage node through the network connection provided by the operator, so as to realize efficient and convenient data transmission between the collection node and the storage node. When the storage node and the collection node perform data transmission in an OTT manner, the manner can be transparent to the 3rd generation partnership project (3GPP) standard, that is, the 3GPP standard does not need to support the data transmission; or the manner can be opaque to the 3GPP, that is, the 3GPP needs to provide a definition of signaling or protocol flow to support the data transmission; or the manner can be based on operation administration and maintenance (OAM) or core network (CN) to realize data transmission between the storage node and the collection node.

[0059] In other examples, the storage node and the collection node can also use other wireless communication manners. For example, the storage node is a storage device provided by the operator, for example, a cloud storage device provided by the operator, and the storage node and the collection node can perform data transmission through the network service provided by the operator.

[0060] The connection manner between the storage node and the usage node can also have various cases, which can be the same as or different from the connection manner between the storage node and the collection node, and is not limited herein.

[0061] Based on the above communication system, an embodiment of the present application provides a data acquisition method, which can include a data collection phase and a data acquisition phase. The following exemplary describes the processing phases involved in the embodiments of the present application.

[0062] I. Data collection phase

[0063] In the data collection phase, the collection node can collect first data and store the first data, for example, the first data can be stored by the first storage node in the storage node.

[0064] Specifically, in some embodiments, as shown in FIG. 2, the method includes steps 201-203.

[0065] Step 201: The collection node sends first data to the first storage node.

[0066] The first data can be part of or all of the data used for the machine learning model. The collection node can transmit the first data independently via communication or can transmit the first data together with other data collected by the collection node to the first storage node.

[0067] The first storage node can be included in the storage nodes of the communication system. In some examples, the first storage node can be one of the storage nodes, and in other examples, the number of storage nodes can be multiple, for example, distributed storage can be implemented by multiple storage nodes, and the first storage node can be one or more of the multiple storage nodes.

[0068] The specific content of the first data can be determined based on the actual application scenario requirements. For example, the first data can be used as training data for a machine learning model for beam prediction, and the first data can include information of beams received and / or transmitted by the collection node.

[0069] The collection node can collect the first data and transmit the first data to the first storage node based on the connection between the collection node and the first storage node after collecting the first data.

[0070] For example, the collection node can include a data collection device and a data communication device. The data collection device can include hardware such as sensors, or software such as web pages and applications. After the data collection device collects the first data, the data collection device can pass the first data to the data communication device, and then transmit the first data to the first storage node via the data communication device.

[0071] Based on different manufacturers of the data collection device and the data communication device, the configuration of the data transfer between the data collection device and the data communication device can be various.

[0072] (1) When the data collection device and the data communication device come from the same manufacturer, the manufacturer can offline pre-configure the data transfer mode between the data collection device and the data communication device, for example, based on the content, format and / or interface of the data transfer specified by the manufacturer's custom or specified communication standard, to pre-configure the data transfer mode between the data collection device and the data communication device.

[0073] (2) When the data collection device and the data communication device come from different manufacturers, different manufacturers can offline negotiate the configuration information of the data transfer, or relevant standards can specify the content, format and / or interface of the data transfer according to the wireless task associated with the machine learning model, so as to realize the data transfer between the data collection device and the data communication device.

[0074] In this way, after the data collection device completes data collection, the data collection device can deliver the collected first data to the data communication device according to the configuration information of data delivery in the collection node. Then, the data communication device can package and send the first data to the first storage node through a transmission protocol such as IP.

[0075] For example, the collection node can send the first data to the first storage node through OTT data transmission. In this way, the collection node and the first storage node can use the network connection provided by the operator to efficiently and conveniently implement data transmission of a large data volume.

[0076] In step 202, the first storage node stores the first data and generates storage indication information about the first data.

[0077] The storage indication information is used to indicate the storage of the first data in the first storage node.

[0078] In the embodiments of the present application, the first storage node can store the first data in various ways, and the specific content of the storage indication information can also have various cases.

[0079] In one example, the first storage node can store the first data based on the collection node. Specifically, in the first storage node, the data collected by a collection node can be stored in the same data set, in other words, the data in one data set comes from one collection node. In addition, one collection node can correspond to one or more data sets. When one collection node corresponds to one data set, in the subsequent data use process, the use node can obtain the data collected by the collection node by obtaining the corresponding data set. When one collection node corresponds to multiple data sets, the division of the multiple data sets corresponding to the collection node can be in various ways, for example, the multiple data sets corresponding to the collection node can be divided based on data type, data storage time, data theme, etc.

[0080] In this example, the first storage node can be connected with one or more collection nodes and store the data collected by the one or more collection nodes. In the storage process, in the first storage node, the data collected by different collection nodes is stored in different data sets, so as to facilitate data query according to the collection node of the required data of the use node in the subsequent data use process.

[0081] In this example, the first storage node can conveniently index the first data through the identifier of the data set containing the first data, and therefore, the storage indication information about the first data can include the identifier of the data set of the first data.

[0082] As can be seen, after the data collection node implements data collection and reports data to the first storage node in the example shown in FIG. 3, the first storage node can store the first data in the data set corresponding to the data collection node, and feed back the identifier of the data set as the storage indication information about the first data to the data collection node, so that the data collection node determines the identifier of the data set containing the first data.

[0083] In another example, the first storage node can store data according to the characteristics of the first data.

[0084] In this example, the first storage node can be connected with one or more data collection nodes to store the data collected by the one or more data collection nodes. In this example, when the number of data collection nodes is multiple, the data from multiple data collection nodes is fused and then stored in the first storage node. Specifically, after the data from multiple data collection nodes is fused, the data can be stored in the first storage node according to the characteristics of the data, so that it is convenient for a use node to request data meeting a specified characteristic in a subsequent use process.

[0085] In some embodiments, the characteristics of the first data can include one or more of the following information:

[0086] The data amount of the first data, the use of the first data, the collection condition of the first data, the function of the first data, the manufacturer of the first data, the type of the first data, the format of the first data, the precision of the first data, the distribution of the first data, and the source of the first data.

[0087] Exemplarily, the use of the first data can indicate that the first data is training data, inference data, or monitoring data. The collection condition of the first data can include indoor data / outdoor data, daytime data / nighttime data, etc. The function of the first data can indicate that the first data is reference data or anchor data, etc. The manufacturer of the first data can indicate that the first data is data of a specific manufacturer. The type of the first data can include one or more of text data, voice data, image data, audio data, video data, channel data, or signal data, etc. The precision of the first data can include integer type, floating point type, etc. The distribution of the first data can include one or more of Gaussian distribution, exponential distribution, or logarithmic distribution, etc. As can be seen, the characteristics of the first data can include attribute information of the first data and / or processing information of the first data. The attribute information of the first data can include type, format, and / or precision of the first data, etc. The processing information of the first data can be determined based on the processing manner of the first data. Exemplarily, the processing information of the first data can include the distribution of the first data.

[0088] In this example, in the first storage node, the data can be stored according to the characteristics of the data, and therefore, the division manner of the data set in the first storage node can be the characteristics of the data. That is, for the first data, the first data in the first storage node is stored based on the characteristics of the first data, and the storage indication information includes the characteristics of the first data.

[0089] For example, in the first storage node, different data sets are used to store different data types, and therefore, the storage indication information can include the data type of the first data, which can describe the state of the data set used to store the first data, so that the collection node determines that the data set in the first storage node that stores the first data is used to store the data of the data type of the first data.

[0090] As shown in the example of FIG. 3, after the collection node implements data collection and reports data to the first storage node, the first storage node can store the first data in the data set corresponding to the characteristics of the first data, and feed back the characteristics of the first data as the storage indication information about the first data to the collection node, so that the collection node determines that the data set containing the first data is used to store data conforming to the characteristics of the first data.

[0091] In step 203, the collection node receives the storage indication information about the first data from the first storage node.

[0092] After the first storage node stores the first data and generates the storage indication information about the first data, the first storage node can send the storage indication information about the first data to the collection node, so that the collection node receives the storage indication information and determines the storage status of the first data in the first storage node.

[0093] For example, if the storage indication information includes the identifier of the data set in the first storage node used to store the first data, the collection node can determine in which data set in the first storage node the first data is stored; and if the storage indication information includes the characteristics of the first data, the collection node can determine that the data set containing the first data in the first storage node is used to store data conforming to the characteristics of the first data.

[0094] In this way, through data transmission between the collection node and the first storage node, unified storage of the data collected by the collection node in the first storage node can be achieved, which facilitates subsequent data use.

[0095] II. Data acquisition phase

[0096] In the data acquisition phase, the use node can acquire the first data from the first storage node that stores the first data based on the indication of the collection node, so as to use the acquired first data in the machine learning model related to the wireless task.

[0097] Specifically, in some embodiments, as shown in FIG. 2, the method can include steps 205-208, and in addition, in some examples, before step 205, step 204 can also be included.

[0098] In step 204, the usage node sends a second acquisition request about the first data to the collection node.

[0099] The second acquisition request can carry information about the first data, for example, it can carry an identifier of the first data, or it can carry characteristic information of the first data, etc. After receiving the second acquisition request, the collection node can perform data matching according to the second acquisition request to determine the first data required by the usage node. For example, the first data can be all data collected by the collection node, or the first data can be data collected by the collection node that meets the specified characteristics.

[0100] In this example, the usage node can send a second acquisition request to the collection node to request to acquire the first data collected by the collection node, thereby triggering step 205 and other subsequent steps.

[0101] In other examples, in the data acquisition phase, step 205 and other subsequent steps can also be triggered in other ways. For example, the collection node can actively send query assistance information about the first data to the usage node (for example, periodically triggered or triggered based on specified instructions) to trigger the usage node to perform step 205 and subsequent steps.

[0102] In step 205, the usage node receives query assistance information about the first data from the collection node.

[0103] The first data is included in the data, and the query assistance information is used to query the first data.

[0104] In the embodiments of the present application, the collection node can send query assistance information about the first data to the usage node, so that the usage node can obtain the query assistance information from the collection node, thereby querying the first data.

[0105] In addition, in the embodiments of the present application, the usage node obtains the query assistance information from the collection node, which can also be considered as the usage node obtaining the query right to the first data from the collection node, so that the usage node can query the first data for use in the machine learning model.

[0106] In the embodiments of the present application, the collection node obtains the query assistance information according to the storage indication information. The specific content of the query assistance information can have multiple cases.

[0107] For example, the query auxiliary information can include one or more of the following information:

[0108] index information indicating a storage location of the first data, a feature of the first data.

[0109] The index information can include one or more of the following information: location information of the first storage node, storage location information of the first data on the first storage node.

[0110] The location information of the first storage node can include an address of the first storage node, for example, can include an Internet Protocol (IP) address and / or a media access control (MAC) address of the first storage node. The storage location information of the first data on the first storage node can be used to index the first data on the first storage node. The specific content of the storage location information can have various forms, for example, the storage location information can include an identifier of a data set in which the first data is stored. In addition, in some examples, when the first storage node stores data according to the feature of the data, the storage location information can also include the feature of the first data to indicate that the first data can be indexed in the first storage node according to the feature of the first data. For example, the feature of the first data contained in the storage location information can include one or more of the following features: data amount of the first data, purpose of the first data, acquisition condition of the first data, function of the first data, manufacturer of the first data, type of the first data, format of the first data, precision of the first data, distribution of the first data, source of the first data.

[0111] In addition, in some examples, for example, in the scenario that the first storage node can store data from multiple acquisition nodes, the first storage node can fuse data from multiple acquisition nodes, and then store data from multiple acquisition nodes according to the feature of the data, then the feature of the data can be used as an index of the data in the first storage node to realize data query. In this example, the query auxiliary information can include the feature of the first data, and the feature of the first data can be used as an index of the first data in the first storage node, so that the first storage node can query the location of the first data in the first storage node according to the feature of the first data.

[0112] Step 206, using the node to send a first acquisition request about the first data to a first storage node storing the first data according to the query auxiliary information.

[0113] The use node can use the query assistance information received from the collection node to query the first data from the first storage node storing the first data. The first acquisition request can carry part or all of the query assistance information. For example, in some examples, the query assistance information can include the address of the first storage node, the identifier of the data set including the first data in the first storage node, and one or more features of the first data. Then, the use node can send a first acquisition request to the address of the first storage node, where the first acquisition request carries the identifier of the data set including the first data in the first storage node and the one or more features of the first data, to instruct the first storage node to query the first data according to the identifier of the data set including the first data and the one or more features of the first data.

[0114] At step 207, the first storage node queries the first data according to the first acquisition request.

[0115] In the embodiments of the present application, there can be various ways for the first storage node to query the first data, which can be determined according to the storage manner of the first data in the first storage node. For example, in one example, one data set in the first storage node corresponds to one collection node, and the first acquisition request can include the identifier of the data set corresponding to the collection node. In this way, the first storage node can index the data set according to the identifier of the data set and obtain the first data in the data set. In another example, the first storage node classifies and stores data according to the features of the data, and the first acquisition request can carry the features of the first data, so that the first storage node indexes according to the features of the first data and obtains data matching the features of the first data as the first data.

[0116] At step 208, the use node receives the first data from the first storage node.

[0117] The use node and the first storage node can transmit the first data through OTT data transmission and the like, that is, the first storage node can send the first data to the use node through OTT data transmission and the like.

[0118] After receiving the first data, the use node can use the first data in the machine learning model for model training, inference, and / or monitoring, and the like.

[0119] In the example as shown in FIG. 3, after obtaining the storage indication information including the identification of the data set including the first data and / or the characteristics of the first data sent by the first storage node, the collection node can perform data matching according to the data request of the usage node, to determine the first data required by the usage node. For example, the first data can be all the data collected by the collection node, or the first data can be the data collected by the collection node that meets the specified characteristics. Then, the query assistance information can be fed back to the usage node, so that the usage node can send a data acquisition request to the first storage node according to the query assistance information, to query the first data from the first storage node and receive the first data from the first storage node, so as to apply the data to the machine learning model of the wireless task.

[0120] It can be seen that, in the embodiments of the present application, the user of the data for the machine learning model can obtain the first data collected by the collection node from the first storage node based on the query assistance information sent by the collection node, so that the user can conveniently and regularly implement the acquisition of the first data based on the indication of the collection node, to implement the training, inference and / or monitoring of the machine learning model in the wireless task and the like.

[0121] In addition, in some examples, the collection node and the usage node can interact with each other through the air interface and the like to obtain the acquisition request and the query assistance information, and OTT data transmission can be used to implement the transmission of the first data and the like between the first storage node and the collection node and the usage node, to implement the regular and efficient transmission of different data between different nodes.

[0122] The above describes the data acquisition method provided by the embodiments of the present application from multiple aspects, and the communication device provided by the embodiments of the present application is described below in combination with the drawings.

[0123] As shown in FIG. 4, the communication device 40 provided by the embodiments of the present application can be used to implement the function of the usage node in the above method embodiments, and can be a terminal or a base station, so as to achieve the beneficial effects of the above method embodiments.

[0124] The communication device 40 includes:

[0125] The receiving module 401 is configured to receive query assistance information about the first data from the collection node, the first data being included in the data for the machine learning model, the collection node being configured to collect data, and the query assistance information being configured to query the first data;

[0126] The sending module 402 is configured to send a first acquisition request about the first data to a first storage node storing the first data according to the query assistance information;

[0127] The receiving module 401 is further configured to receive the first data from the first storage node.

[0128] Optionally, the query assistance information comprises index information used for indicating the storage location of the first data.

[0129] Optionally, the index information comprises one or more of the following information:

[0130] the location information of the first storage node, and the storage location information of the first data on the first storage node.

[0131] Optionally, the query assistance information comprises a feature of the first data.

[0132] Optionally, the sending module 402 is further configured to send, to the collection node, a second acquisition request about the first data.

[0133] As shown in FIG. 5, the embodiment of the present application provides a communication apparatus 50, which can be used to implement the function of the collection node in the above-mentioned method embodiments, and can be a terminal or a base station, and thus can also achieve the beneficial effects possessed by the above-mentioned method embodiments.

[0134] The communication apparatus 50 comprises:

[0135] The sending module 501 is configured to send, to a usage node, query assistance information about first data, the first data being contained in data used for a machine learning model, the usage node being a node that uses the data, and the query assistance information being used for instructing the usage node to query the first data from a first storage node that stores the first data.

[0136] Optionally, the communication apparatus 50 further comprises a processing module 502 and a receiving module 503.

[0137] The sending module 501 is configured to send, to the first storage node, the first data.

[0138] The receiving module 503 is configured to receive, from the first storage node, storage indication information about the first data, the storage indication information being used for indicating the storage condition of the first data on the first storage node.

[0139] The processing module 502 is configured to obtain the query assistance information according to the storage indication information.

[0140] Optionally, the storage indication information is used for indicating the storage location of the first data.

[0141] Optionally, the storage indication information comprises a feature of the first data, and the first data in the first storage node is stored based on the feature of the first data.

[0142] Optionally, the sending module 501 is configured to send, to the first storage node, the first data through over-the-top (OTT) data transmission.

[0143] Optionally, the query assistance information comprises index information used for indicating the storage location of the first data.

[0144] Optionally, the index information comprises one or more of the following information:

[0145] the location information of the first storage node, the storage location information of the first data on the first storage node.

[0146] Optionally, the query assistance information comprises a feature of the first data.

[0147] As shown in FIG. 6, the communication apparatus 60 comprises a processor 601 and an interface circuit 602. The processor 601 and the interface circuit 602 are coupled with each other. It can be understood that the interface circuit 602 can be a transceiver or an input / output interface. Optionally, the communication apparatus 60 further comprises a memory 603, used for storing instructions executed by the processor 601 or storing input data required by the processor 601 for running instructions or storing data generated after the processor 601 runs instructions.

[0148] When the communication apparatus 60 is used for implementing any of the above method embodiments, the processor 601 is used for implementing the functions of one or more modules in the communication apparatus 40 or the communication apparatus 50, and the interface circuit 602 is used for implementing the functions of one or more modules in the receiving module 401, the sending module 402, the sending module 501 and the receiving module 503.

[0149] The communication apparatus is used for implementing the functions of the using node and / or the collecting node in the above method embodiments. The using node can be a terminal or a chip of a terminal, and the collecting node can be a base station or a module of a base station; or, the using node can be a terminal or a chip of a terminal, and the collecting node can be a base station or a module of a base station.

[0150] When the above communication apparatus is a chip applied to a terminal, the terminal chip implements the functions of the terminal in the above method embodiments. The terminal chip receives information from other modules (such as a radio frequency module or an antenna) in the terminal, and the information is sent by a base station to the terminal; or, the terminal chip sends information to other modules (such as a radio frequency module or an antenna) in the terminal, and the information is sent by the terminal to the base station.

[0151] When the communication device is a module applied to a base station, the base station module implements the functions of the base station in the method embodiments. The base station module receives information from other modules (such as a radio frequency module or an antenna) in the base station, and the information is sent by a terminal to the base station; or the base station module sends information to other modules (such as a radio frequency module or an antenna) in the base station, and the information is sent by the base station to the terminal. The base station module herein can be a baseband chip of the base station, or a DU or other module, and the DU herein can be a DU under an open radio access network (O-RAN) architecture.

[0152] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be 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. The general-purpose processor can be a microprocessor, or any conventional processor.

[0153] The method steps in the embodiments of the present application can be implemented in hardware, or in software instructions executable by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from the storage medium and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a base station or a terminal. The processor and the storage medium can also exist as discrete components in the base station or the terminal.

[0154] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, all or part of the processes or functions of the embodiments are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center and the like integrated with one or more available media. The available media can be a magnetic medium, for example, a floppy disk, a hard disk, a magnetic tape; or an optical medium, for example, a digital video disc; or a semiconductor medium, for example, a solid state disk. The computer readable storage medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile storage media.

[0155] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

Claims

1. A data acquisition method, characterized by, The communication system comprises a usage node of data for a machine learning model, a collection node of the data, and a storage node of the data, and the method comprises: The usage node receives query assistance information about first data from the collection node, the first data being contained in the data, the query assistance information being used to query the first data; The usage node sends a first acquisition request about the first data to a first storage node storing the first data according to the query assistance information, the first storage node being contained in the storage node; The usage node receives the first data from the first storage node.

2. The method of claim 1, wherein, The query assistance information comprises index information used to indicate a storage location of the first data.

3. The method of claim 2, wherein, The index information comprises one or more of the following information: Location information of the first storage node, storage location information of the first data on the first storage node.

4. The method according to any one of claims 1 to 3, characterized in that, The query assistance information comprises a feature of the first data.

5. The method according to any one of claims 1 to 4, characterized in that, Before the usage node receives query assistance information about first data from the collection node, the method further comprises: The usage node sends a second acquisition request about the first data to the collection node.

6. A data acquisition method characterized by, The communication system comprises a usage node of data for a machine learning model, a collection node of the data, and a storage node of the data, and the method comprises: The collection node sends query assistance information about first data to the usage node, the first data being contained in the data, the query assistance information being used to instruct the usage node to query the first data from a first storage node storing the first data.

7. The method of claim 6, wherein, Before the collection node sends query assistance information about first data to the usage node, the method further comprises: The collection node sends the first data to the first storage node; The collection node receives storage indication information about the first data from the first storage node, the storage indication information being used to indicate a storage status of the first data on the first storage node; The collection node obtains the query assistance information according to the storage indication information.

8. The method of claim 7, wherein, The storage indication information is used to indicate a storage location of the first data.

9. The method according to claim 6 or 7, characterized in that, The storage indication information comprises a feature of the first data, and the first data in the first storage node is stored based on the feature of the first data.

10. The method according to any one of claims 6-9, characterized in that, The collection node sends the first data to the first storage node, comprising: The collection node sends the first data to the first storage node through over-the-top (OTT) data transmission.

11. The method according to any one of claims 6-10, characterized in that, The query assistance information comprises index information used to indicate a storage location of the first data.

12. The method of claim 11, wherein, The index information comprises one or more of the following information: Location information of the first storage node, storage location information of the first data on the first storage node.

13. The method according to any one of claims 6-12, characterized in that, The query assistance information comprises a feature of the first data.

14. A communications device, characterized by Comprise: receive, from a collection node, query assistance information about first data, the first data being included in data for a machine learning model, the collection node being configured to collect the data, the query assistance information being used to query the first data; send, to a first storage node storing the first data, a first obtaining request about the first data according to the query assistance information; receive, from the first storage node, the first data.

15. The apparatus of claim 14, wherein, The query assistance information comprises index information used to indicate a storage location of the first data.

16. The apparatus of claim 14 or 15, wherein, The query assistance information comprises a feature of the first data.

17. A communications device, characterized by Comprise: send, to a usage node, query assistance information about first data, the first data being included in data for a machine learning model, the usage node being configured to use the data, the query assistance information being used to instruct the usage node to query the first data from a first storage node storing the first data.

18. The apparatus of claim 17, wherein, Further comprise a receiving module and a processing module; The sending module is configured to send the first data to the first storage node; The receiving module is configured to receive storage indication information about the first data from the first storage node, the storage indication information being used to indicate a storage status of the first data in the first storage node; The processing module is configured to obtain the query assistance information according to the storage indication information.

19. The apparatus of claim 17 or 18, wherein: The sending module is configured to send the first data to the first storage node through over-the-top (OTT) data transmission.

20. A communications device, characterized by comprise a module for performing the method of any one of claims 1 to 5, or a module for performing the method of any one of claims 6 to 13.

21. A communications device, characterized by comprise a processor configured to execute a program, so that the communication apparatus performs the method of any one of claims 1 to 5, or so that the communication apparatus performs the method of any one of claims 6 to 13.

22. The communication apparatus according to claim 21, wherein, Further comprise a memory storing a computer program or instructions.

23. The communication apparatus according to claim 21 or 22, wherein, The communication apparatus is a chip or a chip system.

24. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor, implement the method of any one of claims 1 to 5; or implement the method of any one of claims 6 to 13.

25. A computer program product comprising instructions, wherein: When the instructions are executed by the processor, implement the method of any one of claims 1 to 5; or implement the method of any one of claims 6 to 13.

Images