A method, apparatus, and system for determining device information

Abstract

The application relates to a method, device and system for determining device information, and relates to the technical field of communication, and is used for realizing correct addressing of a training device by an inference device. The method comprises the following steps: an inference device sends a first request to a service discovery entity, the first request is used for requesting information of one or more training devices, and the first request comprises an algorithm type or an algorithm identifier of a first model requested by the inference device; the inference device receives the information of the one or more training devices from the service discovery entity; the information of the training device comprises capability information; and the inference device determines a first training device from the information of the one or more training devices according to a preset condition.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communication technology, and in particular to a method, apparatus and system for determining device information. BACKGROUND

[0002] Currently, a network data analysis function (NWDAF) integrates a training module and an inference module. The inference module includes training a model based on training data, and the inference module includes generating a data analysis result based on the trained model and inference data.

[0003] However, since the deployment cost of the training module is much higher than that of the inference module, in order to reduce the deployment cost, the training module and the inference module can be separated and deployed as a training device and an inference device respectively. The training device with high deployment cost is centrally deployed, and the inference device with low deployment cost is distributedly deployed. When the training device and the inference device are deployed separately, how the inference device addresses the training device is a technical problem to be solved urgently. SUMMARY

[0004] Embodiments of the present application provide a method, apparatus and system for determining device information, to realize correct addressing of the training device by the inference device.

[0005] To achieve the above object, the embodiments of the present application provide the following technical solutions:

[0006] In a first aspect, the embodiments of the present application provide a method for determining device information, comprising: an inference device sending a first request for requesting information of one or more training devices to a service discovery entity. The first request carries first information including an algorithm type of a first model requested by the inference device, or an identifier of the algorithm. The inference device receives the information of the one or more training devices from the service discovery entity. The information of the training device includes capability information. The inference device determines a first training device from the information of the one or more training devices according to a preset condition.

[0007] The embodiment of the present application provides a method for determining device information. When a training device and an inference device are separately deployed, due to different positions of the training device, different loads and different AI capabilities supported by the training device, the information of one or more training devices can be registered at a service discovery entity, so that the inference device can provide an algorithm type (Algorithm Type) or an algorithm identifier (Algorithm ID) of a first model requested by the inference device to the service discovery entity, so that the inference device can obtain the information of the one or more training devices from the service discovery entity, and the inference device can correctly address the one or more training devices. Subsequently, an auxiliary inference device can select a suitable first training device for model training. The model training process can be smooth, the model training speed can be fast, and the model generalization capability can be as strong as possible. In addition, the separate deployment of the training device and the inference device can also reduce the deployment cost.

[0008] In a possible implementation, the capability information provided by the embodiment of the present application includes any one or more of the following information: an algorithm type, an algorithm identifier, an algorithm performance evaluation index, an algorithm convergence time, an algorithm convergence speed, and an algorithm confidence. In this way, the inference device can select a first training device that meets the requirements of the inference device according to the capability information.

[0009] In a possible implementation, the first information further includes any one or more of the following information: location information of the inference device and address information of the inference device. In this way, the service discovery entity can select the information of one or more training devices that are relatively close to the inference device according to the location information of the inference device and the address information of the inference device.

[0010] In a possible implementation, the preset condition includes any one or more of the following: the algorithm convergence time corresponding to the algorithm of the first training device is the fastest among the algorithm convergence times corresponding to one or more algorithms of the one or more training devices; or, the algorithm performance evaluation index corresponding to one or more algorithms of the first training device is the highest among the algorithm performance evaluation indexes corresponding to one or more algorithms of the one or more training devices. The accuracy of the first training device in training the first model can be improved.

[0011] In a possible implementation, the information of the training device further includes any one of the following information: location information and load information, and the preset condition can further include: the load of the first training device is the lowest among the loads of the one or more training devices. By selecting the training device with the lowest load as the first training device, the processing burden of the first training device can be reduced.

[0012] In a possible implementation, the method provided by the embodiments of the present application further includes: the inference device sending a fourth request for requesting information of the first model to the first training device. The fourth request includes second information, and the second information includes any one or more of the following information corresponding to the first model: an algorithm type, an algorithm identifier, an algorithm performance requirement, a data type, and a data address. The inference device receives the information of the first model from the first training device, and the information of the first model includes any one or more of the following information: a model identifier, a model input, and a model parameter. In this way, the first training device can determine, according to the fourth request, that the first model required by the inference device meets the requirement.

[0013] In a possible implementation, the information of the first model further includes any one or more of the following information: a model output, model additional information, and a result of a model evaluation index. For example, the result of the model evaluation index can be an optimal value.

[0014] In a possible implementation, the inference device sends a third request for registering or updating the information of the first model to the service discovery entity. The third request includes any one or more of the following information: an analytics result identifier Analytics ID corresponding to the first model, and an effective area, a service area, or a coverage area of the analytics result corresponding to the first model. In this way, a network element that needs to use the data analytics result corresponding to the Analytics ID can query, according to the Analytics ID, the address of the inference device from the service discovery entity, and then request, according to the Analytics ID, the data analytics result from the inference device. The inference device further subscribes to online inference data from a network element that provides data for generating the data analytics result, determines the data analytics result based on the model and the obtained online inference data, and sends the data analytics result to a consumer network element.

[0015] In a possible implementation, the third request further includes location information of the inference device.

[0016] In a second aspect, the embodiments of the present application provide a method for determining device information, including: a service discovery entity receiving a first request for requesting information of one or more training devices from an inference device. The first request carries first information including an algorithm type or an algorithm identifier of a first model requested by the inference device. The service discovery entity determines information of the one or more training devices according to the first information, and the information of the training device includes capability information. The service discovery entity sends the information of the one or more training devices to the inference device.

[0017] In a possible implementation, the one or more training devices are training devices that support the algorithm type required by the inference device, and / or the one or more training devices are training devices that satisfy a preset requirement in distance from the inference device.

[0018] In a possible implementation, the load of the one or more training devices is lower than a preset load threshold.

[0019] In a possible implementation, the method provided by the embodiment of the present application further includes: the service discovery entity receives a second request from the first training device, the second request being used for requesting registration or updating of information of the first training device at the service discovery entity, the second request including any one or more of the following information of the first training device: address information, location information, load, capability information, the first training device being any one of the one or more training devices.

[0020] In a possible implementation, the method provided by the embodiment of the present application further includes: the service discovery entity sends a response message to the first training device, the response message being used for indicating successful registration or updating of the information of the first training device.

[0021] In a possible implementation, the capability information includes any one or more of the following information: algorithm type, algorithm identifier, algorithm performance evaluation index, convergence time of the algorithm, convergence speed of the algorithm, and algorithm confidence.

[0022] In a possible implementation, the method provided by the embodiment of the present application further includes: the service discovery entity receives a third request from the inference device, the third request being used for registering or updating information of the first model, the third request including any one or more of the following information: Analytics ID corresponding to the first model, and effective area, service area or coverage area of the analysis result corresponding to the first model.

[0023] In a possible implementation, the method provided by the embodiment of the present application further includes: the service discovery entity receives a third request from the inference device, the third request being used for registering or updating information of the first model, the third request including any one or more of the following information: Analytics ID corresponding to the first model, and effective area, service area or coverage area of the analysis result corresponding to the first model.

[0024] In a possible implementation, the first training device determines the information of the first model according to the second information, including: the first training device collects training data according to the data type and the data address. The first training device performs model training on the data according to an algorithm determined according to the algorithm identifier, to obtain the information of the first model, and the performance index of the first model satisfies the algorithm performance requirement.

[0025] In a possible implementation, the information of the first model further includes any one or more of the following information: model output, model additional information, result of model evaluation index.

[0026] In a possible implementation, the method provided by the embodiments of the present application further includes: the first training device sends a second request of the first training device to the service discovery entity, the second request being used for requesting registration or updating of information of the first training device at the service discovery entity, the second request including any one or more of the following information of the first training device: address information, location information, load, capability information, the first training device being any one of the one or more training devices.

[0027] In a possible implementation, the method provided by the embodiments of the present application further includes: the first training device receives a response message from the service discovery entity, the response message being used for indicating that the information of the first training device is successfully registered or updated.

[0028] In a fourth aspect, the embodiments of the present application provide a device for determining device information, which can implement the method in the first aspect or any possible implementation manner of the first aspect, and thus can achieve the beneficial effects of the first aspect or any possible implementation manner of the first aspect. The device for determining device information can be an inference device, or a device that can support the inference device to implement the method in the first aspect or any possible implementation manner of the first aspect, for example, a chip applied to the inference device. The device can implement the above method by software, hardware, or by hardware executing corresponding software.

[0029] In an example, the device for determining device information includes: a communication unit configured to send a first request to a service discovery entity, the first request being used for requesting information of one or more training devices. The first request carries first information, and the first information includes an algorithm type or an algorithm identifier of a first model requested by the device. The communication unit is configured to receive information of the one or more training devices from the service discovery entity, the information of the training device including capability information. A processing unit is configured to determine a first training device from the information of the one or more training devices according to a preset condition.

[0030] In a possible implementation, the capability information includes any one or more of the following information: algorithm type, algorithm identifier, algorithm performance evaluation index, algorithm convergence time, algorithm convergence speed, and algorithm confidence.

[0031] In a possible implementation, the first information further includes any one or more of the following information: location information of the device, and address information of the device.

[0032] In a possible implementation, the preset condition comprises any one or more of the following: the algorithm convergence time corresponding to the algorithm of the first training device is the fastest among the algorithm convergence time corresponding to one or more algorithms of the one or more training devices; or, the algorithm performance evaluation index corresponding to the one or more algorithms of the first training device is the highest among the algorithm performance evaluation index corresponding to one or more algorithms of the one or more training devices.

[0033] In a possible implementation, the information of the training device further comprises any one of the following: position information, load information, and the preset condition further comprises that the load of the first training device is the lowest among the loads of the one or more training devices.

[0034] In a possible implementation, the communication unit is further configured to send, to the first training device, a fourth request for requesting information of the first model. The fourth request comprises second information. The second information comprises any one or more of the following information corresponding to the first model: an algorithm type, an algorithm identifier, an algorithm performance requirement, a data type, and a data address. The communication unit is further configured to receive, from the first training device, the information of the first model, the information of the first model comprising any one or more of the following: a model identifier, a model input, and a model parameter.

[0035] In a possible implementation, the information of the first model further comprises any one or more of the following: a model output, model additional information, and a result of a model evaluation index.

[0036] In a possible implementation, the communication unit is configured to send, to the service discovery entity, a third request, the third request being used for registering or updating the information of the first model, and the third request comprising any one or more of the following: an analytics result identifier Analytics ID corresponding to the first model, and an effective area, a service area, or a coverage area of an analytics result corresponding to the first model.

[0037] In a possible implementation, the third request further comprises position information of the inference device.

[0038] In another example, the apparatus for determining device information can be an inference device or a chip in the inference device. When the apparatus for determining device information is the inference device, the communication unit can be a communication interface. The processing unit can be a processor. The apparatus for determining device information can further include a storage unit. The storage unit can be a memory. The storage unit can be configured to store computer program code including instructions. The processing unit can be configured to execute the instructions stored in the storage unit to enable the inference device to implement the method for determining device information described in the first aspect or any possible implementation of the first aspect. When the apparatus for determining device information is a chip in the inference device, the processing unit can be a processor and the communication unit can be collectively referred to as a communication interface. For example, the communication interface can be an input / output interface, a pin, or a circuit, etc. The processing unit can be configured to execute computer program code stored in the storage unit to enable the inference device to implement the method for determining device information described in the first aspect or any possible implementation of the first aspect. The storage unit can be a storage unit (e.g., a register, a cache, etc.) in the chip or a storage unit (e.g., a read-only memory, a random access memory, etc.) outside the chip in the management network element.

[0039] Optionally, the processor, the communication interface, and the memory are coupled with each other.

[0040] In a fifth aspect, an apparatus for determining device information is provided. The apparatus for determining device information can implement the method in the second aspect or any possible implementation of the second aspect, and thus can achieve the beneficial effects of the second aspect or any possible implementation of the second aspect. The apparatus for determining device information can be a service discovery entity or an apparatus that can support a service discovery entity to implement the method in the second aspect or any possible implementation of the second aspect, such as a chip applied in the service discovery entity. The apparatus can implement the above method by software, hardware, or by executing corresponding software by hardware.

[0041] In one example, the apparatus for determining device information includes a communication unit configured to receive a first request for requesting information of one or more training devices from an inference device. The first request carries first information, and the first information includes an algorithm type or an algorithm identifier of a first model requested by the inference device. A processing unit is configured to determine information of the one or more training devices according to the first information, and the information of the training device includes capability information. The communication unit is further configured to send the information of the one or more training devices to the inference device.

[0042] In a possible implementation, the one or more training devices are training devices of an algorithm type required by the inference device, and / or the one or more training devices are training devices that satisfy a preset requirement in terms of distance from the inference device.

[0043] In a possible implementation, the load of the one or more training devices is lower than a preset load threshold.

[0044] In a possible implementation, the communication unit is further configured to receive a second request from the first training device, the second request being used to request registration or update of information of the first training device at the apparatus, and the second request comprising any one or more of the following information of the first training device: address information, location information, load, and capability information, the first training device being any one of the one or more training devices.

[0045] In a possible implementation, the capability information comprises any one or more of the following information: algorithm type, algorithm identifier, algorithm performance evaluation index, convergence time of the algorithm, convergence speed of the algorithm, and algorithm confidence.

[0046] In a possible implementation, the communication unit is further configured to receive a third request from the inference device, the third request being used to register or update information of the first model, and the third request comprising any one or more of the following information: Analytics ID of an analysis result corresponding to the first model, and effective area, service area, or coverage area of the analysis result corresponding to the first model.

[0047] In another example, the embodiments of the present application provide a device for determining device information. The device for determining device information can be a service discovery entity or a chip in the service discovery entity. When the device for determining device information is the service discovery entity, the communication unit can be a communication interface. The processing unit can be a processor. The device for communication can further include a storage unit. The storage unit can be a memory. The storage unit is configured to store computer program code including instructions. The processing unit executes the instructions stored in the storage unit to enable the service discovery entity to implement the method for determining device information described in the second aspect or any possible implementation of the second aspect. When the device for determining device information is the chip in the service discovery entity, the processing unit can be a processor, and the communication unit can be collectively referred to as a communication interface. For example, the communication interface can be an input / output interface, a pin, or a circuit, etc. The processing unit executes the computer program code stored in the storage unit to enable the service discovery entity to implement the method for determining device information described in the second aspect or any possible implementation of the second aspect. The storage unit can be a storage unit (e.g., a register, a cache, etc.) in the chip or a storage unit (e.g., a read-only memory, a random access memory, etc.) outside the chip in the service discovery entity.

[0048] Optionally, the processor, the communication interface, and the memory are coupled with each other.

[0049] In a sixth aspect, the embodiments of the present application provide a device for determining device information. The device for determining device information can implement the method in the third aspect or any possible implementation of the third aspect, and thus can achieve the beneficial effects of the third aspect or any possible implementation of the third aspect. The device for communication can be the first training device or a device that can support the first training device to implement the method in the third aspect or any possible implementation of the third aspect, such as a chip applied in the first training device. The device can implement the above method by software, hardware, or by executing corresponding software by hardware.

[0050] In one example, the embodiments of the present application provide a device for determining device information, which includes: a communication unit configured to receive a fourth request including second information from an inference device. The second information includes any one or more of the following information corresponding to a first model: an algorithm type, an algorithm identifier, an algorithm performance requirement, a data type, and a data address. A processing unit is configured to determine information of the first model according to the second information. The information of the first model includes any one or more of the following information: a model identifier, a model input, and a model parameter. The communication unit is further configured to send the information of the first model to the inference device.

[0051] In a possible implementation, the first training device determines the information of the first model according to the second information, including: the first training device collects training data according to the data type and the data address. The first training device performs model training on the data according to the algorithm determined according to the algorithm identifier, to obtain the information of the first model, and the performance indicator of the first model meets the algorithm performance requirement.

[0052] In a possible implementation, the information of the first model further includes any one or more of the following information: model output, model additional information, and result of a model evaluation indicator.

[0053] In a possible implementation, the communication unit is further configured to send, to the service discovery entity, a second request of the first training device, the second request being used to request registration or update of information of the first training device at the service discovery entity, and the second request including any one or more of the following information of the first training device: address information, location information, load, and capability information, the first training device being any one of one or more training devices.

[0054] In a possible implementation, the communication unit is further configured to receive a response message from the service discovery entity, the response message being used to indicate that the information of the first training device is successfully registered or updated.

[0055] In a seventh aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program or instructions, when the computer program or instructions run on a computer, the computer program or instructions cause the computer to execute a method for determining device information as described in any possible implementation of the first aspect to the first aspect.

[0056] In an eighth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program or instructions, when the computer program or instructions run on a computer, the computer program or instructions cause the computer to execute a method for determining device information as described in any possible implementation of the second aspect to the second aspect.

[0057] In a ninth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program or instructions, when the computer program or instructions run on a computer, the computer program or instructions cause the computer to execute a method for determining device information as described in any possible implementation of the third aspect to the third aspect.

[0058] In a tenth aspect, an embodiment of the present application provides a computer program product including instructions, when the instructions run on a computer, the instructions cause the computer to execute a method for determining device information as described in the first aspect or various possible implementations of the first aspect.

[0059] In a eleventh aspect, the present application provides a computer program product comprising instructions which, when executed on a computer, cause the computer to carry out the method of determining device information according to the second aspect or any possible implementation of the second aspect.

[0060] In a twelfth aspect, the present application provides a computer program product comprising instructions which, when executed on a computer, cause the computer to carry out the method of determining device information according to the third aspect or any possible implementation of the third aspect.

[0061] In a thirteenth aspect, the embodiments of the present application provide a communication apparatus for implementing various methods in any of various possible designs of any of the first aspect to the third aspect. The communication apparatus can be the inference device, or a device comprising the inference device. Alternatively, the communication apparatus can be the service discovery entity, or a device comprising the service discovery entity. Alternatively, the communication apparatus can be the first training device, or a device comprising the first training device. The communication apparatus comprises modules, units, or means for implementing the corresponding methods, which can be implemented by hardware, by software, or by hardware and software. The hardware or software comprises one or more modules or units corresponding to the above functions.

[0062] In a fourteenth aspect, the embodiments of the present application provide a communication apparatus, comprising at least one processor and a communication interface. When the communication apparatus is running, the processor executes computer-executable instructions stored in the communication apparatus to cause the communication apparatus to perform any of the methods in any of various possible designs of any of the first aspect to the third aspect. For example, the communication apparatus can be the inference device, or a chip applied to the inference device. For example, the communication apparatus can be the service discovery entity, or a chip applied to the service discovery entity. For example, the communication apparatus can be the first training device, or a chip applied to the first training device.

[0063] It should be understood that the communication apparatus described in the above fourteenth aspect can further comprise a bus and a memory for storing codes and data. Optionally, the at least one processor, the communication interface, and the memory are coupled to each other.

[0064] In a fifteenth aspect, the embodiments of the present application provide a communication apparatus, comprising a processor and a storage medium. The storage medium stores instructions which, when executed by the processor, implement the method of determining device information according to the first aspect or any possible implementation of the first aspect.

[0065] In a sixteenth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor and a storage medium, the storage medium storing instructions, and the instructions being executed by the processor to implement a method for determining device information as described in the second aspect or various possible implementation manners of the second aspect.

[0066] In a seventeenth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor and a storage medium, the storage medium storing instructions, and the instructions being executed by the processor to implement a method for determining device information as described in the third aspect or various possible implementation manners of the third aspect.

[0067] In an eighteenth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor, the processor being coupled with a memory, and the memory being configured to store instructions or computer programs, and the instructions or computer programs being executed by the processor to implement a method for determining device information as described in the first aspect or various possible implementation manners of the first aspect.

[0068] In a nineteenth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor, a memory being coupled with the processor, and the memory being configured to store instructions or computer programs, and the instructions or computer programs being executed by the processor to implement a method for determining device information as described in the second aspect or various possible implementation manners of the second aspect.

[0069] In a twentieth aspect, an embodiment of the present application provides a communication apparatus, which comprises a processor, a memory being coupled with the processor, and the memory being configured to store instructions or computer programs, and the instructions or computer programs being executed by the processor to implement a method for determining device information as described in the third aspect or various possible implementation manners of the third aspect.

[0070] In a twenty-first aspect, an embodiment of the present application provides a communication apparatus, which comprises one or more modules for implementing the method in the first aspect, the second aspect, or the third aspect, and the one or more modules can correspond to each step in the method in the first aspect, the second aspect, or the third aspect.

[0071] In a twenty-second aspect, an embodiment of the present application provides a chip, which comprises a processor and a communication interface, the communication interface being coupled with the processor, and the processor being configured to execute computer programs or instructions to implement a method for determining device information as described in the first aspect or various possible implementation manners of the first aspect. The communication interface is configured to communicate with other modules outside the chip.

[0072] In a twenty-third aspect, an embodiment of the present application provides a chip, which comprises a processor and a communication interface, the communication interface and the processor are coupled, the processor is configured to run computer programs or instructions to implement the method for determining device information described in the second aspect or various possible implementation manners of the second aspect. The communication interface is configured to communicate with other modules outside the chip.

[0073] In a twenty-fourth aspect, an embodiment of the present application provides a chip, which comprises a processor and a communication interface, the communication interface and the processor are coupled, the processor is configured to run computer programs or instructions to implement the method for determining device information described in the third aspect or various possible implementation manners of the third aspect. The communication interface is configured to communicate with other modules outside the chip.

[0074] Specifically, the chip provided in the embodiments of the present application further comprises a memory configured to store computer programs or instructions.

[0075] In a twenty-fifth aspect, an embodiment of the present application provides a communication system, which comprises: the apparatus described in the fourth aspect or any possible implementation manner of the fourth aspect, the apparatus described in the fifth aspect or any possible implementation manner of the fifth aspect, and any apparatus provided above.

[0076] In an optional implementation manner, the communication system can further comprise: the apparatus described in the sixth aspect or any possible implementation manner of the sixth aspect.

[0077] Any apparatus, computer storage medium, computer program product, chip or communication system provided above are configured to execute the corresponding method provided above, and thus the beneficial effects thereof can refer to the beneficial effects of the corresponding solutions in the corresponding method provided above, which will not be described herein again. BRIEF DESCRIPTION OF DRAWINGS

[0078] Figure 1 FIG. 1 is a schematic diagram of an architecture of a data analysis network element according to an embodiment of the present application;

[0079] Figure 2 FIG. 2 is a schematic diagram of a scenario according to an embodiment of the present application;

[0080] Figure 3 FIG. 3 is a schematic diagram of a communication system architecture according to an embodiment of the present application;

[0081] Figure 4 FIG. 4 is a schematic diagram of a structure of a communication device according to an embodiment of the present application;

[0082] Figure 5 FIG. 5 is a schematic diagram of a flow of a method for determining device information according to an embodiment of the present application;

[0083] Figure 6Another flowchart of a method for determining device information according to an embodiment of the present application is shown in FIG. 2.

[0084] Figure 7 A structural diagram of an apparatus according to an embodiment of the present application is shown in FIG. 3.

[0085] Figure 8 Another structural diagram of an apparatus according to an embodiment of the present application is shown in FIG. 4.

[0086] Figure 9 A structural diagram of a chip according to an embodiment of the present application is shown in FIG. 5. DETAILED DESCRIPTION

[0087] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the same items or similar items with basically the same functions and roles are distinguished by using "first", "second", etc. For example, the first training device and the second training device are merely used to distinguish different training devices, and do not limit the order. Those skilled in the art can understand that "first", "second", etc. do not limit the number and execution order, and "first", "second", etc. also do not necessarily mean different.

[0088] It should be noted that in the present application, "exemplary" or "for example" is used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0089] In the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the association between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0090] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: code division multiple access (CDMA), time division multiple access (TDMA), frequency division multiple access (FDMA), orthogonal frequency division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), and other systems, etc. The term "system" can be replaced by "network". 3GPP in long term evolution (LTE) and various versions based on LTE evolution are new versions of UMTS using E-UTRA. The 5G communication system, new radio (NR), is a next-generation communication system under study. In addition, the communication system can also be applied to future-oriented communication technologies, and the technical solutions provided by the embodiments of the present application are applicable.

[0091] The system architecture and service scenarios described in the embodiments of the present application are used 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 by the embodiments of the present application. Those skilled in the art can know that, as the network architecture evolves and new service scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0092] As shown in Figure 1 The NWDAF black box integrates the following three components: data lake, inference module, and training module. The deployment form is single: data lake, inference module, and training module. Among them, the data lake includes data collection, data preprocessing, feature engineering, etc. The training module includes model training, model storage, etc. The inference module includes model deployment, model application, etc.

[0093] Generally, the deployment cost of the training module is much higher than that of the inference module, considering the following two aspects: on the one hand, the training module has higher requirements for hardware, such as requiring an artificial intelligence (AI) chip, a large cluster, and a graphics processing unit (GPU) computing capability, while the inference module can use a general central processing unit (CPU). On the other hand, the AI engineering design personnel requirement of the training module is higher, especially the professional field expert experience of feature selection and model training, while the design personnel of the inference module often only needs to obtain the specification of the model from the training module to realize local deployment of the model.

[0094] Therefore, small and medium-sized operators and large operators have their own appeals to the deployment form of the NWDAF network element based on the consideration of deployment cost. Small and medium-sized operators (such as small operators in some countries in Africa) hope to separate the AI model training function in the NWDAF network element from the existing Rel-16 architecture in Rel-17, and then realize AI model training through an AI public cloud (such as SoftCOM AI) as a training device. In the actual deployment process, the operator only deploys the inference device, then provides data to the training device to realize model training, and then the inference device obtains the model from the training device for local deployment, and finally generates data analysis results based on the model and the data of the network.

[0095] Similarly, large operators hope to distribute the NWDAF network element within the same operator in Rel-17, that is, to sink the inference function of the NWDAF to the city, and to centrally deploy the training device of the NWDAF network element. For example, for China Mobile, it can be considered to deploy a large-area NWDAF training device, and then to deploy a NWDAF network element with an inference module at the provincial level or the municipal level or the county level, so as to reduce the cost.

[0096] In Figure 1An application function (AF) network element can provide service data to the NWDAF network element, for example, an operation, administration, and maintenance (OAM) network element (may also be referred to as an operation administration maintenance network element), a 5G network element (a base station or a core network network element (for example, an access and mobility management function (AMF) network element / policy control function (PCF) network element / user plane function (UPF) network element / session management function (SMF) network element)) can provide network data to the NWDAF network element.

[0097] To this end, as Figure 2 indicated, Figure 2 A network architecture after separating the training device from the inference device is shown.

[0098] The main functions of the training device separated from the Rel-16 NWDAF network element are as follows: training data collection: obtaining training data from the inference device or a database network element (for example, an application function (AF) network element) or a 5G network element; model training: training an optimal model based on training data, an algorithm, and a training platform (such as a network artificial intelligence engine (NAIE) of Huawei, Tensorflow of Google, Caffe of Facebook, and MXnet of Amazon); model storage: serializing and storing the optimal model obtained by training, to prepare for a request for the model.

[0099] The inference device includes a data lake, a model application (Model application), and model output (Model deployment). The main functions of the inference device are as follows: model deployment: requesting and receiving a model from the training device, and installing and deploying the model locally; model input data collection: collecting model input data from a network network element, and obtaining model output based on the model; model application: determining a data analytics result (data Analytics) based on model output verification and data restoration, and preparing a corresponding analytic ID to prepare for a request for calling by a policy network element.

[0100] Optionally, a lightweight model training module can be reserved in the inference device for local training of the inference device. For example, compared with the heavyweight model training of the training device, the lightweight model in the inference device does not require massive distributed data storage, distributed data processing, and does not require a large number of AI experts to participate.

[0101] As shown in Figure 3 Figure 3 A communication system to which a method for determining device information provided by an embodiment of the present application is applied is shown. The communication system includes a service discovery entity 10 and an inference device 20 in communication with the service discovery entity 10.

[0102] In an optional implementation, the communication system can further include one or more training devices (for example, a training device 301, training devices 302 to 30n). Wherein n is an integer greater than or equal to 1. Wherein the inference device 20 and the one or more training devices can communicate with each other. Wherein the service discovery entity 10 supports the discovery, registration, and authentication functions of network functions or network services. In the 5GC, the service discovery entity 10 can be a network repository function (NRF) network element. For example, the service discovery entity 10 can be a domain name system (DNS) server.

[0103] It should be noted that the service discovery entity 10 is taken as an example of an NRF network element in the embodiments of the present application. In future networks, the service discovery entity 10 can be an NRF network element or have other names, which are not limited by the present application.

[0104] Wherein the training device has any one of the following functions: registering capability information to the service discovery entity 10, model training, model storage. Specifically, the training device is configured to register address information of the training device, load of the training device, and a list of algorithms supported by the training device (including type, identifier, additional information, evaluation index, algorithm convergence time, and confidence of each algorithm) to the service discovery entity 10. The training device receives a model request (including the specific algorithm identifier requirement of the model and the evaluation index requirement of the model) from the inference device 20, and feeds back a model (including the model identifier, the algorithm identifier used by the model, the model input, the model output, the parameter list, the result-optimal value of the model evaluation index, and the algorithm additional information) to the inference device 20.

[0105] For example, the inference device can be a module with model deployment and model application in a data analysis network element, or the inference device can be the data analysis network element. The data analysis network element can be a NWDAF network element.

[0106] ​The service discovery entity 10 has the following functions: receiving registration information of the training device from the training device, and saving.

[0107] Note: The training device can update the initial registration information, especially the common variables such as load of the training device, algorithm performance index, algorithm convergence time, etc. The training device receives a training device addressing request from the inference device to find the address of a suitable training device. In the request, the algorithm type to be used and the location information of the inference device can be carried. The training device sends a response of the training device addressing to the inference device, including the address of the training device, the algorithm identifier of the specific algorithm supported by the training device, the evaluation index of the algorithm, the algorithm convergence time, the confidence, etc.

[0108] The inference device is used for model deployment and model application. Specifically, first, the inference device determines the algorithm type of the algorithm corresponding to the model to be requested, and further addresses a suitable training device to the NRF. Then, the inference device requests the model from the training device. The request parameters and the corresponding parameters of the model are described in the training device and the following embodiments.

[0109] Figure 4 The hardware structure of the communication device provided by the embodiment of the application is shown. The hardware structure of the service discovery entity 10, the inference device 20, and the training device in the embodiment of the application can all refer to the hardware structure of the communication device shown in the embodiment of the application. Figure 4 The hardware structure of the communication device provided by the embodiment of the application is shown. The hardware structure of the service discovery entity 10, the inference device 20, and the training device in the embodiment of the application can all refer to the hardware structure of the communication device shown in the embodiment of the application. Figure 4 The communication device includes a processor 41, a communication line 44, and at least one communication interface (for example, the communication interface 43 is taken as an example for description in the embodiment).

[0110] The processor 41 can be a general central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the scheme of the application.

[0111] The communication line 44 can include a channel for transmitting information between the above-mentioned components.

[0112] The communication interface 43 uses any transceiver-like device, for communicating with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0113] Optionally, the communication device can further include a memory 42.

[0114] The memory 42 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may exist independently and be connected to the processor via communication line 44. The memory may also be integrated with the processor.

[0115] The memory 42 stores computer execution instructions for implementing the scheme of this application, and the processor 41 controls the execution. The processor 41 executes the computer execution instructions stored in the memory 42, thereby implementing the method for determining device information provided in the following embodiments of this application.

[0116] Optionally, the computer execution instructions in the embodiments of this application may also be referred to as application code, and the embodiments of this application do not specifically limit this.

[0117] In a specific implementation, as one example, processor 41 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 in the CPU.

[0118] In a specific implementation, as one example, the communication device may include multiple processors, for example... Figure 4 Processors 41 and 45 are included. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor here may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0119] In the embodiments of the present application, the specific structure of the execution subject of the method for determining device information is not particularly limited as long as the execution subject can communicate according to the method for determining device information by running the program in which the code of the method for determining device information is recorded. For example, the execution subject of the method for determining device information can be a service discovery entity or a communication device applied in the service discovery entity, such as a chip. The present application does not limit this. Alternatively, the execution subject of the method for determining device information can be an inference device or a communication device applied in the inference device, such as a chip. The present application does not limit this. Alternatively, the execution subject of the method for determining device information can be a training device or a communication device applied in the training device, such as a chip. The present application does not limit this. The following embodiments take the execution subject of the method for determining device information as an inference device, a service discovery entity, and a training device, respectively, as examples for description.

[0120] As shown in Figure 5 , in combination with the communication system shown in Figure 3 , the embodiments of the present application provide a method for determining device information, which comprises the following steps:

[0121] In step 501, the inference device sends a first request to the service discovery entity, so that the service discovery entity receives the first request from the inference device. The first request is used to request the information of one or more training devices, and the first request comprises the algorithm type (Algorithm Type) or the algorithm identifier (Algorithm ID) of the first model requested by the inference device.

[0122] It should be understood that the service discovery entity has a set of training devices. The set of training devices comprises at least one or more training devices. The process of the service discovery entity having the set of training devices can be referred to the description of the following embodiments, which will not be described here.

[0123] For example, the first request can be a service-based network function discovery request (Nnrf_NFDiscovery_Request). For example, the first request can further comprise any one or more of the following information: the location information of the inference device, the address information of the inference device, or the identifier of the inference device. Specifically, the first request carries demand information, which is used to request the information of one or more training devices meeting the requirements of the inference device. For example, the demand information comprises the algorithm type of the first model requested by the inference device, the algorithm identifier of the first model required by the inference device, the location information of the inference device, the address information of the inference device, or the identifier of the inference device.

[0124] The address information of the inference device is used to determine an IP address of the inference device, and the location information of the inference device is used to determine a location or a geographic region where the inference device is located. The address information of the inference device is used to index or look up the inference device, and the location information of the inference device is used to index a region covered by the inference device.

[0125] For example, the algorithm type of the first model requested by the inference device is any one or more of the following algorithm types: regression, clustering, association analysis, classification, recommendation. Each specific algorithm type can correspond to one or more algorithms. The algorithms corresponding to each specific algorithm type can be referred to in Table 1, which will not be described here.

[0126] Table 1: Algorithms corresponding to algorithm types and algorithm identifiers

[0127]

[0128]

[0129] Generally, the inference device is deployed by the operator. The operator determines to trigger a specific data analysis task, preliminarily determines the algorithm type required by the data analysis task (such as a classification task or a regression task), and then addresses the training device that meets the requirements through the inference device of the operator to train data.

[0130] In step 502, the service discovery entity determines the information of the one or more training devices according to the algorithm type of the first model requested by the inference device. The information of the training device includes capability information.

[0131] For example, the capability information includes any one or more of the following information corresponding to any algorithm: algorithm type, algorithm identifier, algorithm performance evaluation index, convergence time of the algorithm, convergence speed of the algorithm, and algorithm confidence.

[0132] For example, the convergence speed of the algorithm is represented by the number of iterations required to reach the same algorithm performance evaluation index requirement.

[0133] For example, the algorithm confidence represents the degree of approximation of the output result to the true result. For example, the algorithm performance evaluation index can include: mean squared error, accuracy, recall rate, and F-Score (harmonic average of accuracy and recall rate).

[0134] For example, as shown in Table 2, Table 2 shows the algorithm performance index measurement method corresponding to different algorithms.

[0135] Table 2: Algorithm performance index measurement method corresponding to different algorithms

[0136]

[0137]

[0138] Wherein, TP (True Positive, true positive) represents the positive tuple correctly classified by the classifier; TN (Trure Negative, true negative) represents the negative tuple correctly classified by the classifier; FP (False Positive, false positive) represents the negative tuple incorrectly labeled as a positive tuple; FN (False Negative, false negative) represents the positive tuple incorrectly labeled as a negative tuple. Wherein, the classifier evaluation metrics include accuracy (also known as: recognition rate), sensitivity or recall, specificity, precision F1 and FB.

[0139] Step 503, the service discovery entity sends the information of one or more training devices to the inference device, so that the inference device receives the information of one or more training devices from the service discovery entity, and the information of the training device includes: capability information.

[0140] Illustratively, the service discovery entity can send the first response to the inference device. The first response includes: the information of one or more training devices. For example, the first response can be: service network function discovery request response (Nnrf_NFDiscovery_Request response).

[0141] Illustratively, the information of the training device can also include: any one or more of the location information of the training device, the load of the training device.

[0142] Step 504, the inference device determines a first training device from the information of one or more training devices according to a preset condition.

[0143] The step 504 in the embodiments of the present application can also be implemented in the following way: the inference device selects any one of the information of one or more training devices as the first training device.

[0144] The method provided by the embodiments of the present application can determine device information. After the training device and the inference device are deployed separately, because the positions, loads and supported AI capabilities of different training devices are different, the information of one or more training devices can be registered at a service discovery entity. Therefore, the inference device can provide the algorithm type (Algorithm Type) or algorithm identifier (Algorithm ID) of a first model requested by the inference device to the service discovery entity, so that the inference device can obtain the information of the one or more training devices from the service discovery entity, and the inference device can correctly address the one or more training devices. Subsequently, an auxiliary inference device can select a suitable first training device for model training. The model training process can be smooth, the model training speed can be fast, and the model generalization capability can be as strong as possible. In addition, the separate deployment of the training device and the inference device can reduce the deployment cost.

[0145] As another possible embodiment, as shown in Figure 6 The method provided by the embodiments of the present application can further include the following steps before step 502:

[0146] Step 505: The first training device or the second training device sends a second request to the service discovery entity, so that the service discovery entity receives the second request from the first training device or the second training device.

[0147] The second request from the first training device is used to request registration or update of the information of the first training device at the service discovery entity, and the second request includes any one or more of the following information of the first training device: address information, position information, load, capability information, the first training device is any one of a training device set, or the first training device or the second training device is any one of the one or more training devices. The one or more training devices belong to the training devices in the training device set. The second request from the second training device is used to request registration or update of the information of the second training device at the service discovery entity.

[0148] Because any training device in the embodiments of the present application can register or update the information of the first training device at the service discovery entity through step 505, step 505 takes the registration or update of the information of the first training device at the service discovery entity by the first training device as an example. The information of any training device can be referred to as artificial intelligence (AI) information, and the registration or update process of the information of any training device at the service discovery entity can be referred to as an AI capability registration process.

[0149] The address information of any one of the training devices in the embodiments of the present application is used to determine the IP address of the training device. The location information of any one of the training devices is used to determine the location of the training device. For example, the area where the training device is located.

[0150] For example, the second request itself has a function of requesting registration or updating of the information of the first training device at the service discovery entity, or the second request has indication information for requesting registration or updating of the information of the first training device at the service discovery entity.

[0151] It can be understood that after each training device in the set of training devices registers or updates the information of the first training device at the service discovery entity, the information of each training device is stored at the service discovery entity.

[0152] In combination Figure 6 , the step 502 in the embodiments of the present application can be implemented in the following manner: the service discovery entity determines the information of the one or more training devices from the set of training devices according to the algorithm type or the algorithm identifier of the first model requested by the inference device.

[0153] As a possible implementation manner, the one or more training devices are training devices supporting the algorithm type required by the inference device, and / or the one or more training devices are training devices meeting a preset requirement in distance from the inference device. For example, the one or more training devices are training devices closest to the inference device.

[0154] As another possible implementation manner, the one or more training devices are training devices with a load lower than a preset load threshold.

[0155] As a possible implementation manner, the one or more training devices are training devices supporting the algorithm identifier required by the inference device.

[0156] For example, the service discovery entity determines, from the training device information stored in the service discovery entity, a set of training devices (including one or more training devices) meeting a preset requirement (for example, closest to the inference device) in distance from the inference device according to the location of the inference device. Then, the service discovery entity filters out training devices not supporting the algorithm type requirement from the set of training devices according to the algorithm type requirement of the inference device. In addition, the service discovery entity can further filter out training devices with a heavy load, and finally filter out one or more training devices meeting the requirements of the inference device.

[0157] In combination Figure 6 , as a possible implementation manner, the step 504 in the embodiments of the present application can be implemented in the following manner:

[0158] Step 5041, the reasoning device determines a training device, whose algorithm convergence time corresponding to the algorithm meets a preset time requirement, as the first training device from the one or more training devices.

[0159] For example, the preset time requirement can be that the algorithm convergence time is the fastest, i.e., the algorithm convergence time is the shortest, or the algorithm convergence time meets a preset algorithm convergence time threshold. The algorithm convergence time T1 corresponding to the training device 1, the algorithm convergence time T2 corresponding to the training device 2, and the algorithm convergence time T3 corresponding to the training device 3, where T1>T2>T3, the reasoning device can determine the first training device as the training device 3.

[0160] Step 5042, the reasoning device determines a training device, whose algorithm performance evaluation index corresponding to the algorithm meets an evaluation index requirement, as the first training device from the one or more training devices.

[0161] For example, the evaluation index requirement can be that the algorithm performance evaluation index is the highest, or the algorithm performance evaluation index meets a preset algorithm performance evaluation index threshold.

[0162] That is, as a possible implementation manner, the preset condition provided by the embodiment of the present application includes any one or more of the following: the algorithm convergence time of the algorithm corresponding to the algorithm of the first training device is the algorithm convergence time of any one of the one or more algorithms in the one or more training devices that meets the preset time requirement; or, the algorithm performance evaluation index of the one or more algorithms of the first training device is the algorithm performance evaluation index of the one or more algorithms in the one or more training devices that meets the evaluation index requirement.

[0163] For example, the algorithm convergence time of the algorithm corresponding to the algorithm of the first training device is the fastest among the algorithm convergence times of the one or more algorithms in the one or more training devices; or, the algorithm performance evaluation index of the one or more algorithms of the first training device is the highest among the algorithm performance evaluation indexes of the one or more algorithms in the one or more training devices.

[0164] Further, the preset condition provided by the embodiment of the present application can also include that the load of the first training device is the load of the one or more training devices that meets a load requirement. For example, the load requirement can be that the load is the lowest, or the load is lower than or equal to a preset load threshold.

[0165] For example, the load of the first training device is the lowest among the loads of the one or more training devices.

[0166] As another possible embodiment, as shown in Figure 6 The method provided by the embodiment of the present application further includes:

[0167] Step 506, the inference device sends a fourth request to the first training device, so that the first training device receives the fourth request from the inference device. The fourth request is used to request information of the first model, and the fourth request includes any one or more of the following information corresponding to the first model: algorithm type, algorithm identifier, algorithm performance requirement, data type (Event ID list), and data address.

[0168] For example, the fourth request carries second information used to request information of the first model. The second information includes any one or more of the following information corresponding to the first model: algorithm type, algorithm identifier, algorithm performance requirement, data type (Event ID list), and data address.

[0169] For example, the algorithm identifier carried in the fourth request can be linear regression or support vector machine, or logistic regression.

[0170] The algorithm performance requirement is, for example, that the mean square error is less than or equal to 0.001.

[0171] For example, the algorithm performance requirement is used to represent the algorithm performance required to be met by the first model.

[0172] For example, the data type can represent one or more data types. The data type is used by the first training device to determine the data type required to be collected when training the first model. The data address is used to determine the address of the data required to be collected when training the first model. For example, the data address can be the Address / IP / ID of a network function (NF) capable of providing the data.

[0173] Step 507, the first training device determines the information of the first model according to the fourth request, and the information of the first model includes any one or more of the following information: model identifier, model input, and model parameter.

[0174] As a possible implementation manner, step 506 in the embodiment of the present application can be implemented in the following manner: the first training device collects training data according to the data type and the data address. The first training device performs model training on the data according to the algorithm determined according to the algorithm identifier, to obtain the information of the first model, and the performance indicator of the first model meets the algorithm performance requirement.

[0175] Taking a voice service mean opinion score (MOS) model as an example, a simple linear regression model (identified by a Model ID) corresponds to a linear regression algorithm (identified by an Algorithm ID) as follows: h(x) = w0x0 + w1x1 + w2x2 + w3x3 + w4x4 + w5x5... + w D xD Specifically, h(x) represents the label data, which is the model output (Model Output list). Specifically, it can be the speech MOS score; x i = (i = 0, 1, 2,..., D) is the training data, that is, the model input data (Model Input list), including QoS flow bit rate, QoS flow packet delay, QoS flow packet error rate, radio signal received power (RSRP) or radio signal received quality (RSRQ), power headroom, received signal strength indicator (RSSI), signal to interference plus noise ratio (SINR), etc.w i = (i = 0, 1, 2,..., D) is the weight, that is, the model parameter (Model Parameter list).

[0176] In summary, a model can be characterized by Table 3 as follows:

[0177] Table 3

[0178]

[0179] Among them, the model parameter list, weight, Pre-Process Function ID in Table 3 correspond to w i = (i = 0, 1, 2,..., D). The model output list, model output, Pre-Process Function ID in Table 3 correspond to h(x). The model input list, Pre-Process Function ID, Event ID in Table 3 correspond to x i = (i = 0, 1, 2,..., D).

[0180] As shown in Table 4, Table 4 shows the model characterization listed by the embodiments of the present application:

[0181] Table 4

[0182]

[0183]

[0184]

[0185] As shown in Table 5, Table 5 shows the pre-processing method listed by the embodiments of the present application.

[0186] Table 5 Pre-processing method

[0187]

[0188] Step 508, the first training device sends the information of the first model to the inference device, so that the inference device receives the information of the first model from the first training device.

[0189] For example, the information of the first model further includes any one or more of the following information: model output, model additional information, and result of model evaluation index.

[0190] The result of the model evaluation index is the optimal value of the model evaluation index. For example, 0.0003. For example, the model additional information is, for a neural network, the number of hidden layers, and which activation function is used for each layer.

[0191] It should be understood that after step 507, the inference device can deploy the first model according to the information of the first model.

[0192] In combination Figure 6 As a possible embodiment, the method provided by the embodiments of the present application can further include, after step 508:

[0193] Step 509, the inference device sends a third request to the service discovery entity, so that the service discovery entity receives the third request from the inference device. The third request is used to register or update the information of the first model, and the third request includes any one or more of the following information: Analytics ID corresponding to the analysis result of the first model, and effective area or service area or coverage area of the analysis result corresponding to the first model.

[0194] In a possible embodiment, the third request can further include address information or location information or identifier of the inference device. In a possible embodiment, the third request carries a registration indication or an update indication. The registration indication is used to indicate the registration of the information of the first model. The update indication is used to indicate the update of the information of the first model.

[0195] Subsequently, the network element that needs the data analysis results corresponding to the Analytics ID queries the service discovery entity for the address of the inference device based on the Analytics ID. Then, the network element requests the data analysis results from the inference device based on the Analytics ID. The inference device further subscribes to online inference data from the network element that provides data to generate the data analysis results. Based on the model and the acquired online inference data, the inference device determines the data analysis results and sends the data analysis results to the consumer network element.

[0196] The above mainly describes the solutions of the embodiments of this application from the perspective of interaction between various network elements. It is understood that each network element, such as the first training device, inference device, service discovery entity, etc., includes corresponding hardware structures and / or software modules to execute the above functions in order to achieve the aforementioned functions. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art 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.

[0197] This application embodiment can divide functional units according to the first training device, inference device, and service discovery entity in the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0198] The above combination Figures 1 to 6 The methods described in the embodiments of this application have been explained. The apparatus for determining device information by performing the above-described methods, provided in the embodiments of this application, is described below. Those skilled in the art will understand that the methods and apparatus can be combined with and referenced in relation to each other. The apparatus for determining device information provided in the embodiments of this application can perform the steps executed by the inference device, service discovery entity, or first training device in the method for determining the device where the model resides.

[0199] When using integrated units, Figure 7 An apparatus for determining device information as described in the above embodiments is shown. The apparatus for determining device information may include a processing unit 101 and a communication unit 102.

[0200] In one example, the apparatus for determining device information is an inference device, or a chip applied in the inference device. In this case, the processing unit 101 is configured to support the apparatus for determining device information to perform the step 504 in the above embodiment performed by the inference device. The communication unit 102 is configured to support the apparatus for determining device information to perform the sending action in the step 501 in the above embodiment performed by the inference device. The communication unit 102 is configured to support the apparatus for determining device information to perform the receiving action in the step 503 in the above embodiment performed by the service discovery entity.

[0201] In one possible embodiment, the processing unit 101 is specifically configured to support the apparatus for determining device information to perform the step 5041, the step 5042 in the above embodiment. The communication unit 102 is further configured to support the apparatus for determining device information to perform the sending action in the step 506, the step 509 in the above embodiment performed by the inference device.

[0202] In one possible embodiment, the communication unit 102 is further configured to support the apparatus for determining device information to perform the receiving action in the step 508 in the above embodiment performed by the inference device.

[0203] In another example, the apparatus for determining device information is a service discovery entity, or a chip applied in the service discovery entity. In this case, the processing unit 101 is configured to support the apparatus for determining device information to perform the step 502 in the above embodiment performed by the service discovery entity. The communication unit 102 is configured to support the apparatus for determining device information to perform the receiving action in the step 501 in the above embodiment performed by the service discovery entity. The communication unit 102 is configured to support the apparatus for determining device information to perform the sending action in the step 503 in the above embodiment performed by the service discovery entity.

[0204] In one possible embodiment, the communication unit 102 is configured to support the apparatus for determining device information to perform the receiving action in the step 505 in the above embodiment performed by the service discovery entity.

[0205] In another example, the apparatus for determining device information is a first training device, or a chip applied in the first training device. In this case, the communication unit 102 is configured to support the apparatus for determining device information to perform the receiving action in the step 506, the sending action in the step 508 in the above embodiment performed by the first training device. The processing unit 101 is configured to support the apparatus for determining device information to perform the step 507 in the above embodiment.

[0206] In a possible implementation, the communication unit 102 is configured to support the apparatus for determining device information to perform the sending action performed by the first training device in step 505 of the above-mentioned embodiments. The communication unit 102 is configured to support the apparatus for determining device information to perform the receiving action performed by the first training device in step 506 of the above-mentioned embodiments.

[0207] In the case of an integrated unit, Figure 8 A possible logical structure of the apparatus for determining device information involved in the above-mentioned embodiments is shown. The apparatus for determining device information includes a processing module 112 and a communication module 113. The processing module 112 is configured to control and manage the actions of the apparatus for determining device information, for example, the processing module 112 is configured to perform the steps of information / data processing performed by the apparatus for determining device information. The communication module 113 is configured to support the apparatus for determining device information to perform the steps of information / data sending or receiving.

[0208] In a possible implementation, the apparatus for determining device information can further include a storage module 111 configured to store the program codes and data available to the apparatus for determining device information.

[0209] In an example, the apparatus for determining device information is an inference device, or a chip applied to an inference device. In this case, the processing module 112 is configured to support the apparatus for determining device information to perform step 504 in the above-mentioned embodiments performed by the inference device. The communication module 113 is configured to support the apparatus for determining device information to perform the sending action performed by the inference device in step 501 of the above-mentioned embodiments. The communication module 113 is configured to support the apparatus for determining device information to perform the receiving action performed by the service discovery entity in step 503 of the above-mentioned embodiments.

[0210] In a possible implementation, the processing module 112 is specifically configured to support the apparatus for determining device information to perform steps 5041 and 5042 in the above-mentioned embodiments. The communication module 113 is further configured to support the apparatus for determining device information to perform the sending action performed by the inference device in steps 506 and 509 of the above-mentioned embodiments.

[0211] In a possible implementation, the communication module 113 is further configured to support the apparatus for determining device information to perform the receiving action performed by the inference device in step 508 of the above-mentioned embodiments.

[0212] In another example, the apparatus for determining device information is a service discovery entity, or a chip applied in the service discovery entity. In this case, the processing module 112 is configured to support the apparatus for determining device information to perform the step 502 performed by the service discovery entity in the above embodiments. The communication module 113 is configured to support the apparatus for determining device information to perform the receiving action performed by the service discovery entity in the step 501 of the above embodiments. The communication module 113 is configured to support the apparatus for determining device information to perform the sending action performed by the service discovery entity in the step 503 of the above embodiments.

[0213] In a possible embodiment, the communication module 113 is configured to support the apparatus for determining device information to perform the receiving action performed by the service discovery entity in the step 505 of the above embodiments.

[0214] In another example, the apparatus for determining device information is a first training device, or a chip applied in the first training device. In this case, the communication module 113 is configured to support the apparatus for determining device information to perform the receiving action performed by the first training device in the step 506 and the sending action performed by the first training device in the step 508 of the above embodiments. The processing module 112 is configured to support the apparatus for determining device information to perform the step 507 of the above embodiments.

[0215] In a possible embodiment, the communication module 113 is configured to support the apparatus for determining device information to perform the sending action performed by the first training device in the step 505 of the above embodiments. The communication module 113 is configured to support the apparatus for determining device information to perform the receiving action performed by the first training device in the step 506 of the above embodiments.

[0216] The processing module 112 can be a processor or a controller, for example, can be a central processing unit, a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array, or other programmable logic device, transistor logic, hardware component, or any combination thereof. It can implement or execute various example logical blocks, modules and circuits described in connection with the disclosure. The processor can also be a combination of implementing computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and the like. The communication module 113 can be a transceiver, a transceiver circuit or a communication interface, etc. The storage module 111 can be a memory.

[0217] When the processing module 112 is the processor 41 or the processor 45, the communication module 113 is the communication interface 43, and the storage module 111 is the memory 42, the apparatus for determining device information involved in the disclosure can be a communication device as shown in the figure. Figure 4 ​

[0218] In one example, the apparatus for determining device information is an inference device, or a chip applied in the inference device. In this case, the processor 41 or the processor 45 is configured to support the apparatus for determining device information to perform the step 504 in the above embodiment performed by the inference device. The communication interface 43 is configured to support the apparatus for determining device information to perform the sending action in the step 501 of the above embodiment performed by the inference device. The communication interface 43 is configured to support the apparatus for determining device information to perform the receiving action in the step 503 of the above embodiment performed by the service discovery entity.

[0219] In one possible embodiment, the processor 41 or the processor 45 is specifically configured to support the apparatus for determining device information to perform the step 5041, the step 5042 in the above embodiment. The communication interface 43 is further configured to support the apparatus for determining device information to perform the sending action in the step 506, the step 509 of the above embodiment performed by the inference device.

[0220] In one possible embodiment, the communication interface 43 is further configured to support the apparatus for determining device information to perform the receiving action in the step 508 of the above embodiment performed by the inference device.

[0221] In another example, the apparatus for determining device information is a service discovery entity, or a chip applied in the service discovery entity. In this case, the processor 41 or the processor 45 is configured to support the apparatus for determining device information to perform the step 502 in the above embodiment performed by the service discovery entity. The communication interface 43 is configured to support the apparatus for determining device information to perform the receiving action in the step 501 of the above embodiment performed by the service discovery entity. The communication interface 43 is configured to support the apparatus for determining device information to perform the sending action in the step 503 of the above embodiment performed by the service discovery entity.

[0222] In one possible embodiment, the communication interface 43 is configured to support the apparatus for determining device information to perform the receiving action in the step 505 of the above embodiment performed by the service discovery entity.

[0223] In another example, the apparatus for determining device information is a first training device, or a chip applied in the first training device. In this case, the communication interface 43 is configured to support the apparatus for determining device information to perform the receiving action in the step 506, the sending action in the step 508 of the above embodiment performed by the first training device. The processor 41 or the processor 45 is configured to support the apparatus for determining device information to perform the step 507 of the above embodiment.

[0224] In a possible implementation, the communication interface 43 is configured to support the determining device information apparatus to perform the sending action performed by the first training device in step 505 of the method in the above embodiments.

[0225] Figure 9 FIG. 1 is a schematic structural diagram of a chip 150 according to an embodiment of the present application. The chip 150 includes one or more (including two) processors 1510 and a communication interface 1530.

[0226] Optionally, the chip 150 further includes a memory 1540, which can include a read-only memory and a random access memory, and provides the processor 1510 with operation instructions and data. Part of the memory 1540 can further include a non-volatile random access memory (NVRAM).

[0227] In some embodiments, the memory 1540 stores the following elements, execution modules or data structures, or a subset thereof, or an extended set thereof.

[0228] In the embodiments of the present application, corresponding operations are performed by invoking operation instructions stored in the memory 1540 (which can be stored in an operating system).

[0229] In a possible implementation, the chip used by the first training device, the inference device and the service discovery entity is similar in structure, and different devices can use different chips to implement respective functions.

[0230] The processor 1510 controls the processing operation of any one of the first training device, the inference device and the service discovery entity, and the processor 1510 can also be referred to as a central processing unit (CPU).

[0231] The memory 1540 can include a read-only memory and a random access memory, and provide the processor 1510 with instructions and data. Part of the memory 1540 can further include an NVRAM. For example, the memory 1540, the communication interface 1530 and the memory 1540 are coupled together through a bus system 1520, which can include a data bus, a power supply bus, a control bus and a state signal bus, etc. However, for the purpose of clear illustration, all kinds of buses are marked as the bus system 1520 in Figure 9 .

[0232] The method disclosed in the embodiments of the present application can be applied to the processor 1510 or implemented by the processor 1510. The processor 1510 can be an integrated circuit chip having a signal processing capability. In the implementation process, the steps of the method can be completed by an integrated logic circuit or an instruction in the form of software in the processor 1510. The processor 1510 described above can be a general processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor or the like. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory 1540, and the processor 1510 reads the information in the memory 1540 and combines the hardware to complete the steps of the method.

[0233] In a possible implementation, the communication interface 1530 is configured to perform the receiving and sending steps of the first training device, the inference device and the service discovery entity in the embodiments shown in the method. Figures 5-6 The processor 1510 is configured to perform the processing steps of the first training device, the inference device and the service discovery entity in the embodiments shown in the method. Figures 5-6 The processor 1510 is configured to perform the processing steps of the first training device, the inference device and the service discovery entity in the embodiments shown in the method.

[0234] The above communication unit can be a communication interface of the device, configured to receive signals from other devices. For example, when the device is implemented in the form of a chip, the communication unit is a communication interface of the chip for receiving or sending signals from or to other chips or devices.

[0235] In addition, the embodiments of the present application can provide a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed, the functions of the service discovery entity in the method are implemented. Figures 5-6 In addition, the embodiments of the present application can provide a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed, the functions of the service discovery entity in the method are implemented.

[0236] The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed, the functions of the inference device in the method are implemented. Figures 5-6 The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed, the functions of the inference device in the method are implemented.

[0237] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores instructions, and when the instructions are executed, the functions of the first training device are realized. Figures 5-6

[0238] The embodiment of the present application provides a computer program product comprising instructions, and when the instructions are executed, the functions of the service discovery entity are realized. Figures 5-6

[0239] The embodiment of the present application provides a computer program product comprising instructions, and when the instructions are executed, the functions of the inference device are realized. Figures 5-6

[0240] The embodiment of the present application provides a computer program product comprising instructions, and when the instructions are executed, the functions of the first training device are realized. Figures 5-6

[0241] The embodiment of the present application provides a chip, which is applied to the first training device, and the chip comprises at least one processor and a communication interface, the communication interface is coupled with the at least one processor, and the processor is used for executing instructions to realize the functions of the first training device. Figures 5-6

[0242] The embodiment of the present application provides a chip, which is applied to the inference device, and the chip comprises at least one processor and a communication interface, the communication interface is coupled with the at least one processor, and the processor is used for executing instructions to realize the functions of the inference device. Figures 5-6

[0243] The embodiment of the present application provides a chip, which is applied to the first terminal, and the chip comprises at least one processor and a communication interface, the communication interface is coupled with the at least one processor, and the processor is used for executing instructions to realize the functions of the service discovery entity. Figure 5 Figure 6 The embodiment of the present application provides a communication system, which comprises an inference device and a service discovery entity.

[0244] The embodiment of the present application provides a communication system, which comprises an inference device and a service discovery entity. Figures 5 to 7 Figures 5 to 6 In an optional implementation manner, the communication system can further comprise: the first training device is used for executing the steps executed by the first training device.

[0245] In an optional implementation manner, the communication system can further comprise: the first training device is used for executing the steps executed by the first training device. Figures 5 to 6

[0246] ​​​​​​​​​In the above embodiments, all or part can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part can be implemented in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded on a computer and executed, all or part of the processes or functions described in the embodiments of the present application are performed. The computer can be a general purpose computer, a special purpose computer, a computer network, a network device, a user equipment or other programmable apparatus. The computer programs or instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer programs or instructions can be transferred from one website site, computer, server or data center to another website site, computer, server or data center through wired or wireless manner. The computer readable storage medium can be any available medium that can be accessed by a computer or data storage device such as a server, data center and the like integrated with one or more available media. The available media can be magnetic media, such as floppy disk, hard disk, magnetic tape; optical media, such as digital video disc (digital video disc, DVD); semiconductor media, such as solid state drive (solid state drive, SSD).

[0247] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and the indefinite articles "a" or "an" do not exclude a plurality. A single processor or other unit can fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0248] Although the present application is described herein in conjunction with specific features and embodiments thereof, it is understood that modifications and combinations can occur to those skilled in the art to which the present application pertains, within its spirit and scope. Accordingly, the description and drawings are to be regarded as illustrative in nature and are not to be taken as limiting the scope of the application as defined in the appended claims. Obviously, various modifications and changes are possible in the present application without departing from the spirit and scope of the application. Accordingly, it is intended that all such modifications and changes be included within this application as long as they fall within the scope of the claims and their equivalents.

Claims

1. A method for determining device information, characterized in that, include: The inference device sends a first request to the service discovery entity. The first request is used to request information about one or more training devices. The first request includes the algorithm type or algorithm identifier of the first model requested by the inference device. The inference device and the training devices are deployed in different locations. The inference device receives information from one or more training devices of the service discovery entity, the information of the training devices including: capability information; the one or more training devices satisfying the algorithm requirements of the inference device; wherein, the capability information includes any one or more of the following: algorithm type, algorithm identifier, algorithm performance evaluation index, algorithm convergence time, algorithm convergence speed, and algorithm confidence. The inference device determines the first training device from the information of the one or more training devices according to preset conditions.

2. The method according to claim 1, characterized in that, The preset conditions include any one or more of the following: The convergence time of the algorithm corresponding to the first training device is the fastest among the convergence times of the algorithms corresponding to any one of the one or more training devices; or, The algorithm performance evaluation index corresponding to the algorithm of the first training device is the highest among all the algorithm performance evaluation indices corresponding to the algorithms of any training device.

3. The method according to claim 2, characterized in that, The information of the training device also includes any one of the following: location information, load information, and the preset conditions also include: The load of the first training device is the lowest among the one or more training devices.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: The inference device sends a fourth request to the first training device. The fourth request is used to request information about the first model. The fourth request includes any one or more of the following information corresponding to the first model: algorithm type, algorithm identifier, algorithm performance requirements, data type, and data address. The inference device receives information from the first model from the first training device. The information of the first model includes one or more of the following: model identifier, model input, and model parameters.

5. The method according to claim 4, characterized in that, The information of the first model also includes one or more of the following: model output, model additional information, and the results of model evaluation metrics.

6. The method according to any one of claims 1-3, characterized in that, The inference device sends a third request to the service discovery entity, the third request being used to register or update information of the first model, the third request including any one or more of the following information: The first model corresponds to the Analytics ID, which represents the effective region, service region, or coverage region of the analysis result.

7. A method for determining equipment information, characterized in that, include: The service discovery entity receives a first request from an inference device, the first request being used to request information from one or more training devices, the first request including the algorithm type or algorithm identifier of a first model requested by the inference device; wherein the inference device and the training device are deployed in different locations; The service discovery entity determines the information of the one or more training devices based on the algorithm type or algorithm identifier of the first model requested by the inference device. The information of the training devices includes: capability information; the one or more training devices meet the algorithm requirements of the inference device; wherein, the capability information includes any one or more of the following: algorithm type, algorithm identifier, algorithm performance evaluation index, algorithm convergence time, algorithm convergence speed, and algorithm confidence. The service discovery entity sends information about the one or more training devices to the inference device.

8. The method according to claim 7, characterized in that, The one or more training devices are training devices that support the algorithm types required by the inference device, and / or, The one or more training devices are training devices whose distance from the inference device meets a preset requirement.

9. The method according to claim 8, characterized in that, The load on one or more training devices is lower than a preset load threshold.

10. The method according to any one of claims 7-9, characterized in that, The method further includes: The service discovery entity receives a second request from the second training device. The second request is for requesting to register or update the information of the second training device with the service discovery entity. The second request includes one or more of the following information of the second training device: address information, location information, load, and capability information. The second training device is any one of the one or more training devices.

11. The method according to any one of claims 7-9, characterized in that, The method further includes: The service discovery entity receives a third request from the inference device, the third request being used to register or update information of the first model, the third request including any one or more of the following information: The first model corresponds to the Analytics ID, which represents the effective region, service region, or coverage region of the analysis result.

12. A device for determining equipment information, characterized in that, include: A communication unit is configured to send a first request to a service discovery entity, the first request being for requesting information about one or more training devices, the first request including the algorithm type or algorithm identifier of a first model requested by the inference device; wherein the device for determining device information is deployed at a different location from the training device; The communication unit is further configured to receive information from the service discovery entity regarding the one or more training devices, the information of which includes: capability information; the one or more training devices meeting the algorithm requirements of the inference device; wherein the capability information includes any one or more of the following: algorithm type, algorithm identifier, algorithm performance evaluation index, algorithm convergence time, algorithm convergence speed, and algorithm confidence. The processing unit is configured to determine the first training device from the information of the one or more training devices according to preset conditions.

13. The apparatus according to claim 12, characterized in that, The preset conditions include any one or more of the following: The convergence time of the algorithm corresponding to the first training device is the fastest among the convergence times of the algorithms corresponding to any one of the one or more training devices; or, The algorithm performance evaluation index corresponding to the algorithm of the first training device is the highest among all the algorithm performance evaluation indices corresponding to the algorithms of any training device.

14. The apparatus according to claim 13, characterized in that, The information of the training device also includes any one of the following: location information, load information, and the preset conditions also include: The load of the first training device is the lowest among the one or more training devices.

15. The apparatus according to any one of claims 12-14, characterized in that, The communication unit is further configured to send a fourth request to the first training device. The fourth request is used to request information about the first model. The fourth request includes any one or more of the following information corresponding to the first model: algorithm type, algorithm identifier, algorithm performance requirements, data type, and data address. The communication unit is further configured to receive information from the first model from the first training device, wherein the information of the first model includes any one or more of the following: model identifier, model input, and model parameters.

16. The apparatus according to claim 15, characterized in that, The information of the first model also includes one or more of the following: model output, model additional information, and the results of model evaluation metrics.

17. The apparatus according to any one of claims 12-14, characterized in that, The communication unit is further configured to send a third request to the service discovery entity, the third request being used to register or update information of the first model, the third request including any one or more of the following information: The first model corresponds to the Analytics ID, which represents the effective region, service region, or coverage region of the analysis result.

18. An apparatus for determining device information, characterized in that, include: A communication unit is configured to receive a first request from an inference device, the first request being for requesting information from one or more training devices, the first request including the algorithm type or algorithm identifier of a first model requested by the inference device; wherein the device for determining device information is deployed at a different location from the training device; The processing unit is configured to determine information about one or more training devices based on the algorithm type of the first model requested by the inference device. The information about the training devices includes: capability information; the one or more training devices satisfy the algorithm requirements of the inference device; wherein the capability information includes any one or more of the following: algorithm type, algorithm identifier, algorithm performance evaluation index, algorithm convergence time, algorithm convergence speed, and algorithm confidence. The communication unit is used to send information about the one or more training devices to the inference device.

19. The apparatus according to claim 18, characterized in that, The one or more training devices are training devices that support the algorithm types required by the inference device, and / or, The one or more training devices are training devices whose distance from the inference device meets a preset requirement.

20. The apparatus according to claim 19, characterized in that, The load on one or more training devices is lower than a preset load threshold.

21. The apparatus according to any one of claims 18-20, characterized in that, The communication unit is further configured to receive a second request from the second training device. The second request is for requesting to register or update the information of the second training device at the service discovery entity. The second request includes one or more of the following information of the second training device: address information, location information, load, and capability information. The second training device is any one of the one or more training devices.

22. The apparatus according to any one of claims 18-20, characterized in that, The communication unit is further configured to receive a third request from the inference device, the third request being used to register or update information of the first model, the third request including any one or more of the following information: The first model corresponds to the Analytics ID, which represents the effective region, service region, or coverage region of the analysis result.

23. A communication system, characterized in that, Includes: the apparatus as described in any one of claims 12-17, or the apparatus as described in any one of claims 18-22.

24. A readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed, implement the method as described in any one of claims 1-6, or the method as described in any one of claims 7-11.

25. A chip, characterized in that, The chip includes a processor and a communication interface coupled to the processor. The processor is used to run computer programs or instructions to implement the method as described in any one of claims 1-6, or the method as described in any one of claims 7-11.

26. A communication device, characterized in that, include: A processor coupled to a memory, the processor being configured to execute a computer program or instructions stored in the memory to implement the method as claimed in any one of claims 1-6, or the method as claimed in any one of claims 7-11.

Images