Communication method, apparatus and system

Abstract

A communication method, apparatus and system, which relate to the technical field of communications. The method comprises: determining a first quality indicator, which is a quality indicator used for instructing a second apparatus to perform data collection; and sending, to the second apparatus, information used for indicating the first quality indicator. A first apparatus can inform a second apparatus of a quality indicator of a required data set, such that the second apparatus can perform data collection on the basis of the quality indicator, thereby avoiding the situation in which the quality of data collected by the second apparatus does not meet the requirements of the first apparatus, and thus improving the overall data collection efficiency of the first apparatus and the second apparatus. In addition, the solution can also avoid the situation in which the quality of data reported by the second apparatus does not meet the requirements of the first apparatus, such that resources required for transmitting the data are saved on, and the power consumption of the first apparatus and the second apparatus can be reduced.

Description

Communication method, device and system

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on February 28, 2024, with application number 202410224846.7 and application name “Communication Methods, Devices and Systems”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and more particularly, to a communication method, device, and system. Background Art

[0003] In wireless networks, many communication functions can be implemented using artificial intelligence (AI) methods. The application of AI technology in wireless networks typically includes data collection, model training, model inference, and model monitoring. The entities that perform data collection and model training are called data collection nodes and model training nodes. However, during the data collection process, data collection nodes may collect a lot of data that is not needed by model training nodes, thereby reducing data collection efficiency.

[0004] Therefore, how to improve the efficiency of data collection is an urgent problem to be solved. Summary of the Invention

[0005] The present application provides a communication method, device and system that can improve the efficiency of data collection.

[0006] In a first aspect, a communication method is provided. The method can be performed by a first device, or by a component (e.g., a processor, circuit, chip, or chip system) in the first device, or by a logic module or software that implements all or part of the functions of the first device. Optionally, the first device includes a network management system, a radio intelligent unit (RIU), a centralized unit (CU), a non-real-time radio access network intelligent controller (RIC), or a near-real-time RIC.

[0007] The method includes: determining a first quality indicator, where the first quality indicator is a quality indicator for instructing a second device to collect data; and sending information indicating the first quality indicator to the second device.

[0008] Through the above embodiment, the first device can inform the second device of the quality indicator of the required data set, allowing the second device to collect data based on the quality indicator, thereby preventing the quality of the data collected by the second device from failing to meet the requirements of the first device, thereby improving the overall data collection efficiency of the first and second devices. In addition, the above solution can also prevent the quality of the data reported by the second device from failing to meet the requirements of the first device, thereby saving resources required for data transmission and reducing power consumption of the first and second devices.

[0009] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0010] Through the above embodiments, when the types of the first quality indicators include range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, or coefficient of dispersion, the first quality indicator can characterize the degree of dispersion of the data in the data set required by the first device. When the types of the first quality indicators include skewness coefficient or kurtosis coefficient, the first quality indicator can characterize the shape characteristics of the probability distribution of the data in the data set required by the first device. When the first quality indicator includes relative entropy or cross entropy, the first quality indicator can characterize the difference between the probability distribution of the data in the data set required by the first device and the target probability distribution. Therefore, the above scheme further indicates the statistical characteristics of the data to be collected and reported by the second device, further avoiding the data set collected or reported by the second device not meeting the quality indicators of the first device, thereby further improving the efficiency of data collection, saving the resources required for data transmission, and reducing the power consumption of the first device and the second device.

[0011] In some implementations, the method further includes: receiving a first data set from the second device, where the first data set satisfies the first quality indicator.

[0012] Through the above embodiment, the data set received by the first device from the second device is a data set that meets the quality index of the first device, avoiding the second device from performing secondary collection and reporting, thereby saving resources required for data transmission.

[0013] In some implementations, the method further includes: receiving first information from the second device, where the first information is used to indicate that the data set generation failed.

[0014] Through the above embodiment, the second device can indicate to the first device that data set generation has failed. This allows the first device to learn of the failure and take appropriate action. For example, the first device can instruct other data collection devices to perform data collection. In another example, the first device can lower the required data set specifications and indicate the lowered specifications to the second device, prompting the second device to re-collect data.

[0015] In some implementations, the method further includes: receiving second information from the second device, where the second information is used to indicate a failure cause value.

[0016] Through the above embodiment, the second device can indicate to the first device the reason why the data set failed. In this way, the first device can know the reason why the second device failed and take corresponding measures according to the reason.

[0017] In some implementations, the failure reason value includes: the generated data set does not meet the first quality indicator and / or the first quantity indicator, and the first quantity indicator is used to indicate the amount of data collected by the second device.

[0018] In some implementations, the method further includes: determining a second quality indicator when the second information is used to indicate that the generated data set does not meet the first quality indicator, and the second quality indicator is lower than the first quality indicator; and / or, determining a second quantity indicator when the second information is used to indicate that the generated data set does not meet the first quantity indicator, and the amount of data indicated by the second quantity indicator is lower than the amount of data indicated by the first quantity indicator.

[0019] In some implementations, the method further includes: receiving third information from the second device, where the third information is used to indicate a third quality indicator, and the third quality indicator is a quality indicator recommended or capable of being provided by the second device.

[0020] Through the above embodiment, the second device can feedback the data quality it can provide or recommend, thereby helping the first device to reasonably determine the quality index of the data and avoid the failure of data collection and reporting by the second device due to excessively high requirements.

[0021] In some implementations, determining the first quality indicator includes determining the first quality indicator based on the third quality indicator.

[0022] Through the above embodiment, the first device can reasonably determine the data quality index based on the data quality that it can provide or recommend as fed back by the second device, to avoid failure of data collection and reporting by the second device due to excessively high index.

[0023] In some implementations, the method further includes: sending fourth information to the second device, where the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator.

[0024] Through the above embodiment, the first device can query the quality indicators recommended or provided by the second device, thereby determining reasonable data quality indicators to avoid failure of data collection and reporting by the second device due to excessively high indicators.

[0025] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0026] Through the above embodiment, the first device can query the types of quality indicators it is concerned about, thereby determining reasonable data quality indicators to avoid failure of data collection and reporting by the second device due to excessively high indicators.

[0027] In a second aspect, a communication method is provided, which can be performed by a second device, or by a component in the second device (for example, a processor, circuit, chip, or chip system, etc.), or by a logic module or software that can implement all or part of the functions of the second device. Optionally, the second device includes a base station (BS), a CU, a distributed unit (DU), an open radio access network (O-RAN) centralized unit control plane (O-RAN central unit control plane, O-CU-CP), an open radio access network centralized unit user plane (O-RAN central unit user plane, O-CU-UP), an open radio access network distributed unit (O-RAN distributed unit, O-DU), an open network architecture evolved NodeB (O-RAN evolved NodeB, O-eNB), or a next generation NodeB (gNB).

[0028] The method includes: receiving first quality indicator information from a first device, where the first quality indicator is a quality indicator used to instruct a second device to collect data; and determining the first quality indicator according to the first quality indicator information.

[0029] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0030] In some implementations, the method further includes: sending a first data set to the first device, where the first data set meets the first quality indicator.

[0031] In some implementations, the method further includes: sending first information to the first device, where the first information is used to indicate that the data set generation failed.

[0032] In some implementations, the method further includes: sending second information to the first device, where the second information is used to indicate a failure cause value.

[0033] In some implementations, the failure reason value includes that the generated data set does not meet the first quality indicator and / or the first quantity indicator, where the first quantity indicator is used to indicate the amount of data collected.

[0034] In some implementations, the method further includes: sending third information to the first device, where the third information is used to indicate a third quality indicator, and the third quality indicator is a quality indicator recommended or capable of being provided by the second device.

[0035] In some implementations, the method further includes: receiving fourth information from the first device, where the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator.

[0036] In some implementations, sending the third information to the first device includes sending the third information to the first device in response to the fourth information.

[0037] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0038] In a third aspect, a communication device is provided, comprising a processing circuit (or processor) and an input / output interface (also referred to as an interface circuit), the input / output interface being used to input and / or output signals, the processing circuit being used to execute the first aspect and any possible method of the first aspect, or the processing circuit being used to execute the second aspect and any possible method of the second aspect.

[0039] In some implementations, the processing circuit is used to communicate with other devices through the interface circuit and execute the above-mentioned first aspect and any possible method of the first aspect, or execute the second aspect and any possible method of the second aspect.

[0040] In a fourth aspect, a communication device is provided, which may include a device or module for performing the functions of the communication device.

[0041] In some implementations, the communication device may include modules, units, or means corresponding to the methods / operations / steps / actions described in the first aspect and any possible implementation of the first aspect. The modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0042] In some implementations, the communication device includes a processing unit and a transceiver unit, the processing unit is used to determine a first quality indicator, which is a quality indicator used to instruct the second device to perform data collection; the transceiver unit is used to send information indicating the first quality indicator to the second device.

[0043] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0044] In some implementations, the transceiver unit is further configured to receive a first data set from the second device, where the first data set meets the first quality indicator.

[0045] In some implementations, the transceiver unit is further configured to receive first information from the second device, where the first information is configured to indicate that generation of the data set has failed.

[0046] In some implementations, the transceiver unit is further configured to receive second information from the second device, where the second information is configured to indicate a failure cause value.

[0047] In some implementations, the failure reason value includes: the generated data set does not meet the first quality indicator and / or the first quantity indicator, and the first quantity indicator is used to indicate the amount of data collected by the second device.

[0048] In some implementations, when the second information is used to indicate that the generated data set does not meet the first quality indicator, the processing unit is further used to determine a second quality indicator, which is lower than the first quality indicator; and / or, when the second information is used to indicate that the generated data set does not meet the first quantity indicator, the processing unit is further used to determine a second quantity indicator, and the amount of data indicated by the second quantity indicator is lower than the amount of data indicated by the first quantity indicator.

[0049] In some implementations, the transceiver unit is further configured to receive third information from the second device, where the third information is configured to indicate a third quality indicator, and the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

[0050] In some implementations, the processing unit is specifically configured to determine the first quality indicator based on the third quality indicator.

[0051] In some implementations, the transceiver unit is further configured to send fourth information to the second device, where the fourth information is configured to instruct the second device to provide a recommended or provideable quality indicator.

[0052] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0053] In some implementations, the communication device may include modules, units, or means corresponding to the methods / operations / steps / actions described in the second aspect and any possible implementation of the second aspect. The modules, units, or means may be hardware circuits, software, or a combination of hardware circuits and software.

[0054] In some implementations, the communication device includes a processing unit and a transceiver unit, the transceiver unit is used to receive information about a first quality indicator from a first device, the first quality indicator being a quality indicator used to instruct a second device to perform data collection; the processing unit is used to determine the first quality indicator based on the information about the first quality indicator.

[0055] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0056] In some implementations, the transceiver unit is further configured to send a first data set to the first device, where the first data set meets the first quality indicator.

[0057] In some implementations, the transceiver unit is further configured to send first information to the first device, where the first information is configured to indicate that generation of the data set has failed.

[0058] In some implementations, the transceiver unit is further configured to send second information to the first device, where the second information is configured to indicate a failure cause value.

[0059] In some implementations, the failure reason value includes that the generated data set does not meet the first quality indicator and / or the first quantity indicator, where the first quantity indicator is used to indicate the amount of data collected.

[0060] In some implementations, the transceiver unit is further configured to send third information to the first device, where the third information is configured to indicate a third quality indicator, where the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

[0061] In some implementations, the transceiver unit is further configured to receive fourth information from the first device, where the fourth information is configured to instruct the second device to provide a recommended or provideable quality indicator.

[0062] In some implementations, the transceiver unit is specifically configured to send the third information to the first device in response to the fourth information.

[0063] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0064] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored. When the computer program or the instruction is run on a computer, the first aspect and any possible method of the first aspect are executed, or the second aspect and any possible method of the second aspect are executed.

[0065] In the sixth aspect, a computer program product is provided, comprising a computer program or instructions, which, when run on a computer, causes the first aspect and any possible method of the first aspect to be executed (or implemented), or causes the second aspect and any possible method of the second aspect to be executed (or implemented).

[0066] In the seventh aspect, a communication device is provided, comprising a processor, for causing the device to execute any possible method of the first aspect through executing a computer program (or computer executable instructions) stored in a memory, and / or, through a logic circuit, or causing the device to execute any possible method of the second aspect.

[0067] In some implementations, the processor is configured to determine a first quality indicator, where the first quality indicator is a quality indicator for instructing the second device to collect data; and the processor is further configured to send information indicating the first quality indicator to the second device.

[0068] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0069] In some implementations, the processor is further configured to receive a first data set from the second device, where the first data set meets the first quality indicator.

[0070] In some implementations, the processor is further configured to receive first information from the second device, where the first information is configured to indicate that generation of the data set has failed.

[0071] In some implementations, the processor is further configured to receive second information from the second device, where the second information is configured to indicate a failure cause value.

[0072] In some implementations, the failure reason value includes: the generated data set does not meet the first quality indicator and / or the first quantity indicator, and the first quantity indicator is used to indicate the amount of data collected by the second device.

[0073] In some implementations, when the second information is used to indicate that the generated data set does not meet the first quality indicator, the processor is further used to determine a second quality indicator, which is lower than the first quality indicator; and / or, when the second information is used to indicate that the generated data set does not meet the first quantity indicator, the processor is further used to determine a second quantity indicator, and the amount of data indicated by the second quantity indicator is lower than the amount of data indicated by the first quantity indicator.

[0074] In some implementations, the processor is further configured to receive third information from the second device, where the third information is configured to indicate a third quality indicator, where the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

[0075] In some implementations, the processor is specifically configured to determine the first quality indicator based on the third quality indicator.

[0076] In some implementations, the processor is further configured to send fourth information to the second device, where the fourth information is configured to instruct the second device to provide a recommended or provideable quality indicator.

[0077] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0078] In some implementations, the processor is configured to receive information about a first quality indicator from a first device, where the first quality indicator is a quality indicator for instructing a second device to collect data; and the processor is further configured to determine the first quality indicator based on the information about the first quality indicator.

[0079] In some implementations, the type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0080] In some implementations, the processor is further configured to send a first data set to the first device, where the first data set meets the first quality indicator.

[0081] In some implementations, the processor is further configured to send first information to the first device, where the first information is configured to indicate that generation of the data set has failed.

[0082] In some implementations, the processor is further configured to send second information to the first device, where the second information is configured to indicate a failure reason value.

[0083] In some implementations, the failure reason value includes that the generated data set does not meet the first quality indicator and / or the first quantity indicator, where the first quantity indicator is used to indicate the amount of data collected.

[0084] In some implementations, the processor is further configured to send third information to the first device, where the third information is configured to indicate a third quality indicator, where the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

[0085] In some implementations, the processor is further configured to receive fourth information from the first device, where the fourth information is configured to instruct the second device to provide a recommended or provideable quality indicator.

[0086] In some implementations, the processor is specifically configured to send the third information to the first device in response to the fourth information.

[0087] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

[0088] In one possible implementation, the device further includes a memory. In one possible implementation, the processor and the memory are integrated together. In another possible implementation, the memory is located outside the communication device. The processor may include one or more.

[0089] In one possible implementation, the communication device further includes a communication interface, which is used for the communication device to communicate with other devices, such as sending or receiving data and / or signals. Exemplarily, the communication interface can be a transceiver, circuit, bus, module, or other type of communication interface.

[0090] In one implementation, the communication device of the third aspect, fourth aspect or seventh aspect may be a chip or a chip system.

[0091] In an eighth aspect, a chip system is provided, comprising one or more processors for calling a computer program or computer instruction in a memory so that the processor executes any one of the implementation methods of the above-mentioned first aspect, or so that the processor executes any one of the implementation methods of the above-mentioned second aspect.

[0092] In some implementations, the processor is coupled to the memory through an interface.

[0093] In the ninth aspect, a communication system is provided, comprising a first device and a second device, wherein the first device is used to execute the above-mentioned first aspect and any possible implementation method of the first aspect, and the second device is used to execute the above-mentioned second aspect and any possible implementation method of the second aspect.

[0094] The description of the advantageous effects of any of the second to ninth aspects etc. may refer to the description of the advantageous effects of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] FIG1 is a schematic block diagram of some communication scenarios.

[0096] FIG2 is a schematic block diagram of a communication system.

[0097] FIG3 is a schematic flow chart of a data acquisition method.

[0098] FIG4 is a schematic flowchart of a communication method provided in an embodiment of the present application in an implementation scenario.

[0099] FIG5 is a schematic flowchart of another communication method provided in an embodiment of the present application.

[0100] FIG6 is a schematic flowchart of another communication method provided in an embodiment of the present application.

[0101] FIG7 is a schematic flow chart of a communication method in another implementation scenario.

[0102] FIG8 is a schematic block diagram of a communication device according to an embodiment of the present application.

[0103] FIG9 is a schematic block diagram of another communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0104] The technical solution in this application will be described below with reference to the accompanying drawings.

[0105] This application will present various aspects, embodiments, or features in the context of systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that each system may include additional devices, components, modules, etc., and / or may not include all of the devices, components, modules, etc. discussed in conjunction with the figures. Furthermore, combinations of these aspects may also be used.

[0106] Additionally, in the embodiments of this application, words such as "exemplary" and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner.

[0107] The business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field will know that with the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0108] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically stated. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless otherwise specifically stated.

[0109] The first, second, etc. descriptions appearing in the embodiments of this application are only used for illustration and distinction of the description objects. There is no order, nor does it indicate a special limitation on the number in the embodiments of this application, and cannot constitute any limitation on the embodiments of this application.

[0110] It should be understood that in the various embodiments of the present application, the size of the serial number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0111] It should be understood that the term "and / or" in this document simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0112] The technical solutions of the embodiments of the present application can be applied to various communication systems, including but not limited to: Long Term Evolution (LTE) system, New Radio (NR) system and other fifth generation (5G) systems. th generation (5G) mobile communication systems, narrowband internet of things (NB-IoT) systems, enhanced machine-type communication (eMTC) systems, enhanced mobile broadband (eMBB) systems, ultra-reliable low latency communications (URLLC) systems, satellite communication systems, LTE-machine-to-machine (LTE-M) systems, or sixth generation (6 th generation, 6G) mobile communication systems and other systems that have evolved after 5G.

[0113] It should be noted that in the embodiments of this application, the term "communication" can also be described as "data transmission," "signal transmission," "information transmission," or "transmission." In the embodiments of this application, transmission can include sending or receiving. For example, transmission can be uplink transmission, such as a terminal device sending a signal to a network device; transmission can also be downlink transmission, such as a network device sending a signal to a terminal device.

[0114] In wireless networks, many communication functions can be implemented using AI methods. For example, AI models can be used to implement channel state information (CSI) feedback compression, thereby reducing the overhead of CSI-reference signal (CSI-RS) feedback. For another example, AI models can be used to perform spatial beam prediction, so that the measurement results of one beam can be used to predict the measurement results of other beams, reducing the number of beam measurements. For another example, AI models can be used to locate user equipment (UE), thereby improving the accuracy of position prediction.

[0115] Applying AI technology in wireless networks typically involves data collection, model training, model inference, and model monitoring. The entities responsible for data collection and model training are referred to as data collection nodes and model training nodes. For example, data collection nodes can be base stations (BSs), control units (CUs), or data units (DUs). For example, model training nodes can be network management systems (NMSs), base stations (BSs), control units (CUs), data units (DUs), or other access network devices. Model training nodes typically rely on data reported by data collection nodes for model training.

[0116] Figure 1 is a schematic block diagram of some communication scenarios. Figure 1 shows multiple examples of model training nodes and data collection nodes. It should be noted that Figure 1 is only an example, and model training nodes and data collection nodes are not limited to Figure 1, and other scenarios are also possible.

[0117] Referring to (a) in FIG1 , the model training node may be a network management unit and / or an RIU, and the data collection node may be a BS.

[0118] Network management (NM) can be used to manage wireless communication systems. NM can be referred to as network management equipment, network management equipment, network management functions, or management equipment for access network devices. For example, NM can include operations administration and maintenance (OAM). As wireless technology evolves, NM may also be referred to by other names.

[0119] In the embodiments of the present application, the apparatus for implementing the network management function may be a network management device, or a device capable of supporting the network management device in implementing the function, such as a chip system, which may be installed in the network management device. The chip system may be composed of a chip or may include a chip and other discrete components.

[0120] The RIU may be a network element or network function that undertakes intelligent functions of the wireless access network (such as model training and model inference). In the process of wireless technology evolution, the RIU may also have other names.

[0121] In the embodiments of the present application, the device for implementing the functions of the RIU may be the RIU, or a device capable of supporting the RIU in implementing the functions, such as a system-on-chip, which may be installed in the RIU. The system-on-chip may be composed of a chip or may include a chip and other discrete components.

[0122] A BS may be a device with wireless transceiver functions. For example, a BS may be a device used to connect a terminal device to a radio access network (RAN). A BS may also sometimes be referred to as an access network device or an access network node. It is understood that in systems using different wireless access technologies, the names of devices with BS functions may vary. In the embodiments of the present application, a BS includes but is not limited to various forms of macro base stations, micro base stations or indoor stations, pico base stations, small stations, balloon stations, relay stations, access points, and the like. A BS may include an evolved node B (eNB or eNodeB) in LTE, an access point (AP) in a wireless fidelity (WiFi) system, a wireless relay node, a wireless backhaul node, a transmission point (TP), or a transmission reception point (TRP), etc. It may also include a gNB or transmission point (TRP or TP) in a 5G system, one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, network nodes constituting a gNB or transmission point, such as a baseband unit (BBU) or a distributed unit (DU), and may also include a BS, server, or vehicle-mounted equipment in networks evolved after 5G, such as 6G. A BS may also be a module or unit that performs some of the functions of a base station, for example, a centralized unit (CU) or a DU. For example, a CU may be responsible for wireless high-layer protocol functions, and a DU may be responsible for wireless low-layer protocol functions.

[0123] In the embodiments of the present application, the device for implementing the functions of the BS may be the BS, or a device capable of supporting the BS in implementing the functions, such as a chip system, which may be installed in the BS. The chip system may be composed of a chip or may include a chip and other discrete devices.

[0124] In another possible scenario, multiple devices collaborate to assist the terminal in achieving wireless access, with different devices implementing parts of the BS's functionality. For example, the BS can be a CU, DU, CU-control plane (CP), CU-user plane (UP), or radio unit (RU). The CU and DU can be configured separately or included in the same network element, such as a BBU. The RU can be included in a radio frequency device or radio unit, such as a radio remote unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0125] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (O-RAN) system, CU may also be referred to as O-CU (open CU), DU may also be referred to as O-DU, CU-CP may also be referred to as O-CU-CP, CU-UP may also be referred to as O-CU-UP, and RU may also be referred to as O-RU. Any unit of the CU (or CU-CP, CU-UP), DU and RU in this application, or any unit of the O-CU (or O-CU-CP, O-CU-UP), O-DU and O-RU, may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. The embodiments of this application do not limit the specific technology and specific equipment form adopted by the BS.

[0126] (a) in FIG1 can be understood as follows: when the BS adopts a non-separated architecture, the model training node can be the network management and / or RIU, and the data collection node can be the BS.

[0127] Referring to (b) in FIG1 , the model training node may be a network management unit and / or an RIU, and the data collection node may be a CU.

[0128] Referring to (c) in FIG1 , the model training node may be the network management unit and / or the RIU, and the data collection node may be the DU.

[0129] Referring to (d) in FIG1 , the model training node may be a CU, and the data acquisition node may be a DU.

[0130] Figure 2 is a schematic block diagram of a communication system. In an O-RAN scenario, the communication system may include a non-real-time radio access network intelligent controller (Non-RT RIC), a near-real-time radio access network intelligent controller (Near-RT RIC), an O-CU-CP, an O-CU-UP, an O-DU, or an O-eNB. In some implementation scenarios, the O-eNB in ​​Figure 2 may be replaced with an O-gNB. In some implementation scenarios, the communication system in Figure 2 also includes an O-gNB (not shown).

[0131] Non-real-time RIC can be used to implement non-real-time intelligent management of RAN functions. Non-real-time RIC can be deployed on nodes with richer computing power than near-real-time RIC. The functions of non-real-time RIC include non-real-time (for example, the delay of the control loop is >1s) control and optimization of RAN network elements and resources, training and updating of AI / machine learning (ML) models, or policy-based guidance of applications or functions in near-real-time RIC. For example, non-real-time RIC can be in the service management and orchestration (SMO) framework of the management plane. In addition, a collection of physical infrastructure nodes that meet the O-RAN requirements can form a cloud computing platform (such as O-Cloud), which can host related O-RAN functions and support software components (such as operating systems, virtual machines, real-time containers, etc.), management and orchestration functions.

[0132] The near-real-time RIC can be used to implement near-real-time intelligent management of the RAN. Its functionality can include providing near-real-time (e.g., control loop latency >= 10ms and < 1s) intelligent control and coordination within the RAN to support network automation and optimization. For example, the near-real-time RIC enables near-real-time control and optimization of O-RAN modules and resources through data collection and related operations on the E2 interface.

[0133] For example, O-CU can be used to implement the 3rd Generation Partnership Project (3GPP). rdThe O-CU is a 3GPP standard that includes the radio resource control (RRC) layer, the packet data convergence protocol (PDCP) layer, the service data adaptation protocol (SDAP) layer, and other control functions. However, this application does not limit the specific functions of the O-CU, and the O-CU may have more or fewer functions.

[0134] For example, the O-CU-CP is similar to the CU-CP in the NR system and can be used to implement the functions of the RRC layer and the control plane functions of the PDCP layer. The O-CU-CP can be part of the O-CU. However, this application does not limit the specific functions of the O-CU-CP, and the O-CU-CP can also have more or fewer functions.

[0135] For example, the O-CU-UP is similar to the CU-UP in the NR system and can be used to implement the functions of the SDAP layer and the user plane functions of the PDCP layer. The O-CU-UP can be part of the O-CU. However, this application does not limit the specific functions of the O-CU-UP, and the O-CU-UP can also have more or fewer functions.

[0136] For example, the O-DU can be divided based on low-layer functions to implement the radio link control (RLC) layer, media access control (MAC) layer, and higher physical layer (Higher PHY) in the 3GPP standard. Among them, the higher physical layer functions may include one or more of the following: feedforward error correction (FEC) encoding / decoding, scrambling / descrambling, or modulation / demodulation. However, this application does not limit the specific functions of the O-DU, and the O-DU may have more or fewer functions.

[0137] The near-real-time RIC can communicate with the O-eNB, O-gNB, O-CU-CP, or O-CU-UP, respectively. The O-CU-CP can communicate with the O-DU, for example, via the F1-C interface; the O-CU-UP can communicate with the O-DU, for example, via the F1-U interface. Optionally, the non-real-time RIC can communicate with the near-real-time RIC, for example, via the A1 interface. Optionally, the non-real-time RIC can communicate with at least one of the O-eNB, O-gNB, O-CU-CP, or O-CU-UP.

[0138] Referring to (e) in Figure 1, the model training node can be a non-real-time RIC, and the data acquisition node can be at least one of O-CU-CP, O-CU-UP, O-DU, O-eNB, or O-gNB.

[0139] Referring to (f) in Figure 1, the model training node can be a near real-time RIC, and the data acquisition node can be at least one of O-CU-CP, O-CU-UP, O-DU, O-eNB, or O-gNB.

[0140] Referring to (g) in Figure 1 , the model training node can be a non-real-time RIC, and the data collection node can be at least one of an O-CU-CP, O-CU-UP, O-DU, O-eNB, or O-gNB. Unlike (e) in Figure 1 , the interaction between the model training node and the data collection node in (g) requires near-real-time RIC transit.

[0141] FIG3 is a schematic flow chart of a data collection method 300. The method 300 is provided as an example only and does not limit the present application. The method 300 is described below with reference to FIG3.

[0142] S310: The model training node determines the type and amount of data required for model training.

[0143] For example, the model training node can determine the type and amount of data required for model training based on the model training requirements. For example, for a model used for channel state information (CSI) feedback compression, the type of data required for training is the channel feature vector measured by the UE, and the amount of data required is 500 thousand (K).

[0144] S320: The model training node informs the data collection node of the required data type and data quantity.

[0145] The above S320 can also be understood as the model training node notifying the data collection node of data collection requirements, which include data type and data quantity.

[0146] S330: The data collection node performs data collection.

[0147] Data collection can include data collection by the data collection node itself, or the data collection node scheduling UEs to collect data. The data collection method can be random collection (for example, randomly selecting UEs for data collection) or collection based on certain criteria (for example, scheduling the UE with the most remaining battery power for data collection).

[0148] S340: The data collection node sends the collected data to the model training node.

[0149] S350, the model training node evaluates the quality of the data.

[0150] Data quality can refer to its statistical characteristics, such as variance and standard deviation. Data quality is correlated with model performance. For example, the more discrete (or diverse) the data, the better the model's generalization performance. Therefore, by evaluating data quality, we can determine whether the model trained using this data meets (or is considered to meet) the model's performance requirements.

[0151] S360: If the data quality does not meet the requirements, repeat S320 to S350.

[0152] That is to say, if the data quality does not meet the requirements, the model training node will continue to trigger the data collection node to collect and report data until data that meets the required data quality is collected.

[0153] S370: The model training node performs model training based on the collected data that meets the requirements.

[0154] In the above solution, data collection nodes may collect a lot of unnecessary data. For example, model training requires highly diverse data, while data collection nodes collect a large amount of data with similar values. Another example is model training requiring measurement data from cell-edge UEs, while data collection nodes collect a large amount of measurement data from cell-center UEs. Collecting and reporting this unnecessary data reduces data collection efficiency and wastes network resources. Furthermore, it increases power consumption of data collection and model training nodes, wasting resources needed to transmit information.

[0155] Therefore, how to improve the efficiency of data collection is an urgent problem to be solved.

[0156] FIG4 is a schematic flow chart of a communication method 400 provided in an embodiment of the present application in an implementation scenario. The method 400 can improve the efficiency of data collection. The method 400 is described below in conjunction with FIG4.

[0157] S410: The first device determines a first quality indicator. Optionally, S410 may be replaced by: the first device determines a first quality requirement.

[0158] Exemplarily, S410 can be executed by the first device, or by a component in the first device (e.g., a processor, chip, circuit, or chip system, etc.), or by a logic module or software that can implement all or part of the functions of the first device.

[0159] Exemplarily, the first device includes a network manager, an RIU, a CU, a non-real-time RIC, or a near-real-time RIC. This application does not limit the name of the first device, and the first device may also be called a model training node, a data demand node, or have other names.

[0160] The first quality indicator may be a quality indicator used to instruct the second device to collect data.

[0161] The first quality requirement may represent the quality of the dataset required by the first device. The dataset required by the first device may also be referred to as the dataset required for model training. The dataset may refer to a collection of data required for model training. For example, the dataset may include data required for model training, model testing, and model validation.

[0162] It is understandable that the first device expects the data set reported by the data acquisition node to meet the first quality requirement. This application does not limit the name of the first quality requirement, and the first quality requirement can also be called data quality, data set quality, quality requirement of the first device, quality requirement of model training, or other names.

[0163] Exemplarily, the second device includes a BS, a CU, a DU, an O-CU-CP, an O-CU-UP, an O-DU, an O-eNB, or a gNB. This application does not limit the name of the second device, and the second device may also be called a data acquisition node, a training auxiliary node, or have other names.

[0164] The first quality indicator may represent the statistical characteristics that the first device expects the data set reported by the second device to achieve. The first quality indicator may include one or more quality indicators. The quality indicator includes the type of quality indicator and the value of the quality indicator. For example, the type of quality indicator is the mean, and the value of the quality indicator is 3, then the quality indicator has a mean equal to 3. If the mean of a data set is equal to 3, then the data set reaches the quality indicator. For another example, the type of quality indicator is the maximum value of the mean, and the value of the quality indicator is 4, then the quality indicator has a maximum value of the mean of 4, or in other words, the mean is less than or equal to 4. If the mean of a data set is less than or equal to 4, then the data set reaches the quality indicator.

[0165] When a data set meets one or more quality indicators included in the first quality indicator, the data set can meet the first quality requirement.

[0166] In some implementations, the type of the first quality indicator includes at least one of the following: range, quartile deviation, mean deviation, variance, standard deviation, coefficient of range, coefficient of variation, coefficient of skewness, coefficient of kurtosis, relative entropy, or cross entropy.

[0167] It should be noted that the range can include at least one of the range itself, the maximum value of the range, or the minimum value of the range. For example, a range of 5 indicates that the range is equal to 5. For another example, a maximum value of 5 indicates that the range is less than or equal to 5. For another example, a minimum value of 5 indicates that the range is greater than or equal to 5. Similar to the range, the interquartile range can include at least one of the interquartile range, the maximum value of the interquartile range, or the minimum value of the interquartile range. The mean difference can include at least one of the mean difference, the maximum value of the mean difference, or the minimum value of the mean difference. The variance can include at least one of the variance itself, the maximum value of the variance, or the minimum value of the variance. The standard deviation can include at least one of the standard deviation itself, the maximum value of the standard deviation, or the minimum value of the standard deviation. The coefficient of variation can include at least one of the coefficient of variation itself, the maximum value of the coefficient of variation, or the minimum value of the coefficient of variation. The coefficient of variation can include at least one of the coefficient of variation itself, the maximum value of the coefficient of variation, or the minimum value of the coefficient of variation. The skewness coefficient may include at least one of the skewness coefficient itself, the maximum value of the skewness coefficient, or the minimum value of the skewness coefficient. The kurtosis coefficient may include at least one of the kurtosis coefficient itself, the maximum value of the kurtosis coefficient, or the minimum value of the kurtosis coefficient. The relative entropy may include at least one of the relative entropy itself, the maximum value of the relative entropy, or the minimum value of the relative entropy. The cross entropy may include at least one of the cross entropy itself, the maximum value of the cross entropy, or the minimum value of the cross entropy.

[0168] The range, interquartile range, mean deviation, variance, standard deviation, coefficient of variation, and coefficient of dispersion can characterize the degree of dispersion of the data in a dataset. The formulas for the above quality indicators, the meanings of the parameters in the formulas, and exemplary descriptions of the quality indicators are shown in Table 1.

[0169] Table 1

[0170] See Table 1, assuming that the data set is {x1,x2,…,x n}, where n is a positive integer. The quality indicators in Table 1 can characterize the data set {x1, x2,…, x n}'s degree of discreteness.

[0171] The skewness coefficient and kurtosis coefficient can characterize the shape of the probability distribution of data in a dataset. The formulas for the skewness coefficient and kurtosis coefficient, the meanings of the parameters in the formulas, and exemplary descriptions of quality indicators are shown in Table 2.

[0172] Table 2

[0173] See Table 2, assuming that the data set is {x1,x2,…,x n}, where n is a positive integer. The quality indicators in Table 2 can characterize the data set {x1, x2,…, x n}Probability distribution shape.

[0174] The relative entropy can be at least one of the relative entropy between the probability distribution p of the data set and the preset probability distribution q, the maximum relative entropy, or the minimum relative entropy. The preset probability distribution may also be called the target probability distribution, the given probability distribution, or have other names. The relative entropy may also be called the KL divergence (Kullback-Leibler divergence).

[0175] The cross entropy may be at least one of the cross entropy between the probability distribution p of the data set and the preset probability distribution q, the maximum cross entropy, or the minimum cross entropy. The preset probability distribution may also be referred to as a target probability distribution, a given probability distribution, or have other names.

[0176] It should be noted that the probability distribution p of the above-mentioned data set can represent the probability distribution of the data in the data set. This application does not limit the attributes of the data represented by the probability distribution of the data set. As an example, the probability distribution of the data set can be the distribution of data values ​​or the distribution of data sources. For example, the proportions of data from low-speed UE, medium-speed UE, and high-speed UE in the data set are 0.3, 0.3, and 0.4. As another example, the probability distribution of the data set can be the probability distribution of the input quantity, the probability distribution of the label, or the joint probability distribution of the input quantity and the label. It can be understood that for unsupervised learning, the data in the data set is the input quantity; for supervised learning, the data in the data set includes the input quantity and the label. In addition, this application does not limit the form of the probability distribution of the data set. For example, the probability distribution of the data set can be a discrete probability distribution or a continuous probability distribution. For another example, the probability distribution of the data set can be a unit probability distribution or a multivariate probability distribution.

[0177] The formulas and exemplary explanations of relative entropy and cross entropy in the case of unit probability distribution are shown in Table 3.

[0178] Table 3

[0179] See Table 3, assuming that the data set is {x1,x2,…,x n}, where y and y i can be the continuous and discrete possible values ​​of the random variable corresponding to the data set, respectively. Where n is a positive integer. The various quality indicators in Table 3 can characterize the difference between the data set probability distribution p and the target probability distribution q. Those skilled in the art will appreciate that for multivariate probability distributions, the formulas in Table 3 can be adaptively modified to multiple summations and multiple integrals.

[0180] Through the above embodiments, when the types of the first quality indicators include range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, or coefficient of dispersion, the first quality indicator can characterize the degree of dispersion of the data in the data set required by the first device. When the types of the first quality indicators include skewness coefficient or kurtosis coefficient, the first quality indicator can characterize the shape characteristics of the probability distribution of the data in the data set required by the first device. When the first quality indicator includes relative entropy or cross entropy, the first quality indicator can characterize the difference between the probability distribution of the data in the data set required by the first device and the target probability distribution. Therefore, the above scheme further indicates the statistical characteristics of the data to be collected and reported by the second device, further avoiding the data set collected or reported by the second device not meeting the quality indicators of the first device, thereby further improving the efficiency of data collection, saving the resources required for data transmission, and reducing the power consumption of the first device and the second device.

[0181] At step S420, the first device sends information indicating the first quality indicator to the second device. Correspondingly, the second device receives the information indicating the first quality indicator from the first device. Alternatively, step S420 may be replaced by: the first device sends information indicating the first quality requirement to the second device. Correspondingly, the second device receives the information indicating the first quality requirement from the first device.

[0182] The information used to indicate the first quality indicator can directly indicate the first quality indicator. For example, the first device can directly send the content of the first quality indicator to the second device. In this way, the second device can directly determine the first quality indicator based on the content of the above information. The information used to indicate the first quality indicator can also indirectly indicate the first quality indicator. For example, the first device can send indication information to the second device, and the indication information does not directly include the content of the first quality indicator. However, the indication information is associated with the first quality indicator, so that the second device can indirectly determine the first quality indicator based on the indication information. For example, the second device has pre-learned the mapping relationship between multiple quality indicators and multiple identifiers. In this way, the first device can only send indication information, and the indication information indicates one of the multiple identifiers. The second device can determine the quality indicator corresponding to the identifier (i.e., the first quality indicator) from the multiple quality indicators based on the identifier indicated in the indication information. Similarly, the information used to indicate the first quality requirement can directly or indirectly indicate the first quality requirement. Specific examples and information used to indicate the first quality indicator are not repeated here.

[0183] In some implementations, the first device may further indicate the type of data of the second device. As an example, the first device may send indication information, and the indication information is used to indicate type 1 and type 2. The indication information may be carried in the information of the first quality indicator (or the first quality requirement), or may be sent independently. The information of the first quality indicator (or the first quality requirement) may indicate the first quality indicator. The first quality indicator may be applicable to all or part of the data types. For example, the first quality indicator is applicable to type 1 and type 2, that is, multiple quality indicators in the first quality indicator may be applicable to all types of data. For another example, the first quality indicator includes quality indicator 1 and quality indicator 2, quality indicator 1 is applicable to type 1, and quality indicator 2 is applicable to type 2, that is, multiple quality indicators in the first quality indicator may be applicable to multiple types of data respectively. As another example, the types of data are predefined, for example, it is predefined that the second device needs to collect data of type 1 and type 2.

[0184] In some other implementations, the first quality indicator (or first quality requirement) information includes the data type and the first quality indicator. For example, the first quality indicator (or first quality requirement) information includes type 1 and quality indicator 1 corresponding to type 1; the first quality indicator (or first quality requirement) information also includes type 2 and quality indicator 2 corresponding to type 2.

[0185] Exemplarily, for the model of CSI feedback compression, the type of data required for training may be the channel matrix or channel eigenvector measured by the UE. For another example, for the model used for spatial beam prediction, the type of data required for training may be the reference signal received power (RSRP) of the CSI-RS and the RSRP of the synchronization signal / physical broadcast channel block (SSB) measured by the UE. For another example, for the model used for UE positioning, the type of data required for training may be the channel impulse response (CIR) and UE coordinates measured by the BS. For another example, for the model used for load balancing, the type of data required for training may be the RSRP of the cell measured by the UE.

[0186] Optionally, when the type of the first quality indicator includes relative entropy and / or cross entropy, the target probability distribution q is predefined. Optionally, when the type of the first quality indicator includes relative entropy and / or cross entropy, method 400 further includes: the first device sends information indicating the target probability distribution q to the second device. Optionally, the information indicating the target probability distribution q may be carried in the information indicating the first quality indicator (or first quality requirement). In other words, the information indicating the first quality indicator (or first quality requirement) may include information indicating the target probability distribution q. In other implementations, the information indicating the target probability distribution q may be carried in other information.

[0187] S430: The second device determines the first quality indicator according to the information of the first quality indicator. Optionally, S430 may be replaced by: the second device determines the first quality indicator according to the information of the first quality requirement.

[0188] The information of the first quality requirement can directly indicate the first quality indicator. For example, the first device can directly send the content of the first quality indicator to the second device. In this way, the second device can directly determine the first quality indicator based on the content of the information of the first quality requirement. The information of the first quality requirement can also indirectly indicate the first quality indicator. Exemplarily, the first device can send indication information to the second device, and the indication information does not directly contain the content of the first quality indicator. However, the indication information is associated with the first quality indicator, so that the second device can indirectly determine the first quality indicator based on the indication information. For example, the second device knows in advance the mapping relationship between multiple quality indicators and multiple identifiers. In this way, the first device can only send indication information, and the indication information indicates one of the multiple identifiers. The second device can determine at least one quality indicator (i.e., the first quality indicator) corresponding to the identifier among the multiple quality indicators based on the identifier indicated by the indication information.

[0189] The information about the first quality indicator can directly or indirectly indicate the first quality indicator. This is similar to the previous example of the information about the first quality requirement directly or indirectly indicating the first quality indicator, and will not be repeated here. The difference is that here, the information about the first quality "indicator" directly or indirectly indicates the first quality indicator.

[0190] Through the above embodiment, the first device can inform the second device of the quality indicator of the required data set, allowing the second device to collect data based on the quality indicator, thereby preventing the quality of the data collected by the second device from failing to meet the requirements of the first device, thereby improving the overall data collection efficiency of the first and second devices. In addition, the above solution can also prevent the quality of the data reported by the second device from failing to meet the requirements of the first device, thereby saving resources required for data transmission and reducing power consumption of the first and second devices.

[0191] Optionally, the method 400 further includes: (S432) the second device determines a data collection strategy according to the first quality requirement or the first quality indicator. It is understood that the first quality requirement may indicate the first quality indicator.

[0192] As an example, the first quality indicator includes a coefficient of dispersion not less than 2 (or, in other words, a minimum value of the coefficient of dispersion of 2). Assume that the first device also instructs the second device that the data reporting time for the required data set is 10 minutes and the data volume is 1000. Then, based on the first quality indicator, the data reporting time, and the data volume, the second device can determine the following data collection strategy: For the first 5 minutes, collect 200 data points per minute, for a total of 1000 data points. If the coefficient of dispersion of these 1000 data points is greater than or equal to 2, then stop collecting data. If the coefficient of dispersion of these 1000 data points is less than 2 and greater than or equal to 1, then collect 200 data points per minute for the next 5 minutes until 1000 data points are found that satisfy the coefficient of dispersion greater than or equal to 2. If the coefficient of dispersion of these 1000 data points is less than 1, then collect 400 data points per minute for the next 5 minutes until 1000 data points are found that satisfy the coefficient of dispersion greater than or equal to 2.

[0193] As another example, the first quality indicator includes a target probability distribution q = {P(RSRP>120dBm) = 0.8, P(RSRP≤120dBm) = 0.2}, which indicates that the probability that RSRP is greater than 120 decibel milliwatts (dBm) is 0.8, and the probability that RSRP is less than or equal to 120dBm is 0.2. The first quality indicator includes a relative entropy not greater than 0.1 (or, the maximum value of the relative entropy is 0.1). Assume that the first device also instructs the second device that the amount of data in the required data set is 1000. Then, the second device can determine the following data (or RSRP) collection strategy based on the first quality indicator and the amount of data: schedule near-point users (e.g., cell center users) and far-point users (e.g., cell edge users) for data collection in a ratio of 8:2. After collecting 1000 data, if the relative entropy meets the condition, then stop collecting; if the condition is not met, then continue collecting. If the probability that the current RSRP is greater than 120dBm is less than 0.8, then the data is scheduled for collection from nearby users; otherwise, the data is scheduled for collection from distant users until 1000 data points are found that meet the first quality indicator.

[0194] Through the above embodiment, the second device can formulate an appropriate data collection strategy according to the quality index to avoid collecting data that is not needed by the first device, thereby reducing the amount of data collected.

[0195] Optionally, the method 400 further includes: (S434) the second device performs data collection according to the data collection strategy.

[0196] For example, the second device may collect data based on the two examples in S432 to generate a data set. In some cases, the generated data set may meet the first quality requirement, or in other words, the indicators of the generated data set may meet the first quality indicator. It should be noted that even if the second device formulates a data collection strategy based on the first quality requirement or the first quality indicator and collects data according to the data collection strategy, the generated data set may still not meet the first quality requirement, or the indicators of the generated data set may not reach the first quality indicator.

[0197] In some implementations, the method 400 further includes: (S440) the first device receives the first data set from the second device. Correspondingly, the second device sends the first data set to the first device. Optionally, the method 400 further includes: the first device performs model training based on the first data set.

[0198] Optionally, the first data set meets the first quality requirement. Optionally, an indicator of the first data set reaches a first quality indicator. Optionally, the first data set meets the first quality indicator.

[0199] Optionally, method 400 further includes: (S436) the second device generates a data set according to the first quality requirement or the first quality indicator. Optionally, S440 includes, if the generated data set meets the first quality requirement (or the first quality indicator), the second device sending the first data set to the first device.

[0200] Through the above embodiment, the data set received by the first device from the second device is a data set that meets the quality index of the first device, avoiding the second device from performing secondary collection and reporting, thereby saving resources required for data transmission.

[0201] In some implementations, the method 400 further includes: (S450) the first device receives the first information from the second device. Correspondingly, the second device sends the first information to the first device.

[0202] Optionally, the first information is used to indicate that data set generation failed.

[0203] Optionally, method 400 further includes: (S436) the second device generates a data set according to the first quality requirement or the first quality indicator. Optionally, S450 includes, if the generated data set does not meet the first quality requirement (or the first quality indicator), the second device sending a first message to the first device.

[0204] It is understandable that even in the present application, the second device fails to generate a data set that meets the quality indicator the first time, but because the second device already knows the quality indicator of the first device, it can send an indication of the data set generation failure. In method 300 shown in Figure 3, the first device only discovers that the data set does not meet the quality indicator after the second device sends the data set that does not meet the quality indicator. In the embodiment of the present application, the second device does not need to send the data set that does not meet the quality indicator, but instead sends an indication. Therefore, compared to method 300, the embodiment of the present application can save transmission resources.

[0205] This application does not limit the name of the first information. For example, the first information may also be called a failure indication, a timeout indication, or have other names.

[0206] Through the above embodiment, the second device can indicate to the first device that data set generation has failed. In this way, the first device can be informed that the second device has failed to generate a data set that meets the first device's requirements and can take appropriate action. For example, the first device can instruct other data collection devices to collect data. For another example, the first device can lower the requirements of the required data set and instruct the second device to re-collect data.

[0207] In some other optional implementations, the method 400 further includes: if the first device does not receive the data set from the second device within a preset time, determining that the data set generation has failed.

[0208] In some implementations, the method 400 further includes: (S452) the first device receives second information from the second device. Correspondingly, the second device sends the second information to the first device.

[0209] Optionally, the second information is used to indicate a failure reason value.

[0210] This application does not limit the name of the second information. For example, the second information may also be called a failure cause indication or have other names.

[0211] Through the above embodiment, the second device can indicate to the first device the reason why the data set failed. In this way, the first device can know the reason why the second device failed and take corresponding measures according to the reason.

[0212] In some implementations, the failure reason value includes: the generated data set does not meet the first quality requirement and / or the first quantity requirement, where the first quantity requirement indicates the amount of data collected by the second device. In some implementations, the failure reason value includes: the generated data set does not meet the first quality indicator and / or the first quantity indicator, where the first quantity indicator indicates the amount of data collected by the second device. The first quantity requirement and the first quantity indicator may be interchangeable.

[0213] The generated dataset not meeting the first quality requirement or first quality indicator may also be referred to as "data quality failing to meet the requirement." For example, the generated dataset not meeting the first quality requirement (or first quality indicator) may include uneven user distribution. Thus, the first device may learn that the generated dataset of the second device fails to meet the quality indicator indicated by the first quality requirement due to uneven user distribution.

[0214] The first quantity requirement (or referred to as the first quantity indicator) can represent the amount of data required by the first device. It is understandable that the first device expects that the data set reported by the data acquisition node can meet the first quantity requirement. This application does not limit the name of the first quantity requirement. The first quantity requirement can also be referred to as data volume, data volume of the data set, quantity requirement of the first device, quantity requirement of model training, data volume requirement of model training, or other names. For example, the first quantity requirement can indicate that the data volume is 500K. In this way, when the data volume of the data set reaches 500K, the data set meets the first quantity requirement.

[0215] The generated dataset not meeting the first quantity requirement can also be referred to as "limited collection capacity." For example, the generated dataset not meeting the first quantity requirement may include limited air interface resources or hardware capabilities. In this way, the first device can learn that the second device is unable to schedule sufficient users for data collection due to limited air interface resources or hardware capabilities, and therefore the data volume of the generated dataset cannot meet the data volume indicated by the first quantity requirement.

[0216] In some implementations, the method 400 further includes: (S453) if the second information indicates that the generated data set does not meet the first quality requirement, the first device determining a second quality requirement, the second quality requirement indicating a second quality indicator, the second quality indicator being lower than the first quality indicator. S453 may be replaced by: if the second information indicates that the generated data set does not meet the first quality indicator, the first device determining a second quality indicator, the second quality indicator being lower than the first quality indicator.

[0217] The above S453 can be understood as indicating that, if the reason value is "data quality cannot be satisfied," the first device may lower the data quality indicator. The second quality requirement may indicate the quality of the data set required by the first device. Further descriptions of the second quality requirement are omitted here. For example, see the description of the first quality requirement in S410. The second quality indicator may indicate the statistical characteristics that the first device expects the data set reported by the second device to achieve. Further descriptions of the second quality indicator are omitted here. See the description of the first quality indicator in this application. For example, see the description of the first quality indicator in S410.

[0218] Optionally, the method 400 further includes: (S454) the first device sends information indicating a second quality requirement (or a second quality indicator) to the second device. Correspondingly, the second device receives the information indicating the second quality requirement (or the second quality indicator) from the first device.

[0219] In some implementations, the method 400 further includes: (S455) when the second information is used to indicate that the generated data set does not meet the first quantity requirement (or first quantity indicator), the first device determines a second quantity requirement (or second quantity indicator), and the amount of data indicated by the second quantity requirement (or second quantity indicator) is lower than the amount of data indicated by the first quantity requirement (or first quantity indicator).

[0220] The above S455 can be understood as that, when the reason value is "limited collection capability", the first device can reduce the data volume. The description of the second quantity requirement is not repeated here, and reference is made to the description of the first quantity requirement in this application, for example, S452.

[0221] Optionally, the method 400 further includes: (S456) the first device sends information indicating a second quantity requirement (or a second quantity indicator) to the second device. Correspondingly, the second device receives the second quantity requirement (or second quantity indicator) information from the first device.

[0222] It is understandable that after S454 and / or S456, the second device learns the updated quality indicator and / or the updated quantity indicator, and can thus continue to collect and report data based on the updated quality indicator and / or the updated quantity indicator.

[0223] Exemplarily, similar to S430 , the second device determines the second quality indicator according to the second quality requirement or the information of the second quality indicator.

[0224] Exemplarily, similar to S432, the second device determines a new data collection strategy based on the second quality indicator and / or the second quantity indicator. Similar to S434, the second device performs data collection according to the new data collection strategy. Similar to S436, the second device generates a new data set based on the collected data. If the data set meets the second quality indicator and / or the second quantity indicator, similar to S440, the second device sends the generated data set to the first device. Then, the first device can perform model training based on the data set. If the data set still does not meet the second quality indicator and / or the second quantity indicator, similar to S450, the second device sends information to the first device indicating that the data set generation failed.

[0225] For example, similar to S452, the second device sends information indicating a failure reason value to the second device. If the failure reason value indicates that data quality is unsatisfactory, then, similar to S453, the first device may further reduce the quality indicator and send the updated quality indicator to the second device. If the failure reason value indicates that collection capacity is limited, then, similar to S455, the first device may further reduce the quantity indicator and send the updated quantity indicator to the second device. Data collection and reporting will then continue until the second device is able to send a data set that meets the requirements.

[0226] FIG5 is a schematic flow chart of another communication method 500 provided in an embodiment of the present application. Method 500 can be combined with method 400. Method 500 is described below in conjunction with FIG5.

[0227] S540: The first device receives third information from the second device. Correspondingly, the second device sends the third information to the first device.

[0228] In some implementations, S520 may be executed before S410, but this application is not limited thereto, and S540 may also be executed at other times.

[0229] Optionally, the third information is used to indicate a third quality indicator. The third information may directly indicate the third quality indicator. For example, the second device may directly send the third information to the first device, and the third information includes the content of the third quality indicator. In this way, the first device can directly determine the third quality indicator based on the content of the above information. The third information may indirectly indicate the third quality indicator. For example, the second device may send the third information to the first device, and the third information includes indication information, and the indication information does not directly include the content of the third quality indicator. However, the indication information is associated with the third quality indicator, so that the first device can indirectly determine the third quality indicator based on the indication information. For example, the first device knows in advance the mapping relationship between multiple quality indicators and multiple identifiers. In this way, the second device may only send indication information, and the indication information indicates one of the multiple identifiers. The first device can determine the quality indicator corresponding to the identifier (i.e., the third quality indicator) from the multiple quality indicators based on the identifier indicated by the indication information.

[0230] In some implementations, the second device may further indicate the type of data of the first device. As an example, the second device may send indication information, the indication information being used to indicate type 1 and type 2. The indication information may be carried in the third information or sent independently. For example, the third quality indicator is applicable to type 1 and type 2, that is, multiple quality indicators in the third quality indicator may be applicable to all types of data. For another example, the third quality indicator includes quality indicator 1 and quality indicator 2, quality indicator 1 is applicable to type 1, and quality indicator 2 is applicable to type 2, that is, multiple quality indicators in the third quality indicator may be applicable to multiple types of data respectively. As another example, the type of data is predefined, for example, the third quality indicator reported by the first device is predefined to be for data of type 1 and type 2.

[0231] In some other implementations, the third information includes the data type and the third quality indicator. For example, the third information includes type 1 and quality indicator 1 corresponding to type 1; the third information also includes type 2 and quality indicator 2 corresponding to type 2.

[0232] This application does not limit the name of the third information. For example, the third information can also be called capability information, recommendation information or have other names.

[0233] Optionally, the third quality indicator may be a quality indicator recommended by the second device. Optionally, the third quality indicator may be a quality indicator that the second device can provide. The third quality indicator may be understood as a quality indicator that can be achieved by the data set generated by the second device.

[0234] Illustratively, the third quality indicator may include at least one of range, interquartile range, mean deviation, variance, standard deviation, range coefficient, dispersion coefficient, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

[0235] The range may include at least one of the range itself, the maximum value of the range, the minimum value of the range, the maximum value of the maximum value of the range (or the upper limit of the maximum value of the range, or the upper bound of the maximum value of the range), the minimum value of the maximum value of the range (or the lower limit of the maximum value of the range, or the lower bound of the maximum value of the range), the maximum value of the minimum value of the range (or the upper limit of the minimum value of the range, or the upper bound of the minimum value of the range), or the minimum value of the minimum value of the range (or the lower limit of the minimum value of the range, or the lower bound of the minimum value of the range). Exemplarily, the range may include at least one of the range itself, the range of values ​​of the range, the range of values ​​of the maximum value of the range, or the range of values ​​of the minimum value of the range. The range of values ​​of the range may include the maximum value of the maximum value of the range and / or the minimum value of the maximum value of the range. The range of values ​​of the range of values ​​of the range may include the maximum value of the maximum value of the range and / or the minimum value of the maximum value of the range. The range of values ​​of the range of values ​​of the range may include the maximum value of the maximum value of the range and / or the minimum value of the maximum value of the range. The range of values ​​of the range of values ​​of the range may include the maximum value of the minimum value of the range and / or the minimum value of the minimum value of the range.

[0236] For example, a range of 5 means that the range of the generated data set can reach 5.

[0237] For another example, the maximum value of the range is 5, which means that the maximum value of the range of the generated data set can reach 5; in other words, the range can be less than or equal to 5.

[0238] For another example, the minimum value of the range is 5, which means that the minimum value of the range of the generated data set can reach 5; in other words, the range can be greater than or equal to 5.

[0239] For another example, the maximum value of the maximum range is 5, which means that the maximum value of the maximum range of the generated data set can reach 5; in other words, the maximum value of the range can be less than or equal to 5; in other words, the maximum range does not exceed 5.

[0240] For another example, the minimum value of the maximum value of the range is 5, which means that the minimum value of the maximum value of the range of the generated data set can reach 5; in other words, the maximum value of the range can be greater than or equal to 5; in other words, the maximum range is not less than 5.

[0241] For another example, the maximum value of the minimum value of the range is 5, which means that the maximum value of the minimum value of the range of the generated data set can reach 5; in other words, the minimum value of the range can be less than or equal to 5; in other words, the minimum value of the range is not less than 5.

[0242] For example, the minimum value of the range is 5, which means that the minimum value of the range of the generated data set can reach 5; in other words, the minimum value of the range can be greater than or equal to 5; in other words, the minimum value of the range does not exceed 5.

[0243] It should be noted that indicators such as the interquartile range, mean deviation, variance, standard deviation, range coefficient, coefficient of dispersion, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy are similar to the range. These indicators include at least one of the indicator itself, the maximum value of the indicator, the minimum value of the indicator, the maximum value of the maximum value of the indicator, the minimum value of the maximum value of the indicator, the maximum value of the minimum value of the indicator, or the minimum value of the minimum value of the indicator. Examples of these indicators can refer to the above examples of the range and are not repeated here.

[0244] For other descriptions of the third quality indicator, please refer to the description of the first quality indicator in this application, for example, refer to the content of S410, and will not be repeated here.

[0245] Through the above embodiment, the second device can feedback the data quality it can provide or recommend, thereby helping the first device to reasonably determine the data quality index and avoid the failure of data collection and reporting by the second device due to the index being too high.

[0246] In some implementations, method 500 further includes: (S550) the first device determines the first quality indicator (or first quality requirement) based on the third quality indicator. In addition, in some implementations, S410 in method 400 includes: the first device determines the first quality indicator (or first quality requirement) based on the third quality indicator.

[0247] For example, the third quality indicator indicates that the minimum value of the variance is 1 and the maximum value of the variance is 10. The type of data corresponding to the third quality indicator is RSRP. In this way, the first quality indicator indicated by the first quality requirement determined by the first device may include: a minimum value of the variance is 5 and a maximum value of the variance is 8.

[0248] Optionally, the first device determines the first quality indicator (or first quality requirement) according to the model accuracy requirement and / or the sampling time requirement, and the third quality indicator.

[0249] Through the above embodiment, the first device can reasonably determine the data quality index based on the data quality that it can provide or recommend as fed back by the second device, to avoid failure of data collection and reporting by the second device due to excessively high index.

[0250] In some implementations, the method 500 further includes: (S510) the first device determines a target type of the quality indicator. For example, the target type of the quality indicator may include at least one of range, interquartile range, mean deviation, variance, standard deviation, coefficient of range, coefficient of dispersion, skewness, kurtosis, relative entropy, or cross entropy.

[0251] The present application does not limit the name of the target type of the quality indicator. For example, the target type of the quality indicator may also be called the type of quality indicator that the first device focuses on or have other names.

[0252] Optionally, method 500 further includes: (S512) the first device determines the type of data required by the model. The type of data required by the model may correspond to the target type of the quality indicator. For example, the channel matrix may correspond to the variance. For another example, the RSRP of the CSI-RS may correspond to the variance, standard deviation, and skewness coefficient.

[0253] In some implementations, the method 500 further includes: (S520) the first device sending fourth information to the second device. Correspondingly, the second device receives the fourth information from the first device.

[0254] Optionally, the fourth information is used to instruct the second apparatus to provide a recommended quality indicator. Optionally, the fourth information is used to instruct the second apparatus to provide a quality indicator that can be provided.

[0255] This application does not limit the name of the fourth information. For example, the third information may also be called capability query information, query information, quality query information or have other names.

[0256] Through the above embodiment, the first device can query the quality indicators recommended or provided by the second device, thereby determining reasonable data quality indicators to avoid failure of data collection and reporting by the second device due to excessively high indicators.

[0257] In some implementations, the first device may also indicate to the second device the type of data. As an example, the first device may send indication information indicating data type 1 and data type 2. This indication information may be included in the fourth information or sent separately. Thus, the fourth information may instruct the second device to provide recommended or available quality indicators for one or more data types. For example, the fourth information instructs the second device to provide recommended or available quality indicators for data type 1 and data type 2.

[0258] In some implementations, the fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or available quality indicator belonging to the target category. In other implementations, the information about the target category of the quality indicator may be predefined or carried in other information and sent to the second device.

[0259] Exemplarily, the target types of quality indicators include variance and skewness coefficient. The fourth information may be used to instruct the second apparatus to provide recommended or capable quality indicators of variance and skewness coefficient.

[0260] Through the above embodiment, the first device can query the types of quality indicators it is concerned about, thereby determining reasonable data quality indicators to avoid failure of data collection and reporting by the second device due to excessively high indicators.

[0261] Optionally, the fourth information also includes information about the time the data was reported. Optionally, the fourth information also includes information about the amount of data in the data set. For example, at least one of the following items of the fourth information includes: the type of data is the RSRP of the cell measured by the UE; the data set reporting time is 10 minutes; the amount of data is 10,000; and the target type of the quality indicator is the maximum variance. If all of the information in the above examples is included, this means that the first device queries the second device to collect 10,000 RSRPs within 10 minutes and what the maximum possible variance of these RSRPs is.

[0262] It should be noted that the information about the time when the data was reported can also be carried in other information. The information about the number of data in the data set can also be carried in other information.

[0263] Optionally, when the target type of the quality indicator includes cross entropy and / or relative entropy, the first device may send information indicating the target probability distribution q to the second device. The information indicating the target probability distribution q may be carried in the fourth information or in other information.

[0264] In some implementations, the method 500 further includes: (S530) the second device determines a third quality indicator.

[0265] In other words, the second device determines the data quality of the data set that can be provided or recommended. Exemplarily, the second device can estimate the range of data quality values ​​based on factors such as UE characteristics and wireless environment characteristics. For example, the second device can estimate the distribution of RSRP based on the number and location of UEs and the mean channel quality, thereby obtaining the range of RSRP variance (i.e., the maximum and minimum values ​​of the RSRP variance).

[0266] FIG6 is a schematic flow chart of another communication method 600 provided in an embodiment of the present application. Method 600 can be combined with method 400 and method 500. Method 600 is described below in conjunction with FIG6.

[0267] S610: The first device determines to perform model training.

[0268] The above S610 can be understood as the first device deciding to train a certain model. This application does not limit the situation for which the model training is targeted. For example, S610 includes: the first device determines to perform initial model training (or initial model training), that is, to train an untrained model based on a certain data set. For another example, S610 includes: the first device determines to perform model retraining, that is, to retrain the trained model based on a new data set. It should be noted that S610 is an optional step.

[0269] This application does not limit the timing of the first device executing S610. As an example, when a new model is deployed to the first device, the first device can execute S610, that is, determine to perform model training. For example, the first device can decide to retrain the model based on the data collected locally by the second device, thereby improving the performance of the model running locally on the second device. As an example, when the first device monitors that the performance of the current model has dropped to a certain level, the first device can execute S610. For example, the first device can decide to retrain the model based on the latest collected data, thereby improving the performance of the model.

[0270] S620: The first device obtains model training requirements.

[0271] Exemplarily, the requirements for model training may include at least one of the model training time, the accuracy of the model, or the application information of the model. The model training time may indicate the completion time or deadline of the model training. For example, a model training time of 10 minutes indicates that the model needs to be trained within 10 minutes. The accuracy of the model can be used to evaluate the practicality of the model. Exemplarily, the accuracy of the model may include at least one of the accuracy, precision, or recall of the model. The application information of the model may characterize the application environment of the model. For example, the application information of the model may indicate that the model will be applied to a cell with a high proportion of high-speed mobile users.

[0272] This application does not limit the way in which the first device obtains the demand for model training. For example, the first device can pre-configure the demand for model training. For another example, the first device is an RIU, and the first device can be configured with the demand for model training by the network manager. For another example, the second device can report the demand for model training to the first device; the first device can receive the demand for model training from the second device (for example, BS). For example, the second device can send some information to the first device; the first device can determine the demand for model training based on this information. That is, in the case where the second device does not directly send the demand for model training to the first device, the first device can deduce the demand for model training based on the information reported by the second device. It should be noted that S620 is an optional step.

[0273] S630: The first device determines the demand for a data set required for model training.

[0274] In some optional embodiments, the dataset requirements required for model training may include a first time requirement (or a first time indicator), a first category requirement (or a first category indicator), a first quantity requirement (or a first quantity indicator), and a first quality requirement (or a first quality indicator). It is understood that if the dataset requirements required for model training include a first quality requirement, S630 may include S410. Furthermore, S630 may include S550, where the first device determines the first quality requirement based on the quality indicator recommended or provided by the second device.

[0275] The first time requirement may indicate the time for acquiring the data set. For example, the first time requirement indicates that the first device needs to acquire the data set within 10 minutes.

[0276] The first type of requirement may indicate the type of data in the dataset. For example, for a model for CSI feedback compression, the type of data required for training may be the channel matrix or channel eigenvector measured by the UE. For another example, for a model for spatial beam prediction, the type of data required for training may be the RSRP of the CSI-RS and the RSRP of the SSB measured by the UE. For another example, for a model for UE positioning, the type of data required for training may be the CIR measured by the BS and the UE coordinates. For another example, for a model for load balancing, the type of data required for training may be the RSRP of the cell measured by the UE.

[0277] The first quantity requirement may be used to indicate the quantity of data in the data set. For example, the first quantity requirement indicates that the first device requires 500K data.

[0278] The description of the first quality requirement is omitted here for details. For example, please refer to the related description of S410 above.

[0279] In other optional embodiments, the dataset requirements for model training may include at least one of the time required to acquire the dataset, the type of data in the dataset, the quantity of data in the dataset, and the quality of the data in the dataset. In other words, the time requirement, type requirement, quantity requirement, or quality requirement may be used as a parameter in the dataset requirements for model training.

[0280] This application does not limit how the first device determines the data set required for model training. As an example, the first device can determine the data set required based on the model training requirements. For example, the first device pre-configures a table of correspondences between model accuracy and data quality. Then, given the model accuracy requirements, the first device can determine the corresponding data quality based on the table. For another example, the first device can determine the required data volume based on the model training time requirements and its own computing power.

[0281] S640: The first device sends information indicating a need for a data set required for model training to the second device.

[0282] The above S640 can be understood as the first device notifying the second device of the requirement for the dataset required for model training. This application does not limit the specific method by which the first device notifies the second device. As an example, the first device may directly send information about the requirement for the dataset required for model training to the second device, where the information about the requirement for the dataset required for model training includes the content of the requirement for the dataset required for model training. In this way, the second device can directly determine the requirement for the dataset required for model training based on the information content of the first device. As another example, the first device may send indication information to the second device, where the indication information does not directly include the content of the requirement for the dataset required for model training. However, the indication information is associated with the requirement for the dataset required for model training, so that the second device can indirectly determine the requirement for the dataset required for model training based on the indication information. For example, the second device may have pre-existing knowledge of the mapping relationship between multiple requirements for datasets required for model training and multiple identifiers. In this case, the first device may only send indication information indicating one of the multiple identifiers. The second device can then determine the requirement for the dataset required for model training corresponding to the identifier from among the multiple requirements for datasets required for model training based on the identifier indicated in the indication information.

[0283] In some optional embodiments, the information regarding the dataset requirements for model training may include information indicating a first time requirement, information indicating a first category requirement, information indicating a first quantity requirement, and information indicating a first quality requirement. It is understood that if the information regarding the dataset requirements for model training includes information indicating a first quality requirement, S640 may include S420.

[0284] The first time requirement information can indicate the time required to obtain the dataset. For example, if the first time requirement information indicates the value "10," it can mean that the first device needs to obtain the dataset within 10 minutes; in other words, the second device needs to report the dataset, or start reporting the dataset, within 10 minutes. In other implementations, the first time requirement information can be included in other information, that is, not included in the information indicating the dataset requirement for model training.

[0285] The information of the first type of requirements may indicate the type of data in the dataset. The information of the first type of requirements may directly or indirectly indicate the type of data in the dataset. As an example, the information of the first type of requirements may include the type of data in the dataset, for example, the information of the first type of requirements may include the channel matrix or channel eigenvector measured by the UE. As another example, the information of the first type of requirements may include indication information, and the indication information is used to indicate the type of data in the dataset. Exemplarily, the information of the first type of requirements may include a bitmap, and the bitmap may indicate the type of data in the dataset. For example, 7 bits are used to indicate the following 7 types of data in sequence: channel matrix, channel eigenvector, RSRP of CSI-RS, RSRP of SSB, CIR, UE coordinates, and RSRP of cell. For example, when each of the 7 bits has a value of 1, it indicates that the corresponding data type needs to be collected and reported; otherwise, collection and reporting are not required. In other implementations, the information of the first type of requirements may be carried in other information, that is, not carried in the information used to indicate the requirement for the dataset required for model training.

[0286] The information of the first quantity requirement may indicate the number of data in the data set. The information of the first quantity requirement may directly indicate the quantity through a numerical value. For example, if the information of the first quantity requirement indicates N, it means that the first device requires N data. The information of the first quantity requirement may indirectly indicate the quantity through a numerical value, where N may be a positive integer. For another example, if the information of the first quantity requirement indicates N, it means that the first device requires N*1000 data, where N may be a positive integer, or N may be a decimal that makes the amount of data an integer. Exemplarily, N may be an integer (for example, 3), one decimal place (for example, 1.1), two decimal places (for example, 2.12), or three decimal places (for example, 3.335). In other implementations, the information of the first quantity requirement may be carried in other information, that is, not carried in the information used to indicate the requirement for the data set required for model training.

[0287] The description of the information of the first quality requirement is omitted for clarity. For example, please refer to the related description of S420 above.

[0288] In other optional embodiments, the dataset requirement information required for model training may include at least one of information about the time the dataset was acquired, information about the type of data in the dataset, information about the quantity of data in the dataset, and information about the quality of the data in the dataset. In other words, the time requirement, type requirement, quantity requirement, or quality requirement may be used as a parameter in the dataset requirement information required for model training.

[0289] Optionally, after S640, some steps from S430 to S456 are performed. Optionally, before S630, some steps from S510 to S550 are performed.

[0290] It should be noted that, in this application, when a first device sends information to a second device, the first device may send the information directly to the second device, or the first device may send the information to the second device via forwarding of one or more devices. Similarly, when a second device sends information to a first device, the second device may send the information directly to the first device, or the second device may send the information to the first device via forwarding of one or more devices.

[0291] Among them, one or more devices responsible for forwarding can be called third devices.

[0292] Exemplarily, S640 may include: the first device sends information indicating the need for a data set required for model training to the third device; the third device sends information indicating the need for a data set required for model training to the second device. It should be noted that the information sent by the third device to the second device may be the same as or different from the information received by the third device from the first device. Exemplarily, the information received by the third device indicating the need for a data set required for model training includes information on the reporting time of the data set. For example, the information on the reporting time of the data set indicates 10 minutes, indicating that the data set needs to be reported within 10 minutes. The third device may send an indication to the second device, indicating that the reporting time of the data set is 10 minutes; the third device may also send an indication to the second device, indicating that the reporting time of the data set is 9 minutes. In this way, the 1-minute margin can be used by the third device for data processing.

[0293] Exemplarily, S520 may include: the first device sends fourth information to the third device; the third device sends fourth information to the second device. It should be noted that the information sent by the third device to the second device may be the same as or different from the information received by the third device from the first device. Exemplarily, the fourth information received by the third device may carry information on the reporting time of the data set. For example, the information on the reporting time of the data set indicates 10 minutes, indicating that the data set needs to be reported within 10 minutes. The third device may send an indication message to the second device, indicating that the reporting time of the data set is 10 minutes; the third device may also send an indication message to the second device, indicating that the reporting time of the data set is 9 minutes. In this way, the 1-minute margin can be used by the third device for data processing.

[0294] FIG7 is a schematic flow chart of a communication method 400 in another implementation scenario.

[0295] S420 may include: (S720) the first device sends information about the first quality indicator to the third device; (S720') the third device sends information about the first quality indicator to the second device.

[0296] S440 may include: (S740) the second device sends the first data set to the third device; (S740') the third device sends the first data set to the first device.

[0297] S450 may include: (S750) the second device sends the first information to the third device; (S750') the third device sends the first information to the first device.

[0298] S452 may include: (S752) the second device sends the second information to the third device; (S752') the third device sends the second information to the first device.

[0299] S454 may include: (S754) the first device sends information about the second quality indicator to the third device; (S754') the third device sends information about the second quality indicator to the second device.

[0300] S456 may include: (S756) the first device sends information about the second quantity indicator to the third device; (S756') the third device sends information about the second quantity indicator to the second device.

[0301] The drawings of method 500 and method 600 in the scenario where the third device forwards information are not drawn again.

[0302] Exemplarily, S540 may include: the second device sending information indicating the third quality indicator to the first device; and the third device sending information indicating the third quality indicator to the first device.

[0303] When the first device is a non-real-time RIC and the second device is at least one of an O-CU-CP, an O-CU-UP, an O-DU, or an O-eNB, the third device may be a near-real-time RIC. For example, see (g) in FIG1 .

[0304] The following is an introduction to the device embodiment corresponding to the method embodiment of the present application. The following is only a brief introduction to the device, and the specific implementation steps and details of the solution can be referred to the method embodiment above.

[0305] To implement the various functions of the method provided herein, the communication device may include hardware structures and / or software modules, and the aforementioned functions may be implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular one of the aforementioned functions is implemented in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0306] Figure 8 is a schematic block diagram of a communication device 800 according to an embodiment of the present application. The communication device 800 includes a processor 810 and a communication interface 820. Optionally, the processor 810 and the communication interface 820 may be interconnected via a bus. The communication device 800 may be a first device or a second device.

[0307] Optionally, the communication device 800 may further include a memory 840. The memory 840 includes, but is not limited to, random access memory (RAM), read-only memory (ROM), cache, erasable programmable read-only memory (EPROM), synchronous dynamic random access memory (SDRAM), hard disk drive (HDD), solid-state drive (SSD), or portable compact disc read-only memory (CD-ROM). The memory 840 is used to store relevant instructions and / or data. The memory 840 can be integrated with the processor 810 or set separately.

[0308] The processor 810 may be one or more central processing units (CPUs). In the case where the processor 810 is a CPU, the CPU may be a single-core CPU or a multi-core CPU. The processor 810 may be a signal processor, a chip, or other integrated circuit that can implement the method of the present application, or a portion of the circuitry used for processing functions in the aforementioned processor, chip, or integrated circuit. In addition, the communication interface 820 may also be an input / output interface, which is used for inputting or outputting signals or data, or may be an input / output circuit.

[0309] Exemplarily, communication device 800 is a first device, and processor 810 is configured to perform the following operations: determine a first quality requirement, where the first quality requirement is used to indicate a first quality indicator for data collection by a second device; and send information indicating the first quality requirement to the second device. Exemplarily, processor 810 is configured to perform the following operations: determine a first quality indicator, where the first quality indicator is a quality indicator for indicating data collection by the second device; and send information indicating the first quality indicator to the second device.

[0310] Exemplarily, communication device 800 is a second device, and processor 810 is configured to perform the following operations: receive information about a first quality requirement from a first device, where the first quality requirement information is used to indicate a first quality indicator for data collection by the second device; and determine the first quality indicator based on the first quality requirement information. Exemplarily, processor 810 is configured to perform the following operations: receive information about a first quality indicator from the first device, where the first quality indicator is a quality indicator for indicating data collection by the second device; and determine the first quality indicator based on the first quality indicator information.

[0311] The above content is only for exemplary description. The communication device 800 is responsible for executing the methods or steps related to the first device or the second device in the above method embodiments.

[0312] In one possible implementation, the communication interface 820 may be a transceiver. The transceiver may include a transmitter and a receiver, where the transmitter is configured to perform a transmission operation and the receiver is configured to perform a reception operation. For example, the processor 810 is configured to control the transceiver to receive and / or transmit signals.

[0313] In a possible implementation, the communication interface 820 may also be a communication circuit, a pin, an input / output interface, a bus, etc.

[0314] It should be noted that the communication device 800 may include a transmitter but not a receiver. Alternatively, the communication device 800 may include a receiver but not a transmitter. The specific implementation depends on whether the above solution executed by the communication device 800 includes a sending action and a receiving action.

[0315] The above description is merely exemplary. For details, please refer to the contents of the above method embodiments. The implementation of each operation in FIG8 may also correspond to the corresponding description of the method embodiments shown in FIG4 to FIG7.

[0316] For example, the communication device 800 may be used to implement the solutions shown in FIG. 4 to FIG. 7 .

[0317] Exemplarily, the communication device 800 is a first device, and the communication interface 820 may be configured to send information indicating the first quality requirement to a second device. Exemplarily, the communication interface 820 may be configured to send information indicating the first quality indicator to the second device.

[0318] Exemplarily, the communication device 800 is a second device, and the communication interface 820 may be used to receive information about a first quality requirement from a first device. Exemplarily, the communication interface 820 may be used to receive information about a first quality indicator from a first device.

[0319] For other implementations, please refer to the detailed description of the embodiments shown in Figures 4 to 7 above, which will not be repeated here. It should be understood that the specific process of each component performing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0320] Figure 9 is a schematic block diagram of another communication device 900 according to an embodiment of the present application. Communication device 900 can be the second device, the first device, or a chip or module in the second device or the first device, and is used to implement the methods involved in the embodiments shown in Figures 4 to 7. For details, please refer to the relevant descriptions in the above method embodiments.

[0321] The communication device 900 includes a transceiver unit 910 and a processing unit 920. The transceiver unit 910 and the processing unit 920 are described below by way of example.

[0322] The transceiver unit 910 may include a transmitting unit and a receiving unit. The transmitting unit is used to perform the transmitting action of the communication device, and the receiving unit is used to perform the receiving action of the communication device. For ease of description, the embodiments of the present application combine the transmitting unit and the receiving unit into a single transceiver unit. This is described here as a unified description and will not be repeated later. The transceiver unit 910 can implement corresponding communication functions. The transceiver unit 910 can also be referred to as a communication interface or communication module.

[0323] It should be noted that the communication device 900 may include a sending unit but not a receiving unit. Alternatively, the communication device 900 may include a receiving unit but not a sending unit. The specific implementation depends on whether the above solution executed by the communication device 900 includes a sending action and a receiving action.

[0324] Exemplarily, the transceiver unit 910 is configured to send information indicating the first quality requirement to the second device. Exemplarily, the transceiver unit 910 is configured to send information indicating the first quality indicator to the second device.

[0325] The processing unit 920 is used to execute the contents of the steps involving processing, coordination, etc. of the communication device 900. For example, the processing unit 920 is used to determine the first quality requirement, etc. For example, the processing unit 920 is used to determine the first quality indicator, etc.

[0326] Exemplarily, the transceiver unit 910 is configured to receive information about a first quality requirement from a first device. Exemplarily, the transceiver unit 910 is configured to receive information about a first quality indicator from a first device.

[0327] The processing unit 920 is configured to execute the contents of the steps involving processing and coordination of the communication device 900. Exemplarily, the processing unit 920 is configured to determine the first quality indicator, etc., based on the information about the first quality requirement. Exemplarily, the processing unit 920 is configured to determine the first quality indicator, etc., based on the information about the first quality indicator.

[0328] The above contents are merely exemplary descriptions, and the communication device 900 is responsible for executing the relevant methods or steps in the above method embodiments.

[0329] Optionally, the communication device 900 further includes a storage unit 930, which is configured to store a program or code for executing the aforementioned method. Alternatively, the storage unit 930 may be configured to store instructions and / or data, and the processing unit 920 may read the instructions and / or data in the storage unit 930 to enable the communication device 900 to implement the aforementioned method embodiments. For example, the communication device 900 may be configured to execute the solutions illustrated in Figures 4 to 7.

[0330] For example, the processing unit 920 may be configured to determine a first quality requirement, where the first quality requirement is used to indicate a first quality indicator for data collection by the second device; the transceiver unit 910 may be configured to send information indicating the first quality requirement to the second device. For example, the processing unit 920 may be configured to determine a first quality indicator, where the first quality indicator is a quality indicator for indicating data collection by the second device; the transceiver unit 910 may be configured to send information indicating the first quality indicator to the second device.

[0331] Exemplarily, the transceiver unit 910 may be configured to receive information about a first quality requirement from a first device, where the first quality requirement information is used to indicate a first quality indicator for data collection by a second device; and the processing unit 920 may be configured to determine the first quality indicator based on the first quality requirement information. Exemplarily, the transceiver unit 910 may be configured to receive information about a first quality indicator from a first device, where the first quality indicator is used to indicate a quality indicator for data collection by the second device; and the processing unit 920 may be configured to determine the first quality indicator based on the first quality indicator information.

[0332] For other implementations, please refer to the detailed description of the embodiments shown in Figures 4 to 7 above, which will not be repeated here. It should be understood that the specific process of each component performing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0333] When the communication device 800 in FIG8 is a chip, the communication interface 820 may be a transceiver, input / output circuit, or communication interface of the chip. The processor 810 may be a processor, microprocessor, or integrated circuit integrated on the chip. The sending operation of the first device or the second device in the above method embodiment can be understood as the output of the chip, and the receiving operation of the first device or the second device in the above method embodiment can be understood as the input of the chip.

[0334] When the communication device 900 in FIG9 is a chip, the transceiver unit 910 may be a transceiver, input / output circuit, or communication interface of the chip. The processing unit 920 may be a processor, microprocessor, or integrated circuit integrated on the chip. The sending operation of the first device or the second device in the above method embodiment can be understood as the output of the chip, and the receiving operation of the first device or the second device in the above method embodiment can be understood as the input of the chip.

[0335] The present application also provides a chip, including a processor, for calling and executing instructions stored in a memory, so that a communication device equipped with the chip executes the methods in the above examples.

[0336] The present application also provides another chip, comprising: an input interface, an output interface, and a processor, wherein the input interface, the output interface, and the processor are connected via an internal connection path, and the processor is configured to execute code in a memory. When the code is executed, the processor is configured to execute the methods in the above examples. Optionally, the chip also includes a memory, which is configured to store computer programs or code.

[0337] The present application also provides a processor for coupling with a memory, and for executing the methods and functions involving a communication device or an encoding device in any of the above embodiments.

[0338] In another embodiment of the present application, a computer program product including a computer program or instructions is provided. When the computer program product is run on a computer, the method of the aforementioned embodiment is implemented.

[0339] The present application also provides a computer program. When the computer program is executed in a computer, the method of the aforementioned embodiment is implemented.

[0340] In another embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a computer, the method described in the above embodiment is implemented.

[0341] The present application also provides a communication system, which includes a first device and a second device. The first device and the second device are respectively used to execute the methods executed by the first device and the second device in the above embodiments.

[0342] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0343] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0344] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0345] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0346] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0347] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0348] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: The method is applied to a first device, and includes: Determining a first quality indicator, where the first quality indicator is a quality indicator for instructing the second device to perform data collection; Information indicating the first quality indicator is sent.

2. The method according to claim 1, characterized in that The type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, range coefficient, dispersion coefficient, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

3. The method according to claim 1 or 2, characterized in that The method further comprises: A first data set is received, where the first data set satisfies the first quality indicator.

4. The method according to claim 1 or 2, characterized in that The method further comprises: First information is received, where the first information is used to indicate that data set generation failed.

5. The method according to claim 4, characterized in that The method further comprises: Second information is received, where the second information is used to indicate a failure cause value.

6. The method according to claim 5, characterized in that The failure reason value includes: the generated data set does not meet the first quality indicator and / or the first quantity indicator, and the first quantity indicator is used to indicate the amount of data collected by the second device.

7. The method according to claim 6, characterized in that The method further comprises: If the second information indicates that the generated data set does not meet the first quality indicator, determining a second quality indicator, the second quality indicator being lower than the first quality indicator; and / or, In a case where the second information is used to indicate that the generated data set does not meet the first quantity indicator, a second quantity indicator is determined, where the amount of data indicated by the second quantity indicator is lower than the amount of data indicated by the first quantity indicator.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: Third information is received, where the third information is used to indicate a third quality indicator, where the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

9. The method according to claim 8, characterized in that Determining the first quality indicator includes: The first quality indicator is determined according to the third quality indicator.

10. The method according to claim 8 or 9, characterized in that The method further comprises: Fourth information is sent, where the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator.

11. The method according to claim 10, characterized in that The fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

12. A communication method, characterized in that: The method is applied to a second device, and includes: receiving information of a first quality indicator, where the first quality indicator is a quality indicator for instructing the second device to collect data; The first quality indicator is determined according to information about the first quality indicator.

13. The method according to claim 12, characterized in that The type of the first quality indicator includes at least one of the following: range, interquartile range, mean deviation, variance, standard deviation, range coefficient, dispersion coefficient, skewness coefficient, kurtosis coefficient, relative entropy, or cross entropy.

14. The method according to claim 12 or 13, characterized in that The method further comprises: A first data set is sent, where the first data set meets the first quality indicator.

15. The method according to claim 12 or 13, characterized in that The method further comprises: First information is sent, where the first information is used to indicate that data set generation has failed.

16. The method according to claim 15, characterized in that The method further comprises: Second information is sent, where the second information is used to indicate a failure cause value.

17. The method according to claim 16, characterized in that The failure reason value includes that the generated data set does not meet the first quality indicator and / or the first quantity indicator, and the first quantity indicator is used to indicate the amount of data collected.

18. The method according to any one of claims 12 to 17, characterized in that The method further comprises: Sending third information, where the third information is used to indicate a third quality indicator, where the third quality indicator is a quality indicator recommended by or capable of being provided by the second device.

19. The method according to claim 18, characterized in that The method further comprises: Fourth information is received, where the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator.

20. The method according to claim 19, characterized in that The sending of the third information includes: In response to the fourth information, the third information is sent.

21. The method according to claim 19 or 20, characterized in that The fourth information includes information about a target category of the quality indicator, and the fourth information is used to instruct the second device to provide a recommended or provideable quality indicator belonging to the target category.

22. A communication device, characterized in that: The method comprises at least one module or at least one unit, wherein the at least one module or the at least one unit is used to execute the method according to any one of claims 1 to 11, or the method according to any one of claims 12 to 21.

23. A communication device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program or instructions, and the processor is used to, by executing the computer program or the instructions, cause the communication device to perform the method of any one of claims 1 to 11, or cause the communication device to perform the method of any one of claims 12 to 21.

24. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program or instructions, which, when executed on a computer, causes the method according to any one of claims 1 to 11 to be executed, or causes the method according to any one of claims 12 to 21 to be executed.

25. A computer program product, characterized in that The method comprises a computer program or an instruction. When the computer program or the instruction is executed, the method according to any one of claims 1 to 11 is implemented, or the method according to any one of claims 12 to 21 is implemented.

26. A communication system, characterized in that: The method comprises a first device and a second device, wherein the first device is used to execute the method according to any one of claims 1 to 11, and the second device is used to execute the method according to any one of claims 12 to 21.

27. A chip, characterized in that: include: A processor, wherein the processor is configured to cause the chip to execute the method according to any one of claims 1 to 11 by executing a computer program or instruction, or to cause the chip to execute the method according to any one of claims 12 to 21.

Images